korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-24 12:44:11 +08:00
Code Issues Packages Projects Releases Wiki Activity
64693ec777
linux/kernel/bpf/devmap.c

1145 lines
29 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 295 Based on 1 normalized pattern(s): 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 extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 64 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Alexios Zavras <alexios.zavras@intel.com> Reviewed-by: Allison Randal <allison@lohutok.net> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190529141901.894819585@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-29 22:18:09 +08:00
// SPDX-License-Identifier: GPL-2.0-only
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io
*/
/* 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
devmap/cpumap: Use flush list instead of bitmap The socket map uses a linked list instead of a bitmap to keep track of which entries to flush. Do the same for devmap and cpumap, as this means we don't have to care about the map index when enqueueing things into the map (and so we can cache the map lookup). Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-28 17:12:34 +08:00
* a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until
* this list is empty, indicating outstanding flush operations have completed.
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
*
* 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.
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
*
* 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.
bpf: devmap fix mutex in rcu critical section Originally we used a mutex to protect concurrent devmap update and delete operations from racing with netdev unregister notifier callbacks. The notifier hook is needed because we increment the netdev ref count when a dev is added to the devmap. This ensures the netdev reference is valid in the datapath. However, we don't want to block unregister events, hence the initial mutex and notifier handler. The concern was in the notifier hook we search the map for dev entries that hold a refcnt on the net device being torn down. But, in order to do this we require two steps, (i) dereference the netdev: dev = rcu_dereference(map[i]) (ii) test ifindex: dev->ifindex == removing_ifindex and then finally we can swap in the NULL dev in the map via an xchg operation, xchg(map[i], NULL) The danger here is a concurrent update could run a different xchg op concurrently leading us to replace the new dev with a NULL dev incorrectly. CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) xchg(map[i], NULL) The above flow would create the incorrect state with the dev reference in the update path being lost. To resolve this the original code used a mutex around the above block. However, updates, deletes, and lookups occur inside rcu critical sections so we can't use a mutex in this context safely. Fortunately, by writing slightly better code we can avoid the mutex altogether. If CPU 1 in the above example uses a cmpxchg and _only_ replaces the dev reference in the map when it is in fact the expected dev the race is removed completely. The two cases being illustrated here, first the race condition, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) odev = cmpxchg(map[i], dev, NULL) Now we can test the cmpxchg return value, detect odev != dev and abort. Or in the good case, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) odev = cmpxchg(map[i], dev, NULL) [...] Now 'odev == dev' and we can do proper cleanup. And viola the original race we tried to solve with a mutex is corrected and the trace noted by Sasha below is resolved due to removal of the mutex. Note: When walking the devmap and removing dev references as needed we depend on the core to fail any calls to dev_get_by_index() using the ifindex of the device being removed. This way we do not race with the user while searching the devmap. Additionally, the mutex was also protecting list add/del/read on the list of maps in-use. This patch converts this to an RCU list and spinlock implementation. This protects the list from concurrent alloc/free operations. The notifier hook walks this list so it uses RCU read semantics. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747 in_atomic(): 1, irqs_disabled(): 0, pid: 16315, name: syz-executor1 1 lock held by syz-executor1/16315: #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] map_delete_elem kernel/bpf/syscall.c:577 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SYSC_bpf kernel/bpf/syscall.c:1427 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SyS_bpf+0x1d32/0x4ba0 kernel/bpf/syscall.c:1388 Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Reported-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-05 13:02:19 +08:00
* 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.
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
*
* The devmap_hash type is a map type which interprets keys as ifindexes and
* indexes these using a hashmap. This allows maps that use ifindex as key to be
* densely packed instead of having holes in the lookup array for unused
* ifindexes. The setup and packet enqueue/send code is shared between the two
* types of devmap; only the lookup and insertion is different.
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
*/
#include <linux/bpf.h>
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
#include <net/xdp.h>
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
#include <linux/filter.h>
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
#include <trace/events/xdp.h>
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
bpf: Add file mode configuration into bpf maps Introduce the map read/write flags to the eBPF syscalls that returns the map fd. The flags is used to set up the file mode when construct a new file descriptor for bpf maps. To not break the backward capability, the f_flags is set to O_RDWR if the flag passed by syscall is 0. Otherwise it should be O_RDONLY or O_WRONLY. When the userspace want to modify or read the map content, it will check the file mode to see if it is allowed to make the change. Signed-off-by: Chenbo Feng <fengc@google.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-19 04:00:22 +08:00
#define DEV_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
struct xdp_dev_bulk_queue {
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
struct xdp_frame *q[DEV_MAP_BULK_SIZE];
devmap/cpumap: Use flush list instead of bitmap The socket map uses a linked list instead of a bitmap to keep track of which entries to flush. Do the same for devmap and cpumap, as this means we don't have to care about the map index when enqueueing things into the map (and so we can cache the map lookup). Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-28 17:12:34 +08:00
struct list_head flush_node;
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
struct net_device *dev;
xdp: add tracepoint for devmap like cpumap have Notice how this allow us get XDP statistic without affecting the XDP performance, as tracepoint is no-longer activated on a per packet basis. V5: Spotted by John Fastabend. Fix 'sent' also counted 'drops' in this patch, a later patch corrected this, but it was a mistake in this intermediate step. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:57 +08:00
struct net_device *dev_rx;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
struct bpf_prog *xdp_prog;
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
unsigned int count;
};
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
struct bpf_dtab_netdev {
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
struct net_device *dev; /* must be first member, due to tracepoint */
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
struct hlist_node index_hlist;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
struct bpf_dtab *dtab;
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
struct bpf_prog *xdp_prog;
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
struct rcu_head rcu;
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
unsigned int idx;
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
struct bpf_devmap_val val;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
};
struct bpf_dtab {
struct bpf_map map;
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
struct list_head list;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
/* these are only used for DEVMAP_HASH type maps */
struct hlist_head *dev_index_head;
spinlock_t index_lock;
unsigned int items;
u32 n_buckets;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
};
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
static DEFINE_PER_CPU(struct list_head, dev_flush_list);
bpf: devmap fix mutex in rcu critical section Originally we used a mutex to protect concurrent devmap update and delete operations from racing with netdev unregister notifier callbacks. The notifier hook is needed because we increment the netdev ref count when a dev is added to the devmap. This ensures the netdev reference is valid in the datapath. However, we don't want to block unregister events, hence the initial mutex and notifier handler. The concern was in the notifier hook we search the map for dev entries that hold a refcnt on the net device being torn down. But, in order to do this we require two steps, (i) dereference the netdev: dev = rcu_dereference(map[i]) (ii) test ifindex: dev->ifindex == removing_ifindex and then finally we can swap in the NULL dev in the map via an xchg operation, xchg(map[i], NULL) The danger here is a concurrent update could run a different xchg op concurrently leading us to replace the new dev with a NULL dev incorrectly. CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) xchg(map[i], NULL) The above flow would create the incorrect state with the dev reference in the update path being lost. To resolve this the original code used a mutex around the above block. However, updates, deletes, and lookups occur inside rcu critical sections so we can't use a mutex in this context safely. Fortunately, by writing slightly better code we can avoid the mutex altogether. If CPU 1 in the above example uses a cmpxchg and _only_ replaces the dev reference in the map when it is in fact the expected dev the race is removed completely. The two cases being illustrated here, first the race condition, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) odev = cmpxchg(map[i], dev, NULL) Now we can test the cmpxchg return value, detect odev != dev and abort. Or in the good case, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) odev = cmpxchg(map[i], dev, NULL) [...] Now 'odev == dev' and we can do proper cleanup. And viola the original race we tried to solve with a mutex is corrected and the trace noted by Sasha below is resolved due to removal of the mutex. Note: When walking the devmap and removing dev references as needed we depend on the core to fail any calls to dev_get_by_index() using the ifindex of the device being removed. This way we do not race with the user while searching the devmap. Additionally, the mutex was also protecting list add/del/read on the list of maps in-use. This patch converts this to an RCU list and spinlock implementation. This protects the list from concurrent alloc/free operations. The notifier hook walks this list so it uses RCU read semantics. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747 in_atomic(): 1, irqs_disabled(): 0, pid: 16315, name: syz-executor1 1 lock held by syz-executor1/16315: #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] map_delete_elem kernel/bpf/syscall.c:577 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SYSC_bpf kernel/bpf/syscall.c:1427 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SyS_bpf+0x1d32/0x4ba0 kernel/bpf/syscall.c:1388 Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Reported-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-05 13:02:19 +08:00
static DEFINE_SPINLOCK(dev_map_lock);
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
static LIST_HEAD(dev_map_list);
devmap: Use bpf_map_area_alloc() for allocating hash buckets Syzkaller discovered that creating a hash of type devmap_hash with a large number of entries can hit the memory allocator limit for allocating contiguous memory regions. There's really no reason to use kmalloc_array() directly in the devmap code, so just switch it to the existing bpf_map_area_alloc() function that is used elsewhere. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200616142829.114173-1-toke@redhat.com
2020-06-16 22:28:29 +08:00
static struct hlist_head *dev_map_create_hash(unsigned int entries,
int numa_node)
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
{
int i;
struct hlist_head *hash;
bpf: Fix integer overflow in argument calculation for bpf_map_area_alloc In 32-bit architecture, the result of sizeof() is a 32-bit integer so the expression becomes the multiplication between 2 32-bit integer which can potentially leads to integer overflow. As a result, bpf_map_area_alloc() allocates less memory than needed. Fix this by casting 1 operand to u64. Fixes: 0d2c4f964050 ("bpf: Eliminate rlimit-based memory accounting for sockmap and sockhash maps") Fixes: 99c51064fb06 ("devmap: Use bpf_map_area_alloc() for allocating hash buckets") Fixes: 546ac1ffb70d ("bpf: add devmap, a map for storing net device references") Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210613143440.71975-1-minhquangbui99@gmail.com
2021-06-13 22:34:39 +08:00
hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node);
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
if (hash != NULL)
for (i = 0; i < entries; i++)
INIT_HLIST_HEAD(&hash[i]);
return hash;
}
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab,
int idx)
{
return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)];
}
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
{
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
u32 valsize = attr->value_size;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
/* check sanity of attributes. 2 value sizes supported:
* 4 bytes: ifindex
* 8 bytes: ifindex + prog fd
*/
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
if (attr->max_entries == 0 || attr->key_size != 4 ||
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
(valsize != offsetofend(struct bpf_devmap_val, ifindex) &&
valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) ||
attr->map_flags & ~DEV_CREATE_FLAG_MASK)
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
return -EINVAL;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
devmap: Allow map lookups from eBPF We don't currently allow lookups into a devmap from eBPF, because the map lookup returns a pointer directly to the dev->ifindex, which shouldn't be modifiable from eBPF. However, being able to do lookups in devmaps is useful to know (e.g.) whether forwarding to a specific interface is enabled. Currently, programs work around this by keeping a shadow map of another type which indicates whether a map index is valid. Since we now have a flag to make maps read-only from the eBPF side, we can simply lift the lookup restriction if we make sure this flag is always set. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-28 17:12:35 +08:00
/* Lookup returns a pointer straight to dev->ifindex, so make sure the
* verifier prevents writes from the BPF side
*/
attr->map_flags |= BPF_F_RDONLY_PROG;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
bpf: add helper for copying attrs to struct bpf_map All map types reimplement the field-by-field copy of union bpf_attr members into struct bpf_map. Add a helper to perform this operation. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-01-12 12:29:06 +08:00
bpf_map_init_from_attr(&dtab->map, attr);
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries);
if (!dtab->n_buckets) /* Overflow check */
return -EINVAL;
}
if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
devmap: Use bpf_map_area_alloc() for allocating hash buckets Syzkaller discovered that creating a hash of type devmap_hash with a large number of entries can hit the memory allocator limit for allocating contiguous memory regions. There's really no reason to use kmalloc_array() directly in the devmap code, so just switch it to the existing bpf_map_area_alloc() function that is used elsewhere. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200616142829.114173-1-toke@redhat.com
2020-06-16 22:28:29 +08:00
dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets,
dtab->map.numa_node);
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
if (!dtab->dev_index_head)
bpf: Eliminate rlimit-based memory accounting for devmap maps Do not use rlimit-based memory accounting for devmap maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20201201215900.3569844-23-guro@fb.com
2020-12-02 05:58:48 +08:00
return -ENOMEM;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
spin_lock_init(&dtab->index_lock);
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
} else {
bpf: Fix integer overflow in argument calculation for bpf_map_area_alloc In 32-bit architecture, the result of sizeof() is a 32-bit integer so the expression becomes the multiplication between 2 32-bit integer which can potentially leads to integer overflow. As a result, bpf_map_area_alloc() allocates less memory than needed. Fix this by casting 1 operand to u64. Fixes: 0d2c4f964050 ("bpf: Eliminate rlimit-based memory accounting for sockmap and sockhash maps") Fixes: 99c51064fb06 ("devmap: Use bpf_map_area_alloc() for allocating hash buckets") Fixes: 546ac1ffb70d ("bpf: add devmap, a map for storing net device references") Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210613143440.71975-1-minhquangbui99@gmail.com
2021-06-13 22:34:39 +08:00
dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries *
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
sizeof(struct bpf_dtab_netdev *),
dtab->map.numa_node);
if (!dtab->netdev_map)
bpf: Eliminate rlimit-based memory accounting for devmap maps Do not use rlimit-based memory accounting for devmap maps. It has been replaced with the memcg-based memory accounting. Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20201201215900.3569844-23-guro@fb.com
2020-12-02 05:58:48 +08:00
return -ENOMEM;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
}
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
return 0;
}
static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
{
struct bpf_dtab *dtab;
int err;
if (!capable(CAP_NET_ADMIN))
return ERR_PTR(-EPERM);
bpf: Refine memcg-based memory accounting for devmap maps Include map metadata and the node size (struct bpf_dtab_netdev) into the accounting. Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20201201215900.3569844-12-guro@fb.com
2020-12-02 05:58:37 +08:00
dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT);
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
if (!dtab)
return ERR_PTR(-ENOMEM);
err = dev_map_init_map(dtab, attr);
if (err) {
kfree(dtab);
return ERR_PTR(err);
}
spin_lock(&dev_map_lock);
list_add_tail_rcu(&dtab->list, &dev_map_list);
spin_unlock(&dev_map_lock);
return &dtab->map;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
}
static void dev_map_free(struct bpf_map *map)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
xdp: Simplify devmap cleanup After the RCU flavor consolidation [1], call_rcu() and synchronize_rcu() waits for preempt-disable regions (NAPI) in addition to the read-side critical sections. As a result of this, the cleanup code in devmap can be simplified * There is no longer a need to flush in __dev_map_entry_free, since we know that this has been done when the call_rcu() callback is triggered. * When freeing the map, there is no need to explicitly wait for a flush. It's guaranteed to be done after the synchronize_rcu() call in dev_map_free(). The rcu_barrier() is still needed, so that the map is not freed prior the elements. [1] https://lwn.net/Articles/777036/ Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20191219061006.21980-2-bjorn.topel@gmail.com
2019-12-19 14:09:59 +08:00
int i;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
/* 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
bpf, xdp: Update devmap comments to reflect napi/rcu usage Now that we rely on synchronize_rcu and call_rcu waiting to exit perempt-disable regions (NAPI) lets update the comments to reflect this. Fixes: 0536b85239b84 ("xdp: Simplify devmap cleanup") Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/1580084042-11598-2-git-send-email-john.fastabend@gmail.com
2020-01-27 08:14:00 +08:00
* disconnected from events. The following synchronize_rcu() guarantees
* both rcu read critical sections complete and waits for
* preempt-disable regions (NAPI being the relevant context here) so we
* are certain there will be no further reads against the netdev_map and
* all flush operations are complete. Flush operations can only be done
* from NAPI context for this reason.
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
*/
bpf: fix double free from dev_map_notification() In the current code, dev_map_free() can still race with dev_map_notification(). In dev_map_free(), we remove dtab from the list of dtabs after we purged all entries from it. However, we don't do xchg() with NULL or the like, so the entry at that point is still pointing to the device. If a unregister notification comes in at the same time, we therefore risk a double-free, since the pointer is still present in the map, and then pushed again to __dev_map_entry_free(). All this is completely unnecessary. Just remove the dtab from the list right before the synchronize_rcu(), so all outstanding readers from the notifier list have finished by then, thus we don't need to deal with this corner case anymore and also wouldn't need to nullify dev entires. This is fine because we iterate over the map releasing all entries and therefore dev references anyway. Fixes: 4cc7b9544b9a ("bpf: devmap fix mutex in rcu critical section") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-21 07:48:12 +08:00
spin_lock(&dev_map_lock);
list_del_rcu(&dtab->list);
spin_unlock(&dev_map_lock);
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
bpf_clear_redirect_map(map);
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
synchronize_rcu();
bpf: devmap: fix use-after-free Read in __dev_map_entry_free synchronize_rcu() is fine when the rcu callbacks only need to free memory (kfree_rcu() or direct kfree() call rcu call backs) __dev_map_entry_free() is a bit more complex, so we need to make sure that call queued __dev_map_entry_free() callbacks have completed. sysbot report: BUG: KASAN: use-after-free in dev_map_flush_old kernel/bpf/devmap.c:365 [inline] BUG: KASAN: use-after-free in __dev_map_entry_free+0x2a8/0x300 kernel/bpf/devmap.c:379 Read of size 8 at addr ffff8801b8da38c8 by task ksoftirqd/1/18 CPU: 1 PID: 18 Comm: ksoftirqd/1 Not tainted 4.17.0+ #39 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433 dev_map_flush_old kernel/bpf/devmap.c:365 [inline] __dev_map_entry_free+0x2a8/0x300 kernel/bpf/devmap.c:379 __rcu_reclaim kernel/rcu/rcu.h:178 [inline] rcu_do_batch kernel/rcu/tree.c:2558 [inline] invoke_rcu_callbacks kernel/rcu/tree.c:2818 [inline] __rcu_process_callbacks kernel/rcu/tree.c:2785 [inline] rcu_process_callbacks+0xe9d/0x1760 kernel/rcu/tree.c:2802 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:284 run_ksoftirqd+0x86/0x100 kernel/softirq.c:645 smpboot_thread_fn+0x417/0x870 kernel/smpboot.c:164 kthread+0x345/0x410 kernel/kthread.c:240 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412 Allocated by task 6675: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553 kmem_cache_alloc_trace+0x152/0x780 mm/slab.c:3620 kmalloc include/linux/slab.h:513 [inline] kzalloc include/linux/slab.h:706 [inline] dev_map_alloc+0x208/0x7f0 kernel/bpf/devmap.c:102 find_and_alloc_map kernel/bpf/syscall.c:129 [inline] map_create+0x393/0x1010 kernel/bpf/syscall.c:453 __do_sys_bpf kernel/bpf/syscall.c:2351 [inline] __se_sys_bpf kernel/bpf/syscall.c:2328 [inline] __x64_sys_bpf+0x303/0x510 kernel/bpf/syscall.c:2328 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 26: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kfree+0xd9/0x260 mm/slab.c:3813 dev_map_free+0x4fa/0x670 kernel/bpf/devmap.c:191 bpf_map_free_deferred+0xba/0xf0 kernel/bpf/syscall.c:262 process_one_work+0xc64/0x1b70 kernel/workqueue.c:2153 worker_thread+0x181/0x13a0 kernel/workqueue.c:2296 kthread+0x345/0x410 kernel/kthread.c:240 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412 The buggy address belongs to the object at ffff8801b8da37c0 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 264 bytes inside of 512-byte region [ffff8801b8da37c0, ffff8801b8da39c0) The buggy address belongs to the page: page:ffffea0006e368c0 count:1 mapcount:0 mapping:ffff8801da800940 index:0xffff8801b8da3540 flags: 0x2fffc0000000100(slab) raw: 02fffc0000000100 ffffea0007217b88 ffffea0006e30cc8 ffff8801da800940 raw: ffff8801b8da3540 ffff8801b8da3040 0000000100000004 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801b8da3780: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb ffff8801b8da3800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb > ffff8801b8da3880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801b8da3900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801b8da3980: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc Fixes: 546ac1ffb70d ("bpf: add devmap, a map for storing net device references") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot+457d3e2ffbcf31aee5c0@syzkaller.appspotmail.com Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-14 00:59:16 +08:00
/* Make sure prior __dev_map_entry_free() have completed. */
rcu_barrier();
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
for (i = 0; i < dtab->n_buckets; i++) {
struct bpf_dtab_netdev *dev;
struct hlist_head *head;
struct hlist_node *next;
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_safe(dev, next, head, index_hlist) {
hlist_del_rcu(&dev->index_hlist);
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
if (dev->xdp_prog)
bpf_prog_put(dev->xdp_prog);
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
dev_put(dev->dev);
kfree(dev);
}
}
devmap: Use bpf_map_area_alloc() for allocating hash buckets Syzkaller discovered that creating a hash of type devmap_hash with a large number of entries can hit the memory allocator limit for allocating contiguous memory regions. There's really no reason to use kmalloc_array() directly in the devmap code, so just switch it to the existing bpf_map_area_alloc() function that is used elsewhere. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200616142829.114173-1-toke@redhat.com
2020-06-16 22:28:29 +08:00
bpf_map_area_free(dtab->dev_index_head);
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
} else {
for (i = 0; i < dtab->map.max_entries; i++) {
struct bpf_dtab_netdev *dev;
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
dev = rcu_dereference_raw(dtab->netdev_map[i]);
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
if (!dev)
continue;
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
if (dev->xdp_prog)
bpf_prog_put(dev->xdp_prog);
xdp: Fix cleanup on map free for devmap_hash map type Tetsuo pointed out that it was not only the device unregister hook that was broken for devmap_hash types, it was also cleanup on map free. So better fix this as well. While we're at it, there's no reason to allocate the netdev_map array for DEVMAP_HASH, so skip that and adjust the cost accordingly. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20191121133612.430414-1-toke@redhat.com
2019-11-21 21:36:12 +08:00
dev_put(dev->dev);
kfree(dev);
}
bpf_map_area_free(dtab->netdev_map);
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
}
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;
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
u32 *next = next_key;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
if (index >= dtab->map.max_entries) {
*next = 0;
return 0;
}
if (index == dtab->map.max_entries - 1)
return -ENOENT;
*next = index + 1;
return 0;
}
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
*/
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct hlist_head *head = dev_map_index_hash(dtab, key);
struct bpf_dtab_netdev *dev;
bpf, devmap: Pass lockdep expression to RCU lists head is traversed using hlist_for_each_entry_rcu outside an RCU read-side critical section but under the protection of dtab->index_lock. Hence, add corresponding lockdep expression to silence false-positive lockdep warnings, and harden RCU lists. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Signed-off-by: Amol Grover <frextrite@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200123120437.26506-1-frextrite@gmail.com
2020-01-23 20:04:38 +08:00
hlist_for_each_entry_rcu(dev, head, index_hlist,
lockdep_is_held(&dtab->index_lock))
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
if (dev->idx == key)
return dev;
return NULL;
}
static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
void *next_key)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
u32 idx, *next = next_key;
struct bpf_dtab_netdev *dev, *next_dev;
struct hlist_head *head;
int i = 0;
if (!key)
goto find_first;
idx = *(u32 *)key;
dev = __dev_map_hash_lookup_elem(map, idx);
if (!dev)
goto find_first;
next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)),
struct bpf_dtab_netdev, index_hlist);
if (next_dev) {
*next = next_dev->idx;
return 0;
}
i = idx & (dtab->n_buckets - 1);
i++;
find_first:
for (; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
struct bpf_dtab_netdev,
index_hlist);
if (next_dev) {
*next = next_dev->idx;
return 0;
}
}
return -ENOENT;
}
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
struct xdp_frame **frames, int n,
struct net_device *dev)
{
struct xdp_txq_info txq = { .dev = dev };
struct xdp_buff xdp;
int i, nframes = 0;
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
u32 act;
int err;
xdp_convert_frame_to_buff(xdpf, &xdp);
xdp.txq = &txq;
act = bpf_prog_run_xdp(xdp_prog, &xdp);
switch (act) {
case XDP_PASS:
err = xdp_update_frame_from_buff(&xdp, xdpf);
if (unlikely(err < 0))
xdp_return_frame_rx_napi(xdpf);
else
frames[nframes++] = xdpf;
break;
default:
bpf: Let bpf_warn_invalid_xdp_action() report more info In non trivial scenarios, the action id alone is not sufficient to identify the program causing the warning. Before the previous patch, the generated stack-trace pointed out at least the involved device driver. Let's additionally include the program name and id, and the relevant device name. If the user needs additional infos, he can fetch them via a kernel probe, leveraging the arguments added here. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/ddb96bb975cbfddb1546cf5da60e77d5100b533c.1638189075.git.pabeni@redhat.com
2021-11-30 18:08:07 +08:00
bpf_warn_invalid_xdp_action(NULL, xdp_prog, act);
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dev, xdp_prog, act);
fallthrough;
case XDP_DROP:
xdp_return_frame_rx_napi(xdpf);
break;
}
}
return nframes; /* sent frames count */
}
bpf: {cpu,dev}map: Change various functions return type from int to void The functions bq_enqueue(), bq_flush_to_queue(), and bq_xmit_all() in {cpu,dev}map.c always return zero. Changing the return type from int to void makes the code easier to follow. Suggested-by: David Ahern <dsahern@gmail.com> Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200901083928.6199-1-bjorn.topel@gmail.com
2020-09-01 16:39:28 +08:00
static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
{
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
struct net_device *dev = bq->dev;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
unsigned int cnt = bq->count;
bpf, devmap: Remove drops variable from bq_xmit_all() As Colin pointed out, the first drops assignment after declaration will be overwritten by the second drops assignment before using, which makes it useless. Since the drops variable will be used only once. Just remove it and use "cnt - sent" in trace_xdp_devmap_xmit(). Fixes: cb261b594b41 ("bpf: Run devmap xdp_prog on flush instead of bulk enqueue") Reported-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210528024356.24333-1-liuhangbin@gmail.com
2021-05-28 10:43:56 +08:00
int sent = 0, err = 0;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
int to_send = cnt;
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
int i;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
if (unlikely(!cnt))
bpf: {cpu,dev}map: Change various functions return type from int to void The functions bq_enqueue(), bq_flush_to_queue(), and bq_xmit_all() in {cpu,dev}map.c always return zero. Changing the return type from int to void makes the code easier to follow. Suggested-by: David Ahern <dsahern@gmail.com> Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200901083928.6199-1-bjorn.topel@gmail.com
2020-09-01 16:39:28 +08:00
return;
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
for (i = 0; i < cnt; i++) {
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
struct xdp_frame *xdpf = bq->q[i];
prefetch(xdpf);
}
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
if (bq->xdp_prog) {
to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev);
if (!to_send)
goto out;
}
sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags);
xdp: change ndo_xdp_xmit API to support bulking This patch change the API for ndo_xdp_xmit to support bulking xdp_frames. When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown. Most of the slowdown is caused by DMA API indirect function calls, but also the net_device->ndo_xdp_xmit() call. Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed performance improved: for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps With frames avail as a bulk inside the driver ndo_xdp_xmit call, further optimizations are possible, like bulk DMA-mapping for TX. Testing without CONFIG_RETPOLINE show the same performance for physical NIC drivers. The virtual NIC driver tun sees a huge performance boost, as it can avoid doing per frame producer locking, but instead amortize the locking cost over the bulk. V2: Fix compile errors reported by kbuild test robot <lkp@intel.com> V4: Isolated ndo, driver changes and callers. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:46:12 +08:00
if (sent < 0) {
bpf, devmap: Move drop error path to devmap for XDP_REDIRECT We want to change the current ndo_xdp_xmit drop semantics because it will allow us to implement better queue overflow handling. This is working towards the larger goal of a XDP TX queue-hook. Move XDP_REDIRECT error path handling from each XDP ethernet driver to devmap code. According to the new APIs, the driver running the ndo_xdp_xmit pointer, will break tx loop whenever the hw reports a tx error and it will just return to devmap caller the number of successfully transmitted frames. It will be devmap responsibility to free dropped frames. Move each XDP ndo_xdp_xmit capable driver to the new APIs: - veth - virtio-net - mvneta - mvpp2 - socionext - amazon ena - bnxt - freescale (dpaa2, dpaa) - xen-frontend - qede - ice - igb - ixgbe - i40e - mlx5 - ti (cpsw, cpsw-new) - tun - sfc Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com> Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Camelia Groza <camelia.groza@nxp.com> Acked-by: Edward Cree <ecree.xilinx@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Shay Agroskin <shayagr@amazon.com> Link: https://lore.kernel.org/bpf/ed670de24f951cfd77590decf0229a0ad7fd12f6.1615201152.git.lorenzo@kernel.org
2021-03-08 19:06:58 +08:00
/* If ndo_xdp_xmit fails with an errno, no frames have
* been xmit'ed.
*/
xdp/trace: extend tracepoint in devmap with an err Extending tracepoint xdp:xdp_devmap_xmit in devmap with an err code allow people to easier identify the reason behind the ndo_xdp_xmit call to a given driver is failing. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:46:17 +08:00
err = sent;
xdp: change ndo_xdp_xmit API to support bulking This patch change the API for ndo_xdp_xmit to support bulking xdp_frames. When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown. Most of the slowdown is caused by DMA API indirect function calls, but also the net_device->ndo_xdp_xmit() call. Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed performance improved: for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps With frames avail as a bulk inside the driver ndo_xdp_xmit call, further optimizations are possible, like bulk DMA-mapping for TX. Testing without CONFIG_RETPOLINE show the same performance for physical NIC drivers. The virtual NIC driver tun sees a huge performance boost, as it can avoid doing per frame producer locking, but instead amortize the locking cost over the bulk. V2: Fix compile errors reported by kbuild test robot <lkp@intel.com> V4: Isolated ndo, driver changes and callers. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:46:12 +08:00
sent = 0;
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
}
bpf, devmap: Move drop error path to devmap for XDP_REDIRECT We want to change the current ndo_xdp_xmit drop semantics because it will allow us to implement better queue overflow handling. This is working towards the larger goal of a XDP TX queue-hook. Move XDP_REDIRECT error path handling from each XDP ethernet driver to devmap code. According to the new APIs, the driver running the ndo_xdp_xmit pointer, will break tx loop whenever the hw reports a tx error and it will just return to devmap caller the number of successfully transmitted frames. It will be devmap responsibility to free dropped frames. Move each XDP ndo_xdp_xmit capable driver to the new APIs: - veth - virtio-net - mvneta - mvpp2 - socionext - amazon ena - bnxt - freescale (dpaa2, dpaa) - xen-frontend - qede - ice - igb - ixgbe - i40e - mlx5 - ti (cpsw, cpsw-new) - tun - sfc Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com> Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Camelia Groza <camelia.groza@nxp.com> Acked-by: Edward Cree <ecree.xilinx@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Shay Agroskin <shayagr@amazon.com> Link: https://lore.kernel.org/bpf/ed670de24f951cfd77590decf0229a0ad7fd12f6.1615201152.git.lorenzo@kernel.org
2021-03-08 19:06:58 +08:00
/* If not all frames have been transmitted, it is our
* responsibility to free them
xdp: change ndo_xdp_xmit API to support bulking This patch change the API for ndo_xdp_xmit to support bulking xdp_frames. When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown. Most of the slowdown is caused by DMA API indirect function calls, but also the net_device->ndo_xdp_xmit() call. Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed performance improved: for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps With frames avail as a bulk inside the driver ndo_xdp_xmit call, further optimizations are possible, like bulk DMA-mapping for TX. Testing without CONFIG_RETPOLINE show the same performance for physical NIC drivers. The virtual NIC driver tun sees a huge performance boost, as it can avoid doing per frame producer locking, but instead amortize the locking cost over the bulk. V2: Fix compile errors reported by kbuild test robot <lkp@intel.com> V4: Isolated ndo, driver changes and callers. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:46:12 +08:00
*/
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
for (i = sent; unlikely(i < to_send); i++)
bpf, devmap: Move drop error path to devmap for XDP_REDIRECT We want to change the current ndo_xdp_xmit drop semantics because it will allow us to implement better queue overflow handling. This is working towards the larger goal of a XDP TX queue-hook. Move XDP_REDIRECT error path handling from each XDP ethernet driver to devmap code. According to the new APIs, the driver running the ndo_xdp_xmit pointer, will break tx loop whenever the hw reports a tx error and it will just return to devmap caller the number of successfully transmitted frames. It will be devmap responsibility to free dropped frames. Move each XDP ndo_xdp_xmit capable driver to the new APIs: - veth - virtio-net - mvneta - mvpp2 - socionext - amazon ena - bnxt - freescale (dpaa2, dpaa) - xen-frontend - qede - ice - igb - ixgbe - i40e - mlx5 - ti (cpsw, cpsw-new) - tun - sfc Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com> Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Camelia Groza <camelia.groza@nxp.com> Acked-by: Edward Cree <ecree.xilinx@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Shay Agroskin <shayagr@amazon.com> Link: https://lore.kernel.org/bpf/ed670de24f951cfd77590decf0229a0ad7fd12f6.1615201152.git.lorenzo@kernel.org
2021-03-08 19:06:58 +08:00
xdp_return_frame_rx_napi(bq->q[i]);
xdp: change ndo_xdp_xmit API to support bulking This patch change the API for ndo_xdp_xmit to support bulking xdp_frames. When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown. Most of the slowdown is caused by DMA API indirect function calls, but also the net_device->ndo_xdp_xmit() call. Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed performance improved: for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps With frames avail as a bulk inside the driver ndo_xdp_xmit call, further optimizations are possible, like bulk DMA-mapping for TX. Testing without CONFIG_RETPOLINE show the same performance for physical NIC drivers. The virtual NIC driver tun sees a huge performance boost, as it can avoid doing per frame producer locking, but instead amortize the locking cost over the bulk. V2: Fix compile errors reported by kbuild test robot <lkp@intel.com> V4: Isolated ndo, driver changes and callers. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:46:12 +08:00
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
out:
bpf, devmap: Move drop error path to devmap for XDP_REDIRECT We want to change the current ndo_xdp_xmit drop semantics because it will allow us to implement better queue overflow handling. This is working towards the larger goal of a XDP TX queue-hook. Move XDP_REDIRECT error path handling from each XDP ethernet driver to devmap code. According to the new APIs, the driver running the ndo_xdp_xmit pointer, will break tx loop whenever the hw reports a tx error and it will just return to devmap caller the number of successfully transmitted frames. It will be devmap responsibility to free dropped frames. Move each XDP ndo_xdp_xmit capable driver to the new APIs: - veth - virtio-net - mvneta - mvpp2 - socionext - amazon ena - bnxt - freescale (dpaa2, dpaa) - xen-frontend - qede - ice - igb - ixgbe - i40e - mlx5 - ti (cpsw, cpsw-new) - tun - sfc Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com> Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org> Reviewed-by: Camelia Groza <camelia.groza@nxp.com> Acked-by: Edward Cree <ecree.xilinx@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Shay Agroskin <shayagr@amazon.com> Link: https://lore.kernel.org/bpf/ed670de24f951cfd77590decf0229a0ad7fd12f6.1615201152.git.lorenzo@kernel.org
2021-03-08 19:06:58 +08:00
bq->count = 0;
bpf, devmap: Remove drops variable from bq_xmit_all() As Colin pointed out, the first drops assignment after declaration will be overwritten by the second drops assignment before using, which makes it useless. Since the drops variable will be used only once. Just remove it and use "cnt - sent" in trace_xdp_devmap_xmit(). Fixes: cb261b594b41 ("bpf: Run devmap xdp_prog on flush instead of bulk enqueue") Reported-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210528024356.24333-1-liuhangbin@gmail.com
2021-05-28 10:43:56 +08:00
trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err);
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
}
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the
* driver before returning from its napi->poll() routine. See the comment above
* xdp_do_flush() in filter.c.
xdp: Add batching support to redirect map For performance reasons we want to avoid updating the tail pointer in the driver tx ring as much as possible. To accomplish this we add batching support to the redirect path in XDP. This adds another ndo op "xdp_flush" that is used to inform the driver that it should bump the tail pointer on the TX ring. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:29:40 +08:00
*/
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
void __dev_flush(void)
xdp: Add batching support to redirect map For performance reasons we want to avoid updating the tail pointer in the driver tx ring as much as possible. To accomplish this we add batching support to the redirect path in XDP. This adds another ndo op "xdp_flush" that is used to inform the driver that it should bump the tail pointer on the TX ring. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:29:40 +08:00
{
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
struct xdp_dev_bulk_queue *bq, *tmp;
xdp: Add batching support to redirect map For performance reasons we want to avoid updating the tail pointer in the driver tx ring as much as possible. To accomplish this we add batching support to the redirect path in XDP. This adds another ndo op "xdp_flush" that is used to inform the driver that it should bump the tail pointer on the TX ring. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:29:40 +08:00
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
xdp: Simplify devmap cleanup After the RCU flavor consolidation [1], call_rcu() and synchronize_rcu() waits for preempt-disable regions (NAPI) in addition to the read-side critical sections. As a result of this, the cleanup code in devmap can be simplified * There is no longer a need to flush in __dev_map_entry_free, since we know that this has been done when the call_rcu() callback is triggered. * When freeing the map, there is no need to explicitly wait for a flush. It's guaranteed to be done after the synchronize_rcu() call in dev_map_free(). The rcu_barrier() is still needed, so that the map is not freed prior the elements. [1] https://lwn.net/Articles/777036/ Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20191219061006.21980-2-bjorn.topel@gmail.com
2019-12-19 14:09:59 +08:00
bq_xmit_all(bq, XDP_XMIT_FLUSH);
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
bq->dev_rx = NULL;
bq->xdp_prog = NULL;
__list_del_clearprev(&bq->flush_node);
}
xdp: Add batching support to redirect map For performance reasons we want to avoid updating the tail pointer in the driver tx ring as much as possible. To accomplish this we add batching support to the redirect path in XDP. This adds another ndo op "xdp_flush" that is used to inform the driver that it should bump the tail pointer on the TX ring. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:29:40 +08:00
}
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
* by local_bh_disable() (from XDP calls inside NAPI). The
* rcu_read_lock_bh_held() below makes lockdep accept both.
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
*/
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
struct bpf_dtab_netdev *obj;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
if (key >= map->max_entries)
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
return NULL;
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
obj = rcu_dereference_check(dtab->netdev_map[key],
rcu_read_lock_bh_held());
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
return obj;
}
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
* variable access, and map elements stick around. See comment above
* xdp_do_flush() in filter.c.
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
*/
bpf: {cpu,dev}map: Change various functions return type from int to void The functions bq_enqueue(), bq_flush_to_queue(), and bq_xmit_all() in {cpu,dev}map.c always return zero. Changing the return type from int to void makes the code easier to follow. Suggested-by: David Ahern <dsahern@gmail.com> Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200901083928.6199-1-bjorn.topel@gmail.com
2020-09-01 16:39:28 +08:00
static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
struct net_device *dev_rx, struct bpf_prog *xdp_prog)
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
{
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
xdp: Simplify devmap cleanup After the RCU flavor consolidation [1], call_rcu() and synchronize_rcu() waits for preempt-disable regions (NAPI) in addition to the read-side critical sections. As a result of this, the cleanup code in devmap can be simplified * There is no longer a need to flush in __dev_map_entry_free, since we know that this has been done when the call_rcu() callback is triggered. * When freeing the map, there is no need to explicitly wait for a flush. It's guaranteed to be done after the synchronize_rcu() call in dev_map_free(). The rcu_barrier() is still needed, so that the map is not freed prior the elements. [1] https://lwn.net/Articles/777036/ Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20191219061006.21980-2-bjorn.topel@gmail.com
2019-12-19 14:09:59 +08:00
bq_xmit_all(bq, 0);
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
xdp: add tracepoint for devmap like cpumap have Notice how this allow us get XDP statistic without affecting the XDP performance, as tracepoint is no-longer activated on a per packet basis. V5: Spotted by John Fastabend. Fix 'sent' also counted 'drops' in this patch, a later patch corrected this, but it was a mistake in this intermediate step. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:57 +08:00
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
* from net_device drivers NAPI func end.
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
*
* Do the same with xdp_prog and flush_list since these fields
* are only ever modified together.
xdp: add tracepoint for devmap like cpumap have Notice how this allow us get XDP statistic without affecting the XDP performance, as tracepoint is no-longer activated on a per packet basis. V5: Spotted by John Fastabend. Fix 'sent' also counted 'drops' in this patch, a later patch corrected this, but it was a mistake in this intermediate step. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:57 +08:00
*/
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
if (!bq->dev_rx) {
xdp: add tracepoint for devmap like cpumap have Notice how this allow us get XDP statistic without affecting the XDP performance, as tracepoint is no-longer activated on a per packet basis. V5: Spotted by John Fastabend. Fix 'sent' also counted 'drops' in this patch, a later patch corrected this, but it was a mistake in this intermediate step. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:57 +08:00
bq->dev_rx = dev_rx;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
bq->xdp_prog = xdp_prog;
list_add(&bq->flush_node, flush_list);
}
xdp: add tracepoint for devmap like cpumap have Notice how this allow us get XDP statistic without affecting the XDP performance, as tracepoint is no-longer activated on a per packet basis. V5: Spotted by John Fastabend. Fix 'sent' also counted 'drops' in this patch, a later patch corrected this, but it was a mistake in this intermediate step. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:57 +08:00
bpf: devmap prepare xdp frames for bulking Like cpumap create queue for xdp frames that will be bulked. For now, this patch simply invoke ndo_xdp_xmit foreach frame. This happens, either when the map flush operation is envoked, or when the limit DEV_MAP_BULK_SIZE is reached. V5: Avoid memleak on error path in dev_map_update_elem() Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:51 +08:00
bq->q[bq->count++] = xdpf;
}
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
struct net_device *dev_rx,
struct bpf_prog *xdp_prog)
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
{
struct xdp_frame *xdpf;
xdp: XDP_REDIRECT should check IFF_UP and MTU Otherwise we end up with attempting to send packets from down devices or to send oversized packets, which may cause unexpected driver/device behaviour. Generic XDP has already done this check, so reuse the logic in native XDP. Fixes: 814abfabef3c ("xdp: add bpf_redirect helper function") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-07-06 10:49:00 +08:00
int err;
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
xdp: XDP_REDIRECT should check IFF_UP and MTU Otherwise we end up with attempting to send packets from down devices or to send oversized packets, which may cause unexpected driver/device behaviour. Generic XDP has already done this check, so reuse the logic in native XDP. Fixes: 814abfabef3c ("xdp: add bpf_redirect helper function") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-07-06 10:49:00 +08:00
err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
if (unlikely(err))
return err;
xdp: Rename convert_to_xdp_frame in xdp_convert_buff_to_frame In order to use standard 'xdp' prefix, rename convert_to_xdp_frame utility routine in xdp_convert_buff_to_frame and replace all the occurrences Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/6344f739be0d1a08ab2b9607584c4d5478c8c083.1590698295.git.lorenzo@kernel.org
2020-05-29 04:47:29 +08:00
xdpf = xdp_convert_buff_to_frame(xdp);
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
if (unlikely(!xdpf))
return -EOVERFLOW;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
bq_enqueue(dev, xdpf, dev_rx, xdp_prog);
bpf: {cpu,dev}map: Change various functions return type from int to void The functions bq_enqueue(), bq_flush_to_queue(), and bq_xmit_all() in {cpu,dev}map.c always return zero. Changing the return type from int to void makes the code easier to follow. Suggested-by: David Ahern <dsahern@gmail.com> Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200901083928.6199-1-bjorn.topel@gmail.com
2020-09-01 16:39:28 +08:00
return 0;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
}
bpf: devmap: Implement devmap prog execution for generic XDP This lifts the restriction on running devmap BPF progs in generic redirect mode. To match native XDP behavior, it is invoked right before generic_xdp_tx is called, and only supports XDP_PASS/XDP_ABORTED/ XDP_DROP actions. We also return 0 even if devmap program drops the packet, as semantically redirect has already succeeded and the devmap prog is the last point before TX of the packet to device where it can deliver a verdict on the packet. This also means it must take care of freeing the skb, as xdp_do_generic_redirect callers only do that in case an error is returned. Since devmap entry prog is supported, remove the check in generic_xdp_install entirely. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210702111825.491065-5-memxor@gmail.com
2021-07-02 19:18:24 +08:00
static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst)
{
struct xdp_txq_info txq = { .dev = dst->dev };
struct xdp_buff xdp;
u32 act;
if (!dst->xdp_prog)
return XDP_PASS;
__skb_pull(skb, skb->mac_len);
xdp.txq = &txq;
act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog);
switch (act) {
case XDP_PASS:
__skb_push(skb, skb->mac_len);
break;
default:
bpf: Let bpf_warn_invalid_xdp_action() report more info In non trivial scenarios, the action id alone is not sufficient to identify the program causing the warning. Before the previous patch, the generated stack-trace pointed out at least the involved device driver. Let's additionally include the program name and id, and the relevant device name. If the user needs additional infos, he can fetch them via a kernel probe, leveraging the arguments added here. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/ddb96bb975cbfddb1546cf5da60e77d5100b533c.1638189075.git.pabeni@redhat.com
2021-11-30 18:08:07 +08:00
bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act);
bpf: devmap: Implement devmap prog execution for generic XDP This lifts the restriction on running devmap BPF progs in generic redirect mode. To match native XDP behavior, it is invoked right before generic_xdp_tx is called, and only supports XDP_PASS/XDP_ABORTED/ XDP_DROP actions. We also return 0 even if devmap program drops the packet, as semantically redirect has already succeeded and the devmap prog is the last point before TX of the packet to device where it can deliver a verdict on the packet. This also means it must take care of freeing the skb, as xdp_do_generic_redirect callers only do that in case an error is returned. Since devmap entry prog is supported, remove the check in generic_xdp_install entirely. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210702111825.491065-5-memxor@gmail.com
2021-07-02 19:18:24 +08:00
fallthrough;
case XDP_ABORTED:
trace_xdp_exception(dst->dev, dst->xdp_prog, act);
fallthrough;
case XDP_DROP:
kfree_skb(skb);
break;
}
return act;
}
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
return __xdp_enqueue(dev, xdp, dev_rx, NULL);
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
}
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
struct net_device *dev = dst->dev;
bpf: Run devmap xdp_prog on flush instead of bulk enqueue This changes the devmap XDP program support to run the program when the bulk queue is flushed instead of before the frame is enqueued. This has a couple of benefits: - It "sorts" the packets by destination devmap entry, and then runs the same BPF program on all the packets in sequence. This ensures that we keep the XDP program and destination device properties hot in I-cache. - It makes the multicast implementation simpler because it can just enqueue packets using bq_enqueue() without having to deal with the devmap program at all. The drawback is that if the devmap program drops the packet, the enqueue step is redundant. However, arguably this is mostly visible in a micro-benchmark, and with more mixed traffic the I-cache benefit should win out. The performance impact of just this patch is as follows: Using 2 10Gb i40e NIC, redirecting one to another, or into a veth interface, which do XDP_DROP on veth peer. With xdp_redirect_map in sample/bpf, send pkts via pktgen cmd: ./pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -t 10 -s 64 There are about +/- 0.1M deviation for native testing, the performance improved for the base-case, but some drop back with xdp devmap prog attached. Version | Test | Generic | Native | Native + 2nd xdp_prog 5.12 rc4 | xdp_redirect_map i40e->i40e | 1.9M | 9.6M | 8.4M 5.12 rc4 | xdp_redirect_map i40e->veth | 1.7M | 11.7M | 9.8M 5.12 rc4 + patch | xdp_redirect_map i40e->i40e | 1.9M | 9.8M | 8.0M 5.12 rc4 + patch | xdp_redirect_map i40e->veth | 1.7M | 12.0M | 9.4M When bq_xmit_all() is called from bq_enqueue(), another packet will always be enqueued immediately after, so clearing dev_rx, xdp_prog and flush_node in bq_xmit_all() is redundant. Move the clear to __dev_flush(), and only check them once in bq_enqueue() since they are all modified together. This change also has the side effect of extending the lifetime of the RCU-protected xdp_prog that lives inside the devmap entries: Instead of just living for the duration of the XDP program invocation, the reference now lives all the way until the bq is flushed. This is safe because the bq flush happens at the end of the NAPI poll loop, so everything happens between a local_bh_disable()/local_bh_enable() pair. However, this is by no means obvious from looking at the call sites; in particular, some drivers have an additional rcu_read_lock() around only the XDP program invocation, which only confuses matters further. Cleaning this up will be done in a separate patch series. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-2-liuhangbin@gmail.com
2021-05-19 17:07:44 +08:00
return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
}
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp)
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
{
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (!obj ||
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
!obj->dev->netdev_ops->ndo_xdp_xmit)
return false;
if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data))
return false;
return true;
}
static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
struct net_device *dev_rx,
struct xdp_frame *xdpf)
{
struct xdp_frame *nxdpf;
nxdpf = xdpf_clone(xdpf);
if (!nxdpf)
return -ENOMEM;
bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog);
return 0;
}
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex)
{
while (num_excluded--) {
if (ifindex == excluded[num_excluded])
return true;
}
return false;
}
/* Get ifindex of each upper device. 'indexes' must be able to hold at
* least MAX_NEST_DEV elements.
* Returns the number of ifindexes added.
*/
static int get_upper_ifindexes(struct net_device *dev, int *indexes)
{
struct net_device *upper;
struct list_head *iter;
int n = 0;
netdev_for_each_upper_dev_rcu(dev, upper, iter) {
indexes[n++] = upper->ifindex;
}
return n;
}
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
struct bpf_map *map, bool exclude_ingress)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dst, *last_dst = NULL;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
int excluded_devices[1+MAX_NEST_DEV];
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
struct hlist_head *head;
struct xdp_frame *xdpf;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
int num_excluded = 0;
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
unsigned int i;
int err;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (exclude_ingress) {
num_excluded = get_upper_ifindexes(dev_rx, excluded_devices);
excluded_devices[num_excluded++] = dev_rx->ifindex;
}
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
xdpf = xdp_convert_buff_to_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
bpf, devmap: Convert remaining READ_ONCE() to rcu_dereference_check() There were a couple of READ_ONCE()-invocations left-over by the devmap RCU conversion. Convert these to rcu_dereference_check() as well to avoid complaints from sparse. Fixes: 782347b6bcad ("xdp: Add proper __rcu annotations to redirect map entries") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Paul E. McKenney <paulmck@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20210629093907.573598-1-toke@redhat.com
2021-06-29 17:39:07 +08:00
dst = rcu_dereference_check(dtab->netdev_map[i],
rcu_read_lock_bh_held());
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (!is_valid_dst(dst, xdp))
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
if (err)
return err;
last_dst = dst;
}
} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
for (i = 0; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_rcu(dst, head, index_hlist,
lockdep_is_held(&dtab->index_lock)) {
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (!is_valid_dst(dst, xdp))
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded,
dst->dev->ifindex))
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf);
if (err)
return err;
last_dst = dst;
}
}
}
/* consume the last copy of the frame */
if (last_dst)
bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog);
else
xdp_return_frame_rx_napi(xdpf); /* dtab is empty */
return 0;
}
xdp: Fix handling of devmap in generic XDP Commit 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") changed the return value type of __devmap_lookup_elem() from struct net_device * to struct bpf_dtab_netdev * but forgot to modify generic XDP code accordingly. Thus generic XDP incorrectly used struct bpf_dtab_netdev where struct net_device is expected, then skb->dev was set to invalid value. v2: - Fix compiler warning without CONFIG_BPF_SYSCALL. Fixes: 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-14 10:07:42 +08:00
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
int err;
xdp: XDP_REDIRECT should check IFF_UP and MTU Otherwise we end up with attempting to send packets from down devices or to send oversized packets, which may cause unexpected driver/device behaviour. Generic XDP has already done this check, so reuse the logic in native XDP. Fixes: 814abfabef3c ("xdp: add bpf_redirect helper function") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-07-06 10:49:00 +08:00
err = xdp_ok_fwd_dev(dst->dev, skb->len);
xdp: Fix handling of devmap in generic XDP Commit 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") changed the return value type of __devmap_lookup_elem() from struct net_device * to struct bpf_dtab_netdev * but forgot to modify generic XDP code accordingly. Thus generic XDP incorrectly used struct bpf_dtab_netdev where struct net_device is expected, then skb->dev was set to invalid value. v2: - Fix compiler warning without CONFIG_BPF_SYSCALL. Fixes: 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-14 10:07:42 +08:00
if (unlikely(err))
return err;
bpf: devmap: Implement devmap prog execution for generic XDP This lifts the restriction on running devmap BPF progs in generic redirect mode. To match native XDP behavior, it is invoked right before generic_xdp_tx is called, and only supports XDP_PASS/XDP_ABORTED/ XDP_DROP actions. We also return 0 even if devmap program drops the packet, as semantically redirect has already succeeded and the devmap prog is the last point before TX of the packet to device where it can deliver a verdict on the packet. This also means it must take care of freeing the skb, as xdp_do_generic_redirect callers only do that in case an error is returned. Since devmap entry prog is supported, remove the check in generic_xdp_install entirely. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210702111825.491065-5-memxor@gmail.com
2021-07-02 19:18:24 +08:00
/* Redirect has already succeeded semantically at this point, so we just
* return 0 even if packet is dropped. Helper below takes care of
* freeing skb.
*/
if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS)
return 0;
xdp: Fix handling of devmap in generic XDP Commit 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") changed the return value type of __devmap_lookup_elem() from struct net_device * to struct bpf_dtab_netdev * but forgot to modify generic XDP code accordingly. Thus generic XDP incorrectly used struct bpf_dtab_netdev where struct net_device is expected, then skb->dev was set to invalid value. v2: - Fix compiler warning without CONFIG_BPF_SYSCALL. Fixes: 67f29e07e131 ("bpf: devmap introduce dev_map_enqueue") Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-06-14 10:07:42 +08:00
skb->dev = dst->dev;
generic_xdp_tx(skb, xdp_prog);
return 0;
}
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst,
struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
struct sk_buff *nskb;
int err;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
err = dev_map_generic_redirect(dst, nskb, xdp_prog);
if (unlikely(err)) {
consume_skb(nskb);
return err;
}
return 0;
}
int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
struct bpf_prog *xdp_prog, struct bpf_map *map,
bool exclude_ingress)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dst, *last_dst = NULL;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
int excluded_devices[1+MAX_NEST_DEV];
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
struct hlist_head *head;
struct hlist_node *next;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
int num_excluded = 0;
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
unsigned int i;
int err;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (exclude_ingress) {
num_excluded = get_upper_ifindexes(dev, excluded_devices);
excluded_devices[num_excluded++] = dev->ifindex;
}
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
bpf, devmap: Convert remaining READ_ONCE() to rcu_dereference_check() There were a couple of READ_ONCE()-invocations left-over by the devmap RCU conversion. Convert these to rcu_dereference_check() as well to avoid complaints from sparse. Fixes: 782347b6bcad ("xdp: Add proper __rcu annotations to redirect map entries") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Paul E. McKenney <paulmck@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20210629093907.573598-1-toke@redhat.com
2021-06-29 17:39:07 +08:00
dst = rcu_dereference_check(dtab->netdev_map[i],
rcu_read_lock_bh_held());
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (!dst)
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
if (err)
return err;
last_dst = dst;
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
}
} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
for (i = 0; i < dtab->n_buckets; i++) {
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_safe(dst, next, head, index_hlist) {
bpf, devmap: Exclude XDP broadcast to master device If the ingress device is bond slave, do not broadcast back through it or the bond master. Signed-off-by: Jussi Maki <joamaki@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210731055738.16820-5-joamaki@gmail.com
2021-07-31 13:57:35 +08:00
if (!dst)
continue;
if (is_ifindex_excluded(excluded_devices, num_excluded,
dst->dev->ifindex))
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
continue;
/* we only need n-1 clones; last_dst enqueued below */
if (!last_dst) {
last_dst = dst;
continue;
}
err = dev_map_redirect_clone(last_dst, skb, xdp_prog);
if (err)
return err;
last_dst = dst;
}
}
}
/* consume the first skb and return */
if (last_dst)
return dev_map_generic_redirect(last_dst, skb, xdp_prog);
/* dtab is empty */
consume_skb(skb);
return 0;
}
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
return obj ? &obj->val : NULL;
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
}
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map,
*(u32 *)key);
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
return obj ? &obj->val : NULL;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
}
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
static void __dev_map_entry_free(struct rcu_head *rcu)
{
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
struct bpf_dtab_netdev *dev;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
if (dev->xdp_prog)
bpf_prog_put(dev->xdp_prog);
bpf: minor cleanups for dev_map Some minor code cleanups, while going over it I also noticed that we're accounting the bitmap only for one CPU currently, so fix that up as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-23 07:47:54 +08:00
dev_put(dev->dev);
kfree(dev);
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
}
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;
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL));
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
return 0;
}
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
static int dev_map_hash_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;
unsigned long flags;
int ret = -ENOENT;
spin_lock_irqsave(&dtab->index_lock, flags);
old_dev = __dev_map_hash_lookup_elem(map, k);
if (old_dev) {
dtab->items--;
hlist_del_init_rcu(&old_dev->index_hlist);
call_rcu(&old_dev->rcu, __dev_map_entry_free);
ret = 0;
}
spin_unlock_irqrestore(&dtab->index_lock, flags);
return ret;
}
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
struct bpf_dtab *dtab,
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
struct bpf_devmap_val *val,
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
unsigned int idx)
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
{
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
struct bpf_prog *prog = NULL;
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
struct bpf_dtab_netdev *dev;
bpf: Refine memcg-based memory accounting for devmap maps Include map metadata and the node size (struct bpf_dtab_netdev) into the accounting. Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20201201215900.3569844-12-guro@fb.com
2020-12-02 05:58:37 +08:00
dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev),
GFP_ATOMIC | __GFP_NOWARN,
dtab->map.numa_node);
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
if (!dev)
return ERR_PTR(-ENOMEM);
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
dev->dev = dev_get_by_index(net, val->ifindex);
if (!dev->dev)
goto err_out;
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
bpf: Devmap adjust uapi for attach bpf program V2: - Defer changing BPF-syscall to start at file-descriptor 1 - Use {} to zero initialise struct. The recent commit fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry"), introduced ability to attach (and run) a separate XDP bpf_prog for each devmap entry. A bpf_prog is added via a file-descriptor. As zero were a valid FD, not using the feature requires using value minus-1. The UAPI is extended via tail-extending struct bpf_devmap_val and using map->value_size to determine the feature set. This will break older userspace applications not using the bpf_prog feature. Consider an old userspace app that is compiled against newer kernel uapi/bpf.h, it will not know that it need to initialise the member bpf_prog.fd to minus-1. Thus, users will be forced to update source code to get program running on newer kernels. This patch remove the minus-1 checks, and have zero mean feature isn't used. Followup patches either for kernel or libbpf should handle and avoid returning file-descriptor zero in the first place. Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159170950687.2102545.7235914718298050113.stgit@firesoul
2020-06-09 21:31:46 +08:00
if (val->bpf_prog.fd > 0) {
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
prog = bpf_prog_get_type_dev(val->bpf_prog.fd,
BPF_PROG_TYPE_XDP, false);
if (IS_ERR(prog))
goto err_put_dev;
if (prog->expected_attach_type != BPF_XDP_DEVMAP)
goto err_put_prog;
}
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
dev->idx = idx;
dev->dtab = dtab;
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
if (prog) {
dev->xdp_prog = prog;
dev->val.bpf_prog.id = prog->aux->id;
} else {
dev->xdp_prog = NULL;
dev->val.bpf_prog.id = 0;
}
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
dev->val.ifindex = val->ifindex;
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
return dev;
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
err_put_prog:
bpf_prog_put(prog);
err_put_dev:
dev_put(dev->dev);
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
err_out:
kfree(dev);
return ERR_PTR(-EINVAL);
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
}
static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
void *key, void *value, u64 map_flags)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
struct bpf_dtab_netdev *dev, *old_dev;
bpf: Devmap adjust uapi for attach bpf program V2: - Defer changing BPF-syscall to start at file-descriptor 1 - Use {} to zero initialise struct. The recent commit fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry"), introduced ability to attach (and run) a separate XDP bpf_prog for each devmap entry. A bpf_prog is added via a file-descriptor. As zero were a valid FD, not using the feature requires using value minus-1. The UAPI is extended via tail-extending struct bpf_devmap_val and using map->value_size to determine the feature set. This will break older userspace applications not using the bpf_prog feature. Consider an old userspace app that is compiled against newer kernel uapi/bpf.h, it will not know that it need to initialise the member bpf_prog.fd to minus-1. Thus, users will be forced to update source code to get program running on newer kernels. This patch remove the minus-1 checks, and have zero mean feature isn't used. Followup patches either for kernel or libbpf should handle and avoid returning file-descriptor zero in the first place. Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159170950687.2102545.7235914718298050113.stgit@firesoul
2020-06-09 21:31:46 +08:00
struct bpf_devmap_val val = {};
devmap/cpumap: Use flush list instead of bitmap The socket map uses a linked list instead of a bitmap to keep track of which entries to flush. Do the same for devmap and cpumap, as this means we don't have to care about the map index when enqueueing things into the map (and so we can cache the map lookup). Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-28 17:12:34 +08:00
u32 i = *(u32 *)key;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
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;
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
/* already verified value_size <= sizeof val */
memcpy(&val, value, map->value_size);
if (!val.ifindex) {
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
dev = NULL;
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
/* can not specify fd if ifindex is 0 */
bpf: Devmap adjust uapi for attach bpf program V2: - Defer changing BPF-syscall to start at file-descriptor 1 - Use {} to zero initialise struct. The recent commit fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry"), introduced ability to attach (and run) a separate XDP bpf_prog for each devmap entry. A bpf_prog is added via a file-descriptor. As zero were a valid FD, not using the feature requires using value minus-1. The UAPI is extended via tail-extending struct bpf_devmap_val and using map->value_size to determine the feature set. This will break older userspace applications not using the bpf_prog feature. Consider an old userspace app that is compiled against newer kernel uapi/bpf.h, it will not know that it need to initialise the member bpf_prog.fd to minus-1. Thus, users will be forced to update source code to get program running on newer kernels. This patch remove the minus-1 checks, and have zero mean feature isn't used. Followup patches either for kernel or libbpf should handle and avoid returning file-descriptor zero in the first place. Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159170950687.2102545.7235914718298050113.stgit@firesoul
2020-06-09 21:31:46 +08:00
if (val.bpf_prog.fd > 0)
bpf: Add support to attach bpf program to a devmap entry Add BPF_XDP_DEVMAP attach type for use with programs associated with a DEVMAP entry. Allow DEVMAPs to associate a program with a device entry by adding a bpf_prog.fd to 'struct bpf_devmap_val'. Values read show the program id, so the fd and id are a union. bpf programs can get access to the struct via vmlinux.h. The program associated with the fd must have type XDP with expected attach type BPF_XDP_DEVMAP. When a program is associated with a device index, the program is run on an XDP_REDIRECT and before the buffer is added to the per-cpu queue. At this point rxq data is still valid; the next patch adds tx device information allowing the prorgam to see both ingress and egress device indices. XDP generic is skb based and XDP programs do not work with skb's. Block the use case by walking maps used by a program that is to be attached via xdpgeneric and fail if any of them are DEVMAP / DEVMAP_HASH with Block attach of BPF_XDP_DEVMAP programs to devices. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-3-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:13 +08:00
return -EINVAL;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
} else {
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
dev = __dev_map_alloc_node(net, dtab, &val, i);
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
if (IS_ERR(dev))
return PTR_ERR(dev);
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
}
/* 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.
*/
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev)));
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
return 0;
}
xdp: Refactor devmap allocation code for reuse The subsequent patch to add a new devmap sub-type can re-use much of the initialisation and allocation code, so refactor it into separate functions. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:53 +08:00
static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
return __dev_map_update_elem(current->nsproxy->net_ns,
map, key, value, map_flags);
}
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map,
void *key, void *value, u64 map_flags)
{
struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
struct bpf_dtab_netdev *dev, *old_dev;
bpf: Devmap adjust uapi for attach bpf program V2: - Defer changing BPF-syscall to start at file-descriptor 1 - Use {} to zero initialise struct. The recent commit fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry"), introduced ability to attach (and run) a separate XDP bpf_prog for each devmap entry. A bpf_prog is added via a file-descriptor. As zero were a valid FD, not using the feature requires using value minus-1. The UAPI is extended via tail-extending struct bpf_devmap_val and using map->value_size to determine the feature set. This will break older userspace applications not using the bpf_prog feature. Consider an old userspace app that is compiled against newer kernel uapi/bpf.h, it will not know that it need to initialise the member bpf_prog.fd to minus-1. Thus, users will be forced to update source code to get program running on newer kernels. This patch remove the minus-1 checks, and have zero mean feature isn't used. Followup patches either for kernel or libbpf should handle and avoid returning file-descriptor zero in the first place. Fixes: fbee97feed9b ("bpf: Add support to attach bpf program to a devmap entry") Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/159170950687.2102545.7235914718298050113.stgit@firesoul
2020-06-09 21:31:46 +08:00
struct bpf_devmap_val val = {};
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
u32 idx = *(u32 *)key;
unsigned long flags;
xdp: Fix race in dev_map_hash_update_elem() when replacing element syzbot found a crash in dev_map_hash_update_elem(), when replacing an element with a new one. Jesper correctly identified the cause of the crash as a race condition between the initial lookup in the map (which is done before taking the lock), and the removal of the old element. Rather than just add a second lookup into the hashmap after taking the lock, fix this by reworking the function logic to take the lock before the initial lookup. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-and-tested-by: syzbot+4e7a85b1432052e8d6f8@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-09-08 16:20:16 +08:00
int err = -EEXIST;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
/* already verified value_size <= sizeof val */
memcpy(&val, value, map->value_size);
if (unlikely(map_flags > BPF_EXIST || !val.ifindex))
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
return -EINVAL;
xdp: Fix race in dev_map_hash_update_elem() when replacing element syzbot found a crash in dev_map_hash_update_elem(), when replacing an element with a new one. Jesper correctly identified the cause of the crash as a race condition between the initial lookup in the map (which is done before taking the lock), and the removal of the old element. Rather than just add a second lookup into the hashmap after taking the lock, fix this by reworking the function logic to take the lock before the initial lookup. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-and-tested-by: syzbot+4e7a85b1432052e8d6f8@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-09-08 16:20:16 +08:00
spin_lock_irqsave(&dtab->index_lock, flags);
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
old_dev = __dev_map_hash_lookup_elem(map, idx);
if (old_dev && (map_flags & BPF_NOEXIST))
xdp: Fix race in dev_map_hash_update_elem() when replacing element syzbot found a crash in dev_map_hash_update_elem(), when replacing an element with a new one. Jesper correctly identified the cause of the crash as a race condition between the initial lookup in the map (which is done before taking the lock), and the removal of the old element. Rather than just add a second lookup into the hashmap after taking the lock, fix this by reworking the function logic to take the lock before the initial lookup. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-and-tested-by: syzbot+4e7a85b1432052e8d6f8@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-09-08 16:20:16 +08:00
goto out_err;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
devmap: Formalize map value as a named struct Add 'struct bpf_devmap_val' to formalize the expected values that can be passed in for a DEVMAP. Update devmap code to use the struct. Signed-off-by: David Ahern <dsahern@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200529220716.75383-2-dsahern@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-30 06:07:12 +08:00
dev = __dev_map_alloc_node(net, dtab, &val, idx);
xdp: Fix race in dev_map_hash_update_elem() when replacing element syzbot found a crash in dev_map_hash_update_elem(), when replacing an element with a new one. Jesper correctly identified the cause of the crash as a race condition between the initial lookup in the map (which is done before taking the lock), and the removal of the old element. Rather than just add a second lookup into the hashmap after taking the lock, fix this by reworking the function logic to take the lock before the initial lookup. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-and-tested-by: syzbot+4e7a85b1432052e8d6f8@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-09-08 16:20:16 +08:00
if (IS_ERR(dev)) {
err = PTR_ERR(dev);
goto out_err;
}
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
if (old_dev) {
hlist_del_rcu(&old_dev->index_hlist);
} else {
if (dtab->items >= dtab->map.max_entries) {
spin_unlock_irqrestore(&dtab->index_lock, flags);
call_rcu(&dev->rcu, __dev_map_entry_free);
return -E2BIG;
}
dtab->items++;
}
hlist_add_head_rcu(&dev->index_hlist,
dev_map_index_hash(dtab, idx));
spin_unlock_irqrestore(&dtab->index_lock, flags);
if (old_dev)
call_rcu(&old_dev->rcu, __dev_map_entry_free);
return 0;
xdp: Fix race in dev_map_hash_update_elem() when replacing element syzbot found a crash in dev_map_hash_update_elem(), when replacing an element with a new one. Jesper correctly identified the cause of the crash as a race condition between the initial lookup in the map (which is done before taking the lock), and the removal of the old element. Rather than just add a second lookup into the hashmap after taking the lock, fix this by reworking the function logic to take the lock before the initial lookup. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-and-tested-by: syzbot+4e7a85b1432052e8d6f8@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-09-08 16:20:16 +08:00
out_err:
spin_unlock_irqrestore(&dtab->index_lock, flags);
return err;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
}
static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
return __dev_map_hash_update_elem(current->nsproxy->net_ns,
map, key, value, map_flags);
}
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
return __bpf_xdp_redirect_map(map, ifindex, flags,
BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
__dev_map_lookup_elem);
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
}
static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
xdp: Extend xdp_redirect_map with broadcast support This patch adds two flags BPF_F_BROADCAST and BPF_F_EXCLUDE_INGRESS to extend xdp_redirect_map for broadcast support. With BPF_F_BROADCAST the packet will be broadcasted to all the interfaces in the map. with BPF_F_EXCLUDE_INGRESS the ingress interface will be excluded when do broadcasting. When getting the devices in dev hash map via dev_map_hash_get_next_key(), there is a possibility that we fall back to the first key when a device was removed. This will duplicate packets on some interfaces. So just walk the whole buckets to avoid this issue. For dev array map, we also walk the whole map to find valid interfaces. Function bpf_clear_redirect_map() was removed in commit ee75aef23afe ("bpf, xdp: Restructure redirect actions"). Add it back as we need to use ri->map again. With test topology: +-------------------+ +-------------------+ | Host A (i40e 10G) | ---------- | eno1(i40e 10G) | +-------------------+ | | | Host B | +-------------------+ | | | Host C (i40e 10G) | ---------- | eno2(i40e 10G) | +-------------------+ | | | +------+ | | veth0 -- | Peer | | | veth1 -- | | | | veth2 -- | NS | | | +------+ | +-------------------+ On Host A: # pktgen/pktgen_sample03_burst_single_flow.sh -i eno1 -d $dst_ip -m $dst_mac -s 64 On Host B(Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz, 128G Memory): Use xdp_redirect_map and xdp_redirect_map_multi in samples/bpf for testing. All the veth peers in the NS have a XDP_DROP program loaded. The forward_map max_entries in xdp_redirect_map_multi is modify to 4. Testing the performance impact on the regular xdp_redirect path with and without patch (to check impact of additional check for broadcast mode): 5.12 rc4 | redirect_map i40e->i40e | 2.0M | 9.7M 5.12 rc4 | redirect_map i40e->veth | 1.7M | 11.8M 5.12 rc4 + patch | redirect_map i40e->i40e | 2.0M | 9.6M 5.12 rc4 + patch | redirect_map i40e->veth | 1.7M | 11.7M Testing the performance when cloning packets with the redirect_map_multi test, using a redirect map size of 4, filled with 1-3 devices: 5.12 rc4 + patch | redirect_map multi i40e->veth (x1) | 1.7M | 11.4M 5.12 rc4 + patch | redirect_map multi i40e->veth (x2) | 1.1M | 4.3M 5.12 rc4 + patch | redirect_map multi i40e->veth (x3) | 0.8M | 2.6M Signed-off-by: Hangbin Liu <liuhangbin@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Link: https://lore.kernel.org/bpf/20210519090747.1655268-3-liuhangbin@gmail.com
2021-05-19 17:07:45 +08:00
return __bpf_xdp_redirect_map(map, ifindex, flags,
BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS,
__dev_map_hash_lookup_elem);
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
}
bpf: Set map_btf_{name, id} for all map types Set map_btf_name and map_btf_id for all map types so that map fields can be accessed by bpf programs. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/a825f808f22af52b018dbe82f1c7d29dab5fc978.1592600985.git.rdna@fb.com
2020-06-20 05:11:44 +08:00
static int dev_map_btf_id;
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
const struct bpf_map_ops dev_map_ops = {
bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
2020-08-28 09:18:06 +08:00
.map_meta_equal = bpf_map_meta_equal,
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
.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,
bpf: decouple btf from seq bpf fs dump and enable more maps Commit a26ca7c982cb ("bpf: btf: Add pretty print support to the basic arraymap") and 699c86d6ec21 ("bpf: btf: add pretty print for hash/lru_hash maps") enabled support for BTF and dumping via BPF fs for array and hash/lru map. However, both can be decoupled from each other such that regular BPF maps can be supported for attaching BTF key/value information, while not all maps necessarily need to dump via map_seq_show_elem() callback. The basic sanity check which is a prerequisite for all maps is that key/value size has to match in any case, and some maps can have extra checks via map_check_btf() callback, e.g. probing certain types or indicating no support in general. With that we can also enable retrieving BTF info for per-cpu map types and lpm. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com>
2018-08-12 07:59:17 +08:00
.map_check_btf = map_check_no_btf,
bpf: Set map_btf_{name, id} for all map types Set map_btf_name and map_btf_id for all map types so that map fields can be accessed by bpf programs. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/a825f808f22af52b018dbe82f1c7d29dab5fc978.1592600985.git.rdna@fb.com
2020-06-20 05:11:44 +08:00
.map_btf_name = "bpf_dtab",
.map_btf_id = &dev_map_btf_id,
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
.map_redirect = dev_map_redirect,
bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:28:56 +08:00
};
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
bpf: Set map_btf_{name, id} for all map types Set map_btf_name and map_btf_id for all map types so that map fields can be accessed by bpf programs. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/a825f808f22af52b018dbe82f1c7d29dab5fc978.1592600985.git.rdna@fb.com
2020-06-20 05:11:44 +08:00
static int dev_map_hash_map_btf_id;
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
const struct bpf_map_ops dev_map_hash_ops = {
bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
2020-08-28 09:18:06 +08:00
.map_meta_equal = bpf_map_meta_equal,
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
.map_alloc = dev_map_alloc,
.map_free = dev_map_free,
.map_get_next_key = dev_map_hash_get_next_key,
.map_lookup_elem = dev_map_hash_lookup_elem,
.map_update_elem = dev_map_hash_update_elem,
.map_delete_elem = dev_map_hash_delete_elem,
.map_check_btf = map_check_no_btf,
bpf: Set map_btf_{name, id} for all map types Set map_btf_name and map_btf_id for all map types so that map fields can be accessed by bpf programs. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/a825f808f22af52b018dbe82f1c7d29dab5fc978.1592600985.git.rdna@fb.com
2020-06-20 05:11:44 +08:00
.map_btf_name = "bpf_dtab",
.map_btf_id = &dev_map_hash_map_btf_id,
bpf, xdp: Make bpf_redirect_map() a map operation Currently the bpf_redirect_map() implementation dispatches to the correct map-lookup function via a switch-statement. To avoid the dispatching, this change adds bpf_redirect_map() as a map operation. Each map provides its bpf_redirect_map() version, and correct function is automatically selected by the BPF verifier. A nice side-effect of the code movement is that the map lookup functions are now local to the map implementation files, which removes one additional function call. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210308112907.559576-2-bjorn.topel@gmail.com
2021-03-08 19:29:06 +08:00
.map_redirect = dev_hash_map_redirect,
xdp: Add devmap_hash map type for looking up devices by hashed index A common pattern when using xdp_redirect_map() is to create a device map where the lookup key is simply ifindex. Because device maps are arrays, this leaves holes in the map, and the map has to be sized to fit the largest ifindex, regardless of how many devices actually are actually needed in the map. This patch adds a second type of device map where the key is looked up using a hashmap, instead of being used as an array index. This allows maps to be densely packed, so they can be smaller. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-07-27 00:06:55 +08:00
};
xdp: Handle device unregister for devmap_hash map type It seems I forgot to add handling of devmap_hash type maps to the device unregister hook for devmaps. This omission causes devices to not be properly released, which causes hangs. Fix this by adding the missing handler. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191019111931.2981954-1-toke@redhat.com
2019-10-19 19:19:31 +08:00
static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
struct net_device *netdev)
{
unsigned long flags;
u32 i;
spin_lock_irqsave(&dtab->index_lock, flags);
for (i = 0; i < dtab->n_buckets; i++) {
struct bpf_dtab_netdev *dev;
struct hlist_head *head;
struct hlist_node *next;
head = dev_map_index_hash(dtab, i);
hlist_for_each_entry_safe(dev, next, head, index_hlist) {
if (netdev != dev->dev)
continue;
dtab->items--;
hlist_del_rcu(&dev->index_hlist);
call_rcu(&dev->rcu, __dev_map_entry_free);
}
}
spin_unlock_irqrestore(&dtab->index_lock, flags);
}
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
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;
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
int i, cpu;
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
switch (event) {
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
case NETDEV_REGISTER:
if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq)
break;
/* will be freed in free_netdev() */
bpf, devmap: Use GFP_KERNEL for xdp bulk queue allocation The devmap bulk queue is allocated with GFP_ATOMIC and the allocation may fail if there is no available space in existing percpu pool. Since commit 75ccae62cb8d42 ("xdp: Move devmap bulk queue into struct net_device") moved the bulk queue allocation to NETDEV_REGISTER callback, whose context is allowed to sleep, use GFP_KERNEL instead of GFP_ATOMIC to let percpu allocator extend the pool when needed and avoid possible failure of netdev registration. As the required alignment is natural, we can simply use alloc_percpu(). Fixes: 75ccae62cb8d42 ("xdp: Move devmap bulk queue into struct net_device") Signed-off-by: Jun'ichi Nomura <junichi.nomura@nec.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210209082451.GA44021@jeru.linux.bs1.fc.nec.co.jp
2021-02-09 16:24:52 +08:00
netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue);
xdp: Move devmap bulk queue into struct net_device Commit 96360004b862 ("xdp: Make devmap flush_list common for all map instances"), changed devmap flushing to be a global operation instead of a per-map operation. However, the queue structure used for bulking was still allocated as part of the containing map. This patch moves the devmap bulk queue into struct net_device. The motivation for this is reusing it for the non-map variant of XDP_REDIRECT, which will be changed in a subsequent commit. To avoid other fields of struct net_device moving to different cache lines, we also move a couple of other members around. We defer the actual allocation of the bulk queue structure until the NETDEV_REGISTER notification devmap.c. This makes it possible to check for ndo_xdp_xmit support before allocating the structure, which is not possible at the time struct net_device is allocated. However, we keep the freeing in free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER. Because of this change, we lose the reference back to the map that originated the redirect, so change the tracepoint to always return 0 as the map ID and index. Otherwise no functional change is intended with this patch. After this patch, the relevant part of struct net_device looks like this, according to pahole: /* --- cacheline 14 boundary (896 bytes) --- */ struct netdev_queue * _tx __attribute__((__aligned__(64))); /* 896 8 */ unsigned int num_tx_queues; /* 904 4 */ unsigned int real_num_tx_queues; /* 908 4 */ struct Qdisc * qdisc; /* 912 8 */ unsigned int tx_queue_len; /* 920 4 */ spinlock_t tx_global_lock; /* 924 4 */ struct xdp_dev_bulk_queue * xdp_bulkq; /* 928 8 */ struct xps_dev_maps * xps_cpus_map; /* 936 8 */ struct xps_dev_maps * xps_rxqs_map; /* 944 8 */ struct mini_Qdisc * miniq_egress; /* 952 8 */ /* --- cacheline 15 boundary (960 bytes) --- */ struct hlist_head qdisc_hash[16]; /* 960 128 */ /* --- cacheline 17 boundary (1088 bytes) --- */ struct timer_list watchdog_timer; /* 1088 40 */ /* XXX last struct has 4 bytes of padding */ int watchdog_timeo; /* 1128 4 */ /* XXX 4 bytes hole, try to pack */ struct list_head todo_list; /* 1136 16 */ /* --- cacheline 18 boundary (1152 bytes) --- */ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk
2020-01-16 23:14:44 +08:00
if (!netdev->xdp_bulkq)
return NOTIFY_BAD;
for_each_possible_cpu(cpu)
per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
break;
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
case NETDEV_UNREGISTER:
bpf: devmap fix mutex in rcu critical section Originally we used a mutex to protect concurrent devmap update and delete operations from racing with netdev unregister notifier callbacks. The notifier hook is needed because we increment the netdev ref count when a dev is added to the devmap. This ensures the netdev reference is valid in the datapath. However, we don't want to block unregister events, hence the initial mutex and notifier handler. The concern was in the notifier hook we search the map for dev entries that hold a refcnt on the net device being torn down. But, in order to do this we require two steps, (i) dereference the netdev: dev = rcu_dereference(map[i]) (ii) test ifindex: dev->ifindex == removing_ifindex and then finally we can swap in the NULL dev in the map via an xchg operation, xchg(map[i], NULL) The danger here is a concurrent update could run a different xchg op concurrently leading us to replace the new dev with a NULL dev incorrectly. CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) xchg(map[i], NULL) The above flow would create the incorrect state with the dev reference in the update path being lost. To resolve this the original code used a mutex around the above block. However, updates, deletes, and lookups occur inside rcu critical sections so we can't use a mutex in this context safely. Fortunately, by writing slightly better code we can avoid the mutex altogether. If CPU 1 in the above example uses a cmpxchg and _only_ replaces the dev reference in the map when it is in fact the expected dev the race is removed completely. The two cases being illustrated here, first the race condition, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) odev = cmpxchg(map[i], dev, NULL) Now we can test the cmpxchg return value, detect odev != dev and abort. Or in the good case, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) odev = cmpxchg(map[i], dev, NULL) [...] Now 'odev == dev' and we can do proper cleanup. And viola the original race we tried to solve with a mutex is corrected and the trace noted by Sasha below is resolved due to removal of the mutex. Note: When walking the devmap and removing dev references as needed we depend on the core to fail any calls to dev_get_by_index() using the ifindex of the device being removed. This way we do not race with the user while searching the devmap. Additionally, the mutex was also protecting list add/del/read on the list of maps in-use. This patch converts this to an RCU list and spinlock implementation. This protects the list from concurrent alloc/free operations. The notifier hook walks this list so it uses RCU read semantics. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747 in_atomic(): 1, irqs_disabled(): 0, pid: 16315, name: syz-executor1 1 lock held by syz-executor1/16315: #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] map_delete_elem kernel/bpf/syscall.c:577 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SYSC_bpf kernel/bpf/syscall.c:1427 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SyS_bpf+0x1d32/0x4ba0 kernel/bpf/syscall.c:1388 Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Reported-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-05 13:02:19 +08:00
/* 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) {
xdp: Handle device unregister for devmap_hash map type It seems I forgot to add handling of devmap_hash type maps to the device unregister hook for devmaps. This omission causes devices to not be properly released, which causes hangs. Fix this by adding the missing handler. Fixes: 6f9d451ab1a3 ("xdp: Add devmap_hash map type for looking up devices by hashed index") Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191019111931.2981954-1-toke@redhat.com
2019-10-19 19:19:31 +08:00
if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
dev_map_hash_remove_netdev(dtab, netdev);
continue;
}
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
for (i = 0; i < dtab->map.max_entries; i++) {
bpf: devmap fix mutex in rcu critical section Originally we used a mutex to protect concurrent devmap update and delete operations from racing with netdev unregister notifier callbacks. The notifier hook is needed because we increment the netdev ref count when a dev is added to the devmap. This ensures the netdev reference is valid in the datapath. However, we don't want to block unregister events, hence the initial mutex and notifier handler. The concern was in the notifier hook we search the map for dev entries that hold a refcnt on the net device being torn down. But, in order to do this we require two steps, (i) dereference the netdev: dev = rcu_dereference(map[i]) (ii) test ifindex: dev->ifindex == removing_ifindex and then finally we can swap in the NULL dev in the map via an xchg operation, xchg(map[i], NULL) The danger here is a concurrent update could run a different xchg op concurrently leading us to replace the new dev with a NULL dev incorrectly. CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) xchg(map[i], NULL) The above flow would create the incorrect state with the dev reference in the update path being lost. To resolve this the original code used a mutex around the above block. However, updates, deletes, and lookups occur inside rcu critical sections so we can't use a mutex in this context safely. Fortunately, by writing slightly better code we can avoid the mutex altogether. If CPU 1 in the above example uses a cmpxchg and _only_ replaces the dev reference in the map when it is in fact the expected dev the race is removed completely. The two cases being illustrated here, first the race condition, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) odev = cmpxchg(map[i], dev, NULL) Now we can test the cmpxchg return value, detect odev != dev and abort. Or in the good case, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) odev = cmpxchg(map[i], dev, NULL) [...] Now 'odev == dev' and we can do proper cleanup. And viola the original race we tried to solve with a mutex is corrected and the trace noted by Sasha below is resolved due to removal of the mutex. Note: When walking the devmap and removing dev references as needed we depend on the core to fail any calls to dev_get_by_index() using the ifindex of the device being removed. This way we do not race with the user while searching the devmap. Additionally, the mutex was also protecting list add/del/read on the list of maps in-use. This patch converts this to an RCU list and spinlock implementation. This protects the list from concurrent alloc/free operations. The notifier hook walks this list so it uses RCU read semantics. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747 in_atomic(): 1, irqs_disabled(): 0, pid: 16315, name: syz-executor1 1 lock held by syz-executor1/16315: #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] map_delete_elem kernel/bpf/syscall.c:577 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SYSC_bpf kernel/bpf/syscall.c:1427 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SyS_bpf+0x1d32/0x4ba0 kernel/bpf/syscall.c:1388 Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Reported-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-05 13:02:19 +08:00
struct bpf_dtab_netdev *dev, *odev;
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
dev = rcu_dereference(dtab->netdev_map[i]);
bpf: devmap: fix wrong interface selection in notifier_call The dev_map_notification() removes interface in devmap if unregistering interface's ifindex is same. But only checking ifindex is not enough because other netns can have same ifindex. so that wrong interface selection could occurred. Hence netdev pointer comparison code is added. v2: compare netdev pointer instead of using net_eq() (Daniel Borkmann) v1: Initial patch Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Signed-off-by: Taehee Yoo <ap420073@gmail.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-10-24 19:15:17 +08:00
if (!dev || netdev != dev->dev)
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
continue;
xdp: Add proper __rcu annotations to redirect map entries XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
2021-06-25 00:05:55 +08:00
odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL));
bpf: devmap fix mutex in rcu critical section Originally we used a mutex to protect concurrent devmap update and delete operations from racing with netdev unregister notifier callbacks. The notifier hook is needed because we increment the netdev ref count when a dev is added to the devmap. This ensures the netdev reference is valid in the datapath. However, we don't want to block unregister events, hence the initial mutex and notifier handler. The concern was in the notifier hook we search the map for dev entries that hold a refcnt on the net device being torn down. But, in order to do this we require two steps, (i) dereference the netdev: dev = rcu_dereference(map[i]) (ii) test ifindex: dev->ifindex == removing_ifindex and then finally we can swap in the NULL dev in the map via an xchg operation, xchg(map[i], NULL) The danger here is a concurrent update could run a different xchg op concurrently leading us to replace the new dev with a NULL dev incorrectly. CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) xchg(map[i], NULL) The above flow would create the incorrect state with the dev reference in the update path being lost. To resolve this the original code used a mutex around the above block. However, updates, deletes, and lookups occur inside rcu critical sections so we can't use a mutex in this context safely. Fortunately, by writing slightly better code we can avoid the mutex altogether. If CPU 1 in the above example uses a cmpxchg and _only_ replaces the dev reference in the map when it is in fact the expected dev the race is removed completely. The two cases being illustrated here, first the race condition, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) odev = cmpxchg(map[i], dev, NULL) Now we can test the cmpxchg return value, detect odev != dev and abort. Or in the good case, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) odev = cmpxchg(map[i], dev, NULL) [...] Now 'odev == dev' and we can do proper cleanup. And viola the original race we tried to solve with a mutex is corrected and the trace noted by Sasha below is resolved due to removal of the mutex. Note: When walking the devmap and removing dev references as needed we depend on the core to fail any calls to dev_get_by_index() using the ifindex of the device being removed. This way we do not race with the user while searching the devmap. Additionally, the mutex was also protecting list add/del/read on the list of maps in-use. This patch converts this to an RCU list and spinlock implementation. This protects the list from concurrent alloc/free operations. The notifier hook walks this list so it uses RCU read semantics. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747 in_atomic(): 1, irqs_disabled(): 0, pid: 16315, name: syz-executor1 1 lock held by syz-executor1/16315: #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] map_delete_elem kernel/bpf/syscall.c:577 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SYSC_bpf kernel/bpf/syscall.c:1427 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SyS_bpf+0x1d32/0x4ba0 kernel/bpf/syscall.c:1388 Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Reported-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-05 13:02:19 +08:00
if (dev == odev)
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
call_rcu(&dev->rcu,
__dev_map_entry_free);
}
}
bpf: devmap fix mutex in rcu critical section Originally we used a mutex to protect concurrent devmap update and delete operations from racing with netdev unregister notifier callbacks. The notifier hook is needed because we increment the netdev ref count when a dev is added to the devmap. This ensures the netdev reference is valid in the datapath. However, we don't want to block unregister events, hence the initial mutex and notifier handler. The concern was in the notifier hook we search the map for dev entries that hold a refcnt on the net device being torn down. But, in order to do this we require two steps, (i) dereference the netdev: dev = rcu_dereference(map[i]) (ii) test ifindex: dev->ifindex == removing_ifindex and then finally we can swap in the NULL dev in the map via an xchg operation, xchg(map[i], NULL) The danger here is a concurrent update could run a different xchg op concurrently leading us to replace the new dev with a NULL dev incorrectly. CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) xchg(map[i], NULL) The above flow would create the incorrect state with the dev reference in the update path being lost. To resolve this the original code used a mutex around the above block. However, updates, deletes, and lookups occur inside rcu critical sections so we can't use a mutex in this context safely. Fortunately, by writing slightly better code we can avoid the mutex altogether. If CPU 1 in the above example uses a cmpxchg and _only_ replaces the dev reference in the map when it is in fact the expected dev the race is removed completely. The two cases being illustrated here, first the race condition, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) dev = rcu_dereference(map[i]) xchg(map[i]), new_dev); rcu_call(dev,...) odev = cmpxchg(map[i], dev, NULL) Now we can test the cmpxchg return value, detect odev != dev and abort. Or in the good case, CPU 1 CPU 2 notifier hook bpf devmap update dev = rcu_dereference(map[i]) odev = cmpxchg(map[i], dev, NULL) [...] Now 'odev == dev' and we can do proper cleanup. And viola the original race we tried to solve with a mutex is corrected and the trace noted by Sasha below is resolved due to removal of the mutex. Note: When walking the devmap and removing dev references as needed we depend on the core to fail any calls to dev_get_by_index() using the ifindex of the device being removed. This way we do not race with the user while searching the devmap. Additionally, the mutex was also protecting list add/del/read on the list of maps in-use. This patch converts this to an RCU list and spinlock implementation. This protects the list from concurrent alloc/free operations. The notifier hook walks this list so it uses RCU read semantics. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:747 in_atomic(): 1, irqs_disabled(): 0, pid: 16315, name: syz-executor1 1 lock held by syz-executor1/16315: #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] map_delete_elem kernel/bpf/syscall.c:577 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SYSC_bpf kernel/bpf/syscall.c:1427 [inline] #0: (rcu_read_lock){......}, at: [<ffffffff8c363bc2>] SyS_bpf+0x1d32/0x4ba0 kernel/bpf/syscall.c:1388 Fixes: 2ddf71e23cc2 ("net: add notifier hooks for devmap bpf map") Reported-by: Sasha Levin <alexander.levin@verizon.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-05 13:02:19 +08:00
rcu_read_unlock();
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
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)
{
xdp: Make devmap flush_list common for all map instances The devmap flush list is used to track entries that need to flushed from via the xdp_do_flush_map() function. This list used to be per-map, but there is really no reason for that. Instead make the flush list global for all devmaps, which simplifies __dev_map_flush() and dev_map_init_map(). Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20191219061006.21980-6-bjorn.topel@gmail.com
2019-12-19 14:10:03 +08:00
int cpu;
bpf: devmap introduce dev_map_enqueue Functionality is the same, but the ndo_xdp_xmit call is now simply invoked from inside the devmap.c code. V2: Fix compile issue reported by kbuild test robot <lkp@intel.com> V5: Cleanups requested by Daniel - Newlines before func definition - Use BUILD_BUG_ON checks - Remove unnecessary use return value store in dev_map_enqueue Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-24 22:45:46 +08:00
/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
offsetof(struct _bpf_dtab_netdev, dev));
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
register_netdevice_notifier(&dev_map_notifier);
xdp: Make devmap flush_list common for all map instances The devmap flush list is used to track entries that need to flushed from via the xdp_do_flush_map() function. This list used to be per-map, but there is really no reason for that. Instead make the flush list global for all devmaps, which simplifies __dev_map_flush() and dev_map_init_map(). Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20191219061006.21980-6-bjorn.topel@gmail.com
2019-12-19 14:10:03 +08:00
for_each_possible_cpu(cpu)
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 23:14:45 +08:00
INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-18 00:30:02 +08:00
return 0;
}
subsys_initcall(dev_map_init);
Reference in New Issue Copy Permalink