summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c36
-rw-r--r--net/core/dev.c1
-rw-r--r--net/core/filter.c112
-rw-r--r--net/core/flow.c8
-rw-r--r--net/core/netpoll.c1
-rw-r--r--net/core/pktgen.c6
-rw-r--r--net/core/skbuff.c27
-rw-r--r--net/core/sock.c21
-rw-r--r--net/core/stream.c10
9 files changed, 157 insertions, 65 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 1bcfef51ac58..f8d322e1ea92 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -47,6 +47,7 @@
#include <linux/rtnetlink.h>
#include <linux/poll.h>
#include <linux/highmem.h>
+#include <linux/spinlock.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
@@ -200,6 +201,41 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
}
/**
+ * skb_kill_datagram - Free a datagram skbuff forcibly
+ * @sk: socket
+ * @skb: datagram skbuff
+ * @flags: MSG_ flags
+ *
+ * This function frees a datagram skbuff that was received by
+ * skb_recv_datagram. The flags argument must match the one
+ * used for skb_recv_datagram.
+ *
+ * If the MSG_PEEK flag is set, and the packet is still on the
+ * receive queue of the socket, it will be taken off the queue
+ * before it is freed.
+ *
+ * This function currently only disables BH when acquiring the
+ * sk_receive_queue lock. Therefore it must not be used in a
+ * context where that lock is acquired in an IRQ context.
+ */
+
+void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
+{
+ if (flags & MSG_PEEK) {
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ if (skb == skb_peek(&sk->sk_receive_queue)) {
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ atomic_dec(&skb->users);
+ }
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ }
+
+ kfree_skb(skb);
+}
+
+EXPORT_SYMBOL(skb_kill_datagram);
+
+/**
* skb_copy_datagram_iovec - Copy a datagram to an iovec.
* @skb: buffer to copy
* @offset: offset in the buffer to start copying from
diff --git a/net/core/dev.c b/net/core/dev.c
index a5efc9ae010b..29ba109d3e54 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3276,7 +3276,6 @@ EXPORT_SYMBOL(dev_close);
EXPORT_SYMBOL(dev_get_by_flags);
EXPORT_SYMBOL(dev_get_by_index);
EXPORT_SYMBOL(dev_get_by_name);
-EXPORT_SYMBOL(dev_ioctl);
EXPORT_SYMBOL(dev_open);
EXPORT_SYMBOL(dev_queue_xmit);
EXPORT_SYMBOL(dev_remove_pack);
diff --git a/net/core/filter.c b/net/core/filter.c
index 3a10e0bc90e8..8964d3445588 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -13,6 +13,7 @@
* 2 of the License, or (at your option) any later version.
*
* Andi Kleen - Fix a few bad bugs and races.
+ * Kris Katterjohn - Added many additional checks in sk_chk_filter()
*/
#include <linux/module.h>
@@ -250,7 +251,7 @@ load_b:
mem[fentry->k] = X;
continue;
default:
- /* Invalid instruction counts as RET */
+ WARN_ON(1);
return 0;
}
@@ -283,8 +284,8 @@ load_b:
*
* Check the user's filter code. If we let some ugly
* filter code slip through kaboom! The filter must contain
- * no references or jumps that are out of range, no illegal instructions
- * and no backward jumps. It must end with a RET instruction
+ * no references or jumps that are out of range, no illegal
+ * instructions, and must end with a RET instruction.
*
* Returns 0 if the rule set is legal or a negative errno code if not.
*/
@@ -300,38 +301,85 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
for (pc = 0; pc < flen; pc++) {
/* all jumps are forward as they are not signed */
ftest = &filter[pc];
- if (BPF_CLASS(ftest->code) == BPF_JMP) {
- /* but they mustn't jump off the end */
- if (BPF_OP(ftest->code) == BPF_JA) {
- /*
- * Note, the large ftest->k might cause loops.
- * Compare this with conditional jumps below,
- * where offsets are limited. --ANK (981016)
- */
- if (ftest->k >= (unsigned)(flen-pc-1))
- return -EINVAL;
- } else {
- /* for conditionals both must be safe */
- if (pc + ftest->jt +1 >= flen ||
- pc + ftest->jf +1 >= flen)
- return -EINVAL;
- }
- }
- /* check for division by zero -Kris Katterjohn 2005-10-30 */
- if (ftest->code == (BPF_ALU|BPF_DIV|BPF_K) && ftest->k == 0)
- return -EINVAL;
+ /* Only allow valid instructions */
+ switch (ftest->code) {
+ case BPF_ALU|BPF_ADD|BPF_K:
+ case BPF_ALU|BPF_ADD|BPF_X:
+ case BPF_ALU|BPF_SUB|BPF_K:
+ case BPF_ALU|BPF_SUB|BPF_X:
+ case BPF_ALU|BPF_MUL|BPF_K:
+ case BPF_ALU|BPF_MUL|BPF_X:
+ case BPF_ALU|BPF_DIV|BPF_X:
+ case BPF_ALU|BPF_AND|BPF_K:
+ case BPF_ALU|BPF_AND|BPF_X:
+ case BPF_ALU|BPF_OR|BPF_K:
+ case BPF_ALU|BPF_OR|BPF_X:
+ case BPF_ALU|BPF_LSH|BPF_K:
+ case BPF_ALU|BPF_LSH|BPF_X:
+ case BPF_ALU|BPF_RSH|BPF_K:
+ case BPF_ALU|BPF_RSH|BPF_X:
+ case BPF_ALU|BPF_NEG:
+ case BPF_LD|BPF_W|BPF_ABS:
+ case BPF_LD|BPF_H|BPF_ABS:
+ case BPF_LD|BPF_B|BPF_ABS:
+ case BPF_LD|BPF_W|BPF_LEN:
+ case BPF_LD|BPF_W|BPF_IND:
+ case BPF_LD|BPF_H|BPF_IND:
+ case BPF_LD|BPF_B|BPF_IND:
+ case BPF_LD|BPF_IMM:
+ case BPF_LDX|BPF_W|BPF_LEN:
+ case BPF_LDX|BPF_B|BPF_MSH:
+ case BPF_LDX|BPF_IMM:
+ case BPF_MISC|BPF_TAX:
+ case BPF_MISC|BPF_TXA:
+ case BPF_RET|BPF_K:
+ case BPF_RET|BPF_A:
+ break;
+
+ /* Some instructions need special checks */
- /* check that memory operations use valid addresses. */
- if (ftest->k >= BPF_MEMWORDS) {
- /* but it might not be a memory operation... */
- switch (ftest->code) {
- case BPF_ST:
- case BPF_STX:
- case BPF_LD|BPF_MEM:
- case BPF_LDX|BPF_MEM:
+ case BPF_ALU|BPF_DIV|BPF_K:
+ /* check for division by zero */
+ if (ftest->k == 0)
return -EINVAL;
- }
+ break;
+
+ case BPF_LD|BPF_MEM:
+ case BPF_LDX|BPF_MEM:
+ case BPF_ST:
+ case BPF_STX:
+ /* check for invalid memory addresses */
+ if (ftest->k >= BPF_MEMWORDS)
+ return -EINVAL;
+ break;
+
+ case BPF_JMP|BPF_JA:
+ /*
+ * Note, the large ftest->k might cause loops.
+ * Compare this with conditional jumps below,
+ * where offsets are limited. --ANK (981016)
+ */
+ if (ftest->k >= (unsigned)(flen-pc-1))
+ return -EINVAL;
+ break;
+
+ case BPF_JMP|BPF_JEQ|BPF_K:
+ case BPF_JMP|BPF_JEQ|BPF_X:
+ case BPF_JMP|BPF_JGE|BPF_K:
+ case BPF_JMP|BPF_JGE|BPF_X:
+ case BPF_JMP|BPF_JGT|BPF_K:
+ case BPF_JMP|BPF_JGT|BPF_X:
+ case BPF_JMP|BPF_JSET|BPF_K:
+ case BPF_JMP|BPF_JSET|BPF_X:
+ /* for conditionals both must be safe */
+ if (pc + ftest->jt + 1 >= flen ||
+ pc + ftest->jf + 1 >= flen)
+ return -EINVAL;
+ break;
+
+ default:
+ return -EINVAL;
}
}
diff --git a/net/core/flow.c b/net/core/flow.c
index 7e95b39de9fd..c4f25385029f 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -23,6 +23,7 @@
#include <net/flow.h>
#include <asm/atomic.h>
#include <asm/semaphore.h>
+#include <linux/security.h>
struct flow_cache_entry {
struct flow_cache_entry *next;
@@ -30,6 +31,7 @@ struct flow_cache_entry {
u8 dir;
struct flowi key;
u32 genid;
+ u32 sk_sid;
void *object;
atomic_t *object_ref;
};
@@ -162,7 +164,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2)
return 0;
}
-void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
+void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir,
flow_resolve_t resolver)
{
struct flow_cache_entry *fle, **head;
@@ -186,6 +188,7 @@ void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
for (fle = *head; fle; fle = fle->next) {
if (fle->family == family &&
fle->dir == dir &&
+ fle->sk_sid == sk_sid &&
flow_key_compare(key, &fle->key) == 0) {
if (fle->genid == atomic_read(&flow_cache_genid)) {
void *ret = fle->object;
@@ -210,6 +213,7 @@ void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
*head = fle;
fle->family = family;
fle->dir = dir;
+ fle->sk_sid = sk_sid;
memcpy(&fle->key, key, sizeof(*key));
fle->object = NULL;
flow_count(cpu)++;
@@ -221,7 +225,7 @@ nocache:
void *obj;
atomic_t *obj_ref;
- resolver(key, family, dir, &obj, &obj_ref);
+ resolver(key, sk_sid, family, dir, &obj, &obj_ref);
if (fle) {
fle->genid = atomic_read(&flow_cache_genid);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 49424a42a2c0..281a632fa6a6 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -13,6 +13,7 @@
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
+#include <linux/if_arp.h>
#include <linux/inetdevice.h>
#include <linux/inet.h>
#include <linux/interrupt.h>
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 7fc3e9e28c34..06cad2d63e8a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -487,9 +487,9 @@ static unsigned int fmt_ip6(char *s,const char ip[16]);
/* Module parameters, defaults. */
static int pg_count_d = 1000; /* 1000 pkts by default */
-static int pg_delay_d = 0;
-static int pg_clone_skb_d = 0;
-static int debug = 0;
+static int pg_delay_d;
+static int pg_clone_skb_d;
+static int debug;
static DECLARE_MUTEX(pktgen_sem);
static struct pktgen_thread *pktgen_threads = NULL;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 83fee37de38e..070f91cfde59 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -135,17 +135,13 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here)
struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
int fclone)
{
+ struct skb_shared_info *shinfo;
struct sk_buff *skb;
u8 *data;
/* Get the HEAD */
- if (fclone)
- skb = kmem_cache_alloc(skbuff_fclone_cache,
- gfp_mask & ~__GFP_DMA);
- else
- skb = kmem_cache_alloc(skbuff_head_cache,
- gfp_mask & ~__GFP_DMA);
-
+ skb = kmem_cache_alloc(fclone ? skbuff_fclone_cache : skbuff_head_cache,
+ gfp_mask & ~__GFP_DMA);
if (!skb)
goto out;
@@ -162,6 +158,16 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb->data = data;
skb->tail = data;
skb->end = data + size;
+ /* make sure we initialize shinfo sequentially */
+ shinfo = skb_shinfo(skb);
+ atomic_set(&shinfo->dataref, 1);
+ shinfo->nr_frags = 0;
+ shinfo->tso_size = 0;
+ shinfo->tso_segs = 0;
+ shinfo->ufo_size = 0;
+ shinfo->ip6_frag_id = 0;
+ shinfo->frag_list = NULL;
+
if (fclone) {
struct sk_buff *child = skb + 1;
atomic_t *fclone_ref = (atomic_t *) (child + 1);
@@ -171,13 +177,6 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
child->fclone = SKB_FCLONE_UNAVAILABLE;
}
- atomic_set(&(skb_shinfo(skb)->dataref), 1);
- skb_shinfo(skb)->nr_frags = 0;
- skb_shinfo(skb)->tso_size = 0;
- skb_shinfo(skb)->tso_segs = 0;
- skb_shinfo(skb)->frag_list = NULL;
- skb_shinfo(skb)->ufo_size = 0;
- skb_shinfo(skb)->ip6_frag_id = 0;
out:
return skb;
nodata:
diff --git a/net/core/sock.c b/net/core/sock.c
index 13cc3be4f056..6465b0e4c8cb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1488,7 +1488,7 @@ int proto_register(struct proto *prot, int alloc_slab)
}
}
- if (prot->twsk_obj_size) {
+ if (prot->twsk_prot != NULL) {
static const char mask[] = "tw_sock_%s";
timewait_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);
@@ -1497,11 +1497,12 @@ int proto_register(struct proto *prot, int alloc_slab)
goto out_free_request_sock_slab;
sprintf(timewait_sock_slab_name, mask, prot->name);
- prot->twsk_slab = kmem_cache_create(timewait_sock_slab_name,
- prot->twsk_obj_size,
- 0, SLAB_HWCACHE_ALIGN,
- NULL, NULL);
- if (prot->twsk_slab == NULL)
+ prot->twsk_prot->twsk_slab =
+ kmem_cache_create(timewait_sock_slab_name,
+ prot->twsk_prot->twsk_obj_size,
+ 0, SLAB_HWCACHE_ALIGN,
+ NULL, NULL);
+ if (prot->twsk_prot->twsk_slab == NULL)
goto out_free_timewait_sock_slab_name;
}
}
@@ -1548,12 +1549,12 @@ void proto_unregister(struct proto *prot)
prot->rsk_prot->slab = NULL;
}
- if (prot->twsk_slab != NULL) {
- const char *name = kmem_cache_name(prot->twsk_slab);
+ if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
+ const char *name = kmem_cache_name(prot->twsk_prot->twsk_slab);
- kmem_cache_destroy(prot->twsk_slab);
+ kmem_cache_destroy(prot->twsk_prot->twsk_slab);
kfree(name);
- prot->twsk_slab = NULL;
+ prot->twsk_prot->twsk_slab = NULL;
}
}
diff --git a/net/core/stream.c b/net/core/stream.c
index 15bfd03e8024..35e25259fd95 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -55,8 +55,9 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
int done;
do {
- if (sk->sk_err)
- return sock_error(sk);
+ int err = sock_error(sk);
+ if (err)
+ return err;
if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV))
return -EPIPE;
if (!*timeo_p)
@@ -67,6 +68,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
sk->sk_write_pending++;
done = sk_wait_event(sk, timeo_p,
+ !sk->sk_err &&
!((1 << sk->sk_state) &
~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)));
finish_wait(sk->sk_sleep, &wait);
@@ -137,7 +139,9 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
- sk_wait_event(sk, &current_timeo, sk_stream_memory_free(sk) &&
+ sk_wait_event(sk, &current_timeo, !sk->sk_err &&
+ !(sk->sk_shutdown & SEND_SHUTDOWN) &&
+ sk_stream_memory_free(sk) &&
vm_wait);
sk->sk_write_pending--;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-14 20:24:41 +0000