summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile1
-rw-r--r--net/core/dev.c153
-rw-r--r--net/core/filter.c1567
-rw-r--r--net/core/flow.c132
-rw-r--r--net/core/flow_dissector.c24
-rw-r--r--net/core/neighbour.c9
-rw-r--r--net/core/net-sysfs.c22
-rw-r--r--net/core/netpoll.c587
-rw-r--r--net/core/pktgen.c32
-rw-r--r--net/core/ptp_classifier.c141
-rw-r--r--net/core/request_sock.c1
-rw-r--r--net/core/rtnetlink.c113
-rw-r--r--net/core/skbuff.c166
-rw-r--r--net/core/sock_diag.c23
-rw-r--r--net/core/timestamping.c19
15 files changed, 1813 insertions, 1177 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 9628c20acff6..826b925aa453 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -21,5 +21,6 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o
obj-$(CONFIG_TRACEPOINTS) += net-traces.o
obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
+obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 4a91591b30a6..757063420ce0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1245,7 +1245,7 @@ static int __dev_open(struct net_device *dev)
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
- netpoll_rx_disable(dev);
+ netpoll_poll_disable(dev);
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
@@ -1260,7 +1260,7 @@ static int __dev_open(struct net_device *dev)
if (!ret && ops->ndo_open)
ret = ops->ndo_open(dev);
- netpoll_rx_enable(dev);
+ netpoll_poll_enable(dev);
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1313,6 +1313,9 @@ static int __dev_close_many(struct list_head *head)
might_sleep();
list_for_each_entry(dev, head, close_list) {
+ /* Temporarily disable netpoll until the interface is down */
+ netpoll_poll_disable(dev);
+
call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
clear_bit(__LINK_STATE_START, &dev->state);
@@ -1343,6 +1346,7 @@ static int __dev_close_many(struct list_head *head)
dev->flags &= ~IFF_UP;
net_dmaengine_put();
+ netpoll_poll_enable(dev);
}
return 0;
@@ -1353,14 +1357,10 @@ static int __dev_close(struct net_device *dev)
int retval;
LIST_HEAD(single);
- /* Temporarily disable netpoll until the interface is down */
- netpoll_rx_disable(dev);
-
list_add(&dev->close_list, &single);
retval = __dev_close_many(&single);
list_del(&single);
- netpoll_rx_enable(dev);
return retval;
}
@@ -1398,14 +1398,9 @@ int dev_close(struct net_device *dev)
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
- /* Block netpoll rx while the interface is going down */
- netpoll_rx_disable(dev);
-
list_add(&dev->close_list, &single);
dev_close_many(&single);
list_del(&single);
-
- netpoll_rx_enable(dev);
}
return 0;
}
@@ -1645,8 +1640,7 @@ static inline void net_timestamp_set(struct sk_buff *skb)
__net_timestamp(SKB); \
} \
-static inline bool is_skb_forwardable(struct net_device *dev,
- struct sk_buff *skb)
+bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb)
{
unsigned int len;
@@ -1665,6 +1659,7 @@ static inline bool is_skb_forwardable(struct net_device *dev,
return false;
}
+EXPORT_SYMBOL_GPL(is_skb_forwardable);
/**
* dev_forward_skb - loopback an skb to another netif
@@ -2885,6 +2880,7 @@ recursion_alert:
rc = -ENETDOWN;
rcu_read_unlock_bh();
+ atomic_long_inc(&dev->tx_dropped);
kfree_skb(skb);
return rc;
out:
@@ -2957,7 +2953,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
flow_table = rcu_dereference(rxqueue->rps_flow_table);
if (!flow_table)
goto out;
- flow_id = skb->rxhash & flow_table->mask;
+ flow_id = skb_get_hash(skb) & flow_table->mask;
rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
rxq_index, flow_id);
if (rc < 0)
@@ -2991,6 +2987,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_sock_flow_table *sock_flow_table;
int cpu = -1;
u16 tcpu;
+ u32 hash;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
@@ -3019,7 +3016,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
skb_reset_network_header(skb);
- if (!skb_get_hash(skb))
+ hash = skb_get_hash(skb);
+ if (!hash)
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3028,11 +3026,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
u16 next_cpu;
struct rps_dev_flow *rflow;
- rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+ rflow = &flow_table->flows[hash & flow_table->mask];
tcpu = rflow->cpu;
- next_cpu = sock_flow_table->ents[skb->rxhash &
- sock_flow_table->mask];
+ next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
/*
* If the desired CPU (where last recvmsg was done) is
@@ -3061,7 +3058,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
if (map) {
- tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+ tcpu = map->cpus[((u64) hash * map->len) >> 32];
if (cpu_online(tcpu)) {
cpu = tcpu;
@@ -3236,10 +3233,6 @@ static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
- /* if netpoll wants it, pretend we never saw it */
- if (netpoll_rx(skb))
- return NET_RX_DROP;
-
net_timestamp_check(netdev_tstamp_prequeue, skb);
trace_netif_rx(skb);
@@ -3500,11 +3493,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
{
switch (skb->protocol) {
- case __constant_htons(ETH_P_ARP):
- case __constant_htons(ETH_P_IP):
- case __constant_htons(ETH_P_IPV6):
- case __constant_htons(ETH_P_8021Q):
- case __constant_htons(ETH_P_8021AD):
+ case htons(ETH_P_ARP):
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ case htons(ETH_P_8021Q):
+ case htons(ETH_P_8021AD):
return true;
default:
return false;
@@ -3525,10 +3518,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
trace_netif_receive_skb(skb);
- /* if we've gotten here through NAPI, check netpoll */
- if (netpoll_receive_skb(skb))
- goto out;
-
orig_dev = skb->dev;
skb_reset_network_header(skb);
@@ -3655,7 +3644,6 @@ drop:
unlock:
rcu_read_unlock();
-out:
return ret;
}
@@ -3845,10 +3833,10 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
diffs |= p->vlan_tci ^ skb->vlan_tci;
if (maclen == ETH_HLEN)
diffs |= compare_ether_header(skb_mac_header(p),
- skb_gro_mac_header(skb));
+ skb_mac_header(skb));
else if (!diffs)
diffs = memcmp(skb_mac_header(p),
- skb_gro_mac_header(skb),
+ skb_mac_header(skb),
maclen);
NAPI_GRO_CB(p)->same_flow = !diffs;
}
@@ -3871,6 +3859,27 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
}
}
+static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
+{
+ struct skb_shared_info *pinfo = skb_shinfo(skb);
+
+ BUG_ON(skb->end - skb->tail < grow);
+
+ memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
+
+ skb->data_len -= grow;
+ skb->tail += grow;
+
+ pinfo->frags[0].page_offset += grow;
+ skb_frag_size_sub(&pinfo->frags[0], grow);
+
+ if (unlikely(!skb_frag_size(&pinfo->frags[0]))) {
+ skb_frag_unref(skb, 0);
+ memmove(pinfo->frags, pinfo->frags + 1,
+ --pinfo->nr_frags * sizeof(pinfo->frags[0]));
+ }
+}
+
static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
@@ -3879,14 +3888,14 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
struct list_head *head = &offload_base;
int same_flow;
enum gro_result ret;
+ int grow;
- if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
+ if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
if (skb_is_gso(skb) || skb_has_frag_list(skb))
goto normal;
- skb_gro_reset_offset(skb);
gro_list_prepare(napi, skb);
NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
@@ -3950,27 +3959,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
ret = GRO_HELD;
pull:
- if (skb_headlen(skb) < skb_gro_offset(skb)) {
- int grow = skb_gro_offset(skb) - skb_headlen(skb);
-
- BUG_ON(skb->end - skb->tail < grow);
-
- memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
-
- skb->tail += grow;
- skb->data_len -= grow;
-
- skb_shinfo(skb)->frags[0].page_offset += grow;
- skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
-
- if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
- skb_frag_unref(skb, 0);
- memmove(skb_shinfo(skb)->frags,
- skb_shinfo(skb)->frags + 1,
- --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
- }
- }
-
+ grow = skb_gro_offset(skb) - skb_headlen(skb);
+ if (grow > 0)
+ gro_pull_from_frag0(skb, grow);
ok:
return ret;
@@ -4038,6 +4029,8 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
trace_napi_gro_receive_entry(skb);
+ skb_gro_reset_offset(skb);
+
return napi_skb_finish(dev_gro_receive(napi, skb), skb);
}
EXPORT_SYMBOL(napi_gro_receive);
@@ -4066,12 +4059,16 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_get_frags);
-static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
- gro_result_t ret)
+static gro_result_t napi_frags_finish(struct napi_struct *napi,
+ struct sk_buff *skb,
+ gro_result_t ret)
{
switch (ret) {
case GRO_NORMAL:
- if (netif_receive_skb_internal(skb))
+ case GRO_HELD:
+ __skb_push(skb, ETH_HLEN);
+ skb->protocol = eth_type_trans(skb, skb->dev);
+ if (ret == GRO_NORMAL && netif_receive_skb_internal(skb))
ret = GRO_DROP;
break;
@@ -4080,7 +4077,6 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
napi_reuse_skb(napi, skb);
break;
- case GRO_HELD:
case GRO_MERGED:
break;
}
@@ -4088,17 +4084,41 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
return ret;
}
+/* Upper GRO stack assumes network header starts at gro_offset=0
+ * Drivers could call both napi_gro_frags() and napi_gro_receive()
+ * We copy ethernet header into skb->data to have a common layout.
+ */
static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
struct sk_buff *skb = napi->skb;
+ const struct ethhdr *eth;
+ unsigned int hlen = sizeof(*eth);
napi->skb = NULL;
- if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
- napi_reuse_skb(napi, skb);
- return NULL;
+ skb_reset_mac_header(skb);
+ skb_gro_reset_offset(skb);
+
+ eth = skb_gro_header_fast(skb, 0);
+ if (unlikely(skb_gro_header_hard(skb, hlen))) {
+ eth = skb_gro_header_slow(skb, hlen, 0);
+ if (unlikely(!eth)) {
+ napi_reuse_skb(napi, skb);
+ return NULL;
+ }
+ } else {
+ gro_pull_from_frag0(skb, hlen);
+ NAPI_GRO_CB(skb)->frag0 += hlen;
+ NAPI_GRO_CB(skb)->frag0_len -= hlen;
}
- skb->protocol = eth_type_trans(skb, skb->dev);
+ __skb_pull(skb, hlen);
+
+ /*
+ * This works because the only protocols we care about don't require
+ * special handling.
+ * We'll fix it up properly in napi_frags_finish()
+ */
+ skb->protocol = eth->h_proto;
return skb;
}
@@ -6251,6 +6271,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
netdev_stats_to_stats64(storage, &dev->stats);
}
storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
+ storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
diff --git a/net/core/filter.c b/net/core/filter.c
index ad30d626a5bd..765556ba32ef 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1,11 +1,16 @@
/*
* Linux Socket Filter - Kernel level socket filtering
*
- * Author:
- * Jay Schulist <jschlst@samba.org>
+ * Based on the design of the Berkeley Packet Filter. The new
+ * internal format has been designed by PLUMgrid:
*
- * Based on the design of:
- * - The Berkeley Packet Filter
+ * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
+ *
+ * Authors:
+ *
+ * Jay Schulist <jschlst@samba.org>
+ * Alexei Starovoitov <ast@plumgrid.com>
+ * Daniel Borkmann <dborkman@redhat.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -108,304 +113,1045 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(sk_filter);
+/* Base function for offset calculation. Needs to go into .text section,
+ * therefore keeping it non-static as well; will also be used by JITs
+ * anyway later on, so do not let the compiler omit it.
+ */
+noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ return 0;
+}
+
/**
- * sk_run_filter - run a filter on a socket
- * @skb: buffer to run the filter on
- * @fentry: filter to apply
+ * __sk_run_filter - run a filter on a given context
+ * @ctx: buffer to run the filter on
+ * @insn: filter to apply
*
- * Decode and apply filter instructions to the skb->data.
- * Return length to keep, 0 for none. @skb is the data we are
- * filtering, @filter is the array of filter instructions.
- * Because all jumps are guaranteed to be before last instruction,
- * and last instruction guaranteed to be a RET, we dont need to check
- * flen. (We used to pass to this function the length of filter)
+ * Decode and apply filter instructions to the skb->data. Return length to
+ * keep, 0 for none. @ctx is the data we are operating on, @insn is the
+ * array of filter instructions.
*/
-unsigned int sk_run_filter(const struct sk_buff *skb,
- const struct sock_filter *fentry)
+unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
{
+ u64 stack[MAX_BPF_STACK / sizeof(u64)];
+ u64 regs[MAX_BPF_REG], tmp;
void *ptr;
- u32 A = 0; /* Accumulator */
- u32 X = 0; /* Index Register */
- u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */
- u32 tmp;
- int k;
+ int off;
- /*
- * Process array of filter instructions.
- */
- for (;; fentry++) {
-#if defined(CONFIG_X86_32)
-#define K (fentry->k)
-#else
- const u32 K = fentry->k;
-#endif
-
- switch (fentry->code) {
- case BPF_S_ALU_ADD_X:
- A += X;
- continue;
- case BPF_S_ALU_ADD_K:
- A += K;
- continue;
- case BPF_S_ALU_SUB_X:
- A -= X;
- continue;
- case BPF_S_ALU_SUB_K:
- A -= K;
- continue;
- case BPF_S_ALU_MUL_X:
- A *= X;
- continue;
- case BPF_S_ALU_MUL_K:
- A *= K;
- continue;
- case BPF_S_ALU_DIV_X:
- if (X == 0)
- return 0;
- A /= X;
- continue;
- case BPF_S_ALU_DIV_K:
- A /= K;
- continue;
- case BPF_S_ALU_MOD_X:
- if (X == 0)
- return 0;
- A %= X;
- continue;
- case BPF_S_ALU_MOD_K:
- A %= K;
- continue;
- case BPF_S_ALU_AND_X:
- A &= X;
- continue;
- case BPF_S_ALU_AND_K:
- A &= K;
- continue;
- case BPF_S_ALU_OR_X:
- A |= X;
- continue;
- case BPF_S_ALU_OR_K:
- A |= K;
- continue;
- case BPF_S_ANC_ALU_XOR_X:
- case BPF_S_ALU_XOR_X:
- A ^= X;
- continue;
- case BPF_S_ALU_XOR_K:
- A ^= K;
- continue;
- case BPF_S_ALU_LSH_X:
- A <<= X;
- continue;
- case BPF_S_ALU_LSH_K:
- A <<= K;
- continue;
- case BPF_S_ALU_RSH_X:
- A >>= X;
- continue;
- case BPF_S_ALU_RSH_K:
- A >>= K;
- continue;
- case BPF_S_ALU_NEG:
- A = -A;
- continue;
- case BPF_S_JMP_JA:
- fentry += K;
- continue;
- case BPF_S_JMP_JGT_K:
- fentry += (A > K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JGE_K:
- fentry += (A >= K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JEQ_K:
- fentry += (A == K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JSET_K:
- fentry += (A & K) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JGT_X:
- fentry += (A > X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JGE_X:
- fentry += (A >= X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JEQ_X:
- fentry += (A == X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_JMP_JSET_X:
- fentry += (A & X) ? fentry->jt : fentry->jf;
- continue;
- case BPF_S_LD_W_ABS:
- k = K;
-load_w:
- ptr = load_pointer(skb, k, 4, &tmp);
- if (ptr != NULL) {
- A = get_unaligned_be32(ptr);
- continue;
- }
- return 0;
- case BPF_S_LD_H_ABS:
- k = K;
-load_h:
- ptr = load_pointer(skb, k, 2, &tmp);
- if (ptr != NULL) {
- A = get_unaligned_be16(ptr);
- continue;
+#define K insn->imm
+#define A regs[insn->a_reg]
+#define X regs[insn->x_reg]
+#define R0 regs[0]
+
+#define CONT ({insn++; goto select_insn; })
+#define CONT_JMP ({insn++; goto select_insn; })
+
+ static const void *jumptable[256] = {
+ [0 ... 255] = &&default_label,
+ /* Now overwrite non-defaults ... */
+#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C
+ DL(BPF_ALU, BPF_ADD, BPF_X),
+ DL(BPF_ALU, BPF_ADD, BPF_K),
+ DL(BPF_ALU, BPF_SUB, BPF_X),
+ DL(BPF_ALU, BPF_SUB, BPF_K),
+ DL(BPF_ALU, BPF_AND, BPF_X),
+ DL(BPF_ALU, BPF_AND, BPF_K),
+ DL(BPF_ALU, BPF_OR, BPF_X),
+ DL(BPF_ALU, BPF_OR, BPF_K),
+ DL(BPF_ALU, BPF_LSH, BPF_X),
+ DL(BPF_ALU, BPF_LSH, BPF_K),
+ DL(BPF_ALU, BPF_RSH, BPF_X),
+ DL(BPF_ALU, BPF_RSH, BPF_K),
+ DL(BPF_ALU, BPF_XOR, BPF_X),
+ DL(BPF_ALU, BPF_XOR, BPF_K),
+ DL(BPF_ALU, BPF_MUL, BPF_X),
+ DL(BPF_ALU, BPF_MUL, BPF_K),
+ DL(BPF_ALU, BPF_MOV, BPF_X),
+ DL(BPF_ALU, BPF_MOV, BPF_K),
+ DL(BPF_ALU, BPF_DIV, BPF_X),
+ DL(BPF_ALU, BPF_DIV, BPF_K),
+ DL(BPF_ALU, BPF_MOD, BPF_X),
+ DL(BPF_ALU, BPF_MOD, BPF_K),
+ DL(BPF_ALU, BPF_NEG, 0),
+ DL(BPF_ALU, BPF_END, BPF_TO_BE),
+ DL(BPF_ALU, BPF_END, BPF_TO_LE),
+ DL(BPF_ALU64, BPF_ADD, BPF_X),
+ DL(BPF_ALU64, BPF_ADD, BPF_K),
+ DL(BPF_ALU64, BPF_SUB, BPF_X),
+ DL(BPF_ALU64, BPF_SUB, BPF_K),
+ DL(BPF_ALU64, BPF_AND, BPF_X),
+ DL(BPF_ALU64, BPF_AND, BPF_K),
+ DL(BPF_ALU64, BPF_OR, BPF_X),
+ DL(BPF_ALU64, BPF_OR, BPF_K),
+ DL(BPF_ALU64, BPF_LSH, BPF_X),
+ DL(BPF_ALU64, BPF_LSH, BPF_K),
+ DL(BPF_ALU64, BPF_RSH, BPF_X),
+ DL(BPF_ALU64, BPF_RSH, BPF_K),
+ DL(BPF_ALU64, BPF_XOR, BPF_X),
+ DL(BPF_ALU64, BPF_XOR, BPF_K),
+ DL(BPF_ALU64, BPF_MUL, BPF_X),
+ DL(BPF_ALU64, BPF_MUL, BPF_K),
+ DL(BPF_ALU64, BPF_MOV, BPF_X),
+ DL(BPF_ALU64, BPF_MOV, BPF_K),
+ DL(BPF_ALU64, BPF_ARSH, BPF_X),
+ DL(BPF_ALU64, BPF_ARSH, BPF_K),
+ DL(BPF_ALU64, BPF_DIV, BPF_X),
+ DL(BPF_ALU64, BPF_DIV, BPF_K),
+ DL(BPF_ALU64, BPF_MOD, BPF_X),
+ DL(BPF_ALU64, BPF_MOD, BPF_K),
+ DL(BPF_ALU64, BPF_NEG, 0),
+ DL(BPF_JMP, BPF_CALL, 0),
+ DL(BPF_JMP, BPF_JA, 0),
+ DL(BPF_JMP, BPF_JEQ, BPF_X),
+ DL(BPF_JMP, BPF_JEQ, BPF_K),
+ DL(BPF_JMP, BPF_JNE, BPF_X),
+ DL(BPF_JMP, BPF_JNE, BPF_K),
+ DL(BPF_JMP, BPF_JGT, BPF_X),
+ DL(BPF_JMP, BPF_JGT, BPF_K),
+ DL(BPF_JMP, BPF_JGE, BPF_X),
+ DL(BPF_JMP, BPF_JGE, BPF_K),
+ DL(BPF_JMP, BPF_JSGT, BPF_X),
+ DL(BPF_JMP, BPF_JSGT, BPF_K),
+ DL(BPF_JMP, BPF_JSGE, BPF_X),
+ DL(BPF_JMP, BPF_JSGE, BPF_K),
+ DL(BPF_JMP, BPF_JSET, BPF_X),
+ DL(BPF_JMP, BPF_JSET, BPF_K),
+ DL(BPF_JMP, BPF_EXIT, 0),
+ DL(BPF_STX, BPF_MEM, BPF_B),
+ DL(BPF_STX, BPF_MEM, BPF_H),
+ DL(BPF_STX, BPF_MEM, BPF_W),
+ DL(BPF_STX, BPF_MEM, BPF_DW),
+ DL(BPF_STX, BPF_XADD, BPF_W),
+ DL(BPF_STX, BPF_XADD, BPF_DW),
+ DL(BPF_ST, BPF_MEM, BPF_B),
+ DL(BPF_ST, BPF_MEM, BPF_H),
+ DL(BPF_ST, BPF_MEM, BPF_W),
+ DL(BPF_ST, BPF_MEM, BPF_DW),
+ DL(BPF_LDX, BPF_MEM, BPF_B),
+ DL(BPF_LDX, BPF_MEM, BPF_H),
+ DL(BPF_LDX, BPF_MEM, BPF_W),
+ DL(BPF_LDX, BPF_MEM, BPF_DW),
+ DL(BPF_LD, BPF_ABS, BPF_W),
+ DL(BPF_LD, BPF_ABS, BPF_H),
+ DL(BPF_LD, BPF_ABS, BPF_B),
+ DL(BPF_LD, BPF_IND, BPF_W),
+ DL(BPF_LD, BPF_IND, BPF_H),
+ DL(BPF_LD, BPF_IND, BPF_B),
+#undef DL
+ };
+
+ regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+ regs[ARG1_REG] = (u64) (unsigned long) ctx;
+
+select_insn:
+ goto *jumptable[insn->code];
+
+ /* ALU */
+#define ALU(OPCODE, OP) \
+ BPF_ALU64_##OPCODE##_BPF_X: \
+ A = A OP X; \
+ CONT; \
+ BPF_ALU_##OPCODE##_BPF_X: \
+ A = (u32) A OP (u32) X; \
+ CONT; \
+ BPF_ALU64_##OPCODE##_BPF_K: \
+ A = A OP K; \
+ CONT; \
+ BPF_ALU_##OPCODE##_BPF_K: \
+ A = (u32) A OP (u32) K; \
+ CONT;
+
+ ALU(BPF_ADD, +)
+ ALU(BPF_SUB, -)
+ ALU(BPF_AND, &)
+ ALU(BPF_OR, |)
+ ALU(BPF_LSH, <<)
+ ALU(BPF_RSH, >>)
+ ALU(BPF_XOR, ^)
+ ALU(BPF_MUL, *)
+#undef ALU
+ BPF_ALU_BPF_NEG_0:
+ A = (u32) -A;
+ CONT;
+ BPF_ALU64_BPF_NEG_0:
+ A = -A;
+ CONT;
+ BPF_ALU_BPF_MOV_BPF_X:
+ A = (u32) X;
+ CONT;
+ BPF_ALU_BPF_MOV_BPF_K:
+ A = (u32) K;
+ CONT;
+ BPF_ALU64_BPF_MOV_BPF_X:
+ A = X;
+ CONT;
+ BPF_ALU64_BPF_MOV_BPF_K:
+ A = K;
+ CONT;
+ BPF_ALU64_BPF_ARSH_BPF_X:
+ (*(s64 *) &A) >>= X;
+ CONT;
+ BPF_ALU64_BPF_ARSH_BPF_K:
+ (*(s64 *) &A) >>= K;
+ CONT;
+ BPF_ALU64_BPF_MOD_BPF_X:
+ tmp = A;
+ if (X)
+ A = do_div(tmp, X);
+ CONT;
+ BPF_ALU_BPF_MOD_BPF_X:
+ tmp = (u32) A;
+ if (X)
+ A = do_div(tmp, (u32) X);
+ CONT;
+ BPF_ALU64_BPF_MOD_BPF_K:
+ tmp = A;
+ if (K)
+ A = do_div(tmp, K);
+ CONT;
+ BPF_ALU_BPF_MOD_BPF_K:
+ tmp = (u32) A;
+ if (K)
+ A = do_div(tmp, (u32) K);
+ CONT;
+ BPF_ALU64_BPF_DIV_BPF_X:
+ if (X)
+ do_div(A, X);
+ CONT;
+ BPF_ALU_BPF_DIV_BPF_X:
+ tmp = (u32) A;
+ if (X)
+ do_div(tmp, (u32) X);
+ A = (u32) tmp;
+ CONT;
+ BPF_ALU64_BPF_DIV_BPF_K:
+ if (K)
+ do_div(A, K);
+ CONT;
+ BPF_ALU_BPF_DIV_BPF_K:
+ tmp = (u32) A;
+ if (K)
+ do_div(tmp, (u32) K);
+ A = (u32) tmp;
+ CONT;
+ BPF_ALU_BPF_END_BPF_TO_BE:
+ switch (K) {
+ case 16:
+ A = (__force u16) cpu_to_be16(A);
+ break;
+ case 32:
+ A = (__force u32) cpu_to_be32(A);
+ break;
+ case 64:
+ A = (__force u64) cpu_to_be64(A);
+ break;
+ }
+ CONT;
+ BPF_ALU_BPF_END_BPF_TO_LE:
+ switch (K) {
+ case 16:
+ A = (__force u16) cpu_to_le16(A);
+ break;
+ case 32:
+ A = (__force u32) cpu_to_le32(A);
+ break;
+ case 64:
+ A = (__force u64) cpu_to_le64(A);
+ break;
+ }
+ CONT;
+
+ /* CALL */
+ BPF_JMP_BPF_CALL_0:
+ /* Function call scratches R1-R5 registers, preserves R6-R9,
+ * and stores return value into R0.
+ */
+ R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3],
+ regs[4], regs[5]);
+ CONT;
+
+ /* JMP */
+ BPF_JMP_BPF_JA_0:
+ insn += insn->off;
+ CONT;
+ BPF_JMP_BPF_JEQ_BPF_X:
+ if (A == X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JEQ_BPF_K:
+ if (A == K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JNE_BPF_X:
+ if (A != X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JNE_BPF_K:
+ if (A != K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGT_BPF_X:
+ if (A > X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGT_BPF_K:
+ if (A > K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGE_BPF_X:
+ if (A >= X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JGE_BPF_K:
+ if (A >= K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGT_BPF_X:
+ if (((s64)A) > ((s64)X)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGT_BPF_K:
+ if (((s64)A) > ((s64)K)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGE_BPF_X:
+ if (((s64)A) >= ((s64)X)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSGE_BPF_K:
+ if (((s64)A) >= ((s64)K)) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSET_BPF_X:
+ if (A & X) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_JSET_BPF_K:
+ if (A & K) {
+ insn += insn->off;
+ CONT_JMP;
+ }
+ CONT;
+ BPF_JMP_BPF_EXIT_0:
+ return R0;
+
+ /* STX and ST and LDX*/
+#define LDST(SIZEOP, SIZE) \
+ BPF_STX_BPF_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (A + insn->off) = X; \
+ CONT; \
+ BPF_ST_BPF_MEM_##SIZEOP: \
+ *(SIZE *)(unsigned long) (A + insn->off) = K; \
+ CONT; \
+ BPF_LDX_BPF_MEM_##SIZEOP: \
+ A = *(SIZE *)(unsigned long) (X + insn->off); \
+ CONT;
+
+ LDST(BPF_B, u8)
+ LDST(BPF_H, u16)
+ LDST(BPF_W, u32)
+ LDST(BPF_DW, u64)
+#undef LDST
+ BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */
+ atomic_add((u32) X, (atomic_t *)(unsigned long)
+ (A + insn->off));
+ CONT;
+ BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */
+ atomic64_add((u64) X, (atomic64_t *)(unsigned long)
+ (A + insn->off));
+ CONT;
+ BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */
+ off = K;
+load_word:
+ /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
+ * appearing in the programs where ctx == skb. All programs
+ * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter()
+ * saves it in R6, internal BPF verifier will check that
+ * R6 == ctx.
+ *
+ * BPF_ABS and BPF_IND are wrappers of function calls, so
+ * they scratch R1-R5 registers, preserve R6-R9, and store
+ * return value into R0.
+ *
+ * Implicit input:
+ * ctx
+ *
+ * Explicit input:
+ * X == any register
+ * K == 32-bit immediate
+ *
+ * Output:
+ * R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+ ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp);
+ if (likely(ptr != NULL)) {
+ R0 = get_unaligned_be32(ptr);
+ CONT;
+ }
+ return 0;
+ BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */
+ off = K;
+load_half:
+ ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp);
+ if (likely(ptr != NULL)) {
+ R0 = get_unaligned_be16(ptr);
+ CONT;
+ }
+ return 0;
+ BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */
+ off = K;
+load_byte:
+ ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp);
+ if (likely(ptr != NULL)) {
+ R0 = *(u8 *)ptr;
+ CONT;
+ }
+ return 0;
+ BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */
+ off = K + X;
+ goto load_word;
+ BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */
+ off = K + X;
+ goto load_half;
+ BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */
+ off = K + X;
+ goto load_byte;
+
+ default_label:
+ /* If we ever reach this, we have a bug somewhere. */
+ WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+ return 0;
+#undef CONT_JMP
+#undef CONT
+
+#undef R0
+#undef X
+#undef A
+#undef K
+}
+
+u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
+ const struct sock_filter_int *insni)
+ __attribute__ ((alias ("__sk_run_filter")));
+
+u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
+ const struct sock_filter_int *insni)
+ __attribute__ ((alias ("__sk_run_filter")));
+EXPORT_SYMBOL_GPL(sk_run_filter_int_skb);
+
+/* Helper to find the offset of pkt_type in sk_buff structure. We want
+ * to make sure its still a 3bit field starting at a byte boundary;
+ * taken from arch/x86/net/bpf_jit_comp.c.
+ */
+#define PKT_TYPE_MAX 7
+static unsigned int pkt_type_offset(void)
+{
+ struct sk_buff skb_probe = { .pkt_type = ~0, };
+ u8 *ct = (u8 *) &skb_probe;
+ unsigned int off;
+
+ for (off = 0; off < sizeof(struct sk_buff); off++) {
+ if (ct[off] == PKT_TYPE_MAX)
+ return off;
+ }
+
+ pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__);
+ return -1;
+}
+
+static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+
+ return __skb_get_poff(skb);
+}
+
+static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+ struct nlattr *nla;
+
+ if (skb_is_nonlinear(skb))
+ return 0;
+
+ if (A > skb->len - sizeof(struct nlattr))
+ return 0;
+
+ nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X);
+ if (nla)
+ return (void *) nla - (void *) skb->data;
+
+ return 0;
+}
+
+static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+ struct nlattr *nla;
+
+ if (skb_is_nonlinear(skb))
+ return 0;
+
+ if (A > skb->len - sizeof(struct nlattr))
+ return 0;
+
+ nla = (struct nlattr *) &skb->data[A];
+ if (nla->nla_len > A - skb->len)
+ return 0;
+
+ nla = nla_find_nested(nla, X);
+ if (nla)
+ return (void *) nla - (void *) skb->data;
+
+ return 0;
+}
+
+static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+ return raw_smp_processor_id();
+}
+
+/* Register mappings for user programs. */
+#define A_REG 0
+#define X_REG 7
+#define TMP_REG 8
+#define ARG2_REG 2
+#define ARG3_REG 3
+
+static bool convert_bpf_extensions(struct sock_filter *fp,
+ struct sock_filter_int **insnp)
+{
+ struct sock_filter_int *insn = *insnp;
+
+ switch (fp->k) {
+ case SKF_AD_OFF + SKF_AD_PROTOCOL:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, protocol);
+ insn++;
+
+ /* A = ntohs(A) [emitting a nop or swap16] */
+ insn->code = BPF_ALU | BPF_END | BPF_FROM_BE;
+ insn->a_reg = A_REG;
+ insn->imm = 16;
+ break;
+
+ case SKF_AD_OFF + SKF_AD_PKTTYPE:
+ insn->code = BPF_LDX | BPF_MEM | BPF_B;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = pkt_type_offset();
+ if (insn->off < 0)
+ return false;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = PKT_TYPE_MAX;
+ break;
+
+ case SKF_AD_OFF + SKF_AD_IFINDEX:
+ case SKF_AD_OFF + SKF_AD_HATYPE:
+ if (FIELD_SIZEOF(struct sk_buff, dev) == 8)
+ insn->code = BPF_LDX | BPF_MEM | BPF_DW;
+ else
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = TMP_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, dev);
+ insn++;
+
+ insn->code = BPF_JMP | BPF_JNE | BPF_K;
+ insn->a_reg = TMP_REG;
+ insn->imm = 0;
+ insn->off = 1;
+ insn++;
+
+ insn->code = BPF_JMP | BPF_EXIT;
+ insn++;
+
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
+ BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
+
+ insn->a_reg = A_REG;
+ insn->x_reg = TMP_REG;
+
+ if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) {
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->off = offsetof(struct net_device, ifindex);
+ } else {
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->off = offsetof(struct net_device, type);
+ }
+ break;
+
+ case SKF_AD_OFF + SKF_AD_MARK:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, mark);
+ break;
+
+ case SKF_AD_OFF + SKF_AD_RXHASH:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, hash);
+ break;
+
+ case SKF_AD_OFF + SKF_AD_QUEUE:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, queue_mapping);
+ break;
+
+ case SKF_AD_OFF + SKF_AD_VLAN_TAG:
+ case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
+ BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+
+ insn->code = BPF_LDX | BPF_MEM | BPF_H;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, vlan_tci);
+ insn++;
+
+ BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
+ if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = ~VLAN_TAG_PRESENT;
+ } else {
+ insn->code = BPF_ALU | BPF_RSH | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 12;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 1;
+ }
+ break;
+
+ case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+ case SKF_AD_OFF + SKF_AD_NLATTR:
+ case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+ case SKF_AD_OFF + SKF_AD_CPU:
+ /* arg1 = ctx */
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = ARG1_REG;
+ insn->x_reg = CTX_REG;
+ insn++;
+
+ /* arg2 = A */
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = ARG2_REG;
+ insn->x_reg = A_REG;
+ insn++;
+
+ /* arg3 = X */
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = ARG3_REG;
+ insn->x_reg = X_REG;
+ insn++;
+
+ /* Emit call(ctx, arg2=A, arg3=X) */
+ insn->code = BPF_JMP | BPF_CALL;
+ switch (fp->k) {
+ case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+ insn->imm = __skb_get_pay_offset - __bpf_call_base;
+ break;
+ case SKF_AD_OFF + SKF_AD_NLATTR:
+ insn->imm = __skb_get_nlattr - __bpf_call_base;
+ break;
+ case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+ insn->imm = __skb_get_nlattr_nest - __bpf_call_base;
+ break;
+ case SKF_AD_OFF + SKF_AD_CPU:
+ insn->imm = __get_raw_cpu_id - __bpf_call_base;
+ break;
+ }
+ break;
+
+ case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
+ insn->code = BPF_ALU | BPF_XOR | BPF_X;
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ break;
+
+ default:
+ /* This is just a dummy call to avoid letting the compiler
+ * evict __bpf_call_base() as an optimization. Placed here
+ * where no-one bothers.
+ */
+ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0);
+ return false;
+ }
+
+ *insnp = insn;
+ return true;
+}
+
+/**
+ * sk_convert_filter - convert filter program
+ * @prog: the user passed filter program
+ * @len: the length of the user passed filter program
+ * @new_prog: buffer where converted program will be stored
+ * @new_len: pointer to store length of converted program
+ *
+ * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
+ * Conversion workflow:
+ *
+ * 1) First pass for calculating the new program length:
+ * sk_convert_filter(old_prog, old_len, NULL, &new_len)
+ *
+ * 2) 2nd pass to remap in two passes: 1st pass finds new
+ * jump offsets, 2nd pass remapping:
+ * new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len);
+ * sk_convert_filter(old_prog, old_len, new_prog, &new_len);
+ *
+ * User BPF's register A is mapped to our BPF register 6, user BPF
+ * register X is mapped to BPF register 7; frame pointer is always
+ * register 10; Context 'void *ctx' is stored in register 1, that is,
+ * for socket filters: ctx == 'struct sk_buff *', for seccomp:
+ * ctx == 'struct seccomp_data *'.
+ */
+int sk_convert_filter(struct sock_filter *prog, int len,
+ struct sock_filter_int *new_prog, int *new_len)
+{
+ int new_flen = 0, pass = 0, target, i;
+ struct sock_filter_int *new_insn;
+ struct sock_filter *fp;
+ int *addrs = NULL;
+ u8 bpf_src;
+
+ BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
+ BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG);
+
+ if (len <= 0 || len >= BPF_MAXINSNS)
+ return -EINVAL;
+
+ if (new_prog) {
+ addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL);
+ if (!addrs)
+ return -ENOMEM;
+ }
+
+do_pass:
+ new_insn = new_prog;
+ fp = prog;
+
+ if (new_insn) {
+ new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ new_insn->a_reg = CTX_REG;
+ new_insn->x_reg = ARG1_REG;
+ }
+ new_insn++;
+
+ for (i = 0; i < len; fp++, i++) {
+ struct sock_filter_int tmp_insns[6] = { };
+ struct sock_filter_int *insn = tmp_insns;
+
+ if (addrs)
+ addrs[i] = new_insn - new_prog;
+
+ switch (fp->code) {
+ /* All arithmetic insns and skb loads map as-is. */
+ case BPF_ALU | BPF_ADD | BPF_X:
+ case BPF_ALU | BPF_ADD | BPF_K:
+ case BPF_ALU | BPF_SUB | BPF_X:
+ case BPF_ALU | BPF_SUB | BPF_K:
+ case BPF_ALU | BPF_AND | BPF_X:
+ case BPF_ALU | BPF_AND | BPF_K:
+ case BPF_ALU | BPF_OR | BPF_X:
+ case BPF_ALU | BPF_OR | BPF_K:
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_LSH | BPF_K:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_K:
+ case BPF_ALU | BPF_XOR | BPF_X:
+ case BPF_ALU | BPF_XOR | BPF_K:
+ case BPF_ALU | BPF_MUL | BPF_X:
+ case BPF_ALU | BPF_MUL | BPF_K:
+ case BPF_ALU | BPF_DIV | BPF_X:
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_X:
+ case BPF_ALU | BPF_MOD | BPF_K:
+ case BPF_ALU | BPF_NEG:
+ case BPF_LD | BPF_ABS | BPF_W:
+ case BPF_LD | BPF_ABS | BPF_H:
+ case BPF_LD | BPF_ABS | BPF_B:
+ case BPF_LD | BPF_IND | BPF_W:
+ case BPF_LD | BPF_IND | BPF_H:
+ case BPF_LD | BPF_IND | BPF_B:
+ /* Check for overloaded BPF extension and
+ * directly convert it if found, otherwise
+ * just move on with mapping.
+ */
+ if (BPF_CLASS(fp->code) == BPF_LD &&
+ BPF_MODE(fp->code) == BPF_ABS &&
+ convert_bpf_extensions(fp, &insn))
+ break;
+
+ insn->code = fp->code;
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ insn->imm = fp->k;
+ break;
+
+ /* Jump opcodes map as-is, but offsets need adjustment. */
+ case BPF_JMP | BPF_JA:
+ target = i + fp->k + 1;
+ insn->code = fp->code;
+#define EMIT_JMP \
+ do { \
+ if (target >= len || target < 0) \
+ goto err; \
+ insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \
+ /* Adjust pc relative offset for 2nd or 3rd insn. */ \
+ insn->off -= insn - tmp_insns; \
+ } while (0)
+
+ EMIT_JMP;
+ break;
+
+ case BPF_JMP | BPF_JEQ | BPF_K:
+ case BPF_JMP | BPF_JEQ | BPF_X:
+ case BPF_JMP | BPF_JSET | BPF_K:
+ case BPF_JMP | BPF_JSET | BPF_X:
+ case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JGE | BPF_X:
+ if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) {
+ /* BPF immediates are signed, zero extend
+ * immediate into tmp register and use it
+ * in compare insn.
+ */
+ insn->code = BPF_ALU | BPF_MOV | BPF_K;
+ insn->a_reg = TMP_REG;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->a_reg = A_REG;
+ insn->x_reg = TMP_REG;
+ bpf_src = BPF_X;
+ } else {
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ insn->imm = fp->k;
+ bpf_src = BPF_SRC(fp->code);
}
- return 0;
- case BPF_S_LD_B_ABS:
- k = K;
-load_b:
- ptr = load_pointer(skb, k, 1, &tmp);
- if (ptr != NULL) {
- A = *(u8 *)ptr;
- continue;
+
+ /* Common case where 'jump_false' is next insn. */
+ if (fp->jf == 0) {
+ insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+ target = i + fp->jt + 1;
+ EMIT_JMP;
+ break;
}
- return 0;
- case BPF_S_LD_W_LEN:
- A = skb->len;
- continue;
- case BPF_S_LDX_W_LEN:
- X = skb->len;
- continue;
- case BPF_S_LD_W_IND:
- k = X + K;
- goto load_w;
- case BPF_S_LD_H_IND:
- k = X + K;
- goto load_h;
- case BPF_S_LD_B_IND:
- k = X + K;
- goto load_b;
- case BPF_S_LDX_B_MSH:
- ptr = load_pointer(skb, K, 1, &tmp);
- if (ptr != NULL) {
- X = (*(u8 *)ptr & 0xf) << 2;
- continue;
+
+ /* Convert JEQ into JNE when 'jump_true' is next insn. */
+ if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
+ insn->code = BPF_JMP | BPF_JNE | bpf_src;
+ target = i + fp->jf + 1;
+ EMIT_JMP;
+ break;
}
- return 0;
- case BPF_S_LD_IMM:
- A = K;
- continue;
- case BPF_S_LDX_IMM:
- X = K;
- continue;
- case BPF_S_LD_MEM:
- A = mem[K];
- continue;
- case BPF_S_LDX_MEM:
- X = mem[K];
- continue;
- case BPF_S_MISC_TAX:
- X = A;
- continue;
- case BPF_S_MISC_TXA:
- A = X;
- continue;
- case BPF_S_RET_K:
- return K;
- case BPF_S_RET_A:
- return A;
- case BPF_S_ST:
- mem[K] = A;
- continue;
- case BPF_S_STX:
- mem[K] = X;
- continue;
- case BPF_S_ANC_PROTOCOL:
- A = ntohs(skb->protocol);
- continue;
- case BPF_S_ANC_PKTTYPE:
- A = skb->pkt_type;
- continue;
- case BPF_S_ANC_IFINDEX:
- if (!skb->dev)
- return 0;
- A = skb->dev->ifindex;
- continue;
- case BPF_S_ANC_MARK:
- A = skb->mark;
- continue;
- case BPF_S_ANC_QUEUE:
- A = skb->queue_mapping;
- continue;
- case BPF_S_ANC_HATYPE:
- if (!skb->dev)
- return 0;
- A = skb->dev->type;
- continue;
- case BPF_S_ANC_RXHASH:
- A = skb->rxhash;
- continue;
- case BPF_S_ANC_CPU:
- A = raw_smp_processor_id();
- continue;
- case BPF_S_ANC_VLAN_TAG:
- A = vlan_tx_tag_get(skb);
- continue;
- case BPF_S_ANC_VLAN_TAG_PRESENT:
- A = !!vlan_tx_tag_present(skb);
- continue;
- case BPF_S_ANC_PAY_OFFSET:
- A = __skb_get_poff(skb);
- continue;
- case BPF_S_ANC_NLATTR: {
- struct nlattr *nla;
-
- if (skb_is_nonlinear(skb))
- return 0;
- if (A > skb->len - sizeof(struct nlattr))
- return 0;
-
- nla = nla_find((struct nlattr *)&skb->data[A],
- skb->len - A, X);
- if (nla)
- A = (void *)nla - (void *)skb->data;
- else
- A = 0;
- continue;
- }
- case BPF_S_ANC_NLATTR_NEST: {
- struct nlattr *nla;
-
- if (skb_is_nonlinear(skb))
- return 0;
- if (A > skb->len - sizeof(struct nlattr))
- return 0;
-
- nla = (struct nlattr *)&skb->data[A];
- if (nla->nla_len > A - skb->len)
- return 0;
-
- nla = nla_find_nested(nla, X);
- if (nla)
- A = (void *)nla - (void *)skb->data;
- else
- A = 0;
- continue;
- }
-#ifdef CONFIG_SECCOMP_FILTER
- case BPF_S_ANC_SECCOMP_LD_W:
- A = seccomp_bpf_load(fentry->k);
- continue;
-#endif
+
+ /* Other jumps are mapped into two insns: Jxx and JA. */
+ target = i + fp->jt + 1;
+ insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+ EMIT_JMP;
+ insn++;
+
+ insn->code = BPF_JMP | BPF_JA;
+ target = i + fp->jf + 1;
+ EMIT_JMP;
+ break;
+
+ /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
+ case BPF_LDX | BPF_MSH | BPF_B:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = TMP_REG;
+ insn->x_reg = A_REG;
+ insn++;
+
+ insn->code = BPF_LD | BPF_ABS | BPF_B;
+ insn->a_reg = A_REG;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_AND | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 0xf;
+ insn++;
+
+ insn->code = BPF_ALU | BPF_LSH | BPF_K;
+ insn->a_reg = A_REG;
+ insn->imm = 2;
+ insn++;
+
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = X_REG;
+ insn->x_reg = A_REG;
+ insn++;
+
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = A_REG;
+ insn->x_reg = TMP_REG;
+ break;
+
+ /* RET_K, RET_A are remaped into 2 insns. */
+ case BPF_RET | BPF_A:
+ case BPF_RET | BPF_K:
+ insn->code = BPF_ALU | BPF_MOV |
+ (BPF_RVAL(fp->code) == BPF_K ?
+ BPF_K : BPF_X);
+ insn->a_reg = 0;
+ insn->x_reg = A_REG;
+ insn->imm = fp->k;
+ insn++;
+
+ insn->code = BPF_JMP | BPF_EXIT;
+ break;
+
+ /* Store to stack. */
+ case BPF_ST:
+ case BPF_STX:
+ insn->code = BPF_STX | BPF_MEM | BPF_W;
+ insn->a_reg = FP_REG;
+ insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG;
+ insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ break;
+
+ /* Load from stack. */
+ case BPF_LD | BPF_MEM:
+ case BPF_LDX | BPF_MEM:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+ A_REG : X_REG;
+ insn->x_reg = FP_REG;
+ insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+ break;
+
+ /* A = K or X = K */
+ case BPF_LD | BPF_IMM:
+ case BPF_LDX | BPF_IMM:
+ insn->code = BPF_ALU | BPF_MOV | BPF_K;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+ A_REG : X_REG;
+ insn->imm = fp->k;
+ break;
+
+ /* X = A */
+ case BPF_MISC | BPF_TAX:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = X_REG;
+ insn->x_reg = A_REG;
+ break;
+
+ /* A = X */
+ case BPF_MISC | BPF_TXA:
+ insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+ insn->a_reg = A_REG;
+ insn->x_reg = X_REG;
+ break;
+
+ /* A = skb->len or X = skb->len */
+ case BPF_LD | BPF_W | BPF_LEN:
+ case BPF_LDX | BPF_W | BPF_LEN:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+ A_REG : X_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = offsetof(struct sk_buff, len);
+ break;
+
+ /* access seccomp_data fields */
+ case BPF_LDX | BPF_ABS | BPF_W:
+ insn->code = BPF_LDX | BPF_MEM | BPF_W;
+ insn->a_reg = A_REG;
+ insn->x_reg = CTX_REG;
+ insn->off = fp->k;
+ break;
+
default:
- WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n",
- fentry->code, fentry->jt,
- fentry->jf, fentry->k);
- return 0;
+ goto err;
}
+
+ insn++;
+ if (new_prog)
+ memcpy(new_insn, tmp_insns,
+ sizeof(*insn) * (insn - tmp_insns));
+
+ new_insn += insn - tmp_insns;
+ }
+
+ if (!new_prog) {
+ /* Only calculating new length. */
+ *new_len = new_insn - new_prog;
+ return 0;
}
+ pass++;
+ if (new_flen != new_insn - new_prog) {
+ new_flen = new_insn - new_prog;
+ if (pass > 2)
+ goto err;
+
+ goto do_pass;
+ }
+
+ kfree(addrs);
+ BUG_ON(*new_len != new_flen);
return 0;
+err:
+ kfree(addrs);
+ return -EINVAL;
}
-EXPORT_SYMBOL(sk_run_filter);
-/*
- * Security :
+/* Security:
+ *
* A BPF program is able to use 16 cells of memory to store intermediate
- * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter())
+ * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()).
+ *
* As we dont want to clear mem[] array for each packet going through
* sk_run_filter(), we check that filter loaded by user never try to read
* a cell if not previously written, and we check all branches to be sure
@@ -629,30 +1375,197 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
}
EXPORT_SYMBOL(sk_chk_filter);
+static int sk_store_orig_filter(struct sk_filter *fp,
+ const struct sock_fprog *fprog)
+{
+ unsigned int fsize = sk_filter_proglen(fprog);
+ struct sock_fprog_kern *fkprog;
+
+ fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL);
+ if (!fp->orig_prog)
+ return -ENOMEM;
+
+ fkprog = fp->orig_prog;
+ fkprog->len = fprog->len;
+ fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL);
+ if (!fkprog->filter) {
+ kfree(fp->orig_prog);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void sk_release_orig_filter(struct sk_filter *fp)
+{
+ struct sock_fprog_kern *fprog = fp->orig_prog;
+
+ if (fprog) {
+ kfree(fprog->filter);
+ kfree(fprog);
+ }
+}
+
/**
* sk_filter_release_rcu - Release a socket filter by rcu_head
* @rcu: rcu_head that contains the sk_filter to free
*/
-void sk_filter_release_rcu(struct rcu_head *rcu)
+static void sk_filter_release_rcu(struct rcu_head *rcu)
{
struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
+ sk_release_orig_filter(fp);
bpf_jit_free(fp);
}
-EXPORT_SYMBOL(sk_filter_release_rcu);
-static int __sk_prepare_filter(struct sk_filter *fp)
+/**
+ * sk_filter_release - release a socket filter
+ * @fp: filter to remove
+ *
+ * Remove a filter from a socket and release its resources.
+ */
+static void sk_filter_release(struct sk_filter *fp)
+{
+ if (atomic_dec_and_test(&fp->refcnt))
+ call_rcu(&fp->rcu, sk_filter_release_rcu);
+}
+
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
+{
+ atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+ sk_filter_release(fp);
+}
+
+void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+ atomic_inc(&fp->refcnt);
+ atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+}
+
+static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp,
+ struct sock *sk,
+ unsigned int len)
+{
+ struct sk_filter *fp_new;
+
+ if (sk == NULL)
+ return krealloc(fp, len, GFP_KERNEL);
+
+ fp_new = sock_kmalloc(sk, len, GFP_KERNEL);
+ if (fp_new) {
+ memcpy(fp_new, fp, sizeof(struct sk_filter));
+ /* As we're kepping orig_prog in fp_new along,
+ * we need to make sure we're not evicting it
+ * from the old fp.
+ */
+ fp->orig_prog = NULL;
+ sk_filter_uncharge(sk, fp);
+ }
+
+ return fp_new;
+}
+
+static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
+ struct sock *sk)
+{
+ struct sock_filter *old_prog;
+ struct sk_filter *old_fp;
+ int i, err, new_len, old_len = fp->len;
+
+ /* We are free to overwrite insns et al right here as it
+ * won't be used at this point in time anymore internally
+ * after the migration to the internal BPF instruction
+ * representation.
+ */
+ BUILD_BUG_ON(sizeof(struct sock_filter) !=
+ sizeof(struct sock_filter_int));
+
+ /* For now, we need to unfiddle BPF_S_* identifiers in place.
+ * This can sooner or later on be subject to removal, e.g. when
+ * JITs have been converted.
+ */
+ for (i = 0; i < fp->len; i++)
+ sk_decode_filter(&fp->insns[i], &fp->insns[i]);
+
+ /* Conversion cannot happen on overlapping memory areas,
+ * so we need to keep the user BPF around until the 2nd
+ * pass. At this time, the user BPF is stored in fp->insns.
+ */
+ old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
+ GFP_KERNEL);
+ if (!old_prog) {
+ err = -ENOMEM;
+ goto out_err;
+ }
+
+ /* 1st pass: calculate the new program length. */
+ err = sk_convert_filter(old_prog, old_len, NULL, &new_len);
+ if (err)
+ goto out_err_free;
+
+ /* Expand fp for appending the new filter representation. */
+ old_fp = fp;
+ fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len));
+ if (!fp) {
+ /* The old_fp is still around in case we couldn't
+ * allocate new memory, so uncharge on that one.
+ */
+ fp = old_fp;
+ err = -ENOMEM;
+ goto out_err_free;
+ }
+
+ fp->bpf_func = sk_run_filter_int_skb;
+ fp->len = new_len;
+
+ /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */
+ err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len);
+ if (err)
+ /* 2nd sk_convert_filter() can fail only if it fails
+ * to allocate memory, remapping must succeed. Note,
+ * that at this time old_fp has already been released
+ * by __sk_migrate_realloc().
+ */
+ goto out_err_free;
+
+ kfree(old_prog);
+ return fp;
+
+out_err_free:
+ kfree(old_prog);
+out_err:
+ /* Rollback filter setup. */
+ if (sk != NULL)
+ sk_filter_uncharge(sk, fp);
+ else
+ kfree(fp);
+ return ERR_PTR(err);
+}
+
+static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
+ struct sock *sk)
{
int err;
- fp->bpf_func = sk_run_filter;
+ fp->bpf_func = NULL;
+ fp->jited = 0;
err = sk_chk_filter(fp->insns, fp->len);
if (err)
- return err;
+ return ERR_PTR(err);
+ /* Probe if we can JIT compile the filter and if so, do
+ * the compilation of the filter.
+ */
bpf_jit_compile(fp);
- return 0;
+
+ /* JIT compiler couldn't process this filter, so do the
+ * internal BPF translation for the optimized interpreter.
+ */
+ if (!fp->jited)
+ fp = __sk_migrate_filter(fp, sk);
+
+ return fp;
}
/**
@@ -668,9 +1581,8 @@ static int __sk_prepare_filter(struct sk_filter *fp)
int sk_unattached_filter_create(struct sk_filter **pfp,
struct sock_fprog *fprog)
{
+ unsigned int fsize = sk_filter_proglen(fprog);
struct sk_filter *fp;
- unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
- int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
@@ -679,20 +1591,26 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
if (!fp)
return -ENOMEM;
+
memcpy(fp->insns, fprog->filter, fsize);
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
+ /* Since unattached filters are not copied back to user
+ * space through sk_get_filter(), we do not need to hold
+ * a copy here, and can spare us the work.
+ */
+ fp->orig_prog = NULL;
- err = __sk_prepare_filter(fp);
- if (err)
- goto free_mem;
+ /* __sk_prepare_filter() already takes care of uncharging
+ * memory in case something goes wrong.
+ */
+ fp = __sk_prepare_filter(fp, NULL);
+ if (IS_ERR(fp))
+ return PTR_ERR(fp);
*pfp = fp;
return 0;
-free_mem:
- kfree(fp);
- return err;
}
EXPORT_SYMBOL_GPL(sk_unattached_filter_create);
@@ -715,7 +1633,7 @@ EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
{
struct sk_filter *fp, *old_fp;
- unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+ unsigned int fsize = sk_filter_proglen(fprog);
unsigned int sk_fsize = sk_filter_size(fprog->len);
int err;
@@ -729,6 +1647,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
if (!fp)
return -ENOMEM;
+
if (copy_from_user(fp->insns, fprog->filter, fsize)) {
sock_kfree_s(sk, fp, sk_fsize);
return -EFAULT;
@@ -737,18 +1656,26 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
- err = __sk_prepare_filter(fp);
+ err = sk_store_orig_filter(fp, fprog);
if (err) {
sk_filter_uncharge(sk, fp);
- return err;
+ return -ENOMEM;
}
+ /* __sk_prepare_filter() already takes care of uncharging
+ * memory in case something goes wrong.
+ */
+ fp = __sk_prepare_filter(fp, sk);
+ if (IS_ERR(fp))
+ return PTR_ERR(fp);
+
old_fp = rcu_dereference_protected(sk->sk_filter,
sock_owned_by_user(sk));
rcu_assign_pointer(sk->sk_filter, fp);
if (old_fp)
sk_filter_uncharge(sk, old_fp);
+
return 0;
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
@@ -768,6 +1695,7 @@ int sk_detach_filter(struct sock *sk)
sk_filter_uncharge(sk, filter);
ret = 0;
}
+
return ret;
}
EXPORT_SYMBOL_GPL(sk_detach_filter);
@@ -850,34 +1778,41 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
to->k = filt->k;
}
-int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
+int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
+ unsigned int len)
{
+ struct sock_fprog_kern *fprog;
struct sk_filter *filter;
- int i, ret;
+ int ret = 0;
lock_sock(sk);
filter = rcu_dereference_protected(sk->sk_filter,
- sock_owned_by_user(sk));
- ret = 0;
+ sock_owned_by_user(sk));
if (!filter)
goto out;
- ret = filter->len;
+
+ /* We're copying the filter that has been originally attached,
+ * so no conversion/decode needed anymore.
+ */
+ fprog = filter->orig_prog;
+
+ ret = fprog->len;
if (!len)
+ /* User space only enquires number of filter blocks. */
goto out;
+
ret = -EINVAL;
- if (len < filter->len)
+ if (len < fprog->len)
goto out;
ret = -EFAULT;
- for (i = 0; i < filter->len; i++) {
- struct sock_filter fb;
-
- sk_decode_filter(&filter->insns[i], &fb);
- if (copy_to_user(&ubuf[i], &fb, sizeof(fb)))
- goto out;
- }
+ if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog)))
+ goto out;
- ret = filter->len;
+ /* Instead of bytes, the API requests to return the number
+ * of filter blocks.
+ */
+ ret = fprog->len;
out:
release_sock(sk);
return ret;
diff --git a/net/core/flow.c b/net/core/flow.c
index dfa602ceb8cd..31cfb365e0c6 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -24,6 +24,7 @@
#include <net/flow.h>
#include <linux/atomic.h>
#include <linux/security.h>
+#include <net/net_namespace.h>
struct flow_cache_entry {
union {
@@ -38,37 +39,14 @@ struct flow_cache_entry {
struct flow_cache_object *object;
};
-struct flow_cache_percpu {
- struct hlist_head *hash_table;
- int hash_count;
- u32 hash_rnd;
- int hash_rnd_recalc;
- struct tasklet_struct flush_tasklet;
-};
-
struct flow_flush_info {
struct flow_cache *cache;
atomic_t cpuleft;
struct completion completion;
};
-struct flow_cache {
- u32 hash_shift;
- struct flow_cache_percpu __percpu *percpu;
- struct notifier_block hotcpu_notifier;
- int low_watermark;
- int high_watermark;
- struct timer_list rnd_timer;
-};
-
-atomic_t flow_cache_genid = ATOMIC_INIT(0);
-EXPORT_SYMBOL(flow_cache_genid);
-static struct flow_cache flow_cache_global;
static struct kmem_cache *flow_cachep __read_mostly;
-static DEFINE_SPINLOCK(flow_cache_gc_lock);
-static LIST_HEAD(flow_cache_gc_list);
-
#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift)
#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ)
@@ -84,16 +62,18 @@ static void flow_cache_new_hashrnd(unsigned long arg)
add_timer(&fc->rnd_timer);
}
-static int flow_entry_valid(struct flow_cache_entry *fle)
+static int flow_entry_valid(struct flow_cache_entry *fle,
+ struct netns_xfrm *xfrm)
{
- if (atomic_read(&flow_cache_genid) != fle->genid)
+ if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
return 0;
if (fle->object && !fle->object->ops->check(fle->object))
return 0;
return 1;
}
-static void flow_entry_kill(struct flow_cache_entry *fle)
+static void flow_entry_kill(struct flow_cache_entry *fle,
+ struct netns_xfrm *xfrm)
{
if (fle->object)
fle->object->ops->delete(fle->object);
@@ -104,26 +84,28 @@ static void flow_cache_gc_task(struct work_struct *work)
{
struct list_head gc_list;
struct flow_cache_entry *fce, *n;
+ struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+ flow_cache_gc_work);
INIT_LIST_HEAD(&gc_list);
- spin_lock_bh(&flow_cache_gc_lock);
- list_splice_tail_init(&flow_cache_gc_list, &gc_list);
- spin_unlock_bh(&flow_cache_gc_lock);
+ spin_lock_bh(&xfrm->flow_cache_gc_lock);
+ list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
+ spin_unlock_bh(&xfrm->flow_cache_gc_lock);
list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
- flow_entry_kill(fce);
+ flow_entry_kill(fce, xfrm);
}
-static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task);
static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
- int deleted, struct list_head *gc_list)
+ int deleted, struct list_head *gc_list,
+ struct netns_xfrm *xfrm)
{
if (deleted) {
fcp->hash_count -= deleted;
- spin_lock_bh(&flow_cache_gc_lock);
- list_splice_tail(gc_list, &flow_cache_gc_list);
- spin_unlock_bh(&flow_cache_gc_lock);
- schedule_work(&flow_cache_gc_work);
+ spin_lock_bh(&xfrm->flow_cache_gc_lock);
+ list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
+ spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+ schedule_work(&xfrm->flow_cache_gc_work);
}
}
@@ -135,6 +117,8 @@ static void __flow_cache_shrink(struct flow_cache *fc,
struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
+ struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+ flow_cache_global);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
int saved = 0;
@@ -142,7 +126,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
if (saved < shrink_to &&
- flow_entry_valid(fle)) {
+ flow_entry_valid(fle, xfrm)) {
saved++;
} else {
deleted++;
@@ -152,7 +136,7 @@ static void __flow_cache_shrink(struct flow_cache *fc,
}
}
- flow_cache_queue_garbage(fcp, deleted, &gc_list);
+ flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
}
static void flow_cache_shrink(struct flow_cache *fc,
@@ -208,7 +192,7 @@ struct flow_cache_object *
flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
flow_resolve_t resolver, void *ctx)
{
- struct flow_cache *fc = &flow_cache_global;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
struct flow_cache_percpu *fcp;
struct flow_cache_entry *fle, *tfle;
struct flow_cache_object *flo;
@@ -258,7 +242,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
fcp->hash_count++;
}
- } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) {
+ } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
flo = fle->object;
if (!flo)
goto ret_object;
@@ -279,7 +263,7 @@ nocache:
}
flo = resolver(net, key, family, dir, flo, ctx);
if (fle) {
- fle->genid = atomic_read(&flow_cache_genid);
+ fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
if (!IS_ERR(flo))
fle->object = flo;
else
@@ -303,12 +287,14 @@ static void flow_cache_flush_tasklet(unsigned long data)
struct hlist_node *tmp;
LIST_HEAD(gc_list);
int i, deleted = 0;
+ struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+ flow_cache_global);
fcp = this_cpu_ptr(fc->percpu);
for (i = 0; i < flow_cache_hash_size(fc); i++) {
hlist_for_each_entry_safe(fle, tmp,
&fcp->hash_table[i], u.hlist) {
- if (flow_entry_valid(fle))
+ if (flow_entry_valid(fle, xfrm))
continue;
deleted++;
@@ -317,7 +303,7 @@ static void flow_cache_flush_tasklet(unsigned long data)
}
}
- flow_cache_queue_garbage(fcp, deleted, &gc_list);
+ flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
if (atomic_dec_and_test(&info->cpuleft))
complete(&info->completion);
@@ -351,10 +337,9 @@ static void flow_cache_flush_per_cpu(void *data)
tasklet_schedule(tasklet);
}
-void flow_cache_flush(void)
+void flow_cache_flush(struct net *net)
{
struct flow_flush_info info;
- static DEFINE_MUTEX(flow_flush_sem);
cpumask_var_t mask;
int i, self;
@@ -365,8 +350,8 @@ void flow_cache_flush(void)
/* Don't want cpus going down or up during this. */
get_online_cpus();
- mutex_lock(&flow_flush_sem);
- info.cache = &flow_cache_global;
+ mutex_lock(&net->xfrm.flow_flush_sem);
+ info.cache = &net->xfrm.flow_cache_global;
for_each_online_cpu(i)
if (!flow_cache_percpu_empty(info.cache, i))
cpumask_set_cpu(i, mask);
@@ -386,21 +371,23 @@ void flow_cache_flush(void)
wait_for_completion(&info.completion);
done:
- mutex_unlock(&flow_flush_sem);
+ mutex_unlock(&net->xfrm.flow_flush_sem);
put_online_cpus();
free_cpumask_var(mask);
}
static void flow_cache_flush_task(struct work_struct *work)
{
- flow_cache_flush();
-}
+ struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+ flow_cache_gc_work);
+ struct net *net = container_of(xfrm, struct net, xfrm);
-static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task);
+ flow_cache_flush(net);
+}
-void flow_cache_flush_deferred(void)
+void flow_cache_flush_deferred(struct net *net)
{
- schedule_work(&flow_cache_flush_work);
+ schedule_work(&net->xfrm.flow_cache_flush_work);
}
static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
@@ -425,7 +412,8 @@ static int flow_cache_cpu(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
- struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier);
+ struct flow_cache *fc = container_of(nfb, struct flow_cache,
+ hotcpu_notifier);
int res, cpu = (unsigned long) hcpu;
struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
@@ -444,9 +432,20 @@ static int flow_cache_cpu(struct notifier_block *nfb,
return NOTIFY_OK;
}
-static int __init flow_cache_init(struct flow_cache *fc)
+int flow_cache_init(struct net *net)
{
int i;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+ if (!flow_cachep)
+ flow_cachep = kmem_cache_create("flow_cache",
+ sizeof(struct flow_cache_entry),
+ 0, SLAB_PANIC, NULL);
+ spin_lock_init(&net->xfrm.flow_cache_gc_lock);
+ INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
+ INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
+ INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
+ mutex_init(&net->xfrm.flow_flush_sem);
fc->hash_shift = 10;
fc->low_watermark = 2 * flow_cache_hash_size(fc);
@@ -484,14 +483,23 @@ err:
return -ENOMEM;
}
+EXPORT_SYMBOL(flow_cache_init);
-static int __init flow_cache_init_global(void)
+void flow_cache_fini(struct net *net)
{
- flow_cachep = kmem_cache_create("flow_cache",
- sizeof(struct flow_cache_entry),
- 0, SLAB_PANIC, NULL);
+ int i;
+ struct flow_cache *fc = &net->xfrm.flow_cache_global;
- return flow_cache_init(&flow_cache_global);
-}
+ del_timer_sync(&fc->rnd_timer);
+ unregister_hotcpu_notifier(&fc->hotcpu_notifier);
-module_init(flow_cache_init_global);
+ for_each_possible_cpu(i) {
+ struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
+ kfree(fcp->hash_table);
+ fcp->hash_table = NULL;
+ }
+
+ free_percpu(fc->percpu);
+ fc->percpu = NULL;
+}
+EXPORT_SYMBOL(flow_cache_fini);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index e29e810663d7..107ed12a5323 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -61,7 +61,7 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
again:
switch (proto) {
- case __constant_htons(ETH_P_IP): {
+ case htons(ETH_P_IP): {
const struct iphdr *iph;
struct iphdr _iph;
ip:
@@ -77,7 +77,7 @@ ip:
iph_to_flow_copy_addrs(flow, iph);
break;
}
- case __constant_htons(ETH_P_IPV6): {
+ case htons(ETH_P_IPV6): {
const struct ipv6hdr *iph;
struct ipv6hdr _iph;
ipv6:
@@ -91,8 +91,8 @@ ipv6:
nhoff += sizeof(struct ipv6hdr);
break;
}
- case __constant_htons(ETH_P_8021AD):
- case __constant_htons(ETH_P_8021Q): {
+ case htons(ETH_P_8021AD):
+ case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
@@ -104,7 +104,7 @@ ipv6:
nhoff += sizeof(*vlan);
goto again;
}
- case __constant_htons(ETH_P_PPP_SES): {
+ case htons(ETH_P_PPP_SES): {
struct {
struct pppoe_hdr hdr;
__be16 proto;
@@ -115,9 +115,9 @@ ipv6:
proto = hdr->proto;
nhoff += PPPOE_SES_HLEN;
switch (proto) {
- case __constant_htons(PPP_IP):
+ case htons(PPP_IP):
goto ip;
- case __constant_htons(PPP_IPV6):
+ case htons(PPP_IPV6):
goto ipv6;
default:
return false;
@@ -203,8 +203,8 @@ static __always_inline u32 __flow_hash_1word(u32 a)
/*
* __skb_get_hash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
+ * and src/dst port numbers. Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash. Also, sets l4_hash in skb
* if hash is a canonical 4-tuple hash over transport ports.
*/
void __skb_get_hash(struct sk_buff *skb)
@@ -216,7 +216,7 @@ void __skb_get_hash(struct sk_buff *skb)
return;
if (keys.ports)
- skb->l4_rxhash = 1;
+ skb->l4_hash = 1;
/* get a consistent hash (same value on both flow directions) */
if (((__force u32)keys.dst < (__force u32)keys.src) ||
@@ -232,7 +232,7 @@ void __skb_get_hash(struct sk_buff *skb)
if (!hash)
hash = 1;
- skb->rxhash = hash;
+ skb->hash = hash;
}
EXPORT_SYMBOL(__skb_get_hash);
@@ -344,7 +344,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol ^
- skb->rxhash;
+ skb->hash;
hash = __flow_hash_1word(hash);
queue_index = map->queues[
((u64)hash * map->len) >> 32];
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index e16129019c66..8f8a96ef9f3f 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -836,10 +836,10 @@ out:
static __inline__ int neigh_max_probes(struct neighbour *n)
{
struct neigh_parms *p = n->parms;
- return (n->nud_state & NUD_PROBE) ?
- NEIGH_VAR(p, UCAST_PROBES) :
- NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
- NEIGH_VAR(p, MCAST_PROBES);
+ int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES);
+ if (!(n->nud_state & NUD_PROBE))
+ max_probes += NEIGH_VAR(p, MCAST_PROBES);
+ return max_probes;
}
static void neigh_invalidate(struct neighbour *neigh)
@@ -945,6 +945,7 @@ static void neigh_timer_handler(unsigned long arg)
neigh->nud_state = NUD_FAILED;
notify = 1;
neigh_invalidate(neigh);
+ goto out;
}
if (neigh->nud_state & NUD_IN_TIMER) {
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 549043c078c9..1cac29ebb05b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -104,6 +104,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
}
NETDEVICE_SHOW_RO(dev_id, fmt_hex);
+NETDEVICE_SHOW_RO(dev_port, fmt_dec);
NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
NETDEVICE_SHOW_RO(addr_len, fmt_dec);
NETDEVICE_SHOW_RO(iflink, fmt_dec);
@@ -252,6 +253,16 @@ static ssize_t operstate_show(struct device *dev,
}
static DEVICE_ATTR_RO(operstate);
+static ssize_t carrier_changes_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ return sprintf(buf, fmt_dec,
+ atomic_read(&netdev->carrier_changes));
+}
+static DEVICE_ATTR_RO(carrier_changes);
+
/* read-write attributes */
static int change_mtu(struct net_device *net, unsigned long new_mtu)
@@ -373,6 +384,7 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_netdev_group.attr,
&dev_attr_type.attr,
&dev_attr_dev_id.attr,
+ &dev_attr_dev_port.attr,
&dev_attr_iflink.attr,
&dev_attr_ifindex.attr,
&dev_attr_addr_assign_type.attr,
@@ -384,6 +396,7 @@ static struct attribute *net_class_attrs[] = {
&dev_attr_duplex.attr,
&dev_attr_dormant.attr,
&dev_attr_operstate.attr,
+ &dev_attr_carrier_changes.attr,
&dev_attr_ifalias.attr,
&dev_attr_carrier.attr,
&dev_attr_mtu.attr,
@@ -996,15 +1009,12 @@ static struct attribute_group dql_group = {
#endif /* CONFIG_BQL */
#ifdef CONFIG_XPS
-static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
+static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
{
struct net_device *dev = queue->dev;
- int i;
-
- for (i = 0; i < dev->num_tx_queues; i++)
- if (queue == &dev->_tx[i])
- break;
+ unsigned int i;
+ i = queue - dev->_tx;
BUG_ON(i >= dev->num_tx_queues);
return i;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index df9e6b1a9759..e33937fb32a0 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -46,13 +46,9 @@
static struct sk_buff_head skb_pool;
-static atomic_t trapped;
-
DEFINE_STATIC_SRCU(netpoll_srcu);
#define USEC_PER_POLL 50
-#define NETPOLL_RX_ENABLED 1
-#define NETPOLL_RX_DROP 2
#define MAX_SKB_SIZE \
(sizeof(struct ethhdr) + \
@@ -61,7 +57,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu);
MAX_UDP_CHUNK)
static void zap_completion_queue(void);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
static void netpoll_async_cleanup(struct work_struct *work);
static unsigned int carrier_timeout = 4;
@@ -74,6 +69,37 @@ module_param(carrier_timeout, uint, 0644);
#define np_notice(np, fmt, ...) \
pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
+static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
+ struct netdev_queue *txq)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ int status = NETDEV_TX_OK;
+ netdev_features_t features;
+
+ features = netif_skb_features(skb);
+
+ if (vlan_tx_tag_present(skb) &&
+ !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
+ if (unlikely(!skb)) {
+ /* This is actually a packet drop, but we
+ * don't want the code that calls this
+ * function to try and operate on a NULL skb.
+ */
+ goto out;
+ }
+ skb->vlan_tci = 0;
+ }
+
+ status = ops->ndo_start_xmit(skb, dev);
+ if (status == NETDEV_TX_OK)
+ txq_trans_update(txq);
+
+out:
+ return status;
+}
+
static void queue_process(struct work_struct *work)
{
struct netpoll_info *npinfo =
@@ -83,51 +109,31 @@ static void queue_process(struct work_struct *work)
while ((skb = skb_dequeue(&npinfo->txq))) {
struct net_device *dev = skb->dev;
- const struct net_device_ops *ops = dev->netdev_ops;
struct netdev_queue *txq;
if (!netif_device_present(dev) || !netif_running(dev)) {
- __kfree_skb(skb);
+ kfree_skb(skb);
continue;
}
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
local_irq_save(flags);
- __netif_tx_lock(txq, smp_processor_id());
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
- ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
+ netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
skb_queue_head(&npinfo->txq, skb);
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
schedule_delayed_work(&npinfo->tx_work, HZ/10);
return;
}
- __netif_tx_unlock(txq);
+ HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
}
}
-static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
- unsigned short ulen, __be32 saddr, __be32 daddr)
-{
- __wsum psum;
-
- if (uh->check == 0 || skb_csum_unnecessary(skb))
- return 0;
-
- psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
-
- if (skb->ip_summed == CHECKSUM_COMPLETE &&
- !csum_fold(csum_add(psum, skb->csum)))
- return 0;
-
- skb->csum = psum;
-
- return __skb_checksum_complete(skb);
-}
-
/*
* Check whether delayed processing was scheduled for our NIC. If so,
* we attempt to grab the poll lock and use ->poll() to pump the card.
@@ -138,14 +144,8 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
* trylock here and interrupts are already disabled in the softirq
* case. Further, we test the poll_owner to avoid recursion on UP
* systems where the lock doesn't exist.
- *
- * In cases where there is bi-directional communications, reading only
- * one message at a time can lead to packets being dropped by the
- * network adapter, forcing superfluous retries and possibly timeouts.
- * Thus, we set our budget to greater than 1.
*/
-static int poll_one_napi(struct netpoll_info *npinfo,
- struct napi_struct *napi, int budget)
+static int poll_one_napi(struct napi_struct *napi, int budget)
{
int work;
@@ -156,52 +156,35 @@ static int poll_one_napi(struct netpoll_info *npinfo,
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
return budget;
- npinfo->rx_flags |= NETPOLL_RX_DROP;
- atomic_inc(&trapped);
set_bit(NAPI_STATE_NPSVC, &napi->state);
work = napi->poll(napi, budget);
+ WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
trace_napi_poll(napi);
clear_bit(NAPI_STATE_NPSVC, &napi->state);
- atomic_dec(&trapped);
- npinfo->rx_flags &= ~NETPOLL_RX_DROP;
return budget - work;
}
-static void poll_napi(struct net_device *dev)
+static void poll_napi(struct net_device *dev, int budget)
{
struct napi_struct *napi;
- int budget = 16;
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
- napi, budget);
+ budget = poll_one_napi(napi, budget);
spin_unlock(&napi->poll_lock);
-
- if (!budget)
- break;
}
}
}
-static void service_neigh_queue(struct netpoll_info *npi)
-{
- if (npi) {
- struct sk_buff *skb;
-
- while ((skb = skb_dequeue(&npi->neigh_tx)))
- netpoll_neigh_reply(skb, npi);
- }
-}
-
static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+ int budget = 0;
/* Don't do any rx activity if the dev_lock mutex is held
* the dev_open/close paths use this to block netpoll activity
@@ -224,31 +207,14 @@ static void netpoll_poll_dev(struct net_device *dev)
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
- poll_napi(dev);
+ poll_napi(dev, budget);
up(&ni->dev_lock);
- if (dev->flags & IFF_SLAVE) {
- if (ni) {
- struct net_device *bond_dev;
- struct sk_buff *skb;
- struct netpoll_info *bond_ni;
-
- bond_dev = netdev_master_upper_dev_get_rcu(dev);
- bond_ni = rcu_dereference_bh(bond_dev->npinfo);
- while ((skb = skb_dequeue(&ni->neigh_tx))) {
- skb->dev = bond_dev;
- skb_queue_tail(&bond_ni->neigh_tx, skb);
- }
- }
- }
-
- service_neigh_queue(ni);
-
zap_completion_queue();
}
-void netpoll_rx_disable(struct net_device *dev)
+void netpoll_poll_disable(struct net_device *dev)
{
struct netpoll_info *ni;
int idx;
@@ -259,9 +225,9 @@ void netpoll_rx_disable(struct net_device *dev)
down(&ni->dev_lock);
srcu_read_unlock(&netpoll_srcu, idx);
}
-EXPORT_SYMBOL(netpoll_rx_disable);
+EXPORT_SYMBOL(netpoll_poll_disable);
-void netpoll_rx_enable(struct net_device *dev)
+void netpoll_poll_enable(struct net_device *dev)
{
struct netpoll_info *ni;
rcu_read_lock();
@@ -270,7 +236,7 @@ void netpoll_rx_enable(struct net_device *dev)
up(&ni->dev_lock);
rcu_read_unlock();
}
-EXPORT_SYMBOL(netpoll_rx_enable);
+EXPORT_SYMBOL(netpoll_poll_enable);
static void refill_skbs(void)
{
@@ -304,7 +270,7 @@ static void zap_completion_queue(void)
while (clist != NULL) {
struct sk_buff *skb = clist;
clist = clist->next;
- if (skb->destructor) {
+ if (!skb_irq_freeable(skb)) {
atomic_inc(&skb->users);
dev_kfree_skb_any(skb); /* put this one back */
} else {
@@ -359,7 +325,6 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
{
int status = NETDEV_TX_BUSY;
unsigned long tries;
- const struct net_device_ops *ops = dev->netdev_ops;
/* It is up to the caller to keep npinfo alive. */
struct netpoll_info *npinfo;
@@ -367,7 +332,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
npinfo = rcu_dereference_bh(np->dev->npinfo);
if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
- __kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
return;
}
@@ -380,29 +345,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
/* try until next clock tick */
for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
tries > 0; --tries) {
- if (__netif_tx_trylock(txq)) {
- if (!netif_xmit_stopped(txq)) {
- if (vlan_tx_tag_present(skb) &&
- !vlan_hw_offload_capable(netif_skb_features(skb),
- skb->vlan_proto)) {
- skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
- if (unlikely(!skb)) {
- /* This is actually a packet drop, but we
- * don't want the code at the end of this
- * function to try and re-queue a NULL skb.
- */
- status = NETDEV_TX_OK;
- goto unlock_txq;
- }
- skb->vlan_tci = 0;
- }
-
- status = ops->ndo_start_xmit(skb, dev);
- if (status == NETDEV_TX_OK)
- txq_trans_update(txq);
- }
- unlock_txq:
- __netif_tx_unlock(txq);
+ if (HARD_TX_TRYLOCK(dev, txq)) {
+ if (!netif_xmit_stopped(txq))
+ status = netpoll_start_xmit(skb, dev, txq);
+
+ HARD_TX_UNLOCK(dev, txq);
if (status == NETDEV_TX_OK)
break;
@@ -417,7 +364,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
WARN_ONCE(!irqs_disabled(),
"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
- dev->name, ops->ndo_start_xmit);
+ dev->name, dev->netdev_ops->ndo_start_xmit);
}
@@ -529,384 +476,6 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
}
EXPORT_SYMBOL(netpoll_send_udp);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
- int size, type = ARPOP_REPLY;
- __be32 sip, tip;
- unsigned char *sha;
- struct sk_buff *send_skb;
- struct netpoll *np, *tmp;
- unsigned long flags;
- int hlen, tlen;
- int hits = 0, proto;
-
- if (list_empty(&npinfo->rx_np))
- return;
-
- /* Before checking the packet, we do some early
- inspection whether this is interesting at all */
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->dev == skb->dev)
- hits++;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-
- /* No netpoll struct is using this dev */
- if (!hits)
- return;
-
- proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto == ETH_P_ARP) {
- struct arphdr *arp;
- unsigned char *arp_ptr;
- /* No arp on this interface */
- if (skb->dev->flags & IFF_NOARP)
- return;
-
- if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
- return;
-
- skb_reset_network_header(skb);
- skb_reset_transport_header(skb);
- arp = arp_hdr(skb);
-
- if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
- arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
- arp->ar_pro != htons(ETH_P_IP) ||
- arp->ar_op != htons(ARPOP_REQUEST))
- return;
-
- arp_ptr = (unsigned char *)(arp+1);
- /* save the location of the src hw addr */
- sha = arp_ptr;
- arp_ptr += skb->dev->addr_len;
- memcpy(&sip, arp_ptr, 4);
- arp_ptr += 4;
- /* If we actually cared about dst hw addr,
- it would get copied here */
- arp_ptr += skb->dev->addr_len;
- memcpy(&tip, arp_ptr, 4);
-
- /* Should we ignore arp? */
- if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
- return;
-
- size = arp_hdr_len(skb->dev);
-
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (tip != np->local_ip.ip)
- continue;
-
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
-
- skb_reset_network_header(send_skb);
- arp = (struct arphdr *) skb_put(send_skb, size);
- send_skb->dev = skb->dev;
- send_skb->protocol = htons(ETH_P_ARP);
-
- /* Fill the device header for the ARP frame */
- if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
- sha, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
- }
-
- /*
- * Fill out the arp protocol part.
- *
- * we only support ethernet device type,
- * which (according to RFC 1390) should
- * always equal 1 (Ethernet).
- */
-
- arp->ar_hrd = htons(np->dev->type);
- arp->ar_pro = htons(ETH_P_IP);
- arp->ar_hln = np->dev->addr_len;
- arp->ar_pln = 4;
- arp->ar_op = htons(type);
-
- arp_ptr = (unsigned char *)(arp + 1);
- memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &tip, 4);
- arp_ptr += 4;
- memcpy(arp_ptr, sha, np->dev->addr_len);
- arp_ptr += np->dev->addr_len;
- memcpy(arp_ptr, &sip, 4);
-
- netpoll_send_skb(np, send_skb);
-
- /* If there are several rx_skb_hooks for the same
- * address we're fine by sending a single reply
- */
- break;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- } else if( proto == ETH_P_IPV6) {
-#if IS_ENABLED(CONFIG_IPV6)
- struct nd_msg *msg;
- u8 *lladdr = NULL;
- struct ipv6hdr *hdr;
- struct icmp6hdr *icmp6h;
- const struct in6_addr *saddr;
- const struct in6_addr *daddr;
- struct inet6_dev *in6_dev = NULL;
- struct in6_addr *target;
-
- in6_dev = in6_dev_get(skb->dev);
- if (!in6_dev || !in6_dev->cnf.accept_ra)
- return;
-
- if (!pskb_may_pull(skb, skb->len))
- return;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
-
- __skb_push(skb, skb->data - skb_transport_header(skb));
-
- if (ipv6_hdr(skb)->hop_limit != 255)
- return;
- if (msg->icmph.icmp6_code != 0)
- return;
- if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
- return;
-
- saddr = &ipv6_hdr(skb)->saddr;
- daddr = &ipv6_hdr(skb)->daddr;
-
- size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
-
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
- continue;
-
- hlen = LL_RESERVED_SPACE(np->dev);
- tlen = np->dev->needed_tailroom;
- send_skb = find_skb(np, size + hlen + tlen, hlen);
- if (!send_skb)
- continue;
-
- send_skb->protocol = htons(ETH_P_IPV6);
- send_skb->dev = skb->dev;
-
- skb_reset_network_header(send_skb);
- hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
- *(__be32*)hdr = htonl(0x60000000);
- hdr->payload_len = htons(size);
- hdr->nexthdr = IPPROTO_ICMPV6;
- hdr->hop_limit = 255;
- hdr->saddr = *saddr;
- hdr->daddr = *daddr;
-
- icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
- icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
- icmp6h->icmp6_router = 0;
- icmp6h->icmp6_solicited = 1;
-
- target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
- *target = msg->target;
- icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
- IPPROTO_ICMPV6,
- csum_partial(icmp6h,
- size, 0));
-
- if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
- lladdr, np->dev->dev_addr,
- send_skb->len) < 0) {
- kfree_skb(send_skb);
- continue;
- }
-
- netpoll_send_skb(np, send_skb);
-
- /* If there are several rx_skb_hooks for the same
- * address, we're fine by sending a single reply
- */
- break;
- }
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-#endif
- }
-}
-
-static bool pkt_is_ns(struct sk_buff *skb)
-{
- struct nd_msg *msg;
- struct ipv6hdr *hdr;
-
- if (skb->protocol != htons(ETH_P_IPV6))
- return false;
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
- return false;
-
- msg = (struct nd_msg *)skb_transport_header(skb);
- __skb_push(skb, skb->data - skb_transport_header(skb));
- hdr = ipv6_hdr(skb);
-
- if (hdr->nexthdr != IPPROTO_ICMPV6)
- return false;
- if (hdr->hop_limit != 255)
- return false;
- if (msg->icmph.icmp6_code != 0)
- return false;
- if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
- return false;
-
- return true;
-}
-
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
- int proto, len, ulen, data_len;
- int hits = 0, offset;
- const struct iphdr *iph;
- struct udphdr *uh;
- struct netpoll *np, *tmp;
- uint16_t source;
-
- if (list_empty(&npinfo->rx_np))
- goto out;
-
- if (skb->dev->type != ARPHRD_ETHER)
- goto out;
-
- /* check if netpoll clients need ARP */
- if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->neigh_tx, skb);
- return 1;
- } else if (pkt_is_ns(skb) && atomic_read(&trapped)) {
- skb_queue_tail(&npinfo->neigh_tx, skb);
- return 1;
- }
-
- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
- skb = vlan_untag(skb);
- if (unlikely(!skb))
- goto out;
- }
-
- proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto != ETH_P_IP && proto != ETH_P_IPV6)
- goto out;
- if (skb->pkt_type == PACKET_OTHERHOST)
- goto out;
- if (skb_shared(skb))
- goto out;
-
- if (proto == ETH_P_IP) {
- if (!pskb_may_pull(skb, sizeof(struct iphdr)))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (iph->ihl < 5 || iph->version != 4)
- goto out;
- if (!pskb_may_pull(skb, iph->ihl*4))
- goto out;
- iph = (struct iphdr *)skb->data;
- if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
- goto out;
-
- len = ntohs(iph->tot_len);
- if (skb->len < len || len < iph->ihl*4)
- goto out;
-
- /*
- * Our transport medium may have padded the buffer out.
- * Now We trim to the true length of the frame.
- */
- if (pskb_trim_rcsum(skb, len))
- goto out;
-
- iph = (struct iphdr *)skb->data;
- if (iph->protocol != IPPROTO_UDP)
- goto out;
-
- len -= iph->ihl*4;
- uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
- offset = (unsigned char *)(uh + 1) - skb->data;
- ulen = ntohs(uh->len);
- data_len = skb->len - offset;
- source = ntohs(uh->source);
-
- if (ulen != len)
- goto out;
- if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
- goto out;
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
- continue;
- if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
-
- np->rx_skb_hook(np, source, skb, offset, data_len);
- hits++;
- }
- } else {
-#if IS_ENABLED(CONFIG_IPV6)
- const struct ipv6hdr *ip6h;
-
- if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
- goto out;
- ip6h = (struct ipv6hdr *)skb->data;
- if (ip6h->version != 6)
- goto out;
- len = ntohs(ip6h->payload_len);
- if (!len)
- goto out;
- if (len + sizeof(struct ipv6hdr) > skb->len)
- goto out;
- if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
- goto out;
- ip6h = ipv6_hdr(skb);
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto out;
- uh = udp_hdr(skb);
- offset = (unsigned char *)(uh + 1) - skb->data;
- ulen = ntohs(uh->len);
- data_len = skb->len - offset;
- source = ntohs(uh->source);
- if (ulen != skb->len)
- goto out;
- if (udp6_csum_init(skb, uh, IPPROTO_UDP))
- goto out;
- list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
- if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
- continue;
- if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
- continue;
- if (np->local_port && np->local_port != ntohs(uh->dest))
- continue;
-
- np->rx_skb_hook(np, source, skb, offset, data_len);
- hits++;
- }
-#endif
- }
-
- if (!hits)
- goto out;
-
- kfree_skb(skb);
- return 1;
-
-out:
- if (atomic_read(&trapped)) {
- kfree_skb(skb);
- return 1;
- }
-
- return 0;
-}
-
void netpoll_print_options(struct netpoll *np)
{
np_info(np, "local port %d\n", np->local_port);
@@ -1026,11 +595,10 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
}
EXPORT_SYMBOL(netpoll_parse_options);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
{
struct netpoll_info *npinfo;
const struct net_device_ops *ops;
- unsigned long flags;
int err;
np->dev = ndev;
@@ -1046,18 +614,13 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
}
if (!ndev->npinfo) {
- npinfo = kmalloc(sizeof(*npinfo), gfp);
+ npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
if (!npinfo) {
err = -ENOMEM;
goto out;
}
- npinfo->rx_flags = 0;
- INIT_LIST_HEAD(&npinfo->rx_np);
-
- spin_lock_init(&npinfo->rx_lock);
sema_init(&npinfo->dev_lock, 1);
- skb_queue_head_init(&npinfo->neigh_tx);
skb_queue_head_init(&npinfo->txq);
INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
@@ -1065,7 +628,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
ops = np->dev->netdev_ops;
if (ops->ndo_netpoll_setup) {
- err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
+ err = ops->ndo_netpoll_setup(ndev, npinfo);
if (err)
goto free_npinfo;
}
@@ -1076,13 +639,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
npinfo->netpoll = np;
- if (np->rx_skb_hook) {
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- npinfo->rx_flags |= NETPOLL_RX_ENABLED;
- list_add_tail(&np->rx, &npinfo->rx_np);
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- }
-
/* last thing to do is link it to the net device structure */
rcu_assign_pointer(ndev->npinfo, npinfo);
@@ -1204,7 +760,7 @@ int netpoll_setup(struct netpoll *np)
/* fill up the skb queue */
refill_skbs();
- err = __netpoll_setup(np, ndev, GFP_KERNEL);
+ err = __netpoll_setup(np, ndev);
if (err)
goto put;
@@ -1231,7 +787,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
struct netpoll_info *npinfo =
container_of(rcu_head, struct netpoll_info, rcu);
- skb_queue_purge(&npinfo->neigh_tx);
skb_queue_purge(&npinfo->txq);
/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -1247,7 +802,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
void __netpoll_cleanup(struct netpoll *np)
{
struct netpoll_info *npinfo;
- unsigned long flags;
/* rtnl_dereference would be preferable here but
* rcu_cleanup_netpoll path can put us in here safely without
@@ -1257,14 +811,6 @@ void __netpoll_cleanup(struct netpoll *np)
if (!npinfo)
return;
- if (!list_empty(&npinfo->rx_np)) {
- spin_lock_irqsave(&npinfo->rx_lock, flags);
- list_del(&np->rx);
- if (list_empty(&npinfo->rx_np))
- npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
- spin_unlock_irqrestore(&npinfo->rx_lock, flags);
- }
-
synchronize_srcu(&netpoll_srcu);
if (atomic_dec_and_test(&npinfo->refcnt)) {
@@ -1274,7 +820,7 @@ void __netpoll_cleanup(struct netpoll *np)
if (ops->ndo_netpoll_cleanup)
ops->ndo_netpoll_cleanup(np->dev);
- rcu_assign_pointer(np->dev->npinfo, NULL);
+ RCU_INIT_POINTER(np->dev->npinfo, NULL);
call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
}
}
@@ -1308,18 +854,3 @@ out:
rtnl_unlock();
}
EXPORT_SYMBOL(netpoll_cleanup);
-
-int netpoll_trap(void)
-{
- return atomic_read(&trapped);
-}
-EXPORT_SYMBOL(netpoll_trap);
-
-void netpoll_set_trap(int trap)
-{
- if (trap)
- atomic_inc(&trapped);
- else
- atomic_dec(&trapped);
-}
-EXPORT_SYMBOL(netpoll_set_trap);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index fdac61cac1bd..d0dac57291af 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -476,23 +476,22 @@ static int pgctrl_show(struct seq_file *seq, void *v)
static ssize_t pgctrl_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- int err = 0;
char data[128];
struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);
- if (!capable(CAP_NET_ADMIN)) {
- err = -EPERM;
- goto out;
- }
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (count == 0)
+ return -EINVAL;
if (count > sizeof(data))
count = sizeof(data);
- if (copy_from_user(data, buf, count)) {
- err = -EFAULT;
- goto out;
- }
- data[count - 1] = 0; /* Make string */
+ if (copy_from_user(data, buf, count))
+ return -EFAULT;
+
+ data[count - 1] = 0; /* Strip trailing '\n' and terminate string */
if (!strcmp(data, "stop"))
pktgen_stop_all_threads_ifs(pn);
@@ -506,10 +505,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
else
pr_warning("Unknown command: %s\n", data);
- err = count;
-
-out:
- return err;
+ return count;
}
static int pgctrl_open(struct inode *inode, struct file *file)
@@ -1251,7 +1247,13 @@ static ssize_t pktgen_if_write(struct file *file,
"Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s",
f,
"IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, "
- "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n");
+ "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, "
+ "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, "
+ "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, "
+#ifdef CONFIG_XFRM
+ "IPSEC, "
+#endif
+ "NODE_ALLOC\n");
return count;
}
sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags);
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
new file mode 100644
index 000000000000..eaba0f68f860
--- /dev/null
+++ b/net/core/ptp_classifier.c
@@ -0,0 +1,141 @@
+/* PTP classifier
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+/* The below program is the bpf_asm (tools/net/) representation of
+ * the opcode array in the ptp_filter structure.
+ *
+ * For convenience, this can easily be altered and reviewed with
+ * bpf_asm and bpf_dbg, e.g. `./bpf_asm -c prog` where prog is a
+ * simple file containing the below program:
+ *
+ * ldh [12] ; load ethertype
+ *
+ * ; PTP over UDP over IPv4 over Ethernet
+ * test_ipv4:
+ * jneq #0x800, test_ipv6 ; ETH_P_IP ?
+ * ldb [23] ; load proto
+ * jneq #17, drop_ipv4 ; IPPROTO_UDP ?
+ * ldh [20] ; load frag offset field
+ * jset #0x1fff, drop_ipv4 ; don't allow fragments
+ * ldxb 4*([14]&0xf) ; load IP header len
+ * ldh [x + 16] ; load UDP dst port
+ * jneq #319, drop_ipv4 ; is port PTP_EV_PORT ?
+ * ldh [x + 22] ; load payload
+ * and #0xf ; mask PTP_CLASS_VMASK
+ * or #0x10 ; PTP_CLASS_IPV4
+ * ret a ; return PTP class
+ * drop_ipv4: ret #0x0 ; PTP_CLASS_NONE
+ *
+ * ; PTP over UDP over IPv6 over Ethernet
+ * test_ipv6:
+ * jneq #0x86dd, test_8021q ; ETH_P_IPV6 ?
+ * ldb [20] ; load proto
+ * jneq #17, drop_ipv6 ; IPPROTO_UDP ?
+ * ldh [56] ; load UDP dst port
+ * jneq #319, drop_ipv6 ; is port PTP_EV_PORT ?
+ * ldh [62] ; load payload
+ * and #0xf ; mask PTP_CLASS_VMASK
+ * or #0x20 ; PTP_CLASS_IPV6
+ * ret a ; return PTP class
+ * drop_ipv6: ret #0x0 ; PTP_CLASS_NONE
+ *
+ * ; PTP over 802.1Q over Ethernet
+ * test_8021q:
+ * jneq #0x8100, test_ieee1588 ; ETH_P_8021Q ?
+ * ldh [16] ; load inner type
+ * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ?
+ * ldb [18] ; load payload
+ * and #0x8 ; as we don't have ports here, test
+ * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these
+ * ldh [18] ; reload payload
+ * and #0xf ; mask PTP_CLASS_VMASK
+ * or #0x40 ; PTP_CLASS_V2_VLAN
+ * ret a ; return PTP class
+ *
+ * ; PTP over Ethernet
+ * test_ieee1588:
+ * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ?
+ * ldb [14] ; load payload
+ * and #0x8 ; as we don't have ports here, test
+ * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these
+ * ldh [14] ; reload payload
+ * and #0xf ; mask PTP_CLASS_VMASK
+ * or #0x30 ; PTP_CLASS_L2
+ * ret a ; return PTP class
+ * drop_ieee1588: ret #0x0 ; PTP_CLASS_NONE
+ */
+
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <linux/ptp_classify.h>
+
+static struct sk_filter *ptp_insns __read_mostly;
+
+unsigned int ptp_classify_raw(const struct sk_buff *skb)
+{
+ return SK_RUN_FILTER(ptp_insns, skb);
+}
+EXPORT_SYMBOL_GPL(ptp_classify_raw);
+
+void __init ptp_classifier_init(void)
+{
+ static struct sock_filter ptp_filter[] = {
+ { 0x28, 0, 0, 0x0000000c },
+ { 0x15, 0, 12, 0x00000800 },
+ { 0x30, 0, 0, 0x00000017 },
+ { 0x15, 0, 9, 0x00000011 },
+ { 0x28, 0, 0, 0x00000014 },
+ { 0x45, 7, 0, 0x00001fff },
+ { 0xb1, 0, 0, 0x0000000e },
+ { 0x48, 0, 0, 0x00000010 },
+ { 0x15, 0, 4, 0x0000013f },
+ { 0x48, 0, 0, 0x00000016 },
+ { 0x54, 0, 0, 0x0000000f },
+ { 0x44, 0, 0, 0x00000010 },
+ { 0x16, 0, 0, 0x00000000 },
+ { 0x06, 0, 0, 0x00000000 },
+ { 0x15, 0, 9, 0x000086dd },
+ { 0x30, 0, 0, 0x00000014 },
+ { 0x15, 0, 6, 0x00000011 },
+ { 0x28, 0, 0, 0x00000038 },
+ { 0x15, 0, 4, 0x0000013f },
+ { 0x28, 0, 0, 0x0000003e },
+ { 0x54, 0, 0, 0x0000000f },
+ { 0x44, 0, 0, 0x00000020 },
+ { 0x16, 0, 0, 0x00000000 },
+ { 0x06, 0, 0, 0x00000000 },
+ { 0x15, 0, 9, 0x00008100 },
+ { 0x28, 0, 0, 0x00000010 },
+ { 0x15, 0, 15, 0x000088f7 },
+ { 0x30, 0, 0, 0x00000012 },
+ { 0x54, 0, 0, 0x00000008 },
+ { 0x15, 0, 12, 0x00000000 },
+ { 0x28, 0, 0, 0x00000012 },
+ { 0x54, 0, 0, 0x0000000f },
+ { 0x44, 0, 0, 0x00000040 },
+ { 0x16, 0, 0, 0x00000000 },
+ { 0x15, 0, 7, 0x000088f7 },
+ { 0x30, 0, 0, 0x0000000e },
+ { 0x54, 0, 0, 0x00000008 },
+ { 0x15, 0, 4, 0x00000000 },
+ { 0x28, 0, 0, 0x0000000e },
+ { 0x54, 0, 0, 0x0000000f },
+ { 0x44, 0, 0, 0x00000030 },
+ { 0x16, 0, 0, 0x00000000 },
+ { 0x06, 0, 0, 0x00000000 },
+ };
+ struct sock_fprog ptp_prog = {
+ .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
+ };
+
+ BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog));
+}
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 4425148d2b51..467f326126e0 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -221,5 +221,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
out:
spin_unlock_bh(&fastopenq->lock);
sock_put(lsk);
- return;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 120eecc0f5a4..d4ff41739b0f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -822,6 +822,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+ nla_total_size(ext_filter_mask
& RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
+ rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -970,7 +971,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
(dev->qdisc &&
nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
(dev->ifalias &&
- nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)))
+ nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+ nla_put_u32(skb, IFLA_CARRIER_CHANGES,
+ atomic_read(&dev->carrier_changes)))
goto nla_put_failure;
if (1) {
@@ -1121,56 +1124,7 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
-{
- struct net *net = sock_net(skb->sk);
- int h, s_h;
- int idx = 0, s_idx;
- struct net_device *dev;
- struct hlist_head *head;
- struct nlattr *tb[IFLA_MAX+1];
- u32 ext_filter_mask = 0;
-
- s_h = cb->args[0];
- s_idx = cb->args[1];
-
- rcu_read_lock();
- cb->seq = net->dev_base_seq;
-
- if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
- ifla_policy) >= 0) {
-
- if (tb[IFLA_EXT_MASK])
- ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
- }
-
- for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
- idx = 0;
- head = &net->dev_index_head[h];
- hlist_for_each_entry_rcu(dev, head, index_hlist) {
- if (idx < s_idx)
- goto cont;
- if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, 0,
- NLM_F_MULTI,
- ext_filter_mask) <= 0)
- goto out;
-
- nl_dump_check_consistent(cb, nlmsg_hdr(skb));
-cont:
- idx++;
- }
- }
-out:
- rcu_read_unlock();
- cb->args[1] = idx;
- cb->args[0] = h;
-
- return skb->len;
-}
-
-const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
[IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
@@ -1196,8 +1150,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
[IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+ [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */
};
-EXPORT_SYMBOL(ifla_policy);
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
[IFLA_INFO_KIND] = { .type = NLA_STRING },
@@ -1235,6 +1189,61 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
[IFLA_PORT_RESPONSE] = { .type = NLA_U16, },
};
+static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ int h, s_h;
+ int idx = 0, s_idx;
+ struct net_device *dev;
+ struct hlist_head *head;
+ struct nlattr *tb[IFLA_MAX+1];
+ u32 ext_filter_mask = 0;
+
+ s_h = cb->args[0];
+ s_idx = cb->args[1];
+
+ rcu_read_lock();
+ cb->seq = net->dev_base_seq;
+
+ if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
+ ifla_policy) >= 0) {
+
+ if (tb[IFLA_EXT_MASK])
+ ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+ }
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ hlist_for_each_entry_rcu(dev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, 0,
+ NLM_F_MULTI,
+ ext_filter_mask) <= 0)
+ goto out;
+
+ nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+cont:
+ idx++;
+ }
+ }
+out:
+ rcu_read_unlock();
+ cb->args[1] = idx;
+ cb->args[0] = h;
+
+ return skb->len;
+}
+
+int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len)
+{
+ return nla_parse(tb, IFLA_MAX, head, len, ifla_policy);
+}
+EXPORT_SYMBOL(rtnl_nla_parse_ifla);
+
struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
{
struct net *net;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 90b96a11b974..30c7d35dd862 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3300,6 +3300,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
return elt;
}
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+ int offset, int len)
+{
+ return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
{
int nsg = __skb_to_sgvec(skb, sg, offset, len);
@@ -3562,15 +3588,47 @@ static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
return 0;
}
+#define MAX_TCP_HDR_LEN (15 * 4)
+
+static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb,
+ typeof(IPPROTO_IP) proto,
+ unsigned int off)
+{
+ switch (proto) {
+ int err;
+
+ case IPPROTO_TCP:
+ err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr),
+ off + MAX_TCP_HDR_LEN);
+ if (!err && !skb_partial_csum_set(skb, off,
+ offsetof(struct tcphdr,
+ check)))
+ err = -EPROTO;
+ return err ? ERR_PTR(err) : &tcp_hdr(skb)->check;
+
+ case IPPROTO_UDP:
+ err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr),
+ off + sizeof(struct udphdr));
+ if (!err && !skb_partial_csum_set(skb, off,
+ offsetof(struct udphdr,
+ check)))
+ err = -EPROTO;
+ return err ? ERR_PTR(err) : &udp_hdr(skb)->check;
+ }
+
+ return ERR_PTR(-EPROTO);
+}
+
/* This value should be large enough to cover a tagged ethernet header plus
* maximally sized IP and TCP or UDP headers.
*/
#define MAX_IP_HDR_LEN 128
-static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate)
{
unsigned int off;
bool fragment;
+ __sum16 *csum;
int err;
fragment = false;
@@ -3591,51 +3649,15 @@ static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
if (fragment)
goto out;
- switch (ip_hdr(skb)->protocol) {
- case IPPROTO_TCP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- tcp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IP_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- udp_hdr(skb)->check =
- ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
- ip_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
+ csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off);
+ if (IS_ERR(csum))
+ return PTR_ERR(csum);
+ if (recalculate)
+ *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr,
+ skb->len - off,
+ ip_hdr(skb)->protocol, 0);
err = 0;
out:
@@ -3658,6 +3680,7 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
unsigned int len;
bool fragment;
bool done;
+ __sum16 *csum;
fragment = false;
done = false;
@@ -3735,51 +3758,14 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
if (!done || fragment)
goto out;
- switch (nexthdr) {
- case IPPROTO_TCP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct tcphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct tcphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- tcp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_TCP, 0);
- break;
- case IPPROTO_UDP:
- err = skb_maybe_pull_tail(skb,
- off + sizeof(struct udphdr),
- MAX_IPV6_HDR_LEN);
- if (err < 0)
- goto out;
-
- if (!skb_partial_csum_set(skb, off,
- offsetof(struct udphdr, check))) {
- err = -EPROTO;
- goto out;
- }
-
- if (recalculate)
- udp_hdr(skb)->check =
- ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
- &ipv6_hdr(skb)->daddr,
- skb->len - off,
- IPPROTO_UDP, 0);
- break;
- default:
- goto out;
- }
+ csum = skb_checksum_setup_ip(skb, nexthdr, off);
+ if (IS_ERR(csum))
+ return PTR_ERR(csum);
+ if (recalculate)
+ *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len - off, nexthdr, 0);
err = 0;
out:
@@ -3797,7 +3783,7 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
switch (skb->protocol) {
case htons(ETH_P_IP):
- err = skb_checksum_setup_ip(skb, recalculate);
+ err = skb_checksum_setup_ipv4(skb, recalculate);
break;
case htons(ETH_P_IPV6):
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6379de..d7af18859322 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -52,9 +52,10 @@ EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
struct sk_buff *skb, int attrtype)
{
- struct nlattr *attr;
+ struct sock_fprog_kern *fprog;
struct sk_filter *filter;
- unsigned int len;
+ struct nlattr *attr;
+ unsigned int flen;
int err = 0;
if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
@@ -63,24 +64,20 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
}
rcu_read_lock();
-
filter = rcu_dereference(sk->sk_filter);
- len = filter ? filter->len * sizeof(struct sock_filter) : 0;
+ if (!filter)
+ goto out;
- attr = nla_reserve(skb, attrtype, len);
+ fprog = filter->orig_prog;
+ flen = sk_filter_proglen(fprog);
+
+ attr = nla_reserve(skb, attrtype, flen);
if (attr == NULL) {
err = -EMSGSIZE;
goto out;
}
- if (filter) {
- struct sock_filter *fb = (struct sock_filter *)nla_data(attr);
- int i;
-
- for (i = 0; i < filter->len; i++, fb++)
- sk_decode_filter(&filter->insns[i], fb);
- }
-
+ memcpy(nla_data(attr), fprog->filter, flen);
out:
rcu_read_unlock();
return err;
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 661b5a40ec10..6521dfd8b7c8 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -23,16 +23,11 @@
#include <linux/skbuff.h>
#include <linux/export.h>
-static struct sock_filter ptp_filter[] = {
- PTP_FILTER
-};
-
static unsigned int classify(const struct sk_buff *skb)
{
- if (likely(skb->dev &&
- skb->dev->phydev &&
+ if (likely(skb->dev && skb->dev->phydev &&
skb->dev->phydev->drv))
- return sk_run_filter(skb, ptp_filter);
+ return ptp_classify_raw(skb);
else
return PTP_CLASS_NONE;
}
@@ -60,11 +55,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
if (likely(phydev->drv->txtstamp)) {
if (!atomic_inc_not_zero(&sk->sk_refcnt))
return;
+
clone = skb_clone(skb, GFP_ATOMIC);
if (!clone) {
sock_put(sk);
return;
}
+
clone->sk = sk;
phydev->drv->txtstamp(phydev, clone, type);
}
@@ -89,12 +86,15 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
}
*skb_hwtstamps(skb) = *hwtstamps;
+
serr = SKB_EXT_ERR(skb);
memset(serr, 0, sizeof(*serr));
serr->ee.ee_errno = ENOMSG;
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
skb->sk = NULL;
+
err = sock_queue_err_skb(sk, skb);
+
sock_put(sk);
if (err)
kfree_skb(skb);
@@ -132,8 +132,3 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb)
return false;
}
EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp);
-
-void __init skb_timestamping_init(void)
-{
- BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter)));
-}
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-12-21 12:21:47 +0000