diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-06 18:39:49 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-06 18:39:49 -0700 |
commit | 1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21 (patch) | |
tree | dcc97181d4d187252e0cc8fdf29d9b365fa3ffd0 /net/xdp/xdp_umem.c | |
parent | 285767604576148fc1be7fcd112e4a90eb0d6ad2 (diff) | |
parent | 7170e6045a6a8b33f4fa5753589dc77b16198e2d (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Add Maglev hashing scheduler to IPVS, from Inju Song.
2) Lots of new TC subsystem tests from Roman Mashak.
3) Add TCP zero copy receive and fix delayed acks and autotuning with
SO_RCVLOWAT, from Eric Dumazet.
4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
Brouer.
5) Add ttl inherit support to vxlan, from Hangbin Liu.
6) Properly separate ipv6 routes into their logically independant
components. fib6_info for the routing table, and fib6_nh for sets of
nexthops, which thus can be shared. From David Ahern.
7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
messages from XDP programs. From Nikita V. Shirokov.
8) Lots of long overdue cleanups to the r8169 driver, from Heiner
Kallweit.
9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.
10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.
11) Plumb extack down into fib_rules, from Roopa Prabhu.
12) Add Flower classifier offload support to igb, from Vinicius Costa
Gomes.
13) Add UDP GSO support, from Willem de Bruijn.
14) Add documentation for eBPF helpers, from Quentin Monnet.
15) Add TLS tx offload to mlx5, from Ilya Lesokhin.
16) Allow applications to be given the number of bytes available to read
on a socket via a control message returned from recvmsg(), from
Soheil Hassas Yeganeh.
17) Add x86_32 eBPF JIT compiler, from Wang YanQing.
18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
From Björn Töpel.
19) Remove indirect load support from all of the BPF JITs and handle
these operations in the verifier by translating them into native BPF
instead. From Daniel Borkmann.
20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.
21) Allow XDP programs to do lookups in the main kernel routing tables
for forwarding. From David Ahern.
22) Allow drivers to store hardware state into an ELF section of kernel
dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.
23) Various RACK and loss detection improvements in TCP, from Yuchung
Cheng.
24) Add TCP SACK compression, from Eric Dumazet.
25) Add User Mode Helper support and basic bpfilter infrastructure, from
Alexei Starovoitov.
26) Support ports and protocol values in RTM_GETROUTE, from Roopa
Prabhu.
27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
Brouer.
28) Add lots of forwarding selftests, from Petr Machata.
29) Add generic network device failover driver, from Sridhar Samudrala.
* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
strparser: Add __strp_unpause and use it in ktls.
rxrpc: Fix terminal retransmission connection ID to include the channel
net: hns3: Optimize PF CMDQ interrupt switching process
net: hns3: Fix for VF mailbox receiving unknown message
net: hns3: Fix for VF mailbox cannot receiving PF response
bnx2x: use the right constant
Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
enic: fix UDP rss bits
netdev-FAQ: clarify DaveM's position for stable backports
rtnetlink: validate attributes in do_setlink()
mlxsw: Add extack messages for port_{un, }split failures
netdevsim: Add extack error message for devlink reload
devlink: Add extack to reload and port_{un, }split operations
net: metrics: add proper netlink validation
ipmr: fix error path when ipmr_new_table fails
ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
net: hns3: remove unused hclgevf_cfg_func_mta_filter
netfilter: provide udp*_lib_lookup for nf_tproxy
qed*: Utilize FW 8.37.2.0
...
Diffstat (limited to 'net/xdp/xdp_umem.c')
-rw-r--r-- | net/xdp/xdp_umem.c | 361 |
1 files changed, 361 insertions, 0 deletions
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c new file mode 100644 index 000000000000..7eb4948a38d2 --- /dev/null +++ b/net/xdp/xdp_umem.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + */ + +#include <linux/init.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include <linux/mm.h> + +#include "xdp_umem.h" +#include "xsk_queue.h" + +#define XDP_UMEM_MIN_CHUNK_SIZE 2048 + +void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) +{ + unsigned long flags; + + spin_lock_irqsave(&umem->xsk_list_lock, flags); + list_add_rcu(&xs->list, &umem->xsk_list); + spin_unlock_irqrestore(&umem->xsk_list_lock, flags); +} + +void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) +{ + unsigned long flags; + + if (xs->dev) { + spin_lock_irqsave(&umem->xsk_list_lock, flags); + list_del_rcu(&xs->list); + spin_unlock_irqrestore(&umem->xsk_list_lock, flags); + + if (umem->zc) + synchronize_net(); + } +} + +int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, + u32 queue_id, u16 flags) +{ + bool force_zc, force_copy; + struct netdev_bpf bpf; + int err; + + force_zc = flags & XDP_ZEROCOPY; + force_copy = flags & XDP_COPY; + + if (force_zc && force_copy) + return -EINVAL; + + if (force_copy) + return 0; + + dev_hold(dev); + + if (dev->netdev_ops->ndo_bpf && dev->netdev_ops->ndo_xsk_async_xmit) { + bpf.command = XDP_QUERY_XSK_UMEM; + + rtnl_lock(); + err = dev->netdev_ops->ndo_bpf(dev, &bpf); + rtnl_unlock(); + + if (err) { + dev_put(dev); + return force_zc ? -ENOTSUPP : 0; + } + + bpf.command = XDP_SETUP_XSK_UMEM; + bpf.xsk.umem = umem; + bpf.xsk.queue_id = queue_id; + + rtnl_lock(); + err = dev->netdev_ops->ndo_bpf(dev, &bpf); + rtnl_unlock(); + + if (err) { + dev_put(dev); + return force_zc ? err : 0; /* fail or fallback */ + } + + umem->dev = dev; + umem->queue_id = queue_id; + umem->zc = true; + return 0; + } + + dev_put(dev); + return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ +} + +static void xdp_umem_clear_dev(struct xdp_umem *umem) +{ + struct netdev_bpf bpf; + int err; + + if (umem->dev) { + bpf.command = XDP_SETUP_XSK_UMEM; + bpf.xsk.umem = NULL; + bpf.xsk.queue_id = umem->queue_id; + + rtnl_lock(); + err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); + rtnl_unlock(); + + if (err) + WARN(1, "failed to disable umem!\n"); + + dev_put(umem->dev); + umem->dev = NULL; + } +} + +static void xdp_umem_unpin_pages(struct xdp_umem *umem) +{ + unsigned int i; + + for (i = 0; i < umem->npgs; i++) { + struct page *page = umem->pgs[i]; + + set_page_dirty_lock(page); + put_page(page); + } + + kfree(umem->pgs); + umem->pgs = NULL; +} + +static void xdp_umem_unaccount_pages(struct xdp_umem *umem) +{ + atomic_long_sub(umem->npgs, &umem->user->locked_vm); + free_uid(umem->user); +} + +static void xdp_umem_release(struct xdp_umem *umem) +{ + struct task_struct *task; + struct mm_struct *mm; + + xdp_umem_clear_dev(umem); + + if (umem->fq) { + xskq_destroy(umem->fq); + umem->fq = NULL; + } + + if (umem->cq) { + xskq_destroy(umem->cq); + umem->cq = NULL; + } + + xdp_umem_unpin_pages(umem); + + task = get_pid_task(umem->pid, PIDTYPE_PID); + put_pid(umem->pid); + if (!task) + goto out; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + goto out; + + mmput(mm); + kfree(umem->pages); + umem->pages = NULL; + + xdp_umem_unaccount_pages(umem); +out: + kfree(umem); +} + +static void xdp_umem_release_deferred(struct work_struct *work) +{ + struct xdp_umem *umem = container_of(work, struct xdp_umem, work); + + xdp_umem_release(umem); +} + +void xdp_get_umem(struct xdp_umem *umem) +{ + refcount_inc(&umem->users); +} + +void xdp_put_umem(struct xdp_umem *umem) +{ + if (!umem) + return; + + if (refcount_dec_and_test(&umem->users)) { + INIT_WORK(&umem->work, xdp_umem_release_deferred); + schedule_work(&umem->work); + } +} + +static int xdp_umem_pin_pages(struct xdp_umem *umem) +{ + unsigned int gup_flags = FOLL_WRITE; + long npgs; + int err; + + umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL); + if (!umem->pgs) + return -ENOMEM; + + down_write(¤t->mm->mmap_sem); + npgs = get_user_pages(umem->address, umem->npgs, + gup_flags, &umem->pgs[0], NULL); + up_write(¤t->mm->mmap_sem); + + if (npgs != umem->npgs) { + if (npgs >= 0) { + umem->npgs = npgs; + err = -ENOMEM; + goto out_pin; + } + err = npgs; + goto out_pgs; + } + return 0; + +out_pin: + xdp_umem_unpin_pages(umem); +out_pgs: + kfree(umem->pgs); + umem->pgs = NULL; + return err; +} + +static int xdp_umem_account_pages(struct xdp_umem *umem) +{ + unsigned long lock_limit, new_npgs, old_npgs; + + if (capable(CAP_IPC_LOCK)) + return 0; + + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + umem->user = get_uid(current_user()); + + do { + old_npgs = atomic_long_read(&umem->user->locked_vm); + new_npgs = old_npgs + umem->npgs; + if (new_npgs > lock_limit) { + free_uid(umem->user); + umem->user = NULL; + return -ENOBUFS; + } + } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs, + new_npgs) != old_npgs); + return 0; +} + +static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) +{ + u32 chunk_size = mr->chunk_size, headroom = mr->headroom; + unsigned int chunks, chunks_per_page; + u64 addr = mr->addr, size = mr->len; + int size_chk, err, i; + + if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { + /* Strictly speaking we could support this, if: + * - huge pages, or* + * - using an IOMMU, or + * - making sure the memory area is consecutive + * but for now, we simply say "computer says no". + */ + return -EINVAL; + } + + if (!is_power_of_2(chunk_size)) + return -EINVAL; + + if (!PAGE_ALIGNED(addr)) { + /* Memory area has to be page size aligned. For + * simplicity, this might change. + */ + return -EINVAL; + } + + if ((addr + size) < addr) + return -EINVAL; + + chunks = (unsigned int)div_u64(size, chunk_size); + if (chunks == 0) + return -EINVAL; + + chunks_per_page = PAGE_SIZE / chunk_size; + if (chunks < chunks_per_page || chunks % chunks_per_page) + return -EINVAL; + + headroom = ALIGN(headroom, 64); + + size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; + if (size_chk < 0) + return -EINVAL; + + umem->pid = get_task_pid(current, PIDTYPE_PID); + umem->address = (unsigned long)addr; + umem->props.chunk_mask = ~((u64)chunk_size - 1); + umem->props.size = size; + umem->headroom = headroom; + umem->chunk_size_nohr = chunk_size - headroom; + umem->npgs = size / PAGE_SIZE; + umem->pgs = NULL; + umem->user = NULL; + INIT_LIST_HEAD(&umem->xsk_list); + spin_lock_init(&umem->xsk_list_lock); + + refcount_set(&umem->users, 1); + + err = xdp_umem_account_pages(umem); + if (err) + goto out; + + err = xdp_umem_pin_pages(umem); + if (err) + goto out_account; + + umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL); + if (!umem->pages) { + err = -ENOMEM; + goto out_account; + } + + for (i = 0; i < umem->npgs; i++) + umem->pages[i].addr = page_address(umem->pgs[i]); + + return 0; + +out_account: + xdp_umem_unaccount_pages(umem); +out: + put_pid(umem->pid); + return err; +} + +struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) +{ + struct xdp_umem *umem; + int err; + + umem = kzalloc(sizeof(*umem), GFP_KERNEL); + if (!umem) + return ERR_PTR(-ENOMEM); + + err = xdp_umem_reg(umem, mr); + if (err) { + kfree(umem); + return ERR_PTR(err); + } + + return umem; +} + +bool xdp_umem_validate_queues(struct xdp_umem *umem) +{ + return umem->fq && umem->cq; +} |