diff options
author | David S. Miller <davem@davemloft.net> | 2019-09-06 17:49:17 +0300 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-09-06 17:49:17 +0300 |
commit | 1e46c09ec10049a9e366153b32e41cc557383fdb (patch) | |
tree | b2f86d40fd1ddf32522b5dd1792158daeab72e21 /net | |
parent | f9bcfe214b00c37a6a8e21cab030503fdfd29aca (diff) | |
parent | 593f191a8005110e20302039834c116676d69be1 (diff) | |
download | linux-1e46c09ec10049a9e366153b32e41cc557383fdb.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Add the ability to use unaligned chunks in the AF_XDP umem. By
relaxing where the chunks can be placed, it allows to use an
arbitrary buffer size and place whenever there is a free
address in the umem. Helps more seamless DPDK AF_XDP driver
integration. Support for i40e, ixgbe and mlx5e, from Kevin and
Maxim.
2) Addition of a wakeup flag for AF_XDP tx and fill rings so the
application can wake up the kernel for rx/tx processing which
avoids busy-spinning of the latter, useful when app and driver
is located on the same core. Support for i40e, ixgbe and mlx5e,
from Magnus and Maxim.
3) bpftool fixes for printf()-like functions so compiler can actually
enforce checks, bpftool build system improvements for custom output
directories, and addition of 'bpftool map freeze' command, from Quentin.
4) Support attaching/detaching XDP programs from 'bpftool net' command,
from Daniel.
5) Automatic xskmap cleanup when AF_XDP socket is released, and several
barrier/{read,write}_once fixes in AF_XDP code, from Björn.
6) Relicense of bpf_helpers.h/bpf_endian.h for future libbpf
inclusion as well as libbpf versioning improvements, from Andrii.
7) Several new BPF kselftests for verifier precision tracking, from Alexei.
8) Several BPF kselftest fixes wrt endianess to run on s390x, from Ilya.
9) And more BPF kselftest improvements all over the place, from Stanislav.
10) Add simple BPF map op cache for nfp driver to batch dumps, from Jakub.
11) AF_XDP socket umem mapping improvements for 32bit archs, from Ivan.
12) Add BPF-to-BPF call and BTF line info support for s390x JIT, from Yauheni.
13) Small optimization in arm64 JIT to spare 1 insns for BPF_MOD, from Jerin.
14) Fix an error check in bpf_tcp_gen_syncookie() helper, from Petar.
15) Various minor fixes and cleanups, from Nathan, Masahiro, Masanari,
Peter, Wei, Yue.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/core/bpf_sk_storage.c | 104 | ||||
-rw-r--r-- | net/core/dev.c | 15 | ||||
-rw-r--r-- | net/core/filter.c | 2 | ||||
-rw-r--r-- | net/core/sock.c | 9 | ||||
-rw-r--r-- | net/xdp/xdp_umem.c | 67 | ||||
-rw-r--r-- | net/xdp/xsk.c | 349 | ||||
-rw-r--r-- | net/xdp/xsk.h | 13 | ||||
-rw-r--r-- | net/xdp/xsk_diag.c | 5 | ||||
-rw-r--r-- | net/xdp/xsk_queue.h | 71 |
9 files changed, 550 insertions, 85 deletions
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94c7f77ecb6b..da5639a5bd3b 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -12,6 +12,9 @@ static atomic_t cache_idx; +#define SK_STORAGE_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_CLONE) + struct bucket { struct hlist_head list; raw_spinlock_t lock; @@ -209,7 +212,6 @@ static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) kfree_rcu(sk_storage, rcu); } -/* sk_storage->lock must be held and sk_storage->list cannot be empty */ static void __selem_link_sk(struct bpf_sk_storage *sk_storage, struct bpf_sk_storage_elem *selem) { @@ -509,7 +511,7 @@ static int sk_storage_delete(struct sock *sk, struct bpf_map *map) return 0; } -/* Called by __sk_destruct() */ +/* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { struct bpf_sk_storage_elem *selem; @@ -557,6 +559,11 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) smap = (struct bpf_sk_storage_map *)map; + /* Note that this map might be concurrently cloned from + * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone + * RCU read section to finish before proceeding. New RCU + * read sections should be prevented via bpf_map_inc_not_zero. + */ synchronize_rcu(); /* bpf prog and the userspace can no longer access this map @@ -601,7 +608,9 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) { - if (attr->map_flags != BPF_F_NO_PREALLOC || attr->max_entries || + if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || + !(attr->map_flags & BPF_F_NO_PREALLOC) || + attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || /* Enforce BTF for userspace sk dumping */ !attr->btf_key_type_id || !attr->btf_value_type_id) @@ -739,6 +748,95 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) return err; } +static struct bpf_sk_storage_elem * +bpf_sk_storage_clone_elem(struct sock *newsk, + struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage_elem *copy_selem; + + copy_selem = selem_alloc(smap, newsk, NULL, true); + if (!copy_selem) + return NULL; + + if (map_value_has_spin_lock(&smap->map)) + copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, + SDATA(selem)->data, true); + else + copy_map_value(&smap->map, SDATA(copy_selem)->data, + SDATA(selem)->data); + + return copy_selem; +} + +int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) +{ + struct bpf_sk_storage *new_sk_storage = NULL; + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_elem *selem; + int ret = 0; + + RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); + + rcu_read_lock(); + sk_storage = rcu_dereference(sk->sk_bpf_storage); + + if (!sk_storage || hlist_empty(&sk_storage->list)) + goto out; + + hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { + struct bpf_sk_storage_elem *copy_selem; + struct bpf_sk_storage_map *smap; + struct bpf_map *map; + + smap = rcu_dereference(SDATA(selem)->smap); + if (!(smap->map.map_flags & BPF_F_CLONE)) + continue; + + /* Note that for lockless listeners adding new element + * here can race with cleanup in bpf_sk_storage_map_free. + * Try to grab map refcnt to make sure that it's still + * alive and prevent concurrent removal. + */ + map = bpf_map_inc_not_zero(&smap->map, false); + if (IS_ERR(map)) + continue; + + copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem); + if (!copy_selem) { + ret = -ENOMEM; + bpf_map_put(map); + goto out; + } + + if (new_sk_storage) { + selem_link_map(smap, copy_selem); + __selem_link_sk(new_sk_storage, copy_selem); + } else { + ret = sk_storage_alloc(newsk, smap, copy_selem); + if (ret) { + kfree(copy_selem); + atomic_sub(smap->elem_size, + &newsk->sk_omem_alloc); + bpf_map_put(map); + goto out; + } + + new_sk_storage = rcu_dereference(copy_selem->sk_storage); + } + bpf_map_put(map); + } + +out: + rcu_read_unlock(); + + /* In case of an error, don't free anything explicitly here, the + * caller is responsible to call bpf_sk_storage_free. + */ + + return ret; +} + BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { diff --git a/net/core/dev.c b/net/core/dev.c index 49589ed2018d..b1afafee3e2a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8126,12 +8126,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_chk = generic_xdp_install; if (fd >= 0) { + u32 prog_id; + if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); return -EEXIST; } - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_query(dev, bpf_op, query)) { + + prog_id = __dev_xdp_query(dev, bpf_op, query); + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } @@ -8146,6 +8149,14 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_prog_put(prog); return -EINVAL; } + + if (prog->aux->id == prog_id) { + bpf_prog_put(prog); + return 0; + } + } else { + if (!__dev_xdp_query(dev, bpf_op, query)) + return 0; } err = dev_xdp_install(dev, bpf_op, extack, flags, prog); diff --git a/net/core/filter.c b/net/core/filter.c index b91988f8b94e..ed6563622ce3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5903,7 +5903,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, default: return -EPROTONOSUPPORT; } - if (mss <= 0) + if (mss == 0) return -ENOENT; return cookie | ((u64)mss << 32); diff --git a/net/core/sock.c b/net/core/sock.c index 545fac19a711..07863edbe6fc 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1851,9 +1851,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) goto out; } RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL); -#ifdef CONFIG_BPF_SYSCALL - RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); -#endif + + if (bpf_sk_storage_clone(sk, newsk)) { + sk_free_unlock_clone(newsk); + newsk = NULL; + goto out; + } newsk->sk_err = 0; newsk->sk_err_soft = 0; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 0e0062127124..947b8ff0227e 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -14,7 +14,7 @@ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/idr.h> -#include <linux/highmem.h> +#include <linux/vmalloc.h> #include "xdp_umem.h" #include "xsk_queue.h" @@ -106,14 +106,22 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, umem->dev = dev; umem->queue_id = queue_id; + if (flags & XDP_USE_NEED_WAKEUP) { + umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; + /* Tx needs to be explicitly woken up the first time. + * Also for supporting drivers that do not implement this + * feature. They will always have to call sendto(). + */ + xsk_set_tx_need_wakeup(umem); + } + dev_hold(dev); if (force_copy) /* For copy-mode, we are done. */ return 0; - if (!dev->netdev_ops->ndo_bpf || - !dev->netdev_ops->ndo_xsk_async_xmit) { + if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { err = -EOPNOTSUPP; goto err_unreg_umem; } @@ -170,7 +178,30 @@ static void xdp_umem_unmap_pages(struct xdp_umem *umem) unsigned int i; for (i = 0; i < umem->npgs; i++) - kunmap(umem->pgs[i]); + if (PageHighMem(umem->pgs[i])) + vunmap(umem->pages[i].addr); +} + +static int xdp_umem_map_pages(struct xdp_umem *umem) +{ + unsigned int i; + void *addr; + + for (i = 0; i < umem->npgs; i++) { + if (PageHighMem(umem->pgs[i])) + addr = vmap(&umem->pgs[i], 1, VM_MAP, PAGE_KERNEL); + else + addr = page_address(umem->pgs[i]); + + if (!addr) { + xdp_umem_unmap_pages(umem); + return -ENOMEM; + } + + umem->pages[i].addr = addr; + } + + return 0; } static void xdp_umem_unpin_pages(struct xdp_umem *umem) @@ -309,10 +340,11 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { + bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; 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; + int size_chk, err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: @@ -324,7 +356,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (!is_power_of_2(chunk_size)) + if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG | + XDP_UMEM_USES_NEED_WAKEUP)) + return -EINVAL; + + if (!unaligned_chunks && !is_power_of_2(chunk_size)) return -EINVAL; if (!PAGE_ALIGNED(addr)) { @@ -341,9 +377,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (chunks == 0) return -EINVAL; - chunks_per_page = PAGE_SIZE / chunk_size; - if (chunks < chunks_per_page || chunks % chunks_per_page) - return -EINVAL; + if (!unaligned_chunks) { + chunks_per_page = PAGE_SIZE / chunk_size; + if (chunks < chunks_per_page || chunks % chunks_per_page) + return -EINVAL; + } headroom = ALIGN(headroom, 64); @@ -352,13 +390,15 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; umem->address = (unsigned long)addr; - umem->chunk_mask = ~((u64)chunk_size - 1); + umem->chunk_mask = unaligned_chunks ? XSK_UNALIGNED_BUF_ADDR_MASK + : ~((u64)chunk_size - 1); umem->size = size; umem->headroom = headroom; umem->chunk_size_nohr = chunk_size - headroom; umem->npgs = size / PAGE_SIZE; umem->pgs = NULL; umem->user = NULL; + umem->flags = mr->flags; INIT_LIST_HEAD(&umem->xsk_list); spin_lock_init(&umem->xsk_list_lock); @@ -378,10 +418,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) goto out_pin; } - for (i = 0; i < umem->npgs; i++) - umem->pages[i].addr = kmap(umem->pgs[i]); + err = xdp_umem_map_pages(umem); + if (!err) + return 0; - return 0; + kfree(umem->pages); out_pin: xdp_umem_unpin_pages(umem); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 59b57d708697..c2f1af3b6a7c 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -45,7 +45,7 @@ EXPORT_SYMBOL(xsk_umem_has_addrs); u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { - return xskq_peek_addr(umem->fq, addr); + return xskq_peek_addr(umem->fq, addr, umem); } EXPORT_SYMBOL(xsk_umem_peek_addr); @@ -55,21 +55,103 @@ void xsk_umem_discard_addr(struct xdp_umem *umem) } EXPORT_SYMBOL(xsk_umem_discard_addr); +void xsk_set_rx_need_wakeup(struct xdp_umem *umem) +{ + if (umem->need_wakeup & XDP_WAKEUP_RX) + return; + + umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP; + umem->need_wakeup |= XDP_WAKEUP_RX; +} +EXPORT_SYMBOL(xsk_set_rx_need_wakeup); + +void xsk_set_tx_need_wakeup(struct xdp_umem *umem) +{ + struct xdp_sock *xs; + + if (umem->need_wakeup & XDP_WAKEUP_TX) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; + } + rcu_read_unlock(); + + umem->need_wakeup |= XDP_WAKEUP_TX; +} +EXPORT_SYMBOL(xsk_set_tx_need_wakeup); + +void xsk_clear_rx_need_wakeup(struct xdp_umem *umem) +{ + if (!(umem->need_wakeup & XDP_WAKEUP_RX)) + return; + + umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; + umem->need_wakeup &= ~XDP_WAKEUP_RX; +} +EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); + +void xsk_clear_tx_need_wakeup(struct xdp_umem *umem) +{ + struct xdp_sock *xs; + + if (!(umem->need_wakeup & XDP_WAKEUP_TX)) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP; + } + rcu_read_unlock(); + + umem->need_wakeup &= ~XDP_WAKEUP_TX; +} +EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); + +bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem) +{ + return umem->flags & XDP_UMEM_USES_NEED_WAKEUP; +} +EXPORT_SYMBOL(xsk_umem_uses_need_wakeup); + +/* If a buffer crosses a page boundary, we need to do 2 memcpy's, one for + * each page. This is only required in copy mode. + */ +static void __xsk_rcv_memcpy(struct xdp_umem *umem, u64 addr, void *from_buf, + u32 len, u32 metalen) +{ + void *to_buf = xdp_umem_get_data(umem, addr); + + addr = xsk_umem_add_offset_to_addr(addr); + if (xskq_crosses_non_contig_pg(umem, addr, len + metalen)) { + void *next_pg_addr = umem->pages[(addr >> PAGE_SHIFT) + 1].addr; + u64 page_start = addr & ~(PAGE_SIZE - 1); + u64 first_len = PAGE_SIZE - (addr - page_start); + + memcpy(to_buf, from_buf, first_len + metalen); + memcpy(next_pg_addr, from_buf + first_len, len - first_len); + + return; + } + + memcpy(to_buf, from_buf, len + metalen); +} + static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { - void *to_buf, *from_buf; + u64 offset = xs->umem->headroom; + u64 addr, memcpy_addr; + void *from_buf; u32 metalen; - u64 addr; int err; - if (!xskq_peek_addr(xs->umem->fq, &addr) || + if (!xskq_peek_addr(xs->umem->fq, &addr, xs->umem) || len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } - addr += xs->umem->headroom; - if (unlikely(xdp_data_meta_unsupported(xdp))) { from_buf = xdp->data; metalen = 0; @@ -78,9 +160,11 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) metalen = xdp->data - xdp->data_meta; } - to_buf = xdp_umem_get_data(xs->umem, addr); - memcpy(to_buf, from_buf, len + metalen); - addr += metalen; + memcpy_addr = xsk_umem_adjust_offset(xs->umem, addr, offset); + __xsk_rcv_memcpy(xs->umem, memcpy_addr, from_buf, len, metalen); + + offset += metalen; + addr = xsk_umem_adjust_offset(xs->umem, addr, offset); err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -102,10 +186,23 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) return err; } +static bool xsk_is_bound(struct xdp_sock *xs) +{ + if (READ_ONCE(xs->state) == XSK_BOUND) { + /* Matches smp_wmb() in bind(). */ + smp_rmb(); + return true; + } + return false; +} + int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 len; + if (!xsk_is_bound(xs)) + return -EINVAL; + if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) return -EINVAL; @@ -125,6 +222,7 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 metalen = xdp->data - xdp->data_meta; u32 len = xdp->data_end - xdp->data; + u64 offset = xs->umem->headroom; void *buffer; u64 addr; int err; @@ -136,17 +234,17 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) goto out_unlock; } - if (!xskq_peek_addr(xs->umem->fq, &addr) || + if (!xskq_peek_addr(xs->umem->fq, &addr, xs->umem) || len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { err = -ENOSPC; goto out_drop; } - addr += xs->umem->headroom; - + addr = xsk_umem_adjust_offset(xs->umem, addr, offset); buffer = xdp_umem_get_data(xs->umem, addr); memcpy(buffer, xdp->data_meta, len + metalen); - addr += metalen; + + addr = xsk_umem_adjust_offset(xs->umem, addr, metalen); err = xskq_produce_batch_desc(xs->rx, addr, len); if (err) goto out_drop; @@ -190,7 +288,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { - if (!xskq_peek_desc(xs->tx, desc)) + if (!xskq_peek_desc(xs->tx, desc, umem)) continue; if (xskq_produce_addr_lazy(umem->cq, desc->addr)) @@ -212,7 +310,8 @@ static int xsk_zc_xmit(struct sock *sk) struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev = xs->dev; - return dev->netdev_ops->ndo_xsk_async_xmit(dev, xs->queue_id); + return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, + XDP_WAKEUP_TX); } static void xsk_destruct_skb(struct sk_buff *skb) @@ -243,7 +342,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - while (xskq_peek_desc(xs->tx, &desc)) { + while (xskq_peek_desc(xs->tx, &desc, xs->umem)) { char *buffer; u64 addr; u32 len; @@ -272,7 +371,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, skb->dev = xs->dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_shinfo(skb)->destructor_arg = (void *)(long)addr; + skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; err = dev_direct_xmit(skb, xs->queue_id); @@ -301,7 +400,7 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); - if (unlikely(!xs->dev)) + if (unlikely(!xsk_is_bound(xs))) return -ENXIO; if (unlikely(!(xs->dev->flags & IFF_UP))) return -ENETDOWN; @@ -317,8 +416,19 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { unsigned int mask = datagram_poll(file, sock, wait); - struct sock *sk = sock->sk; - struct xdp_sock *xs = xdp_sk(sk); + struct xdp_sock *xs = xdp_sk(sock->sk); + struct net_device *dev; + struct xdp_umem *umem; + + if (unlikely(!xsk_is_bound(xs))) + return mask; + + dev = xs->dev; + umem = xs->umem; + + if (umem->need_wakeup) + dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, + umem->need_wakeup); if (xs->rx && !xskq_empty_desc(xs->rx)) mask |= POLLIN | POLLRDNORM; @@ -342,7 +452,7 @@ static int xsk_init_queue(u32 entries, struct xsk_queue **queue, /* Make sure queue is ready before it can be seen by others */ smp_wmb(); - *queue = q; + WRITE_ONCE(*queue, q); return 0; } @@ -350,10 +460,9 @@ static void xsk_unbind_dev(struct xdp_sock *xs) { struct net_device *dev = xs->dev; - if (!dev || xs->state != XSK_BOUND) + if (xs->state != XSK_BOUND) return; - - xs->state = XSK_UNBOUND; + WRITE_ONCE(xs->state, XSK_UNBOUND); /* Wait for driver to stop using the xdp socket. */ xdp_del_sk_umem(xs->umem, xs); @@ -362,6 +471,52 @@ static void xsk_unbind_dev(struct xdp_sock *xs) dev_put(dev); } +static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, + struct xdp_sock ***map_entry) +{ + struct xsk_map *map = NULL; + struct xsk_map_node *node; + + *map_entry = NULL; + + spin_lock_bh(&xs->map_list_lock); + node = list_first_entry_or_null(&xs->map_list, struct xsk_map_node, + node); + if (node) { + WARN_ON(xsk_map_inc(node->map)); + map = node->map; + *map_entry = node->map_entry; + } + spin_unlock_bh(&xs->map_list_lock); + return map; +} + +static void xsk_delete_from_maps(struct xdp_sock *xs) +{ + /* This function removes the current XDP socket from all the + * maps it resides in. We need to take extra care here, due to + * the two locks involved. Each map has a lock synchronizing + * updates to the entries, and each socket has a lock that + * synchronizes access to the list of maps (map_list). For + * deadlock avoidance the locks need to be taken in the order + * "map lock"->"socket map list lock". We start off by + * accessing the socket map list, and take a reference to the + * map to guarantee existence between the + * xsk_get_map_list_entry() and xsk_map_try_sock_delete() + * calls. Then we ask the map to remove the socket, which + * tries to remove the socket from the map. Note that there + * might be updates to the map between + * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). + */ + struct xdp_sock **map_entry = NULL; + struct xsk_map *map; + + while ((map = xsk_get_map_list_entry(xs, &map_entry))) { + xsk_map_try_sock_delete(map, xs, map_entry); + xsk_map_put(map); + } +} + static int xsk_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -381,7 +536,10 @@ static int xsk_release(struct socket *sock) sock_prot_inuse_add(net, sk->sk_prot, -1); local_bh_enable(); + xsk_delete_from_maps(xs); + mutex_lock(&xs->mutex); xsk_unbind_dev(xs); + mutex_unlock(&xs->mutex); xskq_destroy(xs->rx); xskq_destroy(xs->tx); @@ -412,6 +570,24 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd) return sock; } +/* Check if umem pages are contiguous. + * If zero-copy mode, use the DMA address to do the page contiguity check + * For all other modes we use addr (kernel virtual address) + * Store the result in the low bits of addr. + */ +static void xsk_check_page_contiguity(struct xdp_umem *umem, u32 flags) +{ + struct xdp_umem_page *pgs = umem->pages; + int i, is_contig; + + for (i = 0; i < umem->npgs - 1; i++) { + is_contig = (flags & XDP_ZEROCOPY) ? + (pgs[i].dma + PAGE_SIZE == pgs[i + 1].dma) : + (pgs[i].addr + PAGE_SIZE == pgs[i + 1].addr); + pgs[i].addr += is_contig << XSK_NEXT_PG_CONTIG_SHIFT; + } +} + static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; @@ -427,7 +603,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) return -EINVAL; flags = sxdp->sxdp_flags; - if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY)) + if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY | + XDP_USE_NEED_WAKEUP)) return -EINVAL; rtnl_lock(); @@ -454,7 +631,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct xdp_sock *umem_xs; struct socket *sock; - if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY)) { + if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) || + (flags & XDP_USE_NEED_WAKEUP)) { /* Cannot specify flags for shared sockets. */ err = -EINVAL; goto out_unlock; @@ -473,19 +651,19 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) } umem_xs = xdp_sk(sock->sk); - if (!umem_xs->umem) { - /* No umem to inherit. */ + if (!xsk_is_bound(umem_xs)) { err = -EBADF; sockfd_put(sock); goto out_unlock; - } else if (umem_xs->dev != dev || umem_xs->queue_id != qid) { + } + if (umem_xs->dev != dev || umem_xs->queue_id != qid) { err = -EINVAL; sockfd_put(sock); goto out_unlock; } xdp_get_umem(umem_xs->umem); - xs->umem = umem_xs->umem; + WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) { err = -EINVAL; @@ -500,6 +678,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); if (err) goto out_unlock; + + xsk_check_page_contiguity(xs->umem, flags); } xs->dev = dev; @@ -510,16 +690,28 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xdp_add_sk_umem(xs->umem, xs); out_unlock: - if (err) + if (err) { dev_put(dev); - else - xs->state = XSK_BOUND; + } else { + /* Matches smp_rmb() in bind() for shared umem + * sockets, and xsk_is_bound(). + */ + smp_wmb(); + WRITE_ONCE(xs->state, XSK_BOUND); + } out_release: mutex_unlock(&xs->mutex); rtnl_unlock(); return err; } +struct xdp_umem_reg_v1 { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; +}; + static int xsk_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -549,15 +741,24 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, } q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx; err = xsk_init_queue(entries, q, false); + if (!err && optname == XDP_TX_RING) + /* Tx needs to be explicitly woken up the first time */ + xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; mutex_unlock(&xs->mutex); return err; } case XDP_UMEM_REG: { - struct xdp_umem_reg mr; + size_t mr_size = sizeof(struct xdp_umem_reg); + struct xdp_umem_reg mr = {}; struct xdp_umem *umem; - if (copy_from_user(&mr, optval, sizeof(mr))) + if (optlen < sizeof(struct xdp_umem_reg_v1)) + return -EINVAL; + else if (optlen < sizeof(mr)) + mr_size = sizeof(struct xdp_umem_reg_v1); + + if (copy_from_user(&mr, optval, mr_size)) return -EFAULT; mutex_lock(&xs->mutex); @@ -574,7 +775,7 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, /* Make sure umem is ready before it can be seen by others */ smp_wmb(); - xs->umem = umem; + WRITE_ONCE(xs->umem, umem); mutex_unlock(&xs->mutex); return 0; } @@ -610,6 +811,20 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, return -ENOPROTOOPT; } +static void xsk_enter_rxtx_offsets(struct xdp_ring_offset_v1 *ring) +{ + ring->producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); + ring->consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); + ring->desc = offsetof(struct xdp_rxtx_ring, desc); +} + +static void xsk_enter_umem_offsets(struct xdp_ring_offset_v1 *ring) +{ + ring->producer = offsetof(struct xdp_umem_ring, ptrs.producer); + ring->consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); + ring->desc = offsetof(struct xdp_umem_ring, desc); +} + static int xsk_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { @@ -649,26 +864,49 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, case XDP_MMAP_OFFSETS: { struct xdp_mmap_offsets off; + struct xdp_mmap_offsets_v1 off_v1; + bool flags_supported = true; + void *to_copy; - if (len < sizeof(off)) + if (len < sizeof(off_v1)) return -EINVAL; + else if (len < sizeof(off)) + flags_supported = false; + + if (flags_supported) { + /* xdp_ring_offset is identical to xdp_ring_offset_v1 + * except for the flags field added to the end. + */ + xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *) + &off.rx); + xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *) + &off.tx); + xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *) + &off.fr); + xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *) + &off.cr); + off.rx.flags = offsetof(struct xdp_rxtx_ring, + ptrs.flags); + off.tx.flags = offsetof(struct xdp_rxtx_ring, + ptrs.flags); + off.fr.flags = offsetof(struct xdp_umem_ring, + ptrs.flags); + off.cr.flags = offsetof(struct xdp_umem_ring, + ptrs.flags); + + len = sizeof(off); + to_copy = &off; + } else { + xsk_enter_rxtx_offsets(&off_v1.rx); + xsk_enter_rxtx_offsets(&off_v1.tx); + xsk_enter_umem_offsets(&off_v1.fr); + xsk_enter_umem_offsets(&off_v1.cr); + + len = sizeof(off_v1); + to_copy = &off_v1; + } - off.rx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); - off.rx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); - off.rx.desc = offsetof(struct xdp_rxtx_ring, desc); - off.tx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); - off.tx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); - off.tx.desc = offsetof(struct xdp_rxtx_ring, desc); - - off.fr.producer = offsetof(struct xdp_umem_ring, ptrs.producer); - off.fr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); - off.fr.desc = offsetof(struct xdp_umem_ring, desc); - off.cr.producer = offsetof(struct xdp_umem_ring, ptrs.producer); - off.cr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); - off.cr.desc = offsetof(struct xdp_umem_ring, desc); - - len = sizeof(off); - if (copy_to_user(optval, &off, len)) + if (copy_to_user(optval, to_copy, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; @@ -713,7 +951,7 @@ static int xsk_mmap(struct file *file, struct socket *sock, unsigned long pfn; struct page *qpg; - if (xs->state != XSK_READY) + if (READ_ONCE(xs->state) != XSK_READY) return -EBUSY; if (offset == XDP_PGOFF_RX_RING) { @@ -855,6 +1093,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, spin_lock_init(&xs->rx_lock); spin_lock_init(&xs->tx_completion_lock); + INIT_LIST_HEAD(&xs->map_list); + spin_lock_init(&xs->map_list_lock); + mutex_lock(&net->xdp.lock); sk_add_node_rcu(sk, &net->xdp.list); mutex_unlock(&net->xdp.lock); diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index ba8120610426..4cfd106bdb53 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -4,6 +4,19 @@ #ifndef XSK_H_ #define XSK_H_ +struct xdp_ring_offset_v1 { + __u64 producer; + __u64 consumer; + __u64 desc; +}; + +struct xdp_mmap_offsets_v1 { + struct xdp_ring_offset_v1 rx; + struct xdp_ring_offset_v1 tx; + struct xdp_ring_offset_v1 fr; + struct xdp_ring_offset_v1 cr; +}; + static inline struct xdp_sock *xdp_sk(struct sock *sk) { return (struct xdp_sock *)sk; diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index d5e06c8e0cbf..f59791ba43a0 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -56,7 +56,7 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) du.id = umem->id; du.size = umem->size; du.num_pages = umem->npgs; - du.chunk_size = (__u32)(~umem->chunk_mask + 1); + du.chunk_size = umem->chunk_size_nohr + umem->headroom; du.headroom = umem->headroom; du.ifindex = umem->dev ? umem->dev->ifindex : 0; du.queue_id = umem->queue_id; @@ -97,6 +97,7 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, msg->xdiag_ino = sk_ino; sock_diag_save_cookie(sk, msg->xdiag_cookie); + mutex_lock(&xs->mutex); if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) goto out_nlmsg_trim; @@ -117,10 +118,12 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO)) goto out_nlmsg_trim; + mutex_unlock(&xs->mutex); nlmsg_end(nlskb, nlh); return 0; out_nlmsg_trim: + mutex_unlock(&xs->mutex); nlmsg_cancel(nlskb, nlh); return -EMSGSIZE; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 909c5168ed0f..eddae4688862 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -16,6 +16,7 @@ struct xdp_ring { u32 producer ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; + u32 flags; }; /* Used for the RX and TX queues for packets */ @@ -133,6 +134,17 @@ static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt) /* UMEM queue */ +static inline bool xskq_crosses_non_contig_pg(struct xdp_umem *umem, u64 addr, + u64 length) +{ + bool cross_pg = (addr & (PAGE_SIZE - 1)) + length > PAGE_SIZE; + bool next_pg_contig = + (unsigned long)umem->pages[(addr >> PAGE_SHIFT)].addr & + XSK_NEXT_PG_CONTIG_MASK; + + return cross_pg && !next_pg_contig; +} + static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) { if (addr >= q->size) { @@ -143,23 +155,51 @@ static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) return true; } -static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr) +static inline bool xskq_is_valid_addr_unaligned(struct xsk_queue *q, u64 addr, + u64 length, + struct xdp_umem *umem) +{ + u64 base_addr = xsk_umem_extract_addr(addr); + + addr = xsk_umem_add_offset_to_addr(addr); + if (base_addr >= q->size || addr >= q->size || + xskq_crosses_non_contig_pg(umem, addr, length)) { + q->invalid_descs++; + return false; + } + + return true; +} + +static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr, + struct xdp_umem *umem) { while (q->cons_tail != q->cons_head) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; unsigned int idx = q->cons_tail & q->ring_mask; *addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask; + + if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) { + if (xskq_is_valid_addr_unaligned(q, *addr, + umem->chunk_size_nohr, + umem)) + return addr; + goto out; + } + if (xskq_is_valid_addr(q, *addr)) return addr; +out: q->cons_tail++; } return NULL; } -static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr) +static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr, + struct xdp_umem *umem) { if (q->cons_tail == q->cons_head) { smp_mb(); /* D, matches A */ @@ -170,7 +210,7 @@ static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr) smp_rmb(); } - return xskq_validate_addr(q, addr); + return xskq_validate_addr(q, addr, umem); } static inline void xskq_discard_addr(struct xsk_queue *q) @@ -229,8 +269,21 @@ static inline int xskq_reserve_addr(struct xsk_queue *q) /* Rx/Tx queue */ -static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) +static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, + struct xdp_umem *umem) { + if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) { + if (!xskq_is_valid_addr_unaligned(q, d->addr, d->len, umem)) + return false; + + if (d->len > umem->chunk_size_nohr || d->options) { + q->invalid_descs++; + return false; + } + + return true; + } + if (!xskq_is_valid_addr(q, d->addr)) return false; @@ -244,14 +297,15 @@ static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) } static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q, - struct xdp_desc *desc) + struct xdp_desc *desc, + struct xdp_umem *umem) { while (q->cons_tail != q->cons_head) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; unsigned int idx = q->cons_tail & q->ring_mask; *desc = READ_ONCE(ring->desc[idx]); - if (xskq_is_valid_desc(q, desc)) + if (xskq_is_valid_desc(q, desc, umem)) return desc; q->cons_tail++; @@ -261,7 +315,8 @@ static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q, } static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q, - struct xdp_desc *desc) + struct xdp_desc *desc, + struct xdp_umem *umem) { if (q->cons_tail == q->cons_head) { smp_mb(); /* D, matches A */ @@ -272,7 +327,7 @@ static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q, smp_rmb(); /* C, matches B */ } - return xskq_validate_desc(q, desc); + return xskq_validate_desc(q, desc, umem); } static inline void xskq_discard_desc(struct xsk_queue *q) |