aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/Kconfig6
-rw-r--r--net/bpf/test_run.c244
-rw-r--r--net/core/Makefile6
-rw-r--r--net/core/bpf_sk_storage.c2
-rw-r--r--net/core/filter.c269
-rw-r--r--net/core/skmsg.c212
-rw-r--r--net/core/sock_map.c77
-rw-r--r--net/ipv4/Makefile2
-rw-r--r--net/ipv4/tcp_bpf.c4
-rw-r--r--net/xdp/xsk.c114
-rw-r--r--net/xdp/xsk_queue.h30
-rw-r--r--net/xdp/xskmap.c17
12 files changed, 572 insertions, 411 deletions
diff --git a/net/Kconfig b/net/Kconfig
index 8cea808ad9e8..0ead7ec0d2bd 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -317,13 +317,9 @@ config BPF_STREAM_PARSER
select STREAM_PARSER
select NET_SOCK_MSG
help
- Enabling this allows a stream parser to be used with
+ Enabling this allows a TCP stream parser to be used with
BPF_MAP_TYPE_SOCKMAP.
- BPF_MAP_TYPE_SOCKMAP provides a map type to use with network sockets.
- It can be used to enforce socket policy, implement socket redirects,
- etc.
-
config NET_FLOW_LIMIT
bool
depends on RPS
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 58bcb8c849d5..0abdd67f44b1 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -10,20 +10,86 @@
#include <net/bpf_sk_storage.h>
#include <net/sock.h>
#include <net/tcp.h>
+#include <net/net_namespace.h>
#include <linux/error-injection.h>
#include <linux/smp.h>
+#include <linux/sock_diag.h>
#define CREATE_TRACE_POINTS
#include <trace/events/bpf_test_run.h>
+struct bpf_test_timer {
+ enum { NO_PREEMPT, NO_MIGRATE } mode;
+ u32 i;
+ u64 time_start, time_spent;
+};
+
+static void bpf_test_timer_enter(struct bpf_test_timer *t)
+ __acquires(rcu)
+{
+ rcu_read_lock();
+ if (t->mode == NO_PREEMPT)
+ preempt_disable();
+ else
+ migrate_disable();
+
+ t->time_start = ktime_get_ns();
+}
+
+static void bpf_test_timer_leave(struct bpf_test_timer *t)
+ __releases(rcu)
+{
+ t->time_start = 0;
+
+ if (t->mode == NO_PREEMPT)
+ preempt_enable();
+ else
+ migrate_enable();
+ rcu_read_unlock();
+}
+
+static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration)
+ __must_hold(rcu)
+{
+ t->i++;
+ if (t->i >= repeat) {
+ /* We're done. */
+ t->time_spent += ktime_get_ns() - t->time_start;
+ do_div(t->time_spent, t->i);
+ *duration = t->time_spent > U32_MAX ? U32_MAX : (u32)t->time_spent;
+ *err = 0;
+ goto reset;
+ }
+
+ if (signal_pending(current)) {
+ /* During iteration: we've been cancelled, abort. */
+ *err = -EINTR;
+ goto reset;
+ }
+
+ if (need_resched()) {
+ /* During iteration: we need to reschedule between runs. */
+ t->time_spent += ktime_get_ns() - t->time_start;
+ bpf_test_timer_leave(t);
+ cond_resched();
+ bpf_test_timer_enter(t);
+ }
+
+ /* Do another round. */
+ return true;
+
+reset:
+ t->i = 0;
+ return false;
+}
+
static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
u32 *retval, u32 *time, bool xdp)
{
struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL };
+ struct bpf_test_timer t = { NO_MIGRATE };
enum bpf_cgroup_storage_type stype;
- u64 time_start, time_spent = 0;
- int ret = 0;
- u32 i;
+ int ret;
for_each_cgroup_storage_type(stype) {
storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
@@ -38,40 +104,16 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
if (!repeat)
repeat = 1;
- rcu_read_lock();
- migrate_disable();
- time_start = ktime_get_ns();
- for (i = 0; i < repeat; i++) {
+ bpf_test_timer_enter(&t);
+ do {
bpf_cgroup_storage_set(storage);
if (xdp)
*retval = bpf_prog_run_xdp(prog, ctx);
else
*retval = BPF_PROG_RUN(prog, ctx);
-
- if (signal_pending(current)) {
- ret = -EINTR;
- break;
- }
-
- if (need_resched()) {
- time_spent += ktime_get_ns() - time_start;
- migrate_enable();
- rcu_read_unlock();
-
- cond_resched();
-
- rcu_read_lock();
- migrate_disable();
- time_start = ktime_get_ns();
- }
- }
- time_spent += ktime_get_ns() - time_start;
- migrate_enable();
- rcu_read_unlock();
-
- do_div(time_spent, repeat);
- *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+ } while (bpf_test_timer_continue(&t, repeat, &ret, time));
+ bpf_test_timer_leave(&t);
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
@@ -674,18 +716,17 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
+ struct bpf_test_timer t = { NO_PREEMPT };
u32 size = kattr->test.data_size_in;
struct bpf_flow_dissector ctx = {};
u32 repeat = kattr->test.repeat;
struct bpf_flow_keys *user_ctx;
struct bpf_flow_keys flow_keys;
- u64 time_start, time_spent = 0;
const struct ethhdr *eth;
unsigned int flags = 0;
u32 retval, duration;
void *data;
int ret;
- u32 i;
if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
return -EINVAL;
@@ -721,48 +762,127 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
ctx.data = data;
ctx.data_end = (__u8 *)data + size;
- rcu_read_lock();
- preempt_disable();
- time_start = ktime_get_ns();
- for (i = 0; i < repeat; i++) {
+ bpf_test_timer_enter(&t);
+ do {
retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN,
size, flags);
+ } while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
+ bpf_test_timer_leave(&t);
- if (signal_pending(current)) {
- preempt_enable();
- rcu_read_unlock();
+ if (ret < 0)
+ goto out;
- ret = -EINTR;
- goto out;
- }
+ ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
+ retval, duration);
+ if (!ret)
+ ret = bpf_ctx_finish(kattr, uattr, user_ctx,
+ sizeof(struct bpf_flow_keys));
- if (need_resched()) {
- time_spent += ktime_get_ns() - time_start;
- preempt_enable();
- rcu_read_unlock();
+out:
+ kfree(user_ctx);
+ kfree(data);
+ return ret;
+}
- cond_resched();
+int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr,
+ union bpf_attr __user *uattr)
+{
+ struct bpf_test_timer t = { NO_PREEMPT };
+ struct bpf_prog_array *progs = NULL;
+ struct bpf_sk_lookup_kern ctx = {};
+ u32 repeat = kattr->test.repeat;
+ struct bpf_sk_lookup *user_ctx;
+ u32 retval, duration;
+ int ret = -EINVAL;
- rcu_read_lock();
- preempt_disable();
- time_start = ktime_get_ns();
- }
+ if (prog->type != BPF_PROG_TYPE_SK_LOOKUP)
+ return -EINVAL;
+
+ if (kattr->test.flags || kattr->test.cpu)
+ return -EINVAL;
+
+ if (kattr->test.data_in || kattr->test.data_size_in || kattr->test.data_out ||
+ kattr->test.data_size_out)
+ return -EINVAL;
+
+ if (!repeat)
+ repeat = 1;
+
+ user_ctx = bpf_ctx_init(kattr, sizeof(*user_ctx));
+ if (IS_ERR(user_ctx))
+ return PTR_ERR(user_ctx);
+
+ if (!user_ctx)
+ return -EINVAL;
+
+ if (user_ctx->sk)
+ goto out;
+
+ if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx)))
+ goto out;
+
+ if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) {
+ ret = -ERANGE;
+ goto out;
}
- time_spent += ktime_get_ns() - time_start;
- preempt_enable();
- rcu_read_unlock();
- do_div(time_spent, repeat);
- duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+ ctx.family = (u16)user_ctx->family;
+ ctx.protocol = (u16)user_ctx->protocol;
+ ctx.dport = (u16)user_ctx->local_port;
+ ctx.sport = (__force __be16)user_ctx->remote_port;
- ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
- retval, duration);
+ switch (ctx.family) {
+ case AF_INET:
+ ctx.v4.daddr = (__force __be32)user_ctx->local_ip4;
+ ctx.v4.saddr = (__force __be32)user_ctx->remote_ip4;
+ break;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ ctx.v6.daddr = (struct in6_addr *)user_ctx->local_ip6;
+ ctx.v6.saddr = (struct in6_addr *)user_ctx->remote_ip6;
+ break;
+#endif
+
+ default:
+ ret = -EAFNOSUPPORT;
+ goto out;
+ }
+
+ progs = bpf_prog_array_alloc(1, GFP_KERNEL);
+ if (!progs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ progs->items[0].prog = prog;
+
+ bpf_test_timer_enter(&t);
+ do {
+ ctx.selected_sk = NULL;
+ retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN);
+ } while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
+ bpf_test_timer_leave(&t);
+
+ if (ret < 0)
+ goto out;
+
+ user_ctx->cookie = 0;
+ if (ctx.selected_sk) {
+ if (ctx.selected_sk->sk_reuseport && !ctx.no_reuseport) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
+ user_ctx->cookie = sock_gen_cookie(ctx.selected_sk);
+ }
+
+ ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration);
if (!ret)
- ret = bpf_ctx_finish(kattr, uattr, user_ctx,
- sizeof(struct bpf_flow_keys));
+ ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx));
out:
+ bpf_prog_array_free(progs);
kfree(user_ctx);
- kfree(data);
return ret;
}
diff --git a/net/core/Makefile b/net/core/Makefile
index 3e2c378e5f31..0c2233c826fd 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -16,7 +16,6 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \
obj-y += net-sysfs.o
obj-$(CONFIG_PAGE_POOL) += page_pool.o
obj-$(CONFIG_PROC_FS) += net-procfs.o
-obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
obj-$(CONFIG_NET_PKTGEN) += pktgen.o
obj-$(CONFIG_NETPOLL) += netpoll.o
obj-$(CONFIG_FIB_RULES) += fib_rules.o
@@ -28,10 +27,13 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
obj-$(CONFIG_LWTUNNEL) += lwtunnel.o
obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o
-obj-$(CONFIG_BPF_STREAM_PARSER) += sock_map.o
obj-$(CONFIG_DST_CACHE) += dst_cache.o
obj-$(CONFIG_HWBM) += hwbm.o
obj-$(CONFIG_NET_DEVLINK) += devlink.o
obj-$(CONFIG_GRO_CELLS) += gro_cells.o
obj-$(CONFIG_FAILOVER) += failover.o
+ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o
+obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
+endif
obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 4edd033e899c..cc3712ad8716 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -89,7 +89,7 @@ static void bpf_sk_storage_map_free(struct bpf_map *map)
smap = (struct bpf_local_storage_map *)map;
bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
- bpf_local_storage_map_free(smap);
+ bpf_local_storage_map_free(smap, NULL);
}
static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
diff --git a/net/core/filter.c b/net/core/filter.c
index adfdad234674..b6732000d8a2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1863,10 +1863,7 @@ static const struct bpf_func_proto bpf_sk_fullsock_proto = {
static inline int sk_skb_try_make_writable(struct sk_buff *skb,
unsigned int write_len)
{
- int err = __bpf_try_make_writable(skb, write_len);
-
- bpf_compute_data_end_sk_skb(skb);
- return err;
+ return __bpf_try_make_writable(skb, write_len);
}
BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
@@ -3412,6 +3409,7 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
+ BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \
BPF_F_ADJ_ROOM_ENCAP_L2( \
BPF_ADJ_ROOM_ENCAP_L2_MASK))
@@ -3448,6 +3446,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
return -EINVAL;
+ if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH &&
+ inner_mac_len < ETH_HLEN)
+ return -EINVAL;
+
if (skb->encapsulation)
return -EALREADY;
@@ -3466,7 +3468,11 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
skb->inner_mac_header = inner_net - inner_mac_len;
skb->inner_network_header = inner_net;
skb->inner_transport_header = inner_trans;
- skb_set_inner_protocol(skb, skb->protocol);
+
+ if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH)
+ skb_set_inner_protocol(skb, htons(ETH_P_TEB));
+ else
+ skb_set_inner_protocol(skb, skb->protocol);
skb->encapsulation = 1;
skb_set_network_header(skb, mac_len);
@@ -3577,7 +3583,6 @@ BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
return -ENOMEM;
__skb_pull(skb, len_diff_abs);
}
- bpf_compute_data_end_sk_skb(skb);
if (tls_sw_has_ctx_rx(skb->sk)) {
struct strp_msg *rxm = strp_msg(skb);
@@ -3742,10 +3747,7 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len,
u64, flags)
{
- int ret = __bpf_skb_change_tail(skb, new_len, flags);
-
- bpf_compute_data_end_sk_skb(skb);
- return ret;
+ return __bpf_skb_change_tail(skb, new_len, flags);
}
static const struct bpf_func_proto sk_skb_change_tail_proto = {
@@ -3808,10 +3810,7 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room,
u64, flags)
{
- int ret = __bpf_skb_change_head(skb, head_room, flags);
-
- bpf_compute_data_end_sk_skb(skb);
- return ret;
+ return __bpf_skb_change_head(skb, head_room, flags);
}
static const struct bpf_func_proto sk_skb_change_head_proto = {
@@ -3919,23 +3918,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
.arg2_type = ARG_ANYTHING,
};
-static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
- struct bpf_map *map, struct xdp_buff *xdp)
-{
- switch (map->map_type) {
- case BPF_MAP_TYPE_DEVMAP:
- case BPF_MAP_TYPE_DEVMAP_HASH:
- return dev_map_enqueue(fwd, xdp, dev_rx);
- case BPF_MAP_TYPE_CPUMAP:
- return cpu_map_enqueue(fwd, xdp, dev_rx);
- case BPF_MAP_TYPE_XSKMAP:
- return __xsk_map_redirect(fwd, xdp);
- default:
- return -EBADRQC;
- }
- return 0;
-}
-
void xdp_do_flush(void)
{
__dev_flush();
@@ -3944,71 +3926,52 @@ void xdp_do_flush(void)
}
EXPORT_SYMBOL_GPL(xdp_do_flush);
-static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
-{
- switch (map->map_type) {
- case BPF_MAP_TYPE_DEVMAP:
- return __dev_map_lookup_elem(map, index);
- case BPF_MAP_TYPE_DEVMAP_HASH:
- return __dev_map_hash_lookup_elem(map, index);
- case BPF_MAP_TYPE_CPUMAP:
- return __cpu_map_lookup_elem(map, index);
- case BPF_MAP_TYPE_XSKMAP:
- return __xsk_map_lookup_elem(map, index);
- default:
- return NULL;
- }
-}
-
-void bpf_clear_redirect_map(struct bpf_map *map)
-{
- struct bpf_redirect_info *ri;
- int cpu;
-
- for_each_possible_cpu(cpu) {
- ri = per_cpu_ptr(&bpf_redirect_info, cpu);
- /* Avoid polluting remote cacheline due to writes if
- * not needed. Once we pass this test, we need the
- * cmpxchg() to make sure it hasn't been changed in
- * the meantime by remote CPU.
- */
- if (unlikely(READ_ONCE(ri->map) == map))
- cmpxchg(&ri->map, map, NULL);
- }
-}
-
int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
- struct bpf_map *map = READ_ONCE(ri->map);
- u32 index = ri->tgt_index;
+ enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
+ u32 map_id = ri->map_id;
int err;
- ri->tgt_index = 0;
- ri->tgt_value = NULL;
- WRITE_ONCE(ri->map, NULL);
+ ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
+ ri->map_type = BPF_MAP_TYPE_UNSPEC;
- if (unlikely(!map)) {
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
- if (unlikely(!fwd)) {
- err = -EINVAL;
- goto err;
+ switch (map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ fallthrough;
+ case BPF_MAP_TYPE_DEVMAP_HASH:
+ err = dev_map_enqueue(fwd, xdp, dev);
+ break;
+ case BPF_MAP_TYPE_CPUMAP:
+ err = cpu_map_enqueue(fwd, xdp, dev);
+ break;
+ case BPF_MAP_TYPE_XSKMAP:
+ err = __xsk_map_redirect(fwd, xdp);
+ break;
+ case BPF_MAP_TYPE_UNSPEC:
+ if (map_id == INT_MAX) {
+ fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
+ break;
+ }
+ err = dev_xdp_enqueue(fwd, xdp, dev);
+ break;
}
-
- err = dev_xdp_enqueue(fwd, xdp, dev);
- } else {
- err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+ fallthrough;
+ default:
+ err = -EBADRQC;
}
if (unlikely(err))
goto err;
- _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+ _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index);
return 0;
err:
- _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+ _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err);
return err;
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
@@ -4017,41 +3980,36 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
struct bpf_prog *xdp_prog,
- struct bpf_map *map)
+ void *fwd,
+ enum bpf_map_type map_type, u32 map_id)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
- u32 index = ri->tgt_index;
- void *fwd = ri->tgt_value;
- int err = 0;
-
- ri->tgt_index = 0;
- ri->tgt_value = NULL;
- WRITE_ONCE(ri->map, NULL);
-
- if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
- map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
- struct bpf_dtab_netdev *dst = fwd;
+ int err;
- err = dev_map_generic_redirect(dst, skb, xdp_prog);
+ switch (map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ fallthrough;
+ case BPF_MAP_TYPE_DEVMAP_HASH:
+ err = dev_map_generic_redirect(fwd, skb, xdp_prog);
if (unlikely(err))
goto err;
- } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
- struct xdp_sock *xs = fwd;
-
- err = xsk_generic_rcv(xs, xdp);
+ break;
+ case BPF_MAP_TYPE_XSKMAP:
+ err = xsk_generic_rcv(fwd, xdp);
if (err)
goto err;
consume_skb(skb);
- } else {
+ break;
+ default:
/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
err = -EBADRQC;
goto err;
}
- _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+ _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index);
return 0;
err:
- _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+ _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err);
return err;
}
@@ -4059,31 +4017,34 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
- struct bpf_map *map = READ_ONCE(ri->map);
- u32 index = ri->tgt_index;
- struct net_device *fwd;
- int err = 0;
-
- if (map)
- return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog,
- map);
- ri->tgt_index = 0;
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
- if (unlikely(!fwd)) {
- err = -EINVAL;
- goto err;
- }
+ enum bpf_map_type map_type = ri->map_type;
+ void *fwd = ri->tgt_value;
+ u32 map_id = ri->map_id;
+ int err;
- err = xdp_ok_fwd_dev(fwd, skb->len);
- if (unlikely(err))
- goto err;
+ ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
+ ri->map_type = BPF_MAP_TYPE_UNSPEC;
- skb->dev = fwd;
- _trace_xdp_redirect(dev, xdp_prog, index);
- generic_xdp_tx(skb, xdp_prog);
- return 0;
+ if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
+ fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
+ goto err;
+ }
+
+ err = xdp_ok_fwd_dev(fwd, skb->len);
+ if (unlikely(err))
+ goto err;
+
+ skb->dev = fwd;
+ _trace_xdp_redirect(dev, xdp_prog, ri->tgt_index);
+ generic_xdp_tx(skb, xdp_prog);
+ return 0;
+ }
+
+ return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id);
err:
- _trace_xdp_redirect_err(dev, xdp_prog, index, err);
+ _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err);
return err;
}
@@ -4094,10 +4055,12 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
if (unlikely(flags))
return XDP_ABORTED;
- ri->flags = flags;
+ /* NB! Map type UNSPEC and map_id == INT_MAX (never generated
+ * by map_idr) is used for ifindex based XDP redirect.
+ */
ri->tgt_index = ifindex;
- ri->tgt_value = NULL;
- WRITE_ONCE(ri->map, NULL);
+ ri->map_id = INT_MAX;
+ ri->map_type = BPF_MAP_TYPE_UNSPEC;
return XDP_REDIRECT;
}
@@ -4113,28 +4076,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex,
u64, flags)
{
- struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-
- /* Lower bits of the flags are used as return code on lookup failure */
- if (unlikely(flags > XDP_TX))
- return XDP_ABORTED;
-
- ri->tgt_value = __xdp_map_lookup_elem(map, ifindex);
- if (unlikely(!ri->tgt_value)) {
- /* If the lookup fails we want to clear out the state in the
- * redirect_info struct completely, so that if an eBPF program
- * performs multiple lookups, the last one always takes
- * precedence.
- */
- WRITE_ONCE(ri->map, NULL);
- return flags;
- }
-
- ri->flags = flags;
- ri->tgt_index = ifindex;
- WRITE_ONCE(ri->map, map);
-
- return XDP_REDIRECT;
+ return map->ops->map_redirect(map, ifindex, flags);
}
static const struct bpf_func_proto bpf_xdp_redirect_map_proto = {
@@ -9655,22 +9597,40 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
return insn - insn_buf;
}
+/* data_end = skb->data + skb_headlen() */
+static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si,
+ struct bpf_insn *insn)
+{
+ /* si->dst_reg = skb->data */
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, data));
+ /* AX = skb->len */
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len),
+ BPF_REG_AX, si->src_reg,
+ offsetof(struct sk_buff, len));
+ /* si->dst_reg = skb->data + skb->len */
+ *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
+ /* AX = skb->data_len */
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len),
+ BPF_REG_AX, si->src_reg,
+ offsetof(struct sk_buff, data_len));
+ /* si->dst_reg = skb->data + skb->len - skb->data_len */
+ *insn++ = BPF_ALU64_REG(BPF_SUB, si->dst_reg, BPF_REG_AX);
+
+ return insn;
+}
+
static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog, u32 *target_size)
{
struct bpf_insn *insn = insn_buf;
- int off;
switch (si->off) {
case offsetof(struct __sk_buff, data_end):
- off = si->off;
- off -= offsetof(struct __sk_buff, data_end);
- off += offsetof(struct sk_buff, cb);
- off += offsetof(struct tcp_skb_cb, bpf.data_end);
- *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
- si->src_reg, off);
+ insn = bpf_convert_data_end_access(si, insn);
break;
default:
return bpf_convert_ctx_access(type, si, insn_buf, prog,
@@ -10449,6 +10409,7 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type,
}
const struct bpf_prog_ops sk_lookup_prog_ops = {
+ .test_run = bpf_prog_test_run_sk_lookup,
};
const struct bpf_verifier_ops sk_lookup_verifier_ops = {
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 1261512d6807..07f54015238a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -525,7 +525,8 @@ static void sk_psock_backlog(struct work_struct *work)
len = skb->len;
off = 0;
start:
- ingress = tcp_skb_bpf_ingress(skb);
+ ingress = skb_bpf_ingress(skb);
+ skb_bpf_redirect_clear(skb);
do {
ret = -EIO;
if (likely(psock->sk->sk_socket))
@@ -618,7 +619,7 @@ struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock)
return link;
}
-void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
+static void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
{
struct sk_msg *msg, *tmp;
@@ -631,7 +632,12 @@ void __sk_psock_purge_ingress_msg(struct sk_psock *psock)
static void sk_psock_zap_ingress(struct sk_psock *psock)
{
- __skb_queue_purge(&psock->ingress_skb);
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue(&psock->ingress_skb)) != NULL) {
+ skb_bpf_redirect_clear(skb);
+ kfree_skb(skb);
+ }
__sk_psock_purge_ingress_msg(psock);
}
@@ -645,15 +651,15 @@ static void sk_psock_link_destroy(struct sk_psock *psock)
}
}
+static void sk_psock_done_strp(struct sk_psock *psock);
+
static void sk_psock_destroy_deferred(struct work_struct *gc)
{
struct sk_psock *psock = container_of(gc, struct sk_psock, gc);
/* No sk_callback_lock since already detached. */
- /* Parser has been stopped */
- if (psock->progs.skb_parser)
- strp_done(&psock->parser.strp);
+ sk_psock_done_strp(psock);
cancel_work_sync(&psock->work);
@@ -685,9 +691,9 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
write_lock_bh(&sk->sk_callback_lock);
sk_psock_restore_proto(sk, psock);
rcu_assign_sk_user_data(sk, NULL);
- if (psock->progs.skb_parser)
+ if (psock->progs.stream_parser)
sk_psock_stop_strp(sk, psock);
- else if (psock->progs.skb_verdict)
+ else if (psock->progs.stream_verdict)
sk_psock_stop_verdict(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
@@ -743,27 +749,12 @@ out:
}
EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
-static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog,
- struct sk_buff *skb)
-{
- bpf_compute_data_end_sk_skb(skb);
- return bpf_prog_run_pin_on_cpu(prog, skb);
-}
-
-static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
-{
- struct sk_psock_parser *parser;
-
- parser = container_of(strp, struct sk_psock_parser, strp);
- return container_of(parser, struct sk_psock, parser);
-}
-
static void sk_psock_skb_redirect(struct sk_buff *skb)
{
struct sk_psock *psock_other;
struct sock *sk_other;
- sk_other = tcp_skb_bpf_redirect_fetch(skb);
+ sk_other = skb_bpf_redirect_fetch(skb);
/* This error is a buggy BPF program, it returned a redirect
* return code, but then didn't set a redirect interface.
*/
@@ -806,16 +797,17 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
int ret = __SK_PASS;
rcu_read_lock();
- prog = READ_ONCE(psock->progs.skb_verdict);
+ prog = READ_ONCE(psock->progs.stream_verdict);
if (likely(prog)) {
/* We skip full set_owner_r here because if we do a SK_PASS
* or SK_DROP we can skip skb memory accounting and use the
* TLS context.
*/
skb->sk = psock->sk;
- tcp_skb_bpf_redirect_clear(skb);
- ret = sk_psock_bpf_run(psock, prog, skb);
- ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+ skb_dst_drop(skb);
+ skb_bpf_redirect_clear(skb);
+ ret = bpf_prog_run_pin_on_cpu(prog, skb);
+ ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
skb->sk = NULL;
}
sk_psock_tls_verdict_apply(skb, psock->sk, ret);
@@ -827,7 +819,6 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
static void sk_psock_verdict_apply(struct sk_psock *psock,
struct sk_buff *skb, int verdict)
{
- struct tcp_skb_cb *tcp;
struct sock *sk_other;
int err = -EIO;
@@ -839,8 +830,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
goto out_free;
}
- tcp = TCP_SKB_CB(skb);
- tcp->bpf.flags |= BPF_F_INGRESS;
+ skb_bpf_set_ingress(skb);
/* If the queue is empty then we can submit directly
* into the msg queue. If its not empty we have to
@@ -866,6 +856,24 @@ out_free:
}
}
+static void sk_psock_write_space(struct sock *sk)
+{
+ struct sk_psock *psock;
+ void (*write_space)(struct sock *sk) = NULL;
+
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (likely(psock)) {
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+ schedule_work(&psock->work);
+ write_space = psock->saved_write_space;
+ }
+ rcu_read_unlock();
+ if (write_space)
+ write_space(sk);
+}
+
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
struct sk_psock *psock;
@@ -881,11 +889,12 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
goto out;
}
skb_set_owner_r(skb, sk);
- prog = READ_ONCE(psock->progs.skb_verdict);
+ prog = READ_ONCE(psock->progs.stream_verdict);
if (likely(prog)) {
- tcp_skb_bpf_redirect_clear(skb);
- ret = sk_psock_bpf_run(psock, prog, skb);
- ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+ skb_dst_drop(skb);
+ skb_bpf_redirect_clear(skb);
+ ret = bpf_prog_run_pin_on_cpu(prog, skb);
+ ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
}
sk_psock_verdict_apply(psock, skb, ret);
out:
@@ -899,15 +908,15 @@ static int sk_psock_strp_read_done(struct strparser *strp, int err)
static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
{
- struct sk_psock *psock = sk_psock_from_strp(strp);
+ struct sk_psock *psock = container_of(strp, struct sk_psock, strp);
struct bpf_prog *prog;
int ret = skb->len;
rcu_read_lock();
- prog = READ_ONCE(psock->progs.skb_parser);
+ prog = READ_ONCE(psock->progs.stream_parser);
if (likely(prog)) {
skb->sk = psock->sk;
- ret = sk_psock_bpf_run(psock, prog, skb);
+ ret = bpf_prog_run_pin_on_cpu(prog, skb);
skb->sk = NULL;
}
rcu_read_unlock();
@@ -923,16 +932,59 @@ static void sk_psock_strp_data_ready(struct sock *sk)
psock = sk_psock(sk);
if (likely(psock)) {
if (tls_sw_has_ctx_rx(sk)) {
- psock->parser.saved_data_ready(sk);
+ psock->saved_data_ready(sk);
} else {
write_lock_bh(&sk->sk_callback_lock);
- strp_data_ready(&psock->parser.strp);
+ strp_data_ready(&psock->strp);
write_unlock_bh(&sk->sk_callback_lock);
}
}
rcu_read_unlock();
}
+int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
+{
+ static const struct strp_callbacks cb = {
+ .rcv_msg = sk_psock_strp_read,
+ .read_sock_done = sk_psock_strp_read_done,
+ .parse_msg = sk_psock_strp_parse,
+ };
+
+ return strp_init(&psock->strp, sk, &cb);
+}
+
+void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
+{
+ if (psock->saved_data_ready)
+ return;
+
+ psock->saved_data_ready = sk->sk_data_ready;
+ sk->sk_data_ready = sk_psock_strp_data_ready;
+ sk->sk_write_space = sk_psock_write_space;
+}
+
+void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
+{
+ if (!psock->saved_data_ready)
+ return;
+
+ sk->sk_data_ready = psock->saved_data_ready;
+ psock->saved_data_ready = NULL;
+ strp_stop(&psock->strp);
+}
+
+static void sk_psock_done_strp(struct sk_psock *psock)
+{
+ /* Parser has been stopped */
+ if (psock->progs.stream_parser)
+ strp_done(&psock->strp);
+}
+#else
+static void sk_psock_done_strp(struct sk_psock *psock)
+{
+}
+#endif /* CONFIG_BPF_STREAM_PARSER */
+
static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
unsigned int offset, size_t orig_len)
{
@@ -957,11 +1009,12 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
goto out;
}
skb_set_owner_r(skb, sk);
- prog = READ_ONCE(psock->progs.skb_verdict);
+ prog = READ_ONCE(psock->progs.stream_verdict);
if (likely(prog)) {
- tcp_skb_bpf_redirect_clear(skb);
- ret = sk_psock_bpf_run(psock, prog, skb);
- ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+ skb_dst_drop(skb);
+ skb_bpf_redirect_clear(skb);
+ ret = bpf_prog_run_pin_on_cpu(prog, skb);
+ ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
}
sk_psock_verdict_apply(psock, skb, ret);
out:
@@ -984,82 +1037,21 @@ static void sk_psock_verdict_data_ready(struct sock *sk)
sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
}
-static void sk_psock_write_space(struct sock *sk)
-{
- struct sk_psock *psock;
- void (*write_space)(struct sock *sk) = NULL;
-
- rcu_read_lock();
- psock = sk_psock(sk);
- if (likely(psock)) {
- if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
- schedule_work(&psock->work);
- write_space = psock->saved_write_space;
- }
- rcu_read_unlock();
- if (write_space)
- write_space(sk);
-}
-
-int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
-{
- static const struct strp_callbacks cb = {
- .rcv_msg = sk_psock_strp_read,
- .read_sock_done = sk_psock_strp_read_done,
- .parse_msg = sk_psock_strp_parse,
- };
-
- psock->parser.enabled = false;
- return strp_init(&psock->parser.strp, sk, &cb);
-}
-
void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
{
- struct sk_psock_parser *parser = &psock->parser;
-
- if (parser->enabled)
+ if (psock->saved_data_ready)
return;
- parser->saved_data_ready = sk->sk_data_ready;
+ psock->saved_data_ready = sk->sk_data_ready;
sk->sk_data_ready = sk_psock_verdict_data_ready;
sk->sk_write_space = sk_psock_write_space;
- parser->enabled = true;
-}
-
-void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
-{
- struct sk_psock_parser *parser = &psock->parser;
-
- if (parser->enabled)
- return;
-
- parser->saved_data_ready = sk->sk_data_ready;
- sk->sk_data_ready = sk_psock_strp_data_ready;
- sk->sk_write_space = sk_psock_write_space;
- parser->enabled = true;
-}
-
-void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
-{
- struct sk_psock_parser *parser = &psock->parser;
-
- if (!parser->enabled)
- return;
-
- sk->sk_data_ready = parser->saved_data_ready;
- parser->saved_data_ready = NULL;
- strp_stop(&parser->strp);
- parser->enabled = false;
}
void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
{
- struct sk_psock_parser *parser = &psock->parser;
-
- if (!parser->enabled)
+ if (!psock->saved_data_ready)
return;
- sk->sk_data_ready = parser->saved_data_ready;
- parser->saved_data_ready = NULL;
- parser->enabled = false;
+ sk->sk_data_ready = psock->saved_data_ready;
+ psock->saved_data_ready = NULL;
}
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index d758fb83c884..dd53a7771d7e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -24,6 +24,9 @@ struct bpf_stab {
#define SOCK_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+ struct bpf_prog *old, u32 which);
+
static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
{
struct bpf_stab *stab;
@@ -148,9 +151,9 @@ static void sock_map_del_link(struct sock *sk,
struct bpf_map *map = link->map;
struct bpf_stab *stab = container_of(map, struct bpf_stab,
map);
- if (psock->parser.enabled && stab->progs.skb_parser)
+ if (psock->saved_data_ready && stab->progs.stream_parser)
strp_stop = true;
- if (psock->parser.enabled && stab->progs.skb_verdict)
+ if (psock->saved_data_ready && stab->progs.stream_verdict)
verdict_stop = true;
list_del(&link->list);
sk_psock_free_link(link);
@@ -224,23 +227,23 @@ out:
static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
struct sock *sk)
{
- struct bpf_prog *msg_parser, *skb_parser, *skb_verdict;
+ struct bpf_prog *msg_parser, *stream_parser, *stream_verdict;
struct sk_psock *psock;
int ret;
- skb_verdict = READ_ONCE(progs->skb_verdict);
- if (skb_verdict) {
- skb_verdict = bpf_prog_inc_not_zero(skb_verdict);
- if (IS_ERR(skb_verdict))
- return PTR_ERR(skb_verdict);
+ stream_verdict = READ_ONCE(progs->stream_verdict);
+ if (stream_verdict) {
+ stream_verdict = bpf_prog_inc_not_zero(stream_verdict);
+ if (IS_ERR(stream_verdict))
+ return PTR_ERR(stream_verdict);
}
- skb_parser = READ_ONCE(progs->skb_parser);
- if (skb_parser) {
- skb_parser = bpf_prog_inc_not_zero(skb_parser);
- if (IS_ERR(skb_parser)) {
- ret = PTR_ERR(skb_parser);
- goto out_put_skb_verdict;
+ stream_parser = READ_ONCE(progs->stream_parser);
+ if (stream_parser) {
+ stream_parser = bpf_prog_inc_not_zero(stream_parser);
+ if (IS_ERR(stream_parser)) {
+ ret = PTR_ERR(stream_parser);
+ goto out_put_stream_verdict;
}
}
@@ -249,7 +252,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
msg_parser = bpf_prog_inc_not_zero(msg_parser);
if (IS_ERR(msg_parser)) {
ret = PTR_ERR(msg_parser);
- goto out_put_skb_parser;
+ goto out_put_stream_parser;
}
}
@@ -261,8 +264,8 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
if (psock) {
if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) ||
- (skb_parser && READ_ONCE(psock->progs.skb_parser)) ||
- (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) {
+ (stream_parser && READ_ONCE(psock->progs.stream_parser)) ||
+ (stream_verdict && READ_ONCE(psock->progs.stream_verdict))) {
sk_psock_put(sk, psock);
ret = -EBUSY;
goto out_progs;
@@ -283,15 +286,15 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
goto out_drop;
write_lock_bh(&sk->sk_callback_lock);
- if (skb_parser && skb_verdict && !psock->parser.enabled) {
+ if (stream_parser && stream_verdict && !psock->saved_data_ready) {
ret = sk_psock_init_strp(sk, psock);
if (ret)
goto out_unlock_drop;
- psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
- psock_set_prog(&psock->progs.skb_parser, skb_parser);
+ psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
+ psock_set_prog(&psock->progs.stream_parser, stream_parser);
sk_psock_start_strp(sk, psock);
- } else if (!skb_parser && skb_verdict && !psock->parser.enabled) {
- psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+ } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) {
+ psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
sk_psock_start_verdict(sk,psock);
}
write_unlock_bh(&sk->sk_callback_lock);
@@ -303,12 +306,12 @@ out_drop:
out_progs:
if (msg_parser)
bpf_prog_put(msg_parser);
-out_put_skb_parser:
- if (skb_parser)
- bpf_prog_put(skb_parser);
-out_put_skb_verdict:
- if (skb_verdict)
- bpf_prog_put(skb_verdict);
+out_put_stream_parser:
+ if (stream_parser)
+ bpf_prog_put(stream_parser);
+out_put_stream_verdict:
+ if (stream_verdict)
+ bpf_prog_put(stream_verdict);
return ret;
}
@@ -657,7 +660,6 @@ const struct bpf_func_proto bpf_sock_map_update_proto = {
BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
struct bpf_map *, map, u32, key, u64, flags)
{
- struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS)))
@@ -667,8 +669,7 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
- tcb->bpf.flags = flags;
- tcb->bpf.sk_redir = sk;
+ skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS);
return SK_PASS;
}
@@ -1250,7 +1251,6 @@ const struct bpf_func_proto bpf_sock_hash_update_proto = {
BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
struct bpf_map *, map, void *, key, u64, flags)
{
- struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
struct sock *sk;
if (unlikely(flags & ~(BPF_F_INGRESS)))
@@ -1260,8 +1260,7 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
return SK_DROP;
- tcb->bpf.flags = flags;
- tcb->bpf.sk_redir = sk;
+ skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS);
return SK_PASS;
}
@@ -1448,8 +1447,8 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
return NULL;
}
-int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
- struct bpf_prog *old, u32 which)
+static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+ struct bpf_prog *old, u32 which)
{
struct sk_psock_progs *progs = sock_map_progs(map);
struct bpf_prog **pprog;
@@ -1461,11 +1460,13 @@ int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
case BPF_SK_MSG_VERDICT:
pprog = &progs->msg_parser;
break;
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
case BPF_SK_SKB_STREAM_PARSER:
- pprog = &progs->skb_parser;
+ pprog = &progs->stream_parser;
break;
+#endif
case BPF_SK_SKB_STREAM_VERDICT:
- pprog = &progs->skb_verdict;
+ pprog = &progs->stream_verdict;
break;
default:
return -EOPNOTSUPP;
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 5b77a46885b9..bbdd9c44f14e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -62,7 +62,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o
-obj-$(CONFIG_BPF_STREAM_PARSER) += udp_bpf.o
+obj-$(CONFIG_BPF_SYSCALL) += udp_bpf.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index bc7d2a586e18..17c322b875fd 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -229,7 +229,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
}
EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
-#ifdef CONFIG_BPF_STREAM_PARSER
+#ifdef CONFIG_BPF_SYSCALL
static bool tcp_bpf_stream_read(const struct sock *sk)
{
struct sk_psock *psock;
@@ -629,4 +629,4 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
newsk->sk_prot = sk->sk_prot_creator;
}
-#endif /* CONFIG_BPF_STREAM_PARSER */
+#endif /* CONFIG_BPF_SYSCALL */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 4faabd1ecfd1..a71ed664da0a 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -445,6 +445,97 @@ static void xsk_destruct_skb(struct sk_buff *skb)
sock_wfree(skb);
}
+static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
+ struct xdp_desc *desc)
+{
+ struct xsk_buff_pool *pool = xs->pool;
+ u32 hr, len, ts, offset, copy, copied;
+ struct sk_buff *skb;
+ struct page *page;
+ void *buffer;
+ int err, i;
+ u64 addr;
+
+ hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
+
+ skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
+ if (unlikely(!skb))
+ return ERR_PTR(err);
+
+ skb_reserve(skb, hr);
+
+ addr = desc->addr;
+ len = desc->len;
+ ts = pool->unaligned ? len : pool->chunk_size;
+
+ buffer = xsk_buff_raw_get_data(pool, addr);
+ offset = offset_in_page(buffer);
+ addr = buffer - pool->addrs;
+
+ for (copied = 0, i = 0; copied < len; i++) {
+ page = pool->umem->pgs[addr >> PAGE_SHIFT];
+ get_page(page);
+
+ copy = min_t(u32, PAGE_SIZE - offset, len - copied);
+ skb_fill_page_desc(skb, i, page, offset, copy);
+
+ copied += copy;
+ addr += copy;
+ offset = 0;
+ }
+
+ skb->len += len;
+ skb->data_len += len;
+ skb->truesize += ts;
+
+ refcount_add(ts, &xs->sk.sk_wmem_alloc);
+
+ return skb;
+}
+
+static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
+ struct xdp_desc *desc)
+{
+ struct net_device *dev = xs->dev;
+ struct sk_buff *skb;
+
+ if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
+ skb = xsk_build_skb_zerocopy(xs, desc);
+ if (IS_ERR(skb))
+ return skb;
+ } else {
+ u32 hr, tr, len;
+ void *buffer;
+ int err;
+
+ hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
+ tr = dev->needed_tailroom;
+ len = desc->len;
+
+ skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
+ if (unlikely(!skb))
+ return ERR_PTR(err);
+
+ skb_reserve(skb, hr);
+ skb_put(skb, len);
+
+ buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
+ err = skb_store_bits(skb, 0, buffer, len);
+ if (unlikely(err)) {
+ kfree_skb(skb);
+ return ERR_PTR(err);
+ }
+ }
+
+ skb->dev = dev;
+ skb->priority = xs->sk.sk_priority;
+ skb->mark = xs->sk.sk_mark;
+ skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
+ skb->destructor = xsk_destruct_skb;
+
+ return skb;
+}
+
static int xsk_generic_xmit(struct sock *sk)
{
struct xdp_sock *xs = xdp_sk(sk);
@@ -461,43 +552,30 @@ static int xsk_generic_xmit(struct sock *sk)
goto out;
while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
- char *buffer;
- u64 addr;
- u32 len;
-
if (max_batch-- == 0) {
err = -EAGAIN;
goto out;
}
- len = desc.len;
- skb = sock_alloc_send_skb(sk, len, 1, &err);
- if (unlikely(!skb))
+ skb = xsk_build_skb(xs, &desc);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
goto out;
+ }
- skb_put(skb, len);
- addr = desc.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.
*/
spin_lock_irqsave(&xs->pool->cq_lock, flags);
- if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
+ if (xskq_prod_reserve(xs->pool->cq)) {
spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
kfree_skb(skb);
goto out;
}
spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
- skb->dev = xs->dev;
- skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
- skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
- skb->destructor = xsk_destruct_skb;
-
err = __dev_direct_xmit(skb, xs->queue_id);
if (err == NETDEV_TX_BUSY) {
/* Tell user-space to retry the send */
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 2823b7c3302d..2ac3802c2cd7 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -47,19 +47,18 @@ struct xsk_queue {
u64 queue_empty_descs;
};
-/* The structure of the shared state of the rings are the same as the
- * ring buffer in kernel/events/ring_buffer.c. For the Rx and completion
- * ring, the kernel is the producer and user space is the consumer. For
- * the Tx and fill rings, the kernel is the consumer and user space is
- * the producer.
+/* The structure of the shared state of the rings are a simple
+ * circular buffer, as outlined in
+ * Documentation/core-api/circular-buffers.rst. For the Rx and
+ * completion ring, the kernel is the producer and user space is the
+ * consumer. For the Tx and fill rings, the kernel is the consumer and
+ * user space is the producer.
*
* producer consumer
*
- * if (LOAD ->consumer) { LOAD ->producer
- * (A) smp_rmb() (C)
+ * if (LOAD ->consumer) { (A) LOAD.acq ->producer (C)
* STORE $data LOAD $data
- * smp_wmb() (B) smp_mb() (D)
- * STORE ->producer STORE ->consumer
+ * STORE.rel ->producer (B) STORE.rel ->consumer (D)
* }
*
* (A) pairs with (D), and (B) pairs with (C).
@@ -78,7 +77,8 @@ struct xsk_queue {
*
* (A) is a control dependency that separates the load of ->consumer
* from the stores of $data. In case ->consumer indicates there is no
- * room in the buffer to store $data we do not. So no barrier is needed.
+ * room in the buffer to store $data we do not. The dependency will
+ * order both of the stores after the loads. So no barrier is needed.
*
* (D) protects the load of the data to be observed to happen after the
* store of the consumer pointer. If we did not have this memory
@@ -227,15 +227,13 @@ static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q,
static inline void __xskq_cons_release(struct xsk_queue *q)
{
- smp_mb(); /* D, matches A */
- WRITE_ONCE(q->ring->consumer, q->cached_cons);
+ smp_store_release(&q->ring->consumer, q->cached_cons); /* D, matchees A */
}
static inline void __xskq_cons_peek(struct xsk_queue *q)
{
/* Refresh the local pointer */
- q->cached_prod = READ_ONCE(q->ring->producer);
- smp_rmb(); /* C, matches B */
+ q->cached_prod = smp_load_acquire(&q->ring->producer); /* C, matches B */
}
static inline void xskq_cons_get_entries(struct xsk_queue *q)
@@ -397,9 +395,7 @@ static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx)
{
- smp_wmb(); /* B, matches C */
-
- WRITE_ONCE(q->ring->producer, idx);
+ smp_store_release(&q->ring->producer, idx); /* B, matches C */
}
static inline void xskq_prod_submit(struct xsk_queue *q)
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 113fd9017203..67b4ce504852 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -87,7 +87,6 @@ static void xsk_map_free(struct bpf_map *map)
{
struct xsk_map *m = container_of(map, struct xsk_map, map);
- bpf_clear_redirect_map(map);
synchronize_net();
bpf_map_area_free(m);
}
@@ -125,6 +124,16 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
return insn - insn_buf;
}
+static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct xsk_map *m = container_of(map, struct xsk_map, map);
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ return READ_ONCE(m->xsk_map[key]);
+}
+
static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
{
WARN_ON_ONCE(!rcu_read_lock_held());
@@ -215,6 +224,11 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
return 0;
}
+static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
+{
+ return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem);
+}
+
void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
struct xdp_sock **map_entry)
{
@@ -247,4 +261,5 @@ const struct bpf_map_ops xsk_map_ops = {
.map_check_btf = map_check_no_btf,
.map_btf_name = "xsk_map",
.map_btf_id = &xsk_map_btf_id,
+ .map_redirect = xsk_map_redirect,
};
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.