summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2020-09-01 23:05:08 +0300
committerDavid S. Miller <davem@davemloft.net>2020-09-01 23:22:59 +0300
commit150f29f5e6ea55d8a7d368b162a4e9947a95d2f5 (patch)
treed028c9c9a7cdddcc79feb49e79fa011af029ff8c /net
parent8aa639e1483bbdc0615796801829c773724f6645 (diff)
parentebc4ecd48ca6552b223047839f66e9a9c09aea4c (diff)
downloadlinux-150f29f5e6ea55d8a7d368b162a4e9947a95d2f5.tar.xz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says: ==================== pull-request: bpf-next 2020-09-01 The following pull-request contains BPF updates for your *net-next* tree. There are two small conflicts when pulling, resolve as follows: 1) Merge conflict in tools/lib/bpf/libbpf.c between 88a82120282b ("libbpf: Factor out common ELF operations and improve logging") in bpf-next and 1e891e513e16 ("libbpf: Fix map index used in error message") in net-next. Resolve by taking the hunk in bpf-next: [...] scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx); data = elf_sec_data(obj, scn); if (!scn || !data) { pr_warn("elf: failed to get %s map definitions for %s\n", MAPS_ELF_SEC, obj->path); return -EINVAL; } [...] 2) Merge conflict in drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c between 9647c57b11e5 ("xsk: i40e: ice: ixgbe: mlx5: Test for dma_need_sync earlier for better performance") in bpf-next and e20f0dbf204f ("net/mlx5e: RX, Add a prefetch command for small L1_CACHE_BYTES") in net-next. Resolve the two locations by retaining net_prefetch() and taking xsk_buff_dma_sync_for_cpu() from bpf-next. Should look like: [...] xdp_set_data_meta_invalid(xdp); xsk_buff_dma_sync_for_cpu(xdp, rq->xsk_pool); net_prefetch(xdp->data); [...] We've added 133 non-merge commits during the last 14 day(s) which contain a total of 246 files changed, 13832 insertions(+), 3105 deletions(-). The main changes are: 1) Initial support for sleepable BPF programs along with bpf_copy_from_user() helper for tracing to reliably access user memory, from Alexei Starovoitov. 2) Add BPF infra for writing and parsing TCP header options, from Martin KaFai Lau. 3) bpf_d_path() helper for returning full path for given 'struct path', from Jiri Olsa. 4) AF_XDP support for shared umems between devices and queues, from Magnus Karlsson. 5) Initial prep work for full BPF-to-BPF call support in libbpf, from Andrii Nakryiko. 6) Generalize bpf_sk_storage map & add local storage for inodes, from KP Singh. 7) Implement sockmap/hash updates from BPF context, from Lorenz Bauer. 8) BPF xor verification for scalar types & add BPF link iterator, from Yonghong Song. 9) Use target's prog type for BPF_PROG_TYPE_EXT prog verification, from Udip Pant. 10) Rework BPF tracing samples to use libbpf loader, from Daniel T. Lee. 11) Fix xdpsock sample to really cycle through all buffers, from Weqaar Janjua. 12) Improve type safety for tun/veth XDP frame handling, from Maciej Żenczykowski. 13) Various smaller cleanups and improvements all over the place. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/bpfilter/Kconfig1
-rw-r--r--net/core/bpf_sk_storage.c833
-rw-r--r--net/core/filter.c416
-rw-r--r--net/core/skmsg.c34
-rw-r--r--net/core/sock_map.c91
-rw-r--r--net/ethtool/channels.c2
-rw-r--r--net/ethtool/ioctl.c2
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_bpf.c13
-rw-r--r--net/ipv4/tcp_fastopen.c2
-rw-r--r--net/ipv4/tcp_input.c127
-rw-r--r--net/ipv4/tcp_ipv4.c5
-rw-r--r--net/ipv4/tcp_minisocks.c1
-rw-r--r--net/ipv4/tcp_output.c193
-rw-r--r--net/ipv4/udp_bpf.c9
-rw-r--r--net/ipv6/tcp_ipv6.c5
-rw-r--r--net/xdp/xdp_umem.c225
-rw-r--r--net/xdp/xdp_umem.h6
-rw-r--r--net/xdp/xsk.c213
-rw-r--r--net/xdp/xsk.h10
-rw-r--r--net/xdp/xsk_buff_pool.c380
-rw-r--r--net/xdp/xsk_diag.c16
-rw-r--r--net/xdp/xsk_queue.h12
-rw-r--r--net/xdp/xskmap.c8
24 files changed, 1451 insertions, 1169 deletions
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index 73d0b12789f1..8ad0233ce497 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -2,6 +2,7 @@
menuconfig BPFILTER
bool "BPF based packet filtering framework (BPFILTER)"
depends on NET && BPF && INET
+ select USERMODE_DRIVER
help
This builds experimental bpfilter framework that is aiming to
provide netfilter compatible functionality via BPF
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index b988f48153a4..a0d1a3265b71 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -7,97 +7,14 @@
#include <linux/spinlock.h>
#include <linux/bpf.h>
#include <linux/btf_ids.h>
+#include <linux/bpf_local_storage.h>
#include <net/bpf_sk_storage.h>
#include <net/sock.h>
#include <uapi/linux/sock_diag.h>
#include <uapi/linux/btf.h>
+#include <linux/btf_ids.h>
-#define SK_STORAGE_CREATE_FLAG_MASK \
- (BPF_F_NO_PREALLOC | BPF_F_CLONE)
-
-struct bucket {
- struct hlist_head list;
- raw_spinlock_t lock;
-};
-
-/* Thp map is not the primary owner of a bpf_sk_storage_elem.
- * Instead, the sk->sk_bpf_storage is.
- *
- * The map (bpf_sk_storage_map) is for two purposes
- * 1. Define the size of the "sk local storage". It is
- * the map's value_size.
- *
- * 2. Maintain a list to keep track of all elems such
- * that they can be cleaned up during the map destruction.
- *
- * When a bpf local storage is being looked up for a
- * particular sk, the "bpf_map" pointer is actually used
- * as the "key" to search in the list of elem in
- * sk->sk_bpf_storage.
- *
- * Hence, consider sk->sk_bpf_storage is the mini-map
- * with the "bpf_map" pointer as the searching key.
- */
-struct bpf_sk_storage_map {
- struct bpf_map map;
- /* Lookup elem does not require accessing the map.
- *
- * Updating/Deleting requires a bucket lock to
- * link/unlink the elem from the map. Having
- * multiple buckets to improve contention.
- */
- struct bucket *buckets;
- u32 bucket_log;
- u16 elem_size;
- u16 cache_idx;
-};
-
-struct bpf_sk_storage_data {
- /* smap is used as the searching key when looking up
- * from sk->sk_bpf_storage.
- *
- * Put it in the same cacheline as the data to minimize
- * the number of cachelines access during the cache hit case.
- */
- struct bpf_sk_storage_map __rcu *smap;
- u8 data[] __aligned(8);
-};
-
-/* Linked to bpf_sk_storage and bpf_sk_storage_map */
-struct bpf_sk_storage_elem {
- struct hlist_node map_node; /* Linked to bpf_sk_storage_map */
- struct hlist_node snode; /* Linked to bpf_sk_storage */
- struct bpf_sk_storage __rcu *sk_storage;
- struct rcu_head rcu;
- /* 8 bytes hole */
- /* The data is stored in aother cacheline to minimize
- * the number of cachelines access during a cache hit.
- */
- struct bpf_sk_storage_data sdata ____cacheline_aligned;
-};
-
-#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata)
-#define SDATA(_SELEM) (&(_SELEM)->sdata)
-#define BPF_SK_STORAGE_CACHE_SIZE 16
-
-static DEFINE_SPINLOCK(cache_idx_lock);
-static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE];
-
-struct bpf_sk_storage {
- struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
- struct hlist_head list; /* List of bpf_sk_storage_elem */
- struct sock *sk; /* The sk that owns the the above "list" of
- * bpf_sk_storage_elem.
- */
- struct rcu_head rcu;
- raw_spinlock_t lock; /* Protect adding/removing from the "list" */
-};
-
-static struct bucket *select_bucket(struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *selem)
-{
- return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
-}
+DEFINE_BPF_STORAGE_CACHE(sk_cache);
static int omem_charge(struct sock *sk, unsigned int size)
{
@@ -111,445 +28,38 @@ static int omem_charge(struct sock *sk, unsigned int size)
return -ENOMEM;
}
-static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem)
-{
- return !hlist_unhashed(&selem->snode);
-}
-
-static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem)
-{
- return !hlist_unhashed(&selem->map_node);
-}
-
-static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
- struct sock *sk, void *value,
- bool charge_omem)
-{
- struct bpf_sk_storage_elem *selem;
-
- if (charge_omem && omem_charge(sk, smap->elem_size))
- return NULL;
-
- selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
- if (selem) {
- if (value)
- memcpy(SDATA(selem)->data, value, smap->map.value_size);
- return selem;
- }
-
- if (charge_omem)
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
-
- return NULL;
-}
-
-/* sk_storage->lock must be held and selem->sk_storage == sk_storage.
- * The caller must ensure selem->smap is still valid to be
- * dereferenced for its smap->elem_size and smap->cache_idx.
- */
-static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage,
- struct bpf_sk_storage_elem *selem,
- bool uncharge_omem)
-{
- struct bpf_sk_storage_map *smap;
- bool free_sk_storage;
- struct sock *sk;
-
- smap = rcu_dereference(SDATA(selem)->smap);
- sk = sk_storage->sk;
-
- /* All uncharging on sk->sk_omem_alloc must be done first.
- * sk may be freed once the last selem is unlinked from sk_storage.
- */
- if (uncharge_omem)
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
-
- free_sk_storage = hlist_is_singular_node(&selem->snode,
- &sk_storage->list);
- if (free_sk_storage) {
- atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
- sk_storage->sk = NULL;
- /* After this RCU_INIT, sk may be freed and cannot be used */
- RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
-
- /* sk_storage is not freed now. sk_storage->lock is
- * still held and raw_spin_unlock_bh(&sk_storage->lock)
- * will be done by the caller.
- *
- * Although the unlock will be done under
- * rcu_read_lock(), it is more intutivie to
- * read if kfree_rcu(sk_storage, rcu) is done
- * after the raw_spin_unlock_bh(&sk_storage->lock).
- *
- * Hence, a "bool free_sk_storage" is returned
- * to the caller which then calls the kfree_rcu()
- * after unlock.
- */
- }
- hlist_del_init_rcu(&selem->snode);
- if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
- SDATA(selem))
- RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);
-
- kfree_rcu(selem, rcu);
-
- return free_sk_storage;
-}
-
-static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
-{
- struct bpf_sk_storage *sk_storage;
- bool free_sk_storage = false;
-
- if (unlikely(!selem_linked_to_sk(selem)))
- /* selem has already been unlinked from sk */
- return;
-
- sk_storage = rcu_dereference(selem->sk_storage);
- raw_spin_lock_bh(&sk_storage->lock);
- if (likely(selem_linked_to_sk(selem)))
- free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
- raw_spin_unlock_bh(&sk_storage->lock);
-
- if (free_sk_storage)
- kfree_rcu(sk_storage, rcu);
-}
-
-static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
- struct bpf_sk_storage_elem *selem)
-{
- RCU_INIT_POINTER(selem->sk_storage, sk_storage);
- hlist_add_head(&selem->snode, &sk_storage->list);
-}
-
-static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
-{
- struct bpf_sk_storage_map *smap;
- struct bucket *b;
-
- if (unlikely(!selem_linked_to_map(selem)))
- /* selem has already be unlinked from smap */
- return;
-
- smap = rcu_dereference(SDATA(selem)->smap);
- b = select_bucket(smap, selem);
- raw_spin_lock_bh(&b->lock);
- if (likely(selem_linked_to_map(selem)))
- hlist_del_init_rcu(&selem->map_node);
- raw_spin_unlock_bh(&b->lock);
-}
-
-static void selem_link_map(struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *selem)
-{
- struct bucket *b = select_bucket(smap, selem);
-
- raw_spin_lock_bh(&b->lock);
- RCU_INIT_POINTER(SDATA(selem)->smap, smap);
- hlist_add_head_rcu(&selem->map_node, &b->list);
- raw_spin_unlock_bh(&b->lock);
-}
-
-static void selem_unlink(struct bpf_sk_storage_elem *selem)
-{
- /* Always unlink from map before unlinking from sk_storage
- * because selem will be freed after successfully unlinked from
- * the sk_storage.
- */
- selem_unlink_map(selem);
- selem_unlink_sk(selem);
-}
-
-static struct bpf_sk_storage_data *
-__sk_storage_lookup(struct bpf_sk_storage *sk_storage,
- struct bpf_sk_storage_map *smap,
- bool cacheit_lockit)
-{
- struct bpf_sk_storage_data *sdata;
- struct bpf_sk_storage_elem *selem;
-
- /* Fast path (cache hit) */
- sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]);
- if (sdata && rcu_access_pointer(sdata->smap) == smap)
- return sdata;
-
- /* Slow path (cache miss) */
- hlist_for_each_entry_rcu(selem, &sk_storage->list, snode)
- if (rcu_access_pointer(SDATA(selem)->smap) == smap)
- break;
-
- if (!selem)
- return NULL;
-
- sdata = SDATA(selem);
- if (cacheit_lockit) {
- /* spinlock is needed to avoid racing with the
- * parallel delete. Otherwise, publishing an already
- * deleted sdata to the cache will become a use-after-free
- * problem in the next __sk_storage_lookup().
- */
- raw_spin_lock_bh(&sk_storage->lock);
- if (selem_linked_to_sk(selem))
- rcu_assign_pointer(sk_storage->cache[smap->cache_idx],
- sdata);
- raw_spin_unlock_bh(&sk_storage->lock);
- }
-
- return sdata;
-}
-
-static struct bpf_sk_storage_data *
+static struct bpf_local_storage_data *
sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
{
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_map *smap;
sk_storage = rcu_dereference(sk->sk_bpf_storage);
if (!sk_storage)
return NULL;
- smap = (struct bpf_sk_storage_map *)map;
- return __sk_storage_lookup(sk_storage, smap, cacheit_lockit);
-}
-
-static int check_flags(const struct bpf_sk_storage_data *old_sdata,
- u64 map_flags)
-{
- if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
- /* elem already exists */
- return -EEXIST;
-
- if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
- /* elem doesn't exist, cannot update it */
- return -ENOENT;
-
- return 0;
-}
-
-static int sk_storage_alloc(struct sock *sk,
- struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *first_selem)
-{
- struct bpf_sk_storage *prev_sk_storage, *sk_storage;
- int err;
-
- err = omem_charge(sk, sizeof(*sk_storage));
- if (err)
- return err;
-
- sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
- if (!sk_storage) {
- err = -ENOMEM;
- goto uncharge;
- }
- INIT_HLIST_HEAD(&sk_storage->list);
- raw_spin_lock_init(&sk_storage->lock);
- sk_storage->sk = sk;
-
- __selem_link_sk(sk_storage, first_selem);
- selem_link_map(smap, first_selem);
- /* Publish sk_storage to sk. sk->sk_lock cannot be acquired.
- * Hence, atomic ops is used to set sk->sk_bpf_storage
- * from NULL to the newly allocated sk_storage ptr.
- *
- * From now on, the sk->sk_bpf_storage pointer is protected
- * by the sk_storage->lock. Hence, when freeing
- * the sk->sk_bpf_storage, the sk_storage->lock must
- * be held before setting sk->sk_bpf_storage to NULL.
- */
- prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage,
- NULL, sk_storage);
- if (unlikely(prev_sk_storage)) {
- selem_unlink_map(first_selem);
- err = -EAGAIN;
- goto uncharge;
-
- /* Note that even first_selem was linked to smap's
- * bucket->list, first_selem can be freed immediately
- * (instead of kfree_rcu) because
- * bpf_sk_storage_map_free() does a
- * synchronize_rcu() before walking the bucket->list.
- * Hence, no one is accessing selem from the
- * bucket->list under rcu_read_lock().
- */
- }
-
- return 0;
-
-uncharge:
- kfree(sk_storage);
- atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
- return err;
-}
-
-/* sk cannot be going away because it is linking new elem
- * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0).
- * Otherwise, it will become a leak (and other memory issues
- * during map destruction).
- */
-static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
- struct bpf_map *map,
- void *value,
- u64 map_flags)
-{
- struct bpf_sk_storage_data *old_sdata = NULL;
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_map *smap;
- int err;
-
- /* BPF_EXIST and BPF_NOEXIST cannot be both set */
- if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
- /* BPF_F_LOCK can only be used in a value with spin_lock */
- unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
- return ERR_PTR(-EINVAL);
-
- smap = (struct bpf_sk_storage_map *)map;
- sk_storage = rcu_dereference(sk->sk_bpf_storage);
- if (!sk_storage || hlist_empty(&sk_storage->list)) {
- /* Very first elem for this sk */
- err = check_flags(NULL, map_flags);
- if (err)
- return ERR_PTR(err);
-
- selem = selem_alloc(smap, sk, value, true);
- if (!selem)
- return ERR_PTR(-ENOMEM);
-
- err = sk_storage_alloc(sk, smap, selem);
- if (err) {
- kfree(selem);
- atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
- return ERR_PTR(err);
- }
-
- return SDATA(selem);
- }
-
- if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
- /* Hoping to find an old_sdata to do inline update
- * such that it can avoid taking the sk_storage->lock
- * and changing the lists.
- */
- old_sdata = __sk_storage_lookup(sk_storage, smap, false);
- err = check_flags(old_sdata, map_flags);
- if (err)
- return ERR_PTR(err);
- if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) {
- copy_map_value_locked(map, old_sdata->data,
- value, false);
- return old_sdata;
- }
- }
-
- raw_spin_lock_bh(&sk_storage->lock);
-
- /* Recheck sk_storage->list under sk_storage->lock */
- if (unlikely(hlist_empty(&sk_storage->list))) {
- /* A parallel del is happening and sk_storage is going
- * away. It has just been checked before, so very
- * unlikely. Return instead of retry to keep things
- * simple.
- */
- err = -EAGAIN;
- goto unlock_err;
- }
-
- old_sdata = __sk_storage_lookup(sk_storage, smap, false);
- err = check_flags(old_sdata, map_flags);
- if (err)
- goto unlock_err;
-
- if (old_sdata && (map_flags & BPF_F_LOCK)) {
- copy_map_value_locked(map, old_sdata->data, value, false);
- selem = SELEM(old_sdata);
- goto unlock;
- }
-
- /* sk_storage->lock is held. Hence, we are sure
- * we can unlink and uncharge the old_sdata successfully
- * later. Hence, instead of charging the new selem now
- * and then uncharge the old selem later (which may cause
- * a potential but unnecessary charge failure), avoid taking
- * a charge at all here (the "!old_sdata" check) and the
- * old_sdata will not be uncharged later during __selem_unlink_sk().
- */
- selem = selem_alloc(smap, sk, value, !old_sdata);
- if (!selem) {
- err = -ENOMEM;
- goto unlock_err;
- }
-
- /* First, link the new selem to the map */
- selem_link_map(smap, selem);
-
- /* Second, link (and publish) the new selem to sk_storage */
- __selem_link_sk(sk_storage, selem);
-
- /* Third, remove old selem, SELEM(old_sdata) */
- if (old_sdata) {
- selem_unlink_map(SELEM(old_sdata));
- __selem_unlink_sk(sk_storage, SELEM(old_sdata), false);
- }
-
-unlock:
- raw_spin_unlock_bh(&sk_storage->lock);
- return SDATA(selem);
-
-unlock_err:
- raw_spin_unlock_bh(&sk_storage->lock);
- return ERR_PTR(err);
+ smap = (struct bpf_local_storage_map *)map;
+ return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
}
static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
sdata = sk_storage_lookup(sk, map, false);
if (!sdata)
return -ENOENT;
- selem_unlink(SELEM(sdata));
+ bpf_selem_unlink(SELEM(sdata));
return 0;
}
-static u16 cache_idx_get(void)
-{
- u64 min_usage = U64_MAX;
- u16 i, res = 0;
-
- spin_lock(&cache_idx_lock);
-
- for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) {
- if (cache_idx_usage_counts[i] < min_usage) {
- min_usage = cache_idx_usage_counts[i];
- res = i;
-
- /* Found a free cache_idx */
- if (!min_usage)
- break;
- }
- }
- cache_idx_usage_counts[res]++;
-
- spin_unlock(&cache_idx_lock);
-
- return res;
-}
-
-static void cache_idx_free(u16 idx)
-{
- spin_lock(&cache_idx_lock);
- cache_idx_usage_counts[idx]--;
- spin_unlock(&cache_idx_lock);
-}
-
/* Called by __sk_destruct() & bpf_sk_storage_clone() */
void bpf_sk_storage_free(struct sock *sk)
{
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage *sk_storage;
bool free_sk_storage = false;
struct hlist_node *n;
@@ -565,7 +75,7 @@ void bpf_sk_storage_free(struct sock *sk)
* Thus, no elem can be added-to or deleted-from the
* sk_storage->list by the bpf_prog or by the bpf-map's syscall.
*
- * It is racing with bpf_sk_storage_map_free() alone
+ * It is racing with bpf_local_storage_map_free() alone
* when unlinking elem from the sk_storage->list and
* the map's bucket->list.
*/
@@ -574,8 +84,9 @@ void bpf_sk_storage_free(struct sock *sk)
/* Always unlink from map before unlinking from
* sk_storage.
*/
- selem_unlink_map(selem);
- free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
+ bpf_selem_unlink_map(selem);
+ free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage,
+ selem, true);
}
raw_spin_unlock_bh(&sk_storage->lock);
rcu_read_unlock();
@@ -584,132 +95,24 @@ void bpf_sk_storage_free(struct sock *sk)
kfree_rcu(sk_storage, rcu);
}
-static void bpf_sk_storage_map_free(struct bpf_map *map)
-{
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage_map *smap;
- struct bucket *b;
- unsigned int i;
-
- smap = (struct bpf_sk_storage_map *)map;
-
- cache_idx_free(smap->cache_idx);
-
- /* 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
- * now. No new selem (of this map) can be added
- * to the sk->sk_bpf_storage or to the map bucket's list.
- *
- * The elem of this map can be cleaned up here
- * or
- * by bpf_sk_storage_free() during __sk_destruct().
- */
- for (i = 0; i < (1U << smap->bucket_log); i++) {
- b = &smap->buckets[i];
-
- rcu_read_lock();
- /* No one is adding to b->list now */
- while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
- struct bpf_sk_storage_elem,
- map_node))) {
- selem_unlink(selem);
- cond_resched_rcu();
- }
- rcu_read_unlock();
- }
-
- /* bpf_sk_storage_free() may still need to access the map.
- * e.g. bpf_sk_storage_free() has unlinked selem from the map
- * which then made the above while((selem = ...)) loop
- * exited immediately.
- *
- * However, the bpf_sk_storage_free() still needs to access
- * the smap->elem_size to do the uncharging in
- * __selem_unlink_sk().
- *
- * Hence, wait another rcu grace period for the
- * bpf_sk_storage_free() to finish.
- */
- synchronize_rcu();
-
- kvfree(smap->buckets);
- kfree(map);
-}
-
-/* U16_MAX is much more than enough for sk local storage
- * considering a tcp_sock is ~2k.
- */
-#define MAX_VALUE_SIZE \
- min_t(u32, \
- (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \
- (U16_MAX - sizeof(struct bpf_sk_storage_elem)))
-
-static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
+static void sk_storage_map_free(struct bpf_map *map)
{
- 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)
- return -EINVAL;
-
- if (!bpf_capable())
- return -EPERM;
+ struct bpf_local_storage_map *smap;
- if (attr->value_size > MAX_VALUE_SIZE)
- return -E2BIG;
-
- return 0;
+ smap = (struct bpf_local_storage_map *)map;
+ bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
+ bpf_local_storage_map_free(smap);
}
-static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
+static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr)
{
- struct bpf_sk_storage_map *smap;
- unsigned int i;
- u32 nbuckets;
- u64 cost;
- int ret;
-
- smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
- if (!smap)
- return ERR_PTR(-ENOMEM);
- bpf_map_init_from_attr(&smap->map, attr);
-
- nbuckets = roundup_pow_of_two(num_possible_cpus());
- /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
- nbuckets = max_t(u32, 2, nbuckets);
- smap->bucket_log = ilog2(nbuckets);
- cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
-
- ret = bpf_map_charge_init(&smap->map.memory, cost);
- if (ret < 0) {
- kfree(smap);
- return ERR_PTR(ret);
- }
-
- smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
- GFP_USER | __GFP_NOWARN);
- if (!smap->buckets) {
- bpf_map_charge_finish(&smap->map.memory);
- kfree(smap);
- return ERR_PTR(-ENOMEM);
- }
+ struct bpf_local_storage_map *smap;
- for (i = 0; i < nbuckets; i++) {
- INIT_HLIST_HEAD(&smap->buckets[i].list);
- raw_spin_lock_init(&smap->buckets[i].lock);
- }
-
- smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
- smap->cache_idx = cache_idx_get();
+ smap = bpf_local_storage_map_alloc(attr);
+ if (IS_ERR(smap))
+ return ERR_CAST(smap);
+ smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
return &smap->map;
}
@@ -719,26 +122,9 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key,
return -ENOTSUPP;
}
-static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
- const struct btf *btf,
- const struct btf_type *key_type,
- const struct btf_type *value_type)
-{
- u32 int_data;
-
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
- return -EINVAL;
-
- return 0;
-}
-
static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
struct socket *sock;
int fd, err;
@@ -756,14 +142,16 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
struct socket *sock;
int fd, err;
fd = *(int *)key;
sock = sockfd_lookup(fd, &err);
if (sock) {
- sdata = sk_storage_update(sock->sk, map, value, map_flags);
+ sdata = bpf_local_storage_update(
+ sock->sk, (struct bpf_local_storage_map *)map, value,
+ map_flags);
sockfd_put(sock);
return PTR_ERR_OR_ZERO(sdata);
}
@@ -787,14 +175,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
return err;
}
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
bpf_sk_storage_clone_elem(struct sock *newsk,
- struct bpf_sk_storage_map *smap,
- struct bpf_sk_storage_elem *selem)
+ struct bpf_local_storage_map *smap,
+ struct bpf_local_storage_elem *selem)
{
- struct bpf_sk_storage_elem *copy_selem;
+ struct bpf_local_storage_elem *copy_selem;
- copy_selem = selem_alloc(smap, newsk, NULL, true);
+ copy_selem = bpf_selem_alloc(smap, newsk, NULL, true);
if (!copy_selem)
return NULL;
@@ -810,9 +198,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk,
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;
+ struct bpf_local_storage *new_sk_storage = NULL;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
int ret = 0;
RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
@@ -824,8 +212,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
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_local_storage_elem *copy_selem;
+ struct bpf_local_storage_map *smap;
struct bpf_map *map;
smap = rcu_dereference(SDATA(selem)->smap);
@@ -833,7 +221,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
continue;
/* Note that for lockless listeners adding new element
- * here can race with cleanup in bpf_sk_storage_map_free.
+ * here can race with cleanup in bpf_local_storage_map_free.
* Try to grab map refcnt to make sure that it's still
* alive and prevent concurrent removal.
*/
@@ -849,10 +237,10 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
}
if (new_sk_storage) {
- selem_link_map(smap, copy_selem);
- __selem_link_sk(new_sk_storage, copy_selem);
+ bpf_selem_link_map(smap, copy_selem);
+ bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
} else {
- ret = sk_storage_alloc(newsk, smap, copy_selem);
+ ret = bpf_local_storage_alloc(newsk, smap, copy_selem);
if (ret) {
kfree(copy_selem);
atomic_sub(smap->elem_size,
@@ -861,7 +249,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
goto out;
}
- new_sk_storage = rcu_dereference(copy_selem->sk_storage);
+ new_sk_storage =
+ rcu_dereference(copy_selem->local_storage);
}
bpf_map_put(map);
}
@@ -879,7 +268,7 @@ out:
BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
void *, value, u64, flags)
{
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage_data *sdata;
if (flags > BPF_SK_STORAGE_GET_F_CREATE)
return (unsigned long)NULL;
@@ -895,7 +284,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
* destruction).
*/
refcount_inc_not_zero(&sk->sk_refcnt)) {
- sdata = sk_storage_update(sk, map, value, BPF_NOEXIST);
+ sdata = bpf_local_storage_update(
+ sk, (struct bpf_local_storage_map *)map, value,
+ BPF_NOEXIST);
/* sk must be a fullsock (guaranteed by verifier),
* so sock_gen_put() is unnecessary.
*/
@@ -920,18 +311,44 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
return -ENOENT;
}
+static int sk_storage_charge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
+{
+ return omem_charge(owner, size);
+}
+
+static void sk_storage_uncharge(struct bpf_local_storage_map *smap,
+ void *owner, u32 size)
+{
+ struct sock *sk = owner;
+
+ atomic_sub(size, &sk->sk_omem_alloc);
+}
+
+static struct bpf_local_storage __rcu **
+sk_storage_ptr(void *owner)
+{
+ struct sock *sk = owner;
+
+ return &sk->sk_bpf_storage;
+}
+
static int sk_storage_map_btf_id;
const struct bpf_map_ops sk_storage_map_ops = {
- .map_alloc_check = bpf_sk_storage_map_alloc_check,
- .map_alloc = bpf_sk_storage_map_alloc,
- .map_free = bpf_sk_storage_map_free,
+ .map_meta_equal = bpf_map_meta_equal,
+ .map_alloc_check = bpf_local_storage_map_alloc_check,
+ .map_alloc = sk_storage_map_alloc,
+ .map_free = sk_storage_map_free,
.map_get_next_key = notsupp_get_next_key,
.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
.map_update_elem = bpf_fd_sk_storage_update_elem,
.map_delete_elem = bpf_fd_sk_storage_delete_elem,
- .map_check_btf = bpf_sk_storage_map_check_btf,
- .map_btf_name = "bpf_sk_storage_map",
+ .map_check_btf = bpf_local_storage_map_check_btf,
+ .map_btf_name = "bpf_local_storage_map",
.map_btf_id = &sk_storage_map_btf_id,
+ .map_local_storage_charge = sk_storage_charge,
+ .map_local_storage_uncharge = sk_storage_uncharge,
+ .map_owner_storage_ptr = sk_storage_ptr,
};
const struct bpf_func_proto bpf_sk_storage_get_proto = {
@@ -962,6 +379,30 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
.arg2_type = ARG_PTR_TO_SOCKET,
};
+BTF_ID_LIST(sk_storage_btf_ids)
+BTF_ID_UNUSED
+BTF_ID(struct, sock)
+
+const struct bpf_func_proto sk_storage_get_btf_proto = {
+ .func = bpf_sk_storage_get,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
+ .arg4_type = ARG_ANYTHING,
+ .btf_id = sk_storage_btf_ids,
+};
+
+const struct bpf_func_proto sk_storage_delete_btf_proto = {
+ .func = bpf_sk_storage_delete,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_PTR,
+ .arg2_type = ARG_PTR_TO_BTF_ID,
+ .btf_id = sk_storage_btf_ids,
+};
+
struct bpf_sk_storage_diag {
u32 nr_maps;
struct bpf_map *maps[];
@@ -1022,7 +463,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
u32 nr_maps = 0;
int rem, err;
- /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as
+ /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as
* the map_alloc_check() side also does.
*/
if (!bpf_capable())
@@ -1072,13 +513,13 @@ err_free:
}
EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc);
-static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb)
+static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb)
{
struct nlattr *nla_stg, *nla_value;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage_map *smap;
/* It cannot exceed max nlattr's payload */
- BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE);
+ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE);
nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE);
if (!nla_stg)
@@ -1114,9 +555,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb,
{
/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
unsigned int diag_size = nla_total_size(0);
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_elem *selem;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
+ struct bpf_local_storage_map *smap;
struct nlattr *nla_stgs;
unsigned int saved_len;
int err = 0;
@@ -1169,8 +610,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
{
/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
unsigned int diag_size = nla_total_size(0);
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_data *sdata;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_data *sdata;
struct nlattr *nla_stgs;
unsigned int saved_len;
int err = 0;
@@ -1197,8 +638,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
saved_len = skb->len;
for (i = 0; i < diag->nr_maps; i++) {
- sdata = __sk_storage_lookup(sk_storage,
- (struct bpf_sk_storage_map *)diag->maps[i],
+ sdata = bpf_local_storage_lookup(sk_storage,
+ (struct bpf_local_storage_map *)diag->maps[i],
false);
if (!sdata)
@@ -1235,19 +676,19 @@ struct bpf_iter_seq_sk_storage_map_info {
unsigned skip_elems;
};
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
- struct bpf_sk_storage_elem *prev_selem)
+ struct bpf_local_storage_elem *prev_selem)
{
- struct bpf_sk_storage *sk_storage;
- struct bpf_sk_storage_elem *selem;
+ struct bpf_local_storage *sk_storage;
+ struct bpf_local_storage_elem *selem;
u32 skip_elems = info->skip_elems;
- struct bpf_sk_storage_map *smap;
+ struct bpf_local_storage_map *smap;
u32 bucket_id = info->bucket_id;
u32 i, count, n_buckets;
- struct bucket *b;
+ struct bpf_local_storage_map_bucket *b;
- smap = (struct bpf_sk_storage_map *)info->map;
+ smap = (struct bpf_local_storage_map *)info->map;
n_buckets = 1U << smap->bucket_log;
if (bucket_id >= n_buckets)
return NULL;
@@ -1257,7 +698,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
count = 0;
while (selem) {
selem = hlist_entry_safe(selem->map_node.next,
- struct bpf_sk_storage_elem, map_node);
+ struct bpf_local_storage_elem, map_node);
if (!selem) {
/* not found, unlock and go to the next bucket */
b = &smap->buckets[bucket_id++];
@@ -1265,7 +706,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
skip_elems = 0;
break;
}
- sk_storage = rcu_dereference_raw(selem->sk_storage);
+ sk_storage = rcu_dereference_raw(selem->local_storage);
if (sk_storage) {
info->skip_elems = skip_elems + count;
return selem;
@@ -1278,7 +719,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
raw_spin_lock_bh(&b->lock);
count = 0;
hlist_for_each_entry(selem, &b->list, map_node) {
- sk_storage = rcu_dereference_raw(selem->sk_storage);
+ sk_storage = rcu_dereference_raw(selem->local_storage);
if (sk_storage && count >= skip_elems) {
info->bucket_id = i;
info->skip_elems = count;
@@ -1297,7 +738,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct bpf_sk_storage_elem *selem;
+ struct bpf_local_storage_elem *selem;
selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL);
if (!selem)
@@ -1330,11 +771,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta,
void *value)
static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
- struct bpf_sk_storage_elem *selem)
+ struct bpf_local_storage_elem *selem)
{
struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
struct bpf_iter__bpf_sk_storage_map ctx = {};
- struct bpf_sk_storage *sk_storage;
+ struct bpf_local_storage *sk_storage;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
int ret = 0;
@@ -1345,8 +786,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
ctx.meta = &meta;
ctx.map = info->map;
if (selem) {
- sk_storage = rcu_dereference_raw(selem->sk_storage);
- ctx.sk = sk_storage->sk;
+ sk_storage = rcu_dereference_raw(selem->local_storage);
+ ctx.sk = sk_storage->owner;
ctx.value = SDATA(selem)->data;
}
ret = bpf_iter_run_prog(prog, &ctx);
@@ -1363,13 +804,13 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
{
struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
- struct bpf_sk_storage_map *smap;
- struct bucket *b;
+ struct bpf_local_storage_map *smap;
+ struct bpf_local_storage_map_bucket *b;
if (!v) {
(void)__bpf_sk_storage_map_seq_show(seq, v);
} else {
- smap = (struct bpf_sk_storage_map *)info->map;
+ smap = (struct bpf_local_storage_map *)info->map;
b = &smap->buckets[info->bucket_id];
raw_spin_unlock_bh(&b->lock);
}
@@ -1437,6 +878,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
.target = "bpf_sk_storage_map",
.attach_target = bpf_iter_attach_map,
.detach_target = bpf_iter_detach_map,
+ .show_fdinfo = bpf_iter_map_show_fdinfo,
+ .fill_link_info = bpf_iter_map_fill_link_info,
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
diff --git a/net/core/filter.c b/net/core/filter.c
index b2df52086445..47eef9a0be6a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4459,6 +4459,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
} else {
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ unsigned long timeout;
if (optlen != sizeof(int))
return -EINVAL;
@@ -4480,6 +4481,20 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
tp->snd_ssthresh = val;
}
break;
+ case TCP_BPF_DELACK_MAX:
+ timeout = usecs_to_jiffies(val);
+ if (timeout > TCP_DELACK_MAX ||
+ timeout < TCP_TIMEOUT_MIN)
+ return -EINVAL;
+ inet_csk(sk)->icsk_delack_max = timeout;
+ break;
+ case TCP_BPF_RTO_MIN:
+ timeout = usecs_to_jiffies(val);
+ if (timeout > TCP_RTO_MIN ||
+ timeout < TCP_TIMEOUT_MIN)
+ return -EINVAL;
+ inet_csk(sk)->icsk_rto_min = timeout;
+ break;
case TCP_SAVE_SYN:
if (val < 0 || val > 1)
ret = -EINVAL;
@@ -4550,9 +4565,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
tp = tcp_sk(sk);
if (optlen <= 0 || !tp->saved_syn ||
- optlen > tp->saved_syn[0])
+ optlen > tcp_saved_syn_len(tp->saved_syn))
goto err_clear;
- memcpy(optval, tp->saved_syn + 1, optlen);
+ memcpy(optval, tp->saved_syn->data, optlen);
break;
default:
goto err_clear;
@@ -4654,9 +4669,99 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
.arg5_type = ARG_CONST_SIZE,
};
+static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
+ int optname, const u8 **start)
+{
+ struct sk_buff *syn_skb = bpf_sock->syn_skb;
+ const u8 *hdr_start;
+ int ret;
+
+ if (syn_skb) {
+ /* sk is a request_sock here */
+
+ if (optname == TCP_BPF_SYN) {
+ hdr_start = syn_skb->data;
+ ret = tcp_hdrlen(syn_skb);
+ } else if (optname == TCP_BPF_SYN_IP) {
+ hdr_start = skb_network_header(syn_skb);
+ ret = skb_network_header_len(syn_skb) +
+ tcp_hdrlen(syn_skb);
+ } else {
+ /* optname == TCP_BPF_SYN_MAC */
+ hdr_start = skb_mac_header(syn_skb);
+ ret = skb_mac_header_len(syn_skb) +
+ skb_network_header_len(syn_skb) +
+ tcp_hdrlen(syn_skb);
+ }
+ } else {
+ struct sock *sk = bpf_sock->sk;
+ struct saved_syn *saved_syn;
+
+ if (sk->sk_state == TCP_NEW_SYN_RECV)
+ /* synack retransmit. bpf_sock->syn_skb will
+ * not be available. It has to resort to
+ * saved_syn (if it is saved).
+ */
+ saved_syn = inet_reqsk(sk)->saved_syn;
+ else
+ saved_syn = tcp_sk(sk)->saved_syn;
+
+ if (!saved_syn)
+ return -ENOENT;
+
+ if (optname == TCP_BPF_SYN) {
+ hdr_start = saved_syn->data +
+ saved_syn->mac_hdrlen +
+ saved_syn->network_hdrlen;
+ ret = saved_syn->tcp_hdrlen;
+ } else if (optname == TCP_BPF_SYN_IP) {
+ hdr_start = saved_syn->data +
+ saved_syn->mac_hdrlen;
+ ret = saved_syn->network_hdrlen +
+ saved_syn->tcp_hdrlen;
+ } else {
+ /* optname == TCP_BPF_SYN_MAC */
+
+ /* TCP_SAVE_SYN may not have saved the mac hdr */
+ if (!saved_syn->mac_hdrlen)
+ return -ENOENT;
+
+ hdr_start = saved_syn->data;
+ ret = saved_syn->mac_hdrlen +
+ saved_syn->network_hdrlen +
+ saved_syn->tcp_hdrlen;
+ }
+ }
+
+ *start = hdr_start;
+ return ret;
+}
+
BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
int, level, int, optname, char *, optval, int, optlen)
{
+ if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
+ optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) {
+ int ret, copy_len = 0;
+ const u8 *start;
+
+ ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start);
+ if (ret > 0) {
+ copy_len = ret;
+ if (optlen < copy_len) {
+ copy_len = optlen;
+ ret = -ENOSPC;
+ }
+
+ memcpy(optval, start, copy_len);
+ }
+
+ /* Zero out unused buffer at the end */
+ memset(optval + copy_len, 0, optlen - copy_len);
+
+ return ret;
+ }
+
return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen);
}
@@ -6150,6 +6255,232 @@ static const struct bpf_func_proto bpf_sk_assign_proto = {
.arg3_type = ARG_ANYTHING,
};
+static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend,
+ u8 search_kind, const u8 *magic,
+ u8 magic_len, bool *eol)
+{
+ u8 kind, kind_len;
+
+ *eol = false;
+
+ while (op < opend) {
+ kind = op[0];
+
+ if (kind == TCPOPT_EOL) {
+ *eol = true;
+ return ERR_PTR(-ENOMSG);
+ } else if (kind == TCPOPT_NOP) {
+ op++;
+ continue;
+ }
+
+ if (opend - op < 2 || opend - op < op[1] || op[1] < 2)
+ /* Something is wrong in the received header.
+ * Follow the TCP stack's tcp_parse_options()
+ * and just bail here.
+ */
+ return ERR_PTR(-EFAULT);
+
+ kind_len = op[1];
+ if (search_kind == kind) {
+ if (!magic_len)
+ return op;
+
+ if (magic_len > kind_len - 2)
+ return ERR_PTR(-ENOMSG);
+
+ if (!memcmp(&op[2], magic, magic_len))
+ return op;
+ }
+
+ op += kind_len;
+ }
+
+ return ERR_PTR(-ENOMSG);
+}
+
+BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+ void *, search_res, u32, len, u64, flags)
+{
+ bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN;
+ const u8 *op, *opend, *magic, *search = search_res;
+ u8 search_kind, search_len, copy_len, magic_len;
+ int ret;
+
+ /* 2 byte is the minimal option len except TCPOPT_NOP and
+ * TCPOPT_EOL which are useless for the bpf prog to learn
+ * and this helper disallow loading them also.
+ */
+ if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN)
+ return -EINVAL;
+
+ search_kind = search[0];
+ search_len = search[1];
+
+ if (search_len > len || search_kind == TCPOPT_NOP ||
+ search_kind == TCPOPT_EOL)
+ return -EINVAL;
+
+ if (search_kind == TCPOPT_EXP || search_kind == 253) {
+ /* 16 or 32 bit magic. +2 for kind and kind length */
+ if (search_len != 4 && search_len != 6)
+ return -EINVAL;
+ magic = &search[2];
+ magic_len = search_len - 2;
+ } else {
+ if (search_len)
+ return -EINVAL;
+ magic = NULL;
+ magic_len = 0;
+ }
+
+ if (load_syn) {
+ ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op);
+ if (ret < 0)
+ return ret;
+
+ opend = op + ret;
+ op += sizeof(struct tcphdr);
+ } else {
+ if (!bpf_sock->skb ||
+ bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB)
+ /* This bpf_sock->op cannot call this helper */
+ return -EPERM;
+
+ opend = bpf_sock->skb_data_end;
+ op = bpf_sock->skb->data + sizeof(struct tcphdr);
+ }
+
+ op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len,
+ &eol);
+ if (IS_ERR(op))
+ return PTR_ERR(op);
+
+ copy_len = op[1];
+ ret = copy_len;
+ if (copy_len > len) {
+ ret = -ENOSPC;
+ copy_len = len;
+ }
+
+ memcpy(search_res, op, copy_len);
+ return ret;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = {
+ .func = bpf_sock_ops_load_hdr_opt,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+ const void *, from, u32, len, u64, flags)
+{
+ u8 new_kind, new_kind_len, magic_len = 0, *opend;
+ const u8 *op, *new_op, *magic = NULL;
+ struct sk_buff *skb;
+ bool eol;
+
+ if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB)
+ return -EPERM;
+
+ if (len < 2 || flags)
+ return -EINVAL;
+
+ new_op = from;
+ new_kind = new_op[0];
+ new_kind_len = new_op[1];
+
+ if (new_kind_len > len || new_kind == TCPOPT_NOP ||
+ new_kind == TCPOPT_EOL)
+ return -EINVAL;
+
+ if (new_kind_len > bpf_sock->remaining_opt_len)
+ return -ENOSPC;
+
+ /* 253 is another experimental kind */
+ if (new_kind == TCPOPT_EXP || new_kind == 253) {
+ if (new_kind_len < 4)
+ return -EINVAL;
+ /* Match for the 2 byte magic also.
+ * RFC 6994: the magic could be 2 or 4 bytes.
+ * Hence, matching by 2 byte only is on the
+ * conservative side but it is the right
+ * thing to do for the 'search-for-duplication'
+ * purpose.
+ */
+ magic = &new_op[2];
+ magic_len = 2;
+ }
+
+ /* Check for duplication */
+ skb = bpf_sock->skb;
+ op = skb->data + sizeof(struct tcphdr);
+ opend = bpf_sock->skb_data_end;
+
+ op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len,
+ &eol);
+ if (!IS_ERR(op))
+ return -EEXIST;
+
+ if (PTR_ERR(op) != -ENOMSG)
+ return PTR_ERR(op);
+
+ if (eol)
+ /* The option has been ended. Treat it as no more
+ * header option can be written.
+ */
+ return -ENOSPC;
+
+ /* No duplication found. Store the header option. */
+ memcpy(opend, from, new_kind_len);
+
+ bpf_sock->remaining_opt_len -= new_kind_len;
+ bpf_sock->skb_data_end += new_kind_len;
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = {
+ .func = bpf_sock_ops_store_hdr_opt,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+ u32, len, u64, flags)
+{
+ if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB)
+ return -EPERM;
+
+ if (flags || len < 2)
+ return -EINVAL;
+
+ if (len > bpf_sock->remaining_opt_len)
+ return -ENOSPC;
+
+ bpf_sock->remaining_opt_len -= len;
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = {
+ .func = bpf_sock_ops_reserve_hdr_opt,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+};
+
#endif /* CONFIG_INET */
bool bpf_helper_changes_pkt_data(void *func)
@@ -6179,6 +6510,9 @@ bool bpf_helper_changes_pkt_data(void *func)
func == bpf_lwt_seg6_adjust_srh ||
func == bpf_lwt_seg6_action ||
#endif
+#ifdef CONFIG_INET
+ func == bpf_sock_ops_store_hdr_opt ||
+#endif
func == bpf_lwt_in_push_encap ||
func == bpf_lwt_xmit_push_encap)
return true;
@@ -6550,6 +6884,12 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_sk_storage_delete:
return &bpf_sk_storage_delete_proto;
#ifdef CONFIG_INET
+ case BPF_FUNC_load_hdr_opt:
+ return &bpf_sock_ops_load_hdr_opt_proto;
+ case BPF_FUNC_store_hdr_opt:
+ return &bpf_sock_ops_store_hdr_opt_proto;
+ case BPF_FUNC_reserve_hdr_opt:
+ return &bpf_sock_ops_reserve_hdr_opt_proto;
case BPF_FUNC_tcp_sock:
return &bpf_tcp_sock_proto;
#endif /* CONFIG_INET */
@@ -7349,6 +7689,20 @@ static bool sock_ops_is_valid_access(int off, int size,
return false;
info->reg_type = PTR_TO_SOCKET_OR_NULL;
break;
+ case offsetof(struct bpf_sock_ops, skb_data):
+ if (size != sizeof(__u64))
+ return false;
+ info->reg_type = PTR_TO_PACKET;
+ break;
+ case offsetof(struct bpf_sock_ops, skb_data_end):
+ if (size != sizeof(__u64))
+ return false;
+ info->reg_type = PTR_TO_PACKET_END;
+ break;
+ case offsetof(struct bpf_sock_ops, skb_tcp_flags):
+ bpf_ctx_record_field_size(info, size_default);
+ return bpf_ctx_narrow_access_ok(off, size,
+ size_default);
default:
if (size != size_default)
return false;
@@ -8450,17 +8804,22 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
return insn - insn_buf;
switch (si->off) {
- case offsetof(struct bpf_sock_ops, op) ...
+ case offsetof(struct bpf_sock_ops, op):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+ op),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern, op));
+ break;
+
+ case offsetof(struct bpf_sock_ops, replylong[0]) ...
offsetof(struct bpf_sock_ops, replylong[3]):
- BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) !=
- sizeof_field(struct bpf_sock_ops_kern, op));
BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) !=
sizeof_field(struct bpf_sock_ops_kern, reply));
BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) !=
sizeof_field(struct bpf_sock_ops_kern, replylong));
off = si->off;
- off -= offsetof(struct bpf_sock_ops, op);
- off += offsetof(struct bpf_sock_ops_kern, op);
+ off -= offsetof(struct bpf_sock_ops, replylong[0]);
+ off += offsetof(struct bpf_sock_ops_kern, replylong[0]);
if (type == BPF_WRITE)
*insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg,
off);
@@ -8681,6 +9040,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
case offsetof(struct bpf_sock_ops, sk):
SOCK_OPS_GET_SK();
break;
+ case offsetof(struct bpf_sock_ops, skb_data_end):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+ skb_data_end),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern,
+ skb_data_end));
+ break;
+ case offsetof(struct bpf_sock_ops, skb_data):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+ skb),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern,
+ skb));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+ si->dst_reg, si->dst_reg,
+ offsetof(struct sk_buff, data));
+ break;
+ case offsetof(struct bpf_sock_ops, skb_len):
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+ skb),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern,
+ skb));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len),
+ si->dst_reg, si->dst_reg,
+ offsetof(struct sk_buff, len));
+ break;
+ case offsetof(struct bpf_sock_ops, skb_tcp_flags):
+ off = offsetof(struct sk_buff, cb);
+ off += offsetof(struct tcp_skb_cb, tcp_flags);
+ *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags);
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+ skb),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sock_ops_kern,
+ skb));
+ *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb,
+ tcp_flags),
+ si->dst_reg, si->dst_reg, off);
+ break;
}
return insn - insn_buf;
}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 6a32a1fd34f8..1c81caf9630f 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -494,14 +494,34 @@ end:
struct sk_psock *sk_psock_init(struct sock *sk, int node)
{
- struct sk_psock *psock = kzalloc_node(sizeof(*psock),
- GFP_ATOMIC | __GFP_NOWARN,
- node);
- if (!psock)
- return NULL;
+ struct sk_psock *psock;
+ struct proto *prot;
+
+ write_lock_bh(&sk->sk_callback_lock);
+
+ if (inet_csk_has_ulp(sk)) {
+ psock = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
+ if (sk->sk_user_data) {
+ psock = ERR_PTR(-EBUSY);
+ goto out;
+ }
+ psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node);
+ if (!psock) {
+ psock = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ prot = READ_ONCE(sk->sk_prot);
psock->sk = sk;
- psock->eval = __SK_NONE;
+ psock->eval = __SK_NONE;
+ psock->sk_proto = prot;
+ psock->saved_unhash = prot->unhash;
+ psock->saved_close = prot->close;
+ psock->saved_write_space = sk->sk_write_space;
INIT_LIST_HEAD(&psock->link);
spin_lock_init(&psock->link_lock);
@@ -516,6 +536,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
rcu_assign_sk_user_data_nocopy(sk, psock);
sock_hold(sk);
+out:
+ write_unlock_bh(&sk->sk_callback_lock);
return psock;
}
EXPORT_SYMBOL_GPL(sk_psock_init);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 119f52a99dc1..078386d7d9a2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -184,8 +184,6 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock)
{
struct proto *prot;
- sock_owned_by_me(sk);
-
switch (sk->sk_type) {
case SOCK_STREAM:
prot = tcp_bpf_get_proto(sk, psock);
@@ -272,8 +270,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
}
} else {
psock = sk_psock_init(sk, map->numa_node);
- if (!psock) {
- ret = -ENOMEM;
+ if (IS_ERR(psock)) {
+ ret = PTR_ERR(psock);
goto out_progs;
}
}
@@ -322,8 +320,8 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk)
if (!psock) {
psock = sk_psock_init(sk, map->numa_node);
- if (!psock)
- return -ENOMEM;
+ if (IS_ERR(psock))
+ return PTR_ERR(psock);
}
ret = sock_map_init_proto(sk, psock);
@@ -478,8 +476,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
return -EINVAL;
if (unlikely(idx >= map->max_entries))
return -E2BIG;
- if (inet_csk_has_ulp(sk))
- return -EINVAL;
link = sk_psock_init_link();
if (!link)
@@ -563,10 +559,12 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
return false;
}
-static int sock_map_update_elem(struct bpf_map *map, void *key,
- void *value, u64 flags)
+static int sock_hash_update_common(struct bpf_map *map, void *key,
+ struct sock *sk, u64 flags);
+
+int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
+ u64 flags)
{
- u32 idx = *(u32 *)key;
struct socket *sock;
struct sock *sk;
int ret;
@@ -595,14 +593,38 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
sock_map_sk_acquire(sk);
if (!sock_map_sk_state_allowed(sk))
ret = -EOPNOTSUPP;
+ else if (map->map_type == BPF_MAP_TYPE_SOCKMAP)
+ ret = sock_map_update_common(map, *(u32 *)key, sk, flags);
else
- ret = sock_map_update_common(map, idx, sk, flags);
+ ret = sock_hash_update_common(map, key, sk, flags);
sock_map_sk_release(sk);
out:
fput(sock->file);
return ret;
}
+static int sock_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 flags)
+{
+ struct sock *sk = (struct sock *)value;
+ int ret;
+
+ if (!sock_map_sk_is_suitable(sk))
+ return -EOPNOTSUPP;
+
+ local_bh_disable();
+ bh_lock_sock(sk);
+ if (!sock_map_sk_state_allowed(sk))
+ ret = -EOPNOTSUPP;
+ else if (map->map_type == BPF_MAP_TYPE_SOCKMAP)
+ ret = sock_map_update_common(map, *(u32 *)key, sk, flags);
+ else
+ ret = sock_hash_update_common(map, key, sk, flags);
+ bh_unlock_sock(sk);
+ local_bh_enable();
+ return ret;
+}
+
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops,
struct bpf_map *, map, void *, key, u64, flags)
{
@@ -683,6 +705,7 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = {
static int sock_map_btf_id;
const struct bpf_map_ops sock_map_ops = {
+ .map_meta_equal = bpf_map_meta_equal,
.map_alloc = sock_map_alloc,
.map_free = sock_map_free,
.map_get_next_key = sock_map_get_next_key,
@@ -855,8 +878,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
WARN_ON_ONCE(!rcu_read_lock_held());
if (unlikely(flags > BPF_EXIST))
return -EINVAL;
- if (inet_csk_has_ulp(sk))
- return -EINVAL;
link = sk_psock_init_link();
if (!link)
@@ -915,45 +936,6 @@ out_free:
return ret;
}
-static int sock_hash_update_elem(struct bpf_map *map, void *key,
- void *value, u64 flags)
-{
- struct socket *sock;
- struct sock *sk;
- int ret;
- u64 ufd;
-
- if (map->value_size == sizeof(u64))
- ufd = *(u64 *)value;
- else
- ufd = *(u32 *)value;
- if (ufd > S32_MAX)
- return -EINVAL;
-
- sock = sockfd_lookup(ufd, &ret);
- if (!sock)
- return ret;
- sk = sock->sk;
- if (!sk) {
- ret = -EINVAL;
- goto out;
- }
- if (!sock_map_sk_is_suitable(sk)) {
- ret = -EOPNOTSUPP;
- goto out;
- }
-
- sock_map_sk_acquire(sk);
- if (!sock_map_sk_state_allowed(sk))
- ret = -EOPNOTSUPP;
- else
- ret = sock_hash_update_common(map, key, sk, flags);
- sock_map_sk_release(sk);
-out:
- fput(sock->file);
- return ret;
-}
-
static int sock_hash_get_next_key(struct bpf_map *map, void *key,
void *key_next)
{
@@ -1219,10 +1201,11 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = {
static int sock_hash_map_btf_id;
const struct bpf_map_ops sock_hash_ops = {
+ .map_meta_equal = bpf_map_meta_equal,
.map_alloc = sock_hash_alloc,
.map_free = sock_hash_free,
.map_get_next_key = sock_hash_get_next_key,
- .map_update_elem = sock_hash_update_elem,
+ .map_update_elem = sock_map_update_elem,
.map_delete_elem = sock_hash_delete_elem,
.map_lookup_elem = sock_hash_lookup,
.map_lookup_elem_sys_only = sock_hash_lookup_sys,
diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 9ef54cdcf662..9ecda09ecb11 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -223,7 +223,7 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
from_channel = channels.combined_count +
min(channels.rx_count, channels.tx_count);
for (i = from_channel; i < old_total; i++)
- if (xdp_get_umem_from_qid(dev, i)) {
+ if (xsk_get_pool_from_qid(dev, i)) {
GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets");
return -EINVAL;
}
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index e6f5cf52023c..d497ca064ef7 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
min(channels.rx_count, channels.tx_count);
to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count);
for (i = from_channel; i < to_channel; i++)
- if (xdp_get_umem_from_qid(dev, i))
+ if (xsk_get_pool_from_qid(dev, i))
return -EINVAL;
ret = dev->ethtool_ops->set_channels(dev, &channels);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 31f3b858db81..57a568875539 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -418,6 +418,8 @@ void tcp_init_sock(struct sock *sk)
INIT_LIST_HEAD(&tp->tsorted_sent_queue);
icsk->icsk_rto = TCP_TIMEOUT_INIT;
+ icsk->icsk_rto_min = TCP_RTO_MIN;
+ icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
@@ -2685,6 +2687,8 @@ int tcp_disconnect(struct sock *sk, int flags)
icsk->icsk_backoff = 0;
icsk->icsk_probes_out = 0;
icsk->icsk_rto = TCP_TIMEOUT_INIT;
+ icsk->icsk_rto_min = TCP_RTO_MIN;
+ icsk->icsk_delack_max = TCP_DELACK_MAX;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd = TCP_INIT_CWND;
tp->snd_cwnd_cnt = 0;
@@ -3207,7 +3211,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
break;
case TCP_SAVE_SYN:
- if (val < 0 || val > 1)
+ /* 0: disable, 1: enable, 2: start from ether_header */
+ if (val < 0 || val > 2)
err = -EINVAL;
else
tp->save_syn = val;
@@ -3788,20 +3793,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
lock_sock(sk);
if (tp->saved_syn) {
- if (len < tp->saved_syn[0]) {
- if (put_user(tp->saved_syn[0], optlen)) {
+ if (len < tcp_saved_syn_len(tp->saved_syn)) {
+ if (put_user(tcp_saved_syn_len(tp->saved_syn),
+ optlen)) {
release_sock(sk);
return -EFAULT;
}
release_sock(sk);
return -EINVAL;
}
- len = tp->saved_syn[0];
+ len = tcp_saved_syn_len(tp->saved_syn);
if (put_user(len, optlen)) {
release_sock(sk);
return -EFAULT;
}
- if (copy_to_user(optval, tp->saved_syn + 1, len)) {
+ if (copy_to_user(optval, tp->saved_syn->data, len)) {
release_sock(sk);
return -EFAULT;
}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 7aa68f4aae6c..37f4cb2bba5c 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -567,10 +567,9 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage;
}
-static void tcp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops)
{
- if (sk->sk_family == AF_INET6 &&
- unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) {
+ if (unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) {
spin_lock_bh(&tcpv6_prot_lock);
if (likely(ops != tcpv6_prot_saved)) {
tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops);
@@ -603,13 +602,11 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE;
- if (!psock->sk_proto) {
- struct proto *ops = READ_ONCE(sk->sk_prot);
-
- if (tcp_bpf_assert_proto_ops(ops))
+ if (sk->sk_family == AF_INET6) {
+ if (tcp_bpf_assert_proto_ops(psock->sk_proto))
return ERR_PTR(-EINVAL);
- tcp_bpf_check_v6_needs_rebuild(sk, ops);
+ tcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
}
return &tcp_bpf_prots[family][config];
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 09b62de04eea..af2814c9342a 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -295,7 +295,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
refcount_set(&req->rsk_refcnt, 2);
/* Now finish processing the fastopen child socket. */
- tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 184ea556f50e..4337841faeff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -138,6 +138,69 @@ void clean_acked_data_flush(void)
EXPORT_SYMBOL_GPL(clean_acked_data_flush);
#endif
+#ifdef CONFIG_CGROUP_BPF
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+ bool unknown_opt = tcp_sk(sk)->rx_opt.saw_unknown &&
+ BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+ BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG);
+ bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+ BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+ struct bpf_sock_ops_kern sock_ops;
+
+ if (likely(!unknown_opt && !parse_all_opt))
+ return;
+
+ /* The skb will be handled in the
+ * bpf_skops_established() or
+ * bpf_skops_write_hdr_opt().
+ */
+ switch (sk->sk_state) {
+ case TCP_SYN_RECV:
+ case TCP_SYN_SENT:
+ case TCP_LISTEN:
+ return;
+ }
+
+ sock_owned_by_me(sk);
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+ sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB;
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+ BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+ struct sk_buff *skb)
+{
+ struct bpf_sock_ops_kern sock_ops;
+
+ sock_owned_by_me(sk);
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+ sock_ops.op = bpf_op;
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ /* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */
+ if (skb)
+ bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+ BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+#else
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+}
+
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+ struct sk_buff *skb)
+{
+}
+#endif
+
static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
unsigned int len)
{
@@ -3801,7 +3864,7 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
foc->exp = exp_opt;
}
-static void smc_parse_options(const struct tcphdr *th,
+static bool smc_parse_options(const struct tcphdr *th,
struct tcp_options_received *opt_rx,
const unsigned char *ptr,
int opsize)
@@ -3810,10 +3873,13 @@ static void smc_parse_options(const struct tcphdr *th,
if (static_branch_unlikely(&tcp_have_smc)) {
if (th->syn && !(opsize & 1) &&
opsize >= TCPOLEN_EXP_SMC_BASE &&
- get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+ get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) {
opt_rx->smc_ok = 1;
+ return true;
+ }
}
#endif
+ return false;
}
/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
@@ -3874,6 +3940,7 @@ void tcp_parse_options(const struct net *net,
ptr = (const unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
+ opt_rx->saw_unknown = 0;
while (length > 0) {
int opcode = *ptr++;
@@ -3964,15 +4031,21 @@ void tcp_parse_options(const struct net *net,
*/
if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE &&
get_unaligned_be16(ptr) ==
- TCPOPT_FASTOPEN_MAGIC)
+ TCPOPT_FASTOPEN_MAGIC) {
tcp_parse_fastopen_option(opsize -
TCPOLEN_EXP_FASTOPEN_BASE,
ptr + 2, th->syn, foc, true);
- else
- smc_parse_options(th, opt_rx, ptr,
- opsize);
+ break;
+ }
+
+ if (smc_parse_options(th, opt_rx, ptr, opsize))
+ break;
+
+ opt_rx->saw_unknown = 1;
break;
+ default:
+ opt_rx->saw_unknown = 1;
}
ptr += opsize-2;
length -= opsize;
@@ -5590,6 +5663,8 @@ syn_challenge:
goto discard;
}
+ bpf_skops_parse_hdr(sk, skb);
+
return true;
discard:
@@ -5798,7 +5873,7 @@ discard:
}
EXPORT_SYMBOL(tcp_rcv_established);
-void tcp_init_transfer(struct sock *sk, int bpf_op)
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
@@ -5819,7 +5894,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
tp->snd_cwnd_stamp = tcp_jiffies32;
- tcp_call_bpf(sk, bpf_op, 0, NULL);
+ bpf_skops_established(sk, bpf_op, skb);
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
}
@@ -5838,7 +5913,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
sk_mark_napi_id(sk, skb);
}
- tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
+ tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb);
/* Prevent spurious tcp_cwnd_restart() on first data
* packet.
@@ -6310,7 +6385,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
} else {
tcp_try_undo_spurious_syn(sk);
tp->retrans_stamp = 0;
- tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+ tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,
+ skb);
WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
}
smp_mb();
@@ -6599,13 +6675,27 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
{
if (tcp_sk(sk)->save_syn) {
u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
- u32 *copy;
+ struct saved_syn *saved_syn;
+ u32 mac_hdrlen;
+ void *base;
+
+ if (tcp_sk(sk)->save_syn == 2) { /* Save full header. */
+ base = skb_mac_header(skb);
+ mac_hdrlen = skb_mac_header_len(skb);
+ len += mac_hdrlen;
+ } else {
+ base = skb_network_header(skb);
+ mac_hdrlen = 0;
+ }
- copy = kmalloc(len + sizeof(u32), GFP_ATOMIC);
- if (copy) {
- copy[0] = len;
- memcpy(&copy[1], skb_network_header(skb), len);
- req->saved_syn = copy;
+ saved_syn = kmalloc(struct_size(saved_syn, data, len),
+ GFP_ATOMIC);
+ if (saved_syn) {
+ saved_syn->mac_hdrlen = mac_hdrlen;
+ saved_syn->network_hdrlen = skb_network_header_len(skb);
+ saved_syn->tcp_hdrlen = tcp_hdrlen(skb);
+ memcpy(saved_syn->data, base, len);
+ req->saved_syn = saved_syn;
}
}
}
@@ -6752,7 +6842,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
}
if (fastopen_sk) {
af_ops->send_synack(fastopen_sk, dst, &fl, req,
- &foc, TCP_SYNACK_FASTOPEN);
+ &foc, TCP_SYNACK_FASTOPEN, skb);
/* Add the child socket directly into the accept queue */
if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
reqsk_fastopen_remove(fastopen_sk, req, false);
@@ -6770,7 +6860,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_timeout_init((struct sock *)req));
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :
- TCP_SYNACK_COOKIE);
+ TCP_SYNACK_COOKIE,
+ skb);
if (want_cookie) {
reqsk_free(req);
return 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 80b42d5c76fe..af27cfa9d8d3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -965,7 +965,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type)
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb)
{
const struct inet_request_sock *ireq = inet_rsk(req);
struct flowi4 fl4;
@@ -976,7 +977,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
return -1;
- skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+ skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 495dda2449fe..56c306e3cd2f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -548,6 +548,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->fastopen_req = NULL;
RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
+ bpf_skops_init_child(sk, newsk);
tcp_bpf_clone(sk, newsk);
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85ff417bda7f..ab79d36ed07f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -438,6 +438,7 @@ struct tcp_out_options {
u8 ws; /* window scale, 0 to disable */
u8 num_sack_blocks; /* number of SACK blocks to include */
u8 hash_size; /* bytes in hash_location */
+ u8 bpf_opt_len; /* length of BPF hdr option */
__u8 *hash_location; /* temporary pointer, overloaded */
__u32 tsval, tsecr; /* need to include OPTION_TS */
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
@@ -452,6 +453,145 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
#endif
}
+#ifdef CONFIG_CGROUP_BPF
+static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb,
+ enum tcp_synack_type synack_type)
+{
+ if (unlikely(!skb))
+ return BPF_WRITE_HDR_TCP_CURRENT_MSS;
+
+ if (unlikely(synack_type == TCP_SYNACK_COOKIE))
+ return BPF_WRITE_HDR_TCP_SYNACK_COOKIE;
+
+ return 0;
+}
+
+/* req, syn_skb and synack_type are used when writing synack */
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req,
+ struct sk_buff *syn_skb,
+ enum tcp_synack_type synack_type,
+ struct tcp_out_options *opts,
+ unsigned int *remaining)
+{
+ struct bpf_sock_ops_kern sock_ops;
+ int err;
+
+ if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) ||
+ !*remaining)
+ return;
+
+ /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */
+
+ /* init sock_ops */
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+ sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB;
+
+ if (req) {
+ /* The listen "sk" cannot be passed here because
+ * it is not locked. It would not make too much
+ * sense to do bpf_setsockopt(listen_sk) based
+ * on individual connection request also.
+ *
+ * Thus, "req" is passed here and the cgroup-bpf-progs
+ * of the listen "sk" will be run.
+ *
+ * "req" is also used here for fastopen even the "sk" here is
+ * a fullsock "child" sk. It is to keep the behavior
+ * consistent between fastopen and non-fastopen on
+ * the bpf programming side.
+ */
+ sock_ops.sk = (struct sock *)req;
+ sock_ops.syn_skb = syn_skb;
+ } else {
+ sock_owned_by_me(sk);
+
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ }
+
+ sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+ sock_ops.remaining_opt_len = *remaining;
+ /* tcp_current_mss() does not pass a skb */
+ if (skb)
+ bpf_skops_init_skb(&sock_ops, skb, 0);
+
+ err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+ if (err || sock_ops.remaining_opt_len == *remaining)
+ return;
+
+ opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len;
+ /* round up to 4 bytes */
+ opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3;
+
+ *remaining -= opts->bpf_opt_len;
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req,
+ struct sk_buff *syn_skb,
+ enum tcp_synack_type synack_type,
+ struct tcp_out_options *opts)
+{
+ u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len;
+ struct bpf_sock_ops_kern sock_ops;
+ int err;
+
+ if (likely(!max_opt_len))
+ return;
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+ sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
+
+ if (req) {
+ sock_ops.sk = (struct sock *)req;
+ sock_ops.syn_skb = syn_skb;
+ } else {
+ sock_owned_by_me(sk);
+
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ }
+
+ sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+ sock_ops.remaining_opt_len = max_opt_len;
+ first_opt_off = tcp_hdrlen(skb) - max_opt_len;
+ bpf_skops_init_skb(&sock_ops, skb, first_opt_off);
+
+ err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+ if (err)
+ nr_written = 0;
+ else
+ nr_written = max_opt_len - sock_ops.remaining_opt_len;
+
+ if (nr_written < max_opt_len)
+ memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP,
+ max_opt_len - nr_written);
+}
+#else
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req,
+ struct sk_buff *syn_skb,
+ enum tcp_synack_type synack_type,
+ struct tcp_out_options *opts,
+ unsigned int *remaining)
+{
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req,
+ struct sk_buff *syn_skb,
+ enum tcp_synack_type synack_type,
+ struct tcp_out_options *opts)
+{
+}
+#endif
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -691,6 +831,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
}
}
+ bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -701,7 +843,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
struct tcp_out_options *opts,
const struct tcp_md5sig_key *md5,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type)
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -758,6 +901,9 @@ static unsigned int tcp_synack_options(const struct sock *sk,
smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
+ bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
+ synack_type, opts, &remaining);
+
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -826,6 +972,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
}
+ if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
+ BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) {
+ unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+
+ bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
+ size = MAX_TCP_OPTION_SPACE - remaining;
+ }
+
return size;
}
@@ -1213,6 +1368,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
}
#endif
+ /* BPF prog is the last one writing header option */
+ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
+
INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check,
tcp_v6_send_check, tcp_v4_send_check,
sk, skb);
@@ -3336,20 +3494,20 @@ int tcp_send_synack(struct sock *sk)
}
/**
- * tcp_make_synack - Prepare a SYN-ACK.
- * sk: listener socket
- * dst: dst entry attached to the SYNACK
- * req: request_sock pointer
- * foc: cookie for tcp fast open
- * synack_type: Type of synback to prepare
- *
- * Allocate one skb and build a SYNACK packet.
- * @dst is consumed : Caller should not use it again.
+ * tcp_make_synack - Allocate one skb and build a SYNACK packet.
+ * @sk: listener socket
+ * @dst: dst entry attached to the SYNACK. It is consumed and caller
+ * should not use it again.
+ * @req: request_sock pointer
+ * @foc: cookie for tcp fast open
+ * @synack_type: Type of synack to prepare
+ * @syn_skb: SYN packet just received. It could be NULL for rtx case.
*/
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type)
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
const struct tcp_sock *tp = tcp_sk(sk);
@@ -3408,8 +3566,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
#endif
skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+ /* bpf program will be interested in the tcp_flags */
+ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
- foc, synack_type) + sizeof(*th);
+ foc, synack_type,
+ syn_skb) + sizeof(*th);
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
@@ -3441,6 +3602,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
rcu_read_unlock();
#endif
+ bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
+ synack_type, &opts);
+
skb->skb_mstamp_ns = now;
tcp_add_tx_delay(skb, tp);
@@ -3741,6 +3905,8 @@ void tcp_send_delayed_ack(struct sock *sk)
ato = min(ato, max_ato);
}
+ ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
+
/* Stay within the limit we were given */
timeout = jiffies + ato;
@@ -3934,7 +4100,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
int res;
tcp_rsk(req)->txhash = net_tx_rndhash();
- res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL);
+ res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
+ NULL);
if (!res) {
__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index eddd973e6575..7a94791efc1a 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -22,10 +22,9 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
prot->close = sock_map_close;
}
-static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
{
- if (sk->sk_family == AF_INET6 &&
- unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
+ if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
spin_lock_bh(&udpv6_prot_lock);
if (likely(ops != udpv6_prot_saved)) {
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
@@ -46,8 +45,8 @@ struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
{
int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
- if (!psock->sk_proto)
- udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot));
+ if (sk->sk_family == AF_INET6)
+ udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
return &udp_bpf_prots[family];
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 305870a72352..87a633e1fbef 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
- enum tcp_synack_type synack_type)
+ enum tcp_synack_type synack_type,
+ struct sk_buff *syn_skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = tcp_inet6_sk(sk);
@@ -515,7 +516,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
IPPROTO_TCP)) == NULL)
goto done;
- skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+ skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
if (skb) {
__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index e97db37354e4..a7227b447228 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -23,162 +23,6 @@
static DEFINE_IDA(umem_ida);
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
- unsigned long flags;
-
- if (!xs->tx)
- return;
-
- spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
- list_add_rcu(&xs->list, &umem->xsk_tx_list);
- spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
- unsigned long flags;
-
- if (!xs->tx)
- return;
-
- spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
- list_del_rcu(&xs->list);
- spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
-/* The umem is stored both in the _rx struct and the _tx struct as we do
- * not know if the device has more tx queues than rx, or the opposite.
- * This might also change during run time.
- */
-static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
- u16 queue_id)
-{
- if (queue_id >= max_t(unsigned int,
- dev->real_num_rx_queues,
- dev->real_num_tx_queues))
- return -EINVAL;
-
- if (queue_id < dev->real_num_rx_queues)
- dev->_rx[queue_id].umem = umem;
- if (queue_id < dev->real_num_tx_queues)
- dev->_tx[queue_id].umem = umem;
-
- return 0;
-}
-
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
- u16 queue_id)
-{
- if (queue_id < dev->real_num_rx_queues)
- return dev->_rx[queue_id].umem;
- if (queue_id < dev->real_num_tx_queues)
- return dev->_tx[queue_id].umem;
-
- return NULL;
-}
-EXPORT_SYMBOL(xdp_get_umem_from_qid);
-
-static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id)
-{
- if (queue_id < dev->real_num_rx_queues)
- dev->_rx[queue_id].umem = NULL;
- if (queue_id < dev->real_num_tx_queues)
- dev->_tx[queue_id].umem = NULL;
-}
-
-int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
- u16 queue_id, u16 flags)
-{
- bool force_zc, force_copy;
- struct netdev_bpf bpf;
- int err = 0;
-
- ASSERT_RTNL();
-
- force_zc = flags & XDP_ZEROCOPY;
- force_copy = flags & XDP_COPY;
-
- if (force_zc && force_copy)
- return -EINVAL;
-
- if (xdp_get_umem_from_qid(dev, queue_id))
- return -EBUSY;
-
- err = xdp_reg_umem_at_qid(dev, umem, queue_id);
- if (err)
- return err;
-
- 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_wakeup) {
- err = -EOPNOTSUPP;
- goto err_unreg_umem;
- }
-
- bpf.command = XDP_SETUP_XSK_UMEM;
- bpf.xsk.umem = umem;
- bpf.xsk.queue_id = queue_id;
-
- err = dev->netdev_ops->ndo_bpf(dev, &bpf);
- if (err)
- goto err_unreg_umem;
-
- umem->zc = true;
- return 0;
-
-err_unreg_umem:
- if (!force_zc)
- err = 0; /* fallback to copy mode */
- if (err)
- xdp_clear_umem_at_qid(dev, queue_id);
- return err;
-}
-
-void xdp_umem_clear_dev(struct xdp_umem *umem)
-{
- struct netdev_bpf bpf;
- int err;
-
- ASSERT_RTNL();
-
- if (!umem->dev)
- return;
-
- if (umem->zc) {
- bpf.command = XDP_SETUP_XSK_UMEM;
- bpf.xsk.umem = NULL;
- bpf.xsk.queue_id = umem->queue_id;
-
- err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
-
- if (err)
- WARN(1, "failed to disable umem!\n");
- }
-
- xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
-
- dev_put(umem->dev);
- umem->dev = NULL;
- umem->zc = false;
-}
-
static void xdp_umem_unpin_pages(struct xdp_umem *umem)
{
unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
@@ -195,38 +39,33 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
}
}
-static void xdp_umem_release(struct xdp_umem *umem)
+static void xdp_umem_addr_unmap(struct xdp_umem *umem)
{
- rtnl_lock();
- xdp_umem_clear_dev(umem);
- rtnl_unlock();
-
- ida_simple_remove(&umem_ida, umem->id);
+ vunmap(umem->addrs);
+ umem->addrs = NULL;
+}
- if (umem->fq) {
- xskq_destroy(umem->fq);
- umem->fq = NULL;
- }
+static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages,
+ u32 nr_pages)
+{
+ umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+ if (!umem->addrs)
+ return -ENOMEM;
+ return 0;
+}
- if (umem->cq) {
- xskq_destroy(umem->cq);
- umem->cq = NULL;
- }
+static void xdp_umem_release(struct xdp_umem *umem)
+{
+ umem->zc = false;
+ ida_simple_remove(&umem_ida, umem->id);
- xp_destroy(umem->pool);
+ xdp_umem_addr_unmap(umem);
xdp_umem_unpin_pages(umem);
xdp_umem_unaccount_pages(umem);
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);
@@ -237,10 +76,8 @@ 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);
- }
+ if (refcount_dec_and_test(&umem->users))
+ xdp_umem_release(umem);
}
static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
@@ -319,8 +156,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
return -EINVAL;
}
- if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG |
- XDP_UMEM_USES_NEED_WAKEUP))
+ if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
return -EINVAL;
if (!unaligned_chunks && !is_power_of_2(chunk_size))
@@ -356,13 +192,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
umem->size = size;
umem->headroom = headroom;
umem->chunk_size = chunk_size;
+ umem->chunks = chunks;
umem->npgs = (u32)npgs;
umem->pgs = NULL;
umem->user = NULL;
umem->flags = mr->flags;
- INIT_LIST_HEAD(&umem->xsk_tx_list);
- spin_lock_init(&umem->xsk_tx_list_lock);
+ INIT_LIST_HEAD(&umem->xsk_dma_list);
refcount_set(&umem->users, 1);
err = xdp_umem_account_pages(umem);
@@ -373,15 +209,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (err)
goto out_account;
- umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size,
- headroom, size, unaligned_chunks);
- if (!umem->pool) {
- err = -ENOMEM;
- goto out_pin;
- }
+ err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs);
+ if (err)
+ goto out_unpin;
+
return 0;
-out_pin:
+out_unpin:
xdp_umem_unpin_pages(umem);
out_account:
xdp_umem_unaccount_pages(umem);
@@ -413,8 +247,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr)
return umem;
}
-
-bool xdp_umem_validate_queues(struct xdp_umem *umem)
-{
- return umem->fq && umem->cq;
-}
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 32067fe98f65..181fdda2f2a8 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -8,14 +8,8 @@
#include <net/xdp_sock_drv.h>
-int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
- u16 queue_id, u16 flags);
-void xdp_umem_clear_dev(struct xdp_umem *umem);
-bool xdp_umem_validate_queues(struct xdp_umem *umem);
void xdp_get_umem(struct xdp_umem *umem);
void xdp_put_umem(struct xdp_umem *umem);
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr);
#endif /* XDP_UMEM_H_ */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index c3231620d210..5eb6662f562a 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -36,68 +36,108 @@ static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);
bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
{
return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) &&
- READ_ONCE(xs->umem->fq);
+ (xs->pool->fq || READ_ONCE(xs->fq_tmp));
}
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
{
- if (umem->need_wakeup & XDP_WAKEUP_RX)
+ if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
return;
- umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
- umem->need_wakeup |= XDP_WAKEUP_RX;
+ pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
+ pool->cached_need_wakeup |= XDP_WAKEUP_RX;
}
EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
{
struct xdp_sock *xs;
- if (umem->need_wakeup & XDP_WAKEUP_TX)
+ if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
return;
rcu_read_lock();
- list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+ list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
}
rcu_read_unlock();
- umem->need_wakeup |= XDP_WAKEUP_TX;
+ pool->cached_need_wakeup |= XDP_WAKEUP_TX;
}
EXPORT_SYMBOL(xsk_set_tx_need_wakeup);
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
{
- if (!(umem->need_wakeup & XDP_WAKEUP_RX))
+ if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX))
return;
- umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
- umem->need_wakeup &= ~XDP_WAKEUP_RX;
+ pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
+ pool->cached_need_wakeup &= ~XDP_WAKEUP_RX;
}
EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
{
struct xdp_sock *xs;
- if (!(umem->need_wakeup & XDP_WAKEUP_TX))
+ if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX))
return;
rcu_read_lock();
- list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+ list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP;
}
rcu_read_unlock();
- umem->need_wakeup &= ~XDP_WAKEUP_TX;
+ pool->cached_need_wakeup &= ~XDP_WAKEUP_TX;
}
EXPORT_SYMBOL(xsk_clear_tx_need_wakeup);
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
{
- return umem->flags & XDP_UMEM_USES_NEED_WAKEUP;
+ return pool->uses_need_wakeup;
+}
+EXPORT_SYMBOL(xsk_uses_need_wakeup);
+
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+ u16 queue_id)
+{
+ if (queue_id < dev->real_num_rx_queues)
+ return dev->_rx[queue_id].pool;
+ if (queue_id < dev->real_num_tx_queues)
+ return dev->_tx[queue_id].pool;
+
+ return NULL;
+}
+EXPORT_SYMBOL(xsk_get_pool_from_qid);
+
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
+{
+ if (queue_id < dev->real_num_rx_queues)
+ dev->_rx[queue_id].pool = NULL;
+ if (queue_id < dev->real_num_tx_queues)
+ dev->_tx[queue_id].pool = NULL;
+}
+
+/* The buffer pool is stored both in the _rx struct and the _tx struct as we do
+ * not know if the device has more tx queues than rx, or the opposite.
+ * This might also change during run time.
+ */
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+ u16 queue_id)
+{
+ if (queue_id >= max_t(unsigned int,
+ dev->real_num_rx_queues,
+ dev->real_num_tx_queues))
+ return -EINVAL;
+
+ if (queue_id < dev->real_num_rx_queues)
+ dev->_rx[queue_id].pool = pool;
+ if (queue_id < dev->real_num_tx_queues)
+ dev->_tx[queue_id].pool = pool;
+
+ return 0;
}
-EXPORT_SYMBOL(xsk_umem_uses_need_wakeup);
void xp_release(struct xdp_buff_xsk *xskb)
{
@@ -155,12 +195,12 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len,
struct xdp_buff *xsk_xdp;
int err;
- if (len > xsk_umem_get_rx_frame_size(xs->umem)) {
+ if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
xs->rx_dropped++;
return -ENOSPC;
}
- xsk_xdp = xsk_buff_alloc(xs->umem);
+ xsk_xdp = xsk_buff_alloc(xs->pool);
if (!xsk_xdp) {
xs->rx_dropped++;
return -ENOSPC;
@@ -208,7 +248,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,
static void xsk_flush(struct xdp_sock *xs)
{
xskq_prod_submit(xs->rx);
- __xskq_cons_release(xs->umem->fq);
+ __xskq_cons_release(xs->pool->fq);
sock_def_readable(&xs->sk);
}
@@ -249,32 +289,32 @@ void __xsk_map_flush(void)
}
}
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
{
- xskq_prod_submit_n(umem->cq, nb_entries);
+ xskq_prod_submit_n(pool->cq, nb_entries);
}
-EXPORT_SYMBOL(xsk_umem_complete_tx);
+EXPORT_SYMBOL(xsk_tx_completed);
-void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+void xsk_tx_release(struct xsk_buff_pool *pool)
{
struct xdp_sock *xs;
rcu_read_lock();
- list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+ list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
__xskq_cons_release(xs->tx);
xs->sk.sk_write_space(&xs->sk);
}
rcu_read_unlock();
}
-EXPORT_SYMBOL(xsk_umem_consume_tx_done);
+EXPORT_SYMBOL(xsk_tx_release);
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
{
struct xdp_sock *xs;
rcu_read_lock();
- list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
- if (!xskq_cons_peek_desc(xs->tx, desc, umem)) {
+ list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
+ if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
xs->tx->queue_empty_descs++;
continue;
}
@@ -284,7 +324,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
* if there is space in it. This avoids having to implement
* any buffering in the Tx path.
*/
- if (xskq_prod_reserve_addr(umem->cq, desc->addr))
+ if (xskq_prod_reserve_addr(pool->cq, desc->addr))
goto out;
xskq_cons_release(xs->tx);
@@ -296,7 +336,7 @@ out:
rcu_read_unlock();
return false;
}
-EXPORT_SYMBOL(xsk_umem_consume_tx);
+EXPORT_SYMBOL(xsk_tx_peek_desc);
static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
{
@@ -322,7 +362,7 @@ static void xsk_destruct_skb(struct sk_buff *skb)
unsigned long flags;
spin_lock_irqsave(&xs->tx_completion_lock, flags);
- xskq_prod_submit_addr(xs->umem->cq, addr);
+ xskq_prod_submit_addr(xs->pool->cq, addr);
spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
sock_wfree(skb);
@@ -342,7 +382,7 @@ static int xsk_generic_xmit(struct sock *sk)
if (xs->queue_id >= xs->dev->real_num_tx_queues)
goto out;
- while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) {
+ while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
char *buffer;
u64 addr;
u32 len;
@@ -359,14 +399,14 @@ static int xsk_generic_xmit(struct sock *sk)
skb_put(skb, len);
addr = desc.addr;
- buffer = xsk_buff_raw_get_data(xs->umem, addr);
+ buffer = xsk_buff_raw_get_data(xs->pool, addr);
err = skb_store_bits(skb, 0, buffer, len);
/* This is the backpressure mechanism for the Tx path.
* Reserve space in the completion queue and only proceed
* if there is space in it. This avoids having to implement
* any buffering in the Tx path.
*/
- if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) {
+ if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
kfree_skb(skb);
goto out;
}
@@ -431,16 +471,16 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
__poll_t mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
struct xdp_sock *xs = xdp_sk(sk);
- struct xdp_umem *umem;
+ struct xsk_buff_pool *pool;
if (unlikely(!xsk_is_bound(xs)))
return mask;
- umem = xs->umem;
+ pool = xs->pool;
- if (umem->need_wakeup) {
+ if (pool->cached_need_wakeup) {
if (xs->zc)
- xsk_wakeup(xs, umem->need_wakeup);
+ xsk_wakeup(xs, pool->cached_need_wakeup);
else
/* Poll needs to drive Tx also in copy mode */
__xsk_sendmsg(sk);
@@ -481,7 +521,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
WRITE_ONCE(xs->state, XSK_UNBOUND);
/* Wait for driver to stop using the xdp socket. */
- xdp_del_sk_umem(xs->umem, xs);
+ xp_del_xsk(xs->pool, xs);
xs->dev = NULL;
synchronize_net();
dev_put(dev);
@@ -559,6 +599,8 @@ static int xsk_release(struct socket *sock)
xskq_destroy(xs->rx);
xskq_destroy(xs->tx);
+ xskq_destroy(xs->fq_tmp);
+ xskq_destroy(xs->cq_tmp);
sock_orphan(sk);
sock->sk = NULL;
@@ -586,6 +628,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd)
return sock;
}
+static bool xsk_validate_queues(struct xdp_sock *xs)
+{
+ return xs->fq_tmp && xs->cq_tmp;
+}
+
static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
@@ -654,29 +701,64 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
sockfd_put(sock);
goto out_unlock;
}
- if (umem_xs->dev != dev || umem_xs->queue_id != qid) {
- err = -EINVAL;
- sockfd_put(sock);
- goto out_unlock;
+
+ if (umem_xs->queue_id != qid || umem_xs->dev != dev) {
+ /* Share the umem with another socket on another qid
+ * and/or device.
+ */
+ xs->pool = xp_create_and_assign_umem(xs,
+ umem_xs->umem);
+ if (!xs->pool) {
+ sockfd_put(sock);
+ goto out_unlock;
+ }
+
+ err = xp_assign_dev_shared(xs->pool, umem_xs->umem,
+ dev, qid);
+ if (err) {
+ xp_destroy(xs->pool);
+ sockfd_put(sock);
+ goto out_unlock;
+ }
+ } else {
+ /* Share the buffer pool with the other socket. */
+ if (xs->fq_tmp || xs->cq_tmp) {
+ /* Do not allow setting your own fq or cq. */
+ err = -EINVAL;
+ sockfd_put(sock);
+ goto out_unlock;
+ }
+
+ xp_get_pool(umem_xs->pool);
+ xs->pool = umem_xs->pool;
}
xdp_get_umem(umem_xs->umem);
WRITE_ONCE(xs->umem, umem_xs->umem);
sockfd_put(sock);
- } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
+ } else if (!xs->umem || !xsk_validate_queues(xs)) {
err = -EINVAL;
goto out_unlock;
} else {
/* This xsk has its own umem. */
- err = xdp_umem_assign_dev(xs->umem, dev, qid, flags);
- if (err)
+ xs->pool = xp_create_and_assign_umem(xs, xs->umem);
+ if (!xs->pool) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+
+ err = xp_assign_dev(xs->pool, dev, qid, flags);
+ if (err) {
+ xp_destroy(xs->pool);
+ xs->pool = NULL;
goto out_unlock;
+ }
}
xs->dev = dev;
xs->zc = xs->umem->zc;
xs->queue_id = qid;
- xdp_add_sk_umem(xs->umem, xs);
+ xp_add_xsk(xs->pool, xs);
out_unlock:
if (err) {
@@ -782,16 +864,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
mutex_unlock(&xs->mutex);
return -EBUSY;
}
- if (!xs->umem) {
- mutex_unlock(&xs->mutex);
- return -EINVAL;
- }
- q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :
- &xs->umem->cq;
+ q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp :
+ &xs->cq_tmp;
err = xsk_init_queue(entries, q, true);
- if (optname == XDP_UMEM_FILL_RING)
- xp_set_fq(xs->umem->pool, *q);
mutex_unlock(&xs->mutex);
return err;
}
@@ -858,7 +934,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
if (extra_stats) {
stats.rx_ring_full = xs->rx_queue_full;
stats.rx_fill_ring_empty_descs =
- xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+ xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx);
} else {
stats.rx_dropped += xs->rx_queue_full;
@@ -960,7 +1036,6 @@ static int xsk_mmap(struct file *file, struct socket *sock,
unsigned long size = vma->vm_end - vma->vm_start;
struct xdp_sock *xs = xdp_sk(sock->sk);
struct xsk_queue *q = NULL;
- struct xdp_umem *umem;
unsigned long pfn;
struct page *qpg;
@@ -972,16 +1047,12 @@ static int xsk_mmap(struct file *file, struct socket *sock,
} else if (offset == XDP_PGOFF_TX_RING) {
q = READ_ONCE(xs->tx);
} else {
- umem = READ_ONCE(xs->umem);
- if (!umem)
- return -EINVAL;
-
/* Matches the smp_wmb() in XDP_UMEM_REG */
smp_rmb();
if (offset == XDP_UMEM_PGOFF_FILL_RING)
- q = READ_ONCE(umem->fq);
+ q = READ_ONCE(xs->fq_tmp);
else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
- q = READ_ONCE(umem->cq);
+ q = READ_ONCE(xs->cq_tmp);
}
if (!q)
@@ -1019,8 +1090,8 @@ static int xsk_notifier(struct notifier_block *this,
xsk_unbind_dev(xs);
- /* Clear device references in umem. */
- xdp_umem_clear_dev(xs->umem);
+ /* Clear device references. */
+ xp_clear_dev(xs->pool);
}
mutex_unlock(&xs->mutex);
}
@@ -1064,7 +1135,7 @@ static void xsk_destruct(struct sock *sk)
if (!sock_flag(sk, SOCK_DEAD))
return;
- xdp_put_umem(xs->umem);
+ xp_put_pool(xs->pool);
sk_refcnt_debug_dec(sk);
}
@@ -1072,8 +1143,8 @@ static void xsk_destruct(struct sock *sk)
static int xsk_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
- struct sock *sk;
struct xdp_sock *xs;
+ struct sock *sk;
if (!ns_capable(net->user_ns, CAP_NET_RAW))
return -EPERM;
diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h
index 455ddd480f3d..da1f73e43924 100644
--- a/net/xdp/xsk.h
+++ b/net/xdp/xsk.h
@@ -11,13 +11,6 @@
#define XSK_NEXT_PG_CONTIG_SHIFT 0
#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
-/* Flags for the umem flags field.
- *
- * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public
- * flags. See inlude/uapi/include/linux/if_xdp.h.
- */
-#define XDP_UMEM_USES_NEED_WAKEUP BIT(1)
-
struct xdp_ring_offset_v1 {
__u64 producer;
__u64 consumer;
@@ -51,5 +44,8 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
struct xdp_sock **map_entry);
int xsk_map_inc(struct xsk_map *map);
void xsk_map_put(struct xsk_map *map);
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id);
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+ u16 queue_id);
#endif /* XSK_H_ */
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index a2044c245215..795d7c81c0ca 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -2,21 +2,37 @@
#include <net/xsk_buff_pool.h>
#include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/swiotlb.h>
#include "xsk_queue.h"
+#include "xdp_umem.h"
+#include "xsk.h"
-static void xp_addr_unmap(struct xsk_buff_pool *pool)
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
{
- vunmap(pool->addrs);
+ unsigned long flags;
+
+ if (!xs->tx)
+ return;
+
+ spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+ list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
+ spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
}
-static int xp_addr_map(struct xsk_buff_pool *pool,
- struct page **pages, u32 nr_pages)
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
{
- pool->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
- if (!pool->addrs)
- return -ENOMEM;
- return 0;
+ unsigned long flags;
+
+ if (!xs->tx)
+ return;
+
+ spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+ list_del_rcu(&xs->tx_list);
+ spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
}
void xp_destroy(struct xsk_buff_pool *pool)
@@ -24,59 +40,61 @@ void xp_destroy(struct xsk_buff_pool *pool)
if (!pool)
return;
- xp_addr_unmap(pool);
kvfree(pool->heads);
kvfree(pool);
}
-struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
- u32 chunk_size, u32 headroom, u64 size,
- bool unaligned)
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+ struct xdp_umem *umem)
{
struct xsk_buff_pool *pool;
struct xdp_buff_xsk *xskb;
- int err;
u32 i;
- pool = kvzalloc(struct_size(pool, free_heads, chunks), GFP_KERNEL);
+ pool = kvzalloc(struct_size(pool, free_heads, umem->chunks),
+ GFP_KERNEL);
if (!pool)
goto out;
- pool->heads = kvcalloc(chunks, sizeof(*pool->heads), GFP_KERNEL);
+ pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL);
if (!pool->heads)
goto out;
- pool->chunk_mask = ~((u64)chunk_size - 1);
- pool->addrs_cnt = size;
- pool->heads_cnt = chunks;
- pool->free_heads_cnt = chunks;
- pool->headroom = headroom;
- pool->chunk_size = chunk_size;
- pool->unaligned = unaligned;
- pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM;
+ pool->chunk_mask = ~((u64)umem->chunk_size - 1);
+ pool->addrs_cnt = umem->size;
+ pool->heads_cnt = umem->chunks;
+ pool->free_heads_cnt = umem->chunks;
+ pool->headroom = umem->headroom;
+ pool->chunk_size = umem->chunk_size;
+ pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+ pool->frame_len = umem->chunk_size - umem->headroom -
+ XDP_PACKET_HEADROOM;
+ pool->umem = umem;
+ pool->addrs = umem->addrs;
INIT_LIST_HEAD(&pool->free_list);
+ INIT_LIST_HEAD(&pool->xsk_tx_list);
+ spin_lock_init(&pool->xsk_tx_list_lock);
+ refcount_set(&pool->users, 1);
+
+ pool->fq = xs->fq_tmp;
+ pool->cq = xs->cq_tmp;
+ xs->fq_tmp = NULL;
+ xs->cq_tmp = NULL;
for (i = 0; i < pool->free_heads_cnt; i++) {
xskb = &pool->heads[i];
xskb->pool = pool;
- xskb->xdp.frame_sz = chunk_size - headroom;
+ xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
pool->free_heads[i] = xskb;
}
- err = xp_addr_map(pool, pages, nr_pages);
- if (!err)
- return pool;
+ return pool;
out:
xp_destroy(pool);
return NULL;
}
-void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq)
-{
- pool->fq = fq;
-}
-
void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
{
u32 i;
@@ -86,70 +104,320 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
}
EXPORT_SYMBOL(xp_set_rxq_info);
-void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
{
- dma_addr_t *dma;
- u32 i;
+ struct netdev_bpf bpf;
+ int err;
- if (pool->dma_pages_cnt == 0)
+ ASSERT_RTNL();
+
+ if (pool->umem->zc) {
+ bpf.command = XDP_SETUP_XSK_POOL;
+ bpf.xsk.pool = NULL;
+ bpf.xsk.queue_id = pool->queue_id;
+
+ err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);
+
+ if (err)
+ WARN(1, "Failed to disable zero-copy!\n");
+ }
+}
+
+static int __xp_assign_dev(struct xsk_buff_pool *pool,
+ struct net_device *netdev, u16 queue_id, u16 flags)
+{
+ bool force_zc, force_copy;
+ struct netdev_bpf bpf;
+ int err = 0;
+
+ ASSERT_RTNL();
+
+ force_zc = flags & XDP_ZEROCOPY;
+ force_copy = flags & XDP_COPY;
+
+ if (force_zc && force_copy)
+ return -EINVAL;
+
+ if (xsk_get_pool_from_qid(netdev, queue_id))
+ return -EBUSY;
+
+ pool->netdev = netdev;
+ pool->queue_id = queue_id;
+ err = xsk_reg_pool_at_qid(netdev, pool, queue_id);
+ if (err)
+ return err;
+
+ if (flags & XDP_USE_NEED_WAKEUP) {
+ pool->uses_need_wakeup = true;
+ /* 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().
+ */
+ pool->cached_need_wakeup = XDP_WAKEUP_TX;
+ }
+
+ dev_hold(netdev);
+
+ if (force_copy)
+ /* For copy-mode, we are done. */
+ return 0;
+
+ if (!netdev->netdev_ops->ndo_bpf ||
+ !netdev->netdev_ops->ndo_xsk_wakeup) {
+ err = -EOPNOTSUPP;
+ goto err_unreg_pool;
+ }
+
+ bpf.command = XDP_SETUP_XSK_POOL;
+ bpf.xsk.pool = pool;
+ bpf.xsk.queue_id = queue_id;
+
+ err = netdev->netdev_ops->ndo_bpf(netdev, &bpf);
+ if (err)
+ goto err_unreg_pool;
+
+ if (!pool->dma_pages) {
+ WARN(1, "Driver did not DMA map zero-copy buffers");
+ goto err_unreg_xsk;
+ }
+ pool->umem->zc = true;
+ return 0;
+
+err_unreg_xsk:
+ xp_disable_drv_zc(pool);
+err_unreg_pool:
+ if (!force_zc)
+ err = 0; /* fallback to copy mode */
+ if (err)
+ xsk_clear_pool_at_qid(netdev, queue_id);
+ return err;
+}
+
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+ u16 queue_id, u16 flags)
+{
+ return __xp_assign_dev(pool, dev, queue_id, flags);
+}
+
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+ struct net_device *dev, u16 queue_id)
+{
+ u16 flags;
+
+ /* One fill and completion ring required for each queue id. */
+ if (!pool->fq || !pool->cq)
+ return -EINVAL;
+
+ flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
+ if (pool->uses_need_wakeup)
+ flags |= XDP_USE_NEED_WAKEUP;
+
+ return __xp_assign_dev(pool, dev, queue_id, flags);
+}
+
+void xp_clear_dev(struct xsk_buff_pool *pool)
+{
+ if (!pool->netdev)
return;
- for (i = 0; i < pool->dma_pages_cnt; i++) {
- dma = &pool->dma_pages[i];
+ xp_disable_drv_zc(pool);
+ xsk_clear_pool_at_qid(pool->netdev, pool->queue_id);
+ dev_put(pool->netdev);
+ pool->netdev = NULL;
+}
+
+static void xp_release_deferred(struct work_struct *work)
+{
+ struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool,
+ work);
+
+ rtnl_lock();
+ xp_clear_dev(pool);
+ rtnl_unlock();
+
+ if (pool->fq) {
+ xskq_destroy(pool->fq);
+ pool->fq = NULL;
+ }
+
+ if (pool->cq) {
+ xskq_destroy(pool->cq);
+ pool->cq = NULL;
+ }
+
+ xdp_put_umem(pool->umem);
+ xp_destroy(pool);
+}
+
+void xp_get_pool(struct xsk_buff_pool *pool)
+{
+ refcount_inc(&pool->users);
+}
+
+void xp_put_pool(struct xsk_buff_pool *pool)
+{
+ if (!pool)
+ return;
+
+ if (refcount_dec_and_test(&pool->users)) {
+ INIT_WORK(&pool->work, xp_release_deferred);
+ schedule_work(&pool->work);
+ }
+}
+
+static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
+{
+ struct xsk_dma_map *dma_map;
+
+ list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) {
+ if (dma_map->netdev == pool->netdev)
+ return dma_map;
+ }
+
+ return NULL;
+}
+
+static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev,
+ u32 nr_pages, struct xdp_umem *umem)
+{
+ struct xsk_dma_map *dma_map;
+
+ dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL);
+ if (!dma_map)
+ return NULL;
+
+ dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL);
+ if (!dma_map) {
+ kfree(dma_map);
+ return NULL;
+ }
+
+ dma_map->netdev = netdev;
+ dma_map->dev = dev;
+ dma_map->dma_need_sync = false;
+ dma_map->dma_pages_cnt = nr_pages;
+ refcount_set(&dma_map->users, 0);
+ list_add(&dma_map->list, &umem->xsk_dma_list);
+ return dma_map;
+}
+
+static void xp_destroy_dma_map(struct xsk_dma_map *dma_map)
+{
+ list_del(&dma_map->list);
+ kvfree(dma_map->dma_pages);
+ kfree(dma_map);
+}
+
+static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
+{
+ dma_addr_t *dma;
+ u32 i;
+
+ for (i = 0; i < dma_map->dma_pages_cnt; i++) {
+ dma = &dma_map->dma_pages[i];
if (*dma) {
- dma_unmap_page_attrs(pool->dev, *dma, PAGE_SIZE,
+ dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
DMA_BIDIRECTIONAL, attrs);
*dma = 0;
}
}
+ xp_destroy_dma_map(dma_map);
+}
+
+void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+{
+ struct xsk_dma_map *dma_map;
+
+ if (pool->dma_pages_cnt == 0)
+ return;
+
+ dma_map = xp_find_dma_map(pool);
+ if (!dma_map) {
+ WARN(1, "Could not find dma_map for device");
+ return;
+ }
+
+ if (!refcount_dec_and_test(&dma_map->users))
+ return;
+
+ __xp_dma_unmap(dma_map, attrs);
kvfree(pool->dma_pages);
pool->dma_pages_cnt = 0;
pool->dev = NULL;
}
EXPORT_SYMBOL(xp_dma_unmap);
-static void xp_check_dma_contiguity(struct xsk_buff_pool *pool)
+static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map)
{
u32 i;
- for (i = 0; i < pool->dma_pages_cnt - 1; i++) {
- if (pool->dma_pages[i] + PAGE_SIZE == pool->dma_pages[i + 1])
- pool->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
+ for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) {
+ if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1])
+ dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
else
- pool->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
+ dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
}
}
+static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map)
+{
+ pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL);
+ if (!pool->dma_pages)
+ return -ENOMEM;
+
+ pool->dev = dma_map->dev;
+ pool->dma_pages_cnt = dma_map->dma_pages_cnt;
+ pool->dma_need_sync = dma_map->dma_need_sync;
+ refcount_inc(&dma_map->users);
+ memcpy(pool->dma_pages, dma_map->dma_pages,
+ pool->dma_pages_cnt * sizeof(*pool->dma_pages));
+
+ return 0;
+}
+
int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
unsigned long attrs, struct page **pages, u32 nr_pages)
{
+ struct xsk_dma_map *dma_map;
dma_addr_t dma;
+ int err;
u32 i;
- pool->dma_pages = kvcalloc(nr_pages, sizeof(*pool->dma_pages),
- GFP_KERNEL);
- if (!pool->dma_pages)
- return -ENOMEM;
+ dma_map = xp_find_dma_map(pool);
+ if (dma_map) {
+ err = xp_init_dma_info(pool, dma_map);
+ if (err)
+ return err;
+
+ return 0;
+ }
- pool->dev = dev;
- pool->dma_pages_cnt = nr_pages;
- pool->dma_need_sync = false;
+ dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem);
+ if (!dma_map)
+ return -ENOMEM;
- for (i = 0; i < pool->dma_pages_cnt; i++) {
+ for (i = 0; i < dma_map->dma_pages_cnt; i++) {
dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE,
DMA_BIDIRECTIONAL, attrs);
if (dma_mapping_error(dev, dma)) {
- xp_dma_unmap(pool, attrs);
+ __xp_dma_unmap(dma_map, attrs);
return -ENOMEM;
}
if (dma_need_sync(dev, dma))
- pool->dma_need_sync = true;
- pool->dma_pages[i] = dma;
+ dma_map->dma_need_sync = true;
+ dma_map->dma_pages[i] = dma;
}
if (pool->unaligned)
- xp_check_dma_contiguity(pool);
+ xp_check_dma_contiguity(dma_map);
+
+ err = xp_init_dma_info(pool, dma_map);
+ if (err) {
+ __xp_dma_unmap(dma_map, attrs);
+ return err;
+ }
+
return 0;
}
EXPORT_SYMBOL(xp_dma_map);
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 21e9c2d123ee..5bd8ea9d206a 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -46,6 +46,7 @@ static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs,
static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
{
+ struct xsk_buff_pool *pool = xs->pool;
struct xdp_umem *umem = xs->umem;
struct xdp_diag_umem du = {};
int err;
@@ -58,8 +59,8 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
du.num_pages = umem->npgs;
du.chunk_size = umem->chunk_size;
du.headroom = umem->headroom;
- du.ifindex = umem->dev ? umem->dev->ifindex : 0;
- du.queue_id = umem->queue_id;
+ du.ifindex = pool->netdev ? pool->netdev->ifindex : 0;
+ du.queue_id = pool->queue_id;
du.flags = 0;
if (umem->zc)
du.flags |= XDP_DU_F_ZEROCOPY;
@@ -67,10 +68,11 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du);
- if (!err && umem->fq)
- err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb);
- if (!err && umem->cq) {
- err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING,
+ if (!err && pool->fq)
+ err = xsk_diag_put_ring(pool->fq,
+ XDP_DIAG_UMEM_FILL_RING, nlskb);
+ if (!err && pool->cq) {
+ err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING,
nlskb);
}
return err;
@@ -83,7 +85,7 @@ static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb)
du.n_rx_dropped = xs->rx_dropped;
du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx);
du.n_rx_full = xs->rx_queue_full;
- du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+ du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx);
du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx);
return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index bf42cfd74b89..2d883f631c85 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -166,9 +166,9 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
struct xdp_desc *d,
- struct xdp_umem *umem)
+ struct xsk_buff_pool *pool)
{
- if (!xp_validate_desc(umem->pool, d)) {
+ if (!xp_validate_desc(pool, d)) {
q->invalid_descs++;
return false;
}
@@ -177,14 +177,14 @@ static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
static inline bool xskq_cons_read_desc(struct xsk_queue *q,
struct xdp_desc *desc,
- struct xdp_umem *umem)
+ struct xsk_buff_pool *pool)
{
while (q->cached_cons != q->cached_prod) {
struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
u32 idx = q->cached_cons & q->ring_mask;
*desc = ring->desc[idx];
- if (xskq_cons_is_valid_desc(q, desc, umem))
+ if (xskq_cons_is_valid_desc(q, desc, pool))
return true;
q->cached_cons++;
@@ -236,11 +236,11 @@ static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
static inline bool xskq_cons_peek_desc(struct xsk_queue *q,
struct xdp_desc *desc,
- struct xdp_umem *umem)
+ struct xsk_buff_pool *pool)
{
if (q->cached_prod == q->cached_cons)
xskq_cons_get_entries(q);
- return xskq_cons_read_desc(q, desc, umem);
+ return xskq_cons_read_desc(q, desc, pool);
}
static inline void xskq_cons_release(struct xsk_queue *q)
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 8367adbbe9df..2a4fd6677155 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -254,8 +254,16 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
spin_unlock_bh(&map->lock);
}
+static bool xsk_map_meta_equal(const struct bpf_map *meta0,
+ const struct bpf_map *meta1)
+{
+ return meta0->max_entries == meta1->max_entries &&
+ bpf_map_meta_equal(meta0, meta1);
+}
+
static int xsk_map_btf_id;
const struct bpf_map_ops xsk_map_ops = {
+ .map_meta_equal = xsk_map_meta_equal,
.map_alloc = xsk_map_alloc,
.map_free = xsk_map_free,
.map_get_next_key = xsk_map_get_next_key,