net: flow_dissector: trigger BPF hook when called from eth_get_headlen
Subsystems (14)
PATCH v6 5/9 net: pass net_device argument to the eth_get_headlen
In reply to Stanislav FomichevUpdate all users of eth_get_headlen to pass network device, fetch network namespace from it and pass it down to the flow dissector. This commit is a noop until administrator inserts BPF flow dissector program.
--- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 ++- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 ++- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- drivers/net/tun.c | 3 ++- include/linux/etherdevice.h | 2 +- net/ethernet/eth.c | 5 +++-- 16 files changed, 22 insertions(+), 17 deletions(-)
drivers/net/ethernet/aquantia/atlantic/aq_ring.c +2 -1
@@ -354,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, hdr_len = buff->len;if (hdr_len >AQ_CFG_RX_HDR_SIZE ) - hdr_len =eth_get_headlen (aq_buf_vaddr (&buff->rxdata), + hdr_len =eth_get_headlen (skb->dev, +aq_buf_vaddr (&buff->rxdata),AQ_CFG_RX_HDR_SIZE ); memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),
drivers/net/ethernet/broadcom/bnxt/bnxt.c +1 -1
@@ -899,7 +899,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, DMA_ATTR_WEAK_ORDERING);if (unlikely (!payload)) - payload =eth_get_headlen (data_ptr, len); + payload =eth_get_headlen (bp->dev, data_ptr, len); skb =napi_alloc_skb (&rxr->bnapi->napi, payload);if (!skb) {
drivers/net/ethernet/hisilicon/hns/hns_enet.c +1 -1
@@ -598,7 +598,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, }else { ring->stats.seg_pkt_cnt++; - pull_len =eth_get_headlen (va,HNS_RX_HEAD_SIZE ); + pull_len =eth_get_headlen (ndev, va,HNS_RX_HEAD_SIZE );memcpy (__skb_put (skb, pull_len), va,ALIGN (pull_len,sizeof (long )));
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +1 -1
@@ -2457,7 +2457,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length, ring->stats.seg_pkt_cnt++;u64_stats_update_end (&ring->syncp); - ring->pull_len =eth_get_headlen (va,HNS3_RX_HEAD_SIZE ); + ring->pull_len =eth_get_headlen (netdev, va,HNS3_RX_HEAD_SIZE );__skb_put (skb, ring->pull_len);hns3_nic_reuse_page (skb, ring->frag_num++, ring, ring->pull_len, desc_cb);
drivers/net/ethernet/intel/fm10k/fm10k_main.c +1 -1
@@ -280,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,/* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len =eth_get_headlen (va,FM10K_RX_HDR_LEN ); + pull_len =eth_get_headlen (skb->dev, va,FM10K_RX_HDR_LEN );/* align pull length to size of long to optimize memcpy performance */ memcpy (__skb_put (skb, pull_len), va,ALIGN (pull_len,sizeof (long )));
drivers/net/ethernet/intel/i40e/i40e_txrx.c +2 -1
@@ -2035,7 +2035,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,/* Determine available headroom for copy */ headlen = size;if (headlen >I40E_RX_HDR_SIZE ) - headlen =eth_get_headlen (xdp->data,I40E_RX_HDR_SIZE ); + headlen =eth_get_headlen (skb->dev, xdp->data, +I40E_RX_HDR_SIZE );/* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), xdp->data,
drivers/net/ethernet/intel/iavf/iavf_txrx.c +1 -1
@@ -1315,7 +1315,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,/* Determine available headroom for copy */ headlen = size;if (headlen >IAVF_RX_HDR_SIZE ) - headlen =eth_get_headlen (va,IAVF_RX_HDR_SIZE ); + headlen =eth_get_headlen (skb->dev, va,IAVF_RX_HDR_SIZE );/* align pull length to size of long to optimize memcpy performance */ memcpy (__skb_put (skb, headlen), va,ALIGN (headlen,sizeof (long )));
drivers/net/ethernet/intel/ice/ice_txrx.c +1 -1
@@ -698,7 +698,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,/* Determine available headroom for copy */ headlen = size;if (headlen >ICE_RX_HDR_SIZE ) - headlen =eth_get_headlen (va,ICE_RX_HDR_SIZE ); + headlen =eth_get_headlen (skb->dev, va,ICE_RX_HDR_SIZE );/* align pull length to size of long to optimize memcpy performance */ memcpy (__skb_put (skb, headlen), va,ALIGN (headlen,sizeof (long )));
drivers/net/ethernet/intel/igb/igb_main.c +1 -1
@@ -8051,7 +8051,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,/* Determine available headroom for copy */ headlen = size;if (headlen >IGB_RX_HDR_LEN ) - headlen =eth_get_headlen (va,IGB_RX_HDR_LEN ); + headlen =eth_get_headlen (skb->dev, va,IGB_RX_HDR_LEN );/* align pull length to size of long to optimize memcpy performance */ memcpy (__skb_put (skb, headlen), va,ALIGN (headlen,sizeof (long )));
drivers/net/ethernet/intel/igc/igc_main.c +1 -1
@@ -1199,7 +1199,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,/* Determine available headroom for copy */ headlen = size;if (headlen >IGC_RX_HDR_LEN ) - headlen =eth_get_headlen (va,IGC_RX_HDR_LEN ); + headlen =eth_get_headlen (skb->dev, va,IGC_RX_HDR_LEN );/* align pull length to size of long to optimize memcpy performance */ memcpy (__skb_put (skb, headlen), va,ALIGN (headlen,sizeof (long )));
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +1 -1
@@ -1800,7 +1800,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ - pull_len =eth_get_headlen (va,IXGBE_RX_HDR_SIZE ); + pull_len =eth_get_headlen (skb->dev, va,IXGBE_RX_HDR_SIZE );/* align pull length to size of long to optimize memcpy performance */ skb_copy_to_linear_data (skb, va,ALIGN (pull_len,sizeof (long )));
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +2 -1
@@ -895,7 +895,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring,/* Determine available headroom for copy */ headlen = size;if (headlen >IXGBEVF_RX_HDR_SIZE ) - headlen =eth_get_headlen (xdp->data,IXGBEVF_RX_HDR_SIZE ); + headlen =eth_get_headlen (skb->dev, xdp->data, +IXGBEVF_RX_HDR_SIZE );/* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), xdp->data,
drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +1 -1
@@ -163,7 +163,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,case MLX5_INLINE_MODE_NONE :return 0 ;case MLX5_INLINE_MODE_TCP_UDP : - hlen =eth_get_headlen (skb->data,skb_headlen (skb)); + hlen =eth_get_headlen (skb->dev, skb->data,skb_headlen (skb));if (hlen ==ETH_HLEN && !skb_vlan_tag_present (skb)) hlen +=VLAN_HLEN ;break ;
drivers/net/tun.c +2 -1
@@ -1965,7 +1965,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,if (frags) {/* Exercise flow dissector code path. */ -u32 headlen =eth_get_headlen (skb->data,skb_headlen (skb)); +u32 headlen =eth_get_headlen (tun->dev, skb->data, +skb_headlen (skb));if (unlikely (headlen >skb_headlen (skb))) {this_cpu_inc (tun->pcpu_stats->rx_dropped);
include/linux/etherdevice.h +1 -1
@@ -33,7 +33,7 @@ struct device;int eth_platform_get_mac_address (struct device *dev,u8 *mac_addr);unsigned char *arch_get_platform_mac_address (void );int nvmem_get_mac_address (struct device *dev,void *addrbuf); -u32 eth_get_headlen (void *data,unsigned int max_len); +u32 eth_get_headlen (const struct net_device *dev,void *data,unsigned int len);__be16 eth_type_trans (struct sk_buff *skb,struct net_device *dev);extern const struct header_ops eth_header_ops;
net/ethernet/eth.c +3 -2
@@ -119,13 +119,14 @@ EXPORT_SYMBOL(eth_header);/** * eth_get_headlen - determine the length of header for an ethernet frame +* @dev: pointer to network device * @data: pointer to start of frame * @len: total length of frame * * Make a best effort attempt to pull the length for all of the headers for * a given frame in a linear buffer. */ -u32 eth_get_headlen (void *data,unsigned int len) +u32 eth_get_headlen (const struct net_device *dev,void *data,unsigned int len) {const unsigned int flags =FLOW_DISSECTOR_F_PARSE_1ST_FRAG ;const struct ethhdr *eth = (const struct ethhdr *)data;
@@ -136,7 +137,7 @@ u32 eth_get_headlen(void *data, unsigned int len)return len;/* parse any remaining L2/L3 headers, check for L4 */ -if (!skb_flow_dissect_flow_keys_basic (NULL ,NULL , &keys, data, +if (!skb_flow_dissect_flow_keys_basic (dev_net (dev),NULL , &keys, data, eth->h_proto,sizeof (*eth), len, flags))return max_t (u32, keys.control.thoff,sizeof (*eth));
Signature · 1 line
2.21.0.593.g511ec345e18-goog
v6 cover net: flow_dissector: trigger BPF hook when called from eth_get_headlen
Currently, when eth_get_headlen calls flow dissector, it doesn't pass any skb. Because we use passed skb to lookup associated networking namespace to find whether we have a BPF program attached or not, we always use C-based flow dissector in this case.
The goal of this patch series is to add new networking namespace argument to the eth_get_headlen and make BPF flow dissector programs be able to work in the skb-less case.
The series goes like this:
* use new kernel context (struct bpf_flow_dissector) for flow dissector programs; this makes it easy to distinguish between skb and no-skb case and supports calling BPF flow dissector on a chunk of raw data
* convert BPF_PROG_TEST_RUN to use raw data
* plumb network namespace into __skb_flow_dissect from all callers
* handle no-skb case in __skb_flow_dissect
* update eth_get_headlen to include net namespace argument and convert all existing users
* add selftest to make sure bpf_skb_load_bytes is not allowed in the no-skb mode
* extend test_progs to exercise skb-less flow dissection as well
* stop adjusting nhoff/thoff by ETH_HLEN in BPF_PROG_TEST_RUN
v6:
* more suggestions by Alexei:
* eth_get_headlen now takes net dev, not net namespace
* test skb-less case via tun eth_get_headlen
* fix return errors in bpf_flow_load
* don't adjust nhoff/thoff by ETH_HLEN
v5:
* API changes have been submitted via bpf/stable tree
v4:
* prohibit access to vlan fields as well (otherwise, inconsistent between skb/skb-less cases)
* drop extra unneeded check for skb->vlan_present in bpf_flow.c
v3:
* new kernel xdp_buff-like context per Alexei suggestion
* drop skb_net helper
* properly clamp flow_keys->nhoff
v2:
* moved temporary skb from stack into percpu (avoids memset of ~200 bytes per packet)
* tightened down access to __sk_buff fields from flow dissector programs to avoid touching shinfo (whitelist only relevant fields)
* addressed suggestions from Willem
Stanislav Fomichev (9):
flow_dissector: switch kernel context to struct bpf_flow_dissector
bpf: when doing BPF_PROG_TEST_RUN for flow dissector use no-skb mode
net: plumb network namespace into __skb_flow_dissect
flow_dissector: handle no-skb use case
net: pass net_device argument to the eth_get_headlen selftests/bpf: add flow dissector bpf_skb_load_bytes helper test selftests/bpf: run flow dissector tests in skb-less mode selftests/bpf: properly return error from bpf_flow_load bpf/flow_dissector: don't adjust nhoff by ETH_HLEN in
BPF_PROG_TEST_RUN
.../net/ethernet/aquantia/atlantic/aq_ring.c | 3 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 +- .../net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- drivers/net/tun.c | 3 +- include/linux/etherdevice.h | 2 +- include/linux/skbuff.h | 28 +++-- include/net/flow_dissector.h | 7 ++ include/net/sch_generic.h | 11 +- net/bpf/test_run.c | 48 +++----- net/core/filter.c | 105 ++++++++++++---- net/core/flow_dissector.c | 90 +++++++------- net/ethernet/eth.c | 8 +- .../selftests/bpf/flow_dissector_load.c | 2 +- .../selftests/bpf/flow_dissector_load.h | 24 +++- .../selftests/bpf/prog_tests/flow_dissector.c | 113 ++++++++++++++++-- .../prog_tests/flow_dissector_load_bytes.c | 48 ++++++++ tools/testing/selftests/bpf/progs/bpf_flow.c | 79 +++++++----- 27 files changed, 411 insertions(+), 186 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 1/9 flow_dissector: switch kernel context to struct bpf_flow_dissector
struct bpf_flow_dissector has a small subset of sk_buff fields that flow dissector BPF program is allowed to access and an optional pointer to real skb. Real skb is used only in bpf_skb_load_bytes helper to read non-linear data.
The real motivation for this is to be able to call flow dissector from eth_get_headlen context where we don't have an skb and need to dissect raw bytes.
--- include/linux/skbuff.h | 4 ++ include/net/flow_dissector.h | 7 +++ include/net/sch_generic.h | 11 ++-- net/bpf/test_run.c | 4 -- net/core/filter.c | 105 +++++++++++++++++++++++++++-------- net/core/flow_dissector.c | 45 +++++++-------- 6 files changed, 117 insertions(+), 59 deletions(-)
include/linux/skbuff.h +4 -0
@@ -1275,6 +1275,10 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) }#endif +struct bpf_flow_dissector ; +bool bpf_flow_dissect (struct bpf_prog *prog,struct bpf_flow_dissector *ctx, +__be16 proto,int nhoff,int hlen); +struct bpf_flow_keys ; bool __skb_flow_bpf_dissect(struct bpf_prog *prog, const struct sk_buff *skb,
include/net/flow_dissector.h +7 -0
@@ -305,4 +305,11 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec return ((char *)target_container) + flow_dissector->offset[key_id]; } +struct bpf_flow_dissector { +struct bpf_flow_keys *flow_keys; +const struct sk_buff *skb; +void *data; +void *data_end; +}; +#endif
include/net/sch_generic.h +4 -7
@@ -364,13 +364,10 @@ struct tcf_proto { };struct qdisc_skb_cb { -union { -struct { -unsigned int pkt_len; -u16 slave_dev_queue_mapping; -u16 tc_classid; - }; -struct bpf_flow_keys *flow_keys; +struct { +unsigned int pkt_len; +u16 slave_dev_queue_mapping; +u16 tc_classid; };#define QDISC_CB_PRIV_LEN 20unsigned char data[QDISC_CB_PRIV_LEN ];
net/bpf/test_run.c +0 -4
@@ -382,7 +382,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,u32 repeat = kattr->test.repeat;struct bpf_flow_keys flow_keys;u64 time_start, time_spent =0 ; -struct bpf_skb_data_end *cb;u32 retval, duration;struct sk_buff *skb;struct sock *sk;
@@ -423,9 +422,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, current->nsproxy->net_ns->loopback_dev);skb_reset_network_header (skb); - cb = (struct bpf_skb_data_end *)skb->cb; - cb->qdisc_cb.flow_keys = &flow_keys; -if (!repeat) repeat =1 ;
net/core/filter.c +82 -23
185 lines not on this page · raw message
net/core/flow_dissector.c +20 -25
59 lines not on this page · raw message
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 2/9 bpf: when doing BPF_PROG_TEST_RUN for flow dissector use no-skb mode
In reply to Stanislav FomichevNow that we have bpf_flow_dissect which can work on raw data, use it when doing BPF_PROG_TEST_RUN for flow dissector.
Simplifies bpf_prog_test_run_flow_dissector and allows us to test no-skb mode.
Note, that previously, with bpf_flow_dissect_skb we used to call eth_type_trans which pulled L2 (ETH_HLEN) header and we explicitly called skb_reset_network_header. That means flow_keys->nhoff would be initialized to 0 (skb_network_offset) in init_flow_keys.
Now we call bpf_flow_dissect with nhoff set to ETH_HLEN and need to undo it once the dissection is done to preserve the existing behavior.
--- net/bpf/test_run.c | 47 +++++++++++++++++----------------------------- 1 file changed, 17 insertions(+), 30 deletions(-)
net/bpf/test_run.c +17 -30
@@ -379,12 +379,12 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, union bpf_attr __user *uattr) {u32 size = kattr->test.data_size_in; +struct bpf_flow_dissector ctx = {};u32 repeat = kattr->test.repeat;struct bpf_flow_keys flow_keys;u64 time_start, time_spent =0 ; +const struct ethhdr *eth;u32 retval, duration; -struct sk_buff *skb; -struct sock *sk;void *data;int ret;u32 i;
@@ -395,43 +395,31 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,if (kattr->test.ctx_in || kattr->test.ctx_out)return -EINVAL ; - data =bpf_test_init (kattr, size,NET_SKB_PAD +NET_IP_ALIGN , -SKB_DATA_ALIGN (sizeof (struct skb_shared_info ))); +if (size <ETH_HLEN ) +return -EINVAL ; + + data =bpf_test_init (kattr, size,0 ,0 );if (IS_ERR (data))return PTR_ERR (data); - sk =kzalloc (sizeof (*sk),GFP_USER ); -if (!sk) { -kfree (data); -return -ENOMEM ; - } -sock_net_set (sk, current->nsproxy->net_ns); -sock_init_data (NULL , sk); - - skb =build_skb (data,0 ); -if (!skb) { -kfree (data); -kfree (sk); -return -ENOMEM ; - } - skb->sk = sk; - -skb_reserve (skb,NET_SKB_PAD +NET_IP_ALIGN ); -__skb_put (skb, size); - skb->protocol =eth_type_trans (skb, - current->nsproxy->net_ns->loopback_dev); -skb_reset_network_header (skb); + eth = (struct ethhdr *)data;if (!repeat) repeat =1 ; + ctx.flow_keys = &flow_keys; + 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++) { - retval =__skb_flow_bpf_dissect (prog, skb, - &flow_keys_dissector, - &flow_keys); + retval =bpf_flow_dissect (prog, &ctx, eth->h_proto,ETH_HLEN , + size); + + flow_keys.nhoff -=ETH_HLEN ; + flow_keys.thoff -=ETH_HLEN ;if (signal_pending (current)) {preempt_enable ();
@@ -464,7 +452,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, retval, duration); out: -kfree_skb (skb); -kfree (sk); +kfree (data);return ret; }
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 3/9 net: plumb network namespace into __skb_flow_dissect
In reply to Stanislav FomichevThis new argument will be used in the next patches for the eth_get_headlen use case. eth_get_headlen calls flow dissector with only data (without skb) so there is currently no way to pull attached BPF flow dissector program. With this new argument, we can amend the callers to explicitly pass network namespace so we can use attached BPF program.
--- include/linux/skbuff.h | 19 +++++++++++-------- net/core/flow_dissector.c | 27 +++++++++++++++++---------- net/ethernet/eth.c | 5 +++-- 3 files changed, 31 insertions(+), 20 deletions(-)
include/linux/skbuff.h +11 -8
@@ -1284,7 +1284,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,const struct sk_buff *skb, struct flow_dissector *flow_dissector, struct bpf_flow_keys *flow_keys); -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen,
@@ -1294,8 +1295,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb,struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
@@ -1303,18 +1304,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) {memset (flow,0 ,sizeof (*flow)); -return __skb_flow_dissect (skb, &flow_keys_dissector, flow, -NULL ,0 ,0 ,0 , flags); +return __skb_flow_dissect (NULL , skb, &flow_keys_dissector, + flow,NULL ,0 ,0 ,0 , flags); }static inline bool -skb_flow_dissect_flow_keys_basic (const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic (const struct net *net, +const struct sk_buff *skb,struct flow_keys_basic *flow,void *data,__be16 proto,int nhoff,int hlen,unsigned int flags) {memset (flow,0 ,sizeof (*flow)); -return __skb_flow_dissect (skb, &flow_keys_basic_dissector, flow, +return __skb_flow_dissect (net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); }
@@ -2494,7 +2496,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb)if (skb_transport_header_was_set (skb))return ; -if (skb_flow_dissect_flow_keys_basic (skb, &keys,NULL ,0 ,0 ,0 ,0 )) +if (skb_flow_dissect_flow_keys_basic (NULL , skb, &keys, +NULL ,0 ,0 ,0 ,0 ))skb_set_transport_header (skb, keys.control.thoff); }
net/core/flow_dissector.c +17 -10
@@ -722,6 +722,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,/** * __skb_flow_dissect - extract the flow_keys struct and return it +* @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into
@@ -738,7 +739,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,* * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen,
@@ -797,13 +799,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb,struct bpf_prog *attached =NULL ;rcu_read_lock (); +if (!net) { +if (skb->dev) + net =dev_net (skb->dev); +else if (skb->sk) + net =sock_net (skb->sk); +else +WARN_ON_ONCE (1 ); + } -if (skb->dev) - attached =rcu_dereference (dev_net (skb->dev)->flow_dissector_prog); -else if (skb->sk) - attached =rcu_dereference (sock_net (skb->sk)->flow_dissector_prog); -else -WARN_ON_ONCE (1 ); +if (net) + attached =rcu_dereference (net->flow_dissector_prog);if (attached) { ret = __skb_flow_bpf_dissect(attached, skb,
@@ -1405,8 +1411,8 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)__flow_hash_secret_init ();memset (&keys,0 ,sizeof (keys)); -__skb_flow_dissect (skb, &flow_keys_dissector_symmetric, &keys, -NULL ,0 ,0 ,0 , +__skb_flow_dissect (NULL , skb, &flow_keys_dissector_symmetric, + &keys,NULL ,0 ,0 ,0 ,FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL );return __flow_hash_from_keys (&keys, hashrnd);
@@ -1507,7 +1513,8 @@ u32 skb_get_poff(const struct sk_buff *skb) {struct flow_keys_basic keys; -if (!skb_flow_dissect_flow_keys_basic (skb, &keys,NULL ,0 ,0 ,0 ,0 )) +if (!skb_flow_dissect_flow_keys_basic (NULL , skb, &keys, +NULL ,0 ,0 ,0 ,0 ))return 0 ;return __skb_get_poff (skb, skb->data, &keys,skb_headlen (skb));
net/ethernet/eth.c +3 -2
@@ -136,8 +136,9 @@ u32 eth_get_headlen(void *data, unsigned int len)return len;/* parse any remaining L2/L3 headers, check for L4 */ -if (!skb_flow_dissect_flow_keys_basic (NULL , &keys, data, eth->h_proto, -sizeof (*eth), len, flags)) +if (!skb_flow_dissect_flow_keys_basic (NULL ,NULL , &keys, data, + eth->h_proto,sizeof (*eth), + len, flags))return max_t (u32, keys.control.thoff,sizeof (*eth));/* parse for any L4 headers */
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 4/9 flow_dissector: handle no-skb use case
In reply to Stanislav FomichevWhen called without skb, gather all required data from the __skb_flow_dissect's arguments and use recently introduces no-skb mode of bpf flow dissector.
Note: WARN_ON_ONCE(!net) will now trigger for eth_get_headlen users.
--- include/linux/skbuff.h | 5 ---- net/core/flow_dissector.c | 52 +++++++++++++++++++-------------------- 2 files changed, 25 insertions(+), 32 deletions(-)
include/linux/skbuff.h +0 -5
@@ -1279,11 +1279,6 @@ struct bpf_flow_dissector;bool bpf_flow_dissect (struct bpf_prog *prog,struct bpf_flow_dissector *ctx,__be16 proto,int nhoff,int hlen); -struct bpf_flow_keys ; -bool __skb_flow_bpf_dissect (struct bpf_prog *prog, -const struct sk_buff *skb, -struct flow_dissector *flow_dissector, -struct bpf_flow_keys *flow_keys); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector,
net/core/flow_dissector.c +25 -27
79 lines not on this page · raw message
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 6/9 selftests/bpf: add flow dissector bpf_skb_load_bytes helper test
In reply to Stanislav FomichevWhen flow dissector is called without skb, we want to make sure bpf_skb_load_bytes invocations return error. Add small test which tries to read single byte from a packet.
bpf_skb_load_bytes should always fail under BPF_PROG_TEST_RUN because it was converted to the skb-less mode.
--- .../prog_tests/flow_dissector_load_bytes.c | 48 +++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c new file +48 -0
@@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_flow_dissector_load_bytes (void ) +{ +struct bpf_flow_keys flow_keys; +__u32 duration =0 , retval, size; +struct bpf_insn prog[] = { +// BPF_REG_1 - 1st argument: context +// BPF_REG_2 - 2nd argument: offset, start at first byte +BPF_MOV64_IMM (BPF_REG_2 ,0 ), +// BPF_REG_3 - 3rd argument: destination, reserve byte on stack +BPF_ALU64_REG (BPF_MOV ,BPF_REG_3 ,BPF_REG_10 ), +BPF_ALU64_IMM (BPF_ADD ,BPF_REG_3 ,-1 ), +// BPF_REG_4 - 4th argument: copy one byte +BPF_MOV64_IMM (BPF_REG_4 ,1 ), +// bpf_skb_load_bytes(ctx, sizeof(pkt_v4), ptr, 1) +BPF_RAW_INSN (BPF_JMP |BPF_CALL ,0 ,0 ,0 , + BPF_FUNC_skb_load_bytes), +BPF_JMP_IMM (BPF_JNE ,BPF_REG_0 ,0 ,2 ), +// if (ret == 0) return BPF_DROP (2) +BPF_MOV64_IMM (BPF_REG_0 ,BPF_DROP ), +BPF_EXIT_INSN (), +// if (ret != 0) return BPF_OK (0) +BPF_MOV64_IMM (BPF_REG_0 ,BPF_OK ), +BPF_EXIT_INSN (), + }; +int fd, err; + +/* make sure bpf_skb_load_bytes is not allowed from skb-less context +*/ + fd =bpf_load_program (BPF_PROG_TYPE_FLOW_DISSECTOR , prog, +ARRAY_SIZE (prog),"GPL" ,0 ,NULL ,0 ); +CHECK (fd <0 , +"flow_dissector-bpf_skb_load_bytes-load" , +"fd %d errno %d\n" , + fd, errno); + + err =bpf_prog_test_run (fd,1 , &pkt_v4,sizeof (pkt_v4), + &flow_keys, &size, &retval, &duration); +CHECK (size !=sizeof (flow_keys) || err || retval !=1 , +"flow_dissector-bpf_skb_load_bytes" , +"err %d errno %d retval %d duration %d size %u/%zu\n" , + err, errno, retval, duration, size,sizeof (flow_keys)); + +if (fd >=-1 ) +close (fd); +}
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 7/9 selftests/bpf: run flow dissector tests in skb-less mode
In reply to Stanislav FomichevExport last_dissection map from flow dissector and use a known place in tun driver to trigger BPF flow dissection.
--- .../selftests/bpf/flow_dissector_load.c | 2 +- .../selftests/bpf/flow_dissector_load.h | 16 ++- .../selftests/bpf/prog_tests/flow_dissector.c | 102 +++++++++++++++++- tools/testing/selftests/bpf/progs/bpf_flow.c | 79 +++++++++----- 4 files changed, 165 insertions(+), 34 deletions(-)
tools/testing/selftests/bpf/flow_dissector_load.c +1 -1
@@ -26,7 +26,7 @@ static void load_and_attach_program(void)struct bpf_object *obj; ret =bpf_flow_load (&obj, cfg_path_name, cfg_section_name, - cfg_map_name, &prog_fd); + cfg_map_name,NULL , &prog_fd,NULL );if (ret)error (1 ,0 ,"bpf_flow_load %s" , cfg_path_name);
tools/testing/selftests/bpf/flow_dissector_load.h +14 -2
@@ -9,10 +9,12 @@ static inline int bpf_flow_load(struct bpf_object **obj,const char *path, const char *section_name, const char *map_name, - int *prog_fd) + const char *keys_map_name, + int *prog_fd, + int *keys_fd) { struct bpf_program *prog, *main_prog; -struct bpf_map *prog_array; +struct bpf_map *prog_array, *keys;int prog_array_fd;int ret, fd, i;
@@ -37,6 +39,16 @@ static inline int bpf_flow_load(struct bpf_object **obj,if (prog_array_fd <0 )return ret; +if (keys_map_name && keys_fd) { + keys =bpf_object__find_map_by_name (*obj, keys_map_name); +if (!keys) +return -1 ; + + *keys_fd =bpf_map__fd (keys); +if (*keys_fd <0 ) +return -1 ; + } + i =0 ;bpf_object__for_each_program (prog, *obj) { fd =bpf_program__fd (prog);
tools/testing/selftests/bpf/prog_tests/flow_dissector.c +100 -2
123 lines not on this page · raw message
tools/testing/selftests/bpf/progs/bpf_flow.c +50 -29
217 lines not on this page · raw message
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 8/9 selftests/bpf: properly return error from bpf_flow_load
In reply to Stanislav FomichevRight now we incorrectly return 'ret' which is always zero at that point.
--- tools/testing/selftests/bpf/flow_dissector_load.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
tools/testing/selftests/bpf/flow_dissector_load.h +4 -4
@@ -25,19 +25,19 @@ static inline int bpf_flow_load(struct bpf_object **obj, main_prog =bpf_object__find_program_by_title (*obj, section_name);if (!main_prog) -return ret; +return -1 ; *prog_fd =bpf_program__fd (main_prog);if (*prog_fd <0 ) -return ret; +return -1 ; prog_array =bpf_object__find_map_by_name (*obj, map_name);if (!prog_array) -return ret; +return -1 ; prog_array_fd =bpf_map__fd (prog_array);if (prog_array_fd <0 ) -return ret; +return -1 ;if (keys_map_name && keys_fd) { keys =bpf_object__find_map_by_name (*obj, keys_map_name);
Signature · 1 line
2.21.0.593.g511ec345e18-goog
PATCH v6 9/9 bpf/flow_dissector: don't adjust nhoff by ETH_HLEN in BPF_PROG_TEST_RUN
In reply to Stanislav FomichevNow that we use skb-less flow dissector let's return true nhoff and thoff. We used to adjust them by ETH_HLEN because that's how it was done in the skb case. For VLAN tests that looks confusing: nhoff is pointing to vlan parts :-\
Warning, this is an API change for BPF_PROG_TEST_RUN! Feel free to drop if you think that it's too late at this point to fix it.
--- net/bpf/test_run.c | 3 --- .../selftests/bpf/prog_tests/flow_dissector.c | 23 ++++++++----------- 2 files changed, 9 insertions(+), 17 deletions(-)
net/bpf/test_run.c +0 -3
@@ -418,9 +418,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, retval =bpf_flow_dissect (prog, &ctx, eth->h_proto,ETH_HLEN , size); - flow_keys.nhoff -=ETH_HLEN ; - flow_keys.thoff -=ETH_HLEN ; -if (signal_pending (current)) {preempt_enable ();rcu_read_unlock ();
tools/testing/selftests/bpf/prog_tests/flow_dissector.c +9 -14
@@ -82,8 +82,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = 0, - .thoff = sizeof(struct iphdr), + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP),
@@ -98,8 +98,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = 0, - .thoff = sizeof(struct ipv6hdr), + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6),
@@ -116,8 +116,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = VLAN_HLEN, - .thoff = VLAN_HLEN + sizeof(struct iphdr), + .nhoff = ETH_HLEN + VLAN_HLEN, + .thoff = ETH_HLEN + VLAN_HLEN + sizeof(struct iphdr), .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP),
@@ -134,8 +134,9 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = VLAN_HLEN * 2, - .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .nhoff = ETH_HLEN + VLAN_HLEN * 2, + .thoff =ETH_HLEN +VLAN_HLEN *2 + + sizeof(struct ipv6hdr), .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6),
@@ -238,9 +239,6 @@ void test_flow_dissector(void)* We use a known path in the net/tun driver that calls * eth_get_headlen and we manually export bpf_flow_keys * via BPF map in this case. -* -* Note, that since eth_get_headlen operates on a L2 level, -* we adjust exported nhoff/thoff by ETH_HLEN. */ err =bpf_prog_attach (prog_fd,0 ,BPF_FLOW_DISSECTOR ,0 );
@@ -262,9 +260,6 @@ void test_flow_dissector(void) err =bpf_map_lookup_elem (keys_fd, &key, &flow_keys);CHECK_ATTR (err, tests[i].name,"bpf_map_lookup_elem %d\n" , err); - flow_keys.nhoff -=ETH_HLEN ; - flow_keys.thoff -=ETH_HLEN ; -CHECK_ATTR (err, tests[i].name,"skb-less err %d\n" , err);CHECK_FLOW_KEYS (tests[i].name, flow_keys, tests[i].keys); }
Signature · 1 line
2.21.0.593.g511ec345e18-goog
Re: [PATCH bpf-next v6 3/9] net: plumb network namespace into __skb_flow_dissect
In reply to Stanislav FomichevQuoted 110 lines · Stanislav Fomichev
This new argument will be used in the next patches for the
eth_get_headlenuse case.eth_get_headlencalls flow dissector with only data (without skb) so there is currently no way to pull attached BPF flow dissector program. With this new argument, we can amend the callers to explicitly pass network namespace so we can use attached BPF program.Signed-off-by Stanislav Fomichev <[email protected]>--- include/linux/skbuff.h | 19 +++++++++++-------- net/core/flow_dissector.c | 27 +++++++++++++++++---------- net/ethernet/eth.c | 5 +++-- 3 files changed, 31 insertions(+), 20 deletions(-)include/linux/skbuff.h +2
-1@@ -1284,7 +1284,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, const struct sk_buff *skb, struct flow_dissector *flow_dissector, struct bpf_flow_keys *flow_keys); -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container,include/linux/skbuff.h +2
-2void *data, __be16 proto, int nhoff, int hlen,@@ -1294,8 +1295,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0,flags);
}static inline bool skb_flow_dissect_flow_keys(const struct
sk_buff
*skb,include/linux/skbuff.h +5
-4@@ -1303,18 +1304,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) { memset(flow, 0, sizeof(*flow)); -return __skb_flow_dissect (skb, &flow_keys_dissector, flow, -NULL ,0 ,0 ,0 , flags); +return __skb_flow_dissect (NULL , skb, &flow_keys_dissector, + flow,NULL ,0 ,0 ,0 , flags); }static inline bool -skb_flow_dissect_flow_keys_basic (const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic (const struct net *net, +const struct sk_buff *skb,struct flow_keys_basic *flow,void *data,__be16 proto,int nhoff,int hlen,unsigned int flags) {memset (flow,0 ,sizeof (*flow)); - return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, + return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector,flow,
include/linux/skbuff.h +2
-1data, proto, nhoff, hlen, flags); }@@ -2494,7 +2496,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb) if (skb_transport_header_was_set(skb)) return; -if (skb_flow_dissect_flow_keys_basic (skb, &keys,NULL ,0 ,0 ,0 , 0)) + if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff);}
net/core/flow_dissector.c +1
-0@@ -722,6 +722,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,/** * __skb_flow_dissect - extract the flow_keys struct and return it +* @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
* @flow_dissector: list of keys to dissect
* @target_container: target structure to put dissected values intonet/core/flow_dissector.c +2
-1@@ -738,7 +739,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog,struct bpf_flow_dissector *ctx, * * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container,
Quoted 1 line
void *data,
__be16proto, int nhoff, int hlen,
LGTM,
Side Note: it is not this patch's fault, but I think that there is lots of room for improvement in __skb_flow_dissect parameters set, it seems that the function can receives two separate sets of parameters and each set is only used when a valid skb is passed, while the other set is used when skb is null but data ptr isn't, this makes this function very hard to read and track it's flow.
My 2 cent is that we need two versions of __skb_flow_dissect, one that uses skb and the other uses data pointer, and the skb version can perfectly use the "data" ptr version, it could be a hard re-factoring task, but i think it is doable.
Re: [PATCH bpf-next v6 3/9] net: plumb network namespace into __skb_flow_dissect
Quoted 125 lines · Saeed Mahameed
Quoted 110 lines · Stanislav Fomichev
This new argument will be used in the next patches for the
eth_get_headlenuse case.eth_get_headlencalls flow dissector with only data (without skb) so there is currently no way to pull attached BPF flow dissector program. With this new argument, we can amend the callers to explicitly pass network namespace so we can use attached BPF program.Signed-off-by Stanislav Fomichev <[email protected]>--- include/linux/skbuff.h | 19 +++++++++++-------- net/core/flow_dissector.c | 27 +++++++++++++++++---------- net/ethernet/eth.c | 5 +++-- 3 files changed, 31 insertions(+), 20 deletions(-)include/linux/skbuff.h +2
-1@@ -1284,7 +1284,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, const struct sk_buff *skb, struct flow_dissector *flow_dissector, struct bpf_flow_keys *flow_keys); -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container,void *data,
__be16proto, int nhoff, int hlen,include/linux/skbuff.h +2
-2@@ -1294,8 +1295,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { - return __skb_flow_dissect(skb, flow_dissector, target_container, - NULL, 0, 0, 0, flags); + return __skb_flow_dissect(NULL, skb, flow_dissector, + target_container, NULL, 0, 0, 0,flags);
}static inline bool skb_flow_dissect_flow_keys(const struct
sk_buff
*skb,include/linux/skbuff.h +5
-4@@ -1303,18 +1304,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, unsigned int flags) { memset(flow, 0, sizeof(*flow)); -return __skb_flow_dissect (skb, &flow_keys_dissector, flow, -NULL ,0 ,0 ,0 , flags); +return __skb_flow_dissect (NULL , skb, &flow_keys_dissector, + flow,NULL ,0 ,0 ,0 , flags); }static inline bool -skb_flow_dissect_flow_keys_basic (const struct sk_buff *skb, +skb_flow_dissect_flow_keys_basic (const struct net *net, +const struct sk_buff *skb,struct flow_keys_basic *flow,void *data,__be16 proto,int nhoff,int hlen,unsigned int flags) {memset (flow,0 ,sizeof (*flow)); - return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, + return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector,flow,
data, proto, nhoff, hlen, flags);}
include/linux/skbuff.h +2
-1@@ -2494,7 +2496,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb) if (skb_transport_header_was_set(skb)) return; -if (skb_flow_dissect_flow_keys_basic (skb, &keys,NULL ,0 ,0 ,0 , 0)) + if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff);}
net/core/flow_dissector.c +1
-0@@ -722,6 +722,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,/** * __skb_flow_dissect - extract the flow_keys struct and return it +* @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
* @flow_dissector: list of keys to dissect
* @target_container: target structure to put dissected values intonet/core/flow_dissector.c +2
-1@@ -738,7 +739,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog,struct bpf_flow_dissector *ctx, * * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container,Quoted 1 line
void *data,
__be16proto, int nhoff, int hlen,LGTM,
Reviewed-by Saeed Mahameed <[email protected]>Side Note: it is not this patch's fault, but I think that there is lots of room for improvement in
__skb_flow_dissectparameters set, it seems that the function can receives two separate sets of parameters and each set is only used when a valid skb is passed, while the other set is used when skb is null but data ptr isn't, this makes this function very hard to read and track it's flow.
Quoted 4 lines
My 2 cent is that we need two versions of
__skb_flow_dissect, one that uses skb and the other uses data pointer, and the skb version can perfectly use the "data" ptr version, it could be a hard re-factoring task, but i think it is doable.
Agreed, the only problem with separating those two is __skb_header_pointer which is occasionally called to fetch more data from the skb frags (for both data!=NULL and skb!=NULL cases).
I was thinking about changing the order of input params to move skb to the end (so it looks more optional) and to move all this !data initialization into a wrapper.
I might look into this at some point..
Quoted 23 lines · Stanislav Fomichev
Currently, when
eth_get_headlencalls flow dissector, it doesn't pass any skb. Because we use passed skb to lookup associated networking namespace to find whether we have a BPF program attached or not, we always use C-based flow dissector in this case.The goal of this patch series is to add new networking namespace argument to the
eth_get_headlenand make BPF flow dissector programs be able to work in the skb-less case.The series goes like this:
* use new kernel context (structbpf_flow_dissector) for flow dissector programs; this makes it easy to distinguish between skb and no-skb case and supports calling BPF flow dissector on a chunk of raw data
* convertBPF_PROG_TEST_RUNto use raw data
* plumb network namespace into__skb_flow_dissectfrom all callers
* handle no-skb case in__skb_flow_dissect
* updateeth_get_headlento include net namespace argument and convert all existing users
* add selftest to make surebpf_skb_load_bytesis not allowed in the no-skb mode
* extendtest_progsto exercise skb-less flow dissection as well
* stop adjusting nhoff/thoff byETH_HLENinBPF_PROG_TEST_RUN
Quoted 6 lines
v6:
* more suggestions by Alexei:
*eth_get_headlennow takes net dev, not net namespace
* test skb-less case via tuneth_get_headlen
* fix return errors inbpf_flow_load
* don't adjust nhoff/thoff byETH_HLEN
All looks good to me.
But I don't trust myself reviewing flow dissector bits :)
Eric and Willem, could you please take a look as well and hopefully ack it ?
Thanks!
Quoted 2 lines · Alexei Starovoitov
Eric and Willem, could you please take a look as well and hopefully ack it ?
Sure, I am taking a look.
Eric Dumazet
Acked-byQuoted 8 lines · Eric Dumazet
Quoted 2 lines · Alexei Starovoitov
Eric and Willem, could you please take a look as well and hopefully ack it ?
Sure, I am taking a look.
For the series :
Thanks
Quoted 9 lines · Eric Dumazet
Quoted 7 lines · Eric Dumazet
Quoted 2 lines · Alexei Starovoitov
Eric and Willem, could you please take a look as well and hopefully ack it ?
Quoted 7 lines
Quoted 1 line
Sure, I am taking a look.
For the series :
Acked-by Eric Dumazet <[email protected]>Thanks
Just finished going over it as well.
Very nice solution wrt testing.
Quoted 16 lines · Willem de Bruijn
Quoted 15 lines · Eric Dumazet
Quoted 8 lines · Eric Dumazet
Quoted 2 lines · Alexei Starovoitov
Eric and Willem, could you please take a look as well and hopefully ack it ?
Sure, I am taking a look.
For the series :
Acked-by Eric Dumazet <[email protected]>
Quoted 7 lines
Quoted 1 line
Thanks
Just finished going over it as well.
Acked-by Willem de Bruijn <[email protected]>Very nice solution wrt testing.
Applied, thanks everyone!