diff options
Diffstat (limited to 'net/core')
44 files changed, 29880 insertions, 11238 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 630da0f0579..71093d94ad2 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -3,16 +3,24 @@ # obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ - gen_stats.o gen_estimator.o + gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o \ - neighbour.o rtnetlink.o utils.o link_watch.o filter.o +obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ + neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ + sock_diag.o dev_ioctl.o tso.o obj-$(CONFIG_XFRM) += flow.o -obj-$(CONFIG_SYSFS) += net-sysfs.o -obj-$(CONFIG_NET_DIVERT) += dv.o +obj-y += net-sysfs.o +obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o -obj-$(CONFIG_NET_RADIO) += wireless.o obj-$(CONFIG_NETPOLL) += netpoll.o +obj-$(CONFIG_NET_DMA) += user_dma.o +obj-$(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/datagram.c b/net/core/datagram.c index f8d322e1ea9..488dd1a825c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -9,7 +9,7 @@ * identical recvmsg() code. So we share it here. The poll was * shared before but buried in udp.c so I moved it. * - * Authors: Alan Cox <alan@redhat.com>. (datagram_poll() from old + * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk>. (datagram_poll() from old * udp.c code) * * Fixes: @@ -37,7 +37,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/errno.h> @@ -48,6 +47,8 @@ #include <linux/poll.h> #include <linux/highmem.h> #include <linux/spinlock.h> +#include <linux/slab.h> +#include <linux/pagemap.h> #include <net/protocol.h> #include <linux/skbuff.h> @@ -55,6 +56,8 @@ #include <net/checksum.h> #include <net/sock.h> #include <net/tcp_states.h> +#include <trace/events/skb.h> +#include <net/busy_poll.h> /* * Is a socket 'connection oriented' ? @@ -64,22 +67,35 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } +static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync, + void *key) +{ + unsigned long bits = (unsigned long)key; + + /* + * Avoid a wakeup if event not interesting for us + */ + if (bits && !(bits & (POLLIN | POLLERR))) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} /* - * Wait for a packet.. + * Wait for the last received packet to be different from skb */ -static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) +static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, + const struct sk_buff *skb) { int error; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, receiver_wake_function); - prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); if (error) goto out_err; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (sk->sk_receive_queue.prev != skb) goto out; /* Socket shut down? */ @@ -101,7 +117,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) error = 0; *timeo_p = schedule_timeout(*timeo_p); out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return error; interrupted: error = sock_intr_errno(*timeo_p); @@ -115,10 +131,12 @@ out_noerr: } /** - * skb_recv_datagram - Receive a datagram skbuff + * __skb_recv_datagram - Receive a datagram skbuff * @sk: socket * @flags: MSG_ flags - * @noblock: blocking operation? + * @peeked: returns non-zero if this packet has been seen before + * @off: an offset in bytes to peek skb from. Returns an offset + * within an skb where data actually starts * @err: error code returned * * Get a datagram skbuff, understands the peeking, nonblocking wakeups @@ -143,10 +161,10 @@ out_noerr: * quite explicitly by POSIX 1003.1g, don't change them without having * the standard around please. */ -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, - int noblock, int *err) +struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, + int *peeked, int *off, int *err) { - struct sk_buff *skb; + struct sk_buff *skb, *last; long timeo; /* * Caller is allowed not to check sk->sk_err before skb_recv_datagram() @@ -156,37 +174,51 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, if (error) goto no_packet; - timeo = sock_rcvtimeo(sk, noblock); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { /* Again only user level code calls this function, so nothing * interrupt level will suddenly eat the receive_queue. * * Look at current nfs client by the way... - * However, this function was corrent in any case. 8) + * However, this function was correct in any case. 8) */ - if (flags & MSG_PEEK) { - unsigned long cpu_flags; - - spin_lock_irqsave(&sk->sk_receive_queue.lock, - cpu_flags); - skb = skb_peek(&sk->sk_receive_queue); - if (skb) + unsigned long cpu_flags; + struct sk_buff_head *queue = &sk->sk_receive_queue; + int _off = *off; + + last = (struct sk_buff *)queue; + spin_lock_irqsave(&queue->lock, cpu_flags); + skb_queue_walk(queue, skb) { + last = skb; + *peeked = skb->peeked; + if (flags & MSG_PEEK) { + if (_off >= skb->len && (skb->len || _off || + skb->peeked)) { + _off -= skb->len; + continue; + } + skb->peeked = 1; atomic_inc(&skb->users); - spin_unlock_irqrestore(&sk->sk_receive_queue.lock, - cpu_flags); - } else - skb = skb_dequeue(&sk->sk_receive_queue); + } else + __skb_unlink(skb, queue); - if (skb) + spin_unlock_irqrestore(&queue->lock, cpu_flags); + *off = _off; return skb; + } + spin_unlock_irqrestore(&queue->lock, cpu_flags); + + if (sk_can_busy_loop(sk) && + sk_busy_loop(sk, flags & MSG_DONTWAIT)) + continue; /* User doesn't want to wait */ error = -EAGAIN; if (!timeo) goto no_packet; - } while (!wait_for_packet(sk, err, &timeo)); + } while (!wait_for_more_packets(sk, err, &timeo, last)); return NULL; @@ -194,11 +226,43 @@ no_packet: *err = error; return NULL; } +EXPORT_SYMBOL(__skb_recv_datagram); + +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, + int noblock, int *err) +{ + int peeked, off = 0; + + return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + &peeked, &off, err); +} +EXPORT_SYMBOL(skb_recv_datagram); void skb_free_datagram(struct sock *sk, struct sk_buff *skb) { - kfree_skb(skb); + consume_skb(skb); + sk_mem_reclaim_partial(sk); } +EXPORT_SYMBOL(skb_free_datagram); + +void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) +{ + bool slow; + + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + + slow = lock_sock_fast(sk); + skb_orphan(skb); + sk_mem_reclaim_partial(sk); + unlock_sock_fast(sk, slow); + + /* skb is now orphaned, can be freed outside of locked section */ + __kfree_skb(skb); +} +EXPORT_SYMBOL(skb_free_datagram_locked); /** * skb_kill_datagram - Free a datagram skbuff forcibly @@ -217,22 +281,31 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb) * 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. + * + * It returns 0 if the packet was removed by us. */ -void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) +int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) { + int err = 0; + if (flags & MSG_PEEK) { + err = -ENOENT; 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); + err = 0; } spin_unlock_bh(&sk->sk_receive_queue.lock); } kfree_skb(skb); -} + atomic_inc(&sk->sk_drops); + sk_mem_reclaim_partial(sk); + return err; +} EXPORT_SYMBOL(skb_kill_datagram); /** @@ -247,60 +320,339 @@ EXPORT_SYMBOL(skb_kill_datagram); int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, struct iovec *to, int len) { - int i, err, fraglen, end = 0; - struct sk_buff *next = skb_shinfo(skb)->frag_list; + int start = skb_headlen(skb); + int i, copy = start - offset; + struct sk_buff *frag_iter; + + trace_skb_copy_datagram_iovec(skb, len); + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_toiovec(to, skb->data + offset, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(frag); + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + struct page *page = skb_frag_page(frag); + + if (copy > len) + copy = len; + vaddr = kmap(page); + err = memcpy_toiovec(to, vaddr + frag->page_offset + + offset - start, copy); + kunmap(page); + if (err) + goto fault; + if (!(len -= copy)) + return 0; + offset += copy; + } + start = end; + } + + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_iovec(frag_iter, + offset - start, + to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + } + start = end; + } if (!len) return 0; -next_skb: - fraglen = skb_headlen(skb); - i = -1; +fault: + return -EFAULT; +} +EXPORT_SYMBOL(skb_copy_datagram_iovec); - while (1) { - int start = end; +/** + * skb_copy_datagram_const_iovec - Copy a datagram to an iovec. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying from + * @to: io vector to copy to + * @to_offset: offset in the io vector to start copying to + * @len: amount of data to copy from buffer to iovec + * + * Returns 0 or -EFAULT. + * Note: the iovec is not modified during the copy. + */ +int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset, + const struct iovec *to, int to_offset, + int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + struct sk_buff *frag_iter; - if ((end += fraglen) > offset) { - int copy = end - offset, o = offset - start; + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to_offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(frag); + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; - if (i == -1) - err = memcpy_toiovec(to, skb->data + o, copy); - else { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; - void *p = kmap(page) + frag->page_offset + o; - err = memcpy_toiovec(to, p, copy); - kunmap(page); - } + vaddr = kmap(page); + err = memcpy_toiovecend(to, vaddr + frag->page_offset + + offset - start, to_offset, copy); + kunmap(page); if (err) goto fault; if (!(len -= copy)) return 0; offset += copy; + to_offset += copy; } - if (++i >= skb_shinfo(skb)->nr_frags) - break; - fraglen = skb_shinfo(skb)->frags[i].size; + start = end; } - if (next) { - skb = next; - BUG_ON(skb_shinfo(skb)->frag_list); - next = skb->next; - goto next_skb; + + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_const_iovec(frag_iter, + offset - start, + to, to_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to_offset += copy; + } + start = end; } + if (!len) + return 0; + fault: return -EFAULT; } +EXPORT_SYMBOL(skb_copy_datagram_const_iovec); + +/** + * skb_copy_datagram_from_iovec - Copy a datagram from an iovec. + * @skb: buffer to copy + * @offset: offset in the buffer to start copying to + * @from: io vector to copy to + * @from_offset: offset in the io vector to start copying from + * @len: amount of data to copy to buffer from iovec + * + * Returns 0 or -EFAULT. + * Note: the iovec is not modified during the copy. + */ +int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, + const struct iovec *from, int from_offset, + int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + struct sk_buff *frag_iter; + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + if (memcpy_fromiovecend(skb->data + offset, from, from_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from_offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(frag); + if ((copy = end - offset) > 0) { + int err; + u8 *vaddr; + struct page *page = skb_frag_page(frag); + + if (copy > len) + copy = len; + vaddr = kmap(page); + err = memcpy_fromiovecend(vaddr + frag->page_offset + + offset - start, + from, from_offset, copy); + kunmap(page); + if (err) + goto fault; + + if (!(len -= copy)) + return 0; + offset += copy; + from_offset += copy; + } + start = end; + } + + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_from_iovec(frag_iter, + offset - start, + from, + from_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from_offset += copy; + } + start = end; + } + if (!len) + return 0; + +fault: + return -EFAULT; +} +EXPORT_SYMBOL(skb_copy_datagram_from_iovec); + +/** + * zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec + * @skb: buffer to copy + * @from: io vector to copy from + * @offset: offset in the io vector to start copying from + * @count: amount of vectors to copy to buffer from + * + * The function will first copy up to headlen, and then pin the userspace + * pages and build frags through them. + * + * Returns 0, -EFAULT or -EMSGSIZE. + * Note: the iovec is not modified during the copy + */ +int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, + int offset, size_t count) +{ + int len = iov_length(from, count) - offset; + int copy = min_t(int, skb_headlen(skb), len); + int size; + int i = 0; + + /* copy up to skb headlen */ + if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy)) + return -EFAULT; + + if (len == copy) + return 0; + + offset += copy; + while (count--) { + struct page *page[MAX_SKB_FRAGS]; + int num_pages; + unsigned long base; + unsigned long truesize; + + /* Skip over from offset and copied */ + if (offset >= from->iov_len) { + offset -= from->iov_len; + ++from; + continue; + } + len = from->iov_len - offset; + base = (unsigned long)from->iov_base + offset; + size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + if (i + size > MAX_SKB_FRAGS) + return -EMSGSIZE; + num_pages = get_user_pages_fast(base, size, 0, &page[i]); + if (num_pages != size) { + release_pages(&page[i], num_pages, 0); + return -EFAULT; + } + truesize = size * PAGE_SIZE; + skb->data_len += len; + skb->len += len; + skb->truesize += truesize; + atomic_add(truesize, &skb->sk->sk_wmem_alloc); + while (len) { + int off = base & ~PAGE_MASK; + int size = min_t(int, len, PAGE_SIZE - off); + skb_fill_page_desc(skb, i, page[i], off, size); + base += size; + len -= size; + i++; + } + offset = 0; + ++from; + } + return 0; +} +EXPORT_SYMBOL(zerocopy_sg_from_iovec); static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, u8 __user *to, int len, - unsigned int *csump) + __wsum *csump) { int start = skb_headlen(skb); - int pos = 0; int i, copy = start - offset; + struct sk_buff *frag_iter; + int pos = 0; /* Copy header. */ if (copy > 0) { @@ -320,16 +672,16 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { - unsigned int csum2; + __wsum csum2; int err = 0; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -351,33 +703,29 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list=list->next) { - int end; - - BUG_TRAP(start <= offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - unsigned int csum2 = 0; - if (copy > len) - copy = len; - if (skb_copy_and_csum_datagram(list, - offset - start, - to, copy, - &csum2)) - goto fault; - *csump = csum_block_add(*csump, csum2, pos); - if ((len -= copy) == 0) - return 0; - offset += copy; - to += copy; - pos += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + __wsum csum2 = 0; + if (copy > len) + copy = len; + if (skb_copy_and_csum_datagram(frag_iter, + offset - start, + to, copy, + &csum2)) + goto fault; + *csump = csum_block_add(*csump, csum2, pos); + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; + pos += copy; } + start = end; } if (!len) return 0; @@ -386,16 +734,42 @@ fault: return -EFAULT; } -unsigned int __skb_checksum_complete(struct sk_buff *skb) +__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) { - unsigned int sum; + __sum16 sum; - sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); + sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev); - skb->ip_summed = CHECKSUM_UNNECESSARY; } + skb->csum_valid = !sum; + return sum; +} +EXPORT_SYMBOL(__skb_checksum_complete_head); + +__sum16 __skb_checksum_complete(struct sk_buff *skb) +{ + __wsum csum; + __sum16 sum; + + csum = skb_checksum(skb, 0, skb->len, 0); + + /* skb->csum holds pseudo checksum */ + sum = csum_fold(csum_add(skb->csum, csum)); + if (likely(!sum)) { + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) + netdev_rx_csum_fault(skb->dev); + } + + /* Save full packet checksum */ + skb->csum = csum; + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum_complete_sw = 1; + skb->csum_valid = !sum; + return sum; } EXPORT_SYMBOL(__skb_checksum_complete); @@ -405,7 +779,7 @@ EXPORT_SYMBOL(__skb_checksum_complete); * @skb: skbuff * @hlen: hardware length * @iov: io vector - * + * * Caller _must_ check that skb will fit to this iovec. * * Returns: 0 - success. @@ -416,9 +790,12 @@ EXPORT_SYMBOL(__skb_checksum_complete); int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen, struct iovec *iov) { - unsigned int csum; + __wsum csum; int chunk = skb->len - hlen; + if (!chunk) + return 0; + /* Skip filled elements. * Pretty silly, look at memcpy_toiovec, though 8) */ @@ -435,9 +812,9 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base, chunk, &csum)) goto fault; - if ((unsigned short)csum_fold(csum)) + if (csum_fold(csum)) goto csum_error; - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); iov->iov_len -= chunk; iov->iov_base += chunk; @@ -448,6 +825,7 @@ csum_error: fault: return -EFAULT; } +EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); /** * datagram_poll - generic datagram poll @@ -469,18 +847,21 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR; + mask |= POLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + + if (sk->sk_shutdown & RCV_SHUTDOWN) + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -500,9 +881,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, return mask; } - EXPORT_SYMBOL(datagram_poll); -EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); -EXPORT_SYMBOL(skb_copy_datagram_iovec); -EXPORT_SYMBOL(skb_free_datagram); -EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index fd070a098f2..367a586d0c8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -73,14 +73,15 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/capability.h> -#include <linux/config.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/hash.h> +#include <linux/slab.h> #include <linux/sched.h> +#include <linux/mutex.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> @@ -90,72 +91,75 @@ #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/ethtool.h> #include <linux/notifier.h> #include <linux/skbuff.h> +#include <net/net_namespace.h> #include <net/sock.h> #include <linux/rtnetlink.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> #include <linux/stat.h> -#include <linux/if_bridge.h> -#include <linux/divert.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> +#include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> -#include <linux/kmod.h> #include <linux/module.h> -#include <linux/kallsyms.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> -#ifdef CONFIG_NET_RADIO -#include <linux/wireless.h> /* Note : will define WIRELESS_EXT */ #include <net/iw_handler.h> -#endif /* CONFIG_NET_RADIO */ #include <asm/current.h> - -/* - * The list of packet types we will receive (as opposed to discard) - * and the routines to invoke. - * - * Why 16. Because with 16 the only overlap we get on a hash of the - * low nibble of the protocol value is RARP/SNAP/X.25. - * - * NOTE: That is no longer true with the addition of VLAN tags. Not - * sure which should go first, but I bet it won't make much - * difference if we are running VLANs. The good news is that - * this protocol won't be in the list unless compiled in, so - * the average user (w/out VLANs) will not be adversly affected. - * --BLG - * - * 0800 IP - * 8100 802.1Q VLAN - * 0001 802.3 - * 0002 AX.25 - * 0004 802.2 - * 8035 RARP - * 0005 SNAP - * 0805 X.25 - * 0806 ARP - * 8137 IPX - * 0009 Localtalk - * 86DD IPv6 - */ +#include <linux/audit.h> +#include <linux/dmaengine.h> +#include <linux/err.h> +#include <linux/ctype.h> +#include <linux/if_arp.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/jhash.h> +#include <linux/random.h> +#include <trace/events/napi.h> +#include <trace/events/net.h> +#include <trace/events/skb.h> +#include <linux/pci.h> +#include <linux/inetdevice.h> +#include <linux/cpu_rmap.h> +#include <linux/static_key.h> +#include <linux/hashtable.h> +#include <linux/vmalloc.h> +#include <linux/if_macvlan.h> + +#include "net-sysfs.h" + +/* Instead of increasing this, you should create a hash table. */ +#define MAX_GRO_SKBS 8 + +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(ptype_lock); -static struct list_head ptype_base[16]; /* 16 way hashed list */ -static struct list_head ptype_all; /* Taps */ +static DEFINE_SPINLOCK(offload_lock); +struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; +struct list_head ptype_all __read_mostly; /* Taps */ +static struct list_head offload_base __read_mostly; + +static int netif_rx_internal(struct sk_buff *skb); +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info); /* - * The @dev_base list is protected by @dev_base_lock and the rtln + * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. * - * Pure readers hold dev_base_lock for reading. + * Pure readers hold dev_base_lock for reading, or rcu_read_lock() * * Writers must hold the rtnl semaphore while they loop through the - * dev_base list, and hold dev_base_lock for writing when they do the + * dev_base_head list, and hold dev_base_lock for writing when they do the * actual updates. This allows pure readers to access the list even * while a writer is preparing to update it. * @@ -167,51 +171,178 @@ static struct list_head ptype_all; /* Taps */ * unregister_netdevice(), which must be called with the rtnl * semaphore held. */ -struct net_device *dev_base; -static struct net_device **dev_tail = &dev_base; DEFINE_RWLOCK(dev_base_lock); - -EXPORT_SYMBOL(dev_base); EXPORT_SYMBOL(dev_base_lock); -#define NETDEV_HASHBITS 8 -static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS]; -static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS]; +/* protects napi_hash addition/deletion and napi_gen_id */ +static DEFINE_SPINLOCK(napi_hash_lock); -static inline struct hlist_head *dev_name_hash(const char *name) +static unsigned int napi_gen_id; +static DEFINE_HASHTABLE(napi_hash, 8); + +static seqcount_t devnet_rename_seq; + +static inline void dev_base_seq_inc(struct net *net) { - unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); - return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)]; + while (++net->dev_base_seq == 0); } -static inline struct hlist_head *dev_index_hash(int ifindex) +static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { - return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)]; + unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; +} + +static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) +{ + return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; +} + +static inline void rps_lock(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + spin_lock(&sd->input_pkt_queue.lock); +#endif +} + +static inline void rps_unlock(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + spin_unlock(&sd->input_pkt_queue.lock); +#endif +} + +/* Device list insertion */ +static void list_netdevice(struct net_device *dev) +{ + struct net *net = dev_net(dev); + + ASSERT_RTNL(); + + write_lock_bh(&dev_base_lock); + list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + hlist_add_head_rcu(&dev->index_hlist, + dev_index_hash(net, dev->ifindex)); + write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(net); +} + +/* Device list removal + * caller must respect a RCU grace period before freeing/reusing dev + */ +static void unlist_netdevice(struct net_device *dev) +{ + ASSERT_RTNL(); + + /* Unlink dev from the device chain */ + write_lock_bh(&dev_base_lock); + list_del_rcu(&dev->dev_list); + hlist_del_rcu(&dev->name_hlist); + hlist_del_rcu(&dev->index_hlist); + write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(dev_net(dev)); } /* * Our notifier list */ -static struct notifier_block *netdev_chain; +static RAW_NOTIFIER_HEAD(netdev_chain); /* * Device drivers call our routines to queue packets here. We empty the * queue in the local softnet handler. */ -DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL }; -#ifdef CONFIG_SYSFS -extern int netdev_sysfs_init(void); -extern int netdev_register_sysfs(struct net_device *); -extern void netdev_unregister_sysfs(struct net_device *); +DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +EXPORT_PER_CPU_SYMBOL(softnet_data); + +#ifdef CONFIG_LOCKDEP +/* + * register_netdevice() inits txq->_xmit_lock and sets lockdep class + * according to dev->type + */ +static const unsigned short netdev_lock_type[] = + {ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, + ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, + ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, + ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, + ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, + ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, + ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, + ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, + ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, + ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, + ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, + ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, + ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, + ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, + ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; + +static const char *const netdev_lock_name[] = + {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", + "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", + "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", + "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", + "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", + "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", + "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", + "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", + "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", + "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", + "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", + "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; + +static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; +static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; + +static inline unsigned short netdev_lock_pos(unsigned short dev_type) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) + if (netdev_lock_type[i] == dev_type) + return i; + /* the last key is used by default */ + return ARRAY_SIZE(netdev_lock_type) - 1; +} + +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) +{ + int i; + + i = netdev_lock_pos(dev_type); + lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], + netdev_lock_name[i]); +} + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ + int i; + + i = netdev_lock_pos(dev->type); + lockdep_set_class_and_name(&dev->addr_list_lock, + &netdev_addr_lock_key[i], + netdev_lock_name[i]); +} #else -#define netdev_sysfs_init() (0) -#define netdev_register_sysfs(dev) (0) -#define netdev_unregister_sysfs(dev) do { } while(0) +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) +{ +} +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ +} #endif - /******************************************************************************* Protocol management and registration routines @@ -219,12 +350,6 @@ extern void netdev_unregister_sysfs(struct net_device *); *******************************************************************************/ /* - * For efficiency - */ - -int netdev_nit; - -/* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. @@ -240,6 +365,14 @@ int netdev_nit; * --ANK (980803) */ +static inline struct list_head *ptype_head(const struct packet_type *pt) +{ + if (pt->type == htons(ETH_P_ALL)) + return &ptype_all; + else + return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; +} + /** * dev_add_pack - add packet handler * @pt: packet type declaration @@ -248,25 +381,20 @@ int netdev_nit; * is linked into kernel lists and may not be freed until it has been * removed from the kernel lists. * - * This call does not sleep therefore it can not + * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new packet type (until the next received packet). */ void dev_add_pack(struct packet_type *pt) { - int hash; + struct list_head *head = ptype_head(pt); - spin_lock_bh(&ptype_lock); - if (pt->type == htons(ETH_P_ALL)) { - netdev_nit++; - list_add_rcu(&pt->list, &ptype_all); - } else { - hash = ntohs(pt->type) & 15; - list_add_rcu(&pt->list, &ptype_base[hash]); - } - spin_unlock_bh(&ptype_lock); + spin_lock(&ptype_lock); + list_add_rcu(&pt->list, head); + spin_unlock(&ptype_lock); } +EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler @@ -275,7 +403,7 @@ void dev_add_pack(struct packet_type *pt) * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function - * returns. + * returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone @@ -283,16 +411,10 @@ void dev_add_pack(struct packet_type *pt) */ void __dev_remove_pack(struct packet_type *pt) { - struct list_head *head; + struct list_head *head = ptype_head(pt); struct packet_type *pt1; - spin_lock_bh(&ptype_lock); - - if (pt->type == htons(ETH_P_ALL)) { - netdev_nit--; - head = &ptype_all; - } else - head = &ptype_base[ntohs(pt->type) & 15]; + spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { @@ -301,10 +423,12 @@ void __dev_remove_pack(struct packet_type *pt) } } - printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); + pr_warn("dev_remove_pack: %p not found\n", pt); out: - spin_unlock_bh(&ptype_lock); + spin_unlock(&ptype_lock); } +EXPORT_SYMBOL(__dev_remove_pack); + /** * dev_remove_pack - remove packet handler * @pt: packet type declaration @@ -320,9 +444,85 @@ out: void dev_remove_pack(struct packet_type *pt) { __dev_remove_pack(pt); - + synchronize_net(); } +EXPORT_SYMBOL(dev_remove_pack); + + +/** + * dev_add_offload - register offload handlers + * @po: protocol offload declaration + * + * Add protocol offload handlers to the networking stack. The passed + * &proto_offload is linked into kernel lists and may not be freed until + * it has been removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new offload handlers (until the next received packet). + */ +void dev_add_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + + spin_lock(&offload_lock); + list_add_rcu(&po->list, head); + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(dev_add_offload); + +/** + * __dev_remove_offload - remove offload handler + * @po: packet offload declaration + * + * Remove a protocol offload handler that was previously added to the + * kernel offload handlers by dev_add_offload(). The passed &offload_type + * is removed from the kernel lists and can be freed or reused once this + * function returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +static void __dev_remove_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + struct packet_offload *po1; + + spin_lock(&offload_lock); + + list_for_each_entry(po1, head, list) { + if (po == po1) { + list_del_rcu(&po->list); + goto out; + } + } + + pr_warn("dev_remove_offload: %p not found\n", po); +out: + spin_unlock(&offload_lock); +} + +/** + * dev_remove_offload - remove packet offload handler + * @po: packet offload declaration + * + * Remove a packet offload handler that was previously added to the kernel + * offload handlers by dev_add_offload(). The passed &offload_type is + * removed from the kernel lists and can be freed or reused once this + * function returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_offload(struct packet_offload *po) +{ + __dev_remove_offload(po); + + synchronize_net(); +} +EXPORT_SYMBOL(dev_remove_offload); /****************************************************************************** @@ -351,7 +551,7 @@ static int netdev_boot_setup_add(char *name, struct ifmap *map) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { memset(s[i].name, 0, sizeof(s[i].name)); - strcpy(s[i].name, name); + strlcpy(s[i].name, name, IFNAMSIZ); memcpy(&s[i].map, map, sizeof(s[i].map)); break; } @@ -376,7 +576,7 @@ int netdev_boot_setup_check(struct net_device *dev) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && - !strncmp(dev->name, s[i].name, strlen(s[i].name))) { + !strcmp(dev->name, s[i].name)) { dev->irq = s[i].map.irq; dev->base_addr = s[i].map.base_addr; dev->mem_start = s[i].map.mem_start; @@ -386,6 +586,7 @@ int netdev_boot_setup_check(struct net_device *dev) } return 0; } +EXPORT_SYMBOL(netdev_boot_setup_check); /** @@ -410,7 +611,7 @@ unsigned long netdev_boot_base(const char *prefix, int unit) * If device already registered then return base of 1 * to indicate not to probe for this interface */ - if (__dev_get_by_name(name)) + if (__dev_get_by_name(&init_net, name)) return 1; for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) @@ -456,6 +657,7 @@ __setup("netdev=", netdev_boot_setup); /** * __dev_get_by_name - find a device by its name + * @net: the applicable net namespace * @name: name to find * * Find an interface by name. Must be called under RTNL semaphore @@ -465,21 +667,47 @@ __setup("netdev=", netdev_boot_setup); * careful with locks. */ -struct net_device *__dev_get_by_name(const char *name) +struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each(p, dev_name_hash(name)) { - struct net_device *dev - = hlist_entry(p, struct net_device, name_hlist); + hlist_for_each_entry(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; - } + + return NULL; +} +EXPORT_SYMBOL(__dev_get_by_name); + +/** + * dev_get_by_name_rcu - find a device by its name + * @net: the applicable net namespace + * @name: name to find + * + * Find an interface by name. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) +{ + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); + + hlist_for_each_entry_rcu(dev, head, name_hlist) + if (!strncmp(dev->name, name, IFNAMSIZ)) + return dev; + return NULL; } +EXPORT_SYMBOL(dev_get_by_name_rcu); /** * dev_get_by_name - find a device by its name + * @net: the applicable net namespace * @name: name to find * * Find an interface by name. This can be called from any @@ -489,20 +717,22 @@ struct net_device *__dev_get_by_name(const char *name) * matching device is found. */ -struct net_device *dev_get_by_name(const char *name) +struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(name); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } +EXPORT_SYMBOL(dev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex + * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device @@ -512,22 +742,47 @@ struct net_device *dev_get_by_name(const char *name) * or @dev_base_lock. */ -struct net_device *__dev_get_by_index(int ifindex) +struct net_device *__dev_get_by_index(struct net *net, int ifindex) { - struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each(p, dev_index_hash(ifindex)) { - struct net_device *dev - = hlist_entry(p, struct net_device, index_hlist); + hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; - } + + return NULL; +} +EXPORT_SYMBOL(__dev_get_by_index); + +/** + * dev_get_by_index_rcu - find a device by its ifindex + * @net: the applicable net namespace + * @ifindex: index of device + * + * Search for an interface by index. Returns %NULL if the device + * is not found or a pointer to the device. The device has not + * had its reference counter increased so the caller must be careful + * about locking. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) +{ + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); + + hlist_for_each_entry_rcu(dev, head, index_hlist) + if (dev->ifindex == ifindex) + return dev; + return NULL; } +EXPORT_SYMBOL(dev_get_by_index_rcu); /** * dev_get_by_index - find a device by its ifindex + * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns NULL if the device @@ -536,124 +791,184 @@ struct net_device *__dev_get_by_index(int ifindex) * dev_put to indicate they have finished with it. */ -struct net_device *dev_get_by_index(int ifindex) +struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } +EXPORT_SYMBOL(dev_get_by_index); /** - * dev_getbyhwaddr - find a device by its hardware address + * netdev_get_name - get a netdevice name, knowing its ifindex. + * @net: network namespace + * @name: a pointer to the buffer where the name will be stored. + * @ifindex: the ifindex of the interface to get the name from. + * + * The use of raw_seqcount_begin() and cond_resched() before + * retrying is required as we want to give the writers a chance + * to complete when CONFIG_PREEMPT is not set. + */ +int netdev_get_name(struct net *net, char *name, int ifindex) +{ + struct net_device *dev; + unsigned int seq; + +retry: + seq = raw_seqcount_begin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { + cond_resched(); + goto retry; + } + + return 0; +} + +/** + * dev_getbyhwaddr_rcu - find a device by its hardware address + * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold the - * rtnl semaphore. The returned device has not had its ref count increased + * is not found or a pointer to the device. + * The caller must hold RCU or RTNL. + * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * - * BUGS: - * If the API was consistent this would be __dev_get_by_hwaddr */ -struct net_device *dev_getbyhwaddr(unsigned short type, char *ha) +struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *ha) { struct net_device *dev; - ASSERT_RTNL(); - - for (dev = dev_base; dev; dev = dev->next) + for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) - break; - return dev; -} + return dev; -EXPORT_SYMBOL(dev_getbyhwaddr); + return NULL; +} +EXPORT_SYMBOL(dev_getbyhwaddr_rcu); -struct net_device *dev_getfirstbyhwtype(unsigned short type) +struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev; - rtnl_lock(); - for (dev = dev_base; dev; dev = dev->next) { + ASSERT_RTNL(); + for_each_netdev(net, dev) + if (dev->type == type) + return dev; + + return NULL; +} +EXPORT_SYMBOL(__dev_getfirstbyhwtype); + +struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) +{ + struct net_device *dev, *ret = NULL; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) if (dev->type == type) { dev_hold(dev); + ret = dev; break; } - } - rtnl_unlock(); - return dev; + rcu_read_unlock(); + return ret; } - EXPORT_SYMBOL(dev_getfirstbyhwtype); /** - * dev_get_by_flags - find any device with given flags + * dev_get_by_flags_rcu - find any device with given flags + * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device - * is not found or a pointer to the device. The device returned has - * had a reference added and the pointer is safe until the user calls - * dev_put to indicate they have finished with it. + * is not found or a pointer to the device. Must be called inside + * rcu_read_lock(), and result refcount is unchanged. */ -struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mask) +struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags, + unsigned short mask) { - struct net_device *dev; + struct net_device *dev, *ret; - read_lock(&dev_base_lock); - for (dev = dev_base; dev != NULL; dev = dev->next) { + ret = NULL; + for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { - dev_hold(dev); + ret = dev; break; } } - read_unlock(&dev_base_lock); - return dev; + return ret; } +EXPORT_SYMBOL(dev_get_by_flags_rcu); /** * dev_valid_name - check if name is okay for network device * @name: name string * * Network device names need to be valid file names to - * to allow sysfs to work + * to allow sysfs to work. We also disallow any kind of + * whitespace. */ -int dev_valid_name(const char *name) +bool dev_valid_name(const char *name) { - return !(*name == '\0' - || !strcmp(name, ".") - || !strcmp(name, "..") - || strchr(name, '/')); + if (*name == '\0') + return false; + if (strlen(name) >= IFNAMSIZ) + return false; + if (!strcmp(name, ".") || !strcmp(name, "..")) + return false; + + while (*name) { + if (*name == '/' || isspace(*name)) + return false; + name++; + } + return true; } +EXPORT_SYMBOL(dev_valid_name); /** - * dev_alloc_name - allocate a name for a device - * @dev: device + * __dev_alloc_name - allocate a name for a device + * @net: network namespace to allocate the device name in * @name: name format string + * @buf: scratch buffer and result name string * * Passed a format string - eg "lt%d" it will try and find a suitable - * id. Not efficient for many devices, not called a lot. The caller - * must hold the dev_base or rtnl lock while allocating the name and - * adding the device in order to avoid duplicates. Returns the number - * of the unit assigned or a negative errno code. + * id. It scans list of devices to build up a free map, then chooses + * the first empty slot. The caller must hold the dev_base or rtnl lock + * while allocating the name and adding the device in order to avoid + * duplicates. + * Limited to bits_per_byte * page size devices (ie 32K on most platforms). + * Returns the number of the unit assigned or a negative errno code. */ -int dev_alloc_name(struct net_device *dev, const char *name) +static int __dev_alloc_name(struct net *net, const char *name, char *buf) { int i = 0; - char buf[IFNAMSIZ]; const char *p; const int max_netdevices = 8*PAGE_SIZE; - long *inuse; + unsigned long *inuse; struct net_device *d; p = strnchr(name, IFNAMSIZ-1, '%'); @@ -667,18 +982,18 @@ int dev_alloc_name(struct net_device *dev, const char *name) return -EINVAL; /* Use one page as a bit array of possible slots */ - inuse = (long *) get_zeroed_page(GFP_ATOMIC); + inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC); if (!inuse) return -ENOMEM; - for (d = dev_base; d; d = d->next) { + for_each_netdev(net, d) { if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ - snprintf(buf, sizeof(buf), name, i); + snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) set_bit(i, inuse); } @@ -687,11 +1002,10 @@ int dev_alloc_name(struct net_device *dev, const char *name) free_page((unsigned long) inuse); } - snprintf(buf, sizeof(buf), name, i); - if (!__dev_get_by_name(buf)) { - strlcpy(dev->name, buf, IFNAMSIZ); + if (buf != name) + snprintf(buf, IFNAMSIZ, name, i); + if (!__dev_get_by_name(net, buf)) return i; - } /* It is possible to run out of possible slots * when the name is long and there isn't enough space left @@ -700,6 +1014,66 @@ int dev_alloc_name(struct net_device *dev, const char *name) return -ENFILE; } +/** + * dev_alloc_name - allocate a name for a device + * @dev: device + * @name: name format string + * + * Passed a format string - eg "lt%d" it will try and find a suitable + * id. It scans list of devices to build up a free map, then chooses + * the first empty slot. The caller must hold the dev_base or rtnl lock + * while allocating the name and adding the device in order to avoid + * duplicates. + * Limited to bits_per_byte * page size devices (ie 32K on most platforms). + * Returns the number of the unit assigned or a negative errno code. + */ + +int dev_alloc_name(struct net_device *dev, const char *name) +{ + char buf[IFNAMSIZ]; + struct net *net; + int ret; + + BUG_ON(!dev_net(dev)); + net = dev_net(dev); + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; +} +EXPORT_SYMBOL(dev_alloc_name); + +static int dev_alloc_name_ns(struct net *net, + struct net_device *dev, + const char *name) +{ + char buf[IFNAMSIZ]; + int ret; + + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; +} + +static int dev_get_valid_name(struct net *net, + struct net_device *dev, + const char *name) +{ + BUG_ON(!net); + + if (!dev_valid_name(name)) + return -EINVAL; + + if (strchr(name, '%')) + return dev_alloc_name_ns(net, dev, name); + else if (__dev_get_by_name(net, name)) + return -EEXIST; + else if (dev->name != name) + strlcpy(dev->name, name, IFNAMSIZ); + + return 0; +} /** * dev_change_name - change name of a device @@ -709,48 +1083,119 @@ int dev_alloc_name(struct net_device *dev, const char *name) * Change name of a device, can pass format strings "eth%d". * for wildcarding. */ -int dev_change_name(struct net_device *dev, char *newname) +int dev_change_name(struct net_device *dev, const char *newname) { + char oldname[IFNAMSIZ]; int err = 0; + int ret; + struct net *net; ASSERT_RTNL(); + BUG_ON(!dev_net(dev)); + net = dev_net(dev); if (dev->flags & IFF_UP) return -EBUSY; - if (!dev_valid_name(newname)) - return -EINVAL; + write_seqcount_begin(&devnet_rename_seq); - if (strchr(newname, '%')) { - err = dev_alloc_name(dev, newname); - if (err < 0) - return err; - strcpy(newname, dev->name); + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { + write_seqcount_end(&devnet_rename_seq); + return 0; } - else if (__dev_get_by_name(newname)) - return -EEXIST; - else - strlcpy(dev->name, newname, IFNAMSIZ); - err = class_device_rename(&dev->class_dev, dev->name); - if (!err) { - hlist_del(&dev->name_hlist); - hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name)); - notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev); + memcpy(oldname, dev->name, IFNAMSIZ); + + err = dev_get_valid_name(net, dev, newname); + if (err < 0) { + write_seqcount_end(&devnet_rename_seq); + return err; + } + +rollback: + ret = device_rename(&dev->dev, dev->name); + if (ret) { + memcpy(dev->name, oldname, IFNAMSIZ); + write_seqcount_end(&devnet_rename_seq); + return ret; + } + + write_seqcount_end(&devnet_rename_seq); + + netdev_adjacent_rename_links(dev, oldname); + + write_lock_bh(&dev_base_lock); + hlist_del_rcu(&dev->name_hlist); + write_unlock_bh(&dev_base_lock); + + synchronize_rcu(); + + write_lock_bh(&dev_base_lock); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + write_unlock_bh(&dev_base_lock); + + ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); + ret = notifier_to_errno(ret); + + if (ret) { + /* err >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { + err = ret; + write_seqcount_begin(&devnet_rename_seq); + memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); + goto rollback; + } else { + pr_err("%s: name change rollback failed: %d\n", + dev->name, ret); + } } return err; } /** - * netdev_features_change - device changes fatures + * dev_set_alias - change ifalias of a device + * @dev: device + * @alias: name up to IFALIASZ + * @len: limit of bytes to copy from info + * + * Set ifalias for a device, + */ +int dev_set_alias(struct net_device *dev, const char *alias, size_t len) +{ + char *new_ifalias; + + ASSERT_RTNL(); + + if (len >= IFALIASZ) + return -EINVAL; + + if (!len) { + kfree(dev->ifalias); + dev->ifalias = NULL; + return 0; + } + + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) + return -ENOMEM; + dev->ifalias = new_ifalias; + + strlcpy(dev->ifalias, alias, len+1); + return len; +} + + +/** + * netdev_features_change - device changes features * @dev: device to cause notification * * Called to indicate a device has changed features. */ void netdev_features_change(struct net_device *dev) { - notifier_call_chain(&netdev_chain, NETDEV_FEAT_CHANGE, dev); + call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev); } EXPORT_SYMBOL(netdev_features_change); @@ -765,40 +1210,77 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = 0; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } +EXPORT_SYMBOL(netdev_state_change); /** - * dev_load - load a network module - * @name: name of interface + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device * - * If a network interface is not present and the process has suitable - * privileges this function loads the module. If module loading is not - * available in this kernel then it becomes a nop. + * Generate traffic such that interested network peers are aware of + * @dev, such as by generating a gratuitous ARP. This may be used when + * a device wants to inform the rest of the network about some sort of + * reconfiguration such as a failover event or virtual machine + * migration. */ +void netdev_notify_peers(struct net_device *dev) +{ + rtnl_lock(); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + rtnl_unlock(); +} +EXPORT_SYMBOL(netdev_notify_peers); -void dev_load(const char *name) +static int __dev_open(struct net_device *dev) { - struct net_device *dev; + const struct net_device_ops *ops = dev->netdev_ops; + int ret; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(name); - read_unlock(&dev_base_lock); + ASSERT_RTNL(); - if (!dev && capable(CAP_SYS_MODULE)) - request_module("%s", name); -} + if (!netif_device_present(dev)) + return -ENODEV; -static int default_rebuild_header(struct sk_buff *skb) -{ - printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n", - skb->dev ? skb->dev->name : "NULL!!!"); - kfree_skb(skb); - return 1; -} + /* Block netpoll from trying to do any rx path servicing. + * 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_poll_disable(dev); + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); + ret = notifier_to_errno(ret); + if (ret) + return ret; + + set_bit(__LINK_STATE_START, &dev->state); + + if (ops->ndo_validate_addr) + ret = ops->ndo_validate_addr(dev); + + if (!ret && ops->ndo_open) + ret = ops->ndo_open(dev); + + netpoll_poll_enable(dev); + + if (ret) + clear_bit(__LINK_STATE_START, &dev->state); + else { + dev->flags |= IFF_UP; + net_dmaengine_get(); + dev_set_rx_mode(dev); + dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); + } + + return ret; +} /** * dev_open - prepare an interface for use. @@ -814,57 +1296,99 @@ static int default_rebuild_header(struct sk_buff *skb) */ int dev_open(struct net_device *dev) { - int ret = 0; - - /* - * Is it already up? - */ + int ret; if (dev->flags & IFF_UP) return 0; - /* - * Is it even present? - */ - if (!netif_device_present(dev)) - return -ENODEV; + ret = __dev_open(dev); + if (ret < 0) + return ret; - /* - * Call device private open method - */ - set_bit(__LINK_STATE_START, &dev->state); - if (dev->open) { - ret = dev->open(dev); - if (ret) - clear_bit(__LINK_STATE_START, &dev->state); - } + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + call_netdevice_notifiers(NETDEV_UP, dev); - /* - * If it went open OK then: - */ + return ret; +} +EXPORT_SYMBOL(dev_open); - if (!ret) { - /* - * Set the flags. - */ - dev->flags |= IFF_UP; +static int __dev_close_many(struct list_head *head) +{ + struct net_device *dev; - /* - * Initialize multicasting status - */ - dev_mc_upload(dev); + ASSERT_RTNL(); + might_sleep(); - /* - * Wakeup transmit queue engine + 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); + + /* Synchronize to scheduled poll. We cannot touch poll list, it + * can be even on different cpu. So just clear netif_running(). + * + * dev->stop() will invoke napi_disable() on all of it's + * napi_struct instances on this device. */ - dev_activate(dev); + smp_mb__after_atomic(); /* Commit netif_running(). */ + } + + dev_deactivate_many(head); + + list_for_each_entry(dev, head, close_list) { + const struct net_device_ops *ops = dev->netdev_ops; /* - * ... and announce new interface. + * Call the device specific close. This cannot fail. + * Only if device is UP + * + * We allow it to be called even after a DETACH hot-plug + * event. */ - notifier_call_chain(&netdev_chain, NETDEV_UP, dev); + if (ops->ndo_stop) + ops->ndo_stop(dev); + + dev->flags &= ~IFF_UP; + net_dmaengine_put(); + netpoll_poll_enable(dev); } - return ret; + + return 0; +} + +static int __dev_close(struct net_device *dev) +{ + int retval; + LIST_HEAD(single); + + list_add(&dev->close_list, &single); + retval = __dev_close_many(&single); + list_del(&single); + + return retval; +} + +static int dev_close_many(struct list_head *head) +{ + struct net_device *dev, *tmp; + + /* Remove the devices that don't need to be closed */ + list_for_each_entry_safe(dev, tmp, head, close_list) + if (!(dev->flags & IFF_UP)) + list_del_init(&dev->close_list); + + __dev_close_many(head); + + list_for_each_entry_safe(dev, tmp, head, close_list) { + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + call_netdevice_notifiers(NETDEV_DOWN, dev); + list_del_init(&dev->close_list); + } + + return 0; } /** @@ -878,60 +1402,57 @@ int dev_open(struct net_device *dev) */ int dev_close(struct net_device *dev) { - if (!(dev->flags & IFF_UP)) - return 0; - - /* - * Tell people we are going down, so that they can - * prepare to death, when device is still operating. - */ - notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev); - - dev_deactivate(dev); - - clear_bit(__LINK_STATE_START, &dev->state); - - /* Synchronize to scheduled poll. We cannot touch poll list, - * it can be even on different cpu. So just clear netif_running(), - * and wait when poll really will happen. Actually, the best place - * for this is inside dev->stop() after device stopped its irq - * engine, but this requires more changes in devices. */ + if (dev->flags & IFF_UP) { + LIST_HEAD(single); - smp_mb__after_clear_bit(); /* Commit netif_running(). */ - while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) { - /* No hurry. */ - msleep(1); + list_add(&dev->close_list, &single); + dev_close_many(&single); + list_del(&single); } + return 0; +} +EXPORT_SYMBOL(dev_close); - /* - * Call the device specific close. This cannot fail. - * Only if device is UP - * - * We allow it to be called even after a DETACH hot-plug - * event. - */ - if (dev->stop) - dev->stop(dev); +/** + * dev_disable_lro - disable Large Receive Offload on a device + * @dev: device + * + * Disable Large Receive Offload (LRO) on a net device. Must be + * called under RTNL. This is needed if received packets may be + * forwarded to another interface. + */ +void dev_disable_lro(struct net_device *dev) +{ /* - * Device is now down. + * If we're trying to disable lro on a vlan device + * use the underlying physical device instead */ + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); - dev->flags &= ~IFF_UP; + /* the same for macvlan devices */ + if (netif_is_macvlan(dev)) + dev = macvlan_dev_real_dev(dev); - /* - * Tell people we are down - */ - notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev); + dev->wanted_features &= ~NETIF_F_LRO; + netdev_update_features(dev); - return 0; + if (unlikely(dev->features & NETIF_F_LRO)) + netdev_WARN(dev, "failed to disable LRO!\n"); } +EXPORT_SYMBOL(dev_disable_lro); +static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, + struct net_device *dev) +{ + struct netdev_notifier_info info; -/* - * Device change register/unregister. These are not inline or static - * as we export them to the world. - */ + netdev_notifier_info_init(&info, dev); + return nb->notifier_call(nb, val, &info); +} + +static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block @@ -943,28 +1464,62 @@ int dev_close(struct net_device *dev) * is returned on a failure. * * When registered all registration and up events are replayed - * to the new notifier to allow device to have a race free + * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) { struct net_device *dev; + struct net_device *last; + struct net *net; int err; rtnl_lock(); - err = notifier_chain_register(&netdev_chain, nb); - if (!err) { - for (dev = dev_base; dev; dev = dev->next) { - nb->notifier_call(nb, NETDEV_REGISTER, dev); + err = raw_notifier_chain_register(&netdev_chain, nb); + if (err) + goto unlock; + if (dev_boot_phase) + goto unlock; + for_each_net(net) { + for_each_netdev(net, dev) { + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); + err = notifier_to_errno(err); + if (err) + goto rollback; - if (dev->flags & IFF_UP) - nb->notifier_call(nb, NETDEV_UP, dev); + if (!(dev->flags & IFF_UP)) + continue; + + call_netdevice_notifier(nb, NETDEV_UP, dev); } } + +unlock: rtnl_unlock(); return err; + +rollback: + last = dev; + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev == last) + goto outroll; + + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); + } + } + +outroll: + raw_notifier_chain_unregister(&netdev_chain, nb); + goto unlock; } +EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block @@ -974,57 +1529,213 @@ int register_netdevice_notifier(struct notifier_block *nb) * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { - return notifier_chain_unregister(&netdev_chain, nb); + struct net_device *dev; + struct net *net; + int err; + + rtnl_lock(); + err = raw_notifier_chain_unregister(&netdev_chain, nb); + if (err) + goto unlock; + + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); + } + } +unlock: + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier); + +/** + * call_netdevice_notifiers_info - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @info: notifier information data + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ + +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info) +{ + ASSERT_RTNL(); + netdev_notifier_info_init(info, dev); + return raw_notifier_call_chain(&netdev_chain, val, info); } /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function - * @v: pointer passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function * * Call all network notifier blocks. Parameters and return value - * are as for notifier_call_chain(). + * are as for raw_notifier_call_chain(). */ -int call_netdevice_notifiers(unsigned long val, void *v) +int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - return notifier_call_chain(&netdev_chain, val, v); + struct netdev_notifier_info info; + + return call_netdevice_notifiers_info(val, dev, &info); } +EXPORT_SYMBOL(call_netdevice_notifiers); -/* When > 0 there are consumers of rx skb time stamps */ -static atomic_t netstamp_needed = ATOMIC_INIT(0); +static struct static_key netstamp_needed __read_mostly; +#ifdef HAVE_JUMP_LABEL +/* We are not allowed to call static_key_slow_dec() from irq context + * If net_disable_timestamp() is called from irq context, defer the + * static_key_slow_dec() calls. + */ +static atomic_t netstamp_needed_deferred; +#endif void net_enable_timestamp(void) { - atomic_inc(&netstamp_needed); +#ifdef HAVE_JUMP_LABEL + int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + + if (deferred) { + while (--deferred) + static_key_slow_dec(&netstamp_needed); + return; + } +#endif + static_key_slow_inc(&netstamp_needed); } +EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { - atomic_dec(&netstamp_needed); +#ifdef HAVE_JUMP_LABEL + if (in_interrupt()) { + atomic_inc(&netstamp_needed_deferred); + return; + } +#endif + static_key_slow_dec(&netstamp_needed); } +EXPORT_SYMBOL(net_disable_timestamp); -void __net_timestamp(struct sk_buff *skb) +static inline void net_timestamp_set(struct sk_buff *skb) { - struct timeval tv; + skb->tstamp.tv64 = 0; + if (static_key_false(&netstamp_needed)) + __net_timestamp(skb); +} + +#define net_timestamp_check(COND, SKB) \ + if (static_key_false(&netstamp_needed)) { \ + if ((COND) && !(SKB)->tstamp.tv64) \ + __net_timestamp(SKB); \ + } \ - do_gettimeofday(&tv); - skb_set_timestamp(skb, &tv); +bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) +{ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + len = dev->mtu + dev->hard_header_len + VLAN_HLEN; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; } -EXPORT_SYMBOL(__net_timestamp); +EXPORT_SYMBOL_GPL(is_skb_forwardable); -static inline void net_timestamp(struct sk_buff *skb) +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - if (atomic_read(&netstamp_needed)) - __net_timestamp(skb); - else { - skb->tstamp.off_sec = 0; - skb->tstamp.off_usec = 0; + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, GFP_ATOMIC)) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } } + + if (unlikely(!is_skb_forwardable(dev, skb))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); + + return 0; +} +EXPORT_SYMBOL_GPL(__dev_forward_skb); + +/** + * dev_forward_skb - loopback an skb to another netif + * + * @dev: destination network device + * @skb: buffer to forward + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped, but freed) + * + * dev_forward_skb can be used for injecting an skb from the + * start_xmit function of one device into the receive queue + * of another device. + * + * The receiving device may be in another namespace, so + * we have to clear all information in the skb that could + * impact namespace isolation. + */ +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); + +static inline int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) +{ + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + return -ENOMEM; + atomic_inc(&skb->users); + return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); +} + +static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) +{ + if (!ptype->af_packet_priv || !skb->sk) + return false; + + if (ptype->id_match) + return ptype->id_match(ptype, skb->sk); + else if ((struct sock *)ptype->af_packet_priv == skb->sk) + return true; + + return false; } /* @@ -1032,11 +1743,11 @@ static inline void net_timestamp(struct sk_buff *skb) * taps currently in use. */ -void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) +static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; - - net_timestamp(skb); + struct sk_buff *skb2 = NULL; + struct packet_type *pt_prev = NULL; rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -1044,179 +1755,1086 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * they originated from - MvS (miquels@drinkel.ow.org) */ if ((ptype->dev == dev || !ptype->dev) && - (ptype->af_packet_priv == NULL || - (struct sock *)ptype->af_packet_priv != skb->sk)) { - struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC); + (!skb_loop_sk(ptype, skb))) { + if (pt_prev) { + deliver_skb(skb2, pt_prev, skb->dev); + pt_prev = ptype; + continue; + } + + skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) break; + net_timestamp_set(skb2); + /* skb->nh should be correctly set by sender, so that the second statement is just protection against buggy protocols. */ - skb2->mac.raw = skb2->data; - - if (skb2->nh.raw < skb2->data || - skb2->nh.raw > skb2->tail) { - if (net_ratelimit()) - printk(KERN_CRIT "protocol %04x is " - "buggy, dev %s\n", - skb2->protocol, dev->name); - skb2->nh.raw = skb2->data; + skb_reset_mac_header(skb2); + + if (skb_network_header(skb2) < skb2->data || + skb_network_header(skb2) > skb_tail_pointer(skb2)) { + net_crit_ratelimited("protocol %04x is buggy, dev %s\n", + ntohs(skb2->protocol), + dev->name); + skb_reset_network_header(skb2); } - skb2->h.raw = skb2->nh.raw; + skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; - ptype->func(skb2, skb->dev, ptype, skb->dev); + pt_prev = ptype; } } + if (pt_prev) + pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); rcu_read_unlock(); } +/** + * netif_setup_tc - Handle tc mappings on real_num_tx_queues change + * @dev: Network device + * @txq: number of queues available + * + * If real_num_tx_queues is changed the tc mappings may no longer be + * valid. To resolve this verify the tc mapping remains valid and if + * not NULL the mapping. With no priorities mapping to this + * offset/count pair it will no longer be used. In the worst case TC0 + * is invalid nothing can be done so disable priority mappings. If is + * expected that drivers will fix this mapping if they can before + * calling netif_set_real_num_tx_queues. + */ +static void netif_setup_tc(struct net_device *dev, unsigned int txq) +{ + int i; + struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; + + /* If TC0 is invalidated disable TC mapping */ + if (tc->offset + tc->count > txq) { + pr_warn("Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); + dev->num_tc = 0; + return; + } + + /* Invalidated prio to tc mappings set to TC0 */ + for (i = 1; i < TC_BITMASK + 1; i++) { + int q = netdev_get_prio_tc_map(dev, i); + + tc = &dev->tc_to_txq[q]; + if (tc->offset + tc->count > txq) { + pr_warn("Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", + i, q); + netdev_set_prio_tc_map(dev, i, 0); + } + } +} + +#ifdef CONFIG_XPS +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, + int cpu, u16 index) +{ + struct xps_map *map = NULL; + int pos; + + if (dev_maps) + map = xmap_dereference(dev_maps->cpu_map[cpu]); + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] == index) { + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; + } else { + RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); + kfree_rcu(map, rcu); + map = NULL; + } + break; + } + } + + return map; +} + +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + int cpu, i; + bool active = false; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(cpu) { + for (i = index; i < dev->num_tx_queues; i++) { + if (!remove_xps_queue(dev_maps, cpu, i)) + break; + } + if (i == dev->num_tx_queues) + active = true; + } + + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + + for (i = index; i < dev->num_tx_queues; i++) + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + +out_no_maps: + mutex_unlock(&xps_map_mutex); +} + +static struct xps_map *expand_xps_map(struct xps_map *map, + int cpu, u16 index) +{ + struct xps_map *new_map; + int alloc_len = XPS_MIN_MAP_ALLOC; + int i, pos; + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] != index) + continue; + return map; + } + + /* Need to add queue to this CPU's existing map */ + if (map) { + if (pos < map->alloc_len) + return map; + + alloc_len = map->alloc_len * 2; + } + + /* Need to allocate new map to store queue on this CPU's map */ + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + return NULL; + + for (i = 0; i < pos; i++) + new_map->queues[i] = map->queues[i]; + new_map->alloc_len = alloc_len; + new_map->len = pos; + + return new_map; +} + +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) +{ + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + struct xps_map *map, *new_map; + int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); + int cpu, numa_node_id = -2; + bool active = false; + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + /* allocate memory for queue storage */ + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, mask)) + continue; + + if (!new_dev_maps) + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) { + mutex_unlock(&xps_map_mutex); + return -ENOMEM; + } + + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + + map = expand_xps_map(map, cpu, index); + if (!map) + goto error; + + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + if (!new_dev_maps) + goto out_no_new_maps; + + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { + /* add queue to CPU maps */ + int pos = 0; + + map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + while ((pos < map->len) && (map->queues[pos] != index)) + pos++; + + if (pos == map->len) + map->queues[map->len++] = index; +#ifdef CONFIG_NUMA + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; +#endif + } else if (dev_maps) { + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->cpu_map[cpu]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + } + + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + + /* Cleanup old maps */ + if (dev_maps) { + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (map && map != new_map) + kfree_rcu(map, rcu); + } + + kfree_rcu(dev_maps, rcu); + } + + dev_maps = new_dev_maps; + active = true; + +out_no_new_maps: + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? numa_node_id : + NUMA_NO_NODE); + + if (!dev_maps) + goto out_no_maps; + + /* removes queue from unused CPUs */ + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) + continue; + + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + /* free map if not active */ + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: + mutex_unlock(&xps_map_mutex); + + return 0; +error: + /* remove any maps that we added */ + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } + + mutex_unlock(&xps_map_mutex); + + kfree(new_dev_maps); + return -ENOMEM; +} +EXPORT_SYMBOL(netif_set_xps_queue); + +#endif +/* + * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues + * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. + */ +int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) +{ + int rc; + + if (txq < 1 || txq > dev->num_tx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) { + ASSERT_RTNL(); + + rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, + txq); + if (rc) + return rc; + + if (dev->num_tc) + netif_setup_tc(dev, txq); + + if (txq < dev->real_num_tx_queues) { + qdisc_reset_all_tx_gt(dev, txq); +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, txq); +#endif + } + } + + dev->real_num_tx_queues = txq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_tx_queues); + +#ifdef CONFIG_SYSFS +/** + * netif_set_real_num_rx_queues - set actual number of RX queues used + * @dev: Network device + * @rxq: Actual number of RX queues + * + * This must be called either with the rtnl_lock held or before + * registration of the net device. Returns 0 on success, or a + * negative error code. If called before registration, it always + * succeeds. + */ +int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) +{ + int rc; + + if (rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); + + rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, + rxq); + if (rc) + return rc; + } + + dev->real_num_rx_queues = rxq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_rx_queues); +#endif + +/** + * netif_get_num_default_rss_queues - default number of RSS queues + * + * This routine should set an upper limit on the number of RSS queues + * used by default by multiqueue devices. + */ +int netif_get_num_default_rss_queues(void) +{ + return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); +} +EXPORT_SYMBOL(netif_get_num_default_rss_queues); + +static inline void __netif_reschedule(struct Qdisc *q) +{ + struct softnet_data *sd; + unsigned long flags; + + local_irq_save(flags); + sd = &__get_cpu_var(softnet_data); + q->next_sched = NULL; + *sd->output_queue_tailp = q; + sd->output_queue_tailp = &q->next_sched; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); +} + +void __netif_schedule(struct Qdisc *q) +{ + if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) + __netif_reschedule(q); +} +EXPORT_SYMBOL(__netif_schedule); + +struct dev_kfree_skb_cb { + enum skb_free_reason reason; +}; + +static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) +{ + return (struct dev_kfree_skb_cb *)skb->cb; +} + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) +{ + unsigned long flags; + + if (likely(atomic_read(&skb->users) == 1)) { + smp_rmb(); + atomic_set(&skb->users, 0); + } else if (likely(!atomic_dec_and_test(&skb->users))) { + return; + } + get_kfree_skb_cb(skb)->reason = reason; + local_irq_save(flags); + skb->next = __this_cpu_read(softnet_data.completion_queue); + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); +} +EXPORT_SYMBOL(__dev_kfree_skb_irq); + +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) +{ + if (in_irq() || irqs_disabled()) + __dev_kfree_skb_irq(skb, reason); + else + dev_kfree_skb(skb); +} +EXPORT_SYMBOL(__dev_kfree_skb_any); + + +/** + * netif_device_detach - mark device as removed + * @dev: network device + * + * Mark device as removed from system and therefore no longer available. + */ +void netif_device_detach(struct net_device *dev) +{ + if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && + netif_running(dev)) { + netif_tx_stop_all_queues(dev); + } +} +EXPORT_SYMBOL(netif_device_detach); + +/** + * netif_device_attach - mark device as attached + * @dev: network device + * + * Mark device as attached from system and restart if needed. + */ +void netif_device_attach(struct net_device *dev) +{ + if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && + netif_running(dev)) { + netif_tx_wake_all_queues(dev); + __netdev_watchdog_up(dev); + } +} +EXPORT_SYMBOL(netif_device_attach); + +static void skb_warn_bad_offload(const struct sk_buff *skb) +{ + static const netdev_features_t null_features = 0; + struct net_device *dev = skb->dev; + const char *driver = ""; + + if (!net_ratelimit()) + return; + + if (dev && dev->dev.parent) + driver = dev_driver_string(dev->dev.parent); + + WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " + "gso_type=%d ip_summed=%d\n", + driver, dev ? &dev->features : &null_features, + skb->sk ? &skb->sk->sk_route_caps : &null_features, + skb->len, skb->data_len, skb_shinfo(skb)->gso_size, + skb_shinfo(skb)->gso_type, skb->ip_summed); +} + /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ -int skb_checksum_help(struct sk_buff *skb, int inward) +int skb_checksum_help(struct sk_buff *skb) { - unsigned int csum; - int ret = 0, offset = skb->h.raw - skb->data; + __wsum csum; + int ret = 0, offset; - if (inward) { - skb->ip_summed = CHECKSUM_NONE; - goto out; + if (skb->ip_summed == CHECKSUM_COMPLETE) + goto out_set_summed; + + if (unlikely(skb_shinfo(skb)->gso_size)) { + skb_warn_bad_offload(skb); + return -EINVAL; } - if (skb_cloned(skb)) { - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (skb_has_shared_frag(skb)) { + ret = __skb_linearize(skb); if (ret) goto out; } - BUG_ON(offset > (int)skb->len); - csum = skb_checksum(skb, offset, skb->len-offset, 0); + offset = skb_checksum_start_offset(skb); + BUG_ON(offset >= skb_headlen(skb)); + csum = skb_checksum(skb, offset, skb->len - offset, 0); - offset = skb->tail - skb->h.raw; - BUG_ON(offset <= 0); - BUG_ON(skb->csum + 2 > offset); + offset += skb->csum_offset; + BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb)); + + if (skb_cloned(skb) && + !skb_clone_writable(skb, offset + sizeof(__sum16))) { + ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (ret) + goto out; + } - *(u16*)(skb->h.raw + skb->csum) = csum_fold(csum); + *(__sum16 *)(skb->data + offset) = csum_fold(csum); +out_set_summed: skb->ip_summed = CHECKSUM_NONE; -out: +out: return ret; } +EXPORT_SYMBOL(skb_checksum_help); + +__be16 skb_network_protocol(struct sk_buff *skb, int *depth) +{ + unsigned int vlan_depth = skb->mac_len; + __be16 type = skb->protocol; + + /* Tunnel gso handlers can set protocol to ethernet. */ + if (type == htons(ETH_P_TEB)) { + struct ethhdr *eth; + + if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) + return 0; + + eth = (struct ethhdr *)skb_mac_header(skb); + type = eth->h_proto; + } + + /* if skb->protocol is 802.1Q/AD then the header should already be + * present at mac_len - VLAN_HLEN (if mac_len > 0), or at + * ETH_HLEN otherwise + */ + if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { + if (vlan_depth) { + if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN))) + return 0; + vlan_depth -= VLAN_HLEN; + } else { + vlan_depth = ETH_HLEN; + } + do { + struct vlan_hdr *vh; + + if (unlikely(!pskb_may_pull(skb, + vlan_depth + VLAN_HLEN))) + return 0; + + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } while (type == htons(ETH_P_8021Q) || + type == htons(ETH_P_8021AD)); + } + + *depth = vlan_depth; + + return type; +} + +/** + * skb_mac_gso_segment - mac layer segmentation handler. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + */ +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_offload *ptype; + int vlan_depth = skb->mac_len; + __be16 type = skb_network_protocol(skb, &vlan_depth); + + if (unlikely(!type)) + return ERR_PTR(-EINVAL); + + __skb_pull(skb, vlan_depth); + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + int err; + + err = ptype->callbacks.gso_send_check(skb); + segs = ERR_PTR(err); + if (err || skb_gso_ok(skb, features)) + break; + __skb_push(skb, (skb->data - + skb_network_header(skb))); + } + segs = ptype->callbacks.gso_segment(skb, features); + break; + } + } + rcu_read_unlock(); + + __skb_push(skb, skb->data - skb_mac_header(skb)); + + return segs; +} +EXPORT_SYMBOL(skb_mac_gso_segment); + + +/* openvswitch calls this on rx path, so we need a different check. + */ +static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + +/** + * __skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path + * + * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. + */ +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) +{ + if (unlikely(skb_needs_check(skb, tx_path))) { + int err; + + skb_warn_bad_offload(skb); + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); + SKB_GSO_CB(skb)->encap_level = 0; + + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return skb_mac_gso_segment(skb, features); +} +EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev) { if (net_ratelimit()) { - printk(KERN_ERR "%s: hw csum failure.\n", - dev ? dev->name : "<unknown>"); + pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); dump_stack(); } } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif -#ifdef CONFIG_HIGHMEM /* Actually, we should eliminate this check as soon as we know, that: * 1. IOMMU is present and allows to map all the memory. * 2. No high memory really exists on this machine. */ -static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { +#ifdef CONFIG_HIGHMEM int i; + if (!(dev->features & NETIF_F_HIGHDMA)) { + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) + return 1; + } + } + + if (PCI_DMA_BUS_IS_PHYS) { + struct device *pdev = dev->dev.parent; - if (dev->features & NETIF_F_HIGHDMA) + if (!pdev) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + dma_addr_t addr = page_to_phys(skb_frag_page(frag)); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) + return 1; + } + } +#endif + return 0; +} + +struct dev_gso_cb { + void (*destructor)(struct sk_buff *skb); +}; + +#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb) + +static void dev_gso_skb_destructor(struct sk_buff *skb) +{ + struct dev_gso_cb *cb; + + kfree_skb_list(skb->next); + skb->next = NULL; + + cb = DEV_GSO_CB(skb); + if (cb->destructor) + cb->destructor(skb); +} + +/** + * dev_gso_segment - Perform emulated hardware segmentation on skb. + * @skb: buffer to segment + * @features: device features as applicable to this skb + * + * This function segments the given skb and stores the list of segments + * in skb->next. + */ +static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) +{ + struct sk_buff *segs; + + segs = skb_gso_segment(skb, features); + + /* Verifying header integrity only. */ + if (!segs) return 0; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - if (PageHighMem(skb_shinfo(skb)->frags[i].page)) - return 1; + if (IS_ERR(segs)) + return PTR_ERR(segs); + + skb->next = segs; + DEV_GSO_CB(skb)->destructor = skb->destructor; + skb->destructor = dev_gso_skb_destructor; return 0; } + +/* If MPLS offload request, verify we are testing hardware MPLS features + * instead of standard features for the netdev. + */ +#ifdef CONFIG_NET_MPLS_GSO +static netdev_features_t net_mpls_features(struct sk_buff *skb, + netdev_features_t features, + __be16 type) +{ + if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC)) + features &= skb->dev->mpls_features; + + return features; +} #else -#define illegal_highdma(dev, skb) (0) +static netdev_features_t net_mpls_features(struct sk_buff *skb, + netdev_features_t features, + __be16 type) +{ + return features; +} #endif -/* Keep head the same: replace data */ -int __skb_linearize(struct sk_buff *skb, gfp_t gfp_mask) +static netdev_features_t harmonize_features(struct sk_buff *skb, + netdev_features_t features) { - unsigned int size; - u8 *data; - long offset; - struct skb_shared_info *ninfo; - int headerlen = skb->data - skb->head; - int expand = (skb->tail + skb->data_len) - skb->end; + int tmp; + __be16 type; - if (skb_shared(skb)) - BUG(); + type = skb_network_protocol(skb, &tmp); + features = net_mpls_features(skb, features, type); - if (expand <= 0) - expand = 0; + if (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, type)) { + features &= ~NETIF_F_ALL_CSUM; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } - size = skb->end - skb->head + expand; - size = SKB_DATA_ALIGN(size); - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); - if (!data) - return -ENOMEM; + return features; +} - /* Copy entire thing */ - if (skb_copy_bits(skb, -headerlen, data, headerlen + skb->len)) - BUG(); +netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + __be16 protocol = skb->protocol; + netdev_features_t features = skb->dev->features; - /* Set up shinfo */ - ninfo = (struct skb_shared_info*)(data + size); - atomic_set(&ninfo->dataref, 1); - ninfo->tso_size = skb_shinfo(skb)->tso_size; - ninfo->tso_segs = skb_shinfo(skb)->tso_segs; - ninfo->nr_frags = 0; - ninfo->frag_list = NULL; + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; - /* Offset between the two in bytes */ - offset = data - skb->head; + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else if (!vlan_tx_tag_present(skb)) { + return harmonize_features(skb, features); + } - /* Free old data. */ - skb_release_data(skb); + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); - skb->head = data; - skb->end = data + size; + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; - /* Set up new pointers */ - skb->h.raw += offset; - skb->nh.raw += offset; - skb->mac.raw += offset; - skb->tail += offset; - skb->data += offset; + return harmonize_features(skb, features); +} +EXPORT_SYMBOL(netif_skb_features); - /* We are no longer a clone, even if we were. */ - skb->cloned = 0; +int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int rc = NETDEV_TX_OK; + unsigned int skb_len; - skb->tail += skb->data_len; - skb->data_len = 0; - return 0; + if (likely(!skb->next)) { + netdev_features_t features; + + /* + * If device doesn't need skb->dst, release it right now while + * its hot in this cpu cache + */ + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(skb); + + 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)) + goto out; + + skb->vlan_tci = 0; + } + + /* If encapsulation offload request, verify we are testing + * hardware encapsulation features instead of standard + * features for the netdev + */ + if (skb->encapsulation) + features &= dev->hw_enc_features; + + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) + goto out_kfree_skb; + if (skb->next) + goto gso; + } else { + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) + goto out_kfree_skb; + + /* If packet is not checksummed and device does not + * support checksumming for this protocol, complete + * checksumming here. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb->encapsulation) + skb_set_inner_transport_header(skb, + skb_checksum_start_offset(skb)); + else + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (!(features & NETIF_F_ALL_CSUM) && + skb_checksum_help(skb)) + goto out_kfree_skb; + } + } + + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + + skb_len = skb->len; + trace_net_dev_start_xmit(skb, dev); + rc = ops->ndo_start_xmit(skb, dev); + trace_net_dev_xmit(skb, rc, dev, skb_len); + if (rc == NETDEV_TX_OK) + txq_trans_update(txq); + return rc; + } + +gso: + do { + struct sk_buff *nskb = skb->next; + + skb->next = nskb->next; + nskb->next = NULL; + + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(nskb, dev); + + skb_len = nskb->len; + trace_net_dev_start_xmit(nskb, dev); + rc = ops->ndo_start_xmit(nskb, dev); + trace_net_dev_xmit(nskb, rc, dev, skb_len); + if (unlikely(rc != NETDEV_TX_OK)) { + if (rc & ~NETDEV_TX_MASK) + goto out_kfree_gso_skb; + nskb->next = skb->next; + skb->next = nskb; + return rc; + } + txq_trans_update(txq); + if (unlikely(netif_xmit_stopped(txq) && skb->next)) + return NETDEV_TX_BUSY; + } while (skb->next); + +out_kfree_gso_skb: + if (likely(skb->next == NULL)) { + skb->destructor = DEV_GSO_CB(skb)->destructor; + consume_skb(skb); + return rc; + } +out_kfree_skb: + kfree_skb(skb); +out: + return rc; } +EXPORT_SYMBOL_GPL(dev_hard_start_xmit); -#define HARD_TX_LOCK(dev, cpu) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ - spin_lock(&dev->xmit_lock); \ - dev->xmit_lock_owner = cpu; \ - } \ +static void qdisc_pkt_len_init(struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len; + u16 gso_segs = shinfo->gso_segs; + + /* mac layer + network layer */ + hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + + /* + transport layer */ + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + + if (shinfo->gso_type & SKB_GSO_DODGY) + gso_segs = DIV_ROUND_UP(skb->len - hdr_len, + shinfo->gso_size); + + qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; + } } -#define HARD_TX_UNLOCK(dev) { \ - if ((dev->features & NETIF_F_LLTX) == 0) { \ - dev->xmit_lock_owner = -1; \ - spin_unlock(&dev->xmit_lock); \ - } \ +static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, + struct netdev_queue *txq) +{ + spinlock_t *root_lock = qdisc_lock(q); + bool contended; + int rc; + + qdisc_pkt_len_init(skb); + qdisc_calculate_pkt_len(skb, q); + /* + * Heuristic to force contended enqueues to serialize on a + * separate lock before trying to get qdisc main lock. + * This permits __QDISC_STATE_RUNNING owner to get the lock more often + * and dequeue packets faster. + */ + contended = qdisc_is_running(q); + if (unlikely(contended)) + spin_lock(&q->busylock); + + spin_lock(root_lock); + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + kfree_skb(skb); + rc = NET_XMIT_DROP; + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && + qdisc_run_begin(q)) { + /* + * This is a work-conserving queue; there are no old skbs + * waiting to be sent out; and the qdisc is not running - + * xmit the skb directly. + */ + if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) + skb_dst_force(skb); + + qdisc_bstats_update(q, skb); + + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } + __qdisc_run(q); + } else + qdisc_run_end(q); + + rc = NET_XMIT_SUCCESS; + } else { + skb_dst_force(skb); + rc = q->enqueue(skb, q) & NET_XMIT_MASK; + if (qdisc_run_begin(q)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } + __qdisc_run(q); + } + } + spin_unlock(root_lock); + if (unlikely(contended)) + spin_unlock(&q->busylock); + return rc; } +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } +} +#else +#define skb_update_prio(skb) +#endif + +static DEFINE_PER_CPU(int, xmit_recursion); +#define RECURSION_LIMIT 10 + +/** + * dev_loopback_xmit - loop back @skb + * @skb: buffer to transmit + */ +int dev_loopback_xmit(struct sk_buff *skb) +{ + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->pkt_type = PACKET_LOOPBACK; + skb->ip_summed = CHECKSUM_UNNECESSARY; + WARN_ON(!skb_dst(skb)); + skb_dst_force(skb); + netif_rx_ni(skb); + return 0; +} +EXPORT_SYMBOL(dev_loopback_xmit); + /** - * dev_queue_xmit - transmit a buffer + * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit + * @accel_priv: private data used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling @@ -1239,78 +2857,39 @@ int __skb_linearize(struct sk_buff *skb, gfp_t gfp_mask) * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ - -int dev_queue_xmit(struct sk_buff *skb) +static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; + struct netdev_queue *txq; struct Qdisc *q; int rc = -ENOMEM; - if (skb_shinfo(skb)->frag_list && - !(dev->features & NETIF_F_FRAGLIST) && - __skb_linearize(skb, GFP_ATOMIC)) - goto out_kfree_skb; + skb_reset_mac_header(skb); - /* Fragmented skb is linearized if device does not support SG, - * or if at least one of fragments is in highmem and device - * does not support DMA from it. + /* Disable soft irqs for various locks below. Also + * stops preemption for RCU. */ - if (skb_shinfo(skb)->nr_frags && - (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) && - __skb_linearize(skb, GFP_ATOMIC)) - goto out_kfree_skb; + rcu_read_lock_bh(); - /* If packet is not checksummed and device does not support - * checksumming for this protocol, complete checksumming here. - */ - if (skb->ip_summed == CHECKSUM_HW && - (!(dev->features & (NETIF_F_HW_CSUM | NETIF_F_NO_CSUM)) && - (!(dev->features & NETIF_F_IP_CSUM) || - skb->protocol != htons(ETH_P_IP)))) - if (skb_checksum_help(skb, 0)) - goto out_kfree_skb; - - spin_lock_prefetch(&dev->queue_lock); + skb_update_prio(skb); - /* Disable soft irqs for various locks below. Also - * stops preemption for RCU. - */ - local_bh_disable(); - - /* Updates of qdisc are serialized by queue_lock. - * The struct Qdisc which is pointed to by qdisc is now a - * rcu structure - it may be accessed without acquiring - * a lock (but the structure may be stale.) The freeing of the - * qdisc will be deferred until it's known that there are no - * more references to it. - * - * If the qdisc has an enqueue function, we still need to - * hold the queue_lock before calling it, since queue_lock - * also serializes access to the device queue. - */ + txq = netdev_pick_tx(dev, skb, accel_priv); + q = rcu_dereference_bh(txq->qdisc); - q = rcu_dereference(dev->qdisc); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS); + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); #endif + trace_net_dev_queue(skb); if (q->enqueue) { - /* Grab device queue */ - spin_lock(&dev->queue_lock); - - rc = q->enqueue(skb, q); - - qdisc_run(dev); - - spin_unlock(&dev->queue_lock); - rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc; + rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } /* The device has no queue. Common case for software devices: loopback, all the sorts of tunnels... - Really, it is unlikely that xmit_lock protection is necessary here. - (f.e. loopback and IP tunnels are clean ignoring statistics + Really, it is unlikely that netif_tx_lock protection is necessary + here. (f.e. loopback and IP tunnels are clean ignoring statistics counters.) However, it is possible, that they rely on protection made by us here. @@ -1321,139 +2900,459 @@ int dev_queue_xmit(struct sk_buff *skb) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (dev->xmit_lock_owner != cpu) { + if (txq->xmit_lock_owner != cpu) { - HARD_TX_LOCK(dev, cpu); + if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) + goto recursion_alert; - if (!netif_queue_stopped(dev)) { - if (netdev_nit) - dev_queue_xmit_nit(skb, dev); + HARD_TX_LOCK(dev, txq, cpu); - rc = 0; - if (!dev->hard_start_xmit(skb, dev)) { - HARD_TX_UNLOCK(dev); + if (!netif_xmit_stopped(txq)) { + __this_cpu_inc(xmit_recursion); + rc = dev_hard_start_xmit(skb, dev, txq); + __this_cpu_dec(xmit_recursion); + if (dev_xmit_complete(rc)) { + HARD_TX_UNLOCK(dev, txq); goto out; } } - HARD_TX_UNLOCK(dev); - if (net_ratelimit()) - printk(KERN_CRIT "Virtual device %s asks to " - "queue packet!\n", dev->name); + HARD_TX_UNLOCK(dev, txq); + net_crit_ratelimited("Virtual device %s asks to queue packet!\n", + dev->name); } else { /* Recursion is detected! It is possible, - * unfortunately */ - if (net_ratelimit()) - printk(KERN_CRIT "Dead loop on virtual device " - "%s, fix it urgently!\n", dev->name); + * unfortunately + */ +recursion_alert: + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); } } rc = -ENETDOWN; - local_bh_enable(); + rcu_read_unlock_bh(); -out_kfree_skb: + atomic_long_inc(&dev->tx_dropped); kfree_skb(skb); return rc; out: - local_bh_enable(); + rcu_read_unlock_bh(); return rc; } +int dev_queue_xmit(struct sk_buff *skb) +{ + return __dev_queue_xmit(skb, NULL); +} +EXPORT_SYMBOL(dev_queue_xmit); + +int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) +{ + return __dev_queue_xmit(skb, accel_priv); +} +EXPORT_SYMBOL(dev_queue_xmit_accel); + /*======================================================================= Receiver routines =======================================================================*/ -int netdev_max_backlog = 1000; -int netdev_budget = 300; -int weight_p = 64; /* old backlog weight */ +int netdev_max_backlog __read_mostly = 1000; +EXPORT_SYMBOL(netdev_max_backlog); + +int netdev_tstamp_prequeue __read_mostly = 1; +int netdev_budget __read_mostly = 300; +int weight_p __read_mostly = 64; /* old backlog weight */ + +/* Called with irq disabled */ +static inline void ____napi_schedule(struct softnet_data *sd, + struct napi_struct *napi) +{ + list_add_tail(&napi->poll_list, &sd->poll_list); + __raise_softirq_irqoff(NET_RX_SOFTIRQ); +} + +#ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; +EXPORT_SYMBOL(rps_sock_flow_table); + +struct static_key rps_needed __read_mostly; + +static struct rps_dev_flow * +set_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow *rflow, u16 next_cpu) +{ + if (next_cpu != RPS_NO_CPU) { +#ifdef CONFIG_RFS_ACCEL + struct netdev_rx_queue *rxqueue; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *old_rflow; + u32 flow_id; + u16 rxq_index; + int rc; + + /* Should we steer this flow to a different hardware queue? */ + if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || + !(dev->features & NETIF_F_NTUPLE)) + goto out; + rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); + if (rxq_index == skb_get_rx_queue(skb)) + goto out; + + rxqueue = dev->_rx + rxq_index; + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (!flow_table) + goto out; + 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) + goto out; + old_rflow = rflow; + rflow = &flow_table->flows[flow_id]; + rflow->filter = rc; + if (old_rflow->filter == rflow->filter) + old_rflow->filter = RPS_NO_FILTER; + out: +#endif + rflow->last_qtail = + per_cpu(softnet_data, next_cpu).input_queue_head; + } + + rflow->cpu = next_cpu; + return rflow; +} + +/* + * get_rps_cpu is called from netif_receive_skb and returns the target + * CPU from the RPS map of the receiving queue for a given skb. + * rcu_read_lock must be held on entry. + */ +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) +{ + struct netdev_rx_queue *rxqueue; + struct rps_map *map; + struct rps_dev_flow_table *flow_table; + 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); + if (unlikely(index >= dev->real_num_rx_queues)) { + WARN_ONCE(dev->real_num_rx_queues > 1, + "%s received packet on queue %u, but number " + "of RX queues is %u\n", + dev->name, index, dev->real_num_rx_queues); + goto done; + } + rxqueue = dev->_rx + index; + } else + rxqueue = dev->_rx; + + map = rcu_dereference(rxqueue->rps_map); + if (map) { + if (map->len == 1 && + !rcu_access_pointer(rxqueue->rps_flow_table)) { + tcpu = map->cpus[0]; + if (cpu_online(tcpu)) + cpu = tcpu; + goto done; + } + } else if (!rcu_access_pointer(rxqueue->rps_flow_table)) { + goto done; + } + + skb_reset_network_header(skb); + hash = skb_get_hash(skb); + if (!hash) + goto done; + + flow_table = rcu_dereference(rxqueue->rps_flow_table); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (flow_table && sock_flow_table) { + u16 next_cpu; + struct rps_dev_flow *rflow; + + rflow = &flow_table->flows[hash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask]; + + /* + * If the desired CPU (where last recvmsg was done) is + * different from current CPU (one in the rx-queue flow + * table entry), switch if one of the following holds: + * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is offline. + * - The current CPU's queue tail has advanced beyond the + * last packet that was enqueued using this table entry. + * This guarantees that all previous packets for the flow + * have been dequeued, thus preserving in order delivery. + */ + if (unlikely(tcpu != next_cpu) && + (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + rflow->last_qtail)) >= 0)) { + tcpu = next_cpu; + rflow = set_rps_cpu(dev, skb, rflow, next_cpu); + } + + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + + if (map) { + tcpu = map->cpus[((u64) hash * map->len) >> 32]; + + if (cpu_online(tcpu)) { + cpu = tcpu; + goto done; + } + } -DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; +done: + return cpu; +} +#ifdef CONFIG_RFS_ACCEL /** - * netif_rx - post buffer to the network code - * @skb: buffer to post - * - * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. - * - * return values: - * NET_RX_SUCCESS (no congestion) - * NET_RX_CN_LOW (low congestion) - * NET_RX_CN_MOD (moderate congestion) - * NET_RX_CN_HIGH (high congestion) - * NET_RX_DROP (packet was dropped) + * rps_may_expire_flow - check whether an RFS hardware filter may be removed + * @dev: Device on which the filter was set + * @rxq_index: RX queue index + * @flow_id: Flow ID passed to ndo_rx_flow_steer() + * @filter_id: Filter ID returned by ndo_rx_flow_steer() * + * Drivers that implement ndo_rx_flow_steer() should periodically call + * this function for each installed filter and remove the filters for + * which it returns %true. */ +bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id) +{ + struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *rflow; + bool expire = true; + int cpu; -int netif_rx(struct sk_buff *skb) + rcu_read_lock(); + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (flow_table && flow_id <= flow_table->mask) { + rflow = &flow_table->flows[flow_id]; + cpu = ACCESS_ONCE(rflow->cpu); + if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + ((int)(per_cpu(softnet_data, cpu).input_queue_head - + rflow->last_qtail) < + (int)(10 * flow_table->mask))) + expire = false; + } + rcu_read_unlock(); + return expire; +} +EXPORT_SYMBOL(rps_may_expire_flow); + +#endif /* CONFIG_RFS_ACCEL */ + +/* Called from hardirq (IPI) context */ +static void rps_trigger_softirq(void *data) { - struct softnet_data *queue; - unsigned long flags; + struct softnet_data *sd = data; - /* if netpoll wants it, pretend we never saw it */ - if (netpoll_rx(skb)) - return NET_RX_DROP; + ____napi_schedule(sd, &sd->backlog); + sd->received_rps++; +} - if (!skb->tstamp.off_sec) - net_timestamp(skb); +#endif /* CONFIG_RPS */ + +/* + * Check if this softnet_data structure is another cpu one + * If yes, queue it to our IPI list and return 1 + * If no, return 0 + */ +static int rps_ipi_queued(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + struct softnet_data *mysd = &__get_cpu_var(softnet_data); + + if (sd != mysd) { + sd->rps_ipi_next = mysd->rps_ipi_list; + mysd->rps_ipi_list = sd; + + __raise_softirq_irqoff(NET_RX_SOFTIRQ); + return 1; + } +#endif /* CONFIG_RPS */ + return 0; +} + +#ifdef CONFIG_NET_FLOW_LIMIT +int netdev_flow_limit_table_len __read_mostly = (1 << 12); +#endif + +static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) +{ +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + struct softnet_data *sd; + unsigned int old_flow, new_flow; + + if (qlen < (netdev_max_backlog >> 1)) + return false; + + sd = &__get_cpu_var(softnet_data); + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) { + new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); + old_flow = fl->history[fl->history_head]; + fl->history[fl->history_head] = new_flow; + + fl->history_head++; + fl->history_head &= FLOW_LIMIT_HISTORY - 1; + + if (likely(fl->buckets[old_flow])) + fl->buckets[old_flow]--; + + if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { + fl->count++; + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); +#endif + return false; +} + +/* + * enqueue_to_backlog is called to queue an skb to a per CPU backlog + * queue (may be a remote CPU queue). + */ +static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + unsigned int *qtail) +{ + struct softnet_data *sd; + unsigned long flags; + unsigned int qlen; + + sd = &per_cpu(softnet_data, cpu); - /* - * The code is rearranged so that the path is the most - * short when CPU is congested, but is still operating. - */ local_irq_save(flags); - queue = &__get_cpu_var(softnet_data); - __get_cpu_var(netdev_rx_stat).total++; - if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { - if (queue->input_pkt_queue.qlen) { + rps_lock(sd); + qlen = skb_queue_len(&sd->input_pkt_queue); + if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { + if (skb_queue_len(&sd->input_pkt_queue)) { enqueue: - dev_hold(skb->dev); - __skb_queue_tail(&queue->input_pkt_queue, skb); + __skb_queue_tail(&sd->input_pkt_queue, skb); + input_queue_tail_incr_save(sd, qtail); + rps_unlock(sd); local_irq_restore(flags); return NET_RX_SUCCESS; } - netif_rx_schedule(&queue->backlog_dev); + /* Schedule NAPI for backlog device + * We can use non atomic operation since we own the queue lock + */ + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) { + if (!rps_ipi_queued(sd)) + ____napi_schedule(sd, &sd->backlog); + } goto enqueue; } - __get_cpu_var(netdev_rx_stat).dropped++; + sd->dropped++; + rps_unlock(sd); + local_irq_restore(flags); + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } +static int netif_rx_internal(struct sk_buff *skb) +{ + int ret; + + net_timestamp_check(netdev_tstamp_prequeue, skb); + + trace_netif_rx(skb); +#ifdef CONFIG_RPS + if (static_key_false(&rps_needed)) { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + + preempt_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); + if (cpu < 0) + cpu = smp_processor_id(); + + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); + preempt_enable(); + } else +#endif + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } + return ret; +} + +/** + * netif_rx - post buffer to the network code + * @skb: buffer to post + * + * This function receives a packet from a device driver and queues it for + * the upper (protocol) levels to process. It always succeeds. The buffer + * may be dropped during processing for congestion control or by the + * protocol layers. + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + */ + +int netif_rx(struct sk_buff *skb) +{ + trace_netif_rx_entry(skb); + + return netif_rx_internal(skb); +} +EXPORT_SYMBOL(netif_rx); + int netif_rx_ni(struct sk_buff *skb) { int err; + trace_netif_rx_ni_entry(skb); + preempt_disable(); - err = netif_rx(skb); + err = netif_rx_internal(skb); if (local_softirq_pending()) do_softirq(); preempt_enable(); return err; } - EXPORT_SYMBOL(netif_rx_ni); -static inline struct net_device *skb_bond(struct sk_buff *skb) -{ - struct net_device *dev = skb->dev; - - if (dev->master) - skb->dev = dev->master; - - return dev; -} - static void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = &__get_cpu_var(softnet_data); @@ -1470,70 +3369,57 @@ static void net_tx_action(struct softirq_action *h) struct sk_buff *skb = clist; clist = clist->next; - BUG_TRAP(!atomic_read(&skb->users)); + WARN_ON(atomic_read(&skb->users)); + if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } if (sd->output_queue) { - struct net_device *head; + struct Qdisc *head; local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; + sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); while (head) { - struct net_device *dev = head; - head = head->next_sched; + struct Qdisc *q = head; + spinlock_t *root_lock; - smp_mb__before_clear_bit(); - clear_bit(__LINK_STATE_SCHED, &dev->state); + head = head->next_sched; - if (spin_trylock(&dev->queue_lock)) { - qdisc_run(dev); - spin_unlock(&dev->queue_lock); + root_lock = qdisc_lock(q); + if (spin_trylock(root_lock)) { + smp_mb__before_atomic(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); + qdisc_run(q); + spin_unlock(root_lock); } else { - netif_schedule(dev); + if (!test_bit(__QDISC_STATE_DEACTIVATED, + &q->state)) { + __netif_reschedule(q); + } else { + smp_mb__before_atomic(); + clear_bit(__QDISC_STATE_SCHED, + &q->state); + } } } } } -static __inline__ int deliver_skb(struct sk_buff *skb, - struct packet_type *pt_prev, - struct net_device *orig_dev) -{ - atomic_inc(&skb->users); - return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); -} - -#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) -int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb); -struct net_bridge; -struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br, - unsigned char *addr); -void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent); - -static __inline__ int handle_bridge(struct sk_buff **pskb, - struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) -{ - struct net_bridge_port *port; - - if ((*pskb)->pkt_type == PACKET_LOOPBACK || - (port = rcu_dereference((*pskb)->dev->br_port)) == NULL) - return 0; - - if (*pt_prev) { - *ret = deliver_skb(*pskb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - - return br_handle_frame_hook(port, pskb); -} -#else -#define handle_bridge(skb, pt_prev, ret, orig_dev) (0) +#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \ + (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)) +/* This hook is defined here for ATM LANE */ +int (*br_fdb_test_addr_hook)(struct net_device *dev, + unsigned char *addr) __read_mostly; +EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif #ifdef CONFIG_NET_CLS_ACT @@ -1541,67 +3427,172 @@ static __inline__ int handle_bridge(struct sk_buff **pskb, * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions * a compare and 2 stores extra right now if we dont have it on * but have CONFIG_NET_CLS_ACT - * NOTE: This doesnt stop any functionality; if you dont have - * the ingress scheduler, you just cant add policies on ingress. + * NOTE: This doesn't stop any functionality; if you dont have + * the ingress scheduler, you just can't add policies on ingress. * */ -static int ing_filter(struct sk_buff *skb) +static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) { - struct Qdisc *q; struct net_device *dev = skb->dev; + u32 ttl = G_TC_RTTL(skb->tc_verd); int result = TC_ACT_OK; - - if (dev->qdisc_ingress) { - __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd); - if (MAX_RED_LOOP < ttl++) { - printk("Redir loop detected Dropping packet (%s->%s)\n", - skb->input_dev->name, skb->dev->name); - return TC_ACT_SHOT; - } - - skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl); + struct Qdisc *q; - skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS); + if (unlikely(MAX_RED_LOOP < ttl++)) { + net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n", + skb->skb_iif, dev->ifindex); + return TC_ACT_SHOT; + } - spin_lock(&dev->ingress_lock); - if ((q = dev->qdisc_ingress) != NULL) - result = q->enqueue(skb, q); - spin_unlock(&dev->ingress_lock); + skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl); + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + q = rxq->qdisc; + if (q != &noop_qdisc) { + spin_lock(qdisc_lock(q)); + if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) + result = qdisc_enqueue_root(skb, q); + spin_unlock(qdisc_lock(q)); } return result; } + +static inline struct sk_buff *handle_ing(struct sk_buff *skb, + struct packet_type **pt_prev, + int *ret, struct net_device *orig_dev) +{ + struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); + + if (!rxq || rxq->qdisc == &noop_qdisc) + goto out; + + if (*pt_prev) { + *ret = deliver_skb(skb, *pt_prev, orig_dev); + *pt_prev = NULL; + } + + switch (ing_filter(skb, rxq)) { + case TC_ACT_SHOT: + case TC_ACT_STOLEN: + kfree_skb(skb); + return NULL; + } + +out: + skb->tc_verd = 0; + return skb; +} #endif -int netif_receive_skb(struct sk_buff *skb) +/** + * netdev_rx_handler_register - register receive handler + * @dev: device to register a handler for + * @rx_handler: receive handler to register + * @rx_handler_data: data pointer that is used by rx handler + * + * Register a receive handler for a device. This handler will then be + * called from __netif_receive_skb. A negative errno code is returned + * on a failure. + * + * The caller must hold the rtnl_mutex. + * + * For a general description of rx_handler, see enum rx_handler_result. + */ +int netdev_rx_handler_register(struct net_device *dev, + rx_handler_func_t *rx_handler, + void *rx_handler_data) +{ + ASSERT_RTNL(); + + if (dev->rx_handler) + return -EBUSY; + + /* Note: rx_handler_data must be set before rx_handler */ + rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); + rcu_assign_pointer(dev->rx_handler, rx_handler); + + return 0; +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_register); + +/** + * netdev_rx_handler_unregister - unregister receive handler + * @dev: device to unregister a handler from + * + * Unregister a receive handler from a device. + * + * The caller must hold the rtnl_mutex. + */ +void netdev_rx_handler_unregister(struct net_device *dev) +{ + + ASSERT_RTNL(); + RCU_INIT_POINTER(dev->rx_handler, NULL); + /* a reader seeing a non NULL rx_handler in a rcu_read_lock() + * section has a guarantee to see a non NULL rx_handler_data + * as well. + */ + synchronize_net(); + RCU_INIT_POINTER(dev->rx_handler_data, NULL); +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); + +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. + */ +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) +{ + switch (skb->protocol) { + 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; + } +} + +static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; + rx_handler_func_t *rx_handler; struct net_device *orig_dev; + struct net_device *null_or_dev; + bool deliver_exact = false; int ret = NET_RX_DROP; - unsigned short type; - - /* if we've gotten here through NAPI, check netpoll */ - if (skb->dev->poll && netpoll_rx(skb)) - return NET_RX_DROP; + __be16 type; - if (!skb->tstamp.off_sec) - net_timestamp(skb); + net_timestamp_check(!netdev_tstamp_prequeue, skb); - if (!skb->input_dev) - skb->input_dev = skb->dev; + trace_netif_receive_skb(skb); - orig_dev = skb_bond(skb); + orig_dev = skb->dev; - __get_cpu_var(netdev_rx_stat).total++; - - skb->h.raw = skb->nh.raw = skb->data; - skb->mac_len = skb->nh.raw - skb->mac.raw; + skb_reset_network_header(skb); + if (!skb_transport_header_was_set(skb)) + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); pt_prev = NULL; rcu_read_lock(); +another_round: + skb->skb_iif = skb->dev->ifindex; + + __this_cpu_inc(softnet_data.processed); + + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto unlock; + } + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -1609,51 +3600,93 @@ int netif_receive_skb(struct sk_buff *skb) } #endif + if (pfmemalloc) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { if (!ptype->dev || ptype->dev == skb->dev) { - if (pt_prev) + if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT - if (pt_prev) { - ret = deliver_skb(skb, pt_prev, orig_dev); - pt_prev = NULL; /* noone else should process this after*/ - } else { - skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); - } + skb = handle_ing(skb, &pt_prev, &ret, orig_dev); + if (!skb) + goto unlock; +ncls: +#endif - ret = ing_filter(skb); + if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) + goto drop; - if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) { - kfree_skb(skb); - goto out; + if (vlan_tx_tag_present(skb)) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + if (vlan_do_receive(&skb)) + goto another_round; + else if (unlikely(!skb)) + goto unlock; } - skb->tc_verd = 0; -ncls: -#endif + rx_handler = rcu_dereference(skb->dev->rx_handler); + if (rx_handler) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + switch (rx_handler(&skb)) { + case RX_HANDLER_CONSUMED: + ret = NET_RX_SUCCESS; + goto unlock; + case RX_HANDLER_ANOTHER: + goto another_round; + case RX_HANDLER_EXACT: + deliver_exact = true; + case RX_HANDLER_PASS: + break; + default: + BUG(); + } + } - handle_diverter(skb); + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; + } - if (handle_bridge(&skb, &pt_prev, &ret, orig_dev)) - goto out; + /* deliver only exact match when indicated */ + null_or_dev = deliver_exact ? skb->dev : NULL; type = skb->protocol; - list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) { + list_for_each_entry_rcu(ptype, + &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { if (ptype->type == type && - (!ptype->dev || ptype->dev == skb->dev)) { - if (pt_prev) + (ptype->dev == null_or_dev || ptype->dev == skb->dev || + ptype->dev == orig_dev)) { + if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } if (pt_prev) { - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + else + ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) @@ -1661,439 +3694,1568 @@ ncls: ret = NET_RX_DROP; } +unlock: + rcu_read_unlock(); + return ret; +} + +static int __netif_receive_skb(struct sk_buff *skb) +{ + int ret; + + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { + unsigned long pflags = current->flags; + + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + current->flags |= PF_MEMALLOC; + ret = __netif_receive_skb_core(skb, true); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + } else + ret = __netif_receive_skb_core(skb, false); + + return ret; +} + +static int netif_receive_skb_internal(struct sk_buff *skb) +{ + net_timestamp_check(netdev_tstamp_prequeue, skb); + + if (skb_defer_rx_timestamp(skb)) + return NET_RX_SUCCESS; + +#ifdef CONFIG_RPS + if (static_key_false(&rps_needed)) { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu, ret; + + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); + + if (cpu >= 0) { + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); + } +#endif + return __netif_receive_skb(skb); +} + +/** + * netif_receive_skb - process receive buffer from network + * @skb: buffer to process + * + * netif_receive_skb() is the main receive data processing function. + * It always succeeds. The buffer may be dropped during processing + * for congestion control or by the protocol layers. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb(struct sk_buff *skb) +{ + trace_netif_receive_skb_entry(skb); + + return netif_receive_skb_internal(skb); +} +EXPORT_SYMBOL(netif_receive_skb); + +/* Network device is going away, flush any packets still pending + * Called with irqs disabled. + */ +static void flush_backlog(void *arg) +{ + struct net_device *dev = arg; + struct softnet_data *sd = &__get_cpu_var(softnet_data); + struct sk_buff *skb, *tmp; + + rps_lock(sd); + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->input_pkt_queue); + kfree_skb(skb); + input_queue_head_incr(sd); + } + } + rps_unlock(sd); + + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->process_queue); + kfree_skb(skb); + input_queue_head_incr(sd); + } + } +} + +static int napi_gro_complete(struct sk_buff *skb) +{ + struct packet_offload *ptype; + __be16 type = skb->protocol; + struct list_head *head = &offload_base; + int err = -ENOENT; + + BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); + + if (NAPI_GRO_CB(skb)->count == 1) { + skb_shinfo(skb)->gso_size = 0; + goto out; + } + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + + err = ptype->callbacks.gro_complete(skb, 0); + break; + } + rcu_read_unlock(); + + if (err) { + WARN_ON(&ptype->list == head); + kfree_skb(skb); + return NET_RX_SUCCESS; + } + out: + return netif_receive_skb_internal(skb); +} + +/* napi->gro_list contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + struct sk_buff *skb, *prev = NULL; + + /* scan list and build reverse chain */ + for (skb = napi->gro_list; skb != NULL; skb = skb->next) { + skb->prev = prev; + prev = skb; + } + + for (skb = prev; skb; skb = prev) { + skb->next = NULL; + + if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) + return; + + prev = skb->prev; + napi_gro_complete(skb); + napi->gro_count--; + } + + napi->gro_list = NULL; +} +EXPORT_SYMBOL(napi_gro_flush); + +static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +{ + struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); + + for (p = napi->gro_list; p; p = p->next) { + unsigned long diffs; + + NAPI_GRO_CB(p)->flush = 0; + + if (hash != skb_get_hash_raw(p)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= p->vlan_tci ^ skb->vlan_tci; + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_mac_header(skb), + maclen); + NAPI_GRO_CB(p)->same_flow = !diffs; + } +} + +static void skb_gro_reset_offset(struct sk_buff *skb) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (skb_mac_header(skb) == skb_tail_pointer(skb) && + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + } +} + +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; + struct packet_offload *ptype; + __be16 type = skb->protocol; + struct list_head *head = &offload_base; + int same_flow; + enum gro_result ret; + int grow; + + if (!(skb->dev->features & NETIF_F_GRO)) + goto normal; + + if (skb_is_gso(skb) || skb_has_frag_list(skb)) + goto normal; + + gro_list_prepare(napi, skb); + NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + + skb_set_network_header(skb, skb_gro_offset(skb)); + skb_reset_mac_len(skb); + NAPI_GRO_CB(skb)->same_flow = 0; + NAPI_GRO_CB(skb)->flush = 0; + NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->udp_mark = 0; + + pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); + break; + } rcu_read_unlock(); + + if (&ptype->list == head) + goto normal; + + same_flow = NAPI_GRO_CB(skb)->same_flow; + ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; + + if (pp) { + struct sk_buff *nskb = *pp; + + *pp = nskb->next; + nskb->next = NULL; + napi_gro_complete(nskb); + napi->gro_count--; + } + + if (same_flow) + goto ok; + + if (NAPI_GRO_CB(skb)->flush) + goto normal; + + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_count++; + } + NAPI_GRO_CB(skb)->count = 1; + NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; + skb_shinfo(skb)->gso_size = skb_gro_len(skb); + skb->next = napi->gro_list; + napi->gro_list = skb; + ret = GRO_HELD; + +pull: + grow = skb_gro_offset(skb) - skb_headlen(skb); + if (grow > 0) + gro_pull_from_frag0(skb, grow); +ok: return ret; + +normal: + ret = GRO_NORMAL; + goto pull; } -static int process_backlog(struct net_device *backlog_dev, int *budget) +struct packet_offload *gro_find_receive_by_type(__be16 type) { - int work = 0; - int quota = min(backlog_dev->quota, *budget); - struct softnet_data *queue = &__get_cpu_var(softnet_data); - unsigned long start_time = jiffies; + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; - backlog_dev->weight = weight_p; - for (;;) { - struct sk_buff *skb; - struct net_device *dev; + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_receive_by_type); - local_irq_disable(); - skb = __skb_dequeue(&queue->input_pkt_queue); - if (!skb) - goto job_done; +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_complete_by_type); + +static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +{ + switch (ret) { + case GRO_NORMAL: + if (netif_receive_skb_internal(skb)) + ret = GRO_DROP; + break; + + case GRO_DROP: + kfree_skb(skb); + break; + + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + kmem_cache_free(skbuff_head_cache, skb); + else + __kfree_skb(skb); + break; + + case GRO_HELD: + case GRO_MERGED: + break; + } + + return ret; +} + +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); + +static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) +{ + __skb_pull(skb, skb_headlen(skb)); + /* restore the reserve we had after netdev_alloc_skb_ip_align() */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); + skb->vlan_tci = 0; + skb->dev = napi->dev; + skb->skb_iif = 0; + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + + napi->skb = skb; +} + +struct sk_buff *napi_get_frags(struct napi_struct *napi) +{ + struct sk_buff *skb = napi->skb; + + if (!skb) { + skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); + napi->skb = skb; + } + return skb; +} +EXPORT_SYMBOL(napi_get_frags); + +static gro_result_t napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) +{ + switch (ret) { + case GRO_NORMAL: + 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; + + case GRO_DROP: + case GRO_MERGED_FREE: + napi_reuse_skb(napi, skb); + break; + + case GRO_MERGED: + break; + } + + 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; + + 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_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; +} + +gro_result_t napi_gro_frags(struct napi_struct *napi) +{ + struct sk_buff *skb = napi_frags_skb(napi); + + if (!skb) + return GRO_DROP; + + trace_napi_gro_frags_entry(skb); + + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); +} +EXPORT_SYMBOL(napi_gro_frags); + +/* + * net_rps_action_and_irq_enable sends any pending IPI's for rps. + * Note: called with local irq disabled, but exits with local irq enabled. + */ +static void net_rps_action_and_irq_enable(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + struct softnet_data *remsd = sd->rps_ipi_list; + + if (remsd) { + sd->rps_ipi_list = NULL; + + local_irq_enable(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + while (remsd) { + struct softnet_data *next = remsd->rps_ipi_next; + + if (cpu_online(remsd->cpu)) + smp_call_function_single_async(remsd->cpu, + &remsd->csd); + remsd = next; + } + } else +#endif local_irq_enable(); +} - dev = skb->dev; +static int process_backlog(struct napi_struct *napi, int quota) +{ + int work = 0; + struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); - netif_receive_skb(skb); +#ifdef CONFIG_RPS + /* Check if we have pending ipi, its better to send them now, + * not waiting net_rx_action() end. + */ + if (sd->rps_ipi_list) { + local_irq_disable(); + net_rps_action_and_irq_enable(sd); + } +#endif + napi->weight = weight_p; + local_irq_disable(); + while (1) { + struct sk_buff *skb; - dev_put(dev); + while ((skb = __skb_dequeue(&sd->process_queue))) { + local_irq_enable(); + __netif_receive_skb(skb); + local_irq_disable(); + input_queue_head_incr(sd); + if (++work >= quota) { + local_irq_enable(); + return work; + } + } - work++; + rps_lock(sd); + if (skb_queue_empty(&sd->input_pkt_queue)) { + /* + * Inline a custom version of __napi_complete(). + * only current cpu owns and manipulates this napi, + * and NAPI_STATE_SCHED is the only possible flag set + * on backlog. + * We can use a plain write instead of clear_bit(), + * and we dont need an smp_mb() memory barrier. + */ + list_del(&napi->poll_list); + napi->state = 0; + rps_unlock(sd); - if (work >= quota || jiffies - start_time > 1) break; + } + skb_queue_splice_tail_init(&sd->input_pkt_queue, + &sd->process_queue); + rps_unlock(sd); } + local_irq_enable(); - backlog_dev->quota -= work; - *budget -= work; - return -1; + return work; +} -job_done: - backlog_dev->quota -= work; - *budget -= work; +/** + * __napi_schedule - schedule for receive + * @n: entry to schedule + * + * The entry's receive function will be scheduled to run + */ +void __napi_schedule(struct napi_struct *n) +{ + unsigned long flags; - list_del(&backlog_dev->poll_list); - smp_mb__before_clear_bit(); - netif_poll_enable(backlog_dev); + local_irq_save(flags); + ____napi_schedule(&__get_cpu_var(softnet_data), n); + local_irq_restore(flags); +} +EXPORT_SYMBOL(__napi_schedule); - local_irq_enable(); - return 0; +void __napi_complete(struct napi_struct *n) +{ + BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); + BUG_ON(n->gro_list); + + list_del(&n->poll_list); + smp_mb__before_atomic(); + clear_bit(NAPI_STATE_SCHED, &n->state); +} +EXPORT_SYMBOL(__napi_complete); + +void napi_complete(struct napi_struct *n) +{ + unsigned long flags; + + /* + * don't let napi dequeue from the cpu poll list + * just in case its running on a different cpu + */ + if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state))) + return; + + napi_gro_flush(n, false); + local_irq_save(flags); + __napi_complete(n); + local_irq_restore(flags); +} +EXPORT_SYMBOL(napi_complete); + +/* must be called under rcu_read_lock(), as we dont take a reference */ +struct napi_struct *napi_by_id(unsigned int napi_id) +{ + unsigned int hash = napi_id % HASH_SIZE(napi_hash); + struct napi_struct *napi; + + hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) + if (napi->napi_id == napi_id) + return napi; + + return NULL; +} +EXPORT_SYMBOL_GPL(napi_by_id); + +void napi_hash_add(struct napi_struct *napi) +{ + if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) { + + spin_lock(&napi_hash_lock); + + /* 0 is not a valid id, we also skip an id that is taken + * we expect both events to be extremely rare + */ + napi->napi_id = 0; + while (!napi->napi_id) { + napi->napi_id = ++napi_gen_id; + if (napi_by_id(napi->napi_id)) + napi->napi_id = 0; + } + + hlist_add_head_rcu(&napi->napi_hash_node, + &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + + spin_unlock(&napi_hash_lock); + } } +EXPORT_SYMBOL_GPL(napi_hash_add); + +/* Warning : caller is responsible to make sure rcu grace period + * is respected before freeing memory containing @napi + */ +void napi_hash_del(struct napi_struct *napi) +{ + spin_lock(&napi_hash_lock); + + if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) + hlist_del_rcu(&napi->napi_hash_node); + + spin_unlock(&napi_hash_lock); +} +EXPORT_SYMBOL_GPL(napi_hash_del); + +void netif_napi_add(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + INIT_LIST_HEAD(&napi->poll_list); + napi->gro_count = 0; + napi->gro_list = NULL; + napi->skb = NULL; + napi->poll = poll; + if (weight > NAPI_POLL_WEIGHT) + pr_err_once("netif_napi_add() called with weight %d on device %s\n", + weight, dev->name); + napi->weight = weight; + list_add(&napi->dev_list, &dev->napi_list); + napi->dev = dev; +#ifdef CONFIG_NETPOLL + spin_lock_init(&napi->poll_lock); + napi->poll_owner = -1; +#endif + set_bit(NAPI_STATE_SCHED, &napi->state); +} +EXPORT_SYMBOL(netif_napi_add); + +void netif_napi_del(struct napi_struct *napi) +{ + list_del_init(&napi->dev_list); + napi_free_frags(napi); + + kfree_skb_list(napi->gro_list); + napi->gro_list = NULL; + napi->gro_count = 0; +} +EXPORT_SYMBOL(netif_napi_del); static void net_rx_action(struct softirq_action *h) { - struct softnet_data *queue = &__get_cpu_var(softnet_data); - unsigned long start_time = jiffies; + struct softnet_data *sd = &__get_cpu_var(softnet_data); + unsigned long time_limit = jiffies + 2; int budget = netdev_budget; void *have; local_irq_disable(); - while (!list_empty(&queue->poll_list)) { - struct net_device *dev; + while (!list_empty(&sd->poll_list)) { + struct napi_struct *n; + int work, weight; - if (budget <= 0 || jiffies - start_time > 1) + /* If softirq window is exhuasted then punt. + * Allow this to run for 2 jiffies since which will allow + * an average latency of 1.5/HZ. + */ + if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) goto softnet_break; local_irq_enable(); - dev = list_entry(queue->poll_list.next, - struct net_device, poll_list); - have = netpoll_poll_lock(dev); + /* Even though interrupts have been re-enabled, this + * access is safe because interrupts can only add new + * entries to the tail of this list, and only ->poll() + * calls can remove this head entry from the list. + */ + n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list); - if (dev->quota <= 0 || dev->poll(dev, &budget)) { - netpoll_poll_unlock(have); - local_irq_disable(); - list_del(&dev->poll_list); - list_add_tail(&dev->poll_list, &queue->poll_list); - if (dev->quota < 0) - dev->quota += dev->weight; - else - dev->quota = dev->weight; - } else { - netpoll_poll_unlock(have); - dev_put(dev); - local_irq_disable(); + have = netpoll_poll_lock(n); + + weight = n->weight; + + /* This NAPI_STATE_SCHED test is for avoiding a race + * with netpoll's poll_napi(). Only the entity which + * obtains the lock and sees NAPI_STATE_SCHED set will + * actually make the ->poll() call. Therefore we avoid + * accidentally calling ->poll() when NAPI is not scheduled. + */ + work = 0; + if (test_bit(NAPI_STATE_SCHED, &n->state)) { + work = n->poll(n, weight); + trace_napi_poll(n); } + + WARN_ON_ONCE(work > weight); + + budget -= work; + + local_irq_disable(); + + /* Drivers must not modify the NAPI state if they + * consume the entire weight. In such cases this code + * still "owns" the NAPI instance and therefore can + * move the instance around on the list at-will. + */ + if (unlikely(work == weight)) { + if (unlikely(napi_disable_pending(n))) { + local_irq_enable(); + napi_complete(n); + local_irq_disable(); + } else { + if (n->gro_list) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + local_irq_enable(); + napi_gro_flush(n, HZ >= 1000); + local_irq_disable(); + } + list_move_tail(&n->poll_list, &sd->poll_list); + } + } + + netpoll_poll_unlock(have); } out: - local_irq_enable(); + net_rps_action_and_irq_enable(sd); + +#ifdef CONFIG_NET_DMA + /* + * There may not be any more sk_buffs coming right now, so push + * any pending DMA copies to hardware + */ + dma_issue_pending_all(); +#endif + return; softnet_break: - __get_cpu_var(netdev_rx_stat).time_squeeze++; + sd->time_squeeze++; __raise_softirq_irqoff(NET_RX_SOFTIRQ); goto out; } -static gifconf_func_t * gifconf_list [NPROTO]; +struct netdev_adjacent { + struct net_device *dev; + + /* upper master flag, there can only be one master device per list */ + bool master; + + /* counter for the number of times this device was added to us */ + u16 ref_nr; + + /* private field for the users */ + void *private; + + struct list_head list; + struct rcu_head rcu; +}; + +static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *adj_list) +{ + struct netdev_adjacent *adj; + + list_for_each_entry(adj, adj_list, list) { + if (adj->dev == adj_dev) + return adj; + } + return NULL; +} /** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler + * netdev_has_upper_dev - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks only immediate upper device, + * not through a complete stack of devices. The caller must hold the RTNL lock. */ -int register_gifconf(unsigned int family, gifconf_func_t * gifconf) +bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) { - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} + ASSERT_RTNL(); + return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); +} +EXPORT_SYMBOL(netdev_has_upper_dev); -/* - * Map an interface index to its name (SIOCGIFNAME) +/** + * netdev_has_any_upper_dev - Check if device is linked to some device + * @dev: device + * + * Find out if a device is linked to an upper device and return true in case + * it is. The caller must hold the RTNL lock. */ +static bool netdev_has_any_upper_dev(struct net_device *dev) +{ + ASSERT_RTNL(); -/* - * We need this ioctl for efficient implementation of the - * if_indextoname() function required by the IPv6 API. Without - * it, we would have to search all the interfaces to find a - * match. --pb + return !list_empty(&dev->all_adj_list.upper); +} + +/** + * netdev_master_upper_dev_get - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RTNL lock. */ +struct net_device *netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_adjacent *upper; + + ASSERT_RTNL(); + + if (list_empty(&dev->adj_list.upper)) + return NULL; -static int dev_ifname(struct ifreq __user *arg) + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get); + +void *netdev_adjacent_get_private(struct list_head *adj_list) { - struct net_device *dev; - struct ifreq ifr; + struct netdev_adjacent *adj; - /* - * Fetch the caller's info block. - */ + adj = list_entry(adj_list, struct netdev_adjacent, list); - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; + return adj->private; +} +EXPORT_SYMBOL(netdev_adjacent_get_private); - read_lock(&dev_base_lock); - dev = __dev_get_by_index(ifr.ifr_ifindex); - if (!dev) { - read_unlock(&dev_base_lock); - return -ENODEV; - } +/** + * netdev_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. + */ +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *upper; - strcpy(ifr.ifr_name, dev->name); - read_unlock(&dev_base_lock); + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) - return -EFAULT; - return 0; + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + + return upper->dev; } +EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); -/* - * Perform a SIOCGIFCONF call. This structure will change - * size eventually, and there is nothing I can do about it. - * Thus we will need a 'compatibility mode'. +/** + * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. */ +struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *upper; + + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); + + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->all_adj_list.upper) + return NULL; -static int dev_ifconf(char __user *arg) + *iter = &upper->list; + + return upper->dev; +} +EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); + +/** + * netdev_lower_get_next_private - Get the next ->private from the + * lower neighbour list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold either hold the + * RTNL lock or its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next_private(struct net_device *dev, + struct list_head **iter) { - struct ifconf ifc; - struct net_device *dev; - char __user *pos; - int len; - int total; - int i; + struct netdev_adjacent *lower; - /* - * Fetch the caller's info block. - */ + lower = list_entry(*iter, struct netdev_adjacent, list); - if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) - return -EFAULT; + if (&lower->list == &dev->adj_list.lower) + return NULL; - pos = ifc.ifc_buf; - len = ifc.ifc_len; + *iter = lower->list.next; - /* - * Loop over the interfaces, and write an info block for each. - */ + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_get_next_private); - total = 0; - for (dev = dev_base; dev; dev = dev->next) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0); - else - done = gifconf_list[i](dev, pos + total, - len - total); - if (done < 0) - return -EFAULT; - total += done; - } - } - } +/** + * netdev_lower_get_next_private_rcu - Get the next ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold RCU read lock. + */ +void *netdev_lower_get_next_private_rcu(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *lower; - /* - * All done. Write the updated control block back to the caller. - */ - ifc.ifc_len = total; + WARN_ON_ONCE(!rcu_read_lock_held()); - /* - * Both BSD and Solaris return 0 here, so we do too. - */ - return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; + lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->private; } +EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); -#ifdef CONFIG_PROC_FS -/* - * This is invoked by the /proc filesystem handler to display a device - * in detail. +/** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. */ -static __inline__ struct net_device *dev_get_idx(loff_t pos) +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { - struct net_device *dev; - loff_t i; + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); - for (i = 0, dev = dev_base; dev && i < pos; ++i, dev = dev->next); + if (&lower->list == &dev->adj_list.lower) + return NULL; - return i == pos ? dev : NULL; + *iter = &lower->list; + + return lower->dev; } +EXPORT_SYMBOL(netdev_lower_get_next); -void *dev_seq_start(struct seq_file *seq, loff_t *pos) +/** + * netdev_lower_get_first_private_rcu - Get the first ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * + * Gets the first netdev_adjacent->private from the dev's lower neighbour + * list. The caller must hold RCU read lock. + */ +void *netdev_lower_get_first_private_rcu(struct net_device *dev) { - read_lock(&dev_base_lock); - return *pos ? dev_get_idx(*pos - 1) : SEQ_START_TOKEN; + struct netdev_adjacent *lower; + + lower = list_first_or_null_rcu(&dev->adj_list.lower, + struct netdev_adjacent, list); + if (lower) + return lower->private; + return NULL; } +EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); -void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +/** + * netdev_master_upper_dev_get_rcu - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RCU read lock. + */ +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { - ++*pos; - return v == SEQ_START_TOKEN ? dev_base : ((struct net_device *)v)->next; + struct netdev_adjacent *upper; + + upper = list_first_or_null_rcu(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (upper && likely(upper->master)) + return upper->dev; + return NULL; } +EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); -void dev_seq_stop(struct seq_file *seq, void *v) +static int netdev_adjacent_sysfs_add(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { - read_unlock(&dev_base_lock); + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", adj_dev->name); + return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), + linkname); } +static void netdev_adjacent_sysfs_del(struct net_device *dev, + char *name, + struct list_head *dev_list) +{ + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", name); + sysfs_remove_link(&(dev->dev.kobj), linkname); +} + +#define netdev_adjacent_is_neigh_list(dev, dev_list) \ + (dev_list == &dev->adj_list.upper || \ + dev_list == &dev->adj_list.lower) -static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) +static int __netdev_adjacent_dev_insert(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list, + void *private, bool master) { - if (dev->get_stats) { - struct net_device_stats *stats = dev->get_stats(dev); + struct netdev_adjacent *adj; + int ret; - seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " - "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", - dev->name, stats->rx_bytes, stats->rx_packets, - stats->rx_errors, - stats->rx_dropped + stats->rx_missed_errors, - stats->rx_fifo_errors, - stats->rx_length_errors + stats->rx_over_errors + - stats->rx_crc_errors + stats->rx_frame_errors, - stats->rx_compressed, stats->multicast, - stats->tx_bytes, stats->tx_packets, - stats->tx_errors, stats->tx_dropped, - stats->tx_fifo_errors, stats->collisions, - stats->tx_carrier_errors + - stats->tx_aborted_errors + - stats->tx_window_errors + - stats->tx_heartbeat_errors, - stats->tx_compressed); - } else - seq_printf(seq, "%6s: No statistics available.\n", dev->name); + adj = __netdev_find_adj(dev, adj_dev, dev_list); + + if (adj) { + adj->ref_nr++; + return 0; + } + + adj = kmalloc(sizeof(*adj), GFP_KERNEL); + if (!adj) + return -ENOMEM; + + adj->dev = adj_dev; + adj->master = master; + adj->ref_nr = 1; + adj->private = private; + dev_hold(adj_dev); + + pr_debug("dev_hold for %s, because of link added from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + + if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); + if (ret) + goto free_adj; + } + + /* Ensure that master link is always the first item in list. */ + if (master) { + ret = sysfs_create_link(&(dev->dev.kobj), + &(adj_dev->dev.kobj), "master"); + if (ret) + goto remove_symlinks; + + list_add_rcu(&adj->list, dev_list); + } else { + list_add_tail_rcu(&adj->list, dev_list); + } + + return 0; + +remove_symlinks: + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); +free_adj: + kfree(adj); + dev_put(adj_dev); + + return ret; } -/* - * Called from the PROCfs module. This now uses the new arbitrary sized - * /proc/net interface to create /proc/net/dev - */ -static int dev_seq_show(struct seq_file *seq, void *v) +static void __netdev_adjacent_dev_remove(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Inter-| Receive " - " | Transmit\n" - " face |bytes packets errs drop fifo frame " - "compressed multicast|bytes packets errs " - "drop fifo colls carrier compressed\n"); - else - dev_seq_printf_stats(seq, v); - return 0; + struct netdev_adjacent *adj; + + adj = __netdev_find_adj(dev, adj_dev, dev_list); + + if (!adj) { + pr_err("tried to remove device %s from %s\n", + dev->name, adj_dev->name); + BUG(); + } + + if (adj->ref_nr > 1) { + pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name, + adj->ref_nr-1); + adj->ref_nr--; + return; + } + + if (adj->master) + sysfs_remove_link(&(dev->dev.kobj), "master"); + + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); + + list_del_rcu(&adj->list); + pr_debug("dev_put for %s, because link removed from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + dev_put(adj_dev); + kfree_rcu(adj, rcu); } -static struct netif_rx_stats *softnet_get_online(loff_t *pos) +static int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { - struct netif_rx_stats *rc = NULL; + int ret; - while (*pos < NR_CPUS) - if (cpu_online(*pos)) { - rc = &per_cpu(netdev_rx_stat, *pos); - break; - } else - ++*pos; - return rc; + ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, + master); + if (ret) + return ret; + + ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, + false); + if (ret) { + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + return ret; + } + + return 0; } -static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) +static int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - return softnet_get_online(pos); + return __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower, + NULL, false); } -static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { - ++*pos; - return softnet_get_online(pos); + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + __netdev_adjacent_dev_remove(upper_dev, dev, down_list); } -static void softnet_seq_stop(struct seq_file *seq, void *v) +static void __netdev_adjacent_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) { + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower); } -static int softnet_seq_show(struct seq_file *seq, void *v) +static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) { - struct netif_rx_stats *s = v; + int ret = __netdev_adjacent_dev_link(dev, upper_dev); + + if (ret) + return ret; + + ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower, + private, master); + if (ret) { + __netdev_adjacent_dev_unlink(dev, upper_dev); + return ret; + } - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", - s->total, s->dropped, s->time_squeeze, 0, - 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision ); return 0; } -static struct seq_operations dev_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_seq_show, -}; - -static int dev_seq_open(struct inode *inode, struct file *file) +static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) { - return seq_open(file, &dev_seq_ops); + __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower); } -static struct file_operations dev_seq_fops = { - .owner = THIS_MODULE, - .open = dev_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; +static int __netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev, bool master, + void *private) +{ + struct netdev_adjacent *i, *j, *to_i, *to_j; + int ret = 0; -static struct seq_operations softnet_seq_ops = { - .start = softnet_seq_start, - .next = softnet_seq_next, - .stop = softnet_seq_stop, - .show = softnet_seq_show, -}; + ASSERT_RTNL(); -static int softnet_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &softnet_seq_ops); -} + if (dev == upper_dev) + return -EBUSY; -static struct file_operations softnet_seq_fops = { - .owner = THIS_MODULE, - .open = softnet_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; + /* To prevent loops, check if dev is not upper device to upper_dev. */ + if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) + return -EBUSY; -#ifdef WIRELESS_EXT -extern int wireless_proc_init(void); -#else -#define wireless_proc_init() 0 -#endif + if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) + return -EEXIST; + + if (master && netdev_master_upper_dev_get(dev)) + return -EBUSY; + + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, + master); + if (ret) + return ret; + + /* Now that we linked these devs, make all the upper_dev's + * all_adj_list.upper visible to every dev's all_adj_list.lower an + * versa, and don't forget the devices itself. All of these + * links are non-neighbours. + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + pr_debug("Interlinking %s with %s, non-neighbour\n", + i->dev->name, j->dev->name); + ret = __netdev_adjacent_dev_link(i->dev, j->dev); + if (ret) + goto rollback_mesh; + } + } + + /* add dev to every upper_dev's upper device */ + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + pr_debug("linking %s's upper device %s with %s\n", + upper_dev->name, i->dev->name, dev->name); + ret = __netdev_adjacent_dev_link(dev, i->dev); + if (ret) + goto rollback_upper_mesh; + } + + /* add upper_dev to every dev's lower device */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + pr_debug("linking %s's lower device %s with %s\n", dev->name, + i->dev->name, upper_dev->name); + ret = __netdev_adjacent_dev_link(i->dev, upper_dev); + if (ret) + goto rollback_lower_mesh; + } + + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); + return 0; + +rollback_lower_mesh: + to_i = i; + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + if (i == to_i) + break; + __netdev_adjacent_dev_unlink(i->dev, upper_dev); + } + + i = NULL; + +rollback_upper_mesh: + to_i = i; + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + if (i == to_i) + break; + __netdev_adjacent_dev_unlink(dev, i->dev); + } + + i = j = NULL; + +rollback_mesh: + to_i = i; + to_j = j; + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + if (i == to_i && j == to_j) + break; + __netdev_adjacent_dev_unlink(i->dev, j->dev); + } + if (i == to_i) + break; + } + + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); + + return ret; +} -static int __init dev_proc_init(void) +/** + * netdev_upper_dev_link - Add a link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. The caller must hold + * the RTNL lock. On a failure a negative errno code is returned. + * On success the reference counts are adjusted and the function + * returns zero. + */ +int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - int rc = -ENOMEM; + return __netdev_upper_dev_link(dev, upper_dev, false, NULL); +} +EXPORT_SYMBOL(netdev_upper_dev_link); - if (!proc_net_fops_create("dev", S_IRUGO, &dev_seq_fops)) - goto out; - if (!proc_net_fops_create("softnet_stat", S_IRUGO, &softnet_seq_fops)) - goto out_dev; - if (wireless_proc_init()) - goto out_softnet; - rc = 0; -out: - return rc; -out_softnet: - proc_net_remove("softnet_stat"); -out_dev: - proc_net_remove("dev"); - goto out; +/** + * netdev_master_upper_dev_link - Add a master link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. In this case, only + * one master upper device can be linked, although other non-master devices + * might be linked as well. The caller must hold the RTNL lock. + * On a failure a negative errno code is returned. On success the reference + * counts are adjusted and the function returns zero. + */ +int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, true, NULL); } -#else -#define dev_proc_init() 0 -#endif /* CONFIG_PROC_FS */ +EXPORT_SYMBOL(netdev_master_upper_dev_link); +int netdev_master_upper_dev_link_private(struct net_device *dev, + struct net_device *upper_dev, + void *private) +{ + return __netdev_upper_dev_link(dev, upper_dev, true, private); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link_private); /** - * netdev_set_master - set up master/slave pair - * @slave: slave device - * @master: new master device + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success the reference counts - * are adjusted, %RTM_NEWLINK is sent to the routing socket and the - * function returns zero. + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. */ -int netdev_set_master(struct net_device *slave, struct net_device *master) +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_adjacent *i, *j; + ASSERT_RTNL(); + + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); + + /* Here is the tricky part. We must remove all dev's lower + * devices from all upper_dev's upper devices and vice + * versa, to maintain the graph relationship. + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) + __netdev_adjacent_dev_unlink(i->dev, j->dev); + + /* remove also the devices itself from lower/upper device + * list + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) + __netdev_adjacent_dev_unlink(i->dev, upper_dev); + + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) + __netdev_adjacent_dev_unlink(dev, i->dev); + + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); +} +EXPORT_SYMBOL(netdev_upper_dev_unlink); + +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) +{ + struct netdev_adjacent *iter; + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + } +} + +void *netdev_lower_dev_get_private(struct net_device *dev, + struct net_device *lower_dev) +{ + struct netdev_adjacent *lower; + + if (!lower_dev) + return NULL; + lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + if (!lower) + return NULL; + + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_dev_get_private); + + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) { - struct net_device *old = slave->master; + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; ASSERT_RTNL(); - if (master) { - if (old) - return -EBUSY; - dev_hold(master); + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; } - slave->master = master; - - synchronize_net(); + if (type_check(dev)) + max_nest++; - if (old) - dev_put(old); + return max_nest; +} +EXPORT_SYMBOL(dev_get_nest_level); - if (master) - slave->flags |= IFF_SLAVE; - else - slave->flags &= ~IFF_SLAVE; +static void dev_change_rx_flags(struct net_device *dev, int flags) +{ + const struct net_device_ops *ops = dev->netdev_ops; - rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); + if (ops->ndo_change_rx_flags) + ops->ndo_change_rx_flags(dev, flags); +} + +static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) +{ + unsigned int old_flags = dev->flags; + kuid_t uid; + kgid_t gid; + + ASSERT_RTNL(); + + dev->flags |= IFF_PROMISC; + dev->promiscuity += inc; + if (dev->promiscuity == 0) { + /* + * Avoid overflow. + * If inc causes overflow, untouch promisc and return error. + */ + if (inc < 0) + dev->flags &= ~IFF_PROMISC; + else { + dev->promiscuity -= inc; + pr_warn("%s: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n", + dev->name); + return -EOVERFLOW; + } + } + if (dev->flags != old_flags) { + pr_info("device %s %s promiscuous mode\n", + dev->name, + dev->flags & IFF_PROMISC ? "entered" : "left"); + if (audit_enabled) { + current_uid_gid(&uid, &gid); + audit_log(current->audit_context, GFP_ATOMIC, + AUDIT_ANOM_PROMISCUOUS, + "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", + dev->name, (dev->flags & IFF_PROMISC), + (old_flags & IFF_PROMISC), + from_kuid(&init_user_ns, audit_get_loginuid(current)), + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), + audit_get_sessionid(current)); + } + + dev_change_rx_flags(dev, IFF_PROMISC); + } + if (notify) + __dev_notify_flags(dev, old_flags, IFF_PROMISC); return 0; } @@ -2102,25 +5264,56 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) * @dev: device * @inc: modifier * - * Add or remove promsicuity from a device. While the count in the device + * Add or remove promiscuity from a device. While the count in the device * remains above zero the interface remains promiscuous. Once it hits zero * the device reverts back to normal filtering operation. A negative inc * value is used to drop promiscuity on the device. + * Return 0 if successful or a negative errno code on error. */ -void dev_set_promiscuity(struct net_device *dev, int inc) +int dev_set_promiscuity(struct net_device *dev, int inc) { - unsigned short old_flags = dev->flags; + unsigned int old_flags = dev->flags; + int err; - if ((dev->promiscuity += inc) == 0) - dev->flags &= ~IFF_PROMISC; - else - dev->flags |= IFF_PROMISC; - if (dev->flags != old_flags) { - dev_mc_upload(dev); - printk(KERN_INFO "device %s %s promiscuous mode\n", - dev->name, (dev->flags & IFF_PROMISC) ? "entered" : - "left"); + err = __dev_set_promiscuity(dev, inc, true); + if (err < 0) + return err; + if (dev->flags != old_flags) + dev_set_rx_mode(dev); + return err; +} +EXPORT_SYMBOL(dev_set_promiscuity); + +static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) +{ + unsigned int old_flags = dev->flags, old_gflags = dev->gflags; + + ASSERT_RTNL(); + + dev->flags |= IFF_ALLMULTI; + dev->allmulti += inc; + if (dev->allmulti == 0) { + /* + * Avoid overflow. + * If inc causes overflow, untouch allmulti and return error. + */ + if (inc < 0) + dev->flags &= ~IFF_ALLMULTI; + else { + dev->allmulti -= inc; + pr_warn("%s: allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n", + dev->name); + return -EOVERFLOW; + } + } + if (dev->flags ^ old_flags) { + dev_change_rx_flags(dev, IFF_ALLMULTI); + dev_set_rx_mode(dev); + if (notify) + __dev_notify_flags(dev, old_flags, + dev->gflags ^ old_gflags); } + return 0; } /** @@ -2133,39 +5326,93 @@ void dev_set_promiscuity(struct net_device *dev, int inc) * to all interfaces. Once it hits zero the device reverts back to normal * filtering operation. A negative @inc value is used to drop the counter * when releasing a resource needing all multicasts. + * Return 0 if successful or a negative errno code on error. */ -void dev_set_allmulti(struct net_device *dev, int inc) +int dev_set_allmulti(struct net_device *dev, int inc) { - unsigned short old_flags = dev->flags; + return __dev_set_allmulti(dev, inc, true); +} +EXPORT_SYMBOL(dev_set_allmulti); - dev->flags |= IFF_ALLMULTI; - if ((dev->allmulti += inc) == 0) - dev->flags &= ~IFF_ALLMULTI; - if (dev->flags ^ old_flags) - dev_mc_upload(dev); +/* + * Upload unicast and multicast address lists to device and + * configure RX filtering. When the device doesn't support unicast + * filtering it is put in promiscuous mode while unicast addresses + * are present. + */ +void __dev_set_rx_mode(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + /* dev_open will call this function so the list will stay sane. */ + if (!(dev->flags&IFF_UP)) + return; + + if (!netif_device_present(dev)) + return; + + if (!(dev->priv_flags & IFF_UNICAST_FLT)) { + /* Unicast addresses changes may only happen under the rtnl, + * therefore calling __dev_set_promiscuity here is safe. + */ + if (!netdev_uc_empty(dev) && !dev->uc_promisc) { + __dev_set_promiscuity(dev, 1, false); + dev->uc_promisc = true; + } else if (netdev_uc_empty(dev) && dev->uc_promisc) { + __dev_set_promiscuity(dev, -1, false); + dev->uc_promisc = false; + } + } + + if (ops->ndo_set_rx_mode) + ops->ndo_set_rx_mode(dev); } -unsigned dev_get_flags(const struct net_device *dev) +void dev_set_rx_mode(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); +} + +/** + * dev_get_flags - get flags reported to userspace + * @dev: device + * + * Get the combination of flag bits exported through APIs to userspace. + */ +unsigned int dev_get_flags(const struct net_device *dev) { - unsigned flags; + unsigned int flags; flags = (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI | - IFF_RUNNING)) | + IFF_RUNNING | + IFF_LOWER_UP | + IFF_DORMANT)) | (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); - if (netif_running(dev) && netif_carrier_ok(dev)) - flags |= IFF_RUNNING; + if (netif_running(dev)) { + if (netif_oper_up(dev)) + flags |= IFF_RUNNING; + if (netif_carrier_ok(dev)) + flags |= IFF_LOWER_UP; + if (netif_dormant(dev)) + flags |= IFF_DORMANT; + } return flags; } +EXPORT_SYMBOL(dev_get_flags); -int dev_change_flags(struct net_device *dev, unsigned flags) +int __dev_change_flags(struct net_device *dev, unsigned int flags) { + unsigned int old_flags = dev->flags; int ret; - int old_flags = dev->flags; + + ASSERT_RTNL(); /* * Set the flags on our device. @@ -2181,7 +5428,10 @@ int dev_change_flags(struct net_device *dev, unsigned flags) * Load in the correct multicast list now the flags have changed. */ - dev_mc_upload(dev); + if ((old_flags ^ flags) & IFF_MULTICAST) + dev_change_rx_flags(dev, IFF_MULTICAST); + + dev_set_rx_mode(dev); /* * Have we downed the interface. We handle IFF_UP ourselves @@ -2191,21 +5441,21 @@ int dev_change_flags(struct net_device *dev, unsigned flags) ret = 0; if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */ - ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev); + ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev); if (!ret) - dev_mc_upload(dev); + dev_set_rx_mode(dev); } - if (dev->flags & IFF_UP && - ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI | - IFF_VOLATILE))) - notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev); - if ((flags ^ dev->gflags) & IFF_PROMISC) { - int inc = (flags & IFF_PROMISC) ? +1 : -1; + int inc = (flags & IFF_PROMISC) ? 1 : -1; + unsigned int old_flags = dev->flags; + dev->gflags ^= IFF_PROMISC; - dev_set_promiscuity(dev, inc); + + if (__dev_set_promiscuity(dev, inc, false) >= 0) + if (dev->flags != old_flags) + dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI @@ -2213,20 +5463,84 @@ int dev_change_flags(struct net_device *dev, unsigned flags) IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { - int inc = (flags & IFF_ALLMULTI) ? +1 : -1; + int inc = (flags & IFF_ALLMULTI) ? 1 : -1; + dev->gflags ^= IFF_ALLMULTI; - dev_set_allmulti(dev, inc); + __dev_set_allmulti(dev, inc, false); + } + + return ret; +} + +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, + unsigned int gchanges) +{ + unsigned int changes = dev->flags ^ old_flags; + + if (gchanges) + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); + + if (changes & IFF_UP) { + if (dev->flags & IFF_UP) + call_netdevice_notifiers(NETDEV_UP, dev); + else + call_netdevice_notifiers(NETDEV_DOWN, dev); + } + + if (dev->flags & IFF_UP && + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = changes; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); } +} + +/** + * dev_change_flags - change device settings + * @dev: device + * @flags: device state flags + * + * Change settings on device based state flags. The flags are + * in the userspace exported format. + */ +int dev_change_flags(struct net_device *dev, unsigned int flags) +{ + int ret; + unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; - if (old_flags ^ dev->flags) - rtmsg_ifinfo(RTM_NEWLINK, dev, old_flags ^ dev->flags); + ret = __dev_change_flags(dev, flags); + if (ret < 0) + return ret; + changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); + __dev_notify_flags(dev, old_flags, changes); return ret; } +EXPORT_SYMBOL(dev_change_flags); + +static int __dev_set_mtu(struct net_device *dev, int new_mtu) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_change_mtu) + return ops->ndo_change_mtu(dev, new_mtu); + + dev->mtu = new_mtu; + return 0; +} +/** + * dev_set_mtu - Change maximum transfer unit + * @dev: device + * @new_mtu: new transfer unit + * + * Change the maximum transfer size of the network device. + */ int dev_set_mtu(struct net_device *dev, int new_mtu) { - int err; + int err, orig_mtu; if (new_mtu == dev->mtu) return 0; @@ -2238,405 +5552,444 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; - err = 0; - if (dev->change_mtu) - err = dev->change_mtu(dev, new_mtu); - else - dev->mtu = new_mtu; - if (!err && dev->flags & IFF_UP) - notifier_call_chain(&netdev_chain, - NETDEV_CHANGEMTU, dev); + err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) + return err; + + orig_mtu = dev->mtu; + err = __dev_set_mtu(dev, new_mtu); + + if (!err) { + err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) { + /* setting mtu back and notifying everyone again, + * so that they have a chance to revert changes. + */ + __dev_set_mtu(dev, orig_mtu); + call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + } + } return err; } +EXPORT_SYMBOL(dev_set_mtu); +/** + * dev_set_group - Change group this device belongs to + * @dev: device + * @new_group: group this device should belong to + */ +void dev_set_group(struct net_device *dev, int new_group) +{ + dev->group = new_group; +} +EXPORT_SYMBOL(dev_set_group); + +/** + * dev_set_mac_address - Change Media Access Control Address + * @dev: device + * @sa: new address + * + * Change the hardware (MAC) address of the device + */ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) { + const struct net_device_ops *ops = dev->netdev_ops; int err; - if (!dev->set_mac_address) + if (!ops->ndo_set_mac_address) return -EOPNOTSUPP; if (sa->sa_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - err = dev->set_mac_address(dev, sa); - if (!err) - notifier_call_chain(&netdev_chain, NETDEV_CHANGEADDR, dev); - return err; + err = ops->ndo_set_mac_address(dev, sa); + if (err) + return err; + dev->addr_assign_type = NET_ADDR_SET; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); + return 0; } +EXPORT_SYMBOL(dev_set_mac_address); -/* - * Perform the SIOCxIFxxx calls. +/** + * dev_change_carrier - Change device carrier + * @dev: device + * @new_carrier: new value + * + * Change device carrier */ -static int dev_ifsioc(struct ifreq *ifr, unsigned int cmd) +int dev_change_carrier(struct net_device *dev, bool new_carrier) { - int err; - struct net_device *dev = __dev_get_by_name(ifr->ifr_name); + const struct net_device_ops *ops = dev->netdev_ops; - if (!dev) + if (!ops->ndo_change_carrier) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) return -ENODEV; + return ops->ndo_change_carrier(dev, new_carrier); +} +EXPORT_SYMBOL(dev_change_carrier); - switch (cmd) { - case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = dev_get_flags(dev); - return 0; +/** + * dev_get_phys_port_id - Get device physical port ID + * @dev: device + * @ppid: port ID + * + * Get device physical port ID + */ +int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid) +{ + const struct net_device_ops *ops = dev->netdev_ops; - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); + if (!ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_id(dev, ppid); +} +EXPORT_SYMBOL(dev_get_phys_port_id); - case SIOCGIFMETRIC: /* Get the metric on the interface - (currently unused) */ - ifr->ifr_metric = 0; - return 0; +/** + * dev_new_index - allocate an ifindex + * @net: the applicable net namespace + * + * Returns a suitable unique value for a new device interface + * number. The caller must hold the rtnl semaphore or the + * dev_base_lock to be sure it remains unique. + */ +static int dev_new_index(struct net *net) +{ + int ifindex = net->ifindex; + for (;;) { + if (++ifindex <= 0) + ifindex = 1; + if (!__dev_get_by_index(net, ifindex)) + return net->ifindex = ifindex; + } +} - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ - return -EOPNOTSUPP; +/* Delayed registration/unregisteration */ +static LIST_HEAD(net_todo_list); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); - case SIOCGIFMTU: /* Get the MTU of a device */ - ifr->ifr_mtu = dev->mtu; - return 0; +static void net_set_todo(struct net_device *dev) +{ + list_add_tail(&dev->todo_list, &net_todo_list); + dev_net(dev)->dev_unreg_count++; +} - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); +static void rollback_registered_many(struct list_head *head) +{ + struct net_device *dev, *tmp; + LIST_HEAD(close_head); - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; + BUG_ON(dev_boot_phase); + ASSERT_RTNL(); - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + list_for_each_entry_safe(dev, tmp, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. Remove those + * devices and proceed with the remaining. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); - case SIOCSIFHWBROADCAST: - if (ifr->ifr_hwaddr.sa_family != dev->type) - return -EINVAL; - memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - notifier_call_chain(&netdev_chain, - NETDEV_CHANGEADDR, dev); - return 0; + WARN_ON(1); + list_del(&dev->unreg_list); + continue; + } + dev->dismantle = true; + BUG_ON(dev->reg_state != NETREG_REGISTERED); + } - case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; + /* If device is running, close it first. */ + list_for_each_entry(dev, head, unreg_list) + list_add_tail(&dev->close_list, &close_head); + dev_close_many(&close_head); - case SIOCSIFMAP: - if (dev->set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return dev->set_config(dev, &ifr->ifr_map); - } - return -EOPNOTSUPP; - - case SIOCADDMULTI: - if (!dev->set_multicast_list || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); - - case SIOCDELMULTI: - if (!dev->set_multicast_list || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); - - case SIOCGIFINDEX: - ifr->ifr_ifindex = dev->ifindex; - return 0; + list_for_each_entry(dev, head, unreg_list) { + /* And unlink it from device chain. */ + unlist_netdevice(dev); - case SIOCGIFTXQLEN: - ifr->ifr_qlen = dev->tx_queue_len; - return 0; + dev->reg_state = NETREG_UNREGISTERING; + } - case SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; + synchronize_net(); - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); + list_for_each_entry(dev, head, unreg_list) { + /* Shutdown queueing discipline. */ + dev_shutdown(dev); + + + /* Notify protocols, that we are about to destroy + this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); /* - * Unknown or private ioctl + * Flush the unicast and multicast chains */ + dev_uc_flush(dev); + dev_mc_flush(dev); - default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || - cmd == SIOCBONDRELEASE || - cmd == SIOCBONDSETHWADDR || - cmd == SIOCBONDSLAVEINFOQUERY || - cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCWANDEV) { - err = -EOPNOTSUPP; - if (dev->do_ioctl) { - if (netif_device_present(dev)) - err = dev->do_ioctl(dev, ifr, - cmd); - else - err = -ENODEV; - } - } else - err = -EINVAL; + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); + + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); + + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif } - return err; + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) + dev_put(dev); } -/* - * This function handles all "interface"-type I/O control requests. The actual - * 'doing' part of this is dev_ifsioc above. - */ +static void rollback_registered(struct net_device *dev) +{ + LIST_HEAD(single); -/** - * dev_ioctl - network device ioctl - * @cmd: command to issue - * @arg: pointer to a struct ifreq in user space - * - * Issue ioctl functions to devices. This is normally called by the - * user space syscall interfaces but can sometimes be useful for - * other purposes. The return value is the return from the syscall if - * positive or a negative errno code on error. - */ + list_add(&dev->unreg_list, &single); + rollback_registered_many(&single); + list_del(&single); +} -int dev_ioctl(unsigned int cmd, void __user *arg) +static netdev_features_t netdev_fix_features(struct net_device *dev, + netdev_features_t features) { - struct ifreq ifr; - int ret; - char *colon; + /* Fix illegal checksum combinations */ + if ((features & NETIF_F_HW_CSUM) && + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_warn(dev, "mixed HW and IP checksum settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); + } - /* One special case: SIOCGIFCONF takes ifconf argument - and requires shared lock, because it sleeps writing - to user space. - */ + /* TSO requires that SG is present as well. */ + if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); + features &= ~NETIF_F_ALL_TSO; + } - if (cmd == SIOCGIFCONF) { - rtnl_shlock(); - ret = dev_ifconf((char __user *) arg); - rtnl_shunlock(); - return ret; + if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IP_CSUM)) { + netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO; + features &= ~NETIF_F_TSO_ECN; } - if (cmd == SIOCGIFNAME) - return dev_ifname((struct ifreq __user *)arg); - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; + if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IPV6_CSUM)) { + netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO6; + } - ifr.ifr_name[IFNAMSIZ-1] = 0; + /* TSO ECN requires that TSO is present as well. */ + if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) + features &= ~NETIF_F_TSO_ECN; - colon = strchr(ifr.ifr_name, ':'); - if (colon) - *colon = 0; + /* Software GSO depends on SG. */ + if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); + features &= ~NETIF_F_GSO; + } - /* - * See which interface the caller is talking about. - */ + /* UFO needs SG and checksumming */ + if (features & NETIF_F_UFO) { + /* maybe split UFO into V4 and V6? */ + if (!((features & NETIF_F_GEN_CSUM) || + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_dbg(dev, + "Dropping NETIF_F_UFO since no checksum offload features.\n"); + features &= ~NETIF_F_UFO; + } - switch (cmd) { - /* - * These ioctl calls: - * - can be done by all. - * - atomic and do not require locking. - * - return a value - */ - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFHWADDR: - case SIOCGIFSLAVE: - case SIOCGIFMAP: - case SIOCGIFINDEX: - case SIOCGIFTXQLEN: - dev_load(ifr.ifr_name); - read_lock(&dev_base_lock); - ret = dev_ifsioc(&ifr, cmd); - read_unlock(&dev_base_lock); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + if (!(features & NETIF_F_SG)) { + netdev_dbg(dev, + "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); + features &= ~NETIF_F_UFO; + } + } - case SIOCETHTOOL: - dev_load(ifr.ifr_name); - rtnl_lock(); - ret = dev_ethtool(&ifr); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; +#ifdef CONFIG_NET_RX_BUSY_POLL + if (dev->netdev_ops->ndo_busy_poll) + features |= NETIF_F_BUSY_POLL; + else +#endif + features &= ~NETIF_F_BUSY_POLL; - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - return a value - */ - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSIFNAME: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - dev_load(ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(&ifr, cmd); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + return features; +} - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFFLAGS: - case SIOCSIFMETRIC: - case SIOCSIFMTU: - case SIOCSIFMAP: - case SIOCSIFHWADDR: - case SIOCSIFSLAVE: - case SIOCADDMULTI: - case SIOCDELMULTI: - case SIOCSIFHWBROADCAST: - case SIOCSIFTXQLEN: - case SIOCSMIIREG: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: - case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - dev_load(ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(&ifr, cmd); - rtnl_unlock(); - return ret; +int __netdev_update_features(struct net_device *dev) +{ + netdev_features_t features; + int err = 0; - case SIOCGIFMEM: - /* Get the per device memory space. We can add this but - * currently do not support it */ - case SIOCSIFMEM: - /* Set the per device memory buffer space. - * Not applicable in our case */ - case SIOCSIFLINK: - return -EINVAL; + ASSERT_RTNL(); - /* - * Unknown or private ioctl. - */ - default: - if (cmd == SIOCWANDEV || - (cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15)) { - dev_load(ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(&ifr, cmd); - rtnl_unlock(); - if (!ret && copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } -#ifdef WIRELESS_EXT - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { - /* If command is `set a parameter', or - * `get the encoding parameters', check if - * the user has the right to do it */ - if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE) { - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - } - dev_load(ifr.ifr_name); - rtnl_lock(); - /* Follow me in net/core/wireless.c */ - ret = wireless_process_ioctl(&ifr, cmd); - rtnl_unlock(); - if (IW_IS_GET(cmd) && - copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } -#endif /* WIRELESS_EXT */ - return -EINVAL; + features = netdev_get_wanted_features(dev); + + if (dev->netdev_ops->ndo_fix_features) + features = dev->netdev_ops->ndo_fix_features(dev, features); + + /* driver might be less strict about feature dependencies */ + features = netdev_fix_features(dev, features); + + if (dev->features == features) + return 0; + + netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", + &dev->features, &features); + + if (dev->netdev_ops->ndo_set_features) + err = dev->netdev_ops->ndo_set_features(dev, features); + + if (unlikely(err < 0)) { + netdev_err(dev, + "set_features() failed (%d); wanted %pNF, left %pNF\n", + err, &features, &dev->features); + return -1; } + + if (!err) + dev->features = features; + + return 1; } +/** + * netdev_update_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications if it + * has changed. Should be called after driver or hardware dependent + * conditions might have changed that influence the features. + */ +void netdev_update_features(struct net_device *dev) +{ + if (__netdev_update_features(dev)) + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_update_features); /** - * dev_new_index - allocate an ifindex + * netdev_change_features - recalculate device features + * @dev: the device to check * - * Returns a suitable unique value for a new device interface - * number. The caller must hold the rtnl semaphore or the - * dev_base_lock to be sure it remains unique. + * Recalculate dev->features set and send notifications even + * if they have not changed. Should be called instead of + * netdev_update_features() if also dev->vlan_features might + * have changed to allow the changes to be propagated to stacked + * VLAN devices. */ -static int dev_new_index(void) +void netdev_change_features(struct net_device *dev) { - static int ifindex; - for (;;) { - if (++ifindex <= 0) - ifindex = 1; - if (!__dev_get_by_index(ifindex)) - return ifindex; + __netdev_update_features(dev); + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_change_features); + +/** + * netif_stacked_transfer_operstate - transfer operstate + * @rootdev: the root or lower level device to transfer state from + * @dev: the device to transfer operstate to + * + * Transfer operational state from root to device. This is normally + * called when a stacking relationship exists between the root + * device and the device(a leaf device). + */ +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev) +{ + if (rootdev->operstate == IF_OPER_DORMANT) + netif_dormant_on(dev); + else + netif_dormant_off(dev); + + if (netif_carrier_ok(rootdev)) { + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); + } else { + if (netif_carrier_ok(dev)) + netif_carrier_off(dev); } } +EXPORT_SYMBOL(netif_stacked_transfer_operstate); -static int dev_boot_phase = 1; +#ifdef CONFIG_SYSFS +static int netif_alloc_rx_queues(struct net_device *dev) +{ + unsigned int i, count = dev->num_rx_queues; + struct netdev_rx_queue *rx; -/* Delayed registration/unregisteration */ -static DEFINE_SPINLOCK(net_todo_list_lock); -static struct list_head net_todo_list = LIST_HEAD_INIT(net_todo_list); + BUG_ON(count < 1); + + rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); + if (!rx) + return -ENOMEM; + + dev->_rx = rx; -static inline void net_set_todo(struct net_device *dev) + for (i = 0; i < count; i++) + rx[i].dev = dev; + return 0; +} +#endif + +static void netdev_init_one_queue(struct net_device *dev, + struct netdev_queue *queue, void *_unused) { - spin_lock(&net_todo_list_lock); - list_add_tail(&dev->todo_list, &net_todo_list); - spin_unlock(&net_todo_list_lock); + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + queue->xmit_lock_owner = -1; + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); + queue->dev = dev; +#ifdef CONFIG_BQL + dql_init(&queue->dql, HZ); +#endif +} + +static void netif_free_tx_queues(struct net_device *dev) +{ + kvfree(dev->_tx); +} + +static int netif_alloc_netdev_queues(struct net_device *dev) +{ + unsigned int count = dev->num_tx_queues; + struct netdev_queue *tx; + size_t sz = count * sizeof(*tx); + + BUG_ON(count < 1 || count > 0xffff); + + tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!tx) { + tx = vzalloc(sz); + if (!tx) + return -ENOMEM; + } + dev->_tx = tx; + + netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); + spin_lock_init(&dev->tx_global_lock); + + return 0; } /** @@ -2658,98 +6011,89 @@ static inline void net_set_todo(struct net_device *dev) int register_netdevice(struct net_device *dev) { - struct hlist_head *head; - struct hlist_node *p; int ret; + struct net *net = dev_net(dev); BUG_ON(dev_boot_phase); ASSERT_RTNL(); + might_sleep(); + /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); + BUG_ON(!net); - spin_lock_init(&dev->queue_lock); - spin_lock_init(&dev->xmit_lock); - dev->xmit_lock_owner = -1; -#ifdef CONFIG_NET_CLS_ACT - spin_lock_init(&dev->ingress_lock); -#endif - - ret = alloc_divert_blk(dev); - if (ret) - goto out; + spin_lock_init(&dev->addr_list_lock); + netdev_set_addr_lockdep_class(dev); dev->iflink = -1; + ret = dev_get_valid_name(net, dev, dev->name); + if (ret < 0) + goto out; + /* Init, if this function is available */ - if (dev->init) { - ret = dev->init(dev); + if (dev->netdev_ops->ndo_init) { + ret = dev->netdev_ops->ndo_init(dev); if (ret) { if (ret > 0) ret = -EIO; - goto out_err; + goto out; } } - - if (!dev_valid_name(dev->name)) { + + if (((dev->hw_features | dev->features) & + NETIF_F_HW_VLAN_CTAG_FILTER) && + (!dev->netdev_ops->ndo_vlan_rx_add_vid || + !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { + netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); ret = -EINVAL; - goto out_err; + goto err_uninit; } - dev->ifindex = dev_new_index(); + ret = -EBUSY; + if (!dev->ifindex) + dev->ifindex = dev_new_index(net); + else if (__dev_get_by_index(net, dev->ifindex)) + goto err_uninit; + if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Check for existence of name */ - head = dev_name_hash(dev->name); - hlist_for_each(p, head) { - struct net_device *d - = hlist_entry(p, struct net_device, name_hlist); - if (!strncmp(d->name, dev->name, IFNAMSIZ)) { - ret = -EEXIST; - goto out_err; - } - } + /* Transfer changeable features to wanted_features and enable + * software offloads (GSO and GRO). + */ + dev->hw_features |= NETIF_F_SOFT_FEATURES; + dev->features |= NETIF_F_SOFT_FEATURES; + dev->wanted_features = dev->features & dev->hw_features; - /* Fix illegal SG+CSUM combinations. */ - if ((dev->features & NETIF_F_SG) && - !(dev->features & (NETIF_F_IP_CSUM | - NETIF_F_NO_CSUM | - NETIF_F_HW_CSUM))) { - printk("%s: Dropping NETIF_F_SG since no checksum feature.\n", - dev->name); - dev->features &= ~NETIF_F_SG; + if (!(dev->flags & IFF_LOOPBACK)) { + dev->hw_features |= NETIF_F_NOCACHE_COPY; } - /* TSO requires that SG is present as well. */ - if ((dev->features & NETIF_F_TSO) && - !(dev->features & NETIF_F_SG)) { - printk("%s: Dropping NETIF_F_TSO since no SG feature.\n", - dev->name); - dev->features &= ~NETIF_F_TSO; - } - if (dev->features & NETIF_F_UFO) { - if (!(dev->features & NETIF_F_HW_CSUM)) { - printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no " - "NETIF_F_HW_CSUM feature.\n", - dev->name); - dev->features &= ~NETIF_F_UFO; - } - if (!(dev->features & NETIF_F_SG)) { - printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no " - "NETIF_F_SG feature.\n", - dev->name); - dev->features &= ~NETIF_F_UFO; - } - } + /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. + */ + dev->vlan_features |= NETIF_F_HIGHDMA; - /* - * nil rebuild_header routine, - * that should be never called and used as just bug trap. + /* Make NETIF_F_SG inheritable to tunnel devices. + */ + dev->hw_enc_features |= NETIF_F_SG; + + /* Make NETIF_F_SG inheritable to MPLS. */ + dev->mpls_features |= NETIF_F_SG; + + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); + ret = notifier_to_errno(ret); + if (ret) + goto err_uninit; + + ret = netdev_register_kobject(dev); + if (ret) + goto err_uninit; + dev->reg_state = NETREG_REGISTERED; - if (!dev->rebuild_header) - dev->rebuild_header = default_rebuild_header; + __netdev_update_features(dev); /* * Default initial state at registry is that the @@ -2758,30 +6102,85 @@ int register_netdevice(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); - dev->next = NULL; + linkwatch_init_dev(dev); + dev_init_scheduler(dev); - write_lock_bh(&dev_base_lock); - *dev_tail = dev; - dev_tail = &dev->next; - hlist_add_head(&dev->name_hlist, head); - hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex)); dev_hold(dev); - dev->reg_state = NETREG_REGISTERING; - write_unlock_bh(&dev_base_lock); + list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); - /* Notify protocols, that a new device appeared. */ - notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev); + /* If the device has permanent device address, driver should + * set dev_addr and also addr_assign_type should be set to + * NET_ADDR_PERM (default value). + */ + if (dev->addr_assign_type == NET_ADDR_PERM) + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); - /* Finish registration after unlock */ - net_set_todo(dev); - ret = 0; + /* Notify protocols, that a new device appeared. */ + ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); + ret = notifier_to_errno(ret); + if (ret) { + rollback_registered(dev); + dev->reg_state = NETREG_UNREGISTERED; + } + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); out: return ret; -out_err: - free_divert_blk(dev); + +err_uninit: + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); goto out; } +EXPORT_SYMBOL(register_netdevice); + +/** + * init_dummy_netdev - init a dummy network device for NAPI + * @dev: device to init + * + * This takes a network device structure and initialize the minimum + * amount of fields so it can be used to schedule NAPI polls without + * registering a full blown interface. This is to be used by drivers + * that need to tie several hardware interfaces to a single NAPI + * poll scheduler due to HW limitations. + */ +int init_dummy_netdev(struct net_device *dev) +{ + /* Clear everything. Note we don't initialize spinlocks + * are they aren't supposed to be taken by any of the + * NAPI code and this dummy netdev is supposed to be + * only ever used for NAPI polls + */ + memset(dev, 0, sizeof(struct net_device)); + + /* make sure we BUG if trying to hit standard + * register/unregister code path + */ + dev->reg_state = NETREG_DUMMY; + + /* NAPI wants this */ + INIT_LIST_HEAD(&dev->napi_list); + + /* a dummy interface is started by default */ + set_bit(__LINK_STATE_PRESENT, &dev->state); + set_bit(__LINK_STATE_START, &dev->state); + + /* Note : We dont allocate pcpu_refcnt for dummy devices, + * because users of this 'device' dont need to change + * its refcount. + */ + + return 0; +} +EXPORT_SYMBOL_GPL(init_dummy_netdev); + /** * register_netdev - register a network device @@ -2792,7 +6191,7 @@ out_err: * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * - * This is a wrapper around register_netdev that takes the rtnl semaphore + * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ @@ -2801,35 +6200,25 @@ int register_netdev(struct net_device *dev) int err; rtnl_lock(); - - /* - * If the name is a format string the caller wants us to do a - * name allocation. - */ - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto out; - } - - /* - * Back compatibility hook. Kill this one in 2.5 - */ - if (dev->name[0] == 0 || dev->name[0] == ' ') { - err = dev_alloc_name(dev, "eth%d"); - if (err < 0) - goto out; - } - err = register_netdevice(dev); -out: rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdev); -/* +int netdev_refcnt_read(const struct net_device *dev) +{ + int i, refcnt = 0; + + for_each_possible_cpu(i) + refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); + return refcnt; +} +EXPORT_SYMBOL(netdev_refcnt_read); + +/** * netdev_wait_allrefs - wait until all references are gone. + * @dev: target net_device * * This is called when unregistering network devices. * @@ -2837,21 +6226,30 @@ EXPORT_SYMBOL(register_netdev); * for netdevice notification, and cleanup and put back the * reference if they receive an UNREGISTER event. * We can get stuck here if buggy protocols don't correctly - * call dev_put. + * call dev_put. */ static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; + int refcnt; + + linkwatch_forget_dev(dev); rebroadcast_time = warning_time = jiffies; - while (atomic_read(&dev->refcnt) != 0) { + refcnt = netdev_refcnt_read(dev); + + while (refcnt != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { - rtnl_shlock(); + rtnl_lock(); /* Rebroadcast unregister notification */ - notifier_call_chain(&netdev_chain, - NETDEV_UNREGISTER, dev); + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + __rtnl_unlock(); + rcu_barrier(); + rtnl_lock(); + + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events @@ -2863,18 +6261,18 @@ static void netdev_wait_allrefs(struct net_device *dev) linkwatch_run_queue(); } - rtnl_shunlock(); + __rtnl_unlock(); rebroadcast_time = jiffies; } msleep(250); + refcnt = netdev_refcnt_read(dev); + if (time_after(jiffies, warning_time + 10 * HZ)) { - printk(KERN_EMERG "unregister_netdevice: " - "waiting for %s to become free. Usage " - "count = %d\n", - dev->name, atomic_read(&dev->refcnt)); + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, refcnt); warning_time = jiffies; } } @@ -2894,274 +6292,522 @@ static void netdev_wait_allrefs(struct net_device *dev) * free_netdev(y1); * free_netdev(y2); * - * We are invoked by rtnl_unlock() after it drops the semaphore. + * We are invoked by rtnl_unlock(). * This allows us to deal with problems: - * 1) We can create/delete sysfs objects which invoke hotplug + * 1) We can delete sysfs objects which invoke hotplug * without deadlocking with linkwatch via keventd. * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. + * + * We must not return until all unregister events added during + * the interval the lock was held have been completed. */ -static DECLARE_MUTEX(net_todo_run_mutex); void netdev_run_todo(void) { - struct list_head list = LIST_HEAD_INIT(list); - int err; + struct list_head list; + /* Snapshot list, allow later requests */ + list_replace_init(&net_todo_list, &list); - /* Need to guard against multiple cpu's getting out of order. */ - down(&net_todo_run_mutex); + __rtnl_unlock(); - /* Not safe to do outside the semaphore. We must not return - * until all unregister events invoked by the local processor - * have been completed (either by this todo run, or one on - * another cpu). - */ - if (list_empty(&net_todo_list)) - goto out; - /* Snapshot list, allow later requests */ - spin_lock(&net_todo_list_lock); - list_splice_init(&net_todo_list, &list); - spin_unlock(&net_todo_list_lock); - + /* Wait for rcu callbacks to finish before next phase */ + if (!list_empty(&list)) + rcu_barrier(); + while (!list_empty(&list)) { struct net_device *dev - = list_entry(list.next, struct net_device, todo_list); + = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); - switch(dev->reg_state) { - case NETREG_REGISTERING: - err = netdev_register_sysfs(dev); - if (err) - printk(KERN_ERR "%s: failed sysfs registration (%d)\n", - dev->name, err); - dev->reg_state = NETREG_REGISTERED; - break; + rtnl_lock(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + __rtnl_unlock(); + + if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { + pr_err("network todo '%s' but state %d\n", + dev->name, dev->reg_state); + dump_stack(); + continue; + } - case NETREG_UNREGISTERING: - netdev_unregister_sysfs(dev); - dev->reg_state = NETREG_UNREGISTERED; + dev->reg_state = NETREG_UNREGISTERED; - netdev_wait_allrefs(dev); + on_each_cpu(flush_backlog, dev, 1); - /* paranoia */ - BUG_ON(atomic_read(&dev->refcnt)); - BUG_TRAP(!dev->ip_ptr); - BUG_TRAP(!dev->ip6_ptr); - BUG_TRAP(!dev->dn_ptr); + netdev_wait_allrefs(dev); + /* paranoia */ + BUG_ON(netdev_refcnt_read(dev)); + WARN_ON(rcu_access_pointer(dev->ip_ptr)); + WARN_ON(rcu_access_pointer(dev->ip6_ptr)); + WARN_ON(dev->dn_ptr); - /* It must be the very last action, - * after this 'dev' may point to freed up memory. - */ - if (dev->destructor) - dev->destructor(dev); - break; + if (dev->destructor) + dev->destructor(dev); - default: - printk(KERN_ERR "network todo '%s' but state %d\n", - dev->name, dev->reg_state); - break; - } + /* Report a network device has been unregistered */ + rtnl_lock(); + dev_net(dev)->dev_unreg_count--; + __rtnl_unlock(); + wake_up(&netdev_unregistering_wq); + + /* Free network device */ + kobject_put(&dev->dev.kobj); } +} -out: - up(&net_todo_run_mutex); +/* Convert net_device_stats to rtnl_link_stats64. They have the same + * fields in the same order, with only the type differing. + */ +void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, + const struct net_device_stats *netdev_stats) +{ +#if BITS_PER_LONG == 64 + BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats)); + memcpy(stats64, netdev_stats, sizeof(*stats64)); +#else + size_t i, n = sizeof(*stats64) / sizeof(u64); + const unsigned long *src = (const unsigned long *)netdev_stats; + u64 *dst = (u64 *)stats64; + + BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) != + sizeof(*stats64) / sizeof(u64)); + for (i = 0; i < n; i++) + dst[i] = src[i]; +#endif } +EXPORT_SYMBOL(netdev_stats_to_stats64); /** - * alloc_netdev - allocate network device + * dev_get_stats - get network device statistics + * @dev: device to get statistics from + * @storage: place to store stats + * + * Get network statistics from device. Return @storage. + * The device driver may provide its own method by setting + * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; + * otherwise the internal statistics structure is used. + */ +struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *storage) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_get_stats64) { + memset(storage, 0, sizeof(*storage)); + ops->ndo_get_stats64(dev, storage); + } else if (ops->ndo_get_stats) { + netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); + } else { + 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); + +struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) +{ + struct netdev_queue *queue = dev_ingress_queue(dev); + +#ifdef CONFIG_NET_CLS_ACT + if (queue) + return queue; + queue = kzalloc(sizeof(*queue), GFP_KERNEL); + if (!queue) + return NULL; + netdev_init_one_queue(dev, queue, NULL); + queue->qdisc = &noop_qdisc; + queue->qdisc_sleeping = &noop_qdisc; + rcu_assign_pointer(dev->ingress_queue, queue); +#endif + return queue; +} + +static const struct ethtool_ops default_ethtool_ops; + +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops) +{ + if (dev->ethtool_ops == &default_ethtool_ops) + dev->ethtool_ops = ops; +} +EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); + +void netdev_freemem(struct net_device *dev) +{ + char *addr = (char *)dev - dev->padded; + + kvfree(addr); +} + +/** + * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @setup: callback to initialize device + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use - * and performs basic initialization. + * and performs basic initialization. Also allocates subqueue structs + * for each queue on the device. */ -struct net_device *alloc_netdev(int sizeof_priv, const char *name, - void (*setup)(struct net_device *)) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs) { - void *p; struct net_device *dev; - int alloc_size; + size_t alloc_size; + struct net_device *p; - /* ensure 32-byte alignment of both the device and private area */ - alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; - alloc_size += sizeof_priv + NETDEV_ALIGN_CONST; + BUG_ON(strlen(name) >= sizeof(dev->name)); - p = kmalloc(alloc_size, GFP_KERNEL); - if (!p) { - printk(KERN_ERR "alloc_dev: Unable to allocate device.\n"); + if (txqs < 1) { + pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); + return NULL; + } + +#ifdef CONFIG_SYSFS + if (rxqs < 1) { + pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } - memset(p, 0, alloc_size); +#endif + + alloc_size = sizeof(struct net_device); + if (sizeof_priv) { + /* ensure 32-byte alignment of private area */ + alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); + alloc_size += sizeof_priv; + } + /* ensure 32-byte alignment of whole construct */ + alloc_size += NETDEV_ALIGN - 1; + + p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!p) + p = vzalloc(alloc_size); + if (!p) + return NULL; - dev = (struct net_device *) - (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); + dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; - if (sizeof_priv) - dev->priv = netdev_priv(dev); + dev->pcpu_refcnt = alloc_percpu(int); + if (!dev->pcpu_refcnt) + goto free_dev; + + if (dev_addr_init(dev)) + goto free_pcpu; + + dev_mc_init(dev); + dev_uc_init(dev); + + dev_net_set(dev, &init_net); + + dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_segs = GSO_MAX_SEGS; + INIT_LIST_HEAD(&dev->napi_list); + INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->close_list); + INIT_LIST_HEAD(&dev->link_watch_list); + INIT_LIST_HEAD(&dev->adj_list.upper); + INIT_LIST_HEAD(&dev->adj_list.lower); + INIT_LIST_HEAD(&dev->all_adj_list.upper); + INIT_LIST_HEAD(&dev->all_adj_list.lower); + dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); + + dev->num_tx_queues = txqs; + dev->real_num_tx_queues = txqs; + if (netif_alloc_netdev_queues(dev)) + goto free_all; + +#ifdef CONFIG_SYSFS + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; + if (netif_alloc_rx_queues(dev)) + goto free_all; +#endif + strcpy(dev->name, name); + dev->group = INIT_NETDEV_GROUP; + if (!dev->ethtool_ops) + dev->ethtool_ops = &default_ethtool_ops; return dev; + +free_all: + free_netdev(dev); + return NULL; + +free_pcpu: + free_percpu(dev->pcpu_refcnt); +free_dev: + netdev_freemem(dev); + return NULL; } -EXPORT_SYMBOL(alloc_netdev); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device * @dev: device * - * This function does the last stage of destroying an allocated device - * interface. The reference to the device object is released. + * This function does the last stage of destroying an allocated device + * interface. The reference to the device object is released. * If this is the last reference then it will be freed. */ void free_netdev(struct net_device *dev) { + struct napi_struct *p, *n; + + release_net(dev_net(dev)); + + netif_free_tx_queues(dev); #ifdef CONFIG_SYSFS - /* Compatiablity with error handling in drivers */ + kfree(dev->_rx); +#endif + + kfree(rcu_dereference_protected(dev->ingress_queue, 1)); + + /* Flush device addresses */ + dev_addr_flush(dev); + + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) + netif_napi_del(p); + + free_percpu(dev->pcpu_refcnt); + dev->pcpu_refcnt = NULL; + + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { - kfree((char *)dev - dev->padded); + netdev_freemem(dev); return; } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); dev->reg_state = NETREG_RELEASED; - /* will free via class release */ - class_device_put(&dev->class_dev); -#else - kfree((char *)dev - dev->padded); -#endif + /* will free via device release */ + put_device(&dev->dev); } - -/* Synchronize with packet receive processing. */ -void synchronize_net(void) +EXPORT_SYMBOL(free_netdev); + +/** + * synchronize_net - Synchronize with packet receive processing + * + * Wait for packets currently being received to be done. + * Does not block later packets from starting. + */ +void synchronize_net(void) { might_sleep(); - synchronize_rcu(); + if (rtnl_is_locked()) + synchronize_rcu_expedited(); + else + synchronize_rcu(); } +EXPORT_SYMBOL(synchronize_net); /** - * unregister_netdevice - remove device from the kernel + * unregister_netdevice_queue - remove device from the kernel * @dev: device + * @head: list * * This function shuts down a device interface and removes it - * from the kernel tables. On success 0 is returned, on a failure - * a negative errno code is returned. + * from the kernel tables. + * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ -int unregister_netdevice(struct net_device *dev) +void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { - struct net_device *d, **dp; - - BUG_ON(dev_boot_phase); ASSERT_RTNL(); - /* Some devices call without registering for initialization unwind. */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - printk(KERN_DEBUG "unregister_netdevice: device %s/%p never " - "was registered\n", dev->name, dev); - return -ENODEV; + if (head) { + list_move_tail(&dev->unreg_list, head); + } else { + rollback_registered(dev); + /* Finish processing unregister after unlock */ + net_set_todo(dev); } +} +EXPORT_SYMBOL(unregister_netdevice_queue); - BUG_ON(dev->reg_state != NETREG_REGISTERED); +/** + * unregister_netdevice_many - unregister many devices + * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. + */ +void unregister_netdevice_many(struct list_head *head) +{ + struct net_device *dev; - /* If device is running, close it first. */ - if (dev->flags & IFF_UP) - dev_close(dev); - - /* And unlink it from device chain. */ - for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) { - if (d == dev) { - write_lock_bh(&dev_base_lock); - hlist_del(&dev->name_hlist); - hlist_del(&dev->index_hlist); - if (dev_tail == &dev->next) - dev_tail = dp; - *dp = d->next; - write_unlock_bh(&dev_base_lock); - break; - } + if (!list_empty(head)) { + rollback_registered_many(head); + list_for_each_entry(dev, head, unreg_list) + net_set_todo(dev); + list_del(head); } - if (!d) { - printk(KERN_ERR "unregister net_device: '%s' not found\n", - dev->name); - return -ENODEV; +} +EXPORT_SYMBOL(unregister_netdevice_many); + +/** + * unregister_netdev - remove device from the kernel + * @dev: device + * + * This function shuts down a device interface and removes it + * from the kernel tables. + * + * This is just a wrapper for unregister_netdevice that takes + * the rtnl semaphore. In general you want to use this and not + * unregister_netdevice. + */ +void unregister_netdev(struct net_device *dev) +{ + rtnl_lock(); + unregister_netdevice(dev); + rtnl_unlock(); +} +EXPORT_SYMBOL(unregister_netdev); + +/** + * dev_change_net_namespace - move device to different nethost namespace + * @dev: device + * @net: network namespace + * @pat: If not NULL name pattern to try if the current device name + * is already taken in the destination network namespace. + * + * This function shuts down a device interface and moves it + * to a new network namespace. On success 0 is returned, on + * a failure a netagive errno code is returned. + * + * Callers must hold the rtnl semaphore. + */ + +int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) +{ + int err; + + ASSERT_RTNL(); + + /* Don't allow namespace local devices to be moved. */ + err = -EINVAL; + if (dev->features & NETIF_F_NETNS_LOCAL) + goto out; + + /* Ensure the device has been registrered */ + if (dev->reg_state != NETREG_REGISTERED) + goto out; + + /* Get out if there is nothing todo */ + err = 0; + if (net_eq(dev_net(dev), net)) + goto out; + + /* Pick the destination device name, and ensure + * we can use it in the destination network namespace. + */ + err = -EEXIST; + if (__dev_get_by_name(net, dev->name)) { + /* We get here if we can't use the current device name */ + if (!pat) + goto out; + if (dev_get_valid_name(net, dev, pat) < 0) + goto out; } - dev->reg_state = NETREG_UNREGISTERING; + /* + * And now a mini version of register_netdevice unregister_netdevice. + */ + + /* If device is running close it first. */ + dev_close(dev); + + /* And unlink it from device chain */ + err = -ENODEV; + unlist_netdevice(dev); synchronize_net(); /* Shutdown queueing discipline. */ dev_shutdown(dev); - /* Notify protocols, that we are about to destroy this device. They should clean all the things. + + Note that dev->reg_state stays at NETREG_REGISTERED. + This is wanted because this way 8021q and macvlan know + the device is just moving and can keep their slaves up. */ - notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev); - + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + rcu_barrier(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + /* - * Flush the multicast chain + * Flush the unicast and multicast chains */ - dev_mc_discard(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); - if (dev->uninit) - dev->uninit(dev); + /* Send a netdev-removed uevent to the old namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); - /* Notifier chain MUST detach us from master device. */ - BUG_TRAP(!dev->master); + /* Actually switch the network namespace */ + dev_net_set(dev, net); - free_divert_blk(dev); + /* If there is an ifindex conflict assign a new one */ + if (__dev_get_by_index(net, dev->ifindex)) { + int iflink = (dev->iflink == dev->ifindex); + dev->ifindex = dev_new_index(net); + if (iflink) + dev->iflink = dev->ifindex; + } - /* Finish processing unregister after unlock */ - net_set_todo(dev); + /* Send a netdev-add uevent to the new namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_ADD); - synchronize_net(); + /* Fixup kobjects */ + err = device_rename(&dev->dev, dev->name); + WARN_ON(err); - dev_put(dev); - return 0; -} + /* Add the device back in the hashes */ + list_netdevice(dev); -/** - * unregister_netdev - remove device from the kernel - * @dev: device - * - * This function shuts down a device interface and removes it - * from the kernel tables. On success 0 is returned, on a failure - * a negative errno code is returned. - * - * This is just a wrapper for unregister_netdevice that takes - * the rtnl semaphore. In general you want to use this and not - * unregister_netdevice. - */ -void unregister_netdev(struct net_device *dev) -{ - rtnl_lock(); - unregister_netdevice(dev); - rtnl_unlock(); -} + /* Notify protocols, that a new device appeared. */ + call_netdevice_notifiers(NETDEV_REGISTER, dev); -EXPORT_SYMBOL(unregister_netdev); + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + + synchronize_net(); + err = 0; +out: + return err; +} +EXPORT_SYMBOL_GPL(dev_change_net_namespace); -#ifdef CONFIG_HOTPLUG_CPU static int dev_cpu_callback(struct notifier_block *nfb, unsigned long action, void *ocpu) { struct sk_buff **list_skb; - struct net_device **list_net; struct sk_buff *skb; unsigned int cpu, oldcpu = (unsigned long)ocpu; struct softnet_data *sd, *oldsd; - if (action != CPU_DEAD) + if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) return NOTIFY_OK; local_irq_disable(); @@ -3177,26 +6823,301 @@ static int dev_cpu_callback(struct notifier_block *nfb, *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; - /* Find end of our output_queue. */ - list_net = &sd->output_queue; - while (*list_net) - list_net = &(*list_net)->next_sched; /* Append output queue from offline CPU. */ - *list_net = oldsd->output_queue; - oldsd->output_queue = NULL; + if (oldsd->output_queue) { + *sd->output_queue_tailp = oldsd->output_queue; + sd->output_queue_tailp = oldsd->output_queue_tailp; + oldsd->output_queue = NULL; + oldsd->output_queue_tailp = &oldsd->output_queue; + } + /* Append NAPI poll list from offline CPU. */ + if (!list_empty(&oldsd->poll_list)) { + list_splice_init(&oldsd->poll_list, &sd->poll_list); + raise_softirq_irqoff(NET_RX_SOFTIRQ); + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) - netif_rx(skb); + while ((skb = __skb_dequeue(&oldsd->process_queue))) { + netif_rx_internal(skb); + input_queue_head_incr(oldsd); + } + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + netif_rx_internal(skb); + input_queue_head_incr(oldsd); + } return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ +/** + * netdev_increment_features - increment feature set by one + * @all: current feature set + * @one: new feature set + * @mask: mask feature set + * + * Computes a new feature set after adding a device with feature set + * @one to the master device with current feature set @all. Will not + * enable anything that is off in @mask. Returns the new feature set. + */ +netdev_features_t netdev_increment_features(netdev_features_t all, + netdev_features_t one, netdev_features_t mask) +{ + if (mask & NETIF_F_GEN_CSUM) + mask |= NETIF_F_ALL_CSUM; + mask |= NETIF_F_VLAN_CHALLENGED; + + all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all &= one | ~NETIF_F_ALL_FOR_ALL; + + /* If one device supports hw checksumming, set for all. */ + if (all & NETIF_F_GEN_CSUM) + all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + + return all; +} +EXPORT_SYMBOL(netdev_increment_features); + +static struct hlist_head * __net_init netdev_create_hash(void) +{ + int i; + struct hlist_head *hash; + + hash = kmalloc(sizeof(*hash) * NETDEV_HASHENTRIES, GFP_KERNEL); + if (hash != NULL) + for (i = 0; i < NETDEV_HASHENTRIES; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; +} + +/* Initialize per network namespace state */ +static int __net_init netdev_init(struct net *net) +{ + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); + + net->dev_name_head = netdev_create_hash(); + if (net->dev_name_head == NULL) + goto err_name; + + net->dev_index_head = netdev_create_hash(); + if (net->dev_index_head == NULL) + goto err_idx; + + return 0; + +err_idx: + kfree(net->dev_name_head); +err_name: + return -ENOMEM; +} + +/** + * netdev_drivername - network driver for the device + * @dev: network device + * + * Determine network driver for device. + */ +const char *netdev_drivername(const struct net_device *dev) +{ + const struct device_driver *driver; + const struct device *parent; + const char *empty = ""; + + parent = dev->dev.parent; + if (!parent) + return empty; + + driver = parent->driver; + if (driver && driver->name) + return driver->name; + return empty; +} + +static int __netdev_printk(const char *level, const struct net_device *dev, + struct va_format *vaf) +{ + int r; + + if (dev && dev->dev.parent) { + r = dev_printk_emit(level[1] - '0', + dev->dev.parent, + "%s %s %s: %pV", + dev_driver_string(dev->dev.parent), + dev_name(dev->dev.parent), + netdev_name(dev), vaf); + } else if (dev) { + r = printk("%s%s: %pV", level, netdev_name(dev), vaf); + } else { + r = printk("%s(NULL net_device): %pV", level, vaf); + } + + return r; +} + +int netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + r = __netdev_printk(level, dev, &vaf); + + va_end(args); + + return r; +} +EXPORT_SYMBOL(netdev_printk); + +#define define_netdev_printk_level(func, level) \ +int func(const struct net_device *dev, const char *fmt, ...) \ +{ \ + int r; \ + struct va_format vaf; \ + va_list args; \ + \ + va_start(args, fmt); \ + \ + vaf.fmt = fmt; \ + vaf.va = &args; \ + \ + r = __netdev_printk(level, dev, &vaf); \ + \ + va_end(args); \ + \ + return r; \ +} \ +EXPORT_SYMBOL(func); + +define_netdev_printk_level(netdev_emerg, KERN_EMERG); +define_netdev_printk_level(netdev_alert, KERN_ALERT); +define_netdev_printk_level(netdev_crit, KERN_CRIT); +define_netdev_printk_level(netdev_err, KERN_ERR); +define_netdev_printk_level(netdev_warn, KERN_WARNING); +define_netdev_printk_level(netdev_notice, KERN_NOTICE); +define_netdev_printk_level(netdev_info, KERN_INFO); + +static void __net_exit netdev_exit(struct net *net) +{ + kfree(net->dev_name_head); + kfree(net->dev_index_head); +} + +static struct pernet_operations __net_initdata netdev_net_ops = { + .init = netdev_init, + .exit = netdev_exit, +}; + +static void __net_exit default_device_exit(struct net *net) +{ + struct net_device *dev, *aux; + /* + * Push all migratable network devices back to the + * initial network namespace + */ + rtnl_lock(); + for_each_netdev_safe(net, dev, aux) { + int err; + char fb_name[IFNAMSIZ]; + + /* Ignore unmoveable devices (i.e. loopback) */ + if (dev->features & NETIF_F_NETNS_LOCAL) + continue; + + /* Leave virtual devices for the generic cleanup */ + if (dev->rtnl_link_ops) + continue; + + /* Push remaining network devices to init_net */ + snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + err = dev_change_net_namespace(dev, &init_net, fb_name); + if (err) { + pr_emerg("%s: failed to move %s to init_net: %d\n", + __func__, dev->name, err); + BUG(); + } + } + rtnl_unlock(); +} + +static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) +{ + /* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace in net_list. + */ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + +static void __net_exit default_device_exit_batch(struct list_head *net_list) +{ + /* At exit all network devices most be removed from a network + * namespace. Do this in the reverse order of registration. + * Do this across as many network namespaces as possible to + * improve batching efficiency. + */ + struct net_device *dev; + struct net *net; + LIST_HEAD(dev_kill_list); + + /* To prevent network device cleanup code from dereferencing + * loopback devices or network devices that have been freed + * wait here for all pending unregistrations to complete, + * before unregistring the loopback device and allowing the + * network namespace be freed. + * + * The netdev todo list containing all network devices + * unregistrations that happen in default_device_exit_batch + * will run in the rtnl_unlock() at the end of + * default_device_exit_batch. + */ + rtnl_lock_unregistering(net_list); + list_for_each_entry(net, net_list, exit_list) { + for_each_netdev_reverse(net, dev) { + if (dev->rtnl_link_ops) + dev->rtnl_link_ops->dellink(dev, &dev_kill_list); + else + unregister_netdevice_queue(dev, &dev_kill_list); + } + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); +} + +static struct pernet_operations __net_initdata default_device_ops = { + .exit = default_device_exit, + .exit_batch = default_device_exit_batch, +}; + /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not @@ -3214,100 +7135,67 @@ static int __init net_dev_init(void) BUG_ON(!dev_boot_phase); - net_random_init(); - if (dev_proc_init()) goto out; - if (netdev_sysfs_init()) + if (netdev_kobject_init()) goto out; INIT_LIST_HEAD(&ptype_all); - for (i = 0; i < 16; i++) + for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); - for (i = 0; i < ARRAY_SIZE(dev_name_head); i++) - INIT_HLIST_HEAD(&dev_name_head[i]); + INIT_LIST_HEAD(&offload_base); - for (i = 0; i < ARRAY_SIZE(dev_index_head); i++) - INIT_HLIST_HEAD(&dev_index_head[i]); + if (register_pernet_subsys(&netdev_net_ops)) + goto out; /* * Initialise the packet receive queues. */ - for (i = 0; i < NR_CPUS; i++) { - struct softnet_data *queue; + for_each_possible_cpu(i) { + struct softnet_data *sd = &per_cpu(softnet_data, i); + + skb_queue_head_init(&sd->input_pkt_queue); + skb_queue_head_init(&sd->process_queue); + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue_tailp = &sd->output_queue; +#ifdef CONFIG_RPS + sd->csd.func = rps_trigger_softirq; + sd->csd.info = sd; + sd->cpu = i; +#endif - queue = &per_cpu(softnet_data, i); - skb_queue_head_init(&queue->input_pkt_queue); - queue->completion_queue = NULL; - INIT_LIST_HEAD(&queue->poll_list); - set_bit(__LINK_STATE_START, &queue->backlog_dev.state); - queue->backlog_dev.weight = weight_p; - queue->backlog_dev.poll = process_backlog; - atomic_set(&queue->backlog_dev.refcnt, 1); + sd->backlog.poll = process_backlog; + sd->backlog.weight = weight_p; } dev_boot_phase = 0; - open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL); - open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL); + /* The loopback device is special if any other network devices + * is present in a network namespace the loopback device must + * be present. Since we now dynamically allocate and free the + * loopback device ensure this invariant is maintained by + * keeping the loopback device as the first device on the + * list of network devices. Ensuring the loopback devices + * is the first device that appears and the last network device + * that disappears. + */ + if (register_pernet_device(&loopback_net_ops)) + goto out; + + if (register_pernet_device(&default_device_ops)) + goto out; + + open_softirq(NET_TX_SOFTIRQ, net_tx_action); + open_softirq(NET_RX_SOFTIRQ, net_rx_action); hotcpu_notifier(dev_cpu_callback, 0); dst_init(); - dev_mcast_init(); rc = 0; out: return rc; } subsys_initcall(net_dev_init); - -EXPORT_SYMBOL(__dev_get_by_index); -EXPORT_SYMBOL(__dev_get_by_name); -EXPORT_SYMBOL(__dev_remove_pack); -EXPORT_SYMBOL(__skb_linearize); -EXPORT_SYMBOL(dev_valid_name); -EXPORT_SYMBOL(dev_add_pack); -EXPORT_SYMBOL(dev_alloc_name); -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_open); -EXPORT_SYMBOL(dev_queue_xmit); -EXPORT_SYMBOL(dev_remove_pack); -EXPORT_SYMBOL(dev_set_allmulti); -EXPORT_SYMBOL(dev_set_promiscuity); -EXPORT_SYMBOL(dev_change_flags); -EXPORT_SYMBOL(dev_set_mtu); -EXPORT_SYMBOL(dev_set_mac_address); -EXPORT_SYMBOL(free_netdev); -EXPORT_SYMBOL(netdev_boot_setup_check); -EXPORT_SYMBOL(netdev_set_master); -EXPORT_SYMBOL(netdev_state_change); -EXPORT_SYMBOL(netif_receive_skb); -EXPORT_SYMBOL(netif_rx); -EXPORT_SYMBOL(register_gifconf); -EXPORT_SYMBOL(register_netdevice); -EXPORT_SYMBOL(register_netdevice_notifier); -EXPORT_SYMBOL(skb_checksum_help); -EXPORT_SYMBOL(synchronize_net); -EXPORT_SYMBOL(unregister_netdevice); -EXPORT_SYMBOL(unregister_netdevice_notifier); -EXPORT_SYMBOL(net_enable_timestamp); -EXPORT_SYMBOL(net_disable_timestamp); -EXPORT_SYMBOL(dev_get_flags); - -#if defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) -EXPORT_SYMBOL(br_handle_frame_hook); -EXPORT_SYMBOL(br_fdb_get_hook); -EXPORT_SYMBOL(br_fdb_put_hook); -#endif - -#ifdef CONFIG_KMOD -EXPORT_SYMBOL(dev_load); -#endif - -EXPORT_PER_CPU_SYMBOL(softnet_data); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c new file mode 100644 index 00000000000..b6b230600b9 --- /dev/null +++ b/net/core/dev_addr_lists.c @@ -0,0 +1,851 @@ +/* + * net/core/dev_addr_lists.c - Functions for handling net device lists + * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> + * + * This file contains functions for working with unicast, multicast and device + * addresses lists. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/export.h> +#include <linux/list.h> + +/* + * General list handling functions + */ + +static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, + bool sync) +{ + struct netdev_hw_addr *ha; + int alloc_size; + + alloc_size = sizeof(*ha); + if (alloc_size < L1_CACHE_BYTES) + alloc_size = L1_CACHE_BYTES; + ha = kmalloc(alloc_size, GFP_ATOMIC); + if (!ha) + return -ENOMEM; + memcpy(ha->addr, addr, addr_len); + ha->type = addr_type; + ha->refcount = 1; + ha->global_use = global; + ha->synced = sync ? 1 : 0; + ha->sync_cnt = 0; + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + + return 0; +} + +static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync, + int sync_count) +{ + struct netdev_hw_addr *ha; + + if (addr_len > MAX_ADDR_LEN) + return -EINVAL; + + list_for_each_entry(ha, &list->list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + ha->type == addr_type) { + if (global) { + /* check if addr is already used as global */ + if (ha->global_use) + return 0; + else + ha->global_use = true; + } + if (sync) { + if (ha->synced && sync_count) + return -EEXIST; + else + ha->synced++; + } + ha->refcount++; + return 0; + } + } + + return __hw_addr_create_ex(list, addr, addr_len, addr_type, global, + sync); +} + +static int __hw_addr_add(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) +{ + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, + 0); +} + +static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, + struct netdev_hw_addr *ha, bool global, + bool sync) +{ + if (global && !ha->global_use) + return -ENOENT; + + if (sync && !ha->synced) + return -ENOENT; + + if (global) + ha->global_use = false; + + if (sync) + ha->synced--; + + if (--ha->refcount) + return 0; + list_del_rcu(&ha->list); + kfree_rcu(ha, rcu_head); + list->count--; + return 0; +} + +static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync) +{ + struct netdev_hw_addr *ha; + + list_for_each_entry(ha, &list->list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + (ha->type == addr_type || !addr_type)) + return __hw_addr_del_entry(list, ha, global, sync); + } + return -ENOENT; +} + +static int __hw_addr_del(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) +{ + return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); +} + +static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr *ha, + int addr_len) +{ + int err; + + err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, + false, true, ha->sync_cnt); + if (err && err != -EEXIST) + return err; + + if (!err) { + ha->sync_cnt++; + ha->refcount++; + } + + return 0; +} + +static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + struct netdev_hw_addr *ha, + int addr_len) +{ + int err; + + err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, + false, true); + if (err) + return; + ha->sync_cnt--; + /* address on from list is not marked synced */ + __hw_addr_del_entry(from_list, ha, false, false); +} + +static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + int err = 0; + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (ha->sync_cnt == ha->refcount) { + __hw_addr_unsync_one(to_list, from_list, ha, addr_len); + } else { + err = __hw_addr_sync_one(to_list, ha, addr_len); + if (err) + break; + } + } + return err; +} + +/* This function only works where there is a strict 1-1 relationship + * between source and destionation of they synch. If you ever need to + * sync addresses to more then 1 destination, you need to use + * __hw_addr_sync_multiple(). + */ +int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + int err = 0; + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (!ha->sync_cnt) { + err = __hw_addr_sync_one(to_list, ha, addr_len); + if (err) + break; + } else if (ha->refcount == 1) + __hw_addr_unsync_one(to_list, from_list, ha, addr_len); + } + return err; +} +EXPORT_SYMBOL(__hw_addr_sync); + +void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (ha->sync_cnt) + __hw_addr_unsync_one(to_list, from_list, ha, addr_len); + } +} +EXPORT_SYMBOL(__hw_addr_unsync); + +/** + * __hw_addr_sync_dev - Synchonize device's multicast list + * @list: address list to syncronize + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * This funciton is intended to be called from the ndo_set_rx_mode + * function of devices that require explicit address add/remove + * notifications. The unsync function may be NULL in which case + * the addresses requiring removal will simply be removed without + * any notification to the device. + **/ +int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + struct netdev_hw_addr *ha, *tmp; + int err; + + /* first go through and flush out any stale entries */ + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (!ha->sync_cnt || ha->refcount != 1) + continue; + + /* if unsync is defined and fails defer unsyncing address */ + if (unsync && unsync(dev, ha->addr)) + continue; + + ha->sync_cnt--; + __hw_addr_del_entry(list, ha, false, false); + } + + /* go through and sync new entries to the list */ + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (ha->sync_cnt) + continue; + + err = sync(dev, ha->addr); + if (err) + return err; + + ha->sync_cnt++; + ha->refcount++; + } + + return 0; +} +EXPORT_SYMBOL(__hw_addr_sync_dev); + +/** + * __hw_addr_unsync_dev - Remove synchonized addresses from device + * @list: address list to remove syncronized addresses from + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by __hw_addr_sync_dev(). + * This function is intended to be called from the ndo_stop or ndo_open + * functions on devices that require explicit address add/remove + * notifications. If the unsync function pointer is NULL then this function + * can be used to just reset the sync_cnt for the addresses in the list. + **/ +void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (!ha->sync_cnt) + continue; + + /* if unsync is defined and fails defer unsyncing address */ + if (unsync && unsync(dev, ha->addr)) + continue; + + ha->sync_cnt--; + __hw_addr_del_entry(list, ha, false, false); + } +} +EXPORT_SYMBOL(__hw_addr_unsync_dev); + +static void __hw_addr_flush(struct netdev_hw_addr_list *list) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &list->list, list) { + list_del_rcu(&ha->list); + kfree_rcu(ha, rcu_head); + } + list->count = 0; +} + +void __hw_addr_init(struct netdev_hw_addr_list *list) +{ + INIT_LIST_HEAD(&list->list); + list->count = 0; +} +EXPORT_SYMBOL(__hw_addr_init); + +/* + * Device addresses handling functions + */ + +/** + * dev_addr_flush - Flush device address list + * @dev: device + * + * Flush device address list and reset ->dev_addr. + * + * The caller must hold the rtnl_mutex. + */ +void dev_addr_flush(struct net_device *dev) +{ + /* rtnl_mutex must be held here */ + + __hw_addr_flush(&dev->dev_addrs); + dev->dev_addr = NULL; +} +EXPORT_SYMBOL(dev_addr_flush); + +/** + * dev_addr_init - Init device address list + * @dev: device + * + * Init device address list and create the first element, + * used by ->dev_addr. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_init(struct net_device *dev) +{ + unsigned char addr[MAX_ADDR_LEN]; + struct netdev_hw_addr *ha; + int err; + + /* rtnl_mutex must be held here */ + + __hw_addr_init(&dev->dev_addrs); + memset(addr, 0, sizeof(addr)); + err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), + NETDEV_HW_ADDR_T_LAN); + if (!err) { + /* + * Get the first (previously created) address from the list + * and set dev_addr pointer to this location. + */ + ha = list_first_entry(&dev->dev_addrs.list, + struct netdev_hw_addr, list); + dev->dev_addr = ha->addr; + } + return err; +} +EXPORT_SYMBOL(dev_addr_init); + +/** + * dev_addr_add - Add a device address + * @dev: device + * @addr: address to add + * @addr_type: address type + * + * Add a device address to the device or increase the reference count if + * it already exists. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_add(struct net_device *dev, const unsigned char *addr, + unsigned char addr_type) +{ + int err; + + ASSERT_RTNL(); + + err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; +} +EXPORT_SYMBOL(dev_addr_add); + +/** + * dev_addr_del - Release a device address. + * @dev: device + * @addr: address to delete + * @addr_type: address type + * + * Release reference to a device address and remove it from the device + * if the reference count drops to zero. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_del(struct net_device *dev, const unsigned char *addr, + unsigned char addr_type) +{ + int err; + struct netdev_hw_addr *ha; + + ASSERT_RTNL(); + + /* + * We can not remove the first address from the list because + * dev->dev_addr points to that. + */ + ha = list_first_entry(&dev->dev_addrs.list, + struct netdev_hw_addr, list); + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == addr_type && ha->refcount == 1) + return -ENOENT; + + err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, + addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; +} +EXPORT_SYMBOL(dev_addr_del); + +/* + * Unicast list handling functions + */ + +/** + * dev_uc_add_excl - Add a global secondary unicast address + * @dev: device + * @addr: address to add + */ +int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) +{ + struct netdev_hw_addr *ha; + int err; + + netif_addr_lock_bh(dev); + list_for_each_entry(ha, &dev->uc.list, list) { + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == NETDEV_HW_ADDR_T_UNICAST) { + err = -EEXIST; + goto out; + } + } + err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST, true, false); + if (!err) + __dev_set_rx_mode(dev); +out: + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_uc_add_excl); + +/** + * dev_uc_add - Add a secondary unicast address + * @dev: device + * @addr: address to add + * + * Add a secondary unicast address to the device or increase + * the reference count if it already exists. + */ +int dev_uc_add(struct net_device *dev, const unsigned char *addr) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_add(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_uc_add); + +/** + * dev_uc_del - Release secondary unicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a secondary unicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_uc_del(struct net_device *dev, const unsigned char *addr) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_del(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_uc_del); + +/** + * dev_uc_sync - Synchronize device's unicast list to another device + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_addr_lock_bh. + * + * This function is intended to be called from the dev->set_rx_mode + * function of layered software devices. This function assumes that + * addresses will only ever be synced to the @to devices and no other. + */ +int dev_uc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_nested(to); + err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock(to); + return err; +} +EXPORT_SYMBOL(dev_uc_sync); + +/** + * dev_uc_sync_multiple - Synchronize device's unicast list to another + * device, but allow for multiple calls to sync to multiple devices. + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have been deleted from the source. The source device + * must be locked by netif_addr_lock_bh. + * + * This function is intended to be called from the dev->set_rx_mode + * function of layered software devices. It allows for a single source + * device to be synced to multiple destination devices. + */ +int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_nested(to); + err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock(to); + return err; +} +EXPORT_SYMBOL(dev_uc_sync_multiple); + +/** + * dev_uc_unsync - Remove synchronized addresses from the destination device + * @to: destination device + * @from: source device + * + * Remove all addresses that were added to the destination device by + * dev_uc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_uc_unsync(struct net_device *to, struct net_device *from) +{ + if (to->addr_len != from->addr_len) + return; + + netif_addr_lock_bh(from); + netif_addr_lock_nested(to); + __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); + __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); +} +EXPORT_SYMBOL(dev_uc_unsync); + +/** + * dev_uc_flush - Flush unicast addresses + * @dev: device + * + * Flush unicast addresses. + */ +void dev_uc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_uc_flush); + +/** + * dev_uc_flush - Init unicast address list + * @dev: device + * + * Init unicast address list. + */ +void dev_uc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->uc); +} +EXPORT_SYMBOL(dev_uc_init); + +/* + * Multicast list handling functions + */ + +/** + * dev_mc_add_excl - Add a global secondary multicast address + * @dev: device + * @addr: address to add + */ +int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) +{ + struct netdev_hw_addr *ha; + int err; + + netif_addr_lock_bh(dev); + list_for_each_entry(ha, &dev->mc.list, list) { + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == NETDEV_HW_ADDR_T_MULTICAST) { + err = -EEXIST; + goto out; + } + } + err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, true, false); + if (!err) + __dev_set_rx_mode(dev); +out: + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_mc_add_excl); + +static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +/** + * dev_mc_add - Add a multicast address + * @dev: device + * @addr: address to add + * + * Add a multicast address to the device or increase + * the reference count if it already exists. + */ +int dev_mc_add(struct net_device *dev, const unsigned char *addr) +{ + return __dev_mc_add(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_add); + +/** + * dev_mc_add_global - Add a global multicast address + * @dev: device + * @addr: address to add + * + * Add a global multicast address to the device. + */ +int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) +{ + return __dev_mc_add(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_add_global); + +static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global, false); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} + +/** + * dev_mc_del - Delete a multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del(struct net_device *dev, const unsigned char *addr) +{ + return __dev_mc_del(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_del); + +/** + * dev_mc_del_global - Delete a global multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) +{ + return __dev_mc_del(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_del_global); + +/** + * dev_mc_sync - Synchronize device's multicast list to another device + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_addr_lock_bh. + * + * This function is intended to be called from the ndo_set_rx_mode + * function of layered software devices. + */ +int dev_mc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_nested(to); + err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock(to); + return err; +} +EXPORT_SYMBOL(dev_mc_sync); + +/** + * dev_mc_sync_multiple - Synchronize device's multicast list to another + * device, but allow for multiple calls to sync to multiple devices. + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_addr_lock_bh. + * + * This function is intended to be called from the ndo_set_rx_mode + * function of layered software devices. It allows for a single + * source device to be synced to multiple destination devices. + */ +int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_nested(to); + err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock(to); + return err; +} +EXPORT_SYMBOL(dev_mc_sync_multiple); + +/** + * dev_mc_unsync - Remove synchronized addresses from the destination device + * @to: destination device + * @from: source device + * + * Remove all addresses that were added to the destination device by + * dev_mc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_mc_unsync(struct net_device *to, struct net_device *from) +{ + if (to->addr_len != from->addr_len) + return; + + netif_addr_lock_bh(from); + netif_addr_lock_nested(to); + __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); + __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); +} +EXPORT_SYMBOL(dev_mc_unsync); + +/** + * dev_mc_flush - Flush multicast addresses + * @dev: device + * + * Flush multicast addresses. + */ +void dev_mc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->mc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_mc_flush); + +/** + * dev_mc_flush - Init multicast address list + * @dev: device + * + * Init multicast address list. + */ +void dev_mc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->mc); +} +EXPORT_SYMBOL(dev_mc_init); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c new file mode 100644 index 00000000000..cf999e09bcd --- /dev/null +++ b/net/core/dev_ioctl.c @@ -0,0 +1,567 @@ +#include <linux/kmod.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/net_tstamp.h> +#include <linux/wireless.h> +#include <net/wext.h> + +/* + * Map an interface index to its name (SIOCGIFNAME) + */ + +/* + * We need this ioctl for efficient implementation of the + * if_indextoname() function required by the IPv6 API. Without + * it, we would have to search all the interfaces to find a + * match. --pb + */ + +static int dev_ifname(struct net *net, struct ifreq __user *arg) +{ + struct ifreq ifr; + int error; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex); + if (error) + return error; + + if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) + return -EFAULT; + return 0; +} + +static gifconf_func_t *gifconf_list[NPROTO]; + +/** + * register_gifconf - register a SIOCGIF handler + * @family: Address family + * @gifconf: Function handler + * + * Register protocol dependent address dumping routines. The handler + * that is passed must not be freed or reused until it has been replaced + * by another handler. + */ +int register_gifconf(unsigned int family, gifconf_func_t *gifconf) +{ + if (family >= NPROTO) + return -EINVAL; + gifconf_list[family] = gifconf; + return 0; +} +EXPORT_SYMBOL(register_gifconf); + +/* + * Perform a SIOCGIFCONF call. This structure will change + * size eventually, and there is nothing I can do about it. + * Thus we will need a 'compatibility mode'. + */ + +static int dev_ifconf(struct net *net, char __user *arg) +{ + struct ifconf ifc; + struct net_device *dev; + char __user *pos; + int len; + int total; + int i; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) + return -EFAULT; + + pos = ifc.ifc_buf; + len = ifc.ifc_len; + + /* + * Loop over the interfaces, and write an info block for each. + */ + + total = 0; + for_each_netdev(net, dev) { + for (i = 0; i < NPROTO; i++) { + if (gifconf_list[i]) { + int done; + if (!pos) + done = gifconf_list[i](dev, NULL, 0); + else + done = gifconf_list[i](dev, pos + total, + len - total); + if (done < 0) + return -EFAULT; + total += done; + } + } + } + + /* + * All done. Write the updated control block back to the caller. + */ + ifc.ifc_len = total; + + /* + * Both BSD and Solaris return 0 here, so we do too. + */ + return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() + */ +static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); + + if (!dev) + return -ENODEV; + + switch (cmd) { + case SIOCGIFFLAGS: /* Get interface flags */ + ifr->ifr_flags = (short) dev_get_flags(dev); + return 0; + + case SIOCGIFMETRIC: /* Get the metric on the interface + (currently unused) */ + ifr->ifr_metric = 0; + return 0; + + case SIOCGIFMTU: /* Get the MTU of a device */ + ifr->ifr_mtu = dev->mtu; + return 0; + + case SIOCGIFHWADDR: + if (!dev->addr_len) + memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); + else + memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + ifr->ifr_hwaddr.sa_family = dev->type; + return 0; + + case SIOCGIFSLAVE: + err = -EINVAL; + break; + + case SIOCGIFMAP: + ifr->ifr_map.mem_start = dev->mem_start; + ifr->ifr_map.mem_end = dev->mem_end; + ifr->ifr_map.base_addr = dev->base_addr; + ifr->ifr_map.irq = dev->irq; + ifr->ifr_map.dma = dev->dma; + ifr->ifr_map.port = dev->if_port; + return 0; + + case SIOCGIFINDEX: + ifr->ifr_ifindex = dev->ifindex; + return 0; + + case SIOCGIFTXQLEN: + ifr->ifr_qlen = dev->tx_queue_len; + return 0; + + default: + /* dev_ioctl() should ensure this case + * is never reached + */ + WARN_ON(1); + err = -ENOTTY; + break; + + } + return err; +} + +static int net_hwtstamp_validate(struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + enum hwtstamp_tx_types tx_type; + enum hwtstamp_rx_filters rx_filter; + int tx_type_valid = 0; + int rx_filter_valid = 0; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.flags) /* reserved for future extensions */ + return -EINVAL; + + tx_type = cfg.tx_type; + rx_filter = cfg.rx_filter; + + switch (tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_ONESTEP_SYNC: + tx_type_valid = 1; + break; + } + + switch (rx_filter) { + case HWTSTAMP_FILTER_NONE: + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + rx_filter_valid = 1; + break; + } + + if (!tx_type_valid || !rx_filter_valid) + return -ERANGE; + + return 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rtnl_lock() + */ +static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + const struct net_device_ops *ops; + + if (!dev) + return -ENODEV; + + ops = dev->netdev_ops; + + switch (cmd) { + case SIOCSIFFLAGS: /* Set interface flags */ + return dev_change_flags(dev, ifr->ifr_flags); + + case SIOCSIFMETRIC: /* Set the metric on the interface + (currently unused) */ + return -EOPNOTSUPP; + + case SIOCSIFMTU: /* Set the MTU of a device */ + return dev_set_mtu(dev, ifr->ifr_mtu); + + case SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + + case SIOCSIFHWBROADCAST: + if (ifr->ifr_hwaddr.sa_family != dev->type) + return -EINVAL; + memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return 0; + + case SIOCSIFMAP: + if (ops->ndo_set_config) { + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_set_config(dev, &ifr->ifr_map); + } + return -EOPNOTSUPP; + + case SIOCADDMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCDELMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCSIFTXQLEN: + if (ifr->ifr_qlen < 0) + return -EINVAL; + dev->tx_queue_len = ifr->ifr_qlen; + return 0; + + case SIOCSIFNAME: + ifr->ifr_newname[IFNAMSIZ-1] = '\0'; + return dev_change_name(dev, ifr->ifr_newname); + + case SIOCSHWTSTAMP: + err = net_hwtstamp_validate(ifr); + if (err) + return err; + /* fall through */ + + /* + * Unknown or private ioctl + */ + default: + if ((cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) || + cmd == SIOCBONDENSLAVE || + cmd == SIOCBONDRELEASE || + cmd == SIOCBONDSETHWADDR || + cmd == SIOCBONDSLAVEINFOQUERY || + cmd == SIOCBONDINFOQUERY || + cmd == SIOCBONDCHANGEACTIVE || + cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCBRADDIF || + cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || + cmd == SIOCGHWTSTAMP || + cmd == SIOCWANDEV) { + err = -EOPNOTSUPP; + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + err = ops->ndo_do_ioctl(dev, ifr, cmd); + else + err = -ENODEV; + } + } else + err = -EINVAL; + + } + return err; +} + +/** + * dev_load - load a network module + * @net: the applicable net namespace + * @name: name of interface + * + * If a network interface is not present and the process has suitable + * privileges this function loads the module. If module loading is not + * available in this kernel then it becomes a nop. + */ + +void dev_load(struct net *net, const char *name) +{ + struct net_device *dev; + int no_module; + + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); + + no_module = !dev; + if (no_module && capable(CAP_NET_ADMIN)) + no_module = request_module("netdev-%s", name); + if (no_module && capable(CAP_SYS_MODULE)) { + if (!request_module("%s", name)) + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); + } +} +EXPORT_SYMBOL(dev_load); + +/* + * This function handles all "interface"-type I/O control requests. The actual + * 'doing' part of this is dev_ifsioc above. + */ + +/** + * dev_ioctl - network device ioctl + * @net: the applicable net namespace + * @cmd: command to issue + * @arg: pointer to a struct ifreq in user space + * + * Issue ioctl functions to devices. This is normally called by the + * user space syscall interfaces but can sometimes be useful for + * other purposes. The return value is the return from the syscall if + * positive or a negative errno code on error. + */ + +int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +{ + struct ifreq ifr; + int ret; + char *colon; + + /* One special case: SIOCGIFCONF takes ifconf argument + and requires shared lock, because it sleeps writing + to user space. + */ + + if (cmd == SIOCGIFCONF) { + rtnl_lock(); + ret = dev_ifconf(net, (char __user *) arg); + rtnl_unlock(); + return ret; + } + if (cmd == SIOCGIFNAME) + return dev_ifname(net, (struct ifreq __user *)arg); + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + ifr.ifr_name[IFNAMSIZ-1] = 0; + + colon = strchr(ifr.ifr_name, ':'); + if (colon) + *colon = 0; + + /* + * See which interface the caller is talking about. + */ + + switch (cmd) { + /* + * These ioctl calls: + * - can be done by all. + * - atomic and do not require locking. + * - return a value + */ + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFHWADDR: + case SIOCGIFSLAVE: + case SIOCGIFMAP: + case SIOCGIFINDEX: + case SIOCGIFTXQLEN: + dev_load(net, ifr.ifr_name); + rcu_read_lock(); + ret = dev_ifsioc_locked(net, &ifr, cmd); + rcu_read_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + case SIOCETHTOOL: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ethtool(net, &ifr); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - return a value + */ + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSIFNAME: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFMAP: + case SIOCSIFTXQLEN: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + /* + * These ioctl calls: + * - require local superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFFLAGS: + case SIOCSIFMETRIC: + case SIOCSIFMTU: + case SIOCSIFHWADDR: + case SIOCSIFSLAVE: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCSIFHWBROADCAST: + case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSHWTSTAMP: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + return ret; + + case SIOCGIFMEM: + /* Get the per device memory space. We can add this but + * currently do not support it */ + case SIOCSIFMEM: + /* Set the per device memory buffer space. + * Not applicable in our case */ + case SIOCSIFLINK: + return -ENOTTY; + + /* + * Unknown or private ioctl. + */ + default: + if (cmd == SIOCWANDEV || + cmd == SIOCGHWTSTAMP || + (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret && copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + return ret; + } + /* Take care of Wireless Extensions */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(net, &ifr, cmd, arg); + return -ENOTTY; + } +} diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c deleted file mode 100644 index 05d60850840..00000000000 --- a/net/core/dev_mcast.c +++ /dev/null @@ -1,298 +0,0 @@ -/* - * Linux NET3: Multicast List maintenance. - * - * Authors: - * Tim Kordas <tjk@nostromo.eeap.cwru.edu> - * Richard Underwood <richard@wuzz.demon.co.uk> - * - * Stir fried together from the IP multicast and CAP patches above - * Alan Cox <Alan.Cox@linux.org> - * - * Fixes: - * Alan Cox : Update the device on a real delete - * rather than any time but... - * Alan Cox : IFF_ALLMULTI support. - * Alan Cox : New format set_multicast_list() calls. - * Gleb Natapov : Remove dev_mc_lock. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/config.h> -#include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> -#include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/init.h> -#include <net/ip.h> -#include <net/route.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/arp.h> - - -/* - * Device multicast list maintenance. - * - * This is used both by IP and by the user level maintenance functions. - * Unlike BSD we maintain a usage count on a given multicast address so - * that a casual user application can add/delete multicasts used by - * protocols without doing damage to the protocols when it deletes the - * entries. It also helps IP as it tracks overlapping maps. - * - * Device mc lists are changed by bh at least if IPv6 is enabled, - * so that it must be bh protected. - * - * We block accesses to device mc filters with dev->xmit_lock. - */ - -/* - * Update the multicast list into the physical NIC controller. - */ - -static void __dev_mc_upload(struct net_device *dev) -{ - /* Don't do anything till we up the interface - * [dev_open will call this function so the list will - * stay sane] - */ - - if (!(dev->flags&IFF_UP)) - return; - - /* - * Devices with no set multicast or which have been - * detached don't get set. - */ - - if (dev->set_multicast_list == NULL || - !netif_device_present(dev)) - return; - - dev->set_multicast_list(dev); -} - -void dev_mc_upload(struct net_device *dev) -{ - spin_lock_bh(&dev->xmit_lock); - __dev_mc_upload(dev); - spin_unlock_bh(&dev->xmit_lock); -} - -/* - * Delete a device level multicast - */ - -int dev_mc_delete(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err = 0; - struct dev_mc_list *dmi, **dmip; - - spin_lock_bh(&dev->xmit_lock); - - for (dmip = &dev->mc_list; (dmi = *dmip) != NULL; dmip = &dmi->next) { - /* - * Find the entry we want to delete. The device could - * have variable length entries so check these too. - */ - if (memcmp(dmi->dmi_addr, addr, dmi->dmi_addrlen) == 0 && - alen == dmi->dmi_addrlen) { - if (glbl) { - int old_glbl = dmi->dmi_gusers; - dmi->dmi_gusers = 0; - if (old_glbl == 0) - break; - } - if (--dmi->dmi_users) - goto done; - - /* - * Last user. So delete the entry. - */ - *dmip = dmi->next; - dev->mc_count--; - - kfree(dmi); - - /* - * We have altered the list, so the card - * loaded filter is now wrong. Fix it - */ - __dev_mc_upload(dev); - - spin_unlock_bh(&dev->xmit_lock); - return 0; - } - } - err = -ENOENT; -done: - spin_unlock_bh(&dev->xmit_lock); - return err; -} - -/* - * Add a device level multicast - */ - -int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err = 0; - struct dev_mc_list *dmi, *dmi1; - - dmi1 = kmalloc(sizeof(*dmi), GFP_ATOMIC); - - spin_lock_bh(&dev->xmit_lock); - for (dmi = dev->mc_list; dmi != NULL; dmi = dmi->next) { - if (memcmp(dmi->dmi_addr, addr, dmi->dmi_addrlen) == 0 && - dmi->dmi_addrlen == alen) { - if (glbl) { - int old_glbl = dmi->dmi_gusers; - dmi->dmi_gusers = 1; - if (old_glbl) - goto done; - } - dmi->dmi_users++; - goto done; - } - } - - if ((dmi = dmi1) == NULL) { - spin_unlock_bh(&dev->xmit_lock); - return -ENOMEM; - } - memcpy(dmi->dmi_addr, addr, alen); - dmi->dmi_addrlen = alen; - dmi->next = dev->mc_list; - dmi->dmi_users = 1; - dmi->dmi_gusers = glbl ? 1 : 0; - dev->mc_list = dmi; - dev->mc_count++; - - __dev_mc_upload(dev); - - spin_unlock_bh(&dev->xmit_lock); - return 0; - -done: - spin_unlock_bh(&dev->xmit_lock); - kfree(dmi1); - return err; -} - -/* - * Discard multicast list when a device is downed - */ - -void dev_mc_discard(struct net_device *dev) -{ - spin_lock_bh(&dev->xmit_lock); - - while (dev->mc_list != NULL) { - struct dev_mc_list *tmp = dev->mc_list; - dev->mc_list = tmp->next; - if (tmp->dmi_users > tmp->dmi_gusers) - printk("dev_mc_discard: multicast leakage! dmi_users=%d\n", tmp->dmi_users); - kfree(tmp); - } - dev->mc_count = 0; - - spin_unlock_bh(&dev->xmit_lock); -} - -#ifdef CONFIG_PROC_FS -static void *dev_mc_seq_start(struct seq_file *seq, loff_t *pos) -{ - struct net_device *dev; - loff_t off = 0; - - read_lock(&dev_base_lock); - for (dev = dev_base; dev; dev = dev->next) { - if (off++ == *pos) - return dev; - } - return NULL; -} - -static void *dev_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct net_device *dev = v; - ++*pos; - return dev->next; -} - -static void dev_mc_seq_stop(struct seq_file *seq, void *v) -{ - read_unlock(&dev_base_lock); -} - - -static int dev_mc_seq_show(struct seq_file *seq, void *v) -{ - struct dev_mc_list *m; - struct net_device *dev = v; - - spin_lock_bh(&dev->xmit_lock); - for (m = dev->mc_list; m; m = m->next) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, m->dmi_users, m->dmi_gusers); - - for (i = 0; i < m->dmi_addrlen; i++) - seq_printf(seq, "%02x", m->dmi_addr[i]); - - seq_putc(seq, '\n'); - } - spin_unlock_bh(&dev->xmit_lock); - return 0; -} - -static struct seq_operations dev_mc_seq_ops = { - .start = dev_mc_seq_start, - .next = dev_mc_seq_next, - .stop = dev_mc_seq_stop, - .show = dev_mc_seq_show, -}; - -static int dev_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &dev_mc_seq_ops); -} - -static struct file_operations dev_mc_seq_fops = { - .owner = THIS_MODULE, - .open = dev_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -#endif - -void __init dev_mcast_init(void) -{ - proc_net_fops_create("dev_mcast", 0, &dev_mc_seq_fops); -} - -EXPORT_SYMBOL(dev_mc_add); -EXPORT_SYMBOL(dev_mc_delete); -EXPORT_SYMBOL(dev_mc_upload); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c new file mode 100644 index 00000000000..e70301eb7a4 --- /dev/null +++ b/net/core/drop_monitor.c @@ -0,0 +1,439 @@ +/* + * Monitoring code for network dropped packet alerts + * + * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#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> +#include <linux/netpoll.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/netlink.h> +#include <linux/net_dropmon.h> +#include <linux/percpu.h> +#include <linux/timer.h> +#include <linux/bitops.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <net/genetlink.h> +#include <net/netevent.h> + +#include <trace/events/skb.h> +#include <trace/events/napi.h> + +#include <asm/unaligned.h> + +#define TRACE_ON 1 +#define TRACE_OFF 0 + +/* + * Globals, our netlink socket pointer + * and the work handle that will send up + * netlink alerts + */ +static int trace_state = TRACE_OFF; +static DEFINE_MUTEX(trace_state_mutex); + +struct per_cpu_dm_data { + spinlock_t lock; + struct sk_buff *skb; + struct work_struct dm_alert_work; + struct timer_list send_timer; +}; + +struct dm_hw_stat_delta { + struct net_device *dev; + unsigned long last_rx; + struct list_head list; + struct rcu_head rcu; + unsigned long last_drop_val; +}; + +static struct genl_family net_drop_monitor_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = "NET_DM", + .version = 2, +}; + +static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); + +static int dm_hit_limit = 64; +static int dm_delay = 1; +static unsigned long dm_hw_check_delta = 2*HZ; +static LIST_HEAD(hw_stats_list); + +static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) +{ + size_t al; + struct net_dm_alert_msg *msg; + struct nlattr *nla; + struct sk_buff *skb; + unsigned long flags; + + al = sizeof(struct net_dm_alert_msg); + al += dm_hit_limit * sizeof(struct net_dm_drop_point); + al += sizeof(struct nlattr); + + skb = genlmsg_new(al, GFP_KERNEL); + + if (skb) { + genlmsg_put(skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + nla = nla_reserve(skb, NLA_UNSPEC, + sizeof(struct net_dm_alert_msg)); + msg = nla_data(nla); + memset(msg, 0, al); + } else { + mod_timer(&data->send_timer, jiffies + HZ / 10); + } + + spin_lock_irqsave(&data->lock, flags); + swap(data->skb, skb); + spin_unlock_irqrestore(&data->lock, flags); + + return skb; +} + +static struct genl_multicast_group dropmon_mcgrps[] = { + { .name = "events", }, +}; + +static void send_dm_alert(struct work_struct *work) +{ + struct sk_buff *skb; + struct per_cpu_dm_data *data; + + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); + + skb = reset_per_cpu_data(data); + + if (skb) + genlmsg_multicast(&net_drop_monitor_family, skb, 0, + 0, GFP_KERNEL); +} + +/* + * This is the timer function to delay the sending of an alert + * in the event that more drops will arrive during the + * hysteresis period. + */ +static void sched_send_work(unsigned long _data) +{ + struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data; + + schedule_work(&data->dm_alert_work); +} + +static void trace_drop_common(struct sk_buff *skb, void *location) +{ + struct net_dm_alert_msg *msg; + struct nlmsghdr *nlh; + struct nlattr *nla; + int i; + struct sk_buff *dskb; + struct per_cpu_dm_data *data; + unsigned long flags; + + local_irq_save(flags); + data = &__get_cpu_var(dm_cpu_data); + spin_lock(&data->lock); + dskb = data->skb; + + if (!dskb) + goto out; + + nlh = (struct nlmsghdr *)dskb->data; + nla = genlmsg_data(nlmsg_data(nlh)); + msg = nla_data(nla); + for (i = 0; i < msg->entries; i++) { + if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { + msg->points[i].count++; + goto out; + } + } + if (msg->entries == dm_hit_limit) + goto out; + /* + * We need to create a new entry + */ + __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); + nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); + memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); + msg->points[msg->entries].count = 1; + msg->entries++; + + if (!timer_pending(&data->send_timer)) { + data->send_timer.expires = jiffies + dm_delay * HZ; + add_timer(&data->send_timer); + } + +out: + spin_unlock_irqrestore(&data->lock, flags); +} + +static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) +{ + trace_drop_common(skb, location); +} + +static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi) +{ + struct dm_hw_stat_delta *new_stat; + + /* + * Don't check napi structures with no associated device + */ + if (!napi->dev) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(new_stat, &hw_stats_list, list) { + /* + * only add a note to our monitor buffer if: + * 1) this is the dev we received on + * 2) its after the last_rx delta + * 3) our rx_dropped count has gone up + */ + if ((new_stat->dev == napi->dev) && + (time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) && + (napi->dev->stats.rx_dropped != new_stat->last_drop_val)) { + trace_drop_common(NULL, NULL); + new_stat->last_drop_val = napi->dev->stats.rx_dropped; + new_stat->last_rx = jiffies; + break; + } + } + rcu_read_unlock(); +} + +static int set_all_monitor_traces(int state) +{ + int rc = 0; + struct dm_hw_stat_delta *new_stat = NULL; + struct dm_hw_stat_delta *temp; + + mutex_lock(&trace_state_mutex); + + if (state == trace_state) { + rc = -EAGAIN; + goto out_unlock; + } + + switch (state) { + case TRACE_ON: + if (!try_module_get(THIS_MODULE)) { + rc = -ENODEV; + break; + } + + rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); + rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL); + break; + + case TRACE_OFF: + rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL); + rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL); + + tracepoint_synchronize_unregister(); + + /* + * Clean the device list + */ + list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { + if (new_stat->dev == NULL) { + list_del_rcu(&new_stat->list); + kfree_rcu(new_stat, rcu); + } + } + + module_put(THIS_MODULE); + + break; + default: + rc = 1; + break; + } + + if (!rc) + trace_state = state; + else + rc = -EINPROGRESS; + +out_unlock: + mutex_unlock(&trace_state_mutex); + + return rc; +} + + +static int net_dm_cmd_config(struct sk_buff *skb, + struct genl_info *info) +{ + return -ENOTSUPP; +} + +static int net_dm_cmd_trace(struct sk_buff *skb, + struct genl_info *info) +{ + switch (info->genlhdr->cmd) { + case NET_DM_CMD_START: + return set_all_monitor_traces(TRACE_ON); + break; + case NET_DM_CMD_STOP: + return set_all_monitor_traces(TRACE_OFF); + break; + } + + return -ENOTSUPP; +} + +static int dropmon_net_event(struct notifier_block *ev_block, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct dm_hw_stat_delta *new_stat = NULL; + struct dm_hw_stat_delta *tmp; + + switch (event) { + case NETDEV_REGISTER: + new_stat = kzalloc(sizeof(struct dm_hw_stat_delta), GFP_KERNEL); + + if (!new_stat) + goto out; + + new_stat->dev = dev; + new_stat->last_rx = jiffies; + mutex_lock(&trace_state_mutex); + list_add_rcu(&new_stat->list, &hw_stats_list); + mutex_unlock(&trace_state_mutex); + break; + case NETDEV_UNREGISTER: + mutex_lock(&trace_state_mutex); + list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { + if (new_stat->dev == dev) { + new_stat->dev = NULL; + if (trace_state == TRACE_OFF) { + list_del_rcu(&new_stat->list); + kfree_rcu(new_stat, rcu); + break; + } + } + } + mutex_unlock(&trace_state_mutex); + break; + } +out: + return NOTIFY_DONE; +} + +static const struct genl_ops dropmon_ops[] = { + { + .cmd = NET_DM_CMD_CONFIG, + .doit = net_dm_cmd_config, + }, + { + .cmd = NET_DM_CMD_START, + .doit = net_dm_cmd_trace, + }, + { + .cmd = NET_DM_CMD_STOP, + .doit = net_dm_cmd_trace, + }, +}; + +static struct notifier_block dropmon_net_notifier = { + .notifier_call = dropmon_net_event +}; + +static int __init init_net_drop_monitor(void) +{ + struct per_cpu_dm_data *data; + int cpu, rc; + + pr_info("Initializing network drop monitor service\n"); + + if (sizeof(void *) > 8) { + pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); + return -ENOSPC; + } + + rc = genl_register_family_with_ops_groups(&net_drop_monitor_family, + dropmon_ops, dropmon_mcgrps); + if (rc) { + pr_err("Could not create drop monitor netlink family\n"); + return rc; + } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); + + rc = register_netdevice_notifier(&dropmon_net_notifier); + if (rc < 0) { + pr_crit("Failed to register netdevice notifier\n"); + goto out_unreg; + } + + rc = 0; + + for_each_possible_cpu(cpu) { + data = &per_cpu(dm_cpu_data, cpu); + INIT_WORK(&data->dm_alert_work, send_dm_alert); + init_timer(&data->send_timer); + data->send_timer.data = (unsigned long)data; + data->send_timer.function = sched_send_work; + spin_lock_init(&data->lock); + reset_per_cpu_data(data); + } + + + goto out; + +out_unreg: + genl_unregister_family(&net_drop_monitor_family); +out: + return rc; +} + +static void exit_net_drop_monitor(void) +{ + struct per_cpu_dm_data *data; + int cpu; + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); + + /* + * Because of the module_get/put we do in the trace state change path + * we are guarnateed not to have any current users when we get here + * all we need to do is make sure that we don't have any running timers + * or pending schedule calls + */ + + for_each_possible_cpu(cpu) { + data = &per_cpu(dm_cpu_data, cpu); + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + /* + * At this point, we should have exclusive access + * to this struct and can free the skb inside it + */ + kfree_skb(data->skb); + } + + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); +} + +module_init(init_net_drop_monitor); +module_exit(exit_net_drop_monitor); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); +MODULE_ALIAS_GENL_FAMILY("NET_DM"); diff --git a/net/core/dst.c b/net/core/dst.c index 470c05bc4cb..a028409ee43 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -9,60 +9,80 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/workqueue.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/netdevice.h> -#include <linux/sched.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> +#include <net/net_namespace.h> +#include <linux/sched.h> +#include <linux/prefetch.h> #include <net/dst.h> -/* Locking strategy: - * 1) Garbage collection state of dead destination cache - * entries is protected by dst_lock. - * 2) GC is run only from BH context, and is the only remover - * of entries. - * 3) Entries are added to the garbage list from both BH - * and non-BH context, so local BH disabling is needed. - * 4) All operations modify state, so a spinlock is used. +/* + * Theory of operations: + * 1) We use a list, protected by a spinlock, to add + * new entries from both BH and non-BH context. + * 2) In order to keep spinlock held for a small delay, + * we use a second list where are stored long lived + * entries, that are handled by the garbage collect thread + * fired by a workqueue. + * 3) This list is guarded by a mutex, + * so that the gc_task and dst_dev_event() can be synchronized. */ -static struct dst_entry *dst_garbage_list; -#if RT_CACHE_DEBUG >= 2 -static atomic_t dst_total = ATOMIC_INIT(0); -#endif -static DEFINE_SPINLOCK(dst_lock); -static unsigned long dst_gc_timer_expires; -static unsigned long dst_gc_timer_inc = DST_GC_MAX; -static void dst_run_gc(unsigned long); -static void ___dst_free(struct dst_entry * dst); +/* + * We want to keep lock & list close together + * to dirty as few cache lines as possible in __dst_free(). + * As this is not a very strong hint, we dont force an alignment on SMP. + */ +static struct { + spinlock_t lock; + struct dst_entry *list; + unsigned long timer_inc; + unsigned long timer_expires; +} dst_garbage = { + .lock = __SPIN_LOCK_UNLOCKED(dst_garbage.lock), + .timer_inc = DST_GC_MAX, +}; +static void dst_gc_task(struct work_struct *work); +static void ___dst_free(struct dst_entry *dst); + +static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task); -static DEFINE_TIMER(dst_gc_timer, dst_run_gc, DST_GC_MIN, 0); +static DEFINE_MUTEX(dst_gc_mutex); +/* + * long lived entries are maintained in this list, guarded by dst_gc_mutex + */ +static struct dst_entry *dst_busy_list; -static void dst_run_gc(unsigned long dummy) +static void dst_gc_task(struct work_struct *work) { int delayed = 0; - int work_performed; - struct dst_entry * dst, **dstp; - - if (!spin_trylock(&dst_lock)) { - mod_timer(&dst_gc_timer, jiffies + HZ/10); - return; - } - - del_timer(&dst_gc_timer); - dstp = &dst_garbage_list; - work_performed = 0; - while ((dst = *dstp) != NULL) { - if (atomic_read(&dst->__refcnt)) { - dstp = &dst->next; + int work_performed = 0; + unsigned long expires = ~0L; + struct dst_entry *dst, *next, head; + struct dst_entry *last = &head; + + mutex_lock(&dst_gc_mutex); + next = dst_busy_list; + +loop: + while ((dst = next) != NULL) { + next = dst->next; + prefetch(&next->next); + cond_resched(); + if (likely(atomic_read(&dst->__refcnt))) { + last->next = dst; + last = dst; delayed++; continue; } - *dstp = dst->next; - work_performed = 1; + work_performed++; dst = dst_destroy(dst); if (dst) { @@ -74,132 +94,160 @@ static void dst_run_gc(unsigned long dummy) * But we do not have state "obsoleted, but * referenced by parent", so it is right. */ - if (dst->obsolete > 1) + if (dst->obsolete > 0) continue; ___dst_free(dst); - dst->next = *dstp; - *dstp = dst; - dstp = &dst->next; + dst->next = next; + next = dst; } } - if (!dst_garbage_list) { - dst_gc_timer_inc = DST_GC_MAX; - goto out; + + spin_lock_bh(&dst_garbage.lock); + next = dst_garbage.list; + if (next) { + dst_garbage.list = NULL; + spin_unlock_bh(&dst_garbage.lock); + goto loop; } - if (!work_performed) { - if ((dst_gc_timer_expires += dst_gc_timer_inc) > DST_GC_MAX) - dst_gc_timer_expires = DST_GC_MAX; - dst_gc_timer_inc += DST_GC_INC; - } else { - dst_gc_timer_inc = DST_GC_INC; - dst_gc_timer_expires = DST_GC_MIN; + last->next = NULL; + dst_busy_list = head.next; + if (!dst_busy_list) + dst_garbage.timer_inc = DST_GC_MAX; + else { + /* + * if we freed less than 1/10 of delayed entries, + * we can sleep longer. + */ + if (work_performed <= delayed/10) { + dst_garbage.timer_expires += dst_garbage.timer_inc; + if (dst_garbage.timer_expires > DST_GC_MAX) + dst_garbage.timer_expires = DST_GC_MAX; + dst_garbage.timer_inc += DST_GC_INC; + } else { + dst_garbage.timer_inc = DST_GC_INC; + dst_garbage.timer_expires = DST_GC_MIN; + } + expires = dst_garbage.timer_expires; + /* + * if the next desired timer is more than 4 seconds in the + * future then round the timer to whole seconds + */ + if (expires > 4*HZ) + expires = round_jiffies_relative(expires); + schedule_delayed_work(&dst_gc_work, expires); } - dst_gc_timer.expires = jiffies + dst_gc_timer_expires; -#if RT_CACHE_DEBUG >= 2 - printk("dst_total: %d/%d %ld\n", - atomic_read(&dst_total), delayed, dst_gc_timer_expires); -#endif - add_timer(&dst_gc_timer); -out: - spin_unlock(&dst_lock); + spin_unlock_bh(&dst_garbage.lock); + mutex_unlock(&dst_gc_mutex); } -static int dst_discard_in(struct sk_buff *skb) +int dst_discard_sk(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } +EXPORT_SYMBOL(dst_discard_sk); -static int dst_discard_out(struct sk_buff *skb) -{ - kfree_skb(skb); - return 0; -} +const u32 dst_default_metrics[RTAX_MAX + 1] = { + /* This initializer is needed to force linker to place this variable + * into const section. Otherwise it might end into bss section. + * We really want to avoid false sharing on this variable, and catch + * any writes on it. + */ + [RTAX_MAX] = 0xdeadbeef, +}; -void * dst_alloc(struct dst_ops * ops) + +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, unsigned short flags) { - struct dst_entry * dst; + struct dst_entry *dst; - if (ops->gc && atomic_read(&ops->entries) > ops->gc_thresh) { - if (ops->gc()) + if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc(ops)) return NULL; } - dst = kmem_cache_alloc(ops->kmem_cachep, SLAB_ATOMIC); + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; - memset(dst, 0, ops->entry_size); - atomic_set(&dst->__refcnt, 0); + dst->child = NULL; + dst->dev = dev; + if (dev) + dev_hold(dev); dst->ops = ops; - dst->lastuse = jiffies; + dst_init_metrics(dst, dst_default_metrics, true); + dst->expires = 0UL; dst->path = dst; - dst->input = dst_discard_in; - dst->output = dst_discard_out; -#if RT_CACHE_DEBUG >= 2 - atomic_inc(&dst_total); + dst->from = NULL; +#ifdef CONFIG_XFRM + dst->xfrm = NULL; #endif - atomic_inc(&ops->entries); + dst->input = dst_discard; + dst->output = dst_discard_sk; + dst->error = 0; + dst->obsolete = initial_obsolete; + dst->header_len = 0; + dst->trailer_len = 0; +#ifdef CONFIG_IP_ROUTE_CLASSID + dst->tclassid = 0; +#endif + atomic_set(&dst->__refcnt, initial_ref); + dst->__use = 0; + dst->lastuse = jiffies; + dst->flags = flags; + dst->pending_confirm = 0; + dst->next = NULL; + if (!(flags & DST_NOCOUNT)) + dst_entries_add(ops, 1); return dst; } +EXPORT_SYMBOL(dst_alloc); -static void ___dst_free(struct dst_entry * dst) +static void ___dst_free(struct dst_entry *dst) { /* The first case (dev==NULL) is required, when protocol module is unloaded. */ if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { - dst->input = dst_discard_in; - dst->output = dst_discard_out; + dst->input = dst_discard; + dst->output = dst_discard_sk; } - dst->obsolete = 2; + dst->obsolete = DST_OBSOLETE_DEAD; } -void __dst_free(struct dst_entry * dst) +void __dst_free(struct dst_entry *dst) { - spin_lock_bh(&dst_lock); + spin_lock_bh(&dst_garbage.lock); ___dst_free(dst); - dst->next = dst_garbage_list; - dst_garbage_list = dst; - if (dst_gc_timer_inc > DST_GC_INC) { - dst_gc_timer_inc = DST_GC_INC; - dst_gc_timer_expires = DST_GC_MIN; - mod_timer(&dst_gc_timer, jiffies + dst_gc_timer_expires); + dst->next = dst_garbage.list; + dst_garbage.list = dst; + if (dst_garbage.timer_inc > DST_GC_INC) { + dst_garbage.timer_inc = DST_GC_INC; + dst_garbage.timer_expires = DST_GC_MIN; + mod_delayed_work(system_wq, &dst_gc_work, + dst_garbage.timer_expires); } - spin_unlock_bh(&dst_lock); + spin_unlock_bh(&dst_garbage.lock); } +EXPORT_SYMBOL(__dst_free); struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; - struct neighbour *neigh; - struct hh_cache *hh; smp_rmb(); again: - neigh = dst->neighbour; - hh = dst->hh; child = dst->child; - dst->hh = NULL; - if (hh && atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); - - if (neigh) { - dst->neighbour = NULL; - neigh_release(neigh); - } - - atomic_dec(&dst->ops->entries); + if (!(dst->flags & DST_NOCOUNT)) + dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); -#if RT_CACHE_DEBUG >= 2 - atomic_dec(&dst_total); -#endif kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; @@ -219,6 +267,89 @@ again: } return NULL; } +EXPORT_SYMBOL(dst_destroy); + +static void dst_destroy_rcu(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); +} + +void dst_release(struct dst_entry *dst) +{ + if (dst) { + int newrefcnt; + + newrefcnt = atomic_dec_return(&dst->__refcnt); + WARN_ON(newrefcnt < 0); + if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) + call_rcu(&dst->rcu_head, dst_destroy_rcu); + } +} +EXPORT_SYMBOL(dst_release); + +u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + + if (p) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + kfree(p); + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} +EXPORT_SYMBOL(dst_cow_metrics_generic); + +/* Caller asserts that dst_metrics_read_only(dst) is false. */ +void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + unsigned long prev, new; + + new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY; + prev = cmpxchg(&dst->_metrics, old, new); + if (prev == old) + kfree(__DST_METRICS_PTR(old)); +} +EXPORT_SYMBOL(__dst_destroy_metrics_generic); + +/** + * __skb_dst_set_noref - sets skb dst, without a reference + * @skb: buffer + * @dst: dst entry + * @force: if force is set, use noref version even for DST_NOCACHE entries + * + * Sets skb dst, assuming a reference was not taken on dst + * skb_dst_drop() should not dst_release() this dst + */ +void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force) +{ + WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + /* If dst not in cache, we must take a reference, because + * dst_release() will destroy dst as soon as its refcount becomes zero + */ + if (unlikely((dst->flags & DST_NOCACHE) && !force)) { + dst_hold(dst); + skb_dst_set(skb, dst); + } else { + skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; + } +} +EXPORT_SYMBOL(__skb_dst_set_noref); /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat @@ -228,8 +359,8 @@ again: * * Commented and originally written by Alexey. */ -static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) +static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int unregister) { if (dst->ops->ifdown) dst->ops->ifdown(dst, dev, unregister); @@ -238,33 +369,42 @@ static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, return; if (!unregister) { - dst->input = dst_discard_in; - dst->output = dst_discard_out; + dst->input = dst_discard; + dst->output = dst_discard_sk; } else { - dst->dev = &loopback_dev; - dev_hold(&loopback_dev); + dst->dev = dev_net(dst->dev)->loopback_dev; + dev_hold(dst->dev); dev_put(dev); - if (dst->neighbour && dst->neighbour->dev == dev) { - dst->neighbour->dev = &loopback_dev; - dev_put(dev); - dev_hold(&loopback_dev); - } } } -static int dst_dev_event(struct notifier_block *this, unsigned long event, void *ptr) +static int dst_dev_event(struct notifier_block *this, unsigned long event, + void *ptr) { - struct net_device *dev = ptr; - struct dst_entry *dst; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct dst_entry *dst, *last = NULL; switch (event) { - case NETDEV_UNREGISTER: + case NETDEV_UNREGISTER_FINAL: case NETDEV_DOWN: - spin_lock_bh(&dst_lock); - for (dst = dst_garbage_list; dst; dst = dst->next) { + mutex_lock(&dst_gc_mutex); + for (dst = dst_busy_list; dst; dst = dst->next) { + last = dst; dst_ifdown(dst, dev, event != NETDEV_DOWN); } - spin_unlock_bh(&dst_lock); + + spin_lock_bh(&dst_garbage.lock); + dst = dst_garbage.list; + dst_garbage.list = NULL; + spin_unlock_bh(&dst_garbage.lock); + + if (last) + last->next = dst; + else + dst_busy_list = dst; + for (; dst; dst = dst->next) + dst_ifdown(dst, dev, event != NETDEV_DOWN); + mutex_unlock(&dst_gc_mutex); break; } return NOTIFY_DONE; @@ -272,13 +412,10 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, void static struct notifier_block dst_dev_notifier = { .notifier_call = dst_dev_event, + .priority = -10, /* must be called after other network notifiers */ }; void __init dst_init(void) { register_netdevice_notifier(&dst_dev_notifier); } - -EXPORT_SYMBOL(__dst_free); -EXPORT_SYMBOL(dst_alloc); -EXPORT_SYMBOL(dst_destroy); diff --git a/net/core/dv.c b/net/core/dv.c deleted file mode 100644 index cf581407538..00000000000 --- a/net/core/dv.c +++ /dev/null @@ -1,549 +0,0 @@ -/* - * INET An implementation of the TCP/IP protocol suite for the LINUX - * operating system. INET is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * Generic frame diversion - * - * Authors: - * Benoit LOCHER: initial integration within the kernel with support for ethernet - * Dave Miller: improvement on the code (correctness, performance and source files) - * - */ -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/inet.h> -#include <linux/ip.h> -#include <linux/udp.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <linux/capability.h> -#include <linux/errno.h> -#include <linux/init.h> -#include <net/dst.h> -#include <net/arp.h> -#include <net/sock.h> -#include <net/ipv6.h> -#include <net/ip.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/checksum.h> -#include <linux/divert.h> -#include <linux/sockios.h> - -const char sysctl_divert_version[32]="0.46"; /* Current version */ - -static int __init dv_init(void) -{ - return 0; -} -module_init(dv_init); - -/* - * Allocate a divert_blk for a device. This must be an ethernet nic. - */ -int alloc_divert_blk(struct net_device *dev) -{ - int alloc_size = (sizeof(struct divert_blk) + 3) & ~3; - - dev->divert = NULL; - if (dev->type == ARPHRD_ETHER) { - dev->divert = (struct divert_blk *) - kmalloc(alloc_size, GFP_KERNEL); - if (dev->divert == NULL) { - printk(KERN_INFO "divert: unable to allocate divert_blk for %s\n", - dev->name); - return -ENOMEM; - } - - memset(dev->divert, 0, sizeof(struct divert_blk)); - dev_hold(dev); - } - - return 0; -} - -/* - * Free a divert_blk allocated by the above function, if it was - * allocated on that device. - */ -void free_divert_blk(struct net_device *dev) -{ - if (dev->divert) { - kfree(dev->divert); - dev->divert=NULL; - dev_put(dev); - } -} - -/* - * Adds a tcp/udp (source or dest) port to an array - */ -static int add_port(u16 ports[], u16 port) -{ - int i; - - if (port == 0) - return -EINVAL; - - /* Storing directly in network format for performance, - * thanks Dave :) - */ - port = htons(port); - - for (i = 0; i < MAX_DIVERT_PORTS; i++) { - if (ports[i] == port) - return -EALREADY; - } - - for (i = 0; i < MAX_DIVERT_PORTS; i++) { - if (ports[i] == 0) { - ports[i] = port; - return 0; - } - } - - return -ENOBUFS; -} - -/* - * Removes a port from an array tcp/udp (source or dest) - */ -static int remove_port(u16 ports[], u16 port) -{ - int i; - - if (port == 0) - return -EINVAL; - - /* Storing directly in network format for performance, - * thanks Dave ! - */ - port = htons(port); - - for (i = 0; i < MAX_DIVERT_PORTS; i++) { - if (ports[i] == port) { - ports[i] = 0; - return 0; - } - } - - return -EINVAL; -} - -/* Some basic sanity checks on the arguments passed to divert_ioctl() */ -static int check_args(struct divert_cf *div_cf, struct net_device **dev) -{ - char devname[32]; - int ret; - - if (dev == NULL) - return -EFAULT; - - /* GETVERSION: all other args are unused */ - if (div_cf->cmd == DIVCMD_GETVERSION) - return 0; - - /* Network device index should reasonably be between 0 and 1000 :) */ - if (div_cf->dev_index < 0 || div_cf->dev_index > 1000) - return -EINVAL; - - /* Let's try to find the ifname */ - sprintf(devname, "eth%d", div_cf->dev_index); - *dev = dev_get_by_name(devname); - - /* dev should NOT be null */ - if (*dev == NULL) - return -EINVAL; - - ret = 0; - - /* user issuing the ioctl must be a super one :) */ - if (!capable(CAP_SYS_ADMIN)) { - ret = -EPERM; - goto out; - } - - /* Device must have a divert_blk member NOT null */ - if ((*dev)->divert == NULL) - ret = -EINVAL; -out: - dev_put(*dev); - return ret; -} - -/* - * control function of the diverter - */ -#if 0 -#define DVDBG(a) \ - printk(KERN_DEBUG "divert_ioctl() line %d %s\n", __LINE__, (a)) -#else -#define DVDBG(a) -#endif - -int divert_ioctl(unsigned int cmd, struct divert_cf __user *arg) -{ - struct divert_cf div_cf; - struct divert_blk *div_blk; - struct net_device *dev; - int ret; - - switch (cmd) { - case SIOCGIFDIVERT: - DVDBG("SIOCGIFDIVERT, copy_from_user"); - if (copy_from_user(&div_cf, arg, sizeof(struct divert_cf))) - return -EFAULT; - DVDBG("before check_args"); - ret = check_args(&div_cf, &dev); - if (ret) - return ret; - DVDBG("after checkargs"); - div_blk = dev->divert; - - DVDBG("befre switch()"); - switch (div_cf.cmd) { - case DIVCMD_GETSTATUS: - /* Now, just give the user the raw divert block - * for him to play with :) - */ - if (copy_to_user(div_cf.arg1.ptr, dev->divert, - sizeof(struct divert_blk))) - return -EFAULT; - break; - - case DIVCMD_GETVERSION: - DVDBG("GETVERSION: checking ptr"); - if (div_cf.arg1.ptr == NULL) - return -EINVAL; - DVDBG("GETVERSION: copying data to userland"); - if (copy_to_user(div_cf.arg1.ptr, - sysctl_divert_version, 32)) - return -EFAULT; - DVDBG("GETVERSION: data copied"); - break; - - default: - return -EINVAL; - } - - break; - - case SIOCSIFDIVERT: - if (copy_from_user(&div_cf, arg, sizeof(struct divert_cf))) - return -EFAULT; - - ret = check_args(&div_cf, &dev); - if (ret) - return ret; - - div_blk = dev->divert; - - switch(div_cf.cmd) { - case DIVCMD_RESET: - div_blk->divert = 0; - div_blk->protos = DIVERT_PROTO_NONE; - memset(div_blk->tcp_dst, 0, - MAX_DIVERT_PORTS * sizeof(u16)); - memset(div_blk->tcp_src, 0, - MAX_DIVERT_PORTS * sizeof(u16)); - memset(div_blk->udp_dst, 0, - MAX_DIVERT_PORTS * sizeof(u16)); - memset(div_blk->udp_src, 0, - MAX_DIVERT_PORTS * sizeof(u16)); - return 0; - - case DIVCMD_DIVERT: - switch(div_cf.arg1.int32) { - case DIVARG1_ENABLE: - if (div_blk->divert) - return -EALREADY; - div_blk->divert = 1; - break; - - case DIVARG1_DISABLE: - if (!div_blk->divert) - return -EALREADY; - div_blk->divert = 0; - break; - - default: - return -EINVAL; - } - - break; - - case DIVCMD_IP: - switch(div_cf.arg1.int32) { - case DIVARG1_ENABLE: - if (div_blk->protos & DIVERT_PROTO_IP) - return -EALREADY; - div_blk->protos |= DIVERT_PROTO_IP; - break; - - case DIVARG1_DISABLE: - if (!(div_blk->protos & DIVERT_PROTO_IP)) - return -EALREADY; - div_blk->protos &= ~DIVERT_PROTO_IP; - break; - - default: - return -EINVAL; - } - - break; - - case DIVCMD_TCP: - switch(div_cf.arg1.int32) { - case DIVARG1_ENABLE: - if (div_blk->protos & DIVERT_PROTO_TCP) - return -EALREADY; - div_blk->protos |= DIVERT_PROTO_TCP; - break; - - case DIVARG1_DISABLE: - if (!(div_blk->protos & DIVERT_PROTO_TCP)) - return -EALREADY; - div_blk->protos &= ~DIVERT_PROTO_TCP; - break; - - default: - return -EINVAL; - } - - break; - - case DIVCMD_TCPDST: - switch(div_cf.arg1.int32) { - case DIVARG1_ADD: - return add_port(div_blk->tcp_dst, - div_cf.arg2.uint16); - - case DIVARG1_REMOVE: - return remove_port(div_blk->tcp_dst, - div_cf.arg2.uint16); - - default: - return -EINVAL; - } - - break; - - case DIVCMD_TCPSRC: - switch(div_cf.arg1.int32) { - case DIVARG1_ADD: - return add_port(div_blk->tcp_src, - div_cf.arg2.uint16); - - case DIVARG1_REMOVE: - return remove_port(div_blk->tcp_src, - div_cf.arg2.uint16); - - default: - return -EINVAL; - } - - break; - - case DIVCMD_UDP: - switch(div_cf.arg1.int32) { - case DIVARG1_ENABLE: - if (div_blk->protos & DIVERT_PROTO_UDP) - return -EALREADY; - div_blk->protos |= DIVERT_PROTO_UDP; - break; - - case DIVARG1_DISABLE: - if (!(div_blk->protos & DIVERT_PROTO_UDP)) - return -EALREADY; - div_blk->protos &= ~DIVERT_PROTO_UDP; - break; - - default: - return -EINVAL; - } - - break; - - case DIVCMD_UDPDST: - switch(div_cf.arg1.int32) { - case DIVARG1_ADD: - return add_port(div_blk->udp_dst, - div_cf.arg2.uint16); - - case DIVARG1_REMOVE: - return remove_port(div_blk->udp_dst, - div_cf.arg2.uint16); - - default: - return -EINVAL; - } - - break; - - case DIVCMD_UDPSRC: - switch(div_cf.arg1.int32) { - case DIVARG1_ADD: - return add_port(div_blk->udp_src, - div_cf.arg2.uint16); - - case DIVARG1_REMOVE: - return remove_port(div_blk->udp_src, - div_cf.arg2.uint16); - - default: - return -EINVAL; - } - - break; - - case DIVCMD_ICMP: - switch(div_cf.arg1.int32) { - case DIVARG1_ENABLE: - if (div_blk->protos & DIVERT_PROTO_ICMP) - return -EALREADY; - div_blk->protos |= DIVERT_PROTO_ICMP; - break; - - case DIVARG1_DISABLE: - if (!(div_blk->protos & DIVERT_PROTO_ICMP)) - return -EALREADY; - div_blk->protos &= ~DIVERT_PROTO_ICMP; - break; - - default: - return -EINVAL; - } - - break; - - default: - return -EINVAL; - } - - break; - - default: - return -EINVAL; - } - - return 0; -} - - -/* - * Check if packet should have its dest mac address set to the box itself - * for diversion - */ - -#define ETH_DIVERT_FRAME(skb) \ - memcpy(eth_hdr(skb), skb->dev->dev_addr, ETH_ALEN); \ - skb->pkt_type=PACKET_HOST - -void divert_frame(struct sk_buff *skb) -{ - struct ethhdr *eth = eth_hdr(skb); - struct iphdr *iph; - struct tcphdr *tcph; - struct udphdr *udph; - struct divert_blk *divert = skb->dev->divert; - int i, src, dst; - unsigned char *skb_data_end = skb->data + skb->len; - - /* Packet is already aimed at us, return */ - if (!compare_ether_addr(eth->h_dest, skb->dev->dev_addr)) - return; - - /* proto is not IP, do nothing */ - if (eth->h_proto != htons(ETH_P_IP)) - return; - - /* Divert all IP frames ? */ - if (divert->protos & DIVERT_PROTO_IP) { - ETH_DIVERT_FRAME(skb); - return; - } - - /* Check for possible (maliciously) malformed IP frame (thanks Dave) */ - iph = (struct iphdr *) skb->data; - if (((iph->ihl<<2)+(unsigned char*)(iph)) >= skb_data_end) { - printk(KERN_INFO "divert: malformed IP packet !\n"); - return; - } - - switch (iph->protocol) { - /* Divert all ICMP frames ? */ - case IPPROTO_ICMP: - if (divert->protos & DIVERT_PROTO_ICMP) { - ETH_DIVERT_FRAME(skb); - return; - } - break; - - /* Divert all TCP frames ? */ - case IPPROTO_TCP: - if (divert->protos & DIVERT_PROTO_TCP) { - ETH_DIVERT_FRAME(skb); - return; - } - - /* Check for possible (maliciously) malformed IP - * frame (thanx Dave) - */ - tcph = (struct tcphdr *) - (((unsigned char *)iph) + (iph->ihl<<2)); - if (((unsigned char *)(tcph+1)) >= skb_data_end) { - printk(KERN_INFO "divert: malformed TCP packet !\n"); - return; - } - - /* Divert some tcp dst/src ports only ?*/ - for (i = 0; i < MAX_DIVERT_PORTS; i++) { - dst = divert->tcp_dst[i]; - src = divert->tcp_src[i]; - if ((dst && dst == tcph->dest) || - (src && src == tcph->source)) { - ETH_DIVERT_FRAME(skb); - return; - } - } - break; - - /* Divert all UDP frames ? */ - case IPPROTO_UDP: - if (divert->protos & DIVERT_PROTO_UDP) { - ETH_DIVERT_FRAME(skb); - return; - } - - /* Check for possible (maliciously) malformed IP - * packet (thanks Dave) - */ - udph = (struct udphdr *) - (((unsigned char *)iph) + (iph->ihl<<2)); - if (((unsigned char *)(udph+1)) >= skb_data_end) { - printk(KERN_INFO - "divert: malformed UDP packet !\n"); - return; - } - - /* Divert some udp dst/src ports only ? */ - for (i = 0; i < MAX_DIVERT_PORTS; i++) { - dst = divert->udp_dst[i]; - src = divert->udp_src[i]; - if ((dst && dst == udph->dest) || - (src && src == udph->source)) { - ETH_DIVERT_FRAME(skb); - return; - } - } - break; - } -} diff --git a/net/core/ethtool.c b/net/core/ethtool.c index e6f76106a99..17cb912793f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -3,10 +3,12 @@ * Copyright (c) 2003 Matthew Wilcox <matthew@wil.cx> * * This file is where we call all the ethtool_ops commands to get - * the information ethtool needs. We fall back to calling do_ioctl() - * for drivers which haven't been converted to ethtool_ops yet. + * the information ethtool needs. * - * It's GPL, stupid. + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. */ #include <linux/module.h> @@ -15,9 +17,16 @@ #include <linux/errno.h> #include <linux/ethtool.h> #include <linux/netdevice.h> -#include <asm/uaccess.h> +#include <linux/net_tstamp.h> +#include <linux/phy.h> +#include <linux/bitops.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> +#include <linux/rtnetlink.h> +#include <linux/sched.h> -/* +/* * Some useful ethtool_ops methods that're device independent. * If we find that all drivers want to do the same thing here, * we can turn these into dev_() function calls. @@ -27,98 +36,317 @@ u32 ethtool_op_get_link(struct net_device *dev) { return netif_carrier_ok(dev) ? 1 : 0; } +EXPORT_SYMBOL(ethtool_op_get_link); -u32 ethtool_op_get_tx_csum(struct net_device *dev) +int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { - return (dev->features & (NETIF_F_IP_CSUM | NETIF_F_HW_CSUM)) != 0; + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + return 0; } +EXPORT_SYMBOL(ethtool_op_get_ts_info); -int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) +/* Handlers for each ethtool command */ + +#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) + +static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { + [NETIF_F_SG_BIT] = "tx-scatter-gather", + [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", + [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", + [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", + [NETIF_F_HIGHDMA_BIT] = "highdma", + [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", + [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", + + [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", + [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", + [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", + [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", + [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", + [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", + [NETIF_F_GSO_BIT] = "tx-generic-segmentation", + [NETIF_F_LLTX_BIT] = "tx-lockless", + [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", + [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_LRO_BIT] = "rx-lro", + + [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", + [NETIF_F_UFO_BIT] = "tx-udp-fragmentation", + [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", + [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", + [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", + [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation", + [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", + [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation", + + [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", + [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", + [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", + [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", + [NETIF_F_RXHASH_BIT] = "rx-hashing", + [NETIF_F_RXCSUM_BIT] = "rx-checksum", + [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", + [NETIF_F_LOOPBACK_BIT] = "loopback", + [NETIF_F_RXFCS_BIT] = "rx-fcs", + [NETIF_F_RXALL_BIT] = "rx-all", + [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", + [NETIF_F_BUSY_POLL_BIT] = "busy-poll", +}; + +static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { - if (data) - dev->features |= NETIF_F_IP_CSUM; - else - dev->features &= ~NETIF_F_IP_CSUM; + struct ethtool_gfeatures cmd = { + .cmd = ETHTOOL_GFEATURES, + .size = ETHTOOL_DEV_FEATURE_WORDS, + }; + struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; + u32 __user *sizeaddr; + u32 copy_size; + int i; + + /* in case feature bits run out again */ + BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t)); + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + features[i].available = (u32)(dev->hw_features >> (32 * i)); + features[i].requested = (u32)(dev->wanted_features >> (32 * i)); + features[i].active = (u32)(dev->features >> (32 * i)); + features[i].never_changed = + (u32)(NETIF_F_NEVER_CHANGE >> (32 * i)); + } + + sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); + if (get_user(copy_size, sizeaddr)) + return -EFAULT; + + if (copy_size > ETHTOOL_DEV_FEATURE_WORDS) + copy_size = ETHTOOL_DEV_FEATURE_WORDS; + + if (copy_to_user(useraddr, &cmd, sizeof(cmd))) + return -EFAULT; + useraddr += sizeof(cmd); + if (copy_to_user(useraddr, features, copy_size * sizeof(*features))) + return -EFAULT; return 0; } -int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) +static int ethtool_set_features(struct net_device *dev, void __user *useraddr) { - if (data) - dev->features |= NETIF_F_HW_CSUM; - else - dev->features &= ~NETIF_F_HW_CSUM; + struct ethtool_sfeatures cmd; + struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; + netdev_features_t wanted = 0, valid = 0; + int i, ret = 0; - return 0; + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + useraddr += sizeof(cmd); + + if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS) + return -EINVAL; + + if (copy_from_user(features, useraddr, sizeof(features))) + return -EFAULT; + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + valid |= (netdev_features_t)features[i].valid << (32 * i); + wanted |= (netdev_features_t)features[i].requested << (32 * i); + } + + if (valid & ~NETIF_F_ETHTOOL_BITS) + return -EINVAL; + + if (valid & ~dev->hw_features) { + valid &= dev->hw_features; + ret |= ETHTOOL_F_UNSUPPORTED; + } + + dev->wanted_features &= ~valid; + dev->wanted_features |= wanted & valid; + __netdev_update_features(dev); + + if ((dev->wanted_features ^ dev->features) & valid) + ret |= ETHTOOL_F_WISH; + + return ret; } -u32 ethtool_op_get_sg(struct net_device *dev) + +static int __ethtool_get_sset_count(struct net_device *dev, int sset) { - return (dev->features & NETIF_F_SG) != 0; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (sset == ETH_SS_FEATURES) + return ARRAY_SIZE(netdev_features_strings); + + if (ops->get_sset_count && ops->get_strings) + return ops->get_sset_count(dev, sset); + else + return -EOPNOTSUPP; } -int ethtool_op_set_sg(struct net_device *dev, u32 data) +static void __ethtool_get_strings(struct net_device *dev, + u32 stringset, u8 *data) { - if (data) - dev->features |= NETIF_F_SG; - else - dev->features &= ~NETIF_F_SG; + const struct ethtool_ops *ops = dev->ethtool_ops; - return 0; + if (stringset == ETH_SS_FEATURES) + memcpy(data, netdev_features_strings, + sizeof(netdev_features_strings)); + else + /* ops->get_strings is valid because checked earlier */ + ops->get_strings(dev, stringset, data); } -u32 ethtool_op_get_tso(struct net_device *dev) +static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) { - return (dev->features & NETIF_F_TSO) != 0; + /* feature masks of legacy discrete ethtool ops */ + + switch (eth_cmd) { + case ETHTOOL_GTXCSUM: + case ETHTOOL_STXCSUM: + return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM; + case ETHTOOL_GRXCSUM: + case ETHTOOL_SRXCSUM: + return NETIF_F_RXCSUM; + case ETHTOOL_GSG: + case ETHTOOL_SSG: + return NETIF_F_SG; + case ETHTOOL_GTSO: + case ETHTOOL_STSO: + return NETIF_F_ALL_TSO; + case ETHTOOL_GUFO: + case ETHTOOL_SUFO: + return NETIF_F_UFO; + case ETHTOOL_GGSO: + case ETHTOOL_SGSO: + return NETIF_F_GSO; + case ETHTOOL_GGRO: + case ETHTOOL_SGRO: + return NETIF_F_GRO; + default: + BUG(); + } } -int ethtool_op_set_tso(struct net_device *dev, u32 data) +static int ethtool_get_one_feature(struct net_device *dev, + char __user *useraddr, u32 ethcmd) { - if (data) - dev->features |= NETIF_F_TSO; - else - dev->features &= ~NETIF_F_TSO; + netdev_features_t mask = ethtool_get_feature_mask(ethcmd); + struct ethtool_value edata = { + .cmd = ethcmd, + .data = !!(dev->features & mask), + }; + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; return 0; } -int ethtool_op_get_perm_addr(struct net_device *dev, struct ethtool_perm_addr *addr, u8 *data) +static int ethtool_set_one_feature(struct net_device *dev, + void __user *useraddr, u32 ethcmd) { - unsigned char len = dev->addr_len; - if ( addr->size < len ) - return -ETOOSMALL; - - addr->size = len; - memcpy(data, dev->perm_addr, len); + struct ethtool_value edata; + netdev_features_t mask; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + mask = ethtool_get_feature_mask(ethcmd); + mask &= dev->hw_features; + if (!mask) + return -EOPNOTSUPP; + + if (edata.data) + dev->wanted_features |= mask; + else + dev->wanted_features &= ~mask; + + __netdev_update_features(dev); + return 0; } - -u32 ethtool_op_get_ufo(struct net_device *dev) +#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \ + ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH) +#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_NTUPLE | \ + NETIF_F_RXHASH) + +static u32 __ethtool_get_flags(struct net_device *dev) { - return (dev->features & NETIF_F_UFO) != 0; + u32 flags = 0; + + if (dev->features & NETIF_F_LRO) + flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) + flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) + flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) + flags |= ETH_FLAG_RXHASH; + + return flags; } -int ethtool_op_set_ufo(struct net_device *dev, u32 data) +static int __ethtool_set_flags(struct net_device *dev, u32 data) { - if (data) - dev->features |= NETIF_F_UFO; - else - dev->features &= ~NETIF_F_UFO; + netdev_features_t features = 0, changed; + + if (data & ~ETH_ALL_FLAGS) + return -EINVAL; + + if (data & ETH_FLAG_LRO) + features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_RX; + if (data & ETH_FLAG_TXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_TX; + if (data & ETH_FLAG_NTUPLE) + features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; + + /* allow changing only bits set in hw_features */ + changed = (features ^ dev->features) & ETH_ALL_FEATURES; + if (changed & ~dev->hw_features) + return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; + + dev->wanted_features = + (dev->wanted_features & ~changed) | (features & changed); + + __netdev_update_features(dev); + return 0; } -/* Handlers for each ethtool command */ - -static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) +int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - int err; + ASSERT_RTNL(); if (!dev->ethtool_ops->get_settings) return -EOPNOTSUPP; - err = dev->ethtool_ops->get_settings(dev, &cmd); + memset(cmd, 0, sizeof(struct ethtool_cmd)); + cmd->cmd = ETHTOOL_GSET; + return dev->ethtool_ops->get_settings(dev, cmd); +} +EXPORT_SYMBOL(__ethtool_get_settings); + +static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) +{ + int err; + struct ethtool_cmd cmd; + + err = __ethtool_get_settings(dev, &cmd); if (err < 0) return err; @@ -140,22 +368,42 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_settings(dev, &cmd); } -static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, + void __user *useraddr) { struct ethtool_drvinfo info; - struct ethtool_ops *ops = dev->ethtool_ops; - - if (!ops->get_drvinfo) - return -EOPNOTSUPP; + const struct ethtool_ops *ops = dev->ethtool_ops; memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; - ops->get_drvinfo(dev, &info); + if (ops->get_drvinfo) { + ops->get_drvinfo(dev, &info); + } else if (dev->dev.parent && dev->dev.parent->driver) { + strlcpy(info.bus_info, dev_name(dev->dev.parent), + sizeof(info.bus_info)); + strlcpy(info.driver, dev->dev.parent->driver->name, + sizeof(info.driver)); + } else { + return -EOPNOTSUPP; + } - if (ops->self_test_count) - info.testinfo_len = ops->self_test_count(dev); - if (ops->get_stats_count) - info.n_stats = ops->get_stats_count(dev); + /* + * this method of obtaining string set info is deprecated; + * Use ETHTOOL_GSSET_INFO instead. + */ + if (ops->get_sset_count) { + int rc; + + rc = ops->get_sset_count(dev, ETH_SS_TEST); + if (rc >= 0) + info.testinfo_len = rc; + rc = ops->get_sset_count(dev, ETH_SS_STATS); + if (rc >= 0) + info.n_stats = rc; + rc = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); + if (rc >= 0) + info.n_priv_flags = rc; + } if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); if (ops->get_eeprom_len) @@ -166,10 +414,438 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) return 0; } +static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_sset_info info; + u64 sset_mask; + int i, idx = 0, n_bits = 0, ret, rc; + u32 *info_buf = NULL; + + if (copy_from_user(&info, useraddr, sizeof(info))) + return -EFAULT; + + /* store copy of mask, because we zero struct later on */ + sset_mask = info.sset_mask; + if (!sset_mask) + return 0; + + /* calculate size of return buffer */ + n_bits = hweight64(sset_mask); + + memset(&info, 0, sizeof(info)); + info.cmd = ETHTOOL_GSSET_INFO; + + info_buf = kzalloc(n_bits * sizeof(u32), GFP_USER); + if (!info_buf) + return -ENOMEM; + + /* + * fill return buffer based on input bitmask and successful + * get_sset_count return + */ + for (i = 0; i < 64; i++) { + if (!(sset_mask & (1ULL << i))) + continue; + + rc = __ethtool_get_sset_count(dev, i); + if (rc >= 0) { + info.sset_mask |= (1ULL << i); + info_buf[idx++] = rc; + } + } + + ret = -EFAULT; + if (copy_to_user(useraddr, &info, sizeof(info))) + goto out; + + useraddr += offsetof(struct ethtool_sset_info, data); + if (copy_to_user(useraddr, info_buf, idx * sizeof(u32))) + goto out; + + ret = 0; + +out: + kfree(info_buf); + return ret; +} + +static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, + u32 cmd, void __user *useraddr) +{ + struct ethtool_rxnfc info; + size_t info_size = sizeof(info); + int rc; + + if (!dev->ethtool_ops->set_rxnfc) + return -EOPNOTSUPP; + + /* struct ethtool_rxnfc was originally defined for + * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data + * members. User-space might still be using that + * definition. */ + if (cmd == ETHTOOL_SRXFH) + info_size = (offsetof(struct ethtool_rxnfc, data) + + sizeof(info.data)); + + if (copy_from_user(&info, useraddr, info_size)) + return -EFAULT; + + rc = dev->ethtool_ops->set_rxnfc(dev, &info); + if (rc) + return rc; + + if (cmd == ETHTOOL_SRXCLSRLINS && + copy_to_user(useraddr, &info, info_size)) + return -EFAULT; + + return 0; +} + +static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, + u32 cmd, void __user *useraddr) +{ + struct ethtool_rxnfc info; + size_t info_size = sizeof(info); + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + void *rule_buf = NULL; + + if (!ops->get_rxnfc) + return -EOPNOTSUPP; + + /* struct ethtool_rxnfc was originally defined for + * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data + * members. User-space might still be using that + * definition. */ + if (cmd == ETHTOOL_GRXFH) + info_size = (offsetof(struct ethtool_rxnfc, data) + + sizeof(info.data)); + + if (copy_from_user(&info, useraddr, info_size)) + return -EFAULT; + + if (info.cmd == ETHTOOL_GRXCLSRLALL) { + if (info.rule_cnt > 0) { + if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32)) + rule_buf = kzalloc(info.rule_cnt * sizeof(u32), + GFP_USER); + if (!rule_buf) + return -ENOMEM; + } + } + + ret = ops->get_rxnfc(dev, &info, rule_buf); + if (ret < 0) + goto err_out; + + ret = -EFAULT; + if (copy_to_user(useraddr, &info, info_size)) + goto err_out; + + if (rule_buf) { + useraddr += offsetof(struct ethtool_rxnfc, rule_locs); + if (copy_to_user(useraddr, rule_buf, + info.rule_cnt * sizeof(u32))) + goto err_out; + } + ret = 0; + +err_out: + kfree(rule_buf); + + return ret; +} + +static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, + struct ethtool_rxnfc *rx_rings, + u32 size) +{ + int i; + + if (copy_from_user(indir, useraddr, size * sizeof(indir[0]))) + return -EFAULT; + + /* Validate ring indices */ + for (i = 0; i < size; i++) + if (indir[i] >= rx_rings->data) + return -EINVAL; + + return 0; +} + +static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, + void __user *useraddr) +{ + u32 user_size, dev_size; + u32 *indir; + int ret; + + if (!dev->ethtool_ops->get_rxfh_indir_size || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + if (dev_size == 0) + return -EOPNOTSUPP; + + if (copy_from_user(&user_size, + useraddr + offsetof(struct ethtool_rxfh_indir, size), + sizeof(user_size))) + return -EFAULT; + + if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size), + &dev_size, sizeof(dev_size))) + return -EFAULT; + + /* If the user buffer size is 0, this is just a query for the + * device table size. Otherwise, if it's smaller than the + * device table size it's an error. + */ + if (user_size < dev_size) + return user_size == 0 ? 0 : -EINVAL; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); + if (!indir) + return -ENOMEM; + + ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL); + if (ret) + goto out; + + if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh_indir, ring_index[0]), + indir, dev_size * sizeof(indir[0]))) + ret = -EFAULT; + +out: + kfree(indir); + return ret; +} + +static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_rxnfc rx_rings; + u32 user_size, dev_size, i; + u32 *indir; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]); + + if (!ops->get_rxfh_indir_size || !ops->set_rxfh || + !ops->get_rxnfc) + return -EOPNOTSUPP; + + dev_size = ops->get_rxfh_indir_size(dev); + if (dev_size == 0) + return -EOPNOTSUPP; + + if (copy_from_user(&user_size, + useraddr + offsetof(struct ethtool_rxfh_indir, size), + sizeof(user_size))) + return -EFAULT; + + if (user_size != 0 && user_size != dev_size) + return -EINVAL; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); + if (!indir) + return -ENOMEM; + + rx_rings.cmd = ETHTOOL_GRXRINGS; + ret = ops->get_rxnfc(dev, &rx_rings, NULL); + if (ret) + goto out; + + if (user_size == 0) { + for (i = 0; i < dev_size; i++) + indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); + } else { + ret = ethtool_copy_validate_indir(indir, + useraddr + ringidx_offset, + &rx_rings, + dev_size); + if (ret) + goto out; + } + + ret = ops->set_rxfh(dev, indir, NULL); + +out: + kfree(indir); + return ret; +} + +static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, + void __user *useraddr) +{ + int ret; + const struct ethtool_ops *ops = dev->ethtool_ops; + u32 user_indir_size, user_key_size; + u32 dev_indir_size = 0, dev_key_size = 0; + struct ethtool_rxfh rxfh; + u32 total_size; + u32 indir_bytes; + u32 *indir = NULL; + u8 *hkey = NULL; + u8 *rss_config; + + if (!(dev->ethtool_ops->get_rxfh_indir_size || + dev->ethtool_ops->get_rxfh_key_size) || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + + if (ops->get_rxfh_indir_size) + dev_indir_size = ops->get_rxfh_indir_size(dev); + if (ops->get_rxfh_key_size) + dev_key_size = ops->get_rxfh_key_size(dev); + + if ((dev_key_size + dev_indir_size) == 0) + return -EOPNOTSUPP; + + if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) + return -EFAULT; + user_indir_size = rxfh.indir_size; + user_key_size = rxfh.key_size; + + /* Check that reserved fields are 0 for now */ + if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1]) + return -EINVAL; + + rxfh.indir_size = dev_indir_size; + rxfh.key_size = dev_key_size; + if (copy_to_user(useraddr, &rxfh, sizeof(rxfh))) + return -EFAULT; + + /* If the user buffer size is 0, this is just a query for the + * device table size and key size. Otherwise, if the User size is + * not equal to device table size or key size it's an error. + */ + if (!user_indir_size && !user_key_size) + return 0; + + if ((user_indir_size && (user_indir_size != dev_indir_size)) || + (user_key_size && (user_key_size != dev_key_size))) + return -EINVAL; + + indir_bytes = user_indir_size * sizeof(indir[0]); + total_size = indir_bytes + user_key_size; + rss_config = kzalloc(total_size, GFP_USER); + if (!rss_config) + return -ENOMEM; + + if (user_indir_size) + indir = (u32 *)rss_config; + + if (user_key_size) + hkey = rss_config + indir_bytes; + + ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey); + if (!ret) { + if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, rss_config[0]), + rss_config, total_size)) + ret = -EFAULT; + } + + kfree(rss_config); + + return ret; +} + +static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, + void __user *useraddr) +{ + int ret; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc rx_rings; + struct ethtool_rxfh rxfh; + u32 dev_indir_size = 0, dev_key_size = 0, i; + u32 *indir = NULL, indir_bytes = 0; + u8 *hkey = NULL; + u8 *rss_config; + u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); + + if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) || + !ops->get_rxnfc || !ops->set_rxfh) + return -EOPNOTSUPP; + + if (ops->get_rxfh_indir_size) + dev_indir_size = ops->get_rxfh_indir_size(dev); + if (ops->get_rxfh_key_size) + dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev); + if ((dev_key_size + dev_indir_size) == 0) + return -EOPNOTSUPP; + + if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) + return -EFAULT; + + /* Check that reserved fields are 0 for now */ + if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1]) + return -EINVAL; + + /* If either indir or hash key is valid, proceed further. + * It is not valid to request that both be unchanged. + */ + if ((rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && + rxfh.indir_size != dev_indir_size) || + (rxfh.key_size && (rxfh.key_size != dev_key_size)) || + (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && + rxfh.key_size == 0)) + return -EINVAL; + + if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) + indir_bytes = dev_indir_size * sizeof(indir[0]); + + rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); + if (!rss_config) + return -ENOMEM; + + rx_rings.cmd = ETHTOOL_GRXRINGS; + ret = ops->get_rxnfc(dev, &rx_rings, NULL); + if (ret) + goto out; + + /* rxfh.indir_size == 0 means reset the indir table to default. + * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged. + */ + if (rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { + indir = (u32 *)rss_config; + ret = ethtool_copy_validate_indir(indir, + useraddr + rss_cfg_offset, + &rx_rings, + rxfh.indir_size); + if (ret) + goto out; + } else if (rxfh.indir_size == 0) { + indir = (u32 *)rss_config; + for (i = 0; i < dev_indir_size; i++) + indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); + } + + if (rxfh.key_size) { + hkey = rss_config + indir_bytes; + if (copy_from_user(hkey, + useraddr + rss_cfg_offset + indir_bytes, + rxfh.key_size)) { + ret = -EFAULT; + goto out; + } + } + + ret = ops->set_rxfh(dev, indir, hkey); + +out: + kfree(rss_config); + return ret; +} + static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) { struct ethtool_regs regs; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; void *regbuf; int reglen, ret; @@ -183,8 +859,8 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = kmalloc(reglen, GFP_USER); - if (!regbuf) + regbuf = vzalloc(reglen); + if (reglen && !regbuf) return -ENOMEM; ops->get_regs(dev, ®s, regbuf); @@ -193,18 +869,38 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (copy_to_user(useraddr, ®s, sizeof(regs))) goto out; useraddr += offsetof(struct ethtool_regs, data); - if (copy_to_user(useraddr, regbuf, regs.len)) + if (regbuf && copy_to_user(useraddr, regbuf, regs.len)) goto out; ret = 0; out: - kfree(regbuf); + vfree(regbuf); return ret; } +static int ethtool_reset(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value reset; + int ret; + + if (!dev->ethtool_ops->reset) + return -EOPNOTSUPP; + + if (copy_from_user(&reset, useraddr, sizeof(reset))) + return -EFAULT; + + ret = dev->ethtool_ops->reset(dev, &reset.data); + if (ret) + return ret; + + if (copy_to_user(useraddr, &reset, sizeof(reset))) + return -EFAULT; + return 0; +} + static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { - struct ethtool_wolinfo wol = { ETHTOOL_GWOL }; + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; @@ -229,32 +925,38 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_wol(dev, &wol); } -static int ethtool_get_msglevel(struct net_device *dev, char __user *useraddr) +static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GMSGLVL }; + struct ethtool_eee edata; + int rc; - if (!dev->ethtool_ops->get_msglevel) + if (!dev->ethtool_ops->get_eee) return -EOPNOTSUPP; - edata.data = dev->ethtool_ops->get_msglevel(dev); + memset(&edata, 0, sizeof(struct ethtool_eee)); + edata.cmd = ETHTOOL_GEEE; + rc = dev->ethtool_ops->get_eee(dev, &edata); + + if (rc) + return rc; if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; + return 0; } -static int ethtool_set_msglevel(struct net_device *dev, char __user *useraddr) +static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) { - struct ethtool_value edata; + struct ethtool_eee edata; - if (!dev->ethtool_ops->set_msglevel) + if (!dev->ethtool_ops->set_eee) return -EOPNOTSUPP; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; - dev->ethtool_ops->set_msglevel(dev, edata.data); - return 0; + return dev->ethtool_ops->set_eee(dev, &edata); } static int ethtool_nway_reset(struct net_device *dev) @@ -265,29 +967,30 @@ static int ethtool_nway_reset(struct net_device *dev) return dev->ethtool_ops->nway_reset(dev); } -static int ethtool_get_link(struct net_device *dev, void __user *useraddr) +static int ethtool_get_link(struct net_device *dev, char __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GLINK }; + struct ethtool_value edata = { .cmd = ETHTOOL_GLINK }; if (!dev->ethtool_ops->get_link) return -EOPNOTSUPP; - edata.data = dev->ethtool_ops->get_link(dev); + edata.data = netif_running(dev) && dev->ethtool_ops->get_link(dev); if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } -static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) +static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, + int (*getter)(struct net_device *, + struct ethtool_eeprom *, u8 *), + u32 total_len) { struct ethtool_eeprom eeprom; - struct ethtool_ops *ops = dev->ethtool_ops; + void __user *userbuf = useraddr + sizeof(eeprom); + u32 bytes_remaining; u8 *data; - int ret; - - if (!ops->get_eeprom || !ops->get_eeprom_len) - return -EOPNOTSUPP; + int ret = 0; if (copy_from_user(&eeprom, useraddr, sizeof(eeprom))) return -EFAULT; @@ -297,39 +1000,57 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) return -EINVAL; /* Check for exceeding total eeprom len */ - if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) + if (eeprom.offset + eeprom.len > total_len) return -EINVAL; - data = kmalloc(eeprom.len, GFP_USER); + data = kmalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; - ret = -EFAULT; - if (copy_from_user(data, useraddr + sizeof(eeprom), eeprom.len)) - goto out; - - ret = ops->get_eeprom(dev, &eeprom, data); - if (ret) - goto out; + bytes_remaining = eeprom.len; + while (bytes_remaining > 0) { + eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE); + + ret = getter(dev, &eeprom, data); + if (ret) + break; + if (copy_to_user(userbuf, data, eeprom.len)) { + ret = -EFAULT; + break; + } + userbuf += eeprom.len; + eeprom.offset += eeprom.len; + bytes_remaining -= eeprom.len; + } - ret = -EFAULT; + eeprom.len = userbuf - (useraddr + sizeof(eeprom)); + eeprom.offset -= eeprom.len; if (copy_to_user(useraddr, &eeprom, sizeof(eeprom))) - goto out; - if (copy_to_user(useraddr + sizeof(eeprom), data, eeprom.len)) - goto out; - ret = 0; + ret = -EFAULT; - out: kfree(data); return ret; } +static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_eeprom || !ops->get_eeprom_len) + return -EOPNOTSUPP; + + return ethtool_get_any_eeprom(dev, useraddr, ops->get_eeprom, + ops->get_eeprom_len(dev)); +} + static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; + void __user *userbuf = useraddr + sizeof(eeprom); + u32 bytes_remaining; u8 *data; - int ret; + int ret = 0; if (!ops->set_eeprom || !ops->get_eeprom_len) return -EOPNOTSUPP; @@ -345,29 +1066,34 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL; - data = kmalloc(eeprom.len, GFP_USER); + data = kmalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; - ret = -EFAULT; - if (copy_from_user(data, useraddr + sizeof(eeprom), eeprom.len)) - goto out; - - ret = ops->set_eeprom(dev, &eeprom, data); - if (ret) - goto out; - - if (copy_to_user(useraddr + sizeof(eeprom), data, eeprom.len)) - ret = -EFAULT; + bytes_remaining = eeprom.len; + while (bytes_remaining > 0) { + eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE); + + if (copy_from_user(data, userbuf, eeprom.len)) { + ret = -EFAULT; + break; + } + ret = ops->set_eeprom(dev, &eeprom, data); + if (ret) + break; + userbuf += eeprom.len; + eeprom.offset += eeprom.len; + bytes_remaining -= eeprom.len; + } - out: kfree(data); return ret; } -static int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, + void __user *useraddr) { - struct ethtool_coalesce coalesce = { ETHTOOL_GCOALESCE }; + struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; @@ -379,7 +1105,8 @@ static int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) return 0; } -static int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, + void __user *useraddr) { struct ethtool_coalesce coalesce; @@ -394,7 +1121,7 @@ static int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_ringparam ringparam = { ETHTOOL_GRINGPARAM }; + struct ethtool_ringparam ringparam = { .cmd = ETHTOOL_GRINGPARAM }; if (!dev->ethtool_ops->get_ringparam) return -EOPNOTSUPP; @@ -419,6 +1146,35 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_ringparam(dev, &ringparam); } +static noinline_for_stack int ethtool_get_channels(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + + if (!dev->ethtool_ops->get_channels) + return -EOPNOTSUPP; + + dev->ethtool_ops->get_channels(dev, &channels); + + if (copy_to_user(useraddr, &channels, sizeof(channels))) + return -EFAULT; + return 0; +} + +static noinline_for_stack int ethtool_set_channels(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_channels channels; + + if (!dev->ethtool_ops->set_channels) + return -EOPNOTSUPP; + + if (copy_from_user(&channels, useraddr, sizeof(channels))) + return -EFAULT; + + return dev->ethtool_ops->set_channels(dev, &channels); +} + static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam = { ETHTOOL_GPAUSEPARAM }; @@ -437,7 +1193,7 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam; - if (!dev->ethtool_ops->get_pauseparam) + if (!dev->ethtool_ops->set_pauseparam) return -EOPNOTSUPP; if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam))) @@ -446,364 +1202,485 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); } -static int ethtool_get_rx_csum(struct net_device *dev, char __user *useraddr) +static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GRXCSUM }; + struct ethtool_test test; + const struct ethtool_ops *ops = dev->ethtool_ops; + u64 *data; + int ret, test_len; - if (!dev->ethtool_ops->get_rx_csum) + if (!ops->self_test || !ops->get_sset_count) return -EOPNOTSUPP; - edata.data = dev->ethtool_ops->get_rx_csum(dev); + test_len = ops->get_sset_count(dev, ETH_SS_TEST); + if (test_len < 0) + return test_len; + WARN_ON(test_len == 0); - if (copy_to_user(useraddr, &edata, sizeof(edata))) + if (copy_from_user(&test, useraddr, sizeof(test))) return -EFAULT; - return 0; + + test.len = test_len; + data = kmalloc(test_len * sizeof(u64), GFP_USER); + if (!data) + return -ENOMEM; + + ops->self_test(dev, &test, data); + + ret = -EFAULT; + if (copy_to_user(useraddr, &test, sizeof(test))) + goto out; + useraddr += sizeof(test); + if (copy_to_user(useraddr, data, test.len * sizeof(u64))) + goto out; + ret = 0; + + out: + kfree(data); + return ret; } -static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr) +static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) { - struct ethtool_value edata; - - if (!dev->ethtool_ops->set_rx_csum) - return -EOPNOTSUPP; + struct ethtool_gstrings gstrings; + u8 *data; + int ret; - if (copy_from_user(&edata, useraddr, sizeof(edata))) + if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) return -EFAULT; - dev->ethtool_ops->set_rx_csum(dev, edata.data); - return 0; + ret = __ethtool_get_sset_count(dev, gstrings.string_set); + if (ret < 0) + return ret; + + gstrings.len = ret; + + data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + if (!data) + return -ENOMEM; + + __ethtool_get_strings(dev, gstrings.string_set, data); + + ret = -EFAULT; + if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) + goto out; + useraddr += sizeof(gstrings); + if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) + goto out; + ret = 0; + +out: + kfree(data); + return ret; } -static int ethtool_get_tx_csum(struct net_device *dev, char __user *useraddr) +static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GTXCSUM }; + struct ethtool_value id; + static bool busy; + const struct ethtool_ops *ops = dev->ethtool_ops; + int rc; - if (!dev->ethtool_ops->get_tx_csum) + if (!ops->set_phys_id) return -EOPNOTSUPP; - edata.data = dev->ethtool_ops->get_tx_csum(dev); + if (busy) + return -EBUSY; - if (copy_to_user(useraddr, &edata, sizeof(edata))) + if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - return 0; -} -static int __ethtool_set_sg(struct net_device *dev, u32 data) -{ - int err; + rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + if (rc < 0) + return rc; - if (!data && dev->ethtool_ops->set_tso) { - err = dev->ethtool_ops->set_tso(dev, 0); - if (err) - return err; + /* Drop the RTNL lock while waiting, but prevent reentry or + * removal of the device. + */ + busy = true; + dev_hold(dev); + rtnl_unlock(); + + if (rc == 0) { + /* Driver will handle this itself */ + schedule_timeout_interruptible( + id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); + } else { + /* Driver expects to be called at twice the frequency in rc */ + int n = rc * 2, i, interval = HZ / n; + + /* Count down seconds */ + do { + /* Count down iterations per second */ + i = n; + do { + rtnl_lock(); + rc = ops->set_phys_id(dev, + (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); + rtnl_unlock(); + if (rc) + break; + schedule_timeout_interruptible(interval); + } while (!signal_pending(current) && --i != 0); + } while (!signal_pending(current) && + (id.data == 0 || --id.data != 0)); } - if (!data && dev->ethtool_ops->set_ufo) { - err = dev->ethtool_ops->set_ufo(dev, 0); - if (err) - return err; - } - return dev->ethtool_ops->set_sg(dev, data); + rtnl_lock(); + dev_put(dev); + busy = false; + + (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + return rc; } -static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr) +static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) { - struct ethtool_value edata; - int err; + struct ethtool_stats stats; + const struct ethtool_ops *ops = dev->ethtool_ops; + u64 *data; + int ret, n_stats; - if (!dev->ethtool_ops->set_tx_csum) + if (!ops->get_ethtool_stats || !ops->get_sset_count) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) + n_stats = ops->get_sset_count(dev, ETH_SS_STATS); + if (n_stats < 0) + return n_stats; + WARN_ON(n_stats == 0); + + if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; - if (!edata.data && dev->ethtool_ops->set_sg) { - err = __ethtool_set_sg(dev, 0); - if (err) - return err; - } + stats.n_stats = n_stats; + data = kmalloc(n_stats * sizeof(u64), GFP_USER); + if (!data) + return -ENOMEM; + + ops->get_ethtool_stats(dev, &stats, data); + + ret = -EFAULT; + if (copy_to_user(useraddr, &stats, sizeof(stats))) + goto out; + useraddr += sizeof(stats); + if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64))) + goto out; + ret = 0; - return dev->ethtool_ops->set_tx_csum(dev, edata.data); + out: + kfree(data); + return ret; } -static int ethtool_get_sg(struct net_device *dev, char __user *useraddr) +static int ethtool_get_perm_addr(struct net_device *dev, void __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GSG }; + struct ethtool_perm_addr epaddr; - if (!dev->ethtool_ops->get_sg) - return -EOPNOTSUPP; + if (copy_from_user(&epaddr, useraddr, sizeof(epaddr))) + return -EFAULT; - edata.data = dev->ethtool_ops->get_sg(dev); + if (epaddr.size < dev->addr_len) + return -ETOOSMALL; + epaddr.size = dev->addr_len; - if (copy_to_user(useraddr, &edata, sizeof(edata))) + if (copy_to_user(useraddr, &epaddr, sizeof(epaddr))) + return -EFAULT; + useraddr += sizeof(epaddr); + if (copy_to_user(useraddr, dev->perm_addr, epaddr.size)) return -EFAULT; return 0; } -static int ethtool_set_sg(struct net_device *dev, char __user *useraddr) +static int ethtool_get_value(struct net_device *dev, char __user *useraddr, + u32 cmd, u32 (*actor)(struct net_device *)) { - struct ethtool_value edata; + struct ethtool_value edata = { .cmd = cmd }; - if (!dev->ethtool_ops->set_sg) + if (!actor) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (edata.data && - !(dev->features & (NETIF_F_IP_CSUM | - NETIF_F_NO_CSUM | - NETIF_F_HW_CSUM))) - return -EINVAL; + edata.data = actor(dev); - return __ethtool_set_sg(dev, edata.data); + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; } -static int ethtool_get_tso(struct net_device *dev, char __user *useraddr) +static int ethtool_set_value_void(struct net_device *dev, char __user *useraddr, + void (*actor)(struct net_device *, u32)) { - struct ethtool_value edata = { ETHTOOL_GTSO }; + struct ethtool_value edata; - if (!dev->ethtool_ops->get_tso) + if (!actor) return -EOPNOTSUPP; - edata.data = dev->ethtool_ops->get_tso(dev); - - if (copy_to_user(useraddr, &edata, sizeof(edata))) + if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; + + actor(dev, edata.data); return 0; } -static int ethtool_set_tso(struct net_device *dev, char __user *useraddr) +static int ethtool_set_value(struct net_device *dev, char __user *useraddr, + int (*actor)(struct net_device *, u32)) { struct ethtool_value edata; - if (!dev->ethtool_ops->set_tso) + if (!actor) return -EOPNOTSUPP; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; - if (edata.data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - - return dev->ethtool_ops->set_tso(dev, edata.data); + return actor(dev, edata.data); } -static int ethtool_get_ufo(struct net_device *dev, char __user *useraddr) +static noinline_for_stack int ethtool_flash_device(struct net_device *dev, + char __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GTSO }; + struct ethtool_flash efl; + + if (copy_from_user(&efl, useraddr, sizeof(efl))) + return -EFAULT; - if (!dev->ethtool_ops->get_ufo) + if (!dev->ethtool_ops->flash_device) return -EOPNOTSUPP; - edata.data = dev->ethtool_ops->get_ufo(dev); - if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; - return 0; + + efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; + + return dev->ethtool_ops->flash_device(dev, &efl); } -static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) + +static int ethtool_set_dump(struct net_device *dev, + void __user *useraddr) { - struct ethtool_value edata; + struct ethtool_dump dump; - if (!dev->ethtool_ops->set_ufo) + if (!dev->ethtool_ops->set_dump) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) + + if (copy_from_user(&dump, useraddr, sizeof(dump))) return -EFAULT; - if (edata.data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - if (edata.data && !(dev->features & NETIF_F_HW_CSUM)) - return -EINVAL; - return dev->ethtool_ops->set_ufo(dev, edata.data); + + return dev->ethtool_ops->set_dump(dev, &dump); } -static int ethtool_self_test(struct net_device *dev, char __user *useraddr) +static int ethtool_get_dump_flag(struct net_device *dev, + void __user *useraddr) { - struct ethtool_test test; - struct ethtool_ops *ops = dev->ethtool_ops; - u64 *data; int ret; + struct ethtool_dump dump; + const struct ethtool_ops *ops = dev->ethtool_ops; - if (!ops->self_test || !ops->self_test_count) + if (!ops->get_dump_flag) return -EOPNOTSUPP; - if (copy_from_user(&test, useraddr, sizeof(test))) + if (copy_from_user(&dump, useraddr, sizeof(dump))) return -EFAULT; - test.len = ops->self_test_count(dev); - data = kmalloc(test.len * sizeof(u64), GFP_USER); - if (!data) - return -ENOMEM; - - ops->self_test(dev, &test, data); - - ret = -EFAULT; - if (copy_to_user(useraddr, &test, sizeof(test))) - goto out; - useraddr += sizeof(test); - if (copy_to_user(useraddr, data, test.len * sizeof(u64))) - goto out; - ret = 0; + ret = ops->get_dump_flag(dev, &dump); + if (ret) + return ret; - out: - kfree(data); - return ret; + if (copy_to_user(useraddr, &dump, sizeof(dump))) + return -EFAULT; + return 0; } -static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) +static int ethtool_get_dump_data(struct net_device *dev, + void __user *useraddr) { - struct ethtool_gstrings gstrings; - struct ethtool_ops *ops = dev->ethtool_ops; - u8 *data; int ret; + __u32 len; + struct ethtool_dump dump, tmp; + const struct ethtool_ops *ops = dev->ethtool_ops; + void *data = NULL; - if (!ops->get_strings) + if (!ops->get_dump_data || !ops->get_dump_flag) return -EOPNOTSUPP; - if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) + if (copy_from_user(&dump, useraddr, sizeof(dump))) return -EFAULT; - switch (gstrings.string_set) { - case ETH_SS_TEST: - if (!ops->self_test_count) - return -EOPNOTSUPP; - gstrings.len = ops->self_test_count(dev); - break; - case ETH_SS_STATS: - if (!ops->get_stats_count) - return -EOPNOTSUPP; - gstrings.len = ops->get_stats_count(dev); - break; - default: - return -EINVAL; - } + memset(&tmp, 0, sizeof(tmp)); + tmp.cmd = ETHTOOL_GET_DUMP_FLAG; + ret = ops->get_dump_flag(dev, &tmp); + if (ret) + return ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + len = min(tmp.len, dump.len); + if (!len) + return -EFAULT; + + /* Don't ever let the driver think there's more space available + * than it requested with .get_dump_flag(). + */ + dump.len = len; + + /* Always allocate enough space to hold the whole thing so that the + * driver does not need to check the length and bother with partial + * dumping. + */ + data = vzalloc(tmp.len); if (!data) return -ENOMEM; + ret = ops->get_dump_data(dev, &dump, data); + if (ret) + goto out; - ops->get_strings(dev, gstrings.string_set, data); + /* There are two sane possibilities: + * 1. The driver's .get_dump_data() does not touch dump.len. + * 2. Or it may set dump.len to how much it really writes, which + * should be tmp.len (or len if it can do a partial dump). + * In any case respond to userspace with the actual length of data + * it's receiving. + */ + WARN_ON(dump.len != len && dump.len != tmp.len); + dump.len = len; - ret = -EFAULT; - if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) - goto out; - useraddr += sizeof(gstrings); - if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) + if (copy_to_user(useraddr, &dump, sizeof(dump))) { + ret = -EFAULT; goto out; - ret = 0; - - out: - kfree(data); + } + useraddr += offsetof(struct ethtool_dump, data); + if (copy_to_user(useraddr, data, len)) + ret = -EFAULT; +out: + vfree(data); return ret; } -static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) +static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) { - struct ethtool_value id; + int err = 0; + struct ethtool_ts_info info; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; - if (!dev->ethtool_ops->phys_id) - return -EOPNOTSUPP; + memset(&info, 0, sizeof(info)); + info.cmd = ETHTOOL_GET_TS_INFO; + + if (phydev && phydev->drv && phydev->drv->ts_info) { + err = phydev->drv->ts_info(phydev, &info); + } else if (ops->get_ts_info) { + err = ops->get_ts_info(dev, &info); + } else { + info.so_timestamping = + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info.phc_index = -1; + } - if (copy_from_user(&id, useraddr, sizeof(id))) - return -EFAULT; + if (err) + return err; + + if (copy_to_user(useraddr, &info, sizeof(info))) + err = -EFAULT; - return dev->ethtool_ops->phys_id(dev, id.data); + return err; } -static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) +static int ethtool_get_module_info(struct net_device *dev, + void __user *useraddr) { - struct ethtool_stats stats; - struct ethtool_ops *ops = dev->ethtool_ops; - u64 *data; int ret; + struct ethtool_modinfo modinfo; + const struct ethtool_ops *ops = dev->ethtool_ops; - if (!ops->get_ethtool_stats || !ops->get_stats_count) + if (!ops->get_module_info) return -EOPNOTSUPP; - if (copy_from_user(&stats, useraddr, sizeof(stats))) + if (copy_from_user(&modinfo, useraddr, sizeof(modinfo))) return -EFAULT; - stats.n_stats = ops->get_stats_count(dev); - data = kmalloc(stats.n_stats * sizeof(u64), GFP_USER); - if (!data) - return -ENOMEM; - - ops->get_ethtool_stats(dev, &stats, data); + ret = ops->get_module_info(dev, &modinfo); + if (ret) + return ret; - ret = -EFAULT; - if (copy_to_user(useraddr, &stats, sizeof(stats))) - goto out; - useraddr += sizeof(stats); - if (copy_to_user(useraddr, data, stats.n_stats * sizeof(u64))) - goto out; - ret = 0; + if (copy_to_user(useraddr, &modinfo, sizeof(modinfo))) + return -EFAULT; - out: - kfree(data); - return ret; + return 0; } -static int ethtool_get_perm_addr(struct net_device *dev, void __user *useraddr) +static int ethtool_get_module_eeprom(struct net_device *dev, + void __user *useraddr) { - struct ethtool_perm_addr epaddr; - u8 *data; int ret; + struct ethtool_modinfo modinfo; + const struct ethtool_ops *ops = dev->ethtool_ops; - if (!dev->ethtool_ops->get_perm_addr) + if (!ops->get_module_info || !ops->get_module_eeprom) return -EOPNOTSUPP; - if (copy_from_user(&epaddr,useraddr,sizeof(epaddr))) - return -EFAULT; - - data = kmalloc(epaddr.size, GFP_USER); - if (!data) - return -ENOMEM; - - ret = dev->ethtool_ops->get_perm_addr(dev,&epaddr,data); + ret = ops->get_module_info(dev, &modinfo); if (ret) return ret; - ret = -EFAULT; - if (copy_to_user(useraddr, &epaddr, sizeof(epaddr))) - goto out; - useraddr += sizeof(epaddr); - if (copy_to_user(useraddr, data, epaddr.size)) - goto out; - ret = 0; - - out: - kfree(data); - return ret; + return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom, + modinfo.eeprom_len); } -/* The main entry point in this file. Called from net/core/dev.c */ +/* The main entry point in this file. Called from net/core/dev_ioctl.c */ -int dev_ethtool(struct ifreq *ifr) +int dev_ethtool(struct net *net, struct ifreq *ifr) { - struct net_device *dev = __dev_get_by_name(ifr->ifr_name); + struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); void __user *useraddr = ifr->ifr_data; u32 ethcmd; int rc; - unsigned long old_features; - - /* - * XXX: This can be pushed down into the ethtool_* handlers that - * need it. Keep existing behaviour for the moment. - */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; + netdev_features_t old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; - if (!dev->ethtool_ops) - goto ioctl; - - if (copy_from_user(ðcmd, useraddr, sizeof (ethcmd))) + if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; - if(dev->ethtool_ops->begin) - if ((rc = dev->ethtool_ops->begin(dev)) < 0) - return rc; + /* Allow some commands to be done by anyone */ + switch (ethcmd) { + case ETHTOOL_GSET: + case ETHTOOL_GDRVINFO: + case ETHTOOL_GMSGLVL: + case ETHTOOL_GLINK: + case ETHTOOL_GCOALESCE: + case ETHTOOL_GRINGPARAM: + case ETHTOOL_GPAUSEPARAM: + case ETHTOOL_GRXCSUM: + case ETHTOOL_GTXCSUM: + case ETHTOOL_GSG: + case ETHTOOL_GSSET_INFO: + case ETHTOOL_GSTRINGS: + case ETHTOOL_GSTATS: + case ETHTOOL_GTSO: + case ETHTOOL_GPERMADDR: + case ETHTOOL_GUFO: + case ETHTOOL_GGSO: + case ETHTOOL_GGRO: + case ETHTOOL_GFLAGS: + case ETHTOOL_GPFLAGS: + case ETHTOOL_GRXFH: + case ETHTOOL_GRXRINGS: + case ETHTOOL_GRXCLSRLCNT: + case ETHTOOL_GRXCLSRULE: + case ETHTOOL_GRXCLSRLALL: + case ETHTOOL_GRXFHINDIR: + case ETHTOOL_GRSSH: + case ETHTOOL_GFEATURES: + case ETHTOOL_GCHANNELS: + case ETHTOOL_GET_TS_INFO: + case ETHTOOL_GEEE: + break; + default: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + } + if (dev->ethtool_ops->begin) { + rc = dev->ethtool_ops->begin(dev); + if (rc < 0) + return rc; + } old_features = dev->features; switch (ethcmd) { @@ -826,10 +1703,18 @@ int dev_ethtool(struct ifreq *ifr) rc = ethtool_set_wol(dev, useraddr); break; case ETHTOOL_GMSGLVL: - rc = ethtool_get_msglevel(dev, useraddr); + rc = ethtool_get_value(dev, useraddr, ethcmd, + dev->ethtool_ops->get_msglevel); break; case ETHTOOL_SMSGLVL: - rc = ethtool_set_msglevel(dev, useraddr); + rc = ethtool_set_value_void(dev, useraddr, + dev->ethtool_ops->set_msglevel); + break; + case ETHTOOL_GEEE: + rc = ethtool_get_eee(dev, useraddr); + break; + case ETHTOOL_SEEE: + rc = ethtool_set_eee(dev, useraddr); break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); @@ -861,30 +1746,6 @@ int dev_ethtool(struct ifreq *ifr) case ETHTOOL_SPAUSEPARAM: rc = ethtool_set_pauseparam(dev, useraddr); break; - case ETHTOOL_GRXCSUM: - rc = ethtool_get_rx_csum(dev, useraddr); - break; - case ETHTOOL_SRXCSUM: - rc = ethtool_set_rx_csum(dev, useraddr); - break; - case ETHTOOL_GTXCSUM: - rc = ethtool_get_tx_csum(dev, useraddr); - break; - case ETHTOOL_STXCSUM: - rc = ethtool_set_tx_csum(dev, useraddr); - break; - case ETHTOOL_GSG: - rc = ethtool_get_sg(dev, useraddr); - break; - case ETHTOOL_SSG: - rc = ethtool_set_sg(dev, useraddr); - break; - case ETHTOOL_GTSO: - rc = ethtool_get_tso(dev, useraddr); - break; - case ETHTOOL_STSO: - rc = ethtool_set_tso(dev, useraddr); - break; case ETHTOOL_TEST: rc = ethtool_self_test(dev, useraddr); break; @@ -900,39 +1761,111 @@ int dev_ethtool(struct ifreq *ifr) case ETHTOOL_GPERMADDR: rc = ethtool_get_perm_addr(dev, useraddr); break; + case ETHTOOL_GFLAGS: + rc = ethtool_get_value(dev, useraddr, ethcmd, + __ethtool_get_flags); + break; + case ETHTOOL_SFLAGS: + rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags); + break; + case ETHTOOL_GPFLAGS: + rc = ethtool_get_value(dev, useraddr, ethcmd, + dev->ethtool_ops->get_priv_flags); + break; + case ETHTOOL_SPFLAGS: + rc = ethtool_set_value(dev, useraddr, + dev->ethtool_ops->set_priv_flags); + break; + case ETHTOOL_GRXFH: + case ETHTOOL_GRXRINGS: + case ETHTOOL_GRXCLSRLCNT: + case ETHTOOL_GRXCLSRULE: + case ETHTOOL_GRXCLSRLALL: + rc = ethtool_get_rxnfc(dev, ethcmd, useraddr); + break; + case ETHTOOL_SRXFH: + case ETHTOOL_SRXCLSRLDEL: + case ETHTOOL_SRXCLSRLINS: + rc = ethtool_set_rxnfc(dev, ethcmd, useraddr); + break; + case ETHTOOL_FLASHDEV: + rc = ethtool_flash_device(dev, useraddr); + break; + case ETHTOOL_RESET: + rc = ethtool_reset(dev, useraddr); + break; + case ETHTOOL_GSSET_INFO: + rc = ethtool_get_sset_info(dev, useraddr); + break; + case ETHTOOL_GRXFHINDIR: + rc = ethtool_get_rxfh_indir(dev, useraddr); + break; + case ETHTOOL_SRXFHINDIR: + rc = ethtool_set_rxfh_indir(dev, useraddr); + break; + case ETHTOOL_GRSSH: + rc = ethtool_get_rxfh(dev, useraddr); + break; + case ETHTOOL_SRSSH: + rc = ethtool_set_rxfh(dev, useraddr); + break; + case ETHTOOL_GFEATURES: + rc = ethtool_get_features(dev, useraddr); + break; + case ETHTOOL_SFEATURES: + rc = ethtool_set_features(dev, useraddr); + break; + case ETHTOOL_GTXCSUM: + case ETHTOOL_GRXCSUM: + case ETHTOOL_GSG: + case ETHTOOL_GTSO: case ETHTOOL_GUFO: - rc = ethtool_get_ufo(dev, useraddr); + case ETHTOOL_GGSO: + case ETHTOOL_GGRO: + rc = ethtool_get_one_feature(dev, useraddr, ethcmd); break; + case ETHTOOL_STXCSUM: + case ETHTOOL_SRXCSUM: + case ETHTOOL_SSG: + case ETHTOOL_STSO: case ETHTOOL_SUFO: - rc = ethtool_set_ufo(dev, useraddr); + case ETHTOOL_SGSO: + case ETHTOOL_SGRO: + rc = ethtool_set_one_feature(dev, useraddr, ethcmd); + break; + case ETHTOOL_GCHANNELS: + rc = ethtool_get_channels(dev, useraddr); + break; + case ETHTOOL_SCHANNELS: + rc = ethtool_set_channels(dev, useraddr); + break; + case ETHTOOL_SET_DUMP: + rc = ethtool_set_dump(dev, useraddr); + break; + case ETHTOOL_GET_DUMP_FLAG: + rc = ethtool_get_dump_flag(dev, useraddr); + break; + case ETHTOOL_GET_DUMP_DATA: + rc = ethtool_get_dump_data(dev, useraddr); + break; + case ETHTOOL_GET_TS_INFO: + rc = ethtool_get_ts_info(dev, useraddr); + break; + case ETHTOOL_GMODULEINFO: + rc = ethtool_get_module_info(dev, useraddr); + break; + case ETHTOOL_GMODULEEEPROM: + rc = ethtool_get_module_eeprom(dev, useraddr); break; default: - rc = -EOPNOTSUPP; + rc = -EOPNOTSUPP; } - - if(dev->ethtool_ops->complete) + + if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (old_features != dev->features) netdev_features_change(dev); return rc; - - ioctl: - if (dev->do_ioctl) - return dev->do_ioctl(dev, ifr, SIOCETHTOOL); - return -EOPNOTSUPP; } - -EXPORT_SYMBOL(dev_ethtool); -EXPORT_SYMBOL(ethtool_op_get_link); -EXPORT_SYMBOL_GPL(ethtool_op_get_perm_addr); -EXPORT_SYMBOL(ethtool_op_get_sg); -EXPORT_SYMBOL(ethtool_op_get_tso); -EXPORT_SYMBOL(ethtool_op_get_tx_csum); -EXPORT_SYMBOL(ethtool_op_set_sg); -EXPORT_SYMBOL(ethtool_op_set_tso); -EXPORT_SYMBOL(ethtool_op_set_tx_csum); -EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); -EXPORT_SYMBOL(ethtool_op_set_ufo); -EXPORT_SYMBOL(ethtool_op_get_ufo); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c new file mode 100644 index 00000000000..185c341fafb --- /dev/null +++ b/net/core/fib_rules.c @@ -0,0 +1,805 @@ +/* + * net/core/fib_rules.c Generic Routing Rules + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/module.h> +#include <net/net_namespace.h> +#include <net/sock.h> +#include <net/fib_rules.h> + +int fib_default_rule_add(struct fib_rules_ops *ops, + u32 pref, u32 table, u32 flags) +{ + struct fib_rule *r; + + r = kzalloc(ops->rule_size, GFP_KERNEL); + if (r == NULL) + return -ENOMEM; + + atomic_set(&r->refcnt, 1); + r->action = FR_ACT_TO_TBL; + r->pref = pref; + r->table = table; + r->flags = flags; + r->fr_net = hold_net(ops->fro_net); + + r->suppress_prefixlen = -1; + r->suppress_ifgroup = -1; + + /* The lock is not required here, the list in unreacheable + * at the moment this function is called */ + list_add_tail(&r->list, &ops->rules_list); + return 0; +} +EXPORT_SYMBOL(fib_default_rule_add); + +u32 fib_default_rule_pref(struct fib_rules_ops *ops) +{ + struct list_head *pos; + struct fib_rule *rule; + + if (!list_empty(&ops->rules_list)) { + pos = ops->rules_list.next; + if (pos->next != &ops->rules_list) { + rule = list_entry(pos->next, struct fib_rule, list); + if (rule->pref) + return rule->pref - 1; + } + } + + return 0; +} +EXPORT_SYMBOL(fib_default_rule_pref); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid); + +static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family) +{ + struct fib_rules_ops *ops; + + rcu_read_lock(); + list_for_each_entry_rcu(ops, &net->rules_ops, list) { + if (ops->family == family) { + if (!try_module_get(ops->owner)) + ops = NULL; + rcu_read_unlock(); + return ops; + } + } + rcu_read_unlock(); + + return NULL; +} + +static void rules_ops_put(struct fib_rules_ops *ops) +{ + if (ops) + module_put(ops->owner); +} + +static void flush_route_cache(struct fib_rules_ops *ops) +{ + if (ops->flush_cache) + ops->flush_cache(ops); +} + +static int __fib_rules_register(struct fib_rules_ops *ops) +{ + int err = -EEXIST; + struct fib_rules_ops *o; + struct net *net; + + net = ops->fro_net; + + if (ops->rule_size < sizeof(struct fib_rule)) + return -EINVAL; + + if (ops->match == NULL || ops->configure == NULL || + ops->compare == NULL || ops->fill == NULL || + ops->action == NULL) + return -EINVAL; + + spin_lock(&net->rules_mod_lock); + list_for_each_entry(o, &net->rules_ops, list) + if (ops->family == o->family) + goto errout; + + hold_net(net); + list_add_tail_rcu(&ops->list, &net->rules_ops); + err = 0; +errout: + spin_unlock(&net->rules_mod_lock); + + return err; +} + +struct fib_rules_ops * +fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) +{ + struct fib_rules_ops *ops; + int err; + + ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&ops->rules_list); + ops->fro_net = net; + + err = __fib_rules_register(ops); + if (err) { + kfree(ops); + ops = ERR_PTR(err); + } + + return ops; +} +EXPORT_SYMBOL_GPL(fib_rules_register); + +static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) +{ + struct fib_rule *rule, *tmp; + + list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { + list_del_rcu(&rule->list); + if (ops->delete) + ops->delete(rule); + fib_rule_put(rule); + } +} + +static void fib_rules_put_rcu(struct rcu_head *head) +{ + struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); + struct net *net = ops->fro_net; + + release_net(net); + kfree(ops); +} + +void fib_rules_unregister(struct fib_rules_ops *ops) +{ + struct net *net = ops->fro_net; + + spin_lock(&net->rules_mod_lock); + list_del_rcu(&ops->list); + fib_rules_cleanup_ops(ops); + spin_unlock(&net->rules_mod_lock); + + call_rcu(&ops->rcu, fib_rules_put_rcu); +} +EXPORT_SYMBOL_GPL(fib_rules_unregister); + +static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, + struct flowi *fl, int flags) +{ + int ret = 0; + + if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) + goto out; + + if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) + goto out; + + if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) + goto out; + + ret = ops->match(rule, fl, flags); +out: + return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; +} + +int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, + int flags, struct fib_lookup_arg *arg) +{ + struct fib_rule *rule; + int err; + + rcu_read_lock(); + + list_for_each_entry_rcu(rule, &ops->rules_list, list) { +jumped: + if (!fib_rule_match(rule, ops, fl, flags)) + continue; + + if (rule->action == FR_ACT_GOTO) { + struct fib_rule *target; + + target = rcu_dereference(rule->ctarget); + if (target == NULL) { + continue; + } else { + rule = target; + goto jumped; + } + } else if (rule->action == FR_ACT_NOP) + continue; + else + err = ops->action(rule, fl, flags, arg); + + if (!err && ops->suppress && ops->suppress(rule, arg)) + continue; + + if (err != -EAGAIN) { + if ((arg->flags & FIB_LOOKUP_NOREF) || + likely(atomic_inc_not_zero(&rule->refcnt))) { + arg->rule = rule; + goto out; + } + break; + } + } + + err = -ESRCH; +out: + rcu_read_unlock(); + + return err; +} +EXPORT_SYMBOL_GPL(fib_rules_lookup); + +static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb, + struct fib_rules_ops *ops) +{ + int err = -EINVAL; + + if (frh->src_len) + if (tb[FRA_SRC] == NULL || + frh->src_len > (ops->addr_size * 8) || + nla_len(tb[FRA_SRC]) != ops->addr_size) + goto errout; + + if (frh->dst_len) + if (tb[FRA_DST] == NULL || + frh->dst_len > (ops->addr_size * 8) || + nla_len(tb[FRA_DST]) != ops->addr_size) + goto errout; + + err = 0; +errout: + return err; +} + +static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) +{ + struct net *net = sock_net(skb->sk); + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule, *r, *last = NULL; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL, unresolved = 0; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(net, frh->family); + if (ops == NULL) { + err = -EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + err = validate_rulemsg(frh, tb, ops); + if (err < 0) + goto errout; + + rule = kzalloc(ops->rule_size, GFP_KERNEL); + if (rule == NULL) { + err = -ENOMEM; + goto errout; + } + rule->fr_net = hold_net(net); + + if (tb[FRA_PRIORITY]) + rule->pref = nla_get_u32(tb[FRA_PRIORITY]); + + if (tb[FRA_IIFNAME]) { + struct net_device *dev; + + rule->iifindex = -1; + nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->iifname); + if (dev) + rule->iifindex = dev->ifindex; + } + + if (tb[FRA_OIFNAME]) { + struct net_device *dev; + + rule->oifindex = -1; + nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->oifname); + if (dev) + rule->oifindex = dev->ifindex; + } + + if (tb[FRA_FWMARK]) { + rule->mark = nla_get_u32(tb[FRA_FWMARK]); + if (rule->mark) + /* compatibility: if the mark value is non-zero all bits + * are compared unless a mask is explicitly specified. + */ + rule->mark_mask = 0xFFFFFFFF; + } + + if (tb[FRA_FWMASK]) + rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); + + rule->action = frh->action; + rule->flags = frh->flags; + rule->table = frh_get_table(frh, tb); + if (tb[FRA_SUPPRESS_PREFIXLEN]) + rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); + else + rule->suppress_prefixlen = -1; + + if (tb[FRA_SUPPRESS_IFGROUP]) + rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); + else + rule->suppress_ifgroup = -1; + + if (!tb[FRA_PRIORITY] && ops->default_pref) + rule->pref = ops->default_pref(ops); + + err = -EINVAL; + if (tb[FRA_GOTO]) { + if (rule->action != FR_ACT_GOTO) + goto errout_free; + + rule->target = nla_get_u32(tb[FRA_GOTO]); + /* Backward jumps are prohibited to avoid endless loops */ + if (rule->target <= rule->pref) + goto errout_free; + + list_for_each_entry(r, &ops->rules_list, list) { + if (r->pref == rule->target) { + RCU_INIT_POINTER(rule->ctarget, r); + break; + } + } + + if (rcu_dereference_protected(rule->ctarget, 1) == NULL) + unresolved = 1; + } else if (rule->action == FR_ACT_GOTO) + goto errout_free; + + err = ops->configure(rule, skb, frh, tb); + if (err < 0) + goto errout_free; + + list_for_each_entry(r, &ops->rules_list, list) { + if (r->pref > rule->pref) + break; + last = r; + } + + fib_rule_get(rule); + + if (last) + list_add_rcu(&rule->list, &last->list); + else + list_add_rcu(&rule->list, &ops->rules_list); + + if (ops->unresolved_rules) { + /* + * There are unresolved goto rules in the list, check if + * any of them are pointing to this new rule. + */ + list_for_each_entry(r, &ops->rules_list, list) { + if (r->action == FR_ACT_GOTO && + r->target == rule->pref && + rtnl_dereference(r->ctarget) == NULL) { + rcu_assign_pointer(r->ctarget, rule); + if (--ops->unresolved_rules == 0) + break; + } + } + } + + if (rule->action == FR_ACT_GOTO) + ops->nr_goto_rules++; + + if (unresolved) + ops->unresolved_rules++; + + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); + flush_route_cache(ops); + rules_ops_put(ops); + return 0; + +errout_free: + release_net(rule->fr_net); + kfree(rule); +errout: + rules_ops_put(ops); + return err; +} + +static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) +{ + struct net *net = sock_net(skb->sk); + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule, *tmp; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(net, frh->family); + if (ops == NULL) { + err = -EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + err = validate_rulemsg(frh, tb, ops); + if (err < 0) + goto errout; + + list_for_each_entry(rule, &ops->rules_list, list) { + if (frh->action && (frh->action != rule->action)) + continue; + + if (frh_get_table(frh, tb) && + (frh_get_table(frh, tb) != rule->table)) + continue; + + if (tb[FRA_PRIORITY] && + (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) + continue; + + if (tb[FRA_IIFNAME] && + nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) + continue; + + if (tb[FRA_OIFNAME] && + nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) + continue; + + if (tb[FRA_FWMARK] && + (rule->mark != nla_get_u32(tb[FRA_FWMARK]))) + continue; + + if (tb[FRA_FWMASK] && + (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK]))) + continue; + + if (!ops->compare(rule, frh, tb)) + continue; + + if (rule->flags & FIB_RULE_PERMANENT) { + err = -EPERM; + goto errout; + } + + list_del_rcu(&rule->list); + + if (rule->action == FR_ACT_GOTO) { + ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } + + /* + * Check if this rule is a target to any of them. If so, + * disable them. As this operation is eventually very + * expensive, it is only performed if goto rules have + * actually been added. + */ + if (ops->nr_goto_rules > 0) { + list_for_each_entry(tmp, &ops->rules_list, list) { + if (rtnl_dereference(tmp->ctarget) == rule) { + RCU_INIT_POINTER(tmp->ctarget, NULL); + ops->unresolved_rules++; + } + } + } + + notify_rule_change(RTM_DELRULE, rule, ops, nlh, + NETLINK_CB(skb).portid); + if (ops->delete) + ops->delete(rule); + fib_rule_put(rule); + flush_route_cache(ops); + rules_ops_put(ops); + return 0; + } + + err = -ENOENT; +errout: + rules_ops_put(ops); + return err; +} + +static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + struct fib_rule *rule) +{ + size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) + + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + + nla_total_size(4) /* FRA_PRIORITY */ + + nla_total_size(4) /* FRA_TABLE */ + + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + + nla_total_size(4) /* FRA_FWMARK */ + + nla_total_size(4); /* FRA_FWMASK */ + + if (ops->nlmsg_payload) + payload += ops->nlmsg_payload(rule); + + return payload; +} + +static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, + u32 pid, u32 seq, int type, int flags, + struct fib_rules_ops *ops) +{ + struct nlmsghdr *nlh; + struct fib_rule_hdr *frh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); + if (nlh == NULL) + return -EMSGSIZE; + + frh = nlmsg_data(nlh); + frh->family = ops->family; + frh->table = rule->table; + if (nla_put_u32(skb, FRA_TABLE, rule->table)) + goto nla_put_failure; + if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) + goto nla_put_failure; + frh->res1 = 0; + frh->res2 = 0; + frh->action = rule->action; + frh->flags = rule->flags; + + if (rule->action == FR_ACT_GOTO && + rcu_access_pointer(rule->ctarget) == NULL) + frh->flags |= FIB_RULE_UNRESOLVED; + + if (rule->iifname[0]) { + if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) + goto nla_put_failure; + if (rule->iifindex == -1) + frh->flags |= FIB_RULE_IIF_DETACHED; + } + + if (rule->oifname[0]) { + if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) + goto nla_put_failure; + if (rule->oifindex == -1) + frh->flags |= FIB_RULE_OIF_DETACHED; + } + + if ((rule->pref && + nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || + (rule->mark && + nla_put_u32(skb, FRA_FWMARK, rule->mark)) || + ((rule->mark_mask || rule->mark) && + nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || + (rule->target && + nla_put_u32(skb, FRA_GOTO, rule->target))) + goto nla_put_failure; + + if (rule->suppress_ifgroup != -1) { + if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) + goto nla_put_failure; + } + + if (ops->fill(rule, skb, frh) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, + struct fib_rules_ops *ops) +{ + int idx = 0; + struct fib_rule *rule; + + rcu_read_lock(); + list_for_each_entry_rcu(rule, &ops->rules_list, list) { + if (idx < cb->args[1]) + goto skip; + + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops) < 0) + break; +skip: + idx++; + } + rcu_read_unlock(); + cb->args[1] = idx; + rules_ops_put(ops); + + return skb->len; +} + +static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct fib_rules_ops *ops; + int idx = 0, family; + + family = rtnl_msg_family(cb->nlh); + if (family != AF_UNSPEC) { + /* Protocol specific dump request */ + ops = lookup_rules_ops(net, family); + if (ops == NULL) + return -EAFNOSUPPORT; + + return dump_rules(skb, cb, ops); + } + + rcu_read_lock(); + list_for_each_entry_rcu(ops, &net->rules_ops, list) { + if (idx < cb->args[0] || !try_module_get(ops->owner)) + goto skip; + + if (dump_rules(skb, cb, ops) < 0) + break; + + cb->args[1] = 0; +skip: + idx++; + } + rcu_read_unlock(); + cb->args[0] = idx; + + return skb->len; +} + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid) +{ + struct net *net; + struct sk_buff *skb; + int err = -ENOBUFS; + + net = ops->fro_net; + skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); + if (skb == NULL) + goto errout; + + err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); + if (err < 0) { + /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, ops->nlgroup, err); +} + +static void attach_rules(struct list_head *rules, struct net_device *dev) +{ + struct fib_rule *rule; + + list_for_each_entry(rule, rules, list) { + if (rule->iifindex == -1 && + strcmp(dev->name, rule->iifname) == 0) + rule->iifindex = dev->ifindex; + if (rule->oifindex == -1 && + strcmp(dev->name, rule->oifname) == 0) + rule->oifindex = dev->ifindex; + } +} + +static void detach_rules(struct list_head *rules, struct net_device *dev) +{ + struct fib_rule *rule; + + list_for_each_entry(rule, rules, list) { + if (rule->iifindex == dev->ifindex) + rule->iifindex = -1; + if (rule->oifindex == dev->ifindex) + rule->oifindex = -1; + } +} + + +static int fib_rules_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + struct fib_rules_ops *ops; + + ASSERT_RTNL(); + + switch (event) { + case NETDEV_REGISTER: + list_for_each_entry(ops, &net->rules_ops, list) + attach_rules(&ops->rules_list, dev); + break; + + case NETDEV_CHANGENAME: + list_for_each_entry(ops, &net->rules_ops, list) { + detach_rules(&ops->rules_list, dev); + attach_rules(&ops->rules_list, dev); + } + break; + + case NETDEV_UNREGISTER: + list_for_each_entry(ops, &net->rules_ops, list) + detach_rules(&ops->rules_list, dev); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block fib_rules_notifier = { + .notifier_call = fib_rules_event, +}; + +static int __net_init fib_rules_net_init(struct net *net) +{ + INIT_LIST_HEAD(&net->rules_ops); + spin_lock_init(&net->rules_mod_lock); + return 0; +} + +static struct pernet_operations fib_rules_net_ops = { + .init = fib_rules_net_init, +}; + +static int __init fib_rules_init(void) +{ + int err; + rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL); + + err = register_pernet_subsys(&fib_rules_net_ops); + if (err < 0) + goto fail; + + err = register_netdevice_notifier(&fib_rules_notifier); + if (err < 0) + goto fail_unregister; + + return 0; + +fail_unregister: + unregister_pernet_subsys(&fib_rules_net_ops); +fail: + rtnl_unregister(PF_UNSPEC, RTM_NEWRULE); + rtnl_unregister(PF_UNSPEC, RTM_DELRULE); + rtnl_unregister(PF_UNSPEC, RTM_GETRULE); + return err; +} + +subsys_initcall(fib_rules_init); diff --git a/net/core/filter.c b/net/core/filter.c index 9540946a48f..1dbf6462f76 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 @@ -18,7 +23,6 @@ #include <linux/module.h> #include <linux/types.h> -#include <linux/sched.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> @@ -26,254 +30,1187 @@ #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> +#include <linux/gfp.h> #include <net/ip.h> #include <net/protocol.h> +#include <net/netlink.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> -#include <asm/system.h> #include <asm/uaccess.h> +#include <asm/unaligned.h> #include <linux/filter.h> +#include <linux/ratelimit.h> +#include <linux/seccomp.h> +#include <linux/if_vlan.h> + +/* Registers */ +#define BPF_R0 regs[BPF_REG_0] +#define BPF_R1 regs[BPF_REG_1] +#define BPF_R2 regs[BPF_REG_2] +#define BPF_R3 regs[BPF_REG_3] +#define BPF_R4 regs[BPF_REG_4] +#define BPF_R5 regs[BPF_REG_5] +#define BPF_R6 regs[BPF_REG_6] +#define BPF_R7 regs[BPF_REG_7] +#define BPF_R8 regs[BPF_REG_8] +#define BPF_R9 regs[BPF_REG_9] +#define BPF_R10 regs[BPF_REG_10] + +/* Named registers */ +#define DST regs[insn->dst_reg] +#define SRC regs[insn->src_reg] +#define FP regs[BPF_REG_FP] +#define ARG1 regs[BPF_REG_ARG1] +#define CTX regs[BPF_REG_CTX] +#define IMM insn->imm -/* No hurry in this branch */ -static void *__load_pointer(struct sk_buff *skb, int k) +/* No hurry in this branch + * + * Exported for the bpf jit load helper. + */ +void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; if (k >= SKF_NET_OFF) - ptr = skb->nh.raw + k - SKF_NET_OFF; + ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) - ptr = skb->mac.raw + k - SKF_LL_OFF; - - if (ptr >= skb->head && ptr < skb->tail) + ptr = skb_mac_header(skb) + k - SKF_LL_OFF; + if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; + return NULL; } -static inline void *load_pointer(struct sk_buff *skb, int k, - unsigned int size, void *buffer) +static inline void *load_pointer(const struct sk_buff *skb, int k, + unsigned int size, void *buffer) { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); - else { - if (k >= SKF_AD_OFF) - return NULL; - return __load_pointer(skb, k); - } + + return bpf_internal_load_pointer_neg_helper(skb, k, size); } /** - * sk_run_filter - run a filter on a socket - * @skb: buffer to run the filter on - * @filter: filter to apply - * @flen: length of filter + * sk_filter - run a packet through a socket filter + * @sk: sock associated with &sk_buff + * @skb: buffer to filter + * + * Run the filter code and then cut skb->data to correct size returned by + * sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller + * than pkt_len we keep whole skb->data. This is the socket level + * wrapper to sk_run_filter. It returns 0 if the packet should + * be accepted or -EPERM if the packet should be tossed. * - * 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, and - * len is the number of filter blocks in the array. */ -unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) +int sk_filter(struct sock *sk, struct sk_buff *skb) { - struct sock_filter *fentry; /* We walk down these */ - void *ptr; - u32 A = 0; /* Accumulator */ - u32 X = 0; /* Index Register */ - u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ - u32 tmp; - int k; - int pc; + int err; + struct sk_filter *filter; /* - * Process array of filter instructions. + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory */ - for (pc = 0; pc < flen; pc++) { - fentry = &filter[pc]; - - switch (fentry->code) { - case BPF_ALU|BPF_ADD|BPF_X: - A += X; - continue; - case BPF_ALU|BPF_ADD|BPF_K: - A += fentry->k; - continue; - case BPF_ALU|BPF_SUB|BPF_X: - A -= X; - continue; - case BPF_ALU|BPF_SUB|BPF_K: - A -= fentry->k; - continue; - case BPF_ALU|BPF_MUL|BPF_X: - A *= X; - continue; - case BPF_ALU|BPF_MUL|BPF_K: - A *= fentry->k; - continue; - case BPF_ALU|BPF_DIV|BPF_X: - if (X == 0) - return 0; - A /= X; - continue; - case BPF_ALU|BPF_DIV|BPF_K: - A /= fentry->k; - continue; - case BPF_ALU|BPF_AND|BPF_X: - A &= X; - continue; - case BPF_ALU|BPF_AND|BPF_K: - A &= fentry->k; - continue; - case BPF_ALU|BPF_OR|BPF_X: - A |= X; - continue; - case BPF_ALU|BPF_OR|BPF_K: - A |= fentry->k; - continue; - case BPF_ALU|BPF_LSH|BPF_X: - A <<= X; - continue; - case BPF_ALU|BPF_LSH|BPF_K: - A <<= fentry->k; - continue; - case BPF_ALU|BPF_RSH|BPF_X: - A >>= X; - continue; - case BPF_ALU|BPF_RSH|BPF_K: - A >>= fentry->k; - continue; - case BPF_ALU|BPF_NEG: - A = -A; - continue; - case BPF_JMP|BPF_JA: - pc += fentry->k; - continue; - case BPF_JMP|BPF_JGT|BPF_K: - pc += (A > fentry->k) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JGE|BPF_K: - pc += (A >= fentry->k) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JEQ|BPF_K: - pc += (A == fentry->k) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JSET|BPF_K: - pc += (A & fentry->k) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JGT|BPF_X: - pc += (A > X) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JGE|BPF_X: - pc += (A >= X) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JEQ|BPF_X: - pc += (A == X) ? fentry->jt : fentry->jf; - continue; - case BPF_JMP|BPF_JSET|BPF_X: - pc += (A & X) ? fentry->jt : fentry->jf; - continue; - case BPF_LD|BPF_W|BPF_ABS: - k = fentry->k; -load_w: - ptr = load_pointer(skb, k, 4, &tmp); - if (ptr != NULL) { - A = ntohl(*(u32 *)ptr); - continue; - } + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + + err = security_sock_rcv_skb(sk, skb); + if (err) + return err; + + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (filter) { + unsigned int pkt_len = SK_RUN_FILTER(filter, skb); + + err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; + } + rcu_read_unlock(); + + return err; +} +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 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. @ctx is the data we are operating on, @insn is the + * array of filter instructions. + */ +static 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; + static const void *jumptable[256] = { + [0 ... 255] = &&default_label, + /* Now overwrite non-defaults ... */ + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, + [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, + [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, + [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, + [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, + [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, + [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, + [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, + [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, + [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, + [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, + [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, + [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, + [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, + [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, + [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, + [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, + [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, + [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, + [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, + [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, + [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, + [BPF_ALU | BPF_NEG] = &&ALU_NEG, + [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, + [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, + /* 64 bit ALU operations */ + [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, + [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, + [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, + [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, + [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, + [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, + [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, + [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, + [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, + [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, + [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, + [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, + [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, + [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, + [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, + [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, + [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, + [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, + [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, + [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, + [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, + [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, + [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, + [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, + [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, + /* Call instruction */ + [BPF_JMP | BPF_CALL] = &&JMP_CALL, + /* Jumps */ + [BPF_JMP | BPF_JA] = &&JMP_JA, + [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, + [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, + [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, + [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, + [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, + [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, + [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, + [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, + [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, + [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, + /* Program return */ + [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, + /* Store instructions */ + [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, + [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, + [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, + [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, + [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, + [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, + [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, + [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, + [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, + [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, + /* Load instructions */ + [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, + [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, + [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, + [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, + [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, + [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, + [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, + [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, + [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, + [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, + }; + void *ptr; + int off; + +#define CONT ({ insn++; goto select_insn; }) +#define CONT_JMP ({ insn++; goto select_insn; }) + + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + ARG1 = (u64) (unsigned long) ctx; + + /* Registers used in classic BPF programs need to be reset first. */ + regs[BPF_REG_A] = 0; + regs[BPF_REG_X] = 0; + +select_insn: + goto *jumptable[insn->code]; + + /* ALU */ +#define ALU(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP SRC; \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP (u32) SRC; \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ + CONT; + + ALU(ADD, +) + ALU(SUB, -) + ALU(AND, &) + ALU(OR, |) + ALU(LSH, <<) + ALU(RSH, >>) + ALU(XOR, ^) + ALU(MUL, *) +#undef ALU + ALU_NEG: + DST = (u32) -DST; + CONT; + ALU64_NEG: + DST = -DST; + CONT; + ALU_MOV_X: + DST = (u32) SRC; + CONT; + ALU_MOV_K: + DST = (u32) IMM; + CONT; + ALU64_MOV_X: + DST = SRC; + CONT; + ALU64_MOV_K: + DST = IMM; + CONT; + ALU64_ARSH_X: + (*(s64 *) &DST) >>= SRC; + CONT; + ALU64_ARSH_K: + (*(s64 *) &DST) >>= IMM; + CONT; + ALU64_MOD_X: + if (unlikely(SRC == 0)) + return 0; + tmp = DST; + DST = do_div(tmp, SRC); + CONT; + ALU_MOD_X: + if (unlikely(SRC == 0)) + return 0; + tmp = (u32) DST; + DST = do_div(tmp, (u32) SRC); + CONT; + ALU64_MOD_K: + tmp = DST; + DST = do_div(tmp, IMM); + CONT; + ALU_MOD_K: + tmp = (u32) DST; + DST = do_div(tmp, (u32) IMM); + CONT; + ALU64_DIV_X: + if (unlikely(SRC == 0)) + return 0; + do_div(DST, SRC); + CONT; + ALU_DIV_X: + if (unlikely(SRC == 0)) + return 0; + tmp = (u32) DST; + do_div(tmp, (u32) SRC); + DST = (u32) tmp; + CONT; + ALU64_DIV_K: + do_div(DST, IMM); + CONT; + ALU_DIV_K: + tmp = (u32) DST; + do_div(tmp, (u32) IMM); + DST = (u32) tmp; + CONT; + ALU_END_TO_BE: + switch (IMM) { + case 16: + DST = (__force u16) cpu_to_be16(DST); break; - case BPF_LD|BPF_H|BPF_ABS: - k = fentry->k; -load_h: - ptr = load_pointer(skb, k, 2, &tmp); - if (ptr != NULL) { - A = ntohs(*(u16 *)ptr); - continue; - } + case 32: + DST = (__force u32) cpu_to_be32(DST); break; - case BPF_LD|BPF_B|BPF_ABS: - k = fentry->k; -load_b: - ptr = load_pointer(skb, k, 1, &tmp); - if (ptr != NULL) { - A = *(u8 *)ptr; - continue; - } + case 64: + DST = (__force u64) cpu_to_be64(DST); + break; + } + CONT; + ALU_END_TO_LE: + switch (IMM) { + case 16: + DST = (__force u16) cpu_to_le16(DST); + break; + case 32: + DST = (__force u32) cpu_to_le32(DST); + break; + case 64: + DST = (__force u64) cpu_to_le64(DST); + break; + } + CONT; + + /* CALL */ + JMP_CALL: + /* Function call scratches BPF_R1-BPF_R5 registers, + * preserves BPF_R6-BPF_R9, and stores return value + * into BPF_R0. + */ + BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, + BPF_R4, BPF_R5); + CONT; + + /* JMP */ + JMP_JA: + insn += insn->off; + CONT; + JMP_JEQ_X: + if (DST == SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JEQ_K: + if (DST == IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JNE_X: + if (DST != SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JNE_K: + if (DST != IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGT_X: + if (DST > SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGT_K: + if (DST > IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGE_X: + if (DST >= SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGE_K: + if (DST >= IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGT_X: + if (((s64) DST) > ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGT_K: + if (((s64) DST) > ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGE_X: + if (((s64) DST) >= ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGE_K: + if (((s64) DST) >= ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSET_X: + if (DST & SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSET_K: + if (DST & IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_EXIT: + return BPF_R0; + + /* STX and ST and LDX*/ +#define LDST(SIZEOP, SIZE) \ + STX_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ + CONT; \ + ST_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ + CONT; \ + LDX_MEM_##SIZEOP: \ + DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; + + LDST(B, u8) + LDST(H, u16) + LDST(W, u32) + LDST(DW, u64) +#undef LDST + STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ + atomic_add((u32) SRC, (atomic_t *)(unsigned long) + (DST + insn->off)); + CONT; + STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ + atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) + (DST + insn->off)); + CONT; + LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ + off = IMM; +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[BPF_REG_CTX] + * == BPF_R6, sk_convert_filter() saves it in BPF_R6, + * internal BPF verifier will check that BPF_R6 == + * ctx. + * + * BPF_ABS and BPF_IND are wrappers of function calls, + * so they scratch BPF_R1-BPF_R5 registers, preserve + * BPF_R6-BPF_R9, and store return value into BPF_R0. + * + * Implicit input: + * ctx == skb == BPF_R6 == CTX + * + * Explicit input: + * SRC == any register + * IMM == 32-bit immediate + * + * Output: + * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness + */ + + ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = get_unaligned_be32(ptr); + CONT; + } + + return 0; + LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ + off = IMM; +load_half: + ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = get_unaligned_be16(ptr); + CONT; + } + + return 0; + LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ + off = IMM; +load_byte: + ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = *(u8 *)ptr; + CONT; + } + + return 0; + LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ + off = IMM + SRC; + goto load_word; + LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ + off = IMM + SRC; + goto load_half; + LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ + off = IMM + SRC; + 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; +} + +/* 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. + */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_TYPE_MAX (7 << 5) +#else +#define PKT_TYPE_MAX 7 +#endif +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) +{ + return __skb_get_poff((struct sk_buff *)(unsigned long) ctx); +} + +static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (skb->len < sizeof(struct nlattr)) + 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 *)(unsigned long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (skb->len < sizeof(struct nlattr)) + return 0; + + if (a > skb->len - sizeof(struct nlattr)) + return 0; + + nla = (struct nlattr *) &skb->data[a]; + if (nla->nla_len > skb->len - a) + 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(); +} + +/* note that this only generates 32-bit random numbers */ +static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + return prandom_u32(); +} + +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); + + /* A = *(u16 *) (CTX + offsetof(protocol)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, protocol)); + /* A = ntohs(A) [emitting a nop or swap16] */ + *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); + break; + + case SKF_AD_OFF + SKF_AD_PKTTYPE: + *insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX, + pkt_type_offset()); + if (insn->off < 0) + return false; + insn++; + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); +#ifdef __BIG_ENDIAN_BITFIELD + insn++; + *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5); +#endif + break; + + case SKF_AD_OFF + SKF_AD_IFINDEX: + case SKF_AD_OFF + SKF_AD_HATYPE: + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, dev)); + /* if (tmp != 0) goto pc + 1 */ + *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); + *insn++ = BPF_EXIT_INSN(); + if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, ifindex)); + else + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, type)); + break; + + case SKF_AD_OFF + SKF_AD_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, mark)); + break; + + case SKF_AD_OFF + SKF_AD_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + 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 = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + 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); + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + /* A = *(u16 *) (CTX + offsetof(vlan_tci)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, vlan_tci)); + if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, + ~VLAN_TAG_PRESENT); + } else { + /* A >>= 12 */ + *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); + /* A &= 1 */ + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 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: + case SKF_AD_OFF + SKF_AD_RANDOM: + /* arg1 = CTX */ + *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); + /* arg2 = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); + /* arg3 = X */ + *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); + /* Emit call(arg1=CTX, arg2=A, arg3=X) */ + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + *insn = BPF_EMIT_CALL(__skb_get_pay_offset); + break; + case SKF_AD_OFF + SKF_AD_NLATTR: + *insn = BPF_EMIT_CALL(__skb_get_nlattr); + break; + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest); + break; + case SKF_AD_OFF + SKF_AD_CPU: + *insn = BPF_EMIT_CALL(__get_raw_cpu_id); + break; + case SKF_AD_OFF + SKF_AD_RANDOM: + *insn = BPF_EMIT_CALL(__get_random_u32); + break; + } + break; + + case SKF_AD_OFF + SKF_AD_ALU_XOR_X: + /* A ^= X */ + *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); + 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(BPF_REG_FP + 1 != MAX_BPF_REG); + + if (len <= 0 || len > BPF_MAXINSNS) + return -EINVAL; + + if (new_prog) { + addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + } + +do_pass: + new_insn = new_prog; + fp = prog; + + if (new_insn) + *new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); + 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 = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); + break; + + /* Jump transformation cannot use BPF block macros + * everywhere as offset calculation and target updates + * require a bit more work than the rest, i.e. jump + * opcodes map as-is, but offsets need adjustment. + */ + +#define BPF_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) + + case BPF_JMP | BPF_JA: + target = i + fp->k + 1; + insn->code = fp->code; + BPF_EMIT_JMP; break; - case BPF_LD|BPF_W|BPF_LEN: - A = skb->len; - continue; - case BPF_LDX|BPF_W|BPF_LEN: - X = skb->len; - continue; - case BPF_LD|BPF_W|BPF_IND: - k = X + fentry->k; - goto load_w; - case BPF_LD|BPF_H|BPF_IND: - k = X + fentry->k; - goto load_h; - case BPF_LD|BPF_B|BPF_IND: - k = X + fentry->k; - goto load_b; - case BPF_LDX|BPF_B|BPF_MSH: - ptr = load_pointer(skb, fentry->k, 1, &tmp); - if (ptr != NULL) { - X = (*(u8 *)ptr & 0xf) << 2; - continue; + + 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++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); + + insn->dst_reg = BPF_REG_A; + insn->src_reg = BPF_REG_TMP; + bpf_src = BPF_X; + } else { + insn->dst_reg = BPF_REG_A; + insn->src_reg = BPF_REG_X; + insn->imm = fp->k; + bpf_src = BPF_SRC(fp->code); } - return 0; - case BPF_LD|BPF_IMM: - A = fentry->k; - continue; - case BPF_LDX|BPF_IMM: - X = fentry->k; - continue; - case BPF_LD|BPF_MEM: - A = mem[fentry->k]; - continue; - case BPF_LDX|BPF_MEM: - X = mem[fentry->k]; - continue; - case BPF_MISC|BPF_TAX: - X = A; - continue; - case BPF_MISC|BPF_TXA: - A = X; - continue; - case BPF_RET|BPF_K: - return fentry->k; - case BPF_RET|BPF_A: - return A; + + /* 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; + BPF_EMIT_JMP; + break; + } + + /* 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; + BPF_EMIT_JMP; + break; + } + + /* 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; + BPF_EMIT_JMP; + insn++; + + insn->code = BPF_JMP | BPF_JA; + target = i + fp->jf + 1; + BPF_EMIT_JMP; + break; + + /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ + case BPF_LDX | BPF_MSH | BPF_B: + /* tmp = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A); + /* A = BPF_R0 = *(u8 *) (skb->data + K) */ + *insn++ = BPF_LD_ABS(BPF_B, fp->k); + /* A &= 0xf */ + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); + /* A <<= 2 */ + *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); + /* X = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); + /* A = tmp */ + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); + break; + + /* RET_K, RET_A are remaped into 2 insns. */ + case BPF_RET | BPF_A: + case BPF_RET | BPF_K: + *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ? + BPF_K : BPF_X, BPF_REG_0, + BPF_REG_A, fp->k); + *insn = BPF_EXIT_INSN(); + break; + + /* Store to stack. */ case BPF_ST: - mem[fentry->k] = A; - continue; case BPF_STX: - mem[fentry->k] = X; - continue; - default: - WARN_ON(1); - return 0; - } + *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == + BPF_ST ? BPF_REG_A : BPF_REG_X, + -(BPF_MEMWORDS - fp->k) * 4); + break; - /* - * Handle ancillary data, which are impossible - * (or very difficult) to get parsing packet contents. - */ - switch (k-SKF_AD_OFF) { - case SKF_AD_PROTOCOL: - A = htons(skb->protocol); - continue; - case SKF_AD_PKTTYPE: - A = skb->pkt_type; - continue; - case SKF_AD_IFINDEX: - A = skb->dev->ifindex; - continue; + /* Load from stack. */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_FP, + -(BPF_MEMWORDS - fp->k) * 4); + break; + + /* A = K or X = K */ + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, fp->k); + break; + + /* X = A */ + case BPF_MISC | BPF_TAX: + *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); + break; + + /* A = X */ + case BPF_MISC | BPF_TXA: + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); + break; + + /* A = skb->len or X = skb->len */ + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LDX | BPF_W | BPF_LEN: + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_CTX, + offsetof(struct sk_buff, len)); + break; + + /* Access seccomp_data fields. */ + case BPF_LDX | BPF_ABS | BPF_W: + /* A = *(u32 *) (ctx + K) */ + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); + break; + + /* Unkown instruction. */ default: - 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; +} + +/* 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()). + * + * 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 + * a malicious user doesn't try to abuse us. + */ +static int check_load_and_stores(struct sock_filter *filter, int flen) +{ + u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ + int pc, ret = 0; + + BUILD_BUG_ON(BPF_MEMWORDS > 16); + + masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); + if (!masks) + return -ENOMEM; + + memset(masks, 0xff, flen * sizeof(*masks)); + + for (pc = 0; pc < flen; pc++) { + memvalid &= masks[pc]; + + switch (filter[pc].code) { + case BPF_ST: + case BPF_STX: + memvalid |= (1 << filter[pc].k); + break; + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + if (!(memvalid & (1 << filter[pc].k))) { + ret = -EINVAL; + goto error; + } + break; + case BPF_JMP | BPF_JA: + /* A jump must set masks on target */ + masks[pc + 1 + filter[pc].k] &= memvalid; + memvalid = ~0; + 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: + /* A jump must set masks on targets */ + masks[pc + 1 + filter[pc].jt] &= memvalid; + masks[pc + 1 + filter[pc].jf] &= memvalid; + memvalid = ~0; + break; + } + } +error: + kfree(masks); + return ret; +} + +static bool chk_code_allowed(u16 code_to_probe) +{ + static const bool codes[] = { + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_K] = true, + [BPF_ALU | BPF_ADD | BPF_X] = true, + [BPF_ALU | BPF_SUB | BPF_K] = true, + [BPF_ALU | BPF_SUB | BPF_X] = true, + [BPF_ALU | BPF_MUL | BPF_K] = true, + [BPF_ALU | BPF_MUL | BPF_X] = true, + [BPF_ALU | BPF_DIV | BPF_K] = true, + [BPF_ALU | BPF_DIV | BPF_X] = true, + [BPF_ALU | BPF_MOD | BPF_K] = true, + [BPF_ALU | BPF_MOD | BPF_X] = true, + [BPF_ALU | BPF_AND | BPF_K] = true, + [BPF_ALU | BPF_AND | BPF_X] = true, + [BPF_ALU | BPF_OR | BPF_K] = true, + [BPF_ALU | BPF_OR | BPF_X] = true, + [BPF_ALU | BPF_XOR | BPF_K] = true, + [BPF_ALU | BPF_XOR | BPF_X] = true, + [BPF_ALU | BPF_LSH | BPF_K] = true, + [BPF_ALU | BPF_LSH | BPF_X] = true, + [BPF_ALU | BPF_RSH | BPF_K] = true, + [BPF_ALU | BPF_RSH | BPF_X] = true, + [BPF_ALU | BPF_NEG] = true, + /* Load instructions */ + [BPF_LD | BPF_W | BPF_ABS] = true, + [BPF_LD | BPF_H | BPF_ABS] = true, + [BPF_LD | BPF_B | BPF_ABS] = true, + [BPF_LD | BPF_W | BPF_LEN] = true, + [BPF_LD | BPF_W | BPF_IND] = true, + [BPF_LD | BPF_H | BPF_IND] = true, + [BPF_LD | BPF_B | BPF_IND] = true, + [BPF_LD | BPF_IMM] = true, + [BPF_LD | BPF_MEM] = true, + [BPF_LDX | BPF_W | BPF_LEN] = true, + [BPF_LDX | BPF_B | BPF_MSH] = true, + [BPF_LDX | BPF_IMM] = true, + [BPF_LDX | BPF_MEM] = true, + /* Store instructions */ + [BPF_ST] = true, + [BPF_STX] = true, + /* Misc instructions */ + [BPF_MISC | BPF_TAX] = true, + [BPF_MISC | BPF_TXA] = true, + /* Return instructions */ + [BPF_RET | BPF_K] = true, + [BPF_RET | BPF_A] = true, + /* Jump instructions */ + [BPF_JMP | BPF_JA] = true, + [BPF_JMP | BPF_JEQ | BPF_K] = true, + [BPF_JMP | BPF_JEQ | BPF_X] = true, + [BPF_JMP | BPF_JGE | BPF_K] = true, + [BPF_JMP | BPF_JGE | BPF_X] = true, + [BPF_JMP | BPF_JGT | BPF_K] = true, + [BPF_JMP | BPF_JGT | BPF_X] = true, + [BPF_JMP | BPF_JSET | BPF_K] = true, + [BPF_JMP | BPF_JSET | BPF_X] = true, + }; + + if (code_to_probe >= ARRAY_SIZE(codes)) + return false; + + return codes[code_to_probe]; } /** @@ -290,101 +1227,352 @@ load_b: * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int sk_chk_filter(struct sock_filter *filter, int flen) +int sk_chk_filter(struct sock_filter *filter, unsigned int flen) { - struct sock_filter *ftest; + bool anc_found; int pc; if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL; - /* check the filter code now */ + /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { - ftest = &filter[pc]; + struct sock_filter *ftest = &filter[pc]; - /* 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; + /* May we actually operate on this code? */ + if (!chk_code_allowed(ftest->code)) + return -EINVAL; /* Some instructions need special checks */ - - case BPF_ALU|BPF_DIV|BPF_K: - /* check for division by zero */ + switch (ftest->code) { + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | 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_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: - /* check for invalid memory addresses */ + /* 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. + 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)) + if (ftest->k >= (unsigned int)(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 */ + 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: + /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; - - default: - return -EINVAL; + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + anc_found = false; + if (bpf_anc_helper(ftest) & BPF_ANC) + anc_found = true; + /* Ancillary operation unknown or unsupported */ + if (anc_found == false && ftest->k >= SKF_AD_OFF) + return -EINVAL; } } - return (BPF_CLASS(filter[flen - 1].code) == BPF_RET) ? 0 : -EINVAL; + /* Last instruction must be a RET code */ + switch (filter[flen - 1].code) { + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: + return check_load_and_stores(filter, flen); + } + + return -EINVAL; +} +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 + */ +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); + sk_filter_free(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) { + *fp_new = *fp; + /* As we're keeping 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 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)); + + /* 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->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; + + sk_filter_select_runtime(fp); + + 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); +} + +void __weak bpf_int_jit_compile(struct sk_filter *prog) +{ +} + +/** + * sk_filter_select_runtime - select execution runtime for BPF program + * @fp: sk_filter populated with internal BPF program + * + * try to JIT internal BPF program, if JIT is not available select interpreter + * BPF program will be executed via SK_RUN_FILTER() macro + */ +void sk_filter_select_runtime(struct sk_filter *fp) +{ + fp->bpf_func = (void *) __sk_run_filter; + + /* Probe if internal BPF can be JITed */ + bpf_int_jit_compile(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_select_runtime); + +/* free internal BPF program */ +void sk_filter_free(struct sk_filter *fp) +{ + bpf_jit_free(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_free); + +static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, + struct sock *sk) +{ + int err; + + fp->bpf_func = NULL; + fp->jited = 0; + + err = sk_chk_filter(fp->insns, fp->len); + if (err) { + if (sk != NULL) + sk_filter_uncharge(sk, fp); + else + kfree(fp); + 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); + + /* 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; +} + +/** + * sk_unattached_filter_create - create an unattached filter + * @pfp: the unattached filter that is created + * @fprog: the filter program + * + * Create a filter independent of any socket. We first run some + * sanity checks on it to make sure it does not explode on us later. + * If an error occurs or there is insufficient memory for the filter + * a negative errno code is returned. On success the return is zero. + */ +int sk_unattached_filter_create(struct sk_filter **pfp, + struct sock_fprog_kern *fprog) +{ + unsigned int fsize = sk_filter_proglen(fprog); + struct sk_filter *fp; + + /* Make sure new filter is there and in the right amounts. */ + if (fprog->filter == NULL) + return -EINVAL; + + 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; + + /* __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; +} +EXPORT_SYMBOL_GPL(sk_unattached_filter_create); + +void sk_unattached_filter_destroy(struct sk_filter *fp) +{ + sk_filter_release(fp); } +EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); /** * sk_attach_filter - attach a socket filter @@ -398,40 +1586,110 @@ int sk_chk_filter(struct sock_filter *filter, int flen) */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { - struct sk_filter *fp; - unsigned int fsize = sizeof(struct sock_filter) * fprog->len; + struct sk_filter *fp, *old_fp; + unsigned int fsize = sk_filter_proglen(fprog); + unsigned int sk_fsize = sk_filter_size(fprog->len); int err; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; - fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL); + 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, fsize+sizeof(*fp)); + sock_kfree_s(sk, fp, sk_fsize); return -EFAULT; } atomic_set(&fp->refcnt, 1); fp->len = fprog->len; - err = sk_chk_filter(fp->insns, fp->len); - if (!err) { - struct sk_filter *old_fp; + err = sk_store_orig_filter(fp, fprog); + if (err) { + sk_filter_uncharge(sk, fp); + return -ENOMEM; + } - spin_lock_bh(&sk->sk_lock.slock); - old_fp = sk->sk_filter; - sk->sk_filter = fp; - spin_unlock_bh(&sk->sk_lock.slock); - fp = old_fp; + /* __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); + +int sk_detach_filter(struct sock *sk) +{ + int ret = -ENOENT; + struct sk_filter *filter; + + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + + filter = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); + if (filter) { + RCU_INIT_POINTER(sk->sk_filter, NULL); + sk_filter_uncharge(sk, filter); + ret = 0; } - if (fp) - sk_filter_release(sk, fp); - return err; + return ret; } +EXPORT_SYMBOL_GPL(sk_detach_filter); -EXPORT_SYMBOL(sk_chk_filter); -EXPORT_SYMBOL(sk_run_filter); +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 ret = 0; + + lock_sock(sk); + filter = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); + if (!filter) + goto out; + + /* 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 < fprog->len) + goto out; + + ret = -EFAULT; + if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog))) + goto out; + + /* 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 c4f25385029..a0348fde1fd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -20,141 +20,165 @@ #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/mutex.h> #include <net/flow.h> -#include <asm/atomic.h> -#include <asm/semaphore.h> +#include <linux/atomic.h> #include <linux/security.h> +#include <net/net_namespace.h> struct flow_cache_entry { - struct flow_cache_entry *next; - u16 family; - u8 dir; - struct flowi key; - u32 genid; - u32 sk_sid; - void *object; - atomic_t *object_ref; + union { + struct hlist_node hlist; + struct list_head gc_list; + } u; + struct net *net; + u16 family; + u8 dir; + u32 genid; + struct flowi key; + struct flow_cache_object *object; }; -atomic_t flow_cache_genid = ATOMIC_INIT(0); - -static u32 flow_hash_shift; -#define flow_hash_size (1 << flow_hash_shift) -static DEFINE_PER_CPU(struct flow_cache_entry **, flow_tables) = { NULL }; - -#define flow_table(cpu) (per_cpu(flow_tables, cpu)) - -static kmem_cache_t *flow_cachep __read_mostly; - -static int flow_lwm, flow_hwm; - -struct flow_percpu_info { - int hash_rnd_recalc; - u32 hash_rnd; - int count; -} ____cacheline_aligned; -static DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 }; - -#define flow_hash_rnd_recalc(cpu) \ - (per_cpu(flow_hash_info, cpu).hash_rnd_recalc) -#define flow_hash_rnd(cpu) \ - (per_cpu(flow_hash_info, cpu).hash_rnd) -#define flow_count(cpu) \ - (per_cpu(flow_hash_info, cpu).count) - -static struct timer_list flow_hash_rnd_timer; - -#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) - struct flow_flush_info { - atomic_t cpuleft; - struct completion completion; + struct flow_cache *cache; + atomic_t cpuleft; + struct completion completion; }; -static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL }; -#define flow_flush_tasklet(cpu) (&per_cpu(flow_flush_tasklets, cpu)) +static struct kmem_cache *flow_cachep __read_mostly; + +#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) +#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) static void flow_cache_new_hashrnd(unsigned long arg) { + struct flow_cache *fc = (void *) arg; int i; - for_each_cpu(i) - flow_hash_rnd_recalc(i) = 1; + for_each_possible_cpu(i) + per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1; - flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&flow_hash_rnd_timer); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); } -static void __flow_cache_shrink(int cpu, int shrink_to) +static int flow_entry_valid(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { - struct flow_cache_entry *fle, **flp; - int i; + if (atomic_read(&xfrm->flow_cache_genid) != fle->genid) + return 0; + if (fle->object && !fle->object->ops->check(fle->object)) + return 0; + return 1; +} - for (i = 0; i < flow_hash_size; i++) { - int k = 0; +static void flow_entry_kill(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) +{ + if (fle->object) + fle->object->ops->delete(fle->object); + kmem_cache_free(flow_cachep, fle); +} - flp = &flow_table(cpu)[i]; - while ((fle = *flp) != NULL && k < shrink_to) { - k++; - flp = &fle->next; - } - while ((fle = *flp) != NULL) { - *flp = fle->next; - if (fle->object) - atomic_dec(fle->object_ref); - kmem_cache_free(flow_cachep, fle); - flow_count(cpu)--; - } +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(&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, xfrm); +} + +static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, + int deleted, struct list_head *gc_list, + struct netns_xfrm *xfrm) +{ + if (deleted) { + fcp->hash_count -= deleted; + 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); } } -static void flow_cache_shrink(int cpu) +static void __flow_cache_shrink(struct flow_cache *fc, + struct flow_cache_percpu *fcp, + int shrink_to) { - int shrink_to = flow_lwm / flow_hash_size; + struct flow_cache_entry *fle; + 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; + + hlist_for_each_entry_safe(fle, tmp, + &fcp->hash_table[i], u.hlist) { + if (saved < shrink_to && + flow_entry_valid(fle, xfrm)) { + saved++; + } else { + deleted++; + hlist_del(&fle->u.hlist); + list_add_tail(&fle->u.gc_list, &gc_list); + } + } + } - __flow_cache_shrink(cpu, shrink_to); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); } -static void flow_new_hash_rnd(int cpu) +static void flow_cache_shrink(struct flow_cache *fc, + struct flow_cache_percpu *fcp) { - get_random_bytes(&flow_hash_rnd(cpu), sizeof(u32)); - flow_hash_rnd_recalc(cpu) = 0; + int shrink_to = fc->low_watermark / flow_cache_hash_size(fc); - __flow_cache_shrink(cpu, 0); + __flow_cache_shrink(fc, fcp, shrink_to); } -static u32 flow_hash_code(struct flowi *key, int cpu) +static void flow_new_hash_rnd(struct flow_cache *fc, + struct flow_cache_percpu *fcp) { - u32 *k = (u32 *) key; - - return (jhash2(k, (sizeof(*key) / sizeof(u32)), flow_hash_rnd(cpu)) & - (flow_hash_size - 1)); + get_random_bytes(&fcp->hash_rnd, sizeof(u32)); + fcp->hash_rnd_recalc = 0; + __flow_cache_shrink(fc, fcp, 0); } -#if (BITS_PER_LONG == 64) -typedef u64 flow_compare_t; -#else -typedef u32 flow_compare_t; -#endif +static u32 flow_hash_code(struct flow_cache *fc, + struct flow_cache_percpu *fcp, + const struct flowi *key, + size_t keysize) +{ + const u32 *k = (const u32 *) key; + const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32); -extern void flowi_is_missized(void); + return jhash2(k, length, fcp->hash_rnd) + & (flow_cache_hash_size(fc) - 1); +} /* I hear what you're saying, use memcmp. But memcmp cannot make - * important assumptions that we can here, such as alignment and - * constant size. + * important assumptions that we can here, such as alignment. */ -static int flow_key_compare(struct flowi *key1, struct flowi *key2) +static int flow_key_compare(const struct flowi *key1, const struct flowi *key2, + size_t keysize) { - flow_compare_t *k1, *k1_lim, *k2; - const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t); - - if (sizeof(struct flowi) % sizeof(flow_compare_t)) - flowi_is_missized(); + const flow_compare_t *k1, *k1_lim, *k2; - k1 = (flow_compare_t *) key1; - k1_lim = k1 + n_elem; + k1 = (const flow_compare_t *) key1; + k1_lim = k1 + keysize; - k2 = (flow_compare_t *) key2; + k2 = (const flow_compare_t *) key2; do { if (*k1++ != *k2++) @@ -164,212 +188,324 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, - flow_resolve_t resolver) +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_entry *fle, **head; + 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; + size_t keysize; unsigned int hash; - int cpu; local_bh_disable(); - cpu = smp_processor_id(); + fcp = this_cpu_ptr(fc->percpu); fle = NULL; + flo = NULL; + + keysize = flow_key_size(family); + if (!keysize) + goto nocache; + /* Packet really early in init? Making flow_cache_init a * pre-smp initcall would solve this. --RR */ - if (!flow_table(cpu)) + if (!fcp->hash_table) goto nocache; - if (flow_hash_rnd_recalc(cpu)) - flow_new_hash_rnd(cpu); - hash = flow_hash_code(key, cpu); - - head = &flow_table(cpu)[hash]; - 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; + if (fcp->hash_rnd_recalc) + flow_new_hash_rnd(fc, fcp); - if (ret) - atomic_inc(fle->object_ref); - local_bh_enable(); - - return ret; - } + hash = flow_hash_code(fc, fcp, key, keysize); + hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) { + if (tfle->net == net && + tfle->family == family && + tfle->dir == dir && + flow_key_compare(key, &tfle->key, keysize) == 0) { + fle = tfle; break; } } - if (!fle) { - if (flow_count(cpu) > flow_hwm) - flow_cache_shrink(cpu); + if (unlikely(!fle)) { + if (fcp->hash_count > fc->high_watermark) + flow_cache_shrink(fc, fcp); - fle = kmem_cache_alloc(flow_cachep, SLAB_ATOMIC); + fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); if (fle) { - fle->next = *head; - *head = fle; + fle->net = net; fle->family = family; fle->dir = dir; - fle->sk_sid = sk_sid; - memcpy(&fle->key, key, sizeof(*key)); + memcpy(&fle->key, key, keysize * sizeof(flow_compare_t)); fle->object = NULL; - flow_count(cpu)++; + hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); + fcp->hash_count++; } + } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) { + flo = fle->object; + if (!flo) + goto ret_object; + flo = flo->ops->get(flo); + if (flo) + goto ret_object; + } else if (fle->object) { + flo = fle->object; + flo->ops->delete(flo); + fle->object = NULL; } nocache: - { - void *obj; - atomic_t *obj_ref; - - resolver(key, sk_sid, family, dir, &obj, &obj_ref); - - if (fle) { - fle->genid = atomic_read(&flow_cache_genid); - - if (fle->object) - atomic_dec(fle->object_ref); - - fle->object = obj; - fle->object_ref = obj_ref; - if (obj) - atomic_inc(fle->object_ref); - } - local_bh_enable(); - - return obj; + flo = NULL; + if (fle) { + flo = fle->object; + fle->object = NULL; + } + flo = resolver(net, key, family, dir, flo, ctx); + if (fle) { + fle->genid = atomic_read(&net->xfrm.flow_cache_genid); + if (!IS_ERR(flo)) + fle->object = flo; + else + fle->genid--; + } else { + if (!IS_ERR_OR_NULL(flo)) + flo->ops->delete(flo); } +ret_object: + local_bh_enable(); + return flo; } +EXPORT_SYMBOL(flow_cache_lookup); static void flow_cache_flush_tasklet(unsigned long data) { struct flow_flush_info *info = (void *)data; - int i; - int cpu; - - cpu = smp_processor_id(); - for (i = 0; i < flow_hash_size; i++) { - struct flow_cache_entry *fle; - - fle = flow_table(cpu)[i]; - for (; fle; fle = fle->next) { - unsigned genid = atomic_read(&flow_cache_genid); - - if (!fle->object || fle->genid == genid) + struct flow_cache *fc = info->cache; + struct flow_cache_percpu *fcp; + struct flow_cache_entry *fle; + 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, xfrm)) continue; - fle->object = NULL; - atomic_dec(fle->object_ref); + deleted++; + hlist_del(&fle->u.hlist); + list_add_tail(&fle->u.gc_list, &gc_list); } } + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); + if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); } -static void flow_cache_flush_per_cpu(void *) __attribute__((__unused__)); +/* + * Return whether a cpu needs flushing. Conservatively, we assume + * the presence of any entries means the core may require flushing, + * since the flow_cache_ops.check() function may assume it's running + * on the same core as the per-cpu cache component. + */ +static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu) +{ + struct flow_cache_percpu *fcp; + int i; + + fcp = per_cpu_ptr(fc->percpu, cpu); + for (i = 0; i < flow_cache_hash_size(fc); i++) + if (!hlist_empty(&fcp->hash_table[i])) + return 0; + return 1; +} + static void flow_cache_flush_per_cpu(void *data) { struct flow_flush_info *info = data; - int cpu; struct tasklet_struct *tasklet; - cpu = smp_processor_id(); - - tasklet = flow_flush_tasklet(cpu); + tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet; tasklet->data = (unsigned long)info; tasklet_schedule(tasklet); } -void flow_cache_flush(void) +void flow_cache_flush(struct net *net) { struct flow_flush_info info; - static DECLARE_MUTEX(flow_flush_sem); + cpumask_var_t mask; + int i, self; + + /* Track which cpus need flushing to avoid disturbing all cores. */ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return; + cpumask_clear(mask); /* Don't want cpus going down or up during this. */ - lock_cpu_hotplug(); - down(&flow_flush_sem); - atomic_set(&info.cpuleft, num_online_cpus()); + get_online_cpus(); + 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); + atomic_set(&info.cpuleft, cpumask_weight(mask)); + if (atomic_read(&info.cpuleft) == 0) + goto done; + init_completion(&info.completion); local_bh_disable(); - smp_call_function(flow_cache_flush_per_cpu, &info, 1, 0); - flow_cache_flush_tasklet((unsigned long)&info); + self = cpumask_test_and_clear_cpu(smp_processor_id(), mask); + on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0); + if (self) + flow_cache_flush_tasklet((unsigned long)&info); local_bh_enable(); wait_for_completion(&info.completion); - up(&flow_flush_sem); - unlock_cpu_hotplug(); + +done: + mutex_unlock(&net->xfrm.flow_flush_sem); + put_online_cpus(); + free_cpumask_var(mask); } -static void __devinit flow_cache_cpu_prepare(int cpu) +static void flow_cache_flush_task(struct work_struct *work) { - struct tasklet_struct *tasklet; - unsigned long order; - - for (order = 0; - (PAGE_SIZE << order) < - (sizeof(struct flow_cache_entry *)*flow_hash_size); - order++) - /* NOTHING */; - - flow_table(cpu) = (struct flow_cache_entry **) - __get_free_pages(GFP_KERNEL, order); - if (!flow_table(cpu)) - panic("NET: failed to allocate flow cache order %lu\n", order); + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); + struct net *net = container_of(xfrm, struct net, xfrm); - memset(flow_table(cpu), 0, PAGE_SIZE << order); + flow_cache_flush(net); +} - flow_hash_rnd_recalc(cpu) = 1; - flow_count(cpu) = 0; +void flow_cache_flush_deferred(struct net *net) +{ + schedule_work(&net->xfrm.flow_cache_flush_work); +} - tasklet = flow_flush_tasklet(cpu); - tasklet_init(tasklet, flow_cache_flush_tasklet, 0); +static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) +{ + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); + size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); + + if (!fcp->hash_table) { + fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); + if (!fcp->hash_table) { + pr_err("NET: failed to allocate flow cache sz %zu\n", sz); + return -ENOMEM; + } + fcp->hash_rnd_recalc = 1; + fcp->hash_count = 0; + tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0); + } + return 0; } -#ifdef CONFIG_HOTPLUG_CPU static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { - if (action == CPU_DEAD) - __flow_cache_shrink((unsigned long)hcpu, 0); + 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); + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + res = flow_cache_cpu_prepare(fc, cpu); + if (res) + return notifier_from_errno(res); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + __flow_cache_shrink(fc, fcp, 0); + break; + } return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ -static int __init flow_cache_init(void) +int flow_cache_init(struct net *net) { int i; - - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + struct flow_cache *fc = &net->xfrm.flow_cache_global; if (!flow_cachep) - panic("NET: failed to allocate flow cache slab\n"); - - flow_hash_shift = 10; - flow_lwm = 2 * flow_hash_size; - flow_hwm = 4 * flow_hash_size; + 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); + fc->high_watermark = 4 * flow_cache_hash_size(fc); + + fc->percpu = alloc_percpu(struct flow_cache_percpu); + if (!fc->percpu) + return -ENOMEM; + + cpu_notifier_register_begin(); + + for_each_online_cpu(i) { + if (flow_cache_cpu_prepare(fc, i)) + goto err; + } + fc->hotcpu_notifier = (struct notifier_block){ + .notifier_call = flow_cache_cpu, + }; + __register_hotcpu_notifier(&fc->hotcpu_notifier); - init_timer(&flow_hash_rnd_timer); - flow_hash_rnd_timer.function = flow_cache_new_hashrnd; - flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&flow_hash_rnd_timer); + cpu_notifier_register_done(); - for_each_cpu(i) - flow_cache_cpu_prepare(i); + setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, + (unsigned long) fc); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); - hotcpu_notifier(flow_cache_cpu, 0); return 0; + +err: + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + cpu_notifier_register_done(); + + free_percpu(fc->percpu); + fc->percpu = NULL; + + return -ENOMEM; } +EXPORT_SYMBOL(flow_cache_init); + +void flow_cache_fini(struct net *net) +{ + int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; -module_init(flow_cache_init); + del_timer_sync(&fc->rnd_timer); + unregister_hotcpu_notifier(&fc->hotcpu_notifier); -EXPORT_SYMBOL(flow_cache_genid); -EXPORT_SYMBOL(flow_cache_lookup); + 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 new file mode 100644 index 00000000000..107ed12a532 --- /dev/null +++ b/net/core/flow_dissector.c @@ -0,0 +1,405 @@ +#include <linux/skbuff.h> +#include <linux/export.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/if_vlan.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <linux/igmp.h> +#include <linux/icmp.h> +#include <linux/sctp.h> +#include <linux/dccp.h> +#include <linux/if_tunnel.h> +#include <linux/if_pppox.h> +#include <linux/ppp_defs.h> +#include <net/flow_keys.h> + +/* copy saddr & daddr, possibly using 64bit load/store + * Equivalent to : flow->src = iph->saddr; + * flow->dst = iph->daddr; + */ +static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph) +{ + BUILD_BUG_ON(offsetof(typeof(*flow), dst) != + offsetof(typeof(*flow), src) + sizeof(flow->src)); + memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst)); +} + +/** + * skb_flow_get_ports - extract the upper layer ports and return them + * @skb: buffer to extract the ports from + * @thoff: transport header offset + * @ip_proto: protocol for which to get port offset + * + * The function will try to retrieve the ports at offset thoff + poff where poff + * is the protocol port offset returned from proto_ports_offset + */ +__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) +{ + int poff = proto_ports_offset(ip_proto); + + if (poff >= 0) { + __be32 *ports, _ports; + + ports = skb_header_pointer(skb, thoff + poff, + sizeof(_ports), &_ports); + if (ports) + return *ports; + } + + return 0; +} +EXPORT_SYMBOL(skb_flow_get_ports); + +bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) +{ + int nhoff = skb_network_offset(skb); + u8 ip_proto; + __be16 proto = skb->protocol; + + memset(flow, 0, sizeof(*flow)); + +again: + switch (proto) { + case htons(ETH_P_IP): { + const struct iphdr *iph; + struct iphdr _iph; +ip: + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph || iph->ihl < 5) + return false; + nhoff += iph->ihl * 4; + + ip_proto = iph->protocol; + if (ip_is_fragment(iph)) + ip_proto = 0; + + iph_to_flow_copy_addrs(flow, iph); + break; + } + case htons(ETH_P_IPV6): { + const struct ipv6hdr *iph; + struct ipv6hdr _iph; +ipv6: + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph) + return false; + + ip_proto = iph->nexthdr; + flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); + flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); + nhoff += sizeof(struct ipv6hdr); + break; + } + case htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): { + const struct vlan_hdr *vlan; + struct vlan_hdr _vlan; + + vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan); + if (!vlan) + return false; + + proto = vlan->h_vlan_encapsulated_proto; + nhoff += sizeof(*vlan); + goto again; + } + case htons(ETH_P_PPP_SES): { + struct { + struct pppoe_hdr hdr; + __be16 proto; + } *hdr, _hdr; + hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr); + if (!hdr) + return false; + proto = hdr->proto; + nhoff += PPPOE_SES_HLEN; + switch (proto) { + case htons(PPP_IP): + goto ip; + case htons(PPP_IPV6): + goto ipv6; + default: + return false; + } + } + default: + return false; + } + + switch (ip_proto) { + case IPPROTO_GRE: { + struct gre_hdr { + __be16 flags; + __be16 proto; + } *hdr, _hdr; + + hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr); + if (!hdr) + return false; + /* + * Only look inside GRE if version zero and no + * routing + */ + if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) { + proto = hdr->proto; + nhoff += 4; + if (hdr->flags & GRE_CSUM) + nhoff += 4; + if (hdr->flags & GRE_KEY) + nhoff += 4; + if (hdr->flags & GRE_SEQ) + nhoff += 4; + if (proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = skb_header_pointer(skb, nhoff, + sizeof(_eth), &_eth); + if (!eth) + return false; + proto = eth->h_proto; + nhoff += sizeof(*eth); + } + goto again; + } + break; + } + case IPPROTO_IPIP: + proto = htons(ETH_P_IP); + goto ip; + case IPPROTO_IPV6: + proto = htons(ETH_P_IPV6); + goto ipv6; + default: + break; + } + + flow->ip_proto = ip_proto; + flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto); + flow->thoff = (u16) nhoff; + + return true; +} +EXPORT_SYMBOL(skb_flow_dissect); + +static u32 hashrnd __read_mostly; +static __always_inline void __flow_hash_secret_init(void) +{ + net_get_random_once(&hashrnd, sizeof(hashrnd)); +} + +static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c) +{ + __flow_hash_secret_init(); + return jhash_3words(a, b, c, hashrnd); +} + +static __always_inline u32 __flow_hash_1word(u32 a) +{ + __flow_hash_secret_init(); + return jhash_1word(a, hashrnd); +} + +/* + * __skb_get_hash: calculate a flow hash based on src/dst addresses + * 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) +{ + struct flow_keys keys; + u32 hash; + + if (!skb_flow_dissect(skb, &keys)) + return; + + if (keys.ports) + skb->l4_hash = 1; + + /* get a consistent hash (same value on both flow directions) */ + if (((__force u32)keys.dst < (__force u32)keys.src) || + (((__force u32)keys.dst == (__force u32)keys.src) && + ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { + swap(keys.dst, keys.src); + swap(keys.port16[0], keys.port16[1]); + } + + hash = __flow_hash_3words((__force u32)keys.dst, + (__force u32)keys.src, + (__force u32)keys.ports); + if (!hash) + hash = 1; + + skb->hash = hash; +} +EXPORT_SYMBOL(__skb_get_hash); + +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) +{ + u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; + + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; + return hash; + } + + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol; + hash = __flow_hash_1word(hash); + + return (u16) (((u64) hash * qcount) >> 32) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + +/* __skb_get_poff() returns the offset to the payload as far as it could + * be dissected. The main user is currently BPF, so that we can dynamically + * truncate packets without needing to push actual payload to the user + * space and can analyze headers only, instead. + */ +u32 __skb_get_poff(const struct sk_buff *skb) +{ + struct flow_keys keys; + u32 poff = 0; + + if (!skb_flow_dissect(skb, &keys)) + return 0; + + poff += keys.thoff; + switch (keys.ip_proto) { + case IPPROTO_TCP: { + const struct tcphdr *tcph; + struct tcphdr _tcph; + + tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph); + if (!tcph) + return poff; + + poff += max_t(u32, sizeof(struct tcphdr), tcph->doff * 4); + break; + } + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + poff += sizeof(struct udphdr); + break; + /* For the rest, we do not really care about header + * extensions at this point for now. + */ + case IPPROTO_ICMP: + poff += sizeof(struct icmphdr); + break; + case IPPROTO_ICMPV6: + poff += sizeof(struct icmp6hdr); + break; + case IPPROTO_IGMP: + poff += sizeof(struct igmphdr); + break; + case IPPROTO_DCCP: + poff += sizeof(struct dccp_hdr); + break; + case IPPROTO_SCTP: + poff += sizeof(struct sctphdr); + break; + } + + return poff; +} + +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->hash; + hash = __flow_hash_1word(hash); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int queue_index = sk_tx_queue_get(sk); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); + + if (queue_index != new_index && sk && + rcu_access_pointer(sk->sk_dst_cache)) + sk_tx_queue_set(sk, new_index); + + queue_index = new_index; + } + + return queue_index; +} + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb, + void *accel_priv) +{ + int queue_index = 0; + + if (dev->real_num_tx_queues != 1) { + const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); + else + queue_index = __netdev_pick_tx(dev, skb); + + if (!accel_priv) + queue_index = netdev_cap_txqueue(dev, queue_index); + } + + skb_set_queue_mapping(skb, queue_index); + return netdev_get_tx_queue(dev, queue_index); +} diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index b07c029e821..6b5b6e7013c 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -14,8 +14,7 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/bitops.h> +#include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -31,6 +30,8 @@ #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> +#include <linux/rbtree.h> +#include <linux/slab.h> #include <net/sock.h> #include <net/gen_stats.h> @@ -65,9 +66,9 @@ NOTES. - * The stored value for avbps is scaled by 2^5, so that maximal - rate is ~1Gbit, avpps is scaled by 2^10. - + * avbps is scaled by 2^5, avpps is scaled by 2^10. + * both values are reported as 32 bit unsigned values. bps can + overflow for fast links : max speed being 34360Mbit/sec * Minimal interval is HZ/4=250msec (it is the greatest common divisor for HZ=100 and HZ=1024 8)), maximal interval is (HZ*2^EST_MAX_INTERVAL)/4 = 8sec. Shorter intervals @@ -79,57 +80,110 @@ struct gen_estimator { - struct gen_estimator *next; - struct gnet_stats_basic *bstats; - struct gnet_stats_rate_est *rate_est; + struct list_head list; + struct gnet_stats_basic_packed *bstats; + struct gnet_stats_rate_est64 *rate_est; spinlock_t *stats_lock; - unsigned interval; int ewma_log; u64 last_bytes; + u64 avbps; u32 last_packets; u32 avpps; - u32 avbps; + struct rcu_head e_rcu; + struct rb_node node; }; struct gen_estimator_head { struct timer_list timer; - struct gen_estimator *list; + struct list_head list; }; static struct gen_estimator_head elist[EST_MAX_INTERVAL+1]; -/* Estimator array lock */ +/* Protects against NULL dereference */ static DEFINE_RWLOCK(est_lock); +/* Protects against soft lockup during large deletion */ +static struct rb_root est_root = RB_ROOT; +static DEFINE_SPINLOCK(est_tree_lock); + static void est_timer(unsigned long arg) { int idx = (int)arg; struct gen_estimator *e; - read_lock(&est_lock); - for (e = elist[idx].list; e; e = e->next) { + rcu_read_lock(); + list_for_each_entry_rcu(e, &elist[idx].list, list) { u64 nbytes; + u64 brate; u32 npackets; u32 rate; spin_lock(e->stats_lock); + read_lock(&est_lock); + if (e->bstats == NULL) + goto skip; + nbytes = e->bstats->bytes; npackets = e->bstats->packets; - rate = (nbytes - e->last_bytes)<<(7 - idx); + brate = (nbytes - e->last_bytes)<<(7 - idx); e->last_bytes = nbytes; - e->avbps += ((long)rate - (long)e->avbps) >> e->ewma_log; + e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log); e->rate_est->bps = (e->avbps+0xF)>>5; rate = (npackets - e->last_packets)<<(12 - idx); e->last_packets = npackets; - e->avpps += ((long)rate - (long)e->avpps) >> e->ewma_log; + e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log); e->rate_est->pps = (e->avpps+0x1FF)>>10; +skip: + read_unlock(&est_lock); spin_unlock(e->stats_lock); } - mod_timer(&elist[idx].timer, jiffies + ((HZ<<idx)/4)); - read_unlock(&est_lock); + if (!list_empty(&elist[idx].list)) + mod_timer(&elist[idx].timer, jiffies + ((HZ/4) << idx)); + rcu_read_unlock(); +} + +static void gen_add_node(struct gen_estimator *est) +{ + struct rb_node **p = &est_root.rb_node, *parent = NULL; + + while (*p) { + struct gen_estimator *e; + + parent = *p; + e = rb_entry(parent, struct gen_estimator, node); + + if (est->bstats > e->bstats) + p = &parent->rb_right; + else + p = &parent->rb_left; + } + rb_link_node(&est->node, parent, p); + rb_insert_color(&est->node, &est_root); +} + +static +struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats, + const struct gnet_stats_rate_est64 *rate_est) +{ + struct rb_node *p = est_root.rb_node; + + while (p) { + struct gen_estimator *e; + + e = rb_entry(p, struct gen_estimator, node); + + if (bstats > e->bstats) + p = p->rb_right; + else if (bstats < e->bstats || rate_est != e->rate_est) + p = p->rb_left; + else + return e; + } + return NULL; } /** @@ -144,27 +198,30 @@ static void est_timer(unsigned long arg) * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabed during this period. - * + * * Returns 0 on success or a negative error code. + * */ -int gen_new_estimator(struct gnet_stats_basic *bstats, - struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, struct rtattr *opt) +int gen_new_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_rate_est64 *rate_est, + spinlock_t *stats_lock, + struct nlattr *opt) { struct gen_estimator *est; - struct gnet_estimator *parm = RTA_DATA(opt); + struct gnet_estimator *parm = nla_data(opt); + int idx; - if (RTA_PAYLOAD(opt) < sizeof(*parm)) + if (nla_len(opt) < sizeof(*parm)) return -EINVAL; if (parm->interval < -2 || parm->interval > 3) return -EINVAL; - est = kmalloc(sizeof(*est), GFP_KERNEL); + est = kzalloc(sizeof(*est), GFP_KERNEL); if (est == NULL) return -ENOBUFS; - memset(est, 0, sizeof(*est)); - est->interval = parm->interval + 2; + idx = parm->interval + 2; est->bstats = bstats; est->rate_est = rate_est; est->stats_lock = stats_lock; @@ -174,57 +231,54 @@ int gen_new_estimator(struct gnet_stats_basic *bstats, est->last_packets = bstats->packets; est->avpps = rate_est->pps<<10; - est->next = elist[est->interval].list; - if (est->next == NULL) { - init_timer(&elist[est->interval].timer); - elist[est->interval].timer.data = est->interval; - elist[est->interval].timer.expires = jiffies + ((HZ<<est->interval)/4); - elist[est->interval].timer.function = est_timer; - add_timer(&elist[est->interval].timer); + spin_lock_bh(&est_tree_lock); + if (!elist[idx].timer.function) { + INIT_LIST_HEAD(&elist[idx].list); + setup_timer(&elist[idx].timer, est_timer, idx); } - write_lock_bh(&est_lock); - elist[est->interval].list = est; - write_unlock_bh(&est_lock); + + if (list_empty(&elist[idx].list)) + mod_timer(&elist[idx].timer, jiffies + ((HZ/4) << idx)); + + list_add_rcu(&est->list, &elist[idx].list); + gen_add_node(est); + spin_unlock_bh(&est_tree_lock); + return 0; } +EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @bstats: basic statistics * @rate_est: rate estimator statistics * - * Removes the rate estimator specified by &bstats and &rate_est - * and deletes the timer. + * Removes the rate estimator specified by &bstats and &rate_est. + * + * Note : Caller should respect an RCU grace period before freeing stats_lock */ -void gen_kill_estimator(struct gnet_stats_basic *bstats, - struct gnet_stats_rate_est *rate_est) +void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_rate_est64 *rate_est) { - int idx; - struct gen_estimator *est, **pest; - - for (idx=0; idx <= EST_MAX_INTERVAL; idx++) { - int killed = 0; - pest = &elist[idx].list; - while ((est=*pest) != NULL) { - if (est->rate_est != rate_est || est->bstats != bstats) { - pest = &est->next; - continue; - } - - write_lock_bh(&est_lock); - *pest = est->next; - write_unlock_bh(&est_lock); - - kfree(est); - killed++; - } - if (killed && elist[idx].list == NULL) - del_timer(&elist[idx].timer); + struct gen_estimator *e; + + spin_lock_bh(&est_tree_lock); + while ((e = gen_find_node(bstats, rate_est))) { + rb_erase(&e->node, &est_root); + + write_lock(&est_lock); + e->bstats = NULL; + write_unlock(&est_lock); + + list_del_rcu(&e->list); + kfree_rcu(e, e_rcu); } + spin_unlock_bh(&est_tree_lock); } +EXPORT_SYMBOL(gen_kill_estimator); /** - * gen_replace_estimator - replace rate estimator configruation + * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @rate_est: rate estimator statistics * @stats_lock: statistics lock @@ -232,19 +286,36 @@ void gen_kill_estimator(struct gnet_stats_basic *bstats, * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). - * + * * Returns 0 on success or a negative error code. */ -int -gen_replace_estimator(struct gnet_stats_basic *bstats, - struct gnet_stats_rate_est *rate_est, spinlock_t *stats_lock, - struct rtattr *opt) +int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_rate_est64 *rate_est, + spinlock_t *stats_lock, struct nlattr *opt) { - gen_kill_estimator(bstats, rate_est); - return gen_new_estimator(bstats, rate_est, stats_lock, opt); + gen_kill_estimator(bstats, rate_est); + return gen_new_estimator(bstats, rate_est, stats_lock, opt); } - - -EXPORT_SYMBOL(gen_kill_estimator); -EXPORT_SYMBOL(gen_new_estimator); EXPORT_SYMBOL(gen_replace_estimator); + +/** + * gen_estimator_active - test if estimator is currently in use + * @bstats: basic statistics + * @rate_est: rate estimator statistics + * + * Returns true if estimator is active, and false if not. + */ +bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, + const struct gnet_stats_rate_est64 *rate_est) +{ + bool res; + + ASSERT_RTNL(); + + spin_lock_bh(&est_tree_lock); + res = gen_find_node(bstats, rate_est) != NULL; + spin_unlock_bh(&est_tree_lock); + + return res; +} +EXPORT_SYMBOL(gen_estimator_active); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 8f21490355f..9d3d9e78397 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -20,16 +20,18 @@ #include <linux/socket.h> #include <linux/rtnetlink.h> #include <linux/gen_stats.h> +#include <net/netlink.h> #include <net/gen_stats.h> static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) { - RTA_PUT(d->skb, type, size, buf); + if (nla_put(d->skb, type, size, buf)) + goto nla_put_failure; return 0; -rtattr_failure: +nla_put_failure: spin_unlock_bh(d->lock); return -1; } @@ -55,13 +57,14 @@ rtattr_failure: int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, int xstats_type, spinlock_t *lock, struct gnet_dump *d) + __acquires(lock) { memset(d, 0, sizeof(*d)); - + spin_lock_bh(lock); d->lock = lock; if (type) - d->tail = (struct rtattr *) skb->tail; + d->tail = (struct nlattr *)skb_tail_pointer(skb); d->skb = skb; d->compat_tc_stats = tc_stats_type; d->compat_xstats = xstats_type; @@ -71,6 +74,7 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, return 0; } +EXPORT_SYMBOL(gnet_stats_start_copy_compat); /** * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode @@ -91,6 +95,7 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, { return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d); } +EXPORT_SYMBOL(gnet_stats_start_copy); /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV @@ -104,22 +109,29 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b) +gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) { if (d->compat_tc_stats) { d->tc_stats.bytes = b->bytes; d->tc_stats.packets = b->packets; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_BASIC, b, sizeof(*b)); + if (d->tail) { + struct gnet_stats_basic sb; + memset(&sb, 0, sizeof(sb)); + sb.bytes = b->bytes; + sb.packets = b->packets; + return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb)); + } return 0; } +EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV * @d: dumping handle + * @b: basic statistics * @r: rate estimator statistics * * Appends the rate estimator statistics to the top level TLV created by @@ -129,18 +141,36 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic *b) * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r) +gnet_stats_copy_rate_est(struct gnet_dump *d, + const struct gnet_stats_basic_packed *b, + struct gnet_stats_rate_est64 *r) { + struct gnet_stats_rate_est est; + int res; + + if (b && !gen_estimator_active(b, r)) + return 0; + + est.bps = min_t(u64, UINT_MAX, r->bps); + /* we have some time before reaching 2^32 packets per second */ + est.pps = r->pps; + if (d->compat_tc_stats) { - d->tc_stats.bps = r->bps; - d->tc_stats.pps = r->pps; + d->tc_stats.bps = est.bps; + d->tc_stats.pps = est.pps; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_RATE_EST, r, sizeof(*r)); + if (d->tail) { + res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est)); + if (res < 0 || est.bps == r->bps) + return res; + /* emit 64bit stats only if needed */ + return gnet_stats_copy(d, TCA_STATS_RATE_EST64, r, sizeof(*r)); + } return 0; } +EXPORT_SYMBOL(gnet_stats_copy_rate_est); /** * gnet_stats_copy_queue - copy queue statistics into statistics TLV @@ -168,6 +198,7 @@ gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q) return 0; } +EXPORT_SYMBOL(gnet_stats_copy_queue); /** * gnet_stats_copy_app - copy application specific statistics into statistics TLV @@ -195,6 +226,7 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return 0; } +EXPORT_SYMBOL(gnet_stats_copy_app); /** * gnet_stats_finish_copy - finish dumping procedure @@ -212,7 +244,7 @@ int gnet_stats_finish_copy(struct gnet_dump *d) { if (d->tail) - d->tail->rta_len = d->skb->tail - (u8 *) d->tail; + d->tail->nla_len = skb_tail_pointer(d->skb) - (u8 *)d->tail; if (d->compat_tc_stats) if (gnet_stats_copy(d, d->compat_tc_stats, &d->tc_stats, @@ -228,12 +260,4 @@ gnet_stats_finish_copy(struct gnet_dump *d) spin_unlock_bh(d->lock); return 0; } - - -EXPORT_SYMBOL(gnet_stats_start_copy); -EXPORT_SYMBOL(gnet_stats_start_copy_compat); -EXPORT_SYMBOL(gnet_stats_copy_basic); -EXPORT_SYMBOL(gnet_stats_copy_rate_est); -EXPORT_SYMBOL(gnet_stats_copy_queue); -EXPORT_SYMBOL(gnet_stats_copy_app); EXPORT_SYMBOL(gnet_stats_finish_copy); diff --git a/net/core/iovec.c b/net/core/iovec.c index 65e4b56fbc7..e1ec45ab1e6 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -18,10 +18,8 @@ #include <linux/errno.h> #include <linux/module.h> -#include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/slab.h> #include <linux/net.h> #include <linux/in6.h> #include <asm/uaccess.h> @@ -37,13 +35,15 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, char *address, int mode) +int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode) { - int size, err, ct; - - if (m->msg_namelen) { + int size, ct, err; + + if (m->msg_name && m->msg_namelen) { if (mode == VERIFY_READ) { - err = move_addr_to_kernel(m->msg_name, m->msg_namelen, + void __user *namep; + namep = (void __user __force *) m->msg_name; + err = move_addr_to_kernel(namep, m->msg_namelen, address); if (err < 0) return err; @@ -51,102 +51,27 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, char *address, int mode) m->msg_name = address; } else { m->msg_name = NULL; + m->msg_namelen = 0; } size = m->msg_iovlen * sizeof(struct iovec); - if (copy_from_user(iov, m->msg_iov, size)) + if (copy_from_user(iov, (void __user __force *) m->msg_iov, size)) return -EFAULT; m->msg_iov = iov; err = 0; for (ct = 0; ct < m->msg_iovlen; ct++) { - err += iov[ct].iov_len; - /* - * Goal is not to verify user data, but to prevent returning - * negative value, which is interpreted as errno. - * Overflow is still possible, but it is harmless. - */ - if (err < 0) - return -EMSGSIZE; - } + size_t len = iov[ct].iov_len; - return err; -} - -/* - * Copy kernel to iovec. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, iov->iov_len, len); - if (copy_to_user(iov->iov_base, kdata, copy)) - return -EFAULT; - kdata += copy; - len -= copy; - iov->iov_len -= copy; - iov->iov_base += copy; + if (len > INT_MAX - err) { + len = INT_MAX - err; + iov[ct].iov_len = len; } - iov++; + err += len; } - return 0; -} - -/* - * Copy iovec to kernel. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, len, iov->iov_len); - if (copy_from_user(kdata, iov->iov_base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov->iov_base += copy; - iov->iov_len -= copy; - } - iov++; - } - - return 0; -} - -/* - * For use with ip_build_xmit - */ -int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, - int len) -{ - /* Skip over the finished iovecs */ - while (offset >= iov->iov_len) { - offset -= iov->iov_len; - iov++; - } - - while (len > 0) { - u8 __user *base = iov->iov_base + offset; - int copy = min_t(unsigned int, len, iov->iov_len - offset); - - offset = 0; - if (copy_from_user(kdata, base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov++; - } - - return 0; + return err; } /* @@ -158,9 +83,9 @@ int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, * call to this function will be unaligned also. */ int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, - int offset, unsigned int len, int *csump) + int offset, unsigned int len, __wsum *csump) { - int csum = *csump; + __wsum csum = *csump; int partial_cnt = 0, err = 0; /* Skip over the finished iovecs */ @@ -209,7 +134,7 @@ int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, if (partial_cnt) { copy -= partial_cnt; if (copy_from_user(kdata + copy, base + copy, - partial_cnt)) + partial_cnt)) goto out_fault; } } @@ -224,7 +149,7 @@ int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, kdata += copy + partial_cnt; iov++; } - *csump = csum; + *csump = csum; out: return err; @@ -232,8 +157,28 @@ out_fault: err = -EFAULT; goto out; } - EXPORT_SYMBOL(csum_partial_copy_fromiovecend); -EXPORT_SYMBOL(memcpy_fromiovec); -EXPORT_SYMBOL(memcpy_fromiovecend); -EXPORT_SYMBOL(memcpy_toiovec); + +unsigned long iov_pages(const struct iovec *iov, int offset, + unsigned long nr_segs) +{ + unsigned long seg, base; + int pages = 0, len, size; + + while (nr_segs && (offset >= iov->iov_len)) { + offset -= iov->iov_len; + ++iov; + --nr_segs; + } + + for (seg = 0; seg < nr_segs; seg++) { + base = (unsigned long)iov[seg].iov_base + offset; + len = iov[seg].iov_len - offset; + size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + pages += size; + offset = 0; + } + + return pages; +} +EXPORT_SYMBOL(iov_pages); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index d43d1201275..bd0767e6b2b 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -11,7 +11,6 @@ * */ -#include <linux/config.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/if.h> @@ -20,125 +19,235 @@ #include <linux/rtnetlink.h> #include <linux/jiffies.h> #include <linux/spinlock.h> -#include <linux/list.h> -#include <linux/slab.h> #include <linux/workqueue.h> #include <linux/bitops.h> #include <asm/types.h> enum lw_bits { - LW_RUNNING = 0, - LW_SE_USED + LW_URGENT = 0, }; static unsigned long linkwatch_flags; static unsigned long linkwatch_nextevent; -static void linkwatch_event(void *dummy); -static DECLARE_WORK(linkwatch_work, linkwatch_event, NULL); +static void linkwatch_event(struct work_struct *dummy); +static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); -struct lw_event { - struct list_head list; - struct net_device *dev; -}; +static unsigned char default_operstate(const struct net_device *dev) +{ + if (!netif_carrier_ok(dev)) + return (dev->ifindex != dev->iflink ? + IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN); -/* Avoid kmalloc() for most systems */ -static struct lw_event singleevent; + if (netif_dormant(dev)) + return IF_OPER_DORMANT; -/* Must be called with the rtnl semaphore held */ -void linkwatch_run_queue(void) + return IF_OPER_UP; +} + + +static void rfc2863_policy(struct net_device *dev) { - LIST_HEAD(head); - struct list_head *n, *next; + unsigned char operstate = default_operstate(dev); - spin_lock_irq(&lweventlist_lock); - list_splice_init(&lweventlist, &head); - spin_unlock_irq(&lweventlist_lock); + if (operstate == dev->operstate) + return; - list_for_each_safe(n, next, &head) { - struct lw_event *event = list_entry(n, struct lw_event, list); - struct net_device *dev = event->dev; + write_lock_bh(&dev_base_lock); - if (event == &singleevent) { - clear_bit(LW_SE_USED, &linkwatch_flags); - } else { - kfree(event); - } + switch(dev->link_mode) { + case IF_LINK_MODE_DORMANT: + if (operstate == IF_OPER_UP) + operstate = IF_OPER_DORMANT; + break; - /* We are about to handle this device, - * so new events can be accepted - */ - clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); + case IF_LINK_MODE_DEFAULT: + default: + break; + } - if (dev->flags & IFF_UP) { - if (netif_carrier_ok(dev)) { - WARN_ON(dev->qdisc_sleeping == &noop_qdisc); - dev_activate(dev); - } else - dev_deactivate(dev); + dev->operstate = operstate; - netdev_state_change(dev); - } + write_unlock_bh(&dev_base_lock); +} - dev_put(dev); - } -} +void linkwatch_init_dev(struct net_device *dev) +{ + /* Handle pre-registration link state changes */ + if (!netif_carrier_ok(dev) || netif_dormant(dev)) + rfc2863_policy(dev); +} -static void linkwatch_event(void *dummy) + +static bool linkwatch_urgent_event(struct net_device *dev) { - /* Limit the number of linkwatch events to one - * per second so that a runaway driver does not - * cause a storm of messages on the netlink - * socket - */ - linkwatch_nextevent = jiffies + HZ; - clear_bit(LW_RUNNING, &linkwatch_flags); - - rtnl_shlock(); - linkwatch_run_queue(); - rtnl_shunlock(); + if (!netif_running(dev)) + return false; + + if (dev->ifindex != dev->iflink) + return true; + + if (dev->priv_flags & IFF_TEAM_PORT) + return true; + + return netif_carrier_ok(dev) && qdisc_tx_changing(dev); } -void linkwatch_fire_event(struct net_device *dev) +static void linkwatch_add_event(struct net_device *dev) { - if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { - unsigned long flags; - struct lw_event *event; - - if (test_and_set_bit(LW_SE_USED, &linkwatch_flags)) { - event = kmalloc(sizeof(struct lw_event), GFP_ATOMIC); - - if (unlikely(event == NULL)) { - clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); - return; - } - } else { - event = &singleevent; - } + unsigned long flags; + spin_lock_irqsave(&lweventlist_lock, flags); + if (list_empty(&dev->link_watch_list)) { + list_add_tail(&dev->link_watch_list, &lweventlist); dev_hold(dev); - event->dev = dev; + } + spin_unlock_irqrestore(&lweventlist_lock, flags); +} + + +static void linkwatch_schedule_work(int urgent) +{ + unsigned long delay = linkwatch_nextevent - jiffies; + + if (test_bit(LW_URGENT, &linkwatch_flags)) + return; + + /* Minimise down-time: drop delay for up event. */ + if (urgent) { + if (test_and_set_bit(LW_URGENT, &linkwatch_flags)) + return; + delay = 0; + } + + /* If we wrap around we'll delay it by at most HZ. */ + if (delay > HZ) + delay = 0; + + /* + * If urgent, schedule immediate execution; otherwise, don't + * override the existing timer. + */ + if (test_bit(LW_URGENT, &linkwatch_flags)) + mod_delayed_work(system_wq, &linkwatch_work, 0); + else + schedule_delayed_work(&linkwatch_work, delay); +} + - spin_lock_irqsave(&lweventlist_lock, flags); - list_add_tail(&event->list, &lweventlist); - spin_unlock_irqrestore(&lweventlist_lock, flags); +static void linkwatch_do_dev(struct net_device *dev) +{ + /* + * Make sure the above read is complete since it can be + * rewritten as soon as we clear the bit below. + */ + smp_mb__before_atomic(); + + /* We are about to handle this device, + * so new events can be accepted + */ + clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); + + rfc2863_policy(dev); + if (dev->flags & IFF_UP) { + if (netif_carrier_ok(dev)) + dev_activate(dev); + else + dev_deactivate(dev); + + netdev_state_change(dev); + } + dev_put(dev); +} + +static void __linkwatch_run_queue(int urgent_only) +{ + struct net_device *dev; + LIST_HEAD(wrk); - if (!test_and_set_bit(LW_RUNNING, &linkwatch_flags)) { - unsigned long thisevent = jiffies; + /* + * Limit the number of linkwatch events to one + * per second so that a runaway driver does not + * cause a storm of messages on the netlink + * socket. This limit does not apply to up events + * while the device qdisc is down. + */ + if (!urgent_only) + linkwatch_nextevent = jiffies + HZ; + /* Limit wrap-around effect on delay. */ + else if (time_after(linkwatch_nextevent, jiffies + HZ)) + linkwatch_nextevent = jiffies; - if (thisevent >= linkwatch_nextevent) { - schedule_work(&linkwatch_work); - } else { - schedule_delayed_work(&linkwatch_work, linkwatch_nextevent - thisevent); - } + clear_bit(LW_URGENT, &linkwatch_flags); + + spin_lock_irq(&lweventlist_lock); + list_splice_init(&lweventlist, &wrk); + + while (!list_empty(&wrk)) { + + dev = list_first_entry(&wrk, struct net_device, link_watch_list); + list_del_init(&dev->link_watch_list); + + if (urgent_only && !linkwatch_urgent_event(dev)) { + list_add_tail(&dev->link_watch_list, &lweventlist); + continue; } + spin_unlock_irq(&lweventlist_lock); + linkwatch_do_dev(dev); + spin_lock_irq(&lweventlist_lock); } + + if (!list_empty(&lweventlist)) + linkwatch_schedule_work(0); + spin_unlock_irq(&lweventlist_lock); } +void linkwatch_forget_dev(struct net_device *dev) +{ + unsigned long flags; + int clean = 0; + + spin_lock_irqsave(&lweventlist_lock, flags); + if (!list_empty(&dev->link_watch_list)) { + list_del_init(&dev->link_watch_list); + clean = 1; + } + spin_unlock_irqrestore(&lweventlist_lock, flags); + if (clean) + linkwatch_do_dev(dev); +} + + +/* Must be called with the rtnl semaphore held */ +void linkwatch_run_queue(void) +{ + __linkwatch_run_queue(0); +} + + +static void linkwatch_event(struct work_struct *dummy) +{ + rtnl_lock(); + __linkwatch_run_queue(time_after(linkwatch_nextevent, jiffies)); + rtnl_unlock(); +} + + +void linkwatch_fire_event(struct net_device *dev) +{ + bool urgent = linkwatch_urgent_event(dev); + + if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { + linkwatch_add_event(dev); + } else if (!urgent) + return; + + linkwatch_schedule_work(urgent); +} EXPORT_SYMBOL(linkwatch_fire_event); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e68700f950a..ef31fef25e5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -15,54 +15,50 @@ * Harald Welte Add neighbour cache statistics like rtstat */ -#include <linux/config.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> -#include <linux/sched.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/times.h> +#include <net/net_namespace.h> #include <net/neighbour.h> #include <net/dst.h> #include <net/sock.h> +#include <net/netevent.h> +#include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> +#include <linux/log2.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> +#define DEBUG #define NEIGH_DEBUG 1 - -#define NEIGH_PRINTK(x...) printk(x) -#define NEIGH_NOPRINTK(x...) do { ; } while(0) -#define NEIGH_PRINTK0 NEIGH_PRINTK -#define NEIGH_PRINTK1 NEIGH_NOPRINTK -#define NEIGH_PRINTK2 NEIGH_NOPRINTK - -#if NEIGH_DEBUG >= 1 -#undef NEIGH_PRINTK1 -#define NEIGH_PRINTK1 NEIGH_PRINTK -#endif -#if NEIGH_DEBUG >= 2 -#undef NEIGH_PRINTK2 -#define NEIGH_PRINTK2 NEIGH_PRINTK -#endif +#define neigh_dbg(level, fmt, ...) \ +do { \ + if (level <= NEIGH_DEBUG) \ + pr_debug(fmt, ##__VA_ARGS__); \ +} while (0) #define PNEIGH_HASHMASK 0xF static void neigh_timer_handler(unsigned long arg); -#ifdef CONFIG_ARPD -static void neigh_app_notify(struct neighbour *n); -#endif +static void __neigh_notify(struct neighbour *n, int type, int flags); +static void neigh_update_notify(struct neighbour *neigh); static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); -void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); static struct neigh_table *neigh_tables; #ifdef CONFIG_PROC_FS -static struct file_operations neigh_stat_seq_fops; +static const struct file_operations neigh_stat_seq_fops; #endif /* @@ -98,12 +94,21 @@ static struct file_operations neigh_stat_seq_fops; static DEFINE_RWLOCK(neigh_tbl_lock); -static int neigh_blackhole(struct sk_buff *skb) +static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) { kfree_skb(skb); return -ENETDOWN; } +static void neigh_cleanup_and_release(struct neighbour *neigh) +{ + if (neigh->parms->neigh_cleanup) + neigh->parms->neigh_cleanup(neigh); + + __neigh_notify(neigh, RTM_DELNEIGH, 0); + neigh_release(neigh); +} + /* * It is random distribution in the interval (1/2)*base...(3/2)*base. * It corresponds to default IPv6 settings and is not overridable, @@ -112,23 +117,29 @@ static int neigh_blackhole(struct sk_buff *skb) unsigned long neigh_rand_reach_time(unsigned long base) { - return (base ? (net_random() % base) + (base >> 1) : 0); + return base ? (prandom_u32() % base) + (base >> 1) : 0; } +EXPORT_SYMBOL(neigh_rand_reach_time); static int neigh_forced_gc(struct neigh_table *tbl) { int shrunk = 0; int i; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); write_lock_bh(&tbl->lock); - for (i = 0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + for (i = 0; i < (1 << nht->hash_shift); i++) { + struct neighbour *n; + struct neighbour __rcu **np; - np = &tbl->hash_buckets[i]; - while ((n = *np) != NULL) { + np = &nht->hash_buckets[i]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { /* Neighbour record may be discarded if: * - nobody refers to it. * - it is not permanent @@ -136,11 +147,13 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & NUD_PERMANENT)) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); n->dead = 1; shrunk = 1; write_unlock(&n->lock); - neigh_release(n); + neigh_cleanup_and_release(n); continue; } write_unlock(&n->lock); @@ -155,6 +168,16 @@ static int neigh_forced_gc(struct neigh_table *tbl) return shrunk; } +static void neigh_add_timer(struct neighbour *n, unsigned long when) +{ + neigh_hold(n); + if (unlikely(mod_timer(&n->timer, when))) { + printk("NEIGH: BUG, double timer add, state is %x\n", + n->nud_state); + dump_stack(); + } +} + static int neigh_del_timer(struct neighbour *n) { if ((n->nud_state & NUD_IN_TIMER) && @@ -178,16 +201,24 @@ static void pneigh_queue_purge(struct sk_buff_head *list) static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) { int i; + struct neigh_hash_table *nht; - for (i = 0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np = &tbl->hash_buckets[i]; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); - while ((n = *np) != NULL) { + for (i = 0; i < (1 << nht->hash_shift); i++) { + struct neighbour *n; + struct neighbour __rcu **np = &nht->hash_buckets[i]; + + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { if (dev && n->dev != dev) { np = &n->next; continue; } - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); write_lock(&n->lock); neigh_del_timer(n); n->dead = 1; @@ -202,16 +233,17 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) we must kill timers etc. and move it to safe state. */ - skb_queue_purge(&n->arp_queue); + __skb_queue_purge(&n->arp_queue); + n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else n->nud_state = NUD_NONE; - NEIGH_PRINTK2("neigh %p is stray.\n", n); + neigh_dbg(2, "neigh %p is stray\n", n); } write_unlock(&n->lock); - neigh_release(n); + neigh_cleanup_and_release(n); } } } @@ -222,6 +254,7 @@ void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) neigh_flush_dev(tbl, dev); write_unlock_bh(&tbl->lock); } +EXPORT_SYMBOL(neigh_changeaddr); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { @@ -234,8 +267,9 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) pneigh_queue_purge(&tbl->proxy_queue); return 0; } +EXPORT_SYMBOL(neigh_ifdown); -static struct neighbour *neigh_alloc(struct neigh_table *tbl) +static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -250,21 +284,19 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl) goto out_entries; } - n = kmem_cache_alloc(tbl->kmem_cachep, SLAB_ATOMIC); + n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; - memset(n, 0, tbl->entry_size); - - skb_queue_head_init(&n->arp_queue); + __skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); + seqlock_init(&n->ha_lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; + seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); - init_timer(&n->timer); - n->timer.function = neigh_timer_handler; - n->timer.data = (unsigned long)n; + setup_timer(&n->timer, neigh_timer_handler, (unsigned long)n); NEIGH_CACHE_STAT_INC(tbl, allocs); n->tbl = tbl; @@ -278,67 +310,93 @@ out_entries: goto out; } -static struct neighbour **neigh_hash_alloc(unsigned int entries) +static void neigh_get_hash_rnd(u32 *x) { - unsigned long size = entries * sizeof(struct neighbour *); - struct neighbour **ret; + get_random_bytes(x, sizeof(*x)); + *x |= 1; +} - if (size <= PAGE_SIZE) { - ret = kmalloc(size, GFP_ATOMIC); - } else { - ret = (struct neighbour **) - __get_free_pages(GFP_ATOMIC, get_order(size)); - } - if (ret) - memset(ret, 0, size); +static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) +{ + size_t size = (1 << shift) * sizeof(struct neighbour *); + struct neigh_hash_table *ret; + struct neighbour __rcu **buckets; + int i; + ret = kmalloc(sizeof(*ret), GFP_ATOMIC); + if (!ret) + return NULL; + if (size <= PAGE_SIZE) + buckets = kzalloc(size, GFP_ATOMIC); + else + buckets = (struct neighbour __rcu **) + __get_free_pages(GFP_ATOMIC | __GFP_ZERO, + get_order(size)); + if (!buckets) { + kfree(ret); + return NULL; + } + ret->hash_buckets = buckets; + ret->hash_shift = shift; + for (i = 0; i < NEIGH_NUM_HASH_RND; i++) + neigh_get_hash_rnd(&ret->hash_rnd[i]); return ret; } -static void neigh_hash_free(struct neighbour **hash, unsigned int entries) +static void neigh_hash_free_rcu(struct rcu_head *head) { - unsigned long size = entries * sizeof(struct neighbour *); + struct neigh_hash_table *nht = container_of(head, + struct neigh_hash_table, + rcu); + size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *); + struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) - kfree(hash); + kfree(buckets); else - free_pages((unsigned long)hash, get_order(size)); + free_pages((unsigned long)buckets, get_order(size)); + kfree(nht); } -static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries) +static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, + unsigned long new_shift) { - struct neighbour **new_hash, **old_hash; - unsigned int i, new_hash_mask, old_entries; + unsigned int i, hash; + struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); - BUG_ON(new_entries & (new_entries - 1)); - new_hash = neigh_hash_alloc(new_entries); - if (!new_hash) - return; - - old_entries = tbl->hash_mask + 1; - new_hash_mask = new_entries - 1; - old_hash = tbl->hash_buckets; + old_nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + new_nht = neigh_hash_alloc(new_shift); + if (!new_nht) + return old_nht; - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); - for (i = 0; i < old_entries; i++) { + for (i = 0; i < (1 << old_nht->hash_shift); i++) { struct neighbour *n, *next; - for (n = old_hash[i]; n; n = next) { - unsigned int hash_val = tbl->hash(n->primary_key, n->dev); - - hash_val &= new_hash_mask; - next = n->next; - - n->next = new_hash[hash_val]; - new_hash[hash_val] = n; + for (n = rcu_dereference_protected(old_nht->hash_buckets[i], + lockdep_is_held(&tbl->lock)); + n != NULL; + n = next) { + hash = tbl->hash(n->primary_key, n->dev, + new_nht->hash_rnd); + + hash >>= (32 - new_nht->hash_shift); + next = rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock)); + + rcu_assign_pointer(n->next, + rcu_dereference_protected( + new_nht->hash_buckets[hash], + lockdep_is_held(&tbl->lock))); + rcu_assign_pointer(new_nht->hash_buckets[hash], n); } } - tbl->hash_buckets = new_hash; - tbl->hash_mask = new_hash_mask; - neigh_hash_free(old_hash, old_entries); + rcu_assign_pointer(tbl->nht, new_nht); + call_rcu(&old_nht->rcu, neigh_hash_free_rcu); + return new_nht; } struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, @@ -346,49 +404,70 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, { struct neighbour *n; int key_len = tbl->key_len; - u32 hash_val = tbl->hash(pkey, dev) & tbl->hash_mask; - + u32 hash_val; + struct neigh_hash_table *nht; + NEIGH_CACHE_STAT_INC(tbl, lookups); - read_lock_bh(&tbl->lock); - for (n = tbl->hash_buckets[hash_val]; n; n = n->next) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { - neigh_hold(n); + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; } } - read_unlock_bh(&tbl->lock); + + rcu_read_unlock_bh(); return n; } +EXPORT_SYMBOL(neigh_lookup); -struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, const void *pkey) +struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, + const void *pkey) { struct neighbour *n; int key_len = tbl->key_len; - u32 hash_val = tbl->hash(pkey, NULL) & tbl->hash_mask; + u32 hash_val; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); - read_lock_bh(&tbl->lock); - for (n = tbl->hash_buckets[hash_val]; n; n = n->next) { - if (!memcmp(n->primary_key, pkey, key_len)) { - neigh_hold(n); + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift); + + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { + if (!memcmp(n->primary_key, pkey, key_len) && + net_eq(dev_net(n->dev), net)) { + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; } } - read_unlock_bh(&tbl->lock); + + rcu_read_unlock_bh(); return n; } +EXPORT_SYMBOL(neigh_lookup_nodev); -struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, - struct net_device *dev) +struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, bool want_ref) { u32 hash_val; int key_len = tbl->key_len; int error; - struct neighbour *n1, *rc, *n = neigh_alloc(tbl); + struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev); + struct neigh_hash_table *nht; if (!n) { rc = ERR_PTR(-ENOBUFS); @@ -405,6 +484,14 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, goto out_neigh_release; } + if (dev->netdev_ops->ndo_neigh_construct) { + error = dev->netdev_ops->ndo_neigh_construct(n); + if (error < 0) { + rc = ERR_PTR(error); + goto out_neigh_release; + } + } + /* Device specific setup. */ if (n->parms->neigh_setup && (error = n->parms->neigh_setup(n)) < 0) { @@ -412,34 +499,44 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, goto out_neigh_release; } - n->confirmed = jiffies - (n->parms->base_reachable_time << 1); + n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) > (tbl->hash_mask + 1)) - neigh_hash_grow(tbl, (tbl->hash_mask + 1) << 1); + if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) + nht = neigh_hash_grow(tbl, nht->hash_shift + 1); - hash_val = tbl->hash(pkey, dev) & tbl->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); goto out_tbl_unlock; } - for (n1 = tbl->hash_buckets[hash_val]; n1; n1 = n1->next) { + for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val], + lockdep_is_held(&tbl->lock)); + n1 != NULL; + n1 = rcu_dereference_protected(n1->next, + lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { - neigh_hold(n1); + if (want_ref) + neigh_hold(n1); rc = n1; goto out_tbl_unlock; } } - n->next = tbl->hash_buckets[hash_val]; - tbl->hash_buckets[hash_val] = n; n->dead = 0; - neigh_hold(n); + if (want_ref) + neigh_hold(n); + rcu_assign_pointer(n->next, + rcu_dereference_protected(nht->hash_buckets[hash_val], + lockdep_is_held(&tbl->lock))); + rcu_assign_pointer(nht->hash_buckets[hash_val], n); write_unlock_bh(&tbl->lock); - NEIGH_PRINTK2("neigh %p is created.\n", n); + neigh_dbg(2, "neigh %p is created\n", n); rc = n; out: return rc; @@ -449,37 +546,68 @@ out_neigh_release: neigh_release(n); goto out; } +EXPORT_SYMBOL(__neigh_create); -struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey, - struct net_device *dev, int creat) +static u32 pneigh_hash(const void *pkey, int key_len) { - struct pneigh_entry *n; - int key_len = tbl->key_len; u32 hash_val = *(u32 *)(pkey + key_len - 4); - hash_val ^= (hash_val >> 16); hash_val ^= hash_val >> 8; hash_val ^= hash_val >> 4; hash_val &= PNEIGH_HASHMASK; + return hash_val; +} - read_lock_bh(&tbl->lock); - - for (n = tbl->phash_buckets[hash_val]; n; n = n->next) { +static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, + struct net *net, + const void *pkey, + int key_len, + struct net_device *dev) +{ + while (n) { if (!memcmp(n->key, pkey, key_len) && - (n->dev == dev || !n->dev)) { - read_unlock_bh(&tbl->lock); - goto out; - } + net_eq(pneigh_net(n), net) && + (n->dev == dev || !n->dev)) + return n; + n = n->next; } + return NULL; +} + +struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, + struct net *net, const void *pkey, struct net_device *dev) +{ + int key_len = tbl->key_len; + u32 hash_val = pneigh_hash(pkey, key_len); + + return __pneigh_lookup_1(tbl->phash_buckets[hash_val], + net, pkey, key_len, dev); +} +EXPORT_SYMBOL_GPL(__pneigh_lookup); + +struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, + struct net *net, const void *pkey, + struct net_device *dev, int creat) +{ + struct pneigh_entry *n; + int key_len = tbl->key_len; + u32 hash_val = pneigh_hash(pkey, key_len); + + read_lock_bh(&tbl->lock); + n = __pneigh_lookup_1(tbl->phash_buckets[hash_val], + net, pkey, key_len, dev); read_unlock_bh(&tbl->lock); - n = NULL; - if (!creat) + + if (n || !creat) goto out; + ASSERT_RTNL(); + n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; + write_pnet(&n->net, hold_net(net)); memcpy(n->key, pkey, key_len); n->dev = dev; if (dev) @@ -488,6 +616,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey, if (tbl->pconstructor && tbl->pconstructor(n)) { if (dev) dev_put(dev); + release_net(net); kfree(n); n = NULL; goto out; @@ -500,30 +629,28 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey, out: return n; } +EXPORT_SYMBOL(pneigh_lookup); -int pneigh_delete(struct neigh_table *tbl, const void *pkey, +int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { struct pneigh_entry *n, **np; int key_len = tbl->key_len; - u32 hash_val = *(u32 *)(pkey + key_len - 4); - - hash_val ^= (hash_val >> 16); - hash_val ^= hash_val >> 8; - hash_val ^= hash_val >> 4; - hash_val &= PNEIGH_HASHMASK; + u32 hash_val = pneigh_hash(pkey, key_len); write_lock_bh(&tbl->lock); for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL; np = &n->next) { - if (!memcmp(n->key, pkey, key_len) && n->dev == dev) { + if (!memcmp(n->key, pkey, key_len) && n->dev == dev && + net_eq(pneigh_net(n), net)) { *np = n->next; write_unlock_bh(&tbl->lock); if (tbl->pdestructor) tbl->pdestructor(n); if (n->dev) dev_put(n->dev); + release_net(pneigh_net(n)); kfree(n); return 0; } @@ -546,6 +673,7 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) tbl->pdestructor(n); if (n->dev) dev_put(n->dev); + release_net(pneigh_net(n)); kfree(n); continue; } @@ -555,6 +683,13 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) return -ENOENT; } +static void neigh_parms_destroy(struct neigh_parms *parms); + +static inline void neigh_parms_put(struct neigh_parms *parms) +{ + if (atomic_dec_and_test(&parms->refcnt)) + neigh_parms_destroy(parms); +} /* * neighbour must already be out of the table; @@ -562,43 +697,36 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) */ void neigh_destroy(struct neighbour *neigh) { - struct hh_cache *hh; + struct net_device *dev = neigh->dev; NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { - printk(KERN_WARNING - "Destroying alive neighbour %p\n", neigh); + pr_warn("Destroying alive neighbour %p\n", neigh); dump_stack(); return; } if (neigh_del_timer(neigh)) - printk(KERN_WARNING "Impossible event.\n"); + pr_warn("Impossible event\n"); - while ((hh = neigh->hh) != NULL) { - neigh->hh = hh->hh_next; - hh->hh_next = NULL; - write_lock_bh(&hh->hh_lock); - hh->hh_output = neigh_blackhole; - write_unlock_bh(&hh->hh_lock); - if (atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); - } - - if (neigh->ops && neigh->ops->destructor) - (neigh->ops->destructor)(neigh); + write_lock_bh(&neigh->lock); + __skb_queue_purge(&neigh->arp_queue); + write_unlock_bh(&neigh->lock); + neigh->arp_queue_len_bytes = 0; - skb_queue_purge(&neigh->arp_queue); + if (dev->netdev_ops->ndo_neigh_destroy) + dev->netdev_ops->ndo_neigh_destroy(neigh); - dev_put(neigh->dev); + dev_put(dev); neigh_parms_put(neigh->parms); - NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh); + neigh_dbg(2, "neigh %p is destroyed\n", neigh); atomic_dec(&neigh->tbl->entries); - kmem_cache_free(neigh->tbl->kmem_cachep, neigh); + kfree_rcu(neigh, rcu); } +EXPORT_SYMBOL(neigh_destroy); /* Neighbour state is suspicious; disable fast path. @@ -607,14 +735,9 @@ void neigh_destroy(struct neighbour *neigh) */ static void neigh_suspect(struct neighbour *neigh) { - struct hh_cache *hh; - - NEIGH_PRINTK2("neigh %p is suspected.\n", neigh); + neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->output = neigh->ops->output; - - for (hh = neigh->hh; hh; hh = hh->hh_next) - hh->hh_output = neigh->ops->output; } /* Neighbour state is OK; @@ -624,99 +747,137 @@ static void neigh_suspect(struct neighbour *neigh) */ static void neigh_connect(struct neighbour *neigh) { - struct hh_cache *hh; - - NEIGH_PRINTK2("neigh %p is connected.\n", neigh); + neigh_dbg(2, "neigh %p is connected\n", neigh); neigh->output = neigh->ops->connected_output; - - for (hh = neigh->hh; hh; hh = hh->hh_next) - hh->hh_output = neigh->ops->hh_output; } -static void neigh_periodic_timer(unsigned long arg) +static void neigh_periodic_work(struct work_struct *work) { - struct neigh_table *tbl = (struct neigh_table *)arg; - struct neighbour *n, **np; - unsigned long expire, now = jiffies; + struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); + struct neighbour *n; + struct neighbour __rcu **np; + unsigned int i; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); - write_lock(&tbl->lock); + write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); /* * periodically recompute ReachableTime from random function */ - if (time_after(now, tbl->last_rand + 300 * HZ)) { + if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; - tbl->last_rand = now; + tbl->last_rand = jiffies; for (p = &tbl->parms; p; p = p->next) p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } - np = &tbl->hash_buckets[tbl->hash_chain_gc]; - tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask); + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + + for (i = 0 ; i < (1 << nht->hash_shift); i++) { + np = &nht->hash_buckets[i]; - while ((n = *np) != NULL) { - unsigned int state; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { + unsigned int state; - write_lock(&n->lock); + write_lock(&n->lock); - state = n->nud_state; - if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { - write_unlock(&n->lock); - goto next_elt; - } + state = n->nud_state; + if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { + write_unlock(&n->lock); + goto next_elt; + } - if (time_before(n->used, n->confirmed)) - n->used = n->confirmed; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; - if (atomic_read(&n->refcnt) == 1 && - (state == NUD_FAILED || - time_after(now, n->used + n->parms->gc_staletime))) { - *np = n->next; - n->dead = 1; + if (atomic_read(&n->refcnt) == 1 && + (state == NUD_FAILED || + time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + *np = n->next; + n->dead = 1; + write_unlock(&n->lock); + neigh_cleanup_and_release(n); + continue; + } write_unlock(&n->lock); - neigh_release(n); - continue; - } - write_unlock(&n->lock); next_elt: - np = &n->next; + np = &n->next; + } + /* + * It's fine to release lock here, even if hash table + * grows while we are preempted. + */ + write_unlock_bh(&tbl->lock); + cond_resched(); + write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); } - - /* Cycle through all hash buckets every base_reachable_time/2 ticks. - * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 - * base_reachable_time. +out: + /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks. + * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2 + * BASE_REACHABLE_TIME. */ - expire = tbl->parms.base_reachable_time >> 1; - expire /= (tbl->hash_mask + 1); - if (!expire) - expire = 1; - - mod_timer(&tbl->gc_timer, now + expire); - - write_unlock(&tbl->lock); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); + write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE ? - p->ucast_probes : - p->ucast_probes + p->app_probes + 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 inline void neigh_add_timer(struct neighbour *n, unsigned long when) +static void neigh_invalidate(struct neighbour *neigh) + __releases(neigh->lock) + __acquires(neigh->lock) { - if (unlikely(mod_timer(&n->timer, when))) { - printk("NEIGH: BUG, double timer add, state is %x\n", - n->nud_state); - dump_stack(); + struct sk_buff *skb; + + NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); + neigh_dbg(2, "neigh %p is failed\n", neigh); + neigh->updated = jiffies; + + /* It is very thin place. report_unreachable is very complicated + routine. Particularly, it can hit the same neighbour entry! + + So that, we try to be accurate and avoid dead loop. --ANK + */ + while (neigh->nud_state == NUD_FAILED && + (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { + write_unlock(&neigh->lock); + neigh->ops->error_report(neigh, skb); + write_lock(&neigh->lock); } + __skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; +} + +static void neigh_probe(struct neighbour *neigh) + __releases(neigh->lock) +{ + struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); + /* keep skb alive even if arp_queue overflows */ + if (skb) + skb = skb_copy(skb, GFP_ATOMIC); + write_unlock(&neigh->lock); + neigh->ops->solicit(neigh, skb); + atomic_inc(&neigh->probes); + kfree_skb(skb); } /* Called when a timer expires for a neighbour entry. */ @@ -725,7 +886,7 @@ static void neigh_timer_handler(unsigned long arg) { unsigned long now, next; struct neighbour *neigh = (struct neighbour *)arg; - unsigned state; + unsigned int state; int notify = 0; write_lock(&neigh->lock); @@ -734,68 +895,57 @@ static void neigh_timer_handler(unsigned long arg) now = jiffies; next = now + HZ; - if (!(state & NUD_IN_TIMER)) { -#ifndef CONFIG_SMP - printk(KERN_WARNING "neigh: timer & !nud_in_timer\n"); -#endif + if (!(state & NUD_IN_TIMER)) goto out; - } if (state & NUD_REACHABLE) { - if (time_before_eq(now, + if (time_before_eq(now, neigh->confirmed + neigh->parms->reachable_time)) { - NEIGH_PRINTK2("neigh %p is still alive.\n", neigh); + neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, - neigh->used + neigh->parms->delay_probe_time)) { - NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); + neigh->used + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { + neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; + neigh->updated = jiffies; neigh_suspect(neigh); - next = now + neigh->parms->delay_probe_time; + next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { - NEIGH_PRINTK2("neigh %p is suspected.\n", neigh); + neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; + neigh->updated = jiffies; neigh_suspect(neigh); + notify = 1; } } else if (state & NUD_DELAY) { - if (time_before_eq(now, - neigh->confirmed + neigh->parms->delay_probe_time)) { - NEIGH_PRINTK2("neigh %p is now reachable.\n", neigh); + if (time_before_eq(now, + neigh->confirmed + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { + neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; + neigh->updated = jiffies; neigh_connect(neigh); + notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { - NEIGH_PRINTK2("neigh %p is probed.\n", neigh); + neigh_dbg(2, "neigh %p is probed\n", neigh); neigh->nud_state = NUD_PROBE; + neigh->updated = jiffies; atomic_set(&neigh->probes, 0); - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { - struct sk_buff *skb; - neigh->nud_state = NUD_FAILED; notify = 1; - NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); - NEIGH_PRINTK2("neigh %p is failed.\n", neigh); - - /* It is very thin place. report_unreachable is very complicated - routine. Particularly, it can hit the same neighbour entry! - - So that, we try to be accurate and avoid dead loop. --ANK - */ - while (neigh->nud_state == NUD_FAILED && - (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - write_unlock(&neigh->lock); - neigh->ops->error_report(neigh, skb); - write_lock(&neigh->lock); - } - skb_queue_purge(&neigh->arp_queue); + neigh_invalidate(neigh); + goto out; } if (neigh->nud_state & NUD_IN_TIMER) { @@ -805,31 +955,22 @@ static void neigh_timer_handler(unsigned long arg) neigh_hold(neigh); } if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) { - struct sk_buff *skb = skb_peek(&neigh->arp_queue); - /* keep skb alive even if arp_queue overflows */ - if (skb) - skb_get(skb); - write_unlock(&neigh->lock); - neigh->ops->solicit(neigh, skb); - atomic_inc(&neigh->probes); - if (skb) - kfree_skb(skb); + neigh_probe(neigh); } else { out: write_unlock(&neigh->lock); } -#ifdef CONFIG_ARPD - if (notify && neigh->parms->app_probes) - neigh_app_notify(neigh); -#endif + if (notify) + neigh_update_notify(neigh); + neigh_release(neigh); } int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { int rc; - unsigned long now; + bool immediate_probe = false; write_lock_bh(&neigh->lock); @@ -837,59 +978,79 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; - now = jiffies; - if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { - if (neigh->parms->mcast_probes + neigh->parms->app_probes) { - atomic_set(&neigh->probes, neigh->parms->ucast_probes); + if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + + NEIGH_VAR(neigh->parms, APP_PROBES)) { + unsigned long next, now = jiffies; + + atomic_set(&neigh->probes, + NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh->nud_state = NUD_INCOMPLETE; - neigh_hold(neigh); - neigh_add_timer(neigh, now + 1); + neigh->updated = now; + next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), + HZ/2); + neigh_add_timer(neigh, next); + immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; + neigh->updated = jiffies; write_unlock_bh(&neigh->lock); - if (skb) - kfree_skb(skb); + kfree_skb(skb); return 1; } } else if (neigh->nud_state & NUD_STALE) { - NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); - neigh_hold(neigh); + neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; - neigh_add_timer(neigh, - jiffies + neigh->parms->delay_probe_time); + neigh->updated = jiffies; + neigh_add_timer(neigh, jiffies + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { - if (skb_queue_len(&neigh->arp_queue) >= - neigh->parms->queue_len) { + while (neigh->arp_queue_len_bytes + skb->truesize > + NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; - buff = neigh->arp_queue.next; - __skb_unlink(buff, &neigh->arp_queue); + + buff = __skb_dequeue(&neigh->arp_queue); + if (!buff) + break; + neigh->arp_queue_len_bytes -= buff->truesize; kfree_skb(buff); + NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } + skb_dst_force(skb); __skb_queue_tail(&neigh->arp_queue, skb); + neigh->arp_queue_len_bytes += skb->truesize; } rc = 1; } out_unlock_bh: - write_unlock_bh(&neigh->lock); + if (immediate_probe) + neigh_probe(neigh); + else + write_unlock(&neigh->lock); + local_bh_enable(); return rc; } +EXPORT_SYMBOL(__neigh_event_send); -static __inline__ void neigh_update_hhs(struct neighbour *neigh) +static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; - void (*update)(struct hh_cache*, struct net_device*, unsigned char *) = - neigh->dev->header_cache_update; + void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) + = NULL; + + if (neigh->dev->header_ops) + update = neigh->dev->header_ops->cache_update; if (update) { - for (hh = neigh->hh; hh; hh = hh->hh_next) { - write_lock_bh(&hh->hh_lock); + hh = &neigh->hh; + if (hh->hh_len) { + write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); - write_unlock_bh(&hh->hh_lock); + write_sequnlock_bh(&hh->hh_lock); } } } @@ -903,13 +1064,13 @@ static __inline__ void neigh_update_hhs(struct neighbour *neigh) NEIGH_UPDATE_F_OVERRIDE allows to override existing lladdr, if it is different. NEIGH_UPDATE_F_WEAK_OVERRIDE will suspect existing "connected" - lladdr instead of overriding it + lladdr instead of overriding it if it is different. It also allows to retain current state if lladdr is unchanged. NEIGH_UPDATE_F_ADMIN means that the change is administrative. - NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing + NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as a router. @@ -922,9 +1083,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, { u8 old; int err; -#ifdef CONFIG_ARPD int notify = 0; -#endif struct net_device *dev; int update_isrouter = 0; @@ -934,7 +1093,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, old = neigh->nud_state; err = -EPERM; - if (!(flags & NEIGH_UPDATE_F_ADMIN) && + if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; @@ -944,9 +1103,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_suspect(neigh); neigh->nud_state = new; err = 0; -#ifdef CONFIG_ARPD notify = old & NUD_VALID; -#endif + if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && + (new & NUD_FAILED)) { + neigh_invalidate(neigh); + notify = 1; + } goto out; } @@ -960,7 +1122,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, - compare new & old - if they are different, check override flag */ - if ((old & NUD_VALID) && + if ((old & NUD_VALID) && !memcmp(lladdr, neigh->ha, dev->addr_len)) lladdr = neigh->ha; } else { @@ -1002,25 +1164,24 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (new != old) { neigh_del_timer(neigh); - if (new & NUD_IN_TIMER) { - neigh_hold(neigh); - neigh_add_timer(neigh, (jiffies + - ((new & NUD_REACHABLE) ? + if (new & NUD_IN_TIMER) + neigh_add_timer(neigh, (jiffies + + ((new & NUD_REACHABLE) ? neigh->parms->reachable_time : 0))); - } neigh->nud_state = new; + notify = 1; } if (lladdr != neigh->ha) { + write_seqlock(&neigh->ha_lock); memcpy(&neigh->ha, lladdr, dev->addr_len); + write_sequnlock(&neigh->ha_lock); neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - - (neigh->parms->base_reachable_time << 1); -#ifdef CONFIG_ARPD + (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; -#endif } if (new == old) goto out; @@ -1035,15 +1196,34 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, while (neigh->nud_state & NUD_VALID && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - struct neighbour *n1 = neigh; + struct dst_entry *dst = skb_dst(skb); + struct neighbour *n2, *n1 = neigh; write_unlock_bh(&neigh->lock); - /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb->dst && skb->dst->neighbour) - n1 = skb->dst->neighbour; - n1->output(skb); + + rcu_read_lock(); + + /* Why not just use 'neigh' as-is? The problem is that + * things such as shaper, eql, and sch_teql can end up + * using alternative, different, neigh objects to output + * the packet in the output path. So what we need to do + * here is re-lookup the top-level neigh in the path so + * we can reinject the packet there. + */ + n2 = NULL; + if (dst) { + n2 = dst_neigh_lookup_skb(dst, skb); + if (n2) + n1 = n2; + } + n1->output(n1, skb); + if (n2) + neigh_release(n2); + rcu_read_unlock(); + write_lock_bh(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; } out: if (update_isrouter) { @@ -1052,12 +1232,28 @@ out: (neigh->flags & ~NTF_ROUTER); } write_unlock_bh(&neigh->lock); -#ifdef CONFIG_ARPD - if (notify && neigh->parms->app_probes) - neigh_app_notify(neigh); -#endif + + if (notify) + neigh_update_notify(neigh); + return err; } +EXPORT_SYMBOL(neigh_update); + +/* Update the neigh to listen temporarily for probe responses, even if it is + * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. + */ +void __neigh_set_probe_once(struct neighbour *neigh) +{ + neigh->updated = jiffies; + if (!(neigh->nud_state & NUD_FAILED)) + return; + neigh->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); + neigh_add_timer(neigh, + jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); +} +EXPORT_SYMBOL(__neigh_set_probe_once); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, @@ -1066,158 +1262,145 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, struct neighbour *neigh = __neigh_lookup(tbl, saddr, dev, lladdr || !dev->addr_len); if (neigh) - neigh_update(neigh, lladdr, NUD_STALE, + neigh_update(neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_OVERRIDE); return neigh; } +EXPORT_SYMBOL(neigh_event_ns); -static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, - u16 protocol) +/* called with read_lock_bh(&n->lock); */ +static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst) { - struct hh_cache *hh; struct net_device *dev = dst->dev; + __be16 prot = dst->ops->protocol; + struct hh_cache *hh = &n->hh; - for (hh = n->hh; hh; hh = hh->hh_next) - if (hh->hh_type == protocol) - break; + write_lock_bh(&n->lock); - if (!hh && (hh = kmalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) { - memset(hh, 0, sizeof(struct hh_cache)); - rwlock_init(&hh->hh_lock); - hh->hh_type = protocol; - atomic_set(&hh->hh_refcnt, 0); - hh->hh_next = NULL; - if (dev->hard_header_cache(n, hh)) { - kfree(hh); - hh = NULL; - } else { - atomic_inc(&hh->hh_refcnt); - hh->hh_next = n->hh; - n->hh = hh; - if (n->nud_state & NUD_CONNECTED) - hh->hh_output = n->ops->hh_output; - else - hh->hh_output = n->ops->output; - } - } - if (hh) { - atomic_inc(&hh->hh_refcnt); - dst->hh = hh; - } + /* Only one thread can come in here and initialize the + * hh_cache entry. + */ + if (!hh->hh_len) + dev->header_ops->cache(n, hh, prot); + + write_unlock_bh(&n->lock); } /* This function can be used in contexts, where only old dev_queue_xmit - worked, f.e. if you want to override normal output path (eql, shaper), - but resolution is not made yet. + * worked, f.e. if you want to override normal output path (eql, shaper), + * but resolution is not made yet. */ -int neigh_compat_output(struct sk_buff *skb) +int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) { struct net_device *dev = skb->dev; - __skb_pull(skb, skb->nh.raw - skb->data); + __skb_pull(skb, skb_network_offset(skb)); - if (dev->hard_header && - dev->hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, - skb->len) < 0 && - dev->rebuild_header(skb)) + if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, + skb->len) < 0 && + dev_rebuild_header(skb)) return 0; return dev_queue_xmit(skb); } +EXPORT_SYMBOL(neigh_compat_output); /* Slow and careful. */ -int neigh_resolve_output(struct sk_buff *skb) +int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; - struct neighbour *neigh; + struct dst_entry *dst = skb_dst(skb); int rc = 0; - if (!dst || !(neigh = dst->neighbour)) + if (!dst) goto discard; - __skb_pull(skb, skb->nh.raw - skb->data); - if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; - if (dev->hard_header_cache && !dst->hh) { - write_lock_bh(&neigh->lock); - if (!dst->hh) - neigh_hh_init(neigh, dst, dst->ops->protocol); - err = dev->hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - write_unlock_bh(&neigh->lock); - } else { - read_lock_bh(&neigh->lock); - err = dev->hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - read_unlock_bh(&neigh->lock); - } + unsigned int seq; + + if (dev->header_ops->cache && !neigh->hh.hh_len) + neigh_hh_init(neigh, dst); + + do { + __skb_pull(skb, skb_network_offset(skb)); + seq = read_seqbegin(&neigh->ha_lock); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); + } while (read_seqretry(&neigh->ha_lock, seq)); + if (err >= 0) - rc = neigh->ops->queue_xmit(skb); + rc = dev_queue_xmit(skb); else goto out_kfree_skb; } out: return rc; discard: - NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n", - dst, dst ? dst->neighbour : NULL); + neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh); out_kfree_skb: rc = -EINVAL; kfree_skb(skb); goto out; } +EXPORT_SYMBOL(neigh_resolve_output); /* As fast as possible without hh cache */ -int neigh_connected_output(struct sk_buff *skb) +int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb) { - int err; - struct dst_entry *dst = skb->dst; - struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; + unsigned int seq; + int err; - __skb_pull(skb, skb->nh.raw - skb->data); + do { + __skb_pull(skb, skb_network_offset(skb)); + seq = read_seqbegin(&neigh->ha_lock); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); + } while (read_seqretry(&neigh->ha_lock, seq)); - read_lock_bh(&neigh->lock); - err = dev->hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - read_unlock_bh(&neigh->lock); if (err >= 0) - err = neigh->ops->queue_xmit(skb); + err = dev_queue_xmit(skb); else { err = -EINVAL; kfree_skb(skb); } return err; } +EXPORT_SYMBOL(neigh_connected_output); + +int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) +{ + return dev_queue_xmit(skb); +} +EXPORT_SYMBOL(neigh_direct_output); static void neigh_proxy_process(unsigned long arg) { struct neigh_table *tbl = (struct neigh_table *)arg; long sched_next = 0; unsigned long now = jiffies; - struct sk_buff *skb; + struct sk_buff *skb, *n; spin_lock(&tbl->proxy_queue.lock); - skb = tbl->proxy_queue.next; - - while (skb != (struct sk_buff *)&tbl->proxy_queue) { - struct sk_buff *back = skb; - long tdif = NEIGH_CB(back)->sched_next - now; + skb_queue_walk_safe(&tbl->proxy_queue, skb, n) { + long tdif = NEIGH_CB(skb)->sched_next - now; - skb = skb->next; if (tdif <= 0) { - struct net_device *dev = back->dev; - __skb_unlink(back, &tbl->proxy_queue); - if (tbl->proxy_redo && netif_running(dev)) - tbl->proxy_redo(back); - else - kfree_skb(back); + struct net_device *dev = skb->dev; + + __skb_unlink(skb, &tbl->proxy_queue); + if (tbl->proxy_redo && netif_running(dev)) { + rcu_read_lock(); + tbl->proxy_redo(skb); + rcu_read_unlock(); + } else { + kfree_skb(skb); + } dev_put(dev); } else if (!sched_next || tdif < sched_next) @@ -1233,9 +1416,11 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % p->proxy_delay); - if (tbl->proxy_queue.qlen > p->proxy_qlen) { + unsigned long sched_next = now + (prandom_u32() % + NEIGH_VAR(p, PROXY_DELAY)); + + if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1248,44 +1433,63 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); spin_unlock(&tbl->proxy_queue.lock); } +EXPORT_SYMBOL(pneigh_enqueue); + +static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, + struct net *net, int ifindex) +{ + struct neigh_parms *p; + + for (p = &tbl->parms; p; p = p->next) { + if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) || + (!p->dev && !ifindex && net_eq(net, &init_net))) + return p; + } + return NULL; +} struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl) { - struct neigh_parms *p = kmalloc(sizeof(*p), GFP_KERNEL); + struct neigh_parms *p; + struct net *net = dev_net(dev); + const struct net_device_ops *ops = dev->netdev_ops; + p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { - memcpy(p, &tbl->parms, sizeof(*p)); p->tbl = tbl; atomic_set(&p->refcnt, 1); - INIT_RCU_HEAD(&p->rcu_head); p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); - if (dev) { - if (dev->neigh_setup && dev->neigh_setup(dev, p)) { - kfree(p); - return NULL; - } + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; - dev_hold(dev); - p->dev = dev; + if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); + kfree(p); + return NULL; } - p->sysctl_table = NULL; + write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; write_unlock_bh(&tbl->lock); + + neigh_parms_data_state_cleanall(p); } return p; } +EXPORT_SYMBOL(neigh_parms_alloc); static void neigh_rcu_free_parms(struct rcu_head *head) { @@ -1314,90 +1518,97 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) } } write_unlock_bh(&tbl->lock); - NEIGH_PRINTK1("neigh_parms_release: not found\n"); + neigh_dbg(1, "%s: not found\n", __func__); } +EXPORT_SYMBOL(neigh_parms_release); -void neigh_parms_destroy(struct neigh_parms *parms) +static void neigh_parms_destroy(struct neigh_parms *parms) { + release_net(neigh_parms_net(parms)); kfree(parms); } +static struct lock_class_key neigh_table_proxy_queue_class; -void neigh_table_init(struct neigh_table *tbl) +static void neigh_table_init_no_netlink(struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; + write_pnet(&tbl->parms.net, &init_net); atomic_set(&tbl->parms.refcnt, 1); - INIT_RCU_HEAD(&tbl->parms.rcu_head); tbl->parms.reachable_time = - neigh_rand_reach_time(tbl->parms.base_reachable_time); - - if (!tbl->kmem_cachep) - tbl->kmem_cachep = kmem_cache_create(tbl->id, - tbl->entry_size, - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!tbl->kmem_cachep) - panic("cannot create neighbour cache"); + neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); - + #ifdef CONFIG_PROC_FS - tbl->pde = create_proc_entry(tbl->id, 0, proc_net_stat); - if (!tbl->pde) + if (!proc_create_data(tbl->id, 0, init_net.proc_net_stat, + &neigh_stat_seq_fops, tbl)) panic("cannot create neighbour proc dir entry"); - tbl->pde->proc_fops = &neigh_stat_seq_fops; - tbl->pde->data = tbl; #endif - tbl->hash_mask = 1; - tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1); + RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); - tbl->phash_buckets = kmalloc(phsize, GFP_KERNEL); + tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); - if (!tbl->hash_buckets || !tbl->phash_buckets) + if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); - memset(tbl->phash_buckets, 0, phsize); - - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); + if (!tbl->entry_size) + tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + + tbl->key_len, NEIGH_PRIV_ALIGN); + else + WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); - init_timer(&tbl->gc_timer); - tbl->gc_timer.data = (unsigned long)tbl; - tbl->gc_timer.function = neigh_periodic_timer; - tbl->gc_timer.expires = now + 1; - add_timer(&tbl->gc_timer); - - init_timer(&tbl->proxy_timer); - tbl->proxy_timer.data = (unsigned long)tbl; - tbl->proxy_timer.function = neigh_proxy_process; - skb_queue_head_init(&tbl->proxy_queue); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + tbl->parms.reachable_time); + setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); + skb_queue_head_init_class(&tbl->proxy_queue, + &neigh_table_proxy_queue_class); tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; +} + +void neigh_table_init(struct neigh_table *tbl) +{ + struct neigh_table *tmp; + + neigh_table_init_no_netlink(tbl); write_lock(&neigh_tbl_lock); + for (tmp = neigh_tables; tmp; tmp = tmp->next) { + if (tmp->family == tbl->family) + break; + } tbl->next = neigh_tables; neigh_tables = tbl; write_unlock(&neigh_tbl_lock); + + if (unlikely(tmp)) { + pr_err("Registering multiple tables for family %d\n", + tbl->family); + dump_stack(); + } } +EXPORT_SYMBOL(neigh_table_init); int neigh_table_clear(struct neigh_table *tbl) { struct neigh_table **tp; /* It is not clean... Fix it to unload IPv6 module safely */ - del_timer_sync(&tbl->gc_timer); + cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) - printk(KERN_CRIT "neighbour leakage\n"); + pr_crit("neighbour leakage\n"); write_lock(&neigh_tbl_lock); for (tp = &neigh_tables; *tp; tp = &(*tp)->next) { if (*tp == tbl) { @@ -1407,216 +1618,274 @@ int neigh_table_clear(struct neigh_table *tbl) } write_unlock(&neigh_tbl_lock); - neigh_hash_free(tbl->hash_buckets, tbl->hash_mask + 1); - tbl->hash_buckets = NULL; + call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, + neigh_hash_free_rcu); + tbl->nht = NULL; kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; + remove_proc_entry(tbl->id, init_net.proc_net_stat); + + free_percpu(tbl->stats); + tbl->stats = NULL; + return 0; } +EXPORT_SYMBOL(neigh_table_clear); -int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *dst_attr; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err = -EINVAL; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + ASSERT_RTNL(); + if (nlmsg_len(nlh) < sizeof(*ndm)) goto out; + dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST); + if (dst_attr == NULL) + goto out; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *dst_attr = nda[NDA_DST - 1]; - struct neighbour *n; + struct neighbour *neigh; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) - goto out_dev_put; + if (nla_len(dst_attr) < tbl->key_len) + goto out; if (ndm->ndm_flags & NTF_PROXY) { - err = pneigh_delete(tbl, RTA_DATA(dst_attr), dev); - goto out_dev_put; + err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); + goto out; } - if (!dev) + if (dev == NULL) goto out; - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - err = neigh_update(n, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); - neigh_release(n); + neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); + if (neigh == NULL) { + err = -ENOENT; + goto out; } - goto out_dev_put; + + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); + goto out; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; -out_dev_put: - if (dev) - dev_put(dev); + err = -EAFNOSUPPORT; + out: return err; } -int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err; + + ASSERT_RTNL(); + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + goto out; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + err = -EINVAL; + if (tb[NDA_DST] == NULL) goto out; + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + + if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) + goto out; + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *lladdr_attr = nda[NDA_LLADDR - 1]; - struct rtattr *dst_attr = nda[NDA_DST - 1]; - int override = 1; - struct neighbour *n; + int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; + struct neighbour *neigh; + void *dst, *lladdr; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) - goto out_dev_put; + if (nla_len(tb[NDA_DST]) < tbl->key_len) + goto out; + dst = nla_data(tb[NDA_DST]); + lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (ndm->ndm_flags & NTF_PROXY) { + struct pneigh_entry *pn; + err = -ENOBUFS; - if (pneigh_lookup(tbl, RTA_DATA(dst_attr), dev, 1)) + pn = pneigh_lookup(tbl, net, dst, dev, 1); + if (pn) { + pn->flags = ndm->ndm_flags; err = 0; - goto out_dev_put; + } + goto out; } - err = -EINVAL; - if (!dev) + if (dev == NULL) goto out; - if (lladdr_attr && RTA_PAYLOAD(lladdr_attr) < dev->addr_len) - goto out_dev_put; - - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - if (nlh->nlmsg_flags & NLM_F_EXCL) { - err = -EEXIST; - neigh_release(n); - goto out_dev_put; + + neigh = neigh_lookup(tbl, dst, dev); + if (neigh == NULL) { + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + err = -ENOENT; + goto out; + } + + neigh = __neigh_lookup_errno(tbl, dst, dev); + if (IS_ERR(neigh)) { + err = PTR_ERR(neigh); + goto out; } - - override = nlh->nlmsg_flags & NLM_F_REPLACE; - } else if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { - err = -ENOENT; - goto out_dev_put; } else { - n = __neigh_lookup_errno(tbl, RTA_DATA(dst_attr), dev); - if (IS_ERR(n)) { - err = PTR_ERR(n); - goto out_dev_put; + if (nlh->nlmsg_flags & NLM_F_EXCL) { + err = -EEXIST; + neigh_release(neigh); + goto out; } - } - err = neigh_update(n, - lladdr_attr ? RTA_DATA(lladdr_attr) : NULL, - ndm->ndm_state, - (override ? NEIGH_UPDATE_F_OVERRIDE : 0) | - NEIGH_UPDATE_F_ADMIN); + if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) + flags &= ~NEIGH_UPDATE_F_OVERRIDE; + } - neigh_release(n); - goto out_dev_put; + if (ndm->ndm_flags & NTF_USE) { + neigh_event_send(neigh, NULL); + err = 0; + } else + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + neigh_release(neigh); + goto out; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; -out_dev_put: - if (dev) - dev_put(dev); + err = -EAFNOSUPPORT; out: return err; } static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { - struct rtattr *nest = NULL; - - nest = RTA_NEST(skb, NDTA_PARMS); + struct nlattr *nest; - if (parms->dev) - RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); - - RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); - RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); - RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); - RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); - RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); - RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); - RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, - parms->base_reachable_time); - RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); - RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); - RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); - RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); - RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); - RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); - - return RTA_NEST_END(skb, nest); - -rtattr_failure: - return RTA_NEST_CANCEL(skb, nest); -} + nest = nla_nest_start(skb, NDTA_PARMS); + if (nest == NULL) + return -ENOBUFS; -static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, - struct netlink_callback *cb) + if ((parms->dev && + nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || + nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || + nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, + NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || + /* approximative value for deprecated QUEUE_LEN (in packets) */ + nla_put_u32(skb, NDTPA_QUEUE_LEN, + NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || + nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || + nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || + nla_put_u32(skb, NDTPA_UCAST_PROBES, + NEIGH_VAR(parms, UCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_PROBES, + NEIGH_VAR(parms, MCAST_PROBES)) || + nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || + nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, + NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || + nla_put_msecs(skb, NDTPA_GC_STALETIME, + NEIGH_VAR(parms, GC_STALETIME)) || + nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, + NEIGH_VAR(parms, DELAY_PROBE_TIME)) || + nla_put_msecs(skb, NDTPA_RETRANS_TIME, + NEIGH_VAR(parms, RETRANS_TIME)) || + nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, + NEIGH_VAR(parms, ANYCAST_DELAY)) || + nla_put_msecs(skb, NDTPA_PROXY_DELAY, + NEIGH_VAR(parms, PROXY_DELAY)) || + nla_put_msecs(skb, NDTPA_LOCKTIME, + NEIGH_VAR(parms, LOCKTIME))) + goto nla_put_failure; + return nla_nest_end(skb, nest); + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, + u32 pid, u32 seq, int type, int flags) { struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -EMSGSIZE; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); - RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); - RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); - RTA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); - + if (nla_put_string(skb, NDTA_NAME, tbl->id) || + nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval) || + nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) || + nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) || + nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3)) + goto nla_put_failure; { unsigned long now = jiffies; unsigned int flush_delta = now - tbl->last_flush; unsigned int rand_delta = now - tbl->last_rand; - + struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, .ndtc_entry_size = tbl->entry_size, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), - .ndtc_hash_rnd = tbl->hash_rnd, - .ndtc_hash_mask = tbl->hash_mask, - .ndtc_hash_chain_gc = tbl->hash_chain_gc, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; - RTA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + ndc.ndtc_hash_rnd = nht->hash_rnd[0]; + ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); + rcu_read_unlock_bh(); + + if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) + goto nla_put_failure; } { @@ -1625,7 +1894,7 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, memset(&ndst, 0, sizeof(ndst)); - for_each_cpu(cpu) { + for_each_possible_cpu(cpu) { struct neigh_statistics *st; st = per_cpu_ptr(tbl->stats, cpu); @@ -1641,312 +1910,477 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, ndst.ndts_forced_gc_runs += st->forced_gc_runs; } - RTA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst)) + goto nla_put_failure; } BUG_ON(tbl->parms.dev); if (neightbl_fill_parms(skb, &tbl->parms) < 0) - goto rtattr_failure; + goto nla_put_failure; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); + return nlmsg_end(skb, nlh); -rtattr_failure: +nla_put_failure: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } -static int neightbl_fill_param_info(struct neigh_table *tbl, +static int neightbl_fill_param_info(struct sk_buff *skb, + struct neigh_table *tbl, struct neigh_parms *parms, - struct sk_buff *skb, - struct netlink_callback *cb) + u32 pid, u32 seq, int type, + unsigned int flags) { struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -EMSGSIZE; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - if (neightbl_fill_parms(skb, parms) < 0) - goto rtattr_failure; + if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 || + neightbl_fill_parms(skb, parms) < 0) + goto errout; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); - -rtattr_failure: + return nlmsg_end(skb, nlh); +errout: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } - -static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, - int ifindex) -{ - struct neigh_parms *p; - - for (p = &tbl->parms; p; p = p->next) - if ((p->dev && p->dev->ifindex == ifindex) || - (!p->dev && !ifindex)) - return p; - return NULL; -} +static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { + [NDTA_NAME] = { .type = NLA_STRING }, + [NDTA_THRESH1] = { .type = NLA_U32 }, + [NDTA_THRESH2] = { .type = NLA_U32 }, + [NDTA_THRESH3] = { .type = NLA_U32 }, + [NDTA_GC_INTERVAL] = { .type = NLA_U64 }, + [NDTA_PARMS] = { .type = NLA_NESTED }, +}; -int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { + [NDTPA_IFINDEX] = { .type = NLA_U32 }, + [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, + [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, + [NDTPA_APP_PROBES] = { .type = NLA_U32 }, + [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, + [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, + [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, + [NDTPA_RETRANS_TIME] = { .type = NLA_U64 }, + [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, + [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, + [NDTPA_LOCKTIME] = { .type = NLA_U64 }, +}; + +static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); struct neigh_table *tbl; - struct ndtmsg *ndtmsg = NLMSG_DATA(nlh); - struct rtattr **tb = arg; - int err = -EINVAL; + struct ndtmsg *ndtmsg; + struct nlattr *tb[NDTA_MAX+1]; + int err; - if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1])) - return -EINVAL; + err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, + nl_neightbl_policy); + if (err < 0) + goto errout; + + if (tb[NDTA_NAME] == NULL) { + err = -EINVAL; + goto errout; + } + ndtmsg = nlmsg_data(nlh); read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; - if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id)) + if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) break; } if (tbl == NULL) { err = -ENOENT; - goto errout; + goto errout_locked; } - /* + /* * We acquire tbl->lock to be nice to the periodic timers and * make sure they always see a consistent set of values. */ write_lock_bh(&tbl->lock); - if (tb[NDTA_THRESH1 - 1]) - tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]); - - if (tb[NDTA_THRESH2 - 1]) - tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]); - - if (tb[NDTA_THRESH3 - 1]) - tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]); - - if (tb[NDTA_GC_INTERVAL - 1]) - tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]); - - if (tb[NDTA_PARMS - 1]) { - struct rtattr *tbp[NDTPA_MAX]; + if (tb[NDTA_PARMS]) { + struct nlattr *tbp[NDTPA_MAX+1]; struct neigh_parms *p; - u32 ifindex = 0; + int i, ifindex = 0; - if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0) - goto rtattr_failure; + err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS], + nl_ntbl_parm_policy); + if (err < 0) + goto errout_tbl_lock; - if (tbp[NDTPA_IFINDEX - 1]) - ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]); + if (tbp[NDTPA_IFINDEX]) + ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); - p = lookup_neigh_params(tbl, ifindex); + p = lookup_neigh_parms(tbl, net, ifindex); if (p == NULL) { err = -ENOENT; - goto rtattr_failure; + goto errout_tbl_lock; } - - if (tbp[NDTPA_QUEUE_LEN - 1]) - p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]); - - if (tbp[NDTPA_PROXY_QLEN - 1]) - p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]); - - if (tbp[NDTPA_APP_PROBES - 1]) - p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]); - if (tbp[NDTPA_UCAST_PROBES - 1]) - p->ucast_probes = - RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]); - - if (tbp[NDTPA_MCAST_PROBES - 1]) - p->mcast_probes = - RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]); - - if (tbp[NDTPA_BASE_REACHABLE_TIME - 1]) - p->base_reachable_time = - RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]); + for (i = 1; i <= NDTPA_MAX; i++) { + if (tbp[i] == NULL) + continue; - if (tbp[NDTPA_GC_STALETIME - 1]) - p->gc_staletime = - RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]); + switch (i) { + case NDTPA_QUEUE_LEN: + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN)); + break; + case NDTPA_QUEUE_LENBYTES: + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i])); + break; + case NDTPA_PROXY_QLEN: + NEIGH_VAR_SET(p, PROXY_QLEN, + nla_get_u32(tbp[i])); + break; + case NDTPA_APP_PROBES: + NEIGH_VAR_SET(p, APP_PROBES, + nla_get_u32(tbp[i])); + break; + case NDTPA_UCAST_PROBES: + NEIGH_VAR_SET(p, UCAST_PROBES, + nla_get_u32(tbp[i])); + break; + case NDTPA_MCAST_PROBES: + NEIGH_VAR_SET(p, MCAST_PROBES, + nla_get_u32(tbp[i])); + break; + case NDTPA_BASE_REACHABLE_TIME: + NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, + nla_get_msecs(tbp[i])); + break; + case NDTPA_GC_STALETIME: + NEIGH_VAR_SET(p, GC_STALETIME, + nla_get_msecs(tbp[i])); + break; + case NDTPA_DELAY_PROBE_TIME: + NEIGH_VAR_SET(p, DELAY_PROBE_TIME, + nla_get_msecs(tbp[i])); + break; + case NDTPA_RETRANS_TIME: + NEIGH_VAR_SET(p, RETRANS_TIME, + nla_get_msecs(tbp[i])); + break; + case NDTPA_ANYCAST_DELAY: + NEIGH_VAR_SET(p, ANYCAST_DELAY, + nla_get_msecs(tbp[i])); + break; + case NDTPA_PROXY_DELAY: + NEIGH_VAR_SET(p, PROXY_DELAY, + nla_get_msecs(tbp[i])); + break; + case NDTPA_LOCKTIME: + NEIGH_VAR_SET(p, LOCKTIME, + nla_get_msecs(tbp[i])); + break; + } + } + } - if (tbp[NDTPA_DELAY_PROBE_TIME - 1]) - p->delay_probe_time = - RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]); + err = -ENOENT; + if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] || + tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) && + !net_eq(net, &init_net)) + goto errout_tbl_lock; - if (tbp[NDTPA_RETRANS_TIME - 1]) - p->retrans_time = - RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]); + if (tb[NDTA_THRESH1]) + tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); - if (tbp[NDTPA_ANYCAST_DELAY - 1]) - p->anycast_delay = - RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]); + if (tb[NDTA_THRESH2]) + tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); - if (tbp[NDTPA_PROXY_DELAY - 1]) - p->proxy_delay = - RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]); + if (tb[NDTA_THRESH3]) + tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); - if (tbp[NDTPA_LOCKTIME - 1]) - p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]); - } + if (tb[NDTA_GC_INTERVAL]) + tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); err = 0; -rtattr_failure: +errout_tbl_lock: write_unlock_bh(&tbl->lock); -errout: +errout_locked: read_unlock(&neigh_tbl_lock); +errout: return err; } -int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { - int idx, family; - int s_idx = cb->args[0]; + struct net *net = sock_net(skb->sk); + int family, tidx, nidx = 0; + int tbl_skip = cb->args[0]; + int neigh_skip = cb->args[1]; struct neigh_table *tbl; - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables, idx = 0; tbl; tbl = tbl->next) { + for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) { struct neigh_parms *p; - if (idx < s_idx || (family && tbl->family != family)) + if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(tbl, skb, cb) <= 0) + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) break; - for (++idx, p = tbl->parms.next; p; p = p->next, idx++) { - if (idx < s_idx) + for (nidx = 0, p = tbl->parms.next; p; p = p->next) { + if (!net_eq(neigh_parms_net(p), net)) continue; - if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0) + if (nidx < neigh_skip) + goto next; + + if (neightbl_fill_param_info(skb, tbl, p, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) goto out; + next: + nidx++; } + neigh_skip = 0; } out: read_unlock(&neigh_tbl_lock); - cb->args[0] = idx; + cb->args[0] = tidx; + cb->args[1] = nidx; return skb->len; } -static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n, - u32 pid, u32 seq, int event, unsigned int flags) +static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, + u32 pid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; - unsigned char *b = skb->tail; struct nda_cacheinfo ci; - int locked = 0; - u32 probes; - struct nlmsghdr *nlh = NLMSG_NEW(skb, pid, seq, event, - sizeof(struct ndmsg), flags); - struct ndmsg *ndm = NLMSG_DATA(nlh); + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; - ndm->ndm_family = n->ops->family; + ndm = nlmsg_data(nlh); + ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = n->flags; - ndm->ndm_type = n->type; - ndm->ndm_ifindex = n->dev->ifindex; - RTA_PUT(skb, NDA_DST, n->tbl->key_len, n->primary_key); - read_lock_bh(&n->lock); - locked = 1; - ndm->ndm_state = n->nud_state; - if (n->nud_state & NUD_VALID) - RTA_PUT(skb, NDA_LLADDR, n->dev->addr_len, n->ha); - ci.ndm_used = now - n->used; - ci.ndm_confirmed = now - n->confirmed; - ci.ndm_updated = now - n->updated; - ci.ndm_refcnt = atomic_read(&n->refcnt) - 1; - probes = atomic_read(&n->probes); - read_unlock_bh(&n->lock); - locked = 0; - RTA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); - RTA_PUT(skb, NDA_PROBES, sizeof(probes), &probes); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + ndm->ndm_flags = neigh->flags; + ndm->ndm_type = neigh->type; + ndm->ndm_ifindex = neigh->dev->ifindex; + + if (nla_put(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key)) + goto nla_put_failure; + + read_lock_bh(&neigh->lock); + ndm->ndm_state = neigh->nud_state; + if (neigh->nud_state & NUD_VALID) { + char haddr[MAX_ADDR_LEN]; + + neigh_ha_snapshot(haddr, neigh, neigh->dev); + if (nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, haddr) < 0) { + read_unlock_bh(&neigh->lock); + goto nla_put_failure; + } + } + + ci.ndm_used = jiffies_to_clock_t(now - neigh->used); + ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); + ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); + ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; + read_unlock_bh(&neigh->lock); + + if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || + nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, + u32 pid, u32 seq, int type, unsigned int flags, + struct neigh_table *tbl) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; -nlmsg_failure: -rtattr_failure: - if (locked) - read_unlock_bh(&n->lock); - skb_trim(skb, b - skb->data); - return -1; + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = tbl->family; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_type = RTN_UNICAST; + ndm->ndm_ifindex = pn->dev->ifindex; + ndm->ndm_state = NUD_NONE; + + if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } +static void neigh_update_notify(struct neighbour *neigh) +{ + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); + __neigh_notify(neigh, RTM_NEWNEIGH, 0); +} static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; + struct neigh_hash_table *nht; - for (h = 0; h <= tbl->hash_mask; h++) { - if (h < s_h) - continue; + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + + for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; - read_lock_bh(&tbl->lock); - for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) { - if (idx < s_idx) + for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; + n != NULL; + n = rcu_dereference_bh(n->next)) { + if (!net_eq(dev_net(n->dev), net)) continue; - if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + if (idx < s_idx) + goto next; + if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) <= 0) { - read_unlock_bh(&tbl->lock); rc = -1; goto out; } +next: + idx++; } - read_unlock_bh(&tbl->lock); } rc = skb->len; out: + rcu_read_unlock_bh(); cb->args[1] = h; cb->args[2] = idx; return rc; } -int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct pneigh_entry *n; + struct net *net = sock_net(skb->sk); + int rc, h, s_h = cb->args[3]; + int idx, s_idx = idx = cb->args[4]; + + read_lock_bh(&tbl->lock); + + for (h = s_h; h <= PNEIGH_HASHMASK; h++) { + if (h > s_h) + s_idx = 0; + for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { + if (dev_net(n->dev) != net) + continue; + if (idx < s_idx) + goto next; + if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI, tbl) <= 0) { + read_unlock_bh(&tbl->lock); + rc = -1; + goto out; + } + next: + idx++; + } + } + + read_unlock_bh(&tbl->lock); + rc = skb->len; +out: + cb->args[3] = h; + cb->args[4] = idx; + return rc; + +} + +static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { struct neigh_table *tbl; int t, family, s_t; + int proxy = 0; + int err; read_lock(&neigh_tbl_lock); - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; + + /* check for full ndmsg structure presence, family member is + * the same for both structures + */ + if (nlmsg_len(cb->nlh) >= sizeof(struct ndmsg) && + ((struct ndmsg *) nlmsg_data(cb->nlh))->ndm_flags == NTF_PROXY) + proxy = 1; + s_t = cb->args[0]; - for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { + for (tbl = neigh_tables, t = 0; tbl; + tbl = tbl->next, t++) { if (t < s_t || (family && tbl->family != family)) continue; if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); - if (neigh_dump_table(tbl, skb, cb) < 0) + if (proxy) + err = pneigh_dump_table(tbl, skb, cb); + else + err = neigh_dump_table(tbl, skb, cb); + if (err < 0) break; } read_unlock(&neigh_tbl_lock); @@ -1958,15 +2392,22 @@ int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie) { int chain; + struct neigh_hash_table *nht; - read_lock_bh(&tbl->lock); - for (chain = 0; chain <= tbl->hash_mask; chain++) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + + read_lock(&tbl->lock); /* avoid resizes */ + for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; - for (n = tbl->hash_buckets[chain]; n; n = n->next) + for (n = rcu_dereference_bh(nht->hash_buckets[chain]); + n != NULL; + n = rcu_dereference_bh(n->next)) cb(n, cookie); } - read_unlock_bh(&tbl->lock); + read_unlock(&tbl->lock); + rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_for_each); @@ -1975,24 +2416,31 @@ void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)) { int chain; + struct neigh_hash_table *nht; - for (chain = 0; chain <= tbl->hash_mask; chain++) { - struct neighbour *n, **np; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + for (chain = 0; chain < (1 << nht->hash_shift); chain++) { + struct neighbour *n; + struct neighbour __rcu **np; - np = &tbl->hash_buckets[chain]; - while ((n = *np) != NULL) { + np = &nht->hash_buckets[chain]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { int release; write_lock(&n->lock); release = cb(n); if (release) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); n->dead = 1; } else np = &n->next; write_unlock(&n->lock); if (release) - neigh_release(n); + neigh_cleanup_and_release(n); } } } @@ -2003,15 +2451,18 @@ EXPORT_SYMBOL(__neigh_for_each_release); static struct neighbour *neigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; - struct neigh_table *tbl = state->tbl; + struct net *net = seq_file_net(seq); + struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; int bucket = state->bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; - for (bucket = 0; bucket <= tbl->hash_mask; bucket++) { - n = tbl->hash_buckets[bucket]; + for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { + n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { + if (!net_eq(dev_net(n->dev), net)) + goto next; if (state->neigh_sub_iter) { loff_t fakep = 0; void *v; @@ -2024,8 +2475,8 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) break; if (n->nud_state & ~NUD_NOARP) break; - next: - n = n->next; +next: + n = rcu_dereference_bh(n->next); } if (n) @@ -2041,17 +2492,20 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; - struct neigh_table *tbl = state->tbl; + struct net *net = seq_file_net(seq); + struct neigh_hash_table *nht = state->nht; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; } - n = n->next; + n = rcu_dereference_bh(n->next); while (1) { while (n) { + if (!net_eq(dev_net(n->dev), net)) + goto next; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) @@ -2063,17 +2517,17 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (n->nud_state & ~NUD_NOARP) break; - next: - n = n->next; +next: + n = rcu_dereference_bh(n->next); } if (n) break; - if (++state->bucket > tbl->hash_mask) + if (++state->bucket >= (1 << nht->hash_shift)) break; - n = tbl->hash_buckets[state->bucket]; + n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); } if (n && pos) @@ -2086,6 +2540,7 @@ static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) struct neighbour *n = neigh_get_first(seq); if (n) { + --(*pos); while (*pos) { n = neigh_get_next(seq, n, pos); if (!n) @@ -2098,6 +2553,7 @@ static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos) static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; + struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct pneigh_entry *pn = NULL; int bucket = state->bucket; @@ -2105,6 +2561,8 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { pn = tbl->phash_buckets[bucket]; + while (pn && !net_eq(pneigh_net(pn), net)) + pn = pn->next; if (pn) break; } @@ -2118,13 +2576,19 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; + struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; pn = tbl->phash_buckets[state->bucket]; + while (pn && !net_eq(pneigh_net(pn), net)) + pn = pn->next; if (pn) break; } @@ -2140,6 +2604,7 @@ static struct pneigh_entry *pneigh_get_idx(struct seq_file *seq, loff_t *pos) struct pneigh_entry *pn = pneigh_get_first(seq); if (pn) { + --(*pos); while (*pos) { pn = pneigh_get_next(seq, pn, pos); if (!pn) @@ -2153,27 +2618,28 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; void *rc; + loff_t idxpos = *pos; - rc = neigh_get_idx(seq, pos); + rc = neigh_get_idx(seq, &idxpos); if (!rc && !(state->flags & NEIGH_SEQ_NEIGH_ONLY)) - rc = pneigh_get_idx(seq, pos); + rc = pneigh_get_idx(seq, &idxpos); return rc; } void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) + __acquires(rcu_bh) { struct neigh_seq_state *state = seq->private; - loff_t pos_minus_one; state->tbl = tbl; state->bucket = 0; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); - read_lock_bh(&tbl->lock); + rcu_read_lock_bh(); + state->nht = rcu_dereference_bh(tbl->nht); - pos_minus_one = *pos - 1; - return *pos ? neigh_get_idx_any(seq, &pos_minus_one) : SEQ_START_TOKEN; + return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } EXPORT_SYMBOL(neigh_seq_start); @@ -2183,7 +2649,7 @@ void *neigh_seq_next(struct seq_file *seq, void *v, loff_t *pos) void *rc; if (v == SEQ_START_TOKEN) { - rc = neigh_get_idx(seq, pos); + rc = neigh_get_first(seq); goto out; } @@ -2205,11 +2671,9 @@ out: EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) + __releases(rcu_bh) { - struct neigh_seq_state *state = seq->private; - struct neigh_table *tbl = state->tbl; - - read_unlock_bh(&tbl->lock); + rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_seq_stop); @@ -2217,14 +2681,13 @@ EXPORT_SYMBOL(neigh_seq_stop); static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) { - struct proc_dir_entry *pde = seq->private; - struct neigh_table *tbl = pde->data; + struct neigh_table *tbl = seq->private; int cpu; if (*pos == 0) return SEQ_START_TOKEN; - - for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) { + + for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -2235,11 +2698,10 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct proc_dir_entry *pde = seq->private; - struct neigh_table *tbl = pde->data; + struct neigh_table *tbl = seq->private; int cpu; - for (cpu = *pos; cpu < NR_CPUS; ++cpu) { + for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -2255,17 +2717,16 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v) static int neigh_stat_seq_show(struct seq_file *seq, void *v) { - struct proc_dir_entry *pde = seq->private; - struct neigh_table *tbl = pde->data; + struct neigh_table *tbl = seq->private; struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs\n"); + seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " - "%08lx %08lx %08lx %08lx\n", + "%08lx %08lx %08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, @@ -2281,13 +2742,14 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) st->rcv_probes_ucast, st->periodic_gc_runs, - st->forced_gc_runs + st->forced_gc_runs, + st->unres_discards ); return 0; } -static struct seq_operations neigh_stat_seq_ops = { +static const struct seq_operations neigh_stat_seq_ops = { .start = neigh_stat_seq_start, .next = neigh_stat_seq_next, .stop = neigh_stat_seq_stop, @@ -2300,12 +2762,12 @@ static int neigh_stat_seq_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - sf->private = PDE(inode); + sf->private = PDE_DATA(inode); } return ret; }; -static struct file_operations neigh_stat_seq_fops = { +static const struct file_operations neigh_stat_seq_fops = { .owner = THIS_MODULE, .open = neigh_stat_seq_open, .read = seq_read, @@ -2315,357 +2777,364 @@ static struct file_operations neigh_stat_seq_fops = { #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_ARPD -void neigh_app_ns(struct neighbour *n) +static inline size_t neigh_nlmsg_size(void) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(struct nda_cacheinfo)) + + nla_total_size(4); /* NDA_PROBES */ +} - if (!skb) - return; +static void __neigh_notify(struct neighbour *n, int type, int flags) +{ + struct net *net = dev_net(n->dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(neigh_nlmsg_size(), GFP_ATOMIC); + if (skb == NULL) + goto errout; - if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, 0) < 0) { + err = neigh_fill_info(skb, n, 0, 0, type, flags); + if (err < 0) { + /* -EMSGSIZE implies BUG in neigh_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - return; + goto errout; } - nlh = (struct nlmsghdr *)skb->data; - nlh->nlmsg_flags = NLM_F_REQUEST; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } -static void neigh_app_notify(struct neighbour *n) +void neigh_app_ns(struct neighbour *n) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); + __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); +} +EXPORT_SYMBOL(neigh_app_ns); - if (!skb) - return; +#ifdef CONFIG_SYSCTL +static int zero; +static int int_max = INT_MAX; +static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); - if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) < 0) { - kfree_skb(skb); - return; +static int proc_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int size, ret; + struct ctl_table tmp = *ctl; + + tmp.extra1 = &zero; + tmp.extra2 = &unres_qlen_max; + tmp.data = &size; + + size = *(int *)ctl->data / SKB_TRUESIZE(ETH_FRAME_LEN); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && !ret) + *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); + return ret; +} + +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); } - nlh = (struct nlmsghdr *)skb->data; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); + return NULL; } -#endif /* CONFIG_ARPD */ +static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, + int index) +{ + struct net_device *dev; + int family = neigh_parms_family(p); -#ifdef CONFIG_SYSCTL + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct neigh_parms *dst_p = + neigh_get_dev_parms_rcu(dev, family); + + if (dst_p && !test_bit(index, dst_p->data_state)) + dst_p->data[index] = p->data[index]; + } + rcu_read_unlock(); +} + +static void neigh_proc_update(struct ctl_table *ctl, int write) +{ + struct net_device *dev = ctl->extra1; + struct neigh_parms *p = ctl->extra2; + struct net *net = neigh_parms_net(p); + int index = (int *) ctl->data - p->data; + + if (!write) + return; + + set_bit(index, p->data_state); + if (!dev) /* NULL dev means this is default value */ + neigh_copy_dflt_parms(net, p, index); +} + +static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *ctl; + int ret; + + tmp.extra1 = &zero; + tmp.extra2 = &int_max; + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec); + +int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); + +static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); + +static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +#define NEIGH_PARMS_DATA_OFFSET(index) \ + (&((struct neigh_parms *) 0)->data[index]) + +#define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ + [NEIGH_VAR_ ## attr] = { \ + .procname = name, \ + .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ + .maxlen = sizeof(int), \ + .mode = mval, \ + .proc_handler = proc, \ + } + +#define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) + +#define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) + +#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - ctl_table neigh_vars[__NET_NEIGH_MAX]; - ctl_table neigh_dev[2]; - ctl_table neigh_neigh_dir[2]; - ctl_table neigh_proto_dir[2]; - ctl_table neigh_root_dir[2]; -} neigh_sysctl_template = { + struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; +} neigh_sysctl_template __read_mostly = { .neigh_vars = { - { - .ctl_name = NET_NEIGH_MCAST_SOLICIT, - .procname = "mcast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = NET_NEIGH_UCAST_SOLICIT, - .procname = "ucast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = NET_NEIGH_APP_SOLICIT, - .procname = "app_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = NET_NEIGH_RETRANS_TIME, - .procname = "retrans_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, - }, - { - .ctl_name = NET_NEIGH_REACHABLE_TIME, - .procname = "base_reachable_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, - }, - { - .ctl_name = NET_NEIGH_DELAY_PROBE_TIME, - .procname = "delay_first_probe_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, - }, - { - .ctl_name = NET_NEIGH_GC_STALE_TIME, - .procname = "gc_stale_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, - }, - { - .ctl_name = NET_NEIGH_UNRES_QLEN, - .procname = "unres_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = NET_NEIGH_PROXY_QLEN, - .procname = "proxy_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = NET_NEIGH_ANYCAST_DELAY, - .procname = "anycast_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, - }, - { - .ctl_name = NET_NEIGH_PROXY_DELAY, - .procname = "proxy_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, - }, - { - .ctl_name = NET_NEIGH_LOCKTIME, - .procname = "locktime", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_userhz_jiffies, - }, - { - .ctl_name = NET_NEIGH_GC_INTERVAL, + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), + NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), + [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, - { - .ctl_name = NET_NEIGH_GC_THRESH1, + [NEIGH_VAR_GC_THRESH1] = { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, - { - .ctl_name = NET_NEIGH_GC_THRESH2, + [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, - { - .ctl_name = NET_NEIGH_GC_THRESH3, + [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, - }, - { - .ctl_name = NET_NEIGH_RETRANS_TIME_MS, - .procname = "retrans_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, - }, - { - .ctl_name = NET_NEIGH_REACHABLE_TIME_MS, - .procname = "base_reachable_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, - }, - }, - .neigh_dev = { - { - .ctl_name = NET_PROTO_CONF_DEFAULT, - .procname = "default", - .mode = 0555, - }, - }, - .neigh_neigh_dir = { - { - .procname = "neigh", - .mode = 0555, - }, - }, - .neigh_proto_dir = { - { - .mode = 0555, - }, - }, - .neigh_root_dir = { - { - .ctl_name = CTL_NET, - .procname = "net", - .mode = 0555, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, + {}, }, }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - int p_id, int pdev_id, char *p_name, - proc_handler *handler, ctl_handler *strategy) + proc_handler *handler) { - struct neigh_sysctl_table *t = kmalloc(sizeof(*t), GFP_KERNEL); - const char *dev_name_source = NULL; - char *dev_name = NULL; - int err = 0; + int i; + struct neigh_sysctl_table *t; + const char *dev_name_source; + char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; + char *p_name; + t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) - return -ENOBUFS; - memcpy(t, &neigh_sysctl_template, sizeof(*t)); - t->neigh_vars[0].data = &p->mcast_probes; - t->neigh_vars[1].data = &p->ucast_probes; - t->neigh_vars[2].data = &p->app_probes; - t->neigh_vars[3].data = &p->retrans_time; - t->neigh_vars[4].data = &p->base_reachable_time; - t->neigh_vars[5].data = &p->delay_probe_time; - t->neigh_vars[6].data = &p->gc_staletime; - t->neigh_vars[7].data = &p->queue_len; - t->neigh_vars[8].data = &p->proxy_qlen; - t->neigh_vars[9].data = &p->anycast_delay; - t->neigh_vars[10].data = &p->proxy_delay; - t->neigh_vars[11].data = &p->locktime; + goto err; + + for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { + t->neigh_vars[i].data += (long) p; + t->neigh_vars[i].extra1 = dev; + t->neigh_vars[i].extra2 = p; + } if (dev) { dev_name_source = dev->name; - t->neigh_dev[0].ctl_name = dev->ifindex; - t->neigh_vars[12].procname = NULL; - t->neigh_vars[13].procname = NULL; - t->neigh_vars[14].procname = NULL; - t->neigh_vars[15].procname = NULL; + /* Terminate the table early */ + memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, + sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { - dev_name_source = t->neigh_dev[0].procname; - t->neigh_vars[12].data = (int *)(p + 1); - t->neigh_vars[13].data = (int *)(p + 1) + 1; - t->neigh_vars[14].data = (int *)(p + 1) + 2; - t->neigh_vars[15].data = (int *)(p + 1) + 3; + struct neigh_table *tbl = p->tbl; + dev_name_source = "default"; + t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval; + t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1; + t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2; + t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3; } - t->neigh_vars[16].data = &p->retrans_time; - t->neigh_vars[17].data = &p->base_reachable_time; - - if (handler || strategy) { + if (handler) { /* RetransTime */ - t->neigh_vars[3].proc_handler = handler; - t->neigh_vars[3].strategy = strategy; - t->neigh_vars[3].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; /* ReachableTime */ - t->neigh_vars[4].proc_handler = handler; - t->neigh_vars[4].strategy = strategy; - t->neigh_vars[4].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; /* RetransTime (in milliseconds)*/ - t->neigh_vars[16].proc_handler = handler; - t->neigh_vars[16].strategy = strategy; - t->neigh_vars[16].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; /* ReachableTime (in milliseconds) */ - t->neigh_vars[17].proc_handler = handler; - t->neigh_vars[17].strategy = strategy; - t->neigh_vars[17].extra1 = dev; - } - - dev_name = kstrdup(dev_name_source, GFP_KERNEL); - if (!dev_name) { - err = -ENOBUFS; - goto free; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; } - t->neigh_dev[0].procname = dev_name; - - t->neigh_neigh_dir[0].ctl_name = pdev_id; + /* Don't export sysctls to unprivileged users */ + if (neigh_parms_net(p)->user_ns != &init_user_ns) + t->neigh_vars[0].procname = NULL; - t->neigh_proto_dir[0].procname = p_name; - t->neigh_proto_dir[0].ctl_name = p_id; + switch (neigh_parms_family(p)) { + case AF_INET: + p_name = "ipv4"; + break; + case AF_INET6: + p_name = "ipv6"; + break; + default: + BUG(); + } - t->neigh_dev[0].child = t->neigh_vars; - t->neigh_neigh_dir[0].child = t->neigh_dev; - t->neigh_proto_dir[0].child = t->neigh_neigh_dir; - t->neigh_root_dir[0].child = t->neigh_proto_dir; + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", + p_name, dev_name_source); + t->sysctl_header = + register_net_sysctl(neigh_parms_net(p), neigh_path, t->neigh_vars); + if (!t->sysctl_header) + goto free; - t->sysctl_header = register_sysctl_table(t->neigh_root_dir, 0); - if (!t->sysctl_header) { - err = -ENOBUFS; - goto free_procname; - } p->sysctl_table = t; return 0; - /* error path */ - free_procname: - kfree(dev_name); - free: +free: kfree(t); - - return err; +err: + return -ENOBUFS; } +EXPORT_SYMBOL(neigh_sysctl_register); void neigh_sysctl_unregister(struct neigh_parms *p) { if (p->sysctl_table) { struct neigh_sysctl_table *t = p->sysctl_table; p->sysctl_table = NULL; - unregister_sysctl_table(t->sysctl_header); - kfree(t->neigh_dev[0].procname); + unregister_net_sysctl_table(t->sysctl_header); kfree(t); } } +EXPORT_SYMBOL(neigh_sysctl_unregister); #endif /* CONFIG_SYSCTL */ -EXPORT_SYMBOL(__neigh_event_send); -EXPORT_SYMBOL(neigh_add); -EXPORT_SYMBOL(neigh_changeaddr); -EXPORT_SYMBOL(neigh_compat_output); -EXPORT_SYMBOL(neigh_connected_output); -EXPORT_SYMBOL(neigh_create); -EXPORT_SYMBOL(neigh_delete); -EXPORT_SYMBOL(neigh_destroy); -EXPORT_SYMBOL(neigh_dump_info); -EXPORT_SYMBOL(neigh_event_ns); -EXPORT_SYMBOL(neigh_ifdown); -EXPORT_SYMBOL(neigh_lookup); -EXPORT_SYMBOL(neigh_lookup_nodev); -EXPORT_SYMBOL(neigh_parms_alloc); -EXPORT_SYMBOL(neigh_parms_release); -EXPORT_SYMBOL(neigh_rand_reach_time); -EXPORT_SYMBOL(neigh_resolve_output); -EXPORT_SYMBOL(neigh_table_clear); -EXPORT_SYMBOL(neigh_table_init); -EXPORT_SYMBOL(neigh_update); -EXPORT_SYMBOL(neigh_update_hhs); -EXPORT_SYMBOL(pneigh_enqueue); -EXPORT_SYMBOL(pneigh_lookup); -EXPORT_SYMBOL(neightbl_dump_info); -EXPORT_SYMBOL(neightbl_set); +static int __init neigh_init(void) +{ + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL); + + rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, + NULL); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL); + + return 0; +} + +subsys_initcall(neigh_init); -#ifdef CONFIG_ARPD -EXPORT_SYMBOL(neigh_app_ns); -#endif -#ifdef CONFIG_SYSCTL -EXPORT_SYMBOL(neigh_sysctl_register); -EXPORT_SYMBOL(neigh_sysctl_unregister); -#endif diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c new file mode 100644 index 00000000000..2bf83299600 --- /dev/null +++ b/net/core/net-procfs.c @@ -0,0 +1,423 @@ +#include <linux/netdevice.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <net/wext.h> + +#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) + +#define get_bucket(x) ((x) >> BUCKET_SPACE) +#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) +#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) + +extern struct list_head ptype_all __read_mostly; +extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; + +static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + struct net_device *dev; + struct hlist_head *h; + unsigned int count = 0, offset = get_offset(*pos); + + h = &net->dev_name_head[get_bucket(*pos)]; + hlist_for_each_entry_rcu(dev, h, name_hlist) { + if (++count == offset) + return dev; + } + + return NULL; +} + +static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) +{ + struct net_device *dev; + unsigned int bucket; + + do { + dev = dev_from_same_bucket(seq, pos); + if (dev) + return dev; + + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); + } while (bucket < NETDEV_HASHENTRIES); + + return NULL; +} + +/* + * This is invoked by the /proc filesystem handler to display a device + * in detail. + */ +static void *dev_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + if (!*pos) + return SEQ_START_TOKEN; + + if (get_bucket(*pos) >= NETDEV_HASHENTRIES) + return NULL; + + return dev_from_bucket(seq, pos); +} + +static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return dev_from_bucket(seq, pos); +} + +static void dev_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) +{ + rcu_read_unlock(); +} + +static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) +{ + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); + + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", + dev->name, stats->rx_bytes, stats->rx_packets, + stats->rx_errors, + stats->rx_dropped + stats->rx_missed_errors, + stats->rx_fifo_errors, + stats->rx_length_errors + stats->rx_over_errors + + stats->rx_crc_errors + stats->rx_frame_errors, + stats->rx_compressed, stats->multicast, + stats->tx_bytes, stats->tx_packets, + stats->tx_errors, stats->tx_dropped, + stats->tx_fifo_errors, stats->collisions, + stats->tx_carrier_errors + + stats->tx_aborted_errors + + stats->tx_window_errors + + stats->tx_heartbeat_errors, + stats->tx_compressed); +} + +/* + * Called from the PROCfs module. This now uses the new arbitrary sized + * /proc/net interface to create /proc/net/dev + */ +static int dev_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Inter-| Receive " + " | Transmit\n" + " face |bytes packets errs drop fifo frame " + "compressed multicast|bytes packets errs " + "drop fifo colls carrier compressed\n"); + else + dev_seq_printf_stats(seq, v); + return 0; +} + +static struct softnet_data *softnet_get_online(loff_t *pos) +{ + struct softnet_data *sd = NULL; + + while (*pos < nr_cpu_ids) + if (cpu_online(*pos)) { + sd = &per_cpu(softnet_data, *pos); + break; + } else + ++*pos; + return sd; +} + +static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) +{ + return softnet_get_online(pos); +} + +static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return softnet_get_online(pos); +} + +static void softnet_seq_stop(struct seq_file *seq, void *v) +{ +} + +static int softnet_seq_show(struct seq_file *seq, void *v) +{ + struct softnet_data *sd = v; + unsigned int flow_limit_count = 0; + +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) + flow_limit_count = fl->count; + rcu_read_unlock(); +#endif + + seq_printf(seq, + "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + sd->processed, sd->dropped, sd->time_squeeze, 0, + 0, 0, 0, 0, /* was fastroute */ + sd->cpu_collision, sd->received_rps, flow_limit_count); + return 0; +} + +static const struct seq_operations dev_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_seq_show, +}; + +static int dev_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_seq_fops = { + .owner = THIS_MODULE, + .open = dev_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static const struct seq_operations softnet_seq_ops = { + .start = softnet_seq_start, + .next = softnet_seq_next, + .stop = softnet_seq_stop, + .show = softnet_seq_show, +}; + +static int softnet_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &softnet_seq_ops); +} + +static const struct file_operations softnet_seq_fops = { + .owner = THIS_MODULE, + .open = softnet_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void *ptype_get_idx(loff_t pos) +{ + struct packet_type *pt = NULL; + loff_t i = 0; + int t; + + list_for_each_entry_rcu(pt, &ptype_all, list) { + if (i == pos) + return pt; + ++i; + } + + for (t = 0; t < PTYPE_HASH_SIZE; t++) { + list_for_each_entry_rcu(pt, &ptype_base[t], list) { + if (i == pos) + return pt; + ++i; + } + } + return NULL; +} + +static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; +} + +static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct packet_type *pt; + struct list_head *nxt; + int hash; + + ++*pos; + if (v == SEQ_START_TOKEN) + return ptype_get_idx(0); + + pt = v; + nxt = pt->list.next; + if (pt->type == htons(ETH_P_ALL)) { + if (nxt != &ptype_all) + goto found; + hash = 0; + nxt = ptype_base[0].next; + } else + hash = ntohs(pt->type) & PTYPE_HASH_MASK; + + while (nxt == &ptype_base[hash]) { + if (++hash >= PTYPE_HASH_SIZE) + return NULL; + nxt = ptype_base[hash].next; + } +found: + return list_entry(nxt, struct packet_type, list); +} + +static void ptype_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) +{ + rcu_read_unlock(); +} + +static int ptype_seq_show(struct seq_file *seq, void *v) +{ + struct packet_type *pt = v; + + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Type Device Function\n"); + else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + if (pt->type == htons(ETH_P_ALL)) + seq_puts(seq, "ALL "); + else + seq_printf(seq, "%04x", ntohs(pt->type)); + + seq_printf(seq, " %-8s %pf\n", + pt->dev ? pt->dev->name : "", pt->func); + } + + return 0; +} + +static const struct seq_operations ptype_seq_ops = { + .start = ptype_seq_start, + .next = ptype_seq_next, + .stop = ptype_seq_stop, + .show = ptype_seq_show, +}; + +static int ptype_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ptype_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations ptype_seq_fops = { + .owner = THIS_MODULE, + .open = ptype_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + + +static int __net_init dev_proc_net_init(struct net *net) +{ + int rc = -ENOMEM; + + if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops)) + goto out; + if (!proc_create("softnet_stat", S_IRUGO, net->proc_net, + &softnet_seq_fops)) + goto out_dev; + if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops)) + goto out_softnet; + + if (wext_proc_init(net)) + goto out_ptype; + rc = 0; +out: + return rc; +out_ptype: + remove_proc_entry("ptype", net->proc_net); +out_softnet: + remove_proc_entry("softnet_stat", net->proc_net); +out_dev: + remove_proc_entry("dev", net->proc_net); + goto out; +} + +static void __net_exit dev_proc_net_exit(struct net *net) +{ + wext_proc_exit(net); + + remove_proc_entry("ptype", net->proc_net); + remove_proc_entry("softnet_stat", net->proc_net); + remove_proc_entry("dev", net->proc_net); +} + +static struct pernet_operations __net_initdata dev_proc_ops = { + .init = dev_proc_net_init, + .exit = dev_proc_net_exit, +}; + +static int dev_mc_seq_show(struct seq_file *seq, void *v) +{ + struct netdev_hw_addr *ha; + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + return 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(ha, dev) { + int i; + + seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, + dev->name, ha->refcount, ha->global_use); + + for (i = 0; i < dev->addr_len; i++) + seq_printf(seq, "%02x", ha->addr[i]); + + seq_putc(seq, '\n'); + } + netif_addr_unlock_bh(dev); + return 0; +} + +static const struct seq_operations dev_mc_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_mc_seq_show, +}; + +static int dev_mc_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_mc_seq_fops = { + .owner = THIS_MODULE, + .open = dev_mc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static int __net_init dev_mc_net_init(struct net *net) +{ + if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit dev_mc_net_exit(struct net *net) +{ + remove_proc_entry("dev_mcast", net->proc_net); +} + +static struct pernet_operations __net_initdata dev_mc_net_ops = { + .init = dev_mc_net_init, + .exit = dev_mc_net_exit, +}; + +int __init dev_proc_init(void) +{ + int ret = register_pernet_subsys(&dev_proc_ops); + if (!ret) + return register_pernet_subsys(&dev_mc_net_ops); + return ret; +} diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e8b2acbc8ea..1cac29ebb05 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -2,7 +2,7 @@ * net-sysfs.c - network device class and attributes * * Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org> - * + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -10,33 +10,40 @@ */ #include <linux/capability.h> -#include <linux/config.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> +#include <linux/slab.h> +#include <linux/nsproxy.h> #include <net/sock.h> +#include <net/net_namespace.h> #include <linux/rtnetlink.h> -#include <linux/wireless.h> -#include <net/iw_handler.h> +#include <linux/vmalloc.h> +#include <linux/export.h> +#include <linux/jiffies.h> +#include <linux/pm_runtime.h> -#define to_class_dev(obj) container_of(obj,struct class_device,kobj) -#define to_net_dev(class) container_of(class, struct net_device, class_dev) +#include "net-sysfs.h" +#ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; +static const char fmt_udec[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; +static const char fmt_u64[] = "%llu\n"; -static inline int dev_isalive(const struct net_device *dev) +static inline int dev_isalive(const struct net_device *dev) { - return dev->reg_state == NETREG_REGISTERED; + return dev->reg_state <= NETREG_REGISTERED; } /* use same locking rules as GIF* ioctl's */ -static ssize_t netdev_show(const struct class_device *cd, char *buf, +static ssize_t netdev_show(const struct device *dev, + struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { - struct net_device *net = to_net_dev(cd); + struct net_device *net = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); @@ -53,32 +60,42 @@ static ssize_t format_##field(const struct net_device *net, char *buf) \ { \ return sprintf(buf, format_string, net->field); \ } \ -static ssize_t show_##field(struct class_device *cd, char *buf) \ +static ssize_t field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ { \ - return netdev_show(cd, buf, format_##field); \ -} + return netdev_show(dev, attr, buf, format_##field); \ +} \ + +#define NETDEVICE_SHOW_RO(field, format_string) \ +NETDEVICE_SHOW(field, format_string); \ +static DEVICE_ATTR_RO(field) +#define NETDEVICE_SHOW_RW(field, format_string) \ +NETDEVICE_SHOW(field, format_string); \ +static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ -static ssize_t netdev_store(struct class_device *dev, +static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { - struct net_device *net = to_net_dev(dev); - char *endp; + struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); unsigned long new; int ret = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - new = simple_strtoul(buf, &endp, 0); - if (endp == buf) + ret = kstrtoul(buf, 0, &new); + if (ret) goto err; - rtnl_lock(); - if (dev_isalive(net)) { - if ((ret = (*set)(net, new)) == 0) + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + if ((ret = (*set)(netdev, new)) == 0) ret = len; } rtnl_unlock(); @@ -86,45 +103,55 @@ static ssize_t netdev_store(struct class_device *dev, return ret; } -NETDEVICE_SHOW(addr_len, fmt_dec); -NETDEVICE_SHOW(iflink, fmt_dec); -NETDEVICE_SHOW(ifindex, fmt_dec); -NETDEVICE_SHOW(features, fmt_long_hex); -NETDEVICE_SHOW(type, fmt_dec); +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); +NETDEVICE_SHOW_RO(ifindex, fmt_dec); +NETDEVICE_SHOW_RO(type, fmt_dec); +NETDEVICE_SHOW_RO(link_mode, fmt_dec); /* use same locking rules as GIFHWADDR ioctl's */ -static ssize_t format_addr(char *buf, const unsigned char *addr, int len) -{ - int i; - char *cp = buf; - - for (i = 0; i < len; i++) - cp += sprintf(cp, "%02x%c", addr[i], - i == (len - 1) ? '\n' : ':'); - return cp - buf; -} - -static ssize_t show_address(struct class_device *dev, char *buf) +static ssize_t address_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct net_device *net = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); if (dev_isalive(net)) - ret = format_addr(buf, net->dev_addr, net->addr_len); + ret = sysfs_format_mac(buf, net->dev_addr, net->addr_len); read_unlock(&dev_base_lock); return ret; } +static DEVICE_ATTR_RO(address); -static ssize_t show_broadcast(struct class_device *dev, char *buf) +static ssize_t broadcast_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct net_device *net = to_net_dev(dev); if (dev_isalive(net)) - return format_addr(buf, net->broadcast, net->addr_len); + return sysfs_format_mac(buf, net->broadcast, net->addr_len); return -EINVAL; } +static DEVICE_ATTR_RO(broadcast); + +static int change_carrier(struct net_device *net, unsigned long new_carrier) +{ + if (!netif_running(net)) + return -EINVAL; + return dev_change_carrier(net, (bool) new_carrier); +} + +static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_carrier); +} -static ssize_t show_carrier(struct class_device *dev, char *buf) +static ssize_t carrier_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) { @@ -132,33 +159,135 @@ static ssize_t show_carrier(struct class_device *dev, char *buf) } return -EINVAL; } +static DEVICE_ATTR_RW(carrier); + +static ssize_t speed_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!__ethtool_get_settings(netdev, &cmd)) + ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd)); + } + rtnl_unlock(); + return ret; +} +static DEVICE_ATTR_RO(speed); + +static ssize_t duplex_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!__ethtool_get_settings(netdev, &cmd)) { + const char *duplex; + switch (cmd.duplex) { + case DUPLEX_HALF: + duplex = "half"; + break; + case DUPLEX_FULL: + duplex = "full"; + break; + default: + duplex = "unknown"; + break; + } + ret = sprintf(buf, "%s\n", duplex); + } + } + rtnl_unlock(); + return ret; +} +static DEVICE_ATTR_RO(duplex); + +static ssize_t dormant_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + + if (netif_running(netdev)) + return sprintf(buf, fmt_dec, !!netif_dormant(netdev)); + + return -EINVAL; +} +static DEVICE_ATTR_RO(dormant); + +static const char *const operstates[] = { + "unknown", + "notpresent", /* currently unused */ + "down", + "lowerlayerdown", + "testing", /* currently unused */ + "dormant", + "up" +}; + +static ssize_t operstate_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct net_device *netdev = to_net_dev(dev); + unsigned char operstate; + + read_lock(&dev_base_lock); + operstate = netdev->operstate; + if (!netif_running(netdev)) + operstate = IF_OPER_DOWN; + read_unlock(&dev_base_lock); + + if (operstate >= ARRAY_SIZE(operstates)) + return -EINVAL; /* should not happen */ + + return sprintf(buf, "%s\n", operstates[operstate]); +} +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 */ -NETDEVICE_SHOW(mtu, fmt_dec); static int change_mtu(struct net_device *net, unsigned long new_mtu) { return dev_set_mtu(net, (int) new_mtu); } -static ssize_t store_mtu(struct class_device *dev, const char *buf, size_t len) +static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) { - return netdev_store(dev, buf, len, change_mtu); + return netdev_store(dev, attr, buf, len, change_mtu); } - -NETDEVICE_SHOW(flags, fmt_hex); +NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *net, unsigned long new_flags) { - return dev_change_flags(net, (unsigned) new_flags); + return dev_change_flags(net, (unsigned int) new_flags); } -static ssize_t store_flags(struct class_device *dev, const char *buf, size_t len) +static ssize_t flags_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) { - return netdev_store(dev, buf, len, change_flags); + return netdev_store(dev, attr, buf, len, change_flags); } - -NETDEVICE_SHOW(tx_queue_len, fmt_ulong); +NETDEVICE_SHOW_RW(flags, fmt_hex); static int change_tx_queue_len(struct net_device *net, unsigned long new_len) { @@ -166,71 +295,149 @@ static int change_tx_queue_len(struct net_device *net, unsigned long new_len) return 0; } -static ssize_t store_tx_queue_len(struct class_device *dev, const char *buf, size_t len) +static ssize_t tx_queue_len_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) { - return netdev_store(dev, buf, len, change_tx_queue_len); + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + return netdev_store(dev, attr, buf, len, change_tx_queue_len); } +NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong); + +static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); + size_t count = len; + ssize_t ret; + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; -NETDEVICE_SHOW(weight, fmt_dec); + /* ignore trailing newline */ + if (len > 0 && buf[len - 1] == '\n') + --count; -static int change_weight(struct net_device *net, unsigned long new_weight) + if (!rtnl_trylock()) + return restart_syscall(); + ret = dev_set_alias(netdev, buf, count); + rtnl_unlock(); + + return ret < 0 ? ret : len; +} + +static ssize_t ifalias_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct net_device *netdev = to_net_dev(dev); + ssize_t ret = 0; + + if (!rtnl_trylock()) + return restart_syscall(); + if (netdev->ifalias) + ret = sprintf(buf, "%s\n", netdev->ifalias); + rtnl_unlock(); + return ret; +} +static DEVICE_ATTR_RW(ifalias); + +static int change_group(struct net_device *net, unsigned long new_group) { - net->weight = new_weight; + dev_set_group(net, (int) new_group); return 0; } -static ssize_t store_weight(struct class_device *dev, const char *buf, size_t len) +static ssize_t group_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) { - return netdev_store(dev, buf, len, change_weight); + return netdev_store(dev, attr, buf, len, change_group); } +NETDEVICE_SHOW(group, fmt_dec); +static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store); -static struct class_device_attribute net_class_attributes[] = { - __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), - __ATTR(iflink, S_IRUGO, show_iflink, NULL), - __ATTR(ifindex, S_IRUGO, show_ifindex, NULL), - __ATTR(features, S_IRUGO, show_features, NULL), - __ATTR(type, S_IRUGO, show_type, NULL), - __ATTR(address, S_IRUGO, show_address, NULL), - __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), - __ATTR(carrier, S_IRUGO, show_carrier, NULL), - __ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu), - __ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags), - __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, - store_tx_queue_len), - __ATTR(weight, S_IRUGO | S_IWUSR, show_weight, store_weight), - {} +static ssize_t phys_port_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + struct netdev_phys_port_id ppid; + + ret = dev_get_phys_port_id(netdev, &ppid); + if (!ret) + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); + } + rtnl_unlock(); + + return ret; +} +static DEVICE_ATTR_RO(phys_port_id); + +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, + &dev_attr_addr_len.attr, + &dev_attr_link_mode.attr, + &dev_attr_address.attr, + &dev_attr_broadcast.attr, + &dev_attr_speed.attr, + &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, + &dev_attr_flags.attr, + &dev_attr_tx_queue_len.attr, + &dev_attr_phys_port_id.attr, + NULL, }; +ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ -static ssize_t netstat_show(const struct class_device *cd, char *buf, +static ssize_t netstat_show(const struct device *d, + struct device_attribute *attr, char *buf, unsigned long offset) { - struct net_device *dev = to_net_dev(cd); - struct net_device_stats *stats; + struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; - if (offset > sizeof(struct net_device_stats) || - offset % sizeof(unsigned long) != 0) - WARN_ON(1); + WARN_ON(offset > sizeof(struct rtnl_link_stats64) || + offset % sizeof(u64) != 0); read_lock(&dev_base_lock); - if (dev_isalive(dev) && dev->get_stats && - (stats = (*dev->get_stats)(dev))) - ret = sprintf(buf, fmt_ulong, - *(unsigned long *)(((u8 *) stats) + offset)); + if (dev_isalive(dev)) { + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); + ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset)); + } read_unlock(&dev_base_lock); return ret; } /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ -static ssize_t show_##name(struct class_device *cd, char *buf) \ +static ssize_t name##_show(struct device *d, \ + struct device_attribute *attr, char *buf) \ { \ - return netstat_show(cd, buf, \ - offsetof(struct net_device_stats, name)); \ + return netstat_show(d, attr, buf, \ + offsetof(struct rtnl_link_stats64, name)); \ } \ -static CLASS_DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) +static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); @@ -257,29 +464,29 @@ NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); static struct attribute *netstat_attrs[] = { - &class_device_attr_rx_packets.attr, - &class_device_attr_tx_packets.attr, - &class_device_attr_rx_bytes.attr, - &class_device_attr_tx_bytes.attr, - &class_device_attr_rx_errors.attr, - &class_device_attr_tx_errors.attr, - &class_device_attr_rx_dropped.attr, - &class_device_attr_tx_dropped.attr, - &class_device_attr_multicast.attr, - &class_device_attr_collisions.attr, - &class_device_attr_rx_length_errors.attr, - &class_device_attr_rx_over_errors.attr, - &class_device_attr_rx_crc_errors.attr, - &class_device_attr_rx_frame_errors.attr, - &class_device_attr_rx_fifo_errors.attr, - &class_device_attr_rx_missed_errors.attr, - &class_device_attr_tx_aborted_errors.attr, - &class_device_attr_tx_carrier_errors.attr, - &class_device_attr_tx_fifo_errors.attr, - &class_device_attr_tx_heartbeat_errors.attr, - &class_device_attr_tx_window_errors.attr, - &class_device_attr_rx_compressed.attr, - &class_device_attr_tx_compressed.attr, + &dev_attr_rx_packets.attr, + &dev_attr_tx_packets.attr, + &dev_attr_rx_bytes.attr, + &dev_attr_tx_bytes.attr, + &dev_attr_rx_errors.attr, + &dev_attr_tx_errors.attr, + &dev_attr_rx_dropped.attr, + &dev_attr_tx_dropped.attr, + &dev_attr_multicast.attr, + &dev_attr_collisions.attr, + &dev_attr_rx_length_errors.attr, + &dev_attr_rx_over_errors.attr, + &dev_attr_rx_crc_errors.attr, + &dev_attr_rx_frame_errors.attr, + &dev_attr_rx_fifo_errors.attr, + &dev_attr_rx_missed_errors.attr, + &dev_attr_tx_aborted_errors.attr, + &dev_attr_tx_carrier_errors.attr, + &dev_attr_tx_fifo_errors.attr, + &dev_attr_tx_heartbeat_errors.attr, + &dev_attr_tx_window_errors.attr, + &dev_attr_rx_compressed.attr, + &dev_attr_tx_compressed.attr, NULL }; @@ -289,176 +496,914 @@ static struct attribute_group netstat_group = { .attrs = netstat_attrs, }; -#ifdef WIRELESS_EXT -/* helper function that does all the locking etc for wireless stats */ -static ssize_t wireless_show(struct class_device *cd, char *buf, - ssize_t (*format)(const struct iw_statistics *, - char *)) +#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) +static struct attribute *wireless_attrs[] = { + NULL +}; + +static struct attribute_group wireless_group = { + .name = "wireless", + .attrs = wireless_attrs, +}; +#endif + +#else /* CONFIG_SYSFS */ +#define net_class_groups NULL +#endif /* CONFIG_SYSFS */ + +#ifdef CONFIG_SYSFS +#define to_rx_queue_attr(_attr) container_of(_attr, \ + struct rx_queue_attribute, attr) + +#define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) + +static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) { - struct net_device *dev = to_net_dev(cd); - const struct iw_statistics *iw = NULL; - ssize_t ret = -EINVAL; - - read_lock(&dev_base_lock); - if (dev_isalive(dev)) { - if(dev->wireless_handlers && - dev->wireless_handlers->get_wireless_stats) - iw = dev->wireless_handlers->get_wireless_stats(dev); - else if (dev->get_wireless_stats) - iw = dev->get_wireless_stats(dev); - if (iw != NULL) - ret = (*format)(iw, buf); + struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); + struct netdev_rx_queue *queue = to_rx_queue(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(queue, attribute, buf); +} + +static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); + struct netdev_rx_queue *queue = to_rx_queue(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(queue, attribute, buf, count); +} + +static const struct sysfs_ops rx_queue_sysfs_ops = { + .show = rx_queue_attr_show, + .store = rx_queue_attr_store, +}; + +#ifdef CONFIG_RPS +static ssize_t show_rps_map(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attribute, char *buf) +{ + struct rps_map *map; + cpumask_var_t mask; + size_t len = 0; + int i; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + rcu_read_lock(); + map = rcu_dereference(queue->rps_map); + if (map) + for (i = 0; i < map->len; i++) + cpumask_set_cpu(map->cpus[i], mask); + + len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); + if (PAGE_SIZE - len < 3) { + rcu_read_unlock(); + free_cpumask_var(mask); + return -EINVAL; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); - return ret; + free_cpumask_var(mask); + len += sprintf(buf + len, "\n"); + return len; } -/* show function template for wireless fields */ -#define WIRELESS_SHOW(name, field, format_string) \ -static ssize_t format_iw_##name(const struct iw_statistics *iw, char *buf) \ +static ssize_t store_rps_map(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct rps_map *old_map, *map; + cpumask_var_t mask; + int err, cpu, i; + static DEFINE_SPINLOCK(rps_map_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) { + free_cpumask_var(mask); + return err; + } + + map = kzalloc(max_t(unsigned int, + RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), + GFP_KERNEL); + if (!map) { + free_cpumask_var(mask); + return -ENOMEM; + } + + i = 0; + for_each_cpu_and(cpu, mask, cpu_online_mask) + map->cpus[i++] = cpu; + + if (i) + map->len = i; + else { + kfree(map); + map = NULL; + } + + spin_lock(&rps_map_lock); + old_map = rcu_dereference_protected(queue->rps_map, + lockdep_is_held(&rps_map_lock)); + rcu_assign_pointer(queue->rps_map, map); + spin_unlock(&rps_map_lock); + + if (map) + static_key_slow_inc(&rps_needed); + if (old_map) { + kfree_rcu(old_map, rcu); + static_key_slow_dec(&rps_needed); + } + free_cpumask_var(mask); + return len; +} + +static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + char *buf) +{ + struct rps_dev_flow_table *flow_table; + unsigned long val = 0; + + rcu_read_lock(); + flow_table = rcu_dereference(queue->rps_flow_table); + if (flow_table) + val = (unsigned long)flow_table->mask + 1; + rcu_read_unlock(); + + return sprintf(buf, "%lu\n", val); +} + +static void rps_dev_flow_table_release(struct rcu_head *rcu) +{ + struct rps_dev_flow_table *table = container_of(rcu, + struct rps_dev_flow_table, rcu); + vfree(table); +} + +static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + const char *buf, size_t len) +{ + unsigned long mask, count; + struct rps_dev_flow_table *table, *old_table; + static DEFINE_SPINLOCK(rps_dev_flow_lock); + int rc; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + rc = kstrtoul(buf, 0, &count); + if (rc < 0) + return rc; + + if (count) { + mask = count - 1; + /* mask = roundup_pow_of_two(count) - 1; + * without overflows... + */ + while ((mask | (mask >> 1)) != mask) + mask |= (mask >> 1); + /* On 64 bit arches, must check mask fits in table->mask (u32), + * and on 32bit arches, must check + * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. + */ +#if BITS_PER_LONG > 32 + if (mask > (unsigned long)(u32)mask) + return -EINVAL; +#else + if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) + / sizeof(struct rps_dev_flow)) { + /* Enforce a limit to prevent overflow */ + return -EINVAL; + } +#endif + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); + if (!table) + return -ENOMEM; + + table->mask = mask; + for (count = 0; count <= mask; count++) + table->flows[count].cpu = RPS_NO_CPU; + } else + table = NULL; + + spin_lock(&rps_dev_flow_lock); + old_table = rcu_dereference_protected(queue->rps_flow_table, + lockdep_is_held(&rps_dev_flow_lock)); + rcu_assign_pointer(queue->rps_flow_table, table); + spin_unlock(&rps_dev_flow_lock); + + if (old_table) + call_rcu(&old_table->rcu, rps_dev_flow_table_release); + + return len; +} + +static struct rx_queue_attribute rps_cpus_attribute = + __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + + +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = + __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); +#endif /* CONFIG_RPS */ + +static struct attribute *rx_queue_default_attrs[] = { +#ifdef CONFIG_RPS + &rps_cpus_attribute.attr, + &rps_dev_flow_table_cnt_attribute.attr, +#endif + NULL +}; + +static void rx_queue_release(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); +#ifdef CONFIG_RPS + struct rps_map *map; + struct rps_dev_flow_table *flow_table; + + + map = rcu_dereference_protected(queue->rps_map, 1); + if (map) { + RCU_INIT_POINTER(queue->rps_map, NULL); + kfree_rcu(map, rcu); + } + + flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); + if (flow_table) { + RCU_INIT_POINTER(queue->rps_flow_table, NULL); + call_rcu(&flow_table->rcu, rps_dev_flow_table_release); + } +#endif + + memset(kobj, 0, sizeof(*kobj)); + dev_put(queue->dev); +} + +static const void *rx_queue_namespace(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + +static struct kobj_type rx_queue_ktype = { + .sysfs_ops = &rx_queue_sysfs_ops, + .release = rx_queue_release, + .default_attrs = rx_queue_default_attrs, + .namespace = rx_queue_namespace +}; + +static int rx_queue_add_kobject(struct net_device *net, int index) +{ + struct netdev_rx_queue *queue = net->_rx + index; + struct kobject *kobj = &queue->kobj; + int error = 0; + + kobj->kset = net->queues_kset; + error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, + "rx-%u", index); + if (error) + goto exit; + + if (net->sysfs_rx_queue_group) { + error = sysfs_create_group(kobj, net->sysfs_rx_queue_group); + if (error) + goto exit; + } + + kobject_uevent(kobj, KOBJ_ADD); + dev_hold(queue->dev); + + return error; +exit: + kobject_put(kobj); + return error; +} +#endif /* CONFIG_SYSFS */ + +int +net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) +{ +#ifdef CONFIG_SYSFS + int i; + int error = 0; + +#ifndef CONFIG_RPS + if (!net->sysfs_rx_queue_group) + return 0; +#endif + for (i = old_num; i < new_num; i++) { + error = rx_queue_add_kobject(net, i); + if (error) { + new_num = old_num; + break; + } + } + + while (--i >= new_num) { + if (net->sysfs_rx_queue_group) + sysfs_remove_group(&net->_rx[i].kobj, + net->sysfs_rx_queue_group); + kobject_put(&net->_rx[i].kobj); + } + + return error; +#else + return 0; +#endif +} + +#ifdef CONFIG_SYSFS +/* + * netdev_queue sysfs structures and functions. + */ +struct netdev_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, char *buf); + ssize_t (*store)(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, const char *buf, size_t len); +}; +#define to_netdev_queue_attr(_attr) container_of(_attr, \ + struct netdev_queue_attribute, attr) + +#define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) + +static ssize_t netdev_queue_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + struct netdev_queue *queue = to_netdev_queue(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(queue, attribute, buf); +} + +static ssize_t netdev_queue_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) +{ + struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + struct netdev_queue *queue = to_netdev_queue(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(queue, attribute, buf, count); +} + +static const struct sysfs_ops netdev_queue_sysfs_ops = { + .show = netdev_queue_attr_show, + .store = netdev_queue_attr_store, +}; + +static ssize_t show_trans_timeout(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + char *buf) +{ + unsigned long trans_timeout; + + spin_lock_irq(&queue->_xmit_lock); + trans_timeout = queue->trans_timeout; + spin_unlock_irq(&queue->_xmit_lock); + + return sprintf(buf, "%lu", trans_timeout); +} + +static struct netdev_queue_attribute queue_trans_timeout = + __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); + +#ifdef CONFIG_BQL +/* + * Byte queue limits sysfs structures and functions. + */ +static ssize_t bql_show(char *buf, unsigned int value) +{ + return sprintf(buf, "%u\n", value); +} + +static ssize_t bql_set(const char *buf, const size_t count, + unsigned int *pvalue) +{ + unsigned int value; + int err; + + if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) + value = DQL_MAX_LIMIT; + else { + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + if (value > DQL_MAX_LIMIT) + return -EINVAL; + } + + *pvalue = value; + + return count; +} + +static ssize_t bql_show_hold_time(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, + char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); +} + +static ssize_t bql_set_hold_time(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct dql *dql = &queue->dql; + unsigned int value; + int err; + + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + + dql->slack_hold_time = msecs_to_jiffies(value); + + return len; +} + +static struct netdev_queue_attribute bql_hold_time_attribute = + __ATTR(hold_time, S_IRUGO | S_IWUSR, bql_show_hold_time, + bql_set_hold_time); + +static ssize_t bql_show_inflight(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, + char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed); +} + +static struct netdev_queue_attribute bql_inflight_attribute = + __ATTR(inflight, S_IRUGO, bql_show_inflight, NULL); + +#define BQL_ATTR(NAME, FIELD) \ +static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ + struct netdev_queue_attribute *attr, \ + char *buf) \ { \ - return sprintf(buf, format_string, iw->field); \ + return bql_show(buf, queue->dql.FIELD); \ } \ -static ssize_t show_iw_##name(struct class_device *cd, char *buf) \ + \ +static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ + struct netdev_queue_attribute *attr, \ + const char *buf, size_t len) \ { \ - return wireless_show(cd, buf, format_iw_##name); \ + return bql_set(buf, len, &queue->dql.FIELD); \ } \ -static CLASS_DEVICE_ATTR(name, S_IRUGO, show_iw_##name, NULL) - -WIRELESS_SHOW(status, status, fmt_hex); -WIRELESS_SHOW(link, qual.qual, fmt_dec); -WIRELESS_SHOW(level, qual.level, fmt_dec); -WIRELESS_SHOW(noise, qual.noise, fmt_dec); -WIRELESS_SHOW(nwid, discard.nwid, fmt_dec); -WIRELESS_SHOW(crypt, discard.code, fmt_dec); -WIRELESS_SHOW(fragment, discard.fragment, fmt_dec); -WIRELESS_SHOW(misc, discard.misc, fmt_dec); -WIRELESS_SHOW(retries, discard.retries, fmt_dec); -WIRELESS_SHOW(beacon, miss.beacon, fmt_dec); + \ +static struct netdev_queue_attribute bql_ ## NAME ## _attribute = \ + __ATTR(NAME, S_IRUGO | S_IWUSR, bql_show_ ## NAME, \ + bql_set_ ## NAME); + +BQL_ATTR(limit, limit) +BQL_ATTR(limit_max, max_limit) +BQL_ATTR(limit_min, min_limit) + +static struct attribute *dql_attrs[] = { + &bql_limit_attribute.attr, + &bql_limit_max_attribute.attr, + &bql_limit_min_attribute.attr, + &bql_hold_time_attribute.attr, + &bql_inflight_attribute.attr, + NULL +}; -static struct attribute *wireless_attrs[] = { - &class_device_attr_status.attr, - &class_device_attr_link.attr, - &class_device_attr_level.attr, - &class_device_attr_noise.attr, - &class_device_attr_nwid.attr, - &class_device_attr_crypt.attr, - &class_device_attr_fragment.attr, - &class_device_attr_retries.attr, - &class_device_attr_misc.attr, - &class_device_attr_beacon.attr, +static struct attribute_group dql_group = { + .name = "byte_queue_limits", + .attrs = dql_attrs, +}; +#endif /* CONFIG_BQL */ + +#ifdef CONFIG_XPS +static unsigned int get_netdev_queue_index(struct netdev_queue *queue) +{ + struct net_device *dev = queue->dev; + unsigned int i; + + i = queue - dev->_tx; + BUG_ON(i >= dev->num_tx_queues); + + return i; +} + + +static ssize_t show_xps_map(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, char *buf) +{ + struct net_device *dev = queue->dev; + struct xps_dev_maps *dev_maps; + cpumask_var_t mask; + unsigned long index; + size_t len = 0; + int i; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + for_each_possible_cpu(i) { + struct xps_map *map = + rcu_dereference(dev_maps->cpu_map[i]); + if (map) { + int j; + for (j = 0; j < map->len; j++) { + if (map->queues[j] == index) { + cpumask_set_cpu(i, mask); + break; + } + } + } + } + } + rcu_read_unlock(); + + len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); + if (PAGE_SIZE - len < 3) { + free_cpumask_var(mask); + return -EINVAL; + } + + free_cpumask_var(mask); + len += sprintf(buf + len, "\n"); + return len; +} + +static ssize_t store_xps_map(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct net_device *dev = queue->dev; + unsigned long index; + cpumask_var_t mask; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) { + free_cpumask_var(mask); + return err; + } + + err = netif_set_xps_queue(dev, mask, index); + + free_cpumask_var(mask); + + return err ? : len; +} + +static struct netdev_queue_attribute xps_cpus_attribute = + __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); +#endif /* CONFIG_XPS */ + +static struct attribute *netdev_queue_default_attrs[] = { + &queue_trans_timeout.attr, +#ifdef CONFIG_XPS + &xps_cpus_attribute.attr, +#endif NULL }; -static struct attribute_group wireless_group = { - .name = "wireless", - .attrs = wireless_attrs, +static void netdev_queue_release(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + + memset(kobj, 0, sizeof(*kobj)); + dev_put(queue->dev); +} + +static const void *netdev_queue_namespace(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + +static struct kobj_type netdev_queue_ktype = { + .sysfs_ops = &netdev_queue_sysfs_ops, + .release = netdev_queue_release, + .default_attrs = netdev_queue_default_attrs, + .namespace = netdev_queue_namespace, }; + +static int netdev_queue_add_kobject(struct net_device *net, int index) +{ + struct netdev_queue *queue = net->_tx + index; + struct kobject *kobj = &queue->kobj; + int error = 0; + + kobj->kset = net->queues_kset; + error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, + "tx-%u", index); + if (error) + goto exit; + +#ifdef CONFIG_BQL + error = sysfs_create_group(kobj, &dql_group); + if (error) + goto exit; #endif -#ifdef CONFIG_HOTPLUG -static int netdev_uevent(struct class_device *cd, char **envp, - int num_envp, char *buf, int size) + kobject_uevent(kobj, KOBJ_ADD); + dev_hold(queue->dev); + + return 0; +exit: + kobject_put(kobj); + return error; +} +#endif /* CONFIG_SYSFS */ + +int +netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { - struct net_device *dev = to_net_dev(cd); - int i = 0; - int n; +#ifdef CONFIG_SYSFS + int i; + int error = 0; + + for (i = old_num; i < new_num; i++) { + error = netdev_queue_add_kobject(net, i); + if (error) { + new_num = old_num; + break; + } + } - /* pass interface to uevent. */ - envp[i++] = buf; - n = snprintf(buf, size, "INTERFACE=%s", dev->name) + 1; - buf += n; - size -= n; + while (--i >= new_num) { + struct netdev_queue *queue = net->_tx + i; + +#ifdef CONFIG_BQL + sysfs_remove_group(&queue->kobj, &dql_group); +#endif + kobject_put(&queue->kobj); + } - if ((size <= 0) || (i >= num_envp)) + return error; +#else + return 0; +#endif /* CONFIG_SYSFS */ +} + +static int register_queue_kobjects(struct net_device *net) +{ + int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; + +#ifdef CONFIG_SYSFS + net->queues_kset = kset_create_and_add("queues", + NULL, &net->dev.kobj); + if (!net->queues_kset) return -ENOMEM; + real_rx = net->real_num_rx_queues; +#endif + real_tx = net->real_num_tx_queues; + + error = net_rx_queue_update_kobjects(net, 0, real_rx); + if (error) + goto error; + rxq = real_rx; + + error = netdev_queue_update_kobjects(net, 0, real_tx); + if (error) + goto error; + txq = real_tx; - envp[i] = NULL; return 0; + +error: + netdev_queue_update_kobjects(net, txq, 0); + net_rx_queue_update_kobjects(net, rxq, 0); + return error; +} + +static void remove_queue_kobjects(struct net_device *net) +{ + int real_rx = 0, real_tx = 0; + +#ifdef CONFIG_SYSFS + real_rx = net->real_num_rx_queues; +#endif + real_tx = net->real_num_tx_queues; + + net_rx_queue_update_kobjects(net, real_rx, 0); + netdev_queue_update_kobjects(net, real_tx, 0); +#ifdef CONFIG_SYSFS + kset_unregister(net->queues_kset); +#endif +} + +static bool net_current_may_mount(void) +{ + struct net *net = current->nsproxy->net_ns; + + return ns_capable(net->user_ns, CAP_SYS_ADMIN); } + +static void *net_grab_current_ns(void) +{ + struct net *ns = current->nsproxy->net_ns; +#ifdef CONFIG_NET_NS + if (ns) + atomic_inc(&ns->passive); #endif + return ns; +} + +static const void *net_initial_ns(void) +{ + return &init_net; +} + +static const void *net_netlink_ns(struct sock *sk) +{ + return sock_net(sk); +} + +struct kobj_ns_type_operations net_ns_type_operations = { + .type = KOBJ_NS_TYPE_NET, + .current_may_mount = net_current_may_mount, + .grab_current_ns = net_grab_current_ns, + .netlink_ns = net_netlink_ns, + .initial_ns = net_initial_ns, + .drop_ns = net_drop_ns, +}; +EXPORT_SYMBOL_GPL(net_ns_type_operations); + +static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) +{ + struct net_device *dev = to_net_dev(d); + int retval; + + /* pass interface to uevent. */ + retval = add_uevent_var(env, "INTERFACE=%s", dev->name); + if (retval) + goto exit; + + /* pass ifindex to uevent. + * ifindex is useful as it won't change (interface name may change) + * and is what RtNetlink uses natively. */ + retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); + +exit: + return retval; +} /* - * netdev_release -- destroy and free a dead device. - * Called when last reference to class_device kobject is gone. + * netdev_release -- destroy and free a dead device. + * Called when last reference to device kobject is gone. */ -static void netdev_release(struct class_device *cd) +static void netdev_release(struct device *d) { - struct net_device *dev - = container_of(cd, struct net_device, class_dev); + struct net_device *dev = to_net_dev(d); BUG_ON(dev->reg_state != NETREG_RELEASED); - kfree((char *)dev - dev->padded); + kfree(dev->ifalias); + netdev_freemem(dev); +} + +static const void *net_namespace(struct device *d) +{ + struct net_device *dev; + dev = container_of(d, struct net_device, dev); + return dev_net(dev); } static struct class net_class = { .name = "net", - .release = netdev_release, - .class_dev_attrs = net_class_attributes, -#ifdef CONFIG_HOTPLUG - .uevent = netdev_uevent, -#endif + .dev_release = netdev_release, + .dev_groups = net_class_groups, + .dev_uevent = netdev_uevent, + .ns_type = &net_ns_type_operations, + .namespace = net_namespace, }; -void netdev_unregister_sysfs(struct net_device * net) +/* Delete sysfs entries but hold kobject reference until after all + * netdev references are gone. + */ +void netdev_unregister_kobject(struct net_device * net) { - struct class_device * class_dev = &(net->class_dev); + struct device *dev = &(net->dev); - if (net->get_stats) - sysfs_remove_group(&class_dev->kobj, &netstat_group); + kobject_get(&dev->kobj); -#ifdef WIRELESS_EXT - if (net->get_wireless_stats || (net->wireless_handlers && - net->wireless_handlers->get_wireless_stats)) - sysfs_remove_group(&class_dev->kobj, &wireless_group); -#endif - class_device_del(class_dev); + remove_queue_kobjects(net); + + pm_runtime_set_memalloc_noio(dev, false); + device_del(dev); } /* Create sysfs entries for network device. */ -int netdev_register_sysfs(struct net_device *net) +int netdev_register_kobject(struct net_device *net) { - struct class_device *class_dev = &(net->class_dev); - int ret; + struct device *dev = &(net->dev); + const struct attribute_group **groups = net->sysfs_groups; + int error = 0; + + device_initialize(dev); + dev->class = &net_class; + dev->platform_data = net; + dev->groups = groups; + + dev_set_name(dev, "%s", net->name); + +#ifdef CONFIG_SYSFS + /* Allow for a device specific group */ + if (*groups) + groups++; + + *groups++ = &netstat_group; + +#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) + if (net->ieee80211_ptr) + *groups++ = &wireless_group; +#if IS_ENABLED(CONFIG_WIRELESS_EXT) + else if (net->wireless_handlers) + *groups++ = &wireless_group; +#endif +#endif +#endif /* CONFIG_SYSFS */ - class_dev->class = &net_class; - class_dev->class_data = net; + error = device_add(dev); + if (error) + return error; - strlcpy(class_dev->class_id, net->name, BUS_ID_SIZE); - if ((ret = class_device_register(class_dev))) - goto out; + error = register_queue_kobjects(net); + if (error) { + device_del(dev); + return error; + } - if (net->get_stats && - (ret = sysfs_create_group(&class_dev->kobj, &netstat_group))) - goto out_unreg; + pm_runtime_set_memalloc_noio(dev, true); -#ifdef WIRELESS_EXT - if (net->get_wireless_stats || (net->wireless_handlers && - net->wireless_handlers->get_wireless_stats)) { - ret = sysfs_create_group(&class_dev->kobj, &wireless_group); - if (ret) - goto out_cleanup; - } - return 0; -out_cleanup: - if (net->get_stats) - sysfs_remove_group(&class_dev->kobj, &netstat_group); -#else - return 0; -#endif + return error; +} -out_unreg: - printk(KERN_WARNING "%s: sysfs attribute registration failed %d\n", - net->name, ret); - class_device_unregister(class_dev); -out: - return ret; +int netdev_class_create_file_ns(struct class_attribute *class_attr, + const void *ns) +{ + return class_create_file_ns(&net_class, class_attr, ns); +} +EXPORT_SYMBOL(netdev_class_create_file_ns); + +void netdev_class_remove_file_ns(struct class_attribute *class_attr, + const void *ns) +{ + class_remove_file_ns(&net_class, class_attr, ns); } +EXPORT_SYMBOL(netdev_class_remove_file_ns); -int netdev_sysfs_init(void) +int __init netdev_kobject_init(void) { + kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); } diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h new file mode 100644 index 00000000000..2745a1b51e0 --- /dev/null +++ b/net/core/net-sysfs.h @@ -0,0 +1,11 @@ +#ifndef __NET_SYSFS_H__ +#define __NET_SYSFS_H__ + +int __init netdev_kobject_init(void); +int netdev_register_kobject(struct net_device *); +void netdev_unregister_kobject(struct net_device *); +int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); +int netdev_queue_update_kobjects(struct net_device *net, + int old_num, int new_num); + +#endif diff --git a/net/core/net-traces.c b/net/core/net-traces.c new file mode 100644 index 00000000000..ba3c0120786 --- /dev/null +++ b/net/core/net-traces.c @@ -0,0 +1,37 @@ +/* + * consolidates trace point definitions + * + * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> + */ + +#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> +#include <linux/export.h> +#include <linux/netpoll.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/rcupdate.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/netlink.h> +#include <linux/net_dropmon.h> +#include <linux/slab.h> + +#include <asm/unaligned.h> +#include <asm/bitops.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/skb.h> +#include <trace/events/net.h> +#include <trace/events/napi.h> +#include <trace/events/sock.h> +#include <trace/events/udp.h> + +EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); + +EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c new file mode 100644 index 00000000000..85b62691f4f --- /dev/null +++ b/net/core/net_namespace.c @@ -0,0 +1,676 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/workqueue.h> +#include <linux/rtnetlink.h> +#include <linux/cache.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/delay.h> +#include <linux/sched.h> +#include <linux/idr.h> +#include <linux/rculist.h> +#include <linux/nsproxy.h> +#include <linux/fs.h> +#include <linux/proc_ns.h> +#include <linux/file.h> +#include <linux/export.h> +#include <linux/user_namespace.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> + +/* + * Our network namespace constructor/destructor lists + */ + +static LIST_HEAD(pernet_list); +static struct list_head *first_device = &pernet_list; +DEFINE_MUTEX(net_mutex); + +LIST_HEAD(net_namespace_list); +EXPORT_SYMBOL_GPL(net_namespace_list); + +struct net init_net = { + .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), +}; +EXPORT_SYMBOL(init_net); + +#define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ + +static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; + +static struct net_generic *net_alloc_generic(void) +{ + struct net_generic *ng; + size_t generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); + + ng = kzalloc(generic_size, GFP_KERNEL); + if (ng) + ng->len = max_gen_ptrs; + + return ng; +} + +static int net_assign_generic(struct net *net, int id, void *data) +{ + struct net_generic *ng, *old_ng; + + BUG_ON(!mutex_is_locked(&net_mutex)); + BUG_ON(id == 0); + + old_ng = rcu_dereference_protected(net->gen, + lockdep_is_held(&net_mutex)); + ng = old_ng; + if (old_ng->len >= id) + goto assign; + + ng = net_alloc_generic(); + if (ng == NULL) + return -ENOMEM; + + /* + * Some synchronisation notes: + * + * The net_generic explores the net->gen array inside rcu + * read section. Besides once set the net->gen->ptr[x] + * pointer never changes (see rules in netns/generic.h). + * + * That said, we simply duplicate this array and schedule + * the old copy for kfree after a grace period. + */ + + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); + + rcu_assign_pointer(net->gen, ng); + kfree_rcu(old_ng, rcu); +assign: + ng->ptr[id - 1] = data; + return 0; +} + +static int ops_init(const struct pernet_operations *ops, struct net *net) +{ + int err = -ENOMEM; + void *data = NULL; + + if (ops->id && ops->size) { + data = kzalloc(ops->size, GFP_KERNEL); + if (!data) + goto out; + + err = net_assign_generic(net, *ops->id, data); + if (err) + goto cleanup; + } + err = 0; + if (ops->init) + err = ops->init(net); + if (!err) + return 0; + +cleanup: + kfree(data); + +out: + return err; +} + +static void ops_free(const struct pernet_operations *ops, struct net *net) +{ + if (ops->id && ops->size) { + int id = *ops->id; + kfree(net_generic(net, id)); + } +} + +static void ops_exit_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->exit) { + list_for_each_entry(net, net_exit_list, exit_list) + ops->exit(net); + } + if (ops->exit_batch) + ops->exit_batch(net_exit_list); +} + +static void ops_free_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->size && ops->id) { + list_for_each_entry(net, net_exit_list, exit_list) + ops_free(ops, net); + } +} + +/* + * setup_net runs the initializers for the network namespace object. + */ +static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) +{ + /* Must be called with net_mutex held */ + const struct pernet_operations *ops, *saved_ops; + int error = 0; + LIST_HEAD(net_exit_list); + + atomic_set(&net->count, 1); + atomic_set(&net->passive, 1); + net->dev_base_seq = 1; + net->user_ns = user_ns; + +#ifdef NETNS_REFCNT_DEBUG + atomic_set(&net->use_count, 0); +#endif + + list_for_each_entry(ops, &pernet_list, list) { + error = ops_init(ops, net); + if (error < 0) + goto out_undo; + } +out: + return error; + +out_undo: + /* Walk through the list backwards calling the exit functions + * for the pernet modules whose init functions did not fail. + */ + list_add(&net->exit_list, &net_exit_list); + saved_ops = ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + ops = saved_ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); + + rcu_barrier(); + goto out; +} + + +#ifdef CONFIG_NET_NS +static struct kmem_cache *net_cachep; +static struct workqueue_struct *netns_wq; + +static struct net *net_alloc(void) +{ + struct net *net = NULL; + struct net_generic *ng; + + ng = net_alloc_generic(); + if (!ng) + goto out; + + net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); + if (!net) + goto out_free; + + rcu_assign_pointer(net->gen, ng); +out: + return net; + +out_free: + kfree(ng); + goto out; +} + +static void net_free(struct net *net) +{ +#ifdef NETNS_REFCNT_DEBUG + if (unlikely(atomic_read(&net->use_count) != 0)) { + pr_emerg("network namespace not free! Usage: %d\n", + atomic_read(&net->use_count)); + return; + } +#endif + kfree(net->gen); + kmem_cache_free(net_cachep, net); +} + +void net_drop_ns(void *p) +{ + struct net *ns = p; + if (ns && atomic_dec_and_test(&ns->passive)) + net_free(ns); +} + +struct net *copy_net_ns(unsigned long flags, + struct user_namespace *user_ns, struct net *old_net) +{ + struct net *net; + int rv; + + if (!(flags & CLONE_NEWNET)) + return get_net(old_net); + + net = net_alloc(); + if (!net) + return ERR_PTR(-ENOMEM); + + get_user_ns(user_ns); + + mutex_lock(&net_mutex); + rv = setup_net(net, user_ns); + if (rv == 0) { + rtnl_lock(); + list_add_tail_rcu(&net->list, &net_namespace_list); + rtnl_unlock(); + } + mutex_unlock(&net_mutex); + if (rv < 0) { + put_user_ns(user_ns); + net_drop_ns(net); + return ERR_PTR(rv); + } + return net; +} + +static DEFINE_SPINLOCK(cleanup_list_lock); +static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ + +static void cleanup_net(struct work_struct *work) +{ + const struct pernet_operations *ops; + struct net *net, *tmp; + struct list_head net_kill_list; + LIST_HEAD(net_exit_list); + + /* Atomically snapshot the list of namespaces to cleanup */ + spin_lock_irq(&cleanup_list_lock); + list_replace_init(&cleanup_list, &net_kill_list); + spin_unlock_irq(&cleanup_list_lock); + + mutex_lock(&net_mutex); + + /* Don't let anyone else find us. */ + rtnl_lock(); + list_for_each_entry(net, &net_kill_list, cleanup_list) { + list_del_rcu(&net->list); + list_add_tail(&net->exit_list, &net_exit_list); + } + rtnl_unlock(); + + /* + * Another CPU might be rcu-iterating the list, wait for it. + * This needs to be before calling the exit() notifiers, so + * the rcu_barrier() below isn't sufficient alone. + */ + synchronize_rcu(); + + /* Run all of the network namespace exit methods */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + /* Free the net generic variables */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); + + mutex_unlock(&net_mutex); + + /* Ensure there are no outstanding rcu callbacks using this + * network namespace. + */ + rcu_barrier(); + + /* Finally it is safe to free my network namespace structure */ + list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { + list_del_init(&net->exit_list); + put_user_ns(net->user_ns); + net_drop_ns(net); + } +} +static DECLARE_WORK(net_cleanup_work, cleanup_net); + +void __put_net(struct net *net) +{ + /* Cleanup the network namespace in process context */ + unsigned long flags; + + spin_lock_irqsave(&cleanup_list_lock, flags); + list_add(&net->cleanup_list, &cleanup_list); + spin_unlock_irqrestore(&cleanup_list_lock, flags); + + queue_work(netns_wq, &net_cleanup_work); +} +EXPORT_SYMBOL_GPL(__put_net); + +struct net *get_net_ns_by_fd(int fd) +{ + struct proc_ns *ei; + struct file *file; + struct net *net; + + file = proc_ns_fget(fd); + if (IS_ERR(file)) + return ERR_CAST(file); + + ei = get_proc_ns(file_inode(file)); + if (ei->ns_ops == &netns_operations) + net = get_net(ei->ns); + else + net = ERR_PTR(-EINVAL); + + fput(file); + return net; +} + +#else +struct net *get_net_ns_by_fd(int fd) +{ + return ERR_PTR(-EINVAL); +} +#endif + +struct net *get_net_ns_by_pid(pid_t pid) +{ + struct task_struct *tsk; + struct net *net; + + /* Lookup the network namespace */ + net = ERR_PTR(-ESRCH); + rcu_read_lock(); + tsk = find_task_by_vpid(pid); + if (tsk) { + struct nsproxy *nsproxy; + nsproxy = task_nsproxy(tsk); + if (nsproxy) + net = get_net(nsproxy->net_ns); + } + rcu_read_unlock(); + return net; +} +EXPORT_SYMBOL_GPL(get_net_ns_by_pid); + +static __net_init int net_ns_net_init(struct net *net) +{ + return proc_alloc_inum(&net->proc_inum); +} + +static __net_exit void net_ns_net_exit(struct net *net) +{ + proc_free_inum(net->proc_inum); +} + +static struct pernet_operations __net_initdata net_ns_ops = { + .init = net_ns_net_init, + .exit = net_ns_net_exit, +}; + +static int __init net_ns_init(void) +{ + struct net_generic *ng; + +#ifdef CONFIG_NET_NS + net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), + SMP_CACHE_BYTES, + SLAB_PANIC, NULL); + + /* Create workqueue for cleanup */ + netns_wq = create_singlethread_workqueue("netns"); + if (!netns_wq) + panic("Could not create netns workq"); +#endif + + ng = net_alloc_generic(); + if (!ng) + panic("Could not allocate generic netns"); + + rcu_assign_pointer(init_net.gen, ng); + + mutex_lock(&net_mutex); + if (setup_net(&init_net, &init_user_ns)) + panic("Could not setup the initial network namespace"); + + rtnl_lock(); + list_add_tail_rcu(&init_net.list, &net_namespace_list); + rtnl_unlock(); + + mutex_unlock(&net_mutex); + + register_pernet_subsys(&net_ns_ops); + + return 0; +} + +pure_initcall(net_ns_init); + +#ifdef CONFIG_NET_NS +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + struct net *net; + int error; + LIST_HEAD(net_exit_list); + + list_add_tail(&ops->list, list); + if (ops->init || (ops->id && ops->size)) { + for_each_net(net) { + error = ops_init(ops, net); + if (error) + goto out_undo; + list_add_tail(&net->exit_list, &net_exit_list); + } + } + return 0; + +out_undo: + /* If I have an error cleanup all namespaces I initialized */ + list_del(&ops->list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); + return error; +} + +static void __unregister_pernet_operations(struct pernet_operations *ops) +{ + struct net *net; + LIST_HEAD(net_exit_list); + + list_del(&ops->list); + for_each_net(net) + list_add_tail(&net->exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); +} + +#else + +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + return ops_init(ops, &init_net); +} + +static void __unregister_pernet_operations(struct pernet_operations *ops) +{ + LIST_HEAD(net_exit_list); + list_add(&init_net.exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); +} + +#endif /* CONFIG_NET_NS */ + +static DEFINE_IDA(net_generic_ids); + +static int register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + int error; + + if (ops->id) { +again: + error = ida_get_new_above(&net_generic_ids, 1, ops->id); + if (error < 0) { + if (error == -EAGAIN) { + ida_pre_get(&net_generic_ids, GFP_KERNEL); + goto again; + } + return error; + } + max_gen_ptrs = max_t(unsigned int, max_gen_ptrs, *ops->id); + } + error = __register_pernet_operations(list, ops); + if (error) { + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); + } + + return error; +} + +static void unregister_pernet_operations(struct pernet_operations *ops) +{ + + __unregister_pernet_operations(ops); + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); +} + +/** + * register_pernet_subsys - register a network namespace subsystem + * @ops: pernet operations structure for the subsystem + * + * Register a subsystem which has init and exit functions + * that are called when network namespaces are created and + * destroyed respectively. + * + * When registered all network namespace init functions are + * called for every existing network namespace. Allowing kernel + * modules to have a race free view of the set of network namespaces. + * + * When a new network namespace is created all of the init + * methods are called in the order in which they were registered. + * + * When a network namespace is destroyed all of the exit methods + * are called in the reverse of the order with which they were + * registered. + */ +int register_pernet_subsys(struct pernet_operations *ops) +{ + int error; + mutex_lock(&net_mutex); + error = register_pernet_operations(first_device, ops); + mutex_unlock(&net_mutex); + return error; +} +EXPORT_SYMBOL_GPL(register_pernet_subsys); + +/** + * unregister_pernet_subsys - unregister a network namespace subsystem + * @ops: pernet operations structure to manipulate + * + * Remove the pernet operations structure from the list to be + * used when network namespaces are created or destroyed. In + * addition run the exit method for all existing network + * namespaces. + */ +void unregister_pernet_subsys(struct pernet_operations *ops) +{ + mutex_lock(&net_mutex); + unregister_pernet_operations(ops); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL_GPL(unregister_pernet_subsys); + +/** + * register_pernet_device - register a network namespace device + * @ops: pernet operations structure for the subsystem + * + * Register a device which has init and exit functions + * that are called when network namespaces are created and + * destroyed respectively. + * + * When registered all network namespace init functions are + * called for every existing network namespace. Allowing kernel + * modules to have a race free view of the set of network namespaces. + * + * When a new network namespace is created all of the init + * methods are called in the order in which they were registered. + * + * When a network namespace is destroyed all of the exit methods + * are called in the reverse of the order with which they were + * registered. + */ +int register_pernet_device(struct pernet_operations *ops) +{ + int error; + mutex_lock(&net_mutex); + error = register_pernet_operations(&pernet_list, ops); + if (!error && (first_device == &pernet_list)) + first_device = &ops->list; + mutex_unlock(&net_mutex); + return error; +} +EXPORT_SYMBOL_GPL(register_pernet_device); + +/** + * unregister_pernet_device - unregister a network namespace netdevice + * @ops: pernet operations structure to manipulate + * + * Remove the pernet operations structure from the list to be + * used when network namespaces are created or destroyed. In + * addition run the exit method for all existing network + * namespaces. + */ +void unregister_pernet_device(struct pernet_operations *ops) +{ + mutex_lock(&net_mutex); + if (&ops->list == first_device) + first_device = first_device->next; + unregister_pernet_operations(ops); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL_GPL(unregister_pernet_device); + +#ifdef CONFIG_NET_NS +static void *netns_get(struct task_struct *task) +{ + struct net *net = NULL; + struct nsproxy *nsproxy; + + rcu_read_lock(); + nsproxy = task_nsproxy(task); + if (nsproxy) + net = get_net(nsproxy->net_ns); + rcu_read_unlock(); + + return net; +} + +static void netns_put(void *ns) +{ + put_net(ns); +} + +static int netns_install(struct nsproxy *nsproxy, void *ns) +{ + struct net *net = ns; + + if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return -EPERM; + + put_net(nsproxy->net_ns); + nsproxy->net_ns = get_net(net); + return 0; +} + +static unsigned int netns_inum(void *ns) +{ + struct net *net = ns; + return net->proc_inum; +} + +const struct proc_ns_operations netns_operations = { + .name = "net", + .type = CLONE_NEWNET, + .get = netns_get, + .put = netns_put, + .install = netns_install, + .inum = netns_inum, +}; +#endif diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c new file mode 100644 index 00000000000..30d903b19c6 --- /dev/null +++ b/net/core/netclassid_cgroup.c @@ -0,0 +1,111 @@ +/* + * net/core/netclassid_cgroup.c Classid Cgroupfs Handling + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/cgroup.h> +#include <linux/fdtable.h> +#include <net/cls_cgroup.h> +#include <net/sock.h> + +static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cgroup_cls_state, css) : NULL; +} + +struct cgroup_cls_state *task_cls_state(struct task_struct *p) +{ + return css_cls_state(task_css(p, net_cls_cgrp_id)); +} +EXPORT_SYMBOL_GPL(task_cls_state); + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_cls_state *cs; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + return &cs->css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + struct cgroup_cls_state *parent = css_cls_state(css->parent); + + if (parent) + cs->classid = parent->classid; + + return 0; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_cls_state(css)); +} + +static int update_classid(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + + if (sock) + sock->sk->sk_classid = (u32)(unsigned long)v; + + return 0; +} + +static void cgrp_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; + struct task_struct *p; + + cgroup_taskset_for_each(p, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_classid, v); + task_unlock(p); + } +} + +static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css_cls_state(css)->classid; +} + +static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, + u64 value) +{ + css_cls_state(css)->classid = (u32) value; + + return 0; +} + +static struct cftype ss_files[] = { + { + .name = "classid", + .read_u64 = read_classid, + .write_u64 = write_classid, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_cls_cgrp_subsys = { + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = cgrp_attach, + .base_cftypes = ss_files, +}; diff --git a/net/core/netevent.c b/net/core/netevent.c new file mode 100644 index 00000000000..f17ccd291d3 --- /dev/null +++ b/net/core/netevent.c @@ -0,0 +1,70 @@ +/* + * Network event notifiers + * + * Authors: + * Tom Tucker <tom@opengridcomputing.com> + * Steve Wise <swise@opengridcomputing.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Fixes: + */ + +#include <linux/rtnetlink.h> +#include <linux/notifier.h> +#include <linux/export.h> +#include <net/netevent.h> + +static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); + +/** + * register_netevent_notifier - register a netevent notifier block + * @nb: notifier + * + * Register a notifier to be called when a netevent occurs. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + */ +int register_netevent_notifier(struct notifier_block *nb) +{ + int err; + + err = atomic_notifier_chain_register(&netevent_notif_chain, nb); + return err; +} +EXPORT_SYMBOL_GPL(register_netevent_notifier); + +/** + * netevent_unregister_notifier - unregister a netevent notifier block + * @nb: notifier + * + * Unregister a notifier previously registered by + * register_neigh_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. + */ + +int unregister_netevent_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&netevent_notif_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_netevent_notifier); + +/** + * call_netevent_notifiers - call all netevent notifier blocks + * @val: value passed unmodified to notifier function + * @v: pointer passed unmodified to notifier function + * + * Call all neighbour notifier blocks. Parameters and return value + * are as for notifier_call_chain(). + */ + +int call_netevent_notifiers(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&netevent_notif_chain, val, v); +} +EXPORT_SYMBOL_GPL(call_netevent_notifiers); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index ea51f8d02eb..e33937fb32a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -9,7 +9,10 @@ * Copyright (C) 2002 Red Hat, Inc. */ -#include <linux/smp_lock.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/moduleparam.h> +#include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> @@ -22,9 +25,16 @@ #include <linux/delay.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/addrconf.h> +#include <net/ndisc.h> +#include <net/ip6_checksum.h> #include <asm/unaligned.h> +#include <trace/events/napi.h> /* * We maintain a small pool of fully-sized skbs, to make sure the @@ -33,89 +43,95 @@ #define MAX_UDP_CHUNK 1460 #define MAX_SKBS 32 -#define MAX_QUEUE_DEPTH (MAX_SKBS / 2) -#define MAX_RETRIES 20000 - -static DEFINE_SPINLOCK(skb_list_lock); -static int nr_skbs; -static struct sk_buff *skbs; -static DEFINE_SPINLOCK(queue_lock); -static int queue_depth; -static struct sk_buff *queue_head, *queue_tail; +static struct sk_buff_head skb_pool; -static atomic_t trapped; +DEFINE_STATIC_SRCU(netpoll_srcu); -#define NETPOLL_RX_ENABLED 1 -#define NETPOLL_RX_DROP 2 +#define USEC_PER_POLL 50 -#define MAX_SKB_SIZE \ - (MAX_UDP_CHUNK + sizeof(struct udphdr) + \ - sizeof(struct iphdr) + sizeof(struct ethhdr)) +#define MAX_SKB_SIZE \ + (sizeof(struct ethhdr) + \ + sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + MAX_UDP_CHUNK) static void zap_completion_queue(void); +static void netpoll_async_cleanup(struct work_struct *work); -static void queue_process(void *p) -{ - unsigned long flags; - struct sk_buff *skb; - - while (queue_head) { - spin_lock_irqsave(&queue_lock, flags); - - skb = queue_head; - queue_head = skb->next; - if (skb == queue_tail) - queue_head = NULL; - - queue_depth--; +static unsigned int carrier_timeout = 4; +module_param(carrier_timeout, uint, 0644); - spin_unlock_irqrestore(&queue_lock, flags); +#define np_info(np, fmt, ...) \ + pr_info("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_err(np, fmt, ...) \ + pr_err("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_notice(np, fmt, ...) \ + pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) - dev_queue_xmit(skb); - } -} - -static DECLARE_WORK(send_queue, queue_process, NULL); - -void netpoll_queue(struct sk_buff *skb) +static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq) { - unsigned long flags; - - if (queue_depth == MAX_QUEUE_DEPTH) { - __kfree_skb(skb); - return; + 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; } - spin_lock_irqsave(&queue_lock, flags); - if (!queue_head) - queue_head = skb; - else - queue_tail->next = skb; - queue_tail = skb; - queue_depth++; - spin_unlock_irqrestore(&queue_lock, flags); + status = ops->ndo_start_xmit(skb, dev); + if (status == NETDEV_TX_OK) + txq_trans_update(txq); - schedule_work(&send_queue); +out: + return status; } -static int checksum_udp(struct sk_buff *skb, struct udphdr *uh, - unsigned short ulen, u32 saddr, u32 daddr) +static void queue_process(struct work_struct *work) { - unsigned int psum; - - if (uh->check == 0 || skb->ip_summed == CHECKSUM_UNNECESSARY) - return 0; + struct netpoll_info *npinfo = + container_of(work, struct netpoll_info, tx_work.work); + struct sk_buff *skb; + unsigned long flags; - psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); + while ((skb = skb_dequeue(&npinfo->txq))) { + struct net_device *dev = skb->dev; + struct netdev_queue *txq; - if (skb->ip_summed == CHECKSUM_HW && - !(u16)csum_fold(csum_add(psum, skb->csum))) - return 0; + if (!netif_device_present(dev) || !netif_running(dev)) { + kfree_skb(skb); + continue; + } - skb->csum = psum; + txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); - return __skb_checksum_complete(skb); + local_irq_save(flags); + HARD_TX_LOCK(dev, txq, smp_processor_id()); + if (netif_xmit_frozen_or_stopped(txq) || + netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { + skb_queue_head(&npinfo->txq, skb); + HARD_TX_UNLOCK(dev, txq); + local_irq_restore(flags); + + schedule_delayed_work(&npinfo->tx_work, HZ/10); + return; + } + HARD_TX_UNLOCK(dev, txq); + local_irq_restore(flags); + } } /* @@ -128,60 +144,114 @@ static int 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 void poll_napi(struct netpoll *np) +static int poll_one_napi(struct napi_struct *napi, int budget) { - struct netpoll_info *npinfo = np->dev->npinfo; - int budget = 16; + int work; - if (test_bit(__LINK_STATE_RX_SCHED, &np->dev->state) && - npinfo->poll_owner != smp_processor_id() && - spin_trylock(&npinfo->poll_lock)) { - npinfo->rx_flags |= NETPOLL_RX_DROP; - atomic_inc(&trapped); + /* net_rx_action's ->poll() invocations and our's are + * synchronized by this test which is only made while + * holding the napi->poll_lock. + */ + if (!test_bit(NAPI_STATE_SCHED, &napi->state)) + return budget; - np->dev->poll(np->dev, &budget); + set_bit(NAPI_STATE_NPSVC, &napi->state); - atomic_dec(&trapped); - npinfo->rx_flags &= ~NETPOLL_RX_DROP; - spin_unlock(&npinfo->poll_lock); + 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); + + return budget - work; +} + +static void poll_napi(struct net_device *dev, int budget) +{ + struct napi_struct *napi; + + 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(napi, budget); + spin_unlock(&napi->poll_lock); + } } } -void netpoll_poll(struct netpoll *np) +static void netpoll_poll_dev(struct net_device *dev) { - if(!np->dev || !netif_running(np->dev) || !np->dev->poll_controller) + 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 + * while changing device state + */ + if (down_trylock(&ni->dev_lock)) + return; + + if (!netif_running(dev)) { + up(&ni->dev_lock); return; + } + + ops = dev->netdev_ops; + if (!ops->ndo_poll_controller) { + up(&ni->dev_lock); + return; + } /* Process pending work on NIC */ - np->dev->poll_controller(np->dev); - if (np->dev->poll) - poll_napi(np); + ops->ndo_poll_controller(dev); + + poll_napi(dev, budget); + + up(&ni->dev_lock); zap_completion_queue(); } +void netpoll_poll_disable(struct net_device *dev) +{ + struct netpoll_info *ni; + int idx; + might_sleep(); + idx = srcu_read_lock(&netpoll_srcu); + ni = srcu_dereference(dev->npinfo, &netpoll_srcu); + if (ni) + down(&ni->dev_lock); + srcu_read_unlock(&netpoll_srcu, idx); +} +EXPORT_SYMBOL(netpoll_poll_disable); + +void netpoll_poll_enable(struct net_device *dev) +{ + struct netpoll_info *ni; + rcu_read_lock(); + ni = rcu_dereference(dev->npinfo); + if (ni) + up(&ni->dev_lock); + rcu_read_unlock(); +} +EXPORT_SYMBOL(netpoll_poll_enable); + static void refill_skbs(void) { struct sk_buff *skb; unsigned long flags; - spin_lock_irqsave(&skb_list_lock, flags); - while (nr_skbs < MAX_SKBS) { + spin_lock_irqsave(&skb_pool.lock, flags); + while (skb_pool.qlen < MAX_SKBS) { skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); if (!skb) break; - skb->next = skbs; - skbs = skb; - nr_skbs++; + __skb_queue_tail(&skb_pool, skb); } - spin_unlock_irqrestore(&skb_list_lock, flags); + spin_unlock_irqrestore(&skb_pool.lock, flags); } static void zap_completion_queue(void) @@ -200,48 +270,37 @@ 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 + } else { __kfree_skb(skb); + } } } put_cpu_var(softnet_data); } -static struct sk_buff * find_skb(struct netpoll *np, int len, int reserve) +static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve) { - int once = 1, count = 0; - unsigned long flags; - struct sk_buff *skb = NULL; + int count = 0; + struct sk_buff *skb; zap_completion_queue(); + refill_skbs(); repeat: - if (nr_skbs < MAX_SKBS) - refill_skbs(); skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) + skb = skb_dequeue(&skb_pool); if (!skb) { - spin_lock_irqsave(&skb_list_lock, flags); - skb = skbs; - if (skb) { - skbs = skb->next; - skb->next = NULL; - nr_skbs--; + if (++count < 10) { + netpoll_poll_dev(np->dev); + goto repeat; } - spin_unlock_irqrestore(&skb_list_lock, flags); - } - - if(!skb) { - count++; - if (once && (count == 1000000)) { - printk("out of netpoll skbs!\n"); - once = 0; - } - netpoll_poll(np); - goto repeat; + return NULL; } atomic_set(&skb->users, 1); @@ -249,445 +308,394 @@ repeat: return skb; } -static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) +static int netpoll_owner_active(struct net_device *dev) { - int status; - struct netpoll_info *npinfo; + struct napi_struct *napi; - if (!np || !np->dev || !netif_running(np->dev)) { - __kfree_skb(skb); - return; + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (napi->poll_owner == smp_processor_id()) + return 1; } + return 0; +} - npinfo = np->dev->npinfo; +/* call with IRQ disabled */ +void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, + struct net_device *dev) +{ + int status = NETDEV_TX_BUSY; + unsigned long tries; + /* It is up to the caller to keep npinfo alive. */ + struct netpoll_info *npinfo; - /* avoid recursion */ - if (npinfo->poll_owner == smp_processor_id() || - np->dev->xmit_lock_owner == smp_processor_id()) { - if (np->drop) - np->drop(skb); - else - __kfree_skb(skb); + WARN_ON_ONCE(!irqs_disabled()); + + npinfo = rcu_dereference_bh(np->dev->npinfo); + if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { + dev_kfree_skb_irq(skb); return; } - do { - npinfo->tries--; - spin_lock(&np->dev->xmit_lock); - np->dev->xmit_lock_owner = smp_processor_id(); + /* don't get messages out of order, and no recursion */ + if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { + struct netdev_queue *txq; - /* - * network drivers do not expect to be called if the queue is - * stopped. - */ - if (netif_queue_stopped(np->dev)) { - np->dev->xmit_lock_owner = -1; - spin_unlock(&np->dev->xmit_lock); - netpoll_poll(np); - udelay(50); - continue; - } + txq = netdev_pick_tx(dev, skb, NULL); - status = np->dev->hard_start_xmit(skb, np->dev); - np->dev->xmit_lock_owner = -1; - spin_unlock(&np->dev->xmit_lock); + /* try until next clock tick */ + for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; + tries > 0; --tries) { + if (HARD_TX_TRYLOCK(dev, txq)) { + if (!netif_xmit_stopped(txq)) + status = netpoll_start_xmit(skb, dev, txq); - /* success */ - if(!status) { - npinfo->tries = MAX_RETRIES; /* reset */ - return; + HARD_TX_UNLOCK(dev, txq); + + if (status == NETDEV_TX_OK) + break; + + } + + /* tickle device maybe there is some cleanup */ + netpoll_poll_dev(np->dev); + + udelay(USEC_PER_POLL); } - /* transmit busy */ - netpoll_poll(np); - udelay(50); - } while (npinfo->tries > 0); + WARN_ONCE(!irqs_disabled(), + "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n", + dev->name, dev->netdev_ops->ndo_start_xmit); + + } + + if (status != NETDEV_TX_OK) { + skb_queue_tail(&npinfo->txq, skb); + schedule_delayed_work(&npinfo->tx_work,0); + } } +EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { - int total_len, eth_len, ip_len, udp_len; + int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; + static atomic_t ip_ident; + struct ipv6hdr *ip6h; udp_len = len + sizeof(*udph); - ip_len = eth_len = udp_len + sizeof(*iph); - total_len = eth_len + ETH_HLEN + NET_IP_ALIGN; + if (np->ipv6) + ip_len = udp_len + sizeof(*ip6h); + else + ip_len = udp_len + sizeof(*iph); - skb = find_skb(np, total_len, total_len - len); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); + + skb = find_skb(np, total_len + np->dev->needed_tailroom, + total_len - len); if (!skb) return; - memcpy(skb->data, msg, len); - skb->len += len; + skb_copy_to_linear_data(skb, msg, len); + skb_put(skb, len); - udph = (struct udphdr *) skb_push(skb, sizeof(*udph)); + skb_push(skb, sizeof(*udph)); + skb_reset_transport_header(skb); + udph = udp_hdr(skb); udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); - udph->check = 0; - - iph = (struct iphdr *)skb_push(skb, sizeof(*iph)); - /* iph->version = 4; iph->ihl = 5; */ - put_unaligned(0x45, (unsigned char *)iph); - iph->tos = 0; - put_unaligned(htons(ip_len), &(iph->tot_len)); - iph->id = 0; - iph->frag_off = 0; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->check = 0; - put_unaligned(htonl(np->local_ip), &(iph->saddr)); - put_unaligned(htonl(np->remote_ip), &(iph->daddr)); - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + if (np->ipv6) { + udph->check = 0; + udph->check = csum_ipv6_magic(&np->local_ip.in6, + &np->remote_ip.in6, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + + /* ip6h->version = 6; ip6h->priority = 0; */ + put_unaligned(0x60, (unsigned char *)ip6h); + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + + ip6h->payload_len = htons(sizeof(struct udphdr) + len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = 32; + ip6h->saddr = np->local_ip.in6; + ip6h->daddr = np->remote_ip.in6; + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IPV6); + } else { + udph->check = 0; + udph->check = csum_tcpudp_magic(np->local_ip.ip, + np->remote_ip.ip, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*iph)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + + /* iph->version = 4; iph->ihl = 5; */ + put_unaligned(0x45, (unsigned char *)iph); + iph->tos = 0; + put_unaligned(htons(ip_len), &(iph->tot_len)); + iph->id = htons(atomic_inc_return(&ip_ident)); + iph->frag_off = 0; + iph->ttl = 64; + iph->protocol = IPPROTO_UDP; + iph->check = 0; + put_unaligned(np->local_ip.ip, &(iph->saddr)); + put_unaligned(np->remote_ip.ip, &(iph->daddr)); + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IP); + } - eth->h_proto = htons(ETH_P_IP); - memcpy(eth->h_source, np->local_mac, 6); - memcpy(eth->h_dest, np->remote_mac, 6); + ether_addr_copy(eth->h_source, np->dev->dev_addr); + ether_addr_copy(eth->h_dest, np->remote_mac); skb->dev = np->dev; netpoll_send_skb(np, skb); } +EXPORT_SYMBOL(netpoll_send_udp); -static void arp_reply(struct sk_buff *skb) +void netpoll_print_options(struct netpoll *np) { - struct netpoll_info *npinfo = skb->dev->npinfo; - struct arphdr *arp; - unsigned char *arp_ptr; - int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; - u32 sip, tip; - struct sk_buff *send_skb; - struct netpoll *np = NULL; - - if (npinfo->rx_np && npinfo->rx_np->dev == skb->dev) - np = npinfo->rx_np; - if (!np) - return; - - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, (sizeof(struct arphdr) + - (2 * skb->dev->addr_len) + - (2 * sizeof(u32))))) - return; - - skb->h.raw = skb->nh.raw = skb->data; - arp = skb->nh.arph; - - 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) + skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4 + skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (tip != htonl(np->local_ip) || LOOPBACK(tip) || MULTICAST(tip)) - return; - - size = sizeof(struct arphdr) + 2 * (skb->dev->addr_len + 4); - send_skb = find_skb(np, size + LL_RESERVED_SPACE(np->dev), - LL_RESERVED_SPACE(np->dev)); - - if (!send_skb) - return; - - send_skb->nh.raw = send_skb->data; - 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 (np->dev->hard_header && - np->dev->hard_header(send_skb, skb->dev, ptype, - np->remote_mac, np->local_mac, - send_skb->len) < 0) { - kfree_skb(send_skb); - return; - } - - /* - * 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, np->remote_mac, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); - - netpoll_send_skb(np, send_skb); + np_info(np, "local port %d\n", np->local_port); + if (np->ipv6) + np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); + else + np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); + np_info(np, "interface '%s'\n", np->dev_name); + np_info(np, "remote port %d\n", np->remote_port); + if (np->ipv6) + np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); + else + np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); + np_info(np, "remote ethernet address %pM\n", np->remote_mac); } +EXPORT_SYMBOL(netpoll_print_options); -int __netpoll_rx(struct sk_buff *skb) +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) { - int proto, len, ulen; - struct iphdr *iph; - struct udphdr *uh; - struct netpoll *np = skb->dev->npinfo->rx_np; + const char *end; - if (!np) - goto out; - if (skb->dev->type != ARPHRD_ETHER) - goto out; - - /* check if netpoll clients need ARP */ - if (skb->protocol == __constant_htons(ETH_P_ARP) && - atomic_read(&trapped)) { - arp_reply(skb); - return 1; + if (!strchr(str, ':') && + in4_pton(str, -1, (void *)addr, -1, &end) > 0) { + if (!*end) + return 0; } - - proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP) - goto out; - if (skb->pkt_type == PACKET_OTHERHOST) - goto out; - if (skb_shared(skb)) - goto out; - - iph = (struct iphdr *)skb->data; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - 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; - - if (iph->protocol != IPPROTO_UDP) - goto out; - - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - ulen = ntohs(uh->len); - - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; - if (np->local_ip && np->local_ip != ntohl(iph->daddr)) - goto out; - if (np->remote_ip && np->remote_ip != ntohl(iph->saddr)) - goto out; - if (np->local_port && np->local_port != ntohs(uh->dest)) - goto out; - - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); - - kfree_skb(skb); - return 1; - -out: - if (atomic_read(&trapped)) { - kfree_skb(skb); - return 1; + if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { +#if IS_ENABLED(CONFIG_IPV6) + if (!*end) + return 1; +#else + return -1; +#endif } - - return 0; + return -1; } int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; + int ipv6; + bool ipversion_set = false; - if(*cur != '@') { + if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; - *delim=0; - np->local_port=simple_strtol(cur, NULL, 10); - cur=delim; + *delim = 0; + if (kstrtou16(cur, 10, &np->local_port)) + goto parse_failed; + cur = delim; } cur++; - printk(KERN_INFO "%s: local port %d\n", np->name, np->local_port); - if(*cur != '/') { + if (*cur != '/') { + ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; - *delim=0; - np->local_ip=ntohl(in_aton(cur)); - cur=delim; - - printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n", - np->name, HIPQUAD(np->local_ip)); + *delim = 0; + ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); + if (ipv6 < 0) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; + cur = delim; } cur++; - if ( *cur != ',') { + if (*cur != ',') { /* parse out dev name */ if ((delim = strchr(cur, ',')) == NULL) goto parse_failed; - *delim=0; + *delim = 0; strlcpy(np->dev_name, cur, sizeof(np->dev_name)); - cur=delim; + cur = delim; } cur++; - printk(KERN_INFO "%s: interface %s\n", np->name, np->dev_name); - - if ( *cur != '@' ) { + if (*cur != '@') { /* dst port */ if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; - *delim=0; - np->remote_port=simple_strtol(cur, NULL, 10); - cur=delim; + *delim = 0; + if (*cur == ' ' || *cur == '\t') + np_info(np, "warning: whitespace is not allowed\n"); + if (kstrtou16(cur, 10, &np->remote_port)) + goto parse_failed; + cur = delim; } cur++; - printk(KERN_INFO "%s: remote port %d\n", np->name, np->remote_port); /* dst ip */ if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; - *delim=0; - np->remote_ip=ntohl(in_aton(cur)); - cur=delim+1; - - printk(KERN_INFO "%s: remote IP %d.%d.%d.%d\n", - np->name, HIPQUAD(np->remote_ip)); + *delim = 0; + ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); + if (ipv6 < 0) + goto parse_failed; + else if (ipversion_set && np->ipv6 != (bool)ipv6) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; + cur = delim + 1; - if( *cur != 0 ) - { + if (*cur != 0) { /* MAC address */ - if ((delim = strchr(cur, ':')) == NULL) + if (!mac_pton(cur, np->remote_mac)) goto parse_failed; - *delim=0; - np->remote_mac[0]=simple_strtol(cur, NULL, 16); - cur=delim+1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim=0; - np->remote_mac[1]=simple_strtol(cur, NULL, 16); - cur=delim+1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim=0; - np->remote_mac[2]=simple_strtol(cur, NULL, 16); - cur=delim+1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim=0; - np->remote_mac[3]=simple_strtol(cur, NULL, 16); - cur=delim+1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim=0; - np->remote_mac[4]=simple_strtol(cur, NULL, 16); - cur=delim+1; - np->remote_mac[5]=simple_strtol(cur, NULL, 16); } - printk(KERN_INFO "%s: remote ethernet address " - "%02x:%02x:%02x:%02x:%02x:%02x\n", - np->name, - np->remote_mac[0], - np->remote_mac[1], - np->remote_mac[2], - np->remote_mac[3], - np->remote_mac[4], - np->remote_mac[5]); + netpoll_print_options(np); return 0; parse_failed: - printk(KERN_INFO "%s: couldn't parse config at %s!\n", - np->name, cur); + np_info(np, "couldn't parse config at '%s'!\n", cur); return -1; } +EXPORT_SYMBOL(netpoll_parse_options); + +int __netpoll_setup(struct netpoll *np, struct net_device *ndev) +{ + struct netpoll_info *npinfo; + const struct net_device_ops *ops; + int err; + + np->dev = ndev; + strlcpy(np->dev_name, ndev->name, IFNAMSIZ); + INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); + + if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || + !ndev->netdev_ops->ndo_poll_controller) { + np_err(np, "%s doesn't support polling, aborting\n", + np->dev_name); + err = -ENOTSUPP; + goto out; + } + + if (!ndev->npinfo) { + npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); + if (!npinfo) { + err = -ENOMEM; + goto out; + } + + sema_init(&npinfo->dev_lock, 1); + skb_queue_head_init(&npinfo->txq); + INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); + + atomic_set(&npinfo->refcnt, 1); + + ops = np->dev->netdev_ops; + if (ops->ndo_netpoll_setup) { + err = ops->ndo_netpoll_setup(ndev, npinfo); + if (err) + goto free_npinfo; + } + } else { + npinfo = rtnl_dereference(ndev->npinfo); + atomic_inc(&npinfo->refcnt); + } + + npinfo->netpoll = np; + + /* last thing to do is link it to the net device structure */ + rcu_assign_pointer(ndev->npinfo, npinfo); + + return 0; + +free_npinfo: + kfree(npinfo); +out: + return err; +} +EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { struct net_device *ndev = NULL; struct in_device *in_dev; - struct netpoll_info *npinfo; - unsigned long flags; + int err; - if (np->dev_name) - ndev = dev_get_by_name(np->dev_name); + rtnl_lock(); + if (np->dev_name) { + struct net *net = current->nsproxy->net_ns; + ndev = __dev_get_by_name(net, np->dev_name); + } if (!ndev) { - printk(KERN_ERR "%s: %s doesn't exist, aborting.\n", - np->name, np->dev_name); - return -1; + np_err(np, "%s doesn't exist, aborting\n", np->dev_name); + err = -ENODEV; + goto unlock; } + dev_hold(ndev); - np->dev = ndev; - if (!ndev->npinfo) { - npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); - if (!npinfo) - goto release; - - npinfo->rx_flags = 0; - npinfo->rx_np = NULL; - spin_lock_init(&npinfo->poll_lock); - npinfo->poll_owner = -1; - npinfo->tries = MAX_RETRIES; - spin_lock_init(&npinfo->rx_lock); - } else - npinfo = ndev->npinfo; - - if (!ndev->poll_controller) { - printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n", - np->name, np->dev_name); - goto release; + if (netdev_master_upper_dev_get(ndev)) { + np_err(np, "%s is a slave device, aborting\n", np->dev_name); + err = -EBUSY; + goto put; } if (!netif_running(ndev)) { unsigned long atmost, atleast; - printk(KERN_INFO "%s: device %s not up yet, forcing it\n", - np->name, np->dev_name); + np_info(np, "device %s not up yet, forcing it\n", np->dev_name); - rtnl_shlock(); - if (dev_change_flags(ndev, ndev->flags | IFF_UP) < 0) { - printk(KERN_ERR "%s: failed to open %s\n", - np->name, np->dev_name); - rtnl_shunlock(); - goto release; + err = dev_open(ndev); + + if (err) { + np_err(np, "failed to open %s\n", ndev->name); + goto put; } - rtnl_shunlock(); + rtnl_unlock(); atleast = jiffies + HZ/10; - atmost = jiffies + 4*HZ; + atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { - printk(KERN_NOTICE - "%s: timeout waiting for carrier\n", - np->name); + np_notice(np, "timeout waiting for carrier\n"); break; } - cond_resched(); + msleep(1); } /* If carrier appears to come up instantly, we don't @@ -696,96 +704,153 @@ int netpoll_setup(struct netpoll *np) */ if (time_before(jiffies, atleast)) { - printk(KERN_NOTICE "%s: carrier detect appears" - " untrustworthy, waiting 4 seconds\n", - np->name); + np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } + rtnl_lock(); } - if (is_zero_ether_addr(np->local_mac) && ndev->dev_addr) - memcpy(np->local_mac, ndev->dev_addr, 6); + if (!np->local_ip.ip) { + if (!np->ipv6) { + in_dev = __in_dev_get_rtnl(ndev); - if (!np->local_ip) { - rcu_read_lock(); - in_dev = __in_dev_get_rcu(ndev); + if (!in_dev || !in_dev->ifa_list) { + np_err(np, "no IP address for %s, aborting\n", + np->dev_name); + err = -EDESTADDRREQ; + goto put; + } - if (!in_dev || !in_dev->ifa_list) { - rcu_read_unlock(); - printk(KERN_ERR "%s: no IP address for %s, aborting\n", - np->name, np->dev_name); - goto release; + np->local_ip.ip = in_dev->ifa_list->ifa_local; + np_info(np, "local IP %pI4\n", &np->local_ip.ip); + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_dev *idev; + + err = -EDESTADDRREQ; + idev = __in6_dev_get(ndev); + if (idev) { + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + continue; + np->local_ip.in6 = ifp->addr; + err = 0; + break; + } + read_unlock_bh(&idev->lock); + } + if (err) { + np_err(np, "no IPv6 address for %s, aborting\n", + np->dev_name); + goto put; + } else + np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); +#else + np_err(np, "IPv6 is not supported %s, aborting\n", + np->dev_name); + err = -EINVAL; + goto put; +#endif } - - np->local_ip = ntohl(in_dev->ifa_list->ifa_local); - rcu_read_unlock(); - printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n", - np->name, HIPQUAD(np->local_ip)); - } - - if (np->rx_hook) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_flags |= NETPOLL_RX_ENABLED; - npinfo->rx_np = np; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); } /* fill up the skb queue */ refill_skbs(); - /* last thing to do is link it to the net device structure */ - ndev->npinfo = npinfo; - - /* avoid racing with NAPI reading npinfo */ - synchronize_rcu(); + err = __netpoll_setup(np, ndev); + if (err) + goto put; + rtnl_unlock(); return 0; - release: - if (!ndev->npinfo) - kfree(npinfo); - np->dev = NULL; +put: dev_put(ndev); - return -1; +unlock: + rtnl_unlock(); + return err; } +EXPORT_SYMBOL(netpoll_setup); -void netpoll_cleanup(struct netpoll *np) +static int __init netpoll_init(void) +{ + skb_queue_head_init(&skb_pool); + return 0; +} +core_initcall(netpoll_init); + +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->txq); + + /* we can't call cancel_delayed_work_sync here, as we are in softirq */ + cancel_delayed_work(&npinfo->tx_work); + + /* clean after last, unfinished work */ + __skb_queue_purge(&npinfo->txq); + /* now cancel it again */ + cancel_delayed_work(&npinfo->tx_work); + kfree(npinfo); +} + +void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; - unsigned long flags; - if (np->dev) { - npinfo = np->dev->npinfo; - if (npinfo && npinfo->rx_np == np) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_np = NULL; - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } - dev_put(np->dev); - } + /* rtnl_dereference would be preferable here but + * rcu_cleanup_netpoll path can put us in here safely without + * holding the rtnl, so plain rcu_dereference it is + */ + npinfo = rtnl_dereference(np->dev->npinfo); + if (!npinfo) + return; - np->dev = NULL; + synchronize_srcu(&netpoll_srcu); + + if (atomic_dec_and_test(&npinfo->refcnt)) { + const struct net_device_ops *ops; + + ops = np->dev->netdev_ops; + if (ops->ndo_netpoll_cleanup) + ops->ndo_netpoll_cleanup(np->dev); + + RCU_INIT_POINTER(np->dev->npinfo, NULL); + call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); + } } +EXPORT_SYMBOL_GPL(__netpoll_cleanup); -int netpoll_trap(void) +static void netpoll_async_cleanup(struct work_struct *work) { - return atomic_read(&trapped); + struct netpoll *np = container_of(work, struct netpoll, cleanup_work); + + rtnl_lock(); + __netpoll_cleanup(np); + rtnl_unlock(); + kfree(np); } -void netpoll_set_trap(int trap) +void __netpoll_free_async(struct netpoll *np) { - if (trap) - atomic_inc(&trapped); - else - atomic_dec(&trapped); + schedule_work(&np->cleanup_work); } +EXPORT_SYMBOL_GPL(__netpoll_free_async); -EXPORT_SYMBOL(netpoll_set_trap); -EXPORT_SYMBOL(netpoll_trap); -EXPORT_SYMBOL(netpoll_parse_options); -EXPORT_SYMBOL(netpoll_setup); +void netpoll_cleanup(struct netpoll *np) +{ + rtnl_lock(); + if (!np->dev) + goto out; + __netpoll_cleanup(np); + dev_put(np->dev); + np->dev = NULL; +out: + rtnl_unlock(); +} EXPORT_SYMBOL(netpoll_cleanup); -EXPORT_SYMBOL(netpoll_send_udp); -EXPORT_SYMBOL(netpoll_poll); -EXPORT_SYMBOL(netpoll_queue); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c new file mode 100644 index 00000000000..2f385b9bccc --- /dev/null +++ b/net/core/netprio_cgroup.c @@ -0,0 +1,288 @@ +/* + * net/core/netprio_cgroup.c Priority Control Group + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Neil Horman <nhorman@tuxdriver.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/cgroup.h> +#include <linux/rcupdate.h> +#include <linux/atomic.h> +#include <net/rtnetlink.h> +#include <net/pkt_cls.h> +#include <net/sock.h> +#include <net/netprio_cgroup.h> + +#include <linux/fdtable.h> + +#define PRIOMAP_MIN_SZ 128 + +/* + * Extend @dev->priomap so that it's large enough to accommodate + * @target_idx. @dev->priomap.priomap_len > @target_idx after successful + * return. Must be called under rtnl lock. + */ +static int extend_netdev_table(struct net_device *dev, u32 target_idx) +{ + struct netprio_map *old, *new; + size_t new_sz, new_len; + + /* is the existing priomap large enough? */ + old = rtnl_dereference(dev->priomap); + if (old && old->priomap_len > target_idx) + return 0; + + /* + * Determine the new size. Let's keep it power-of-two. We start + * from PRIOMAP_MIN_SZ and double it until it's large enough to + * accommodate @target_idx. + */ + new_sz = PRIOMAP_MIN_SZ; + while (true) { + new_len = (new_sz - offsetof(struct netprio_map, priomap)) / + sizeof(new->priomap[0]); + if (new_len > target_idx) + break; + new_sz *= 2; + /* overflowed? */ + if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) + return -ENOSPC; + } + + /* allocate & copy */ + new = kzalloc(new_sz, GFP_KERNEL); + if (!new) + return -ENOMEM; + + if (old) + memcpy(new->priomap, old->priomap, + old->priomap_len * sizeof(old->priomap[0])); + + new->priomap_len = new_len; + + /* install the new priomap */ + rcu_assign_pointer(dev->priomap, new); + if (old) + kfree_rcu(old, rcu); + return 0; +} + +/** + * netprio_prio - return the effective netprio of a cgroup-net_device pair + * @css: css part of the target pair + * @dev: net_device part of the target pair + * + * Should be called under RCU read or rtnl lock. + */ +static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) +{ + struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); + int id = css->cgroup->id; + + if (map && id < map->priomap_len) + return map->priomap[id]; + return 0; +} + +/** + * netprio_set_prio - set netprio on a cgroup-net_device pair + * @css: css part of the target pair + * @dev: net_device part of the target pair + * @prio: prio to set + * + * Set netprio to @prio on @css-@dev pair. Should be called under rtnl + * lock and may fail under memory pressure for non-zero @prio. + */ +static int netprio_set_prio(struct cgroup_subsys_state *css, + struct net_device *dev, u32 prio) +{ + struct netprio_map *map; + int id = css->cgroup->id; + int ret; + + /* avoid extending priomap for zero writes */ + map = rtnl_dereference(dev->priomap); + if (!prio && (!map || map->priomap_len <= id)) + return 0; + + ret = extend_netdev_table(dev, id); + if (ret) + return ret; + + map = rtnl_dereference(dev->priomap); + map->priomap[id] = prio; + return 0; +} + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_subsys_state *css; + + css = kzalloc(sizeof(*css), GFP_KERNEL); + if (!css) + return ERR_PTR(-ENOMEM); + + return css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys_state *parent_css = css->parent; + struct net_device *dev; + int ret = 0; + + if (!parent_css) + return 0; + + rtnl_lock(); + /* + * Inherit prios from the parent. As all prios are set during + * onlining, there is no need to clear them on offline. + */ + for_each_netdev(&init_net, dev) { + u32 prio = netprio_prio(parent_css, dev); + + ret = netprio_set_prio(css, dev, prio); + if (ret) + break; + } + rtnl_unlock(); + return ret; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css); +} + +static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css->cgroup->id; +} + +static int read_priomap(struct seq_file *sf, void *v) +{ + struct net_device *dev; + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) + seq_printf(sf, "%s %u\n", dev->name, + netprio_prio(seq_css(sf), dev)); + rcu_read_unlock(); + return 0; +} + +static ssize_t write_priomap(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + char devname[IFNAMSIZ + 1]; + struct net_device *dev; + u32 prio; + int ret; + + if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) + return -EINVAL; + + dev = dev_get_by_name(&init_net, devname); + if (!dev) + return -ENODEV; + + rtnl_lock(); + + ret = netprio_set_prio(of_css(of), dev, prio); + + rtnl_unlock(); + dev_put(dev); + return ret ?: nbytes; +} + +static int update_netprio(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + if (sock) + sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v; + return 0; +} + +static void net_prio_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *p; + void *v = (void *)(unsigned long)css->cgroup->id; + + cgroup_taskset_for_each(p, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_netprio, v); + task_unlock(p); + } +} + +static struct cftype ss_files[] = { + { + .name = "prioidx", + .read_u64 = read_prioidx, + }, + { + .name = "ifpriomap", + .seq_show = read_priomap, + .write = write_priomap, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_prio_cgrp_subsys = { + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = net_prio_attach, + .base_cftypes = ss_files, +}; + +static int netprio_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netprio_map *old; + + /* + * Note this is called with rtnl_lock held so we have update side + * protection on our rcu assignments + */ + + switch (event) { + case NETDEV_UNREGISTER: + old = rtnl_dereference(dev->priomap); + RCU_INIT_POINTER(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block netprio_device_notifier = { + .notifier_call = netprio_device_event +}; + +static int __init init_cgroup_netprio(void) +{ + register_netdevice_notifier(&netprio_device_notifier); + return 0; +} + +subsys_initcall(init_cgroup_netprio); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index da16f8fd149..fc17a9d309a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -6,7 +6,7 @@ * * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Ben Greear <greearb@candelatech.com> - * Jens Låås <jens.laas@data.slu.se> + * Jens Låås <jens.laas@data.slu.se> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -15,7 +15,7 @@ * * * A tool for loading the network with preconfigurated packets. - * The tool is implemented as a linux module. Parameters are output + * The tool is implemented as a linux module. Parameters are output * device, delay (to hard_xmit), number of packets, and whether * to use multiple SKBs or just the same one. * pktgen uses the installed interface's output routine. @@ -44,14 +44,14 @@ * * Add IOCTL interface to easily get counters & configuration. * --Ben Greear <greearb@candelatech.com> * - * Renamed multiskb to clone_skb and cleaned up sending core for two distinct - * skb modes. A clone_skb=0 mode for Ben "ranges" work and a clone_skb != 0 + * Renamed multiskb to clone_skb and cleaned up sending core for two distinct + * skb modes. A clone_skb=0 mode for Ben "ranges" work and a clone_skb != 0 * as a "fastpath" with a configurable number of clones after alloc's. - * clone_skb=0 means all packets are allocated this also means ranges time - * stamps etc can be used. clone_skb=100 means 1 malloc is followed by 100 + * clone_skb=0 means all packets are allocated this also means ranges time + * stamps etc can be used. clone_skb=100 means 1 malloc is followed by 100 * clones. * - * Also moved to /proc/net/pktgen/ + * Also moved to /proc/net/pktgen/ * --ro * * Sept 10: Fixed threading/locking. Lots of bone-headed and more clever @@ -60,28 +60,28 @@ * * Integrated to 2.5.x 021029 --Lucio Maciel (luciomaciel@zipmail.com.br) * - * + * * 021124 Finished major redesign and rewrite for new functionality. * See Documentation/networking/pktgen.txt for how to use this. * * The new operation: - * For each CPU one thread/process is created at start. This process checks - * for running devices in the if_list and sends packets until count is 0 it - * also the thread checks the thread->control which is used for inter-process - * communication. controlling process "posts" operations to the threads this + * For each CPU one thread/process is created at start. This process checks + * for running devices in the if_list and sends packets until count is 0 it + * also the thread checks the thread->control which is used for inter-process + * communication. controlling process "posts" operations to the threads this * way. The if_lock should be possible to remove when add/rem_device is merged * into this too. * - * By design there should only be *one* "controlling" process. In practice - * multiple write accesses gives unpredictable result. Understood by "write" + * By design there should only be *one* "controlling" process. In practice + * multiple write accesses gives unpredictable result. Understood by "write" * to /proc gives result code thats should be read be the "writer". * For practical use this should be no problem. * - * Note when adding devices to a specific CPU there good idea to also assign - * /proc/irq/XX/smp_affinity so TX-interrupts gets bound to the same CPU. + * Note when adding devices to a specific CPU there good idea to also assign + * /proc/irq/XX/smp_affinity so TX-interrupts gets bound to the same CPU. * --ro * - * Fix refcount off by one if first packet fails, potential null deref, + * Fix refcount off by one if first packet fails, potential null deref, * memleak 030710- KJP * * First "ranges" functionality for ipv6 030726 --ro @@ -89,30 +89,41 @@ * Included flow support. 030802 ANK. * * Fixed unaligned access on IA-64 Grant Grundler <grundler@parisc-linux.org> - * + * * Remove if fix from added Harald Welte <laforge@netfilter.org> 040419 * ia64 compilation fix from Aron Griffis <aron@hp.com> 040604 * - * New xmit() return, do_div and misc clean up by Stephen Hemminger + * New xmit() return, do_div and misc clean up by Stephen Hemminger * <shemminger@osdl.org> 040923 * - * Randy Dunlap fixed u64 printk compiler waring + * Randy Dunlap fixed u64 printk compiler waring * * Remove FCS from BW calculation. Lennert Buytenhek <buytenh@wantstofly.org> * New time handling. Lennert Buytenhek <buytenh@wantstofly.org> 041213 * - * Corrections from Nikolai Malykh (nmalykh@bilim.com) + * Corrections from Nikolai Malykh (nmalykh@bilim.com) * Removed unused flags F_SET_SRCMAC & F_SET_SRCIP 041230 * - * interruptible_sleep_on_timeout() replaced Nishanth Aravamudan <nacc@us.ibm.com> + * interruptible_sleep_on_timeout() replaced Nishanth Aravamudan <nacc@us.ibm.com> * 050103 + * + * MPLS support by Steven Whitehouse <steve@chygwyn.com> + * + * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com> + * + * Fixed src_mac command to set source mac of packet to value specified in + * command by Adit Ranadive <adit.262@gmail.com> + * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/sys.h> #include <linux/types.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> -#include <linux/smp_lock.h> +#include <linux/mutex.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/vmalloc.h> @@ -123,8 +134,11 @@ #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/capability.h> +#include <linux/hrtimer.h> +#include <linux/freezer.h> #include <linux/delay.h> #include <linux/timer.h> +#include <linux/list.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netdevice.h> @@ -132,6 +146,7 @@ #include <linux/inetdevice.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> +#include <linux/if_vlan.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -140,47 +155,58 @@ #include <linux/seq_file.h> #include <linux/wait.h> #include <linux/etherdevice.h> +#include <linux/kthread.h> +#include <linux/prefetch.h> +#include <net/net_namespace.h> #include <net/checksum.h> #include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> #include <net/addrconf.h> +#ifdef CONFIG_XFRM +#include <net/xfrm.h> +#endif +#include <net/netns/generic.h> #include <asm/byteorder.h> #include <linux/rcupdate.h> -#include <asm/bitops.h> -#include <asm/io.h> +#include <linux/bitops.h> +#include <linux/io.h> +#include <linux/timex.h> +#include <linux/uaccess.h> #include <asm/dma.h> -#include <asm/uaccess.h> -#include <asm/div64.h> /* do_div */ -#include <asm/timex.h> - - -#define VERSION "pktgen v2.63: Packet Generator for packet performance testing.\n" - -/* #define PG_DEBUG(a) a */ -#define PG_DEBUG(a) +#include <asm/div64.h> /* do_div */ -/* The buckets are exponential in 'width' */ -#define LAT_BUCKETS_MAX 32 +#define VERSION "2.74" #define IP_NAME_SZ 32 +#define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ +#define MPLS_STACK_BOTTOM htonl(0x00000100) + +#define func_enter() pr_debug("entering %s\n", __func__); /* Device flag bits */ -#define F_IPSRC_RND (1<<0) /* IP-Src Random */ -#define F_IPDST_RND (1<<1) /* IP-Dst Random */ -#define F_UDPSRC_RND (1<<2) /* UDP-Src Random */ -#define F_UDPDST_RND (1<<3) /* UDP-Dst Random */ -#define F_MACSRC_RND (1<<4) /* MAC-Src Random */ -#define F_MACDST_RND (1<<5) /* MAC-Dst Random */ -#define F_TXSIZE_RND (1<<6) /* Transmit size is random */ -#define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ +#define F_IPSRC_RND (1<<0) /* IP-Src Random */ +#define F_IPDST_RND (1<<1) /* IP-Dst Random */ +#define F_UDPSRC_RND (1<<2) /* UDP-Src Random */ +#define F_UDPDST_RND (1<<3) /* UDP-Dst Random */ +#define F_MACSRC_RND (1<<4) /* MAC-Src Random */ +#define F_MACDST_RND (1<<5) /* MAC-Dst Random */ +#define F_TXSIZE_RND (1<<6) /* Transmit size is random */ +#define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ +#define F_MPLS_RND (1<<8) /* Random MPLS labels */ +#define F_VID_RND (1<<9) /* Random VLAN ID */ +#define F_SVID_RND (1<<10) /* Random SVLAN ID */ +#define F_FLOW_SEQ (1<<11) /* Sequential flows */ +#define F_IPSEC_ON (1<<12) /* ipsec on for flows */ +#define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ +#define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ +#define F_NODE (1<<15) /* Node memory alloc*/ +#define F_UDPCSUM (1<<16) /* Include UDP checksum */ /* Thread control flag bits */ -#define T_TERMINATE (1<<0) -#define T_STOP (1<<1) /* Stop run */ -#define T_RUN (1<<2) /* Start run */ -#define T_REMDEV (1<<3) /* Remove all devs */ - -/* Locks */ -#define thread_lock() down(&pktgen_sem) -#define thread_unlock() up(&pktgen_sem) +#define T_STOP (1<<0) /* Stop run */ +#define T_RUN (1<<1) /* Start run */ +#define T_REMDEVALL (1<<2) /* Remove all devs */ +#define T_REMDEV (1<<3) /* Remove one dev */ /* If lock -- can be removed after some work */ #define if_lock(t) spin_lock(&(t->if_lock)); @@ -190,507 +216,543 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir = NULL; #define MAX_CFLOWS 65536 -struct flow_state -{ - __u32 cur_daddr; - int count; +#define VLAN_TAG_SIZE(x) ((x)->vlan_id == 0xffff ? 0 : 4) +#define SVLAN_TAG_SIZE(x) ((x)->svlan_id == 0xffff ? 0 : 4) + +struct flow_state { + __be32 cur_daddr; + int count; +#ifdef CONFIG_XFRM + struct xfrm_state *x; +#endif + __u32 flags; }; -struct pktgen_dev { +/* flow flag bits */ +#define F_INIT (1<<0) /* flow has been initialized */ +struct pktgen_dev { /* * Try to keep frequent/infrequent used vars. separated. */ + struct proc_dir_entry *entry; /* proc file */ + struct pktgen_thread *pg_thread;/* the owner */ + struct list_head list; /* chaining in the thread's run-queue */ + + int running; /* if false, the test will stop */ - char ifname[IFNAMSIZ]; - char result[512]; - - struct pktgen_thread* pg_thread; /* the owner */ - struct pktgen_dev *next; /* Used for chaining in the thread's run-queue */ - - int running; /* if this changes to false, the test will stop */ - - /* If min != max, then we will either do a linear iteration, or - * we will do a random selection from within the range. - */ - __u32 flags; - - int min_pkt_size; /* = ETH_ZLEN; */ - int max_pkt_size; /* = ETH_ZLEN; */ - int nfrags; - __u32 delay_us; /* Default delay */ - __u32 delay_ns; - __u64 count; /* Default No packets to send */ - __u64 sofar; /* How many pkts we've sent so far */ - __u64 tx_bytes; /* How many bytes we've transmitted */ - __u64 errors; /* Errors when trying to transmit, pkts will be re-sent */ - - /* runtime counters relating to clone_skb */ - __u64 next_tx_us; /* timestamp of when to tx next */ - __u32 next_tx_ns; - - __u64 allocated_skbs; - __u32 clone_count; - int last_ok; /* Was last skb sent? - * Or a failed transmit of some sort? This will keep - * sequence numbers in order, for example. - */ - __u64 started_at; /* micro-seconds */ - __u64 stopped_at; /* micro-seconds */ - __u64 idle_acc; /* micro-seconds */ - __u32 seq_num; - - int clone_skb; /* Use multiple SKBs during packet gen. If this number - * is greater than 1, then that many copies of the same - * packet will be sent before a new packet is allocated. - * For instance, if you want to send 1024 identical packets - * before creating a new packet, set clone_skb to 1024. - */ - - char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - char dst_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - char src_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - char src_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ - - struct in6_addr in6_saddr; - struct in6_addr in6_daddr; - struct in6_addr cur_in6_daddr; - struct in6_addr cur_in6_saddr; + /* If min != max, then we will either do a linear iteration, or + * we will do a random selection from within the range. + */ + __u32 flags; + int removal_mark; /* non-zero => the device is marked for + * removal by worker thread */ + + int min_pkt_size; + int max_pkt_size; + int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ + int nfrags; + struct page *page; + u64 delay; /* nano-seconds */ + + __u64 count; /* Default No packets to send */ + __u64 sofar; /* How many pkts we've sent so far */ + __u64 tx_bytes; /* How many bytes we've transmitted */ + __u64 errors; /* Errors when trying to transmit, */ + + /* runtime counters relating to clone_skb */ + + __u64 allocated_skbs; + __u32 clone_count; + int last_ok; /* Was last skb sent? + * Or a failed transmit of some sort? + * This will keep sequence numbers in order + */ + ktime_t next_tx; + ktime_t started_at; + ktime_t stopped_at; + u64 idle_acc; /* nano-seconds */ + + __u32 seq_num; + + int clone_skb; /* + * Use multiple SKBs during packet gen. + * If this number is greater than 1, then + * that many copies of the same packet will be + * sent before a new packet is allocated. + * If you want to send 1024 identical packets + * before creating a new packet, + * set clone_skb to 1024. + */ + + char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + char dst_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + char src_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + char src_max[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ + + struct in6_addr in6_saddr; + struct in6_addr in6_daddr; + struct in6_addr cur_in6_daddr; + struct in6_addr cur_in6_saddr; /* For ranges */ - struct in6_addr min_in6_daddr; - struct in6_addr max_in6_daddr; - struct in6_addr min_in6_saddr; - struct in6_addr max_in6_saddr; - - /* If we're doing ranges, random or incremental, then this - * defines the min/max for those ranges. - */ - __u32 saddr_min; /* inclusive, source IP address */ - __u32 saddr_max; /* exclusive, source IP address */ - __u32 daddr_min; /* inclusive, dest IP address */ - __u32 daddr_max; /* exclusive, dest IP address */ - - __u16 udp_src_min; /* inclusive, source UDP port */ - __u16 udp_src_max; /* exclusive, source UDP port */ - __u16 udp_dst_min; /* inclusive, dest UDP port */ - __u16 udp_dst_max; /* exclusive, dest UDP port */ - - __u32 src_mac_count; /* How many MACs to iterate through */ - __u32 dst_mac_count; /* How many MACs to iterate through */ - - unsigned char dst_mac[ETH_ALEN]; - unsigned char src_mac[ETH_ALEN]; - - __u32 cur_dst_mac_offset; - __u32 cur_src_mac_offset; - __u32 cur_saddr; - __u32 cur_daddr; - __u16 cur_udp_dst; - __u16 cur_udp_src; - __u32 cur_pkt_size; - - __u8 hh[14]; - /* = { - 0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB, - - We fill in SRC address later - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x08, 0x00 - }; - */ - __u16 pad; /* pad out the hh struct to an even 16 bytes */ - - struct sk_buff* skb; /* skb we are to transmit next, mainly used for when we - * are transmitting the same one multiple times - */ - struct net_device* odev; /* The out-going device. Note that the device should - * have it's pg_info pointer pointing back to this - * device. This will be set when the user specifies - * the out-going device name (not when the inject is - * started as it used to do.) - */ + struct in6_addr min_in6_daddr; + struct in6_addr max_in6_daddr; + struct in6_addr min_in6_saddr; + struct in6_addr max_in6_saddr; + + /* If we're doing ranges, random or incremental, then this + * defines the min/max for those ranges. + */ + __be32 saddr_min; /* inclusive, source IP address */ + __be32 saddr_max; /* exclusive, source IP address */ + __be32 daddr_min; /* inclusive, dest IP address */ + __be32 daddr_max; /* exclusive, dest IP address */ + + __u16 udp_src_min; /* inclusive, source UDP port */ + __u16 udp_src_max; /* exclusive, source UDP port */ + __u16 udp_dst_min; /* inclusive, dest UDP port */ + __u16 udp_dst_max; /* exclusive, dest UDP port */ + + /* DSCP + ECN */ + __u8 tos; /* six MSB of (former) IPv4 TOS + are for dscp codepoint */ + __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 + (see RFC 3260, sec. 4) */ + + /* MPLS */ + unsigned int nr_labels; /* Depth of stack, 0 = no MPLS */ + __be32 labels[MAX_MPLS_LABELS]; + + /* VLAN/SVLAN (802.1Q/Q-in-Q) */ + __u8 vlan_p; + __u8 vlan_cfi; + __u16 vlan_id; /* 0xffff means no vlan tag */ + + __u8 svlan_p; + __u8 svlan_cfi; + __u16 svlan_id; /* 0xffff means no svlan tag */ + + __u32 src_mac_count; /* How many MACs to iterate through */ + __u32 dst_mac_count; /* How many MACs to iterate through */ + + unsigned char dst_mac[ETH_ALEN]; + unsigned char src_mac[ETH_ALEN]; + + __u32 cur_dst_mac_offset; + __u32 cur_src_mac_offset; + __be32 cur_saddr; + __be32 cur_daddr; + __u16 ip_id; + __u16 cur_udp_dst; + __u16 cur_udp_src; + __u16 cur_queue_map; + __u32 cur_pkt_size; + __u32 last_pkt_size; + + __u8 hh[14]; + /* = { + 0x00, 0x80, 0xC8, 0x79, 0xB3, 0xCB, + + We fill in SRC address later + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x08, 0x00 + }; + */ + __u16 pad; /* pad out the hh struct to an even 16 bytes */ + + struct sk_buff *skb; /* skb we are to transmit next, used for when we + * are transmitting the same one multiple times + */ + struct net_device *odev; /* The out-going device. + * Note that the device should have it's + * pg_info pointer pointing back to this + * device. + * Set when the user specifies the out-going + * device name (not when the inject is + * started as it used to do.) + */ + char odevname[32]; struct flow_state *flows; - unsigned cflows; /* Concurrent flows (config) */ - unsigned lflow; /* Flow length (config) */ - unsigned nflows; /* accumulated flows (stats) */ + unsigned int cflows; /* Concurrent flows (config) */ + unsigned int lflow; /* Flow length (config) */ + unsigned int nflows; /* accumulated flows (stats) */ + unsigned int curfl; /* current sequenced flow (state)*/ + + u16 queue_map_min; + u16 queue_map_max; + __u32 skb_priority; /* skb priority field */ + int node; /* Memory node */ + +#ifdef CONFIG_XFRM + __u8 ipsmode; /* IPSEC mode (config) */ + __u8 ipsproto; /* IPSEC type (config) */ + __u32 spi; + struct dst_entry dst; + struct dst_ops dstops; +#endif + char result[512]; }; struct pktgen_hdr { - __u32 pgh_magic; - __u32 seq_num; - __u32 tv_sec; - __u32 tv_usec; + __be32 pgh_magic; + __be32 seq_num; + __be32 tv_sec; + __be32 tv_usec; }; -struct pktgen_thread { - spinlock_t if_lock; - struct pktgen_dev *if_list; /* All device here */ - struct pktgen_thread* next; - char name[32]; - char result[512]; - u32 max_before_softirq; /* We'll call do_softirq to prevent starvation. */ - - /* Field for thread to receive "posted" events terminate, stop ifs etc.*/ - - u32 control; - int pid; - int cpu; - - wait_queue_head_t queue; -}; -#define REMOVE 1 -#define FIND 0 +static int pg_net_id __read_mostly; -/* This code works around the fact that do_div cannot handle two 64-bit - numbers, and regular 64-bit division doesn't work on x86 kernels. - --Ben -*/ - -#define PG_DIV 0 - -/* This was emailed to LMKL by: Chris Caputo <ccaputo@alt.net> - * Function copied/adapted/optimized from: - * - * nemesis.sourceforge.net/browse/lib/static/intmath/ix86/intmath.c.html - * - * Copyright 1994, University of Cambridge Computer Laboratory - * All Rights Reserved. - * - */ -static inline s64 divremdi3(s64 x, s64 y, int type) -{ - u64 a = (x < 0) ? -x : x; - u64 b = (y < 0) ? -y : y; - u64 res = 0, d = 1; - - if (b > 0) { - while (b < a) { - b <<= 1; - d <<= 1; - } - } - - do { - if ( a >= b ) { - a -= b; - res += d; - } - b >>= 1; - d >>= 1; - } - while (d); - - if (PG_DIV == type) { - return (((x ^ y) & (1ll<<63)) == 0) ? res : -(s64)res; - } - else { - return ((x & (1ll<<63)) == 0) ? a : -(s64)a; - } -} - -/* End of hacks to deal with 64-bit math on x86 */ - -/** Convert to milliseconds */ -static inline __u64 tv_to_ms(const struct timeval* tv) -{ - __u64 ms = tv->tv_usec / 1000; - ms += (__u64)tv->tv_sec * (__u64)1000; - return ms; -} - - -/** Convert to micro-seconds */ -static inline __u64 tv_to_us(const struct timeval* tv) -{ - __u64 us = tv->tv_usec; - us += (__u64)tv->tv_sec * (__u64)1000000; - return us; -} - -static inline __u64 pg_div(__u64 n, __u32 base) { - __u64 tmp = n; - do_div(tmp, base); - /* printk("pktgen: pg_div, n: %llu base: %d rv: %llu\n", - n, base, tmp); */ - return tmp; -} - -static inline __u64 pg_div64(__u64 n, __u64 base) -{ - __u64 tmp = n; -/* - * How do we know if the architecture we are running on - * supports division with 64 bit base? - * - */ -#if defined(__sparc_v9__) || defined(__powerpc64__) || defined(__alpha__) || defined(__x86_64__) || defined(__ia64__) - - do_div(tmp, base); -#else - tmp = divremdi3(n, base, PG_DIV); -#endif - return tmp; -} - -static inline u32 pktgen_random(void) -{ -#if 0 - __u32 n; - get_random_bytes(&n, 4); - return n; -#else - return net_random(); -#endif -} +struct pktgen_net { + struct net *net; + struct proc_dir_entry *proc_dir; + struct list_head pktgen_threads; + bool pktgen_exiting; +}; -static inline __u64 getCurMs(void) -{ - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_ms(&tv); -} +struct pktgen_thread { + spinlock_t if_lock; /* for list of devices */ + struct list_head if_list; /* All device here */ + struct list_head th_list; + struct task_struct *tsk; + char result[512]; -static inline __u64 getCurUs(void) -{ - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_us(&tv); -} + /* Field for thread to receive "posted" events terminate, + stop ifs etc. */ -static inline __u64 tv_diff(const struct timeval* a, const struct timeval* b) -{ - return tv_to_us(a) - tv_to_us(b); -} + u32 control; + int cpu; + wait_queue_head_t queue; + struct completion start_done; + struct pktgen_net *net; +}; -/* old include end */ +#define REMOVE 1 +#define FIND 0 -static char version[] __initdata = VERSION; +static const char version[] = + "Packet Generator for packet performance testing. " + "Version: " VERSION "\n"; -static int pktgen_remove_device(struct pktgen_thread* t, struct pktgen_dev *i); -static int pktgen_add_device(struct pktgen_thread* t, const char* ifname); -static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread* t, const char* ifname); +static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); +static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); +static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, + const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); -static void pktgen_run_all_threads(void); -static void pktgen_stop_all_threads_ifs(void); -static int pktgen_stop_device(struct pktgen_dev *pkt_dev); -static void pktgen_stop(struct pktgen_thread* t); +static void pktgen_run_all_threads(struct pktgen_net *pn); +static void pktgen_reset_all_threads(struct pktgen_net *pn); +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); + +static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); -static struct pktgen_dev *pktgen_NN_threads(const char* dev_name, int remove); -static unsigned int scan_ip6(const char *s,char ip[16]); -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; -static int pg_clone_skb_d; -static int debug; +static int pg_count_d __read_mostly = 1000; +static int pg_delay_d __read_mostly; +static int pg_clone_skb_d __read_mostly; +static int debug __read_mostly; -static DECLARE_MUTEX(pktgen_sem); -static struct pktgen_thread *pktgen_threads = NULL; +static DEFINE_MUTEX(pktgen_thread_lock); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, }; /* - * /proc handling functions + * /proc handling functions * */ static int pgctrl_show(struct seq_file *seq, void *v) -{ - seq_puts(seq, VERSION); +{ + seq_puts(seq, version); return 0; } -static ssize_t pgctrl_write(struct file* file,const char __user * buf, +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(); + if (!strcmp(data, "stop")) + pktgen_stop_all_threads_ifs(pn); - else if (!strcmp(data, "start")) - pktgen_run_all_threads(); + else if (!strcmp(data, "start")) + pktgen_run_all_threads(pn); - else - printk("pktgen: Unknown command: %s\n", data); + else if (!strcmp(data, "reset")) + pktgen_reset_all_threads(pn); - err = count; + else + pr_warning("Unknown command: %s\n", data); - out: - return err; + return count; } static int pgctrl_open(struct inode *inode, struct file *file) { - return single_open(file, pgctrl_show, PDE(inode)->data); + return single_open(file, pgctrl_show, PDE_DATA(inode)); } -static struct file_operations pktgen_fops = { - .owner = THIS_MODULE, - .open = pgctrl_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pgctrl_write, - .release = single_release, +static const struct file_operations pktgen_fops = { + .owner = THIS_MODULE, + .open = pgctrl_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pgctrl_write, + .release = single_release, }; static int pktgen_if_show(struct seq_file *seq, void *v) { - int i; - struct pktgen_dev *pkt_dev = seq->private; - __u64 sa; - __u64 stopped; - __u64 now = getCurUs(); - - seq_printf(seq, "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", - (unsigned long long) pkt_dev->count, - pkt_dev->min_pkt_size, pkt_dev->max_pkt_size); - - seq_printf(seq, " frags: %d delay: %u clone_skb: %d ifname: %s\n", - pkt_dev->nfrags, 1000*pkt_dev->delay_us+pkt_dev->delay_ns, pkt_dev->clone_skb, pkt_dev->ifname); - - seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); - - - if(pkt_dev->flags & F_IPV6) { - char b1[128], b2[128], b3[128]; - fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); - seq_printf(seq, " saddr: %s min_saddr: %s max_saddr: %s\n", b1, b2, b3); - - fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); - seq_printf(seq, " daddr: %s min_daddr: %s max_daddr: %s\n", b1, b2, b3); - - } - else - seq_printf(seq," dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", - pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, pkt_dev->src_max); + const struct pktgen_dev *pkt_dev = seq->private; + ktime_t stopped; + u64 idle; + + seq_printf(seq, + "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", + (unsigned long long)pkt_dev->count, pkt_dev->min_pkt_size, + pkt_dev->max_pkt_size); + + seq_printf(seq, + " frags: %d delay: %llu clone_skb: %d ifname: %s\n", + pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, + pkt_dev->clone_skb, pkt_dev->odevname); + + seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, + pkt_dev->lflow); + + seq_printf(seq, + " queue_map_min: %u queue_map_max: %u\n", + pkt_dev->queue_map_min, + pkt_dev->queue_map_max); + + if (pkt_dev->skb_priority) + seq_printf(seq, " skb_priority: %u\n", + pkt_dev->skb_priority); + + if (pkt_dev->flags & F_IPV6) { + seq_printf(seq, + " saddr: %pI6c min_saddr: %pI6c max_saddr: %pI6c\n" + " daddr: %pI6c min_daddr: %pI6c max_daddr: %pI6c\n", + &pkt_dev->in6_saddr, + &pkt_dev->min_in6_saddr, &pkt_dev->max_in6_saddr, + &pkt_dev->in6_daddr, + &pkt_dev->min_in6_daddr, &pkt_dev->max_in6_daddr); + } else { + seq_printf(seq, + " dst_min: %s dst_max: %s\n", + pkt_dev->dst_min, pkt_dev->dst_max); + seq_printf(seq, + " src_min: %s src_max: %s\n", + pkt_dev->src_min, pkt_dev->src_max); + } seq_puts(seq, " src_mac: "); - if (is_zero_ether_addr(pkt_dev->src_mac)) - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->odev->dev_addr[i], i == 5 ? " " : ":"); - else - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->src_mac[i], i == 5 ? " " : ":"); + seq_printf(seq, "%pM ", + is_zero_ether_addr(pkt_dev->src_mac) ? + pkt_dev->odev->dev_addr : pkt_dev->src_mac); - seq_printf(seq, "dst_mac: "); - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->dst_mac[i], i == 5 ? "\n" : ":"); + seq_puts(seq, "dst_mac: "); + seq_printf(seq, "%pM\n", pkt_dev->dst_mac); - seq_printf(seq, " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", - pkt_dev->udp_src_min, pkt_dev->udp_src_max, pkt_dev->udp_dst_min, - pkt_dev->udp_dst_max); + seq_printf(seq, + " udp_src_min: %d udp_src_max: %d" + " udp_dst_min: %d udp_dst_max: %d\n", + pkt_dev->udp_src_min, pkt_dev->udp_src_max, + pkt_dev->udp_dst_min, pkt_dev->udp_dst_max); - seq_printf(seq, " src_mac_count: %d dst_mac_count: %d \n Flags: ", + seq_printf(seq, + " src_mac_count: %d dst_mac_count: %d\n", pkt_dev->src_mac_count, pkt_dev->dst_mac_count); + if (pkt_dev->nr_labels) { + unsigned int i; + seq_puts(seq, " mpls: "); + for (i = 0; i < pkt_dev->nr_labels; i++) + seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), + i == pkt_dev->nr_labels-1 ? "\n" : ", "); + } + + if (pkt_dev->vlan_id != 0xffff) + seq_printf(seq, " vlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->vlan_id, pkt_dev->vlan_p, + pkt_dev->vlan_cfi); + + if (pkt_dev->svlan_id != 0xffff) + seq_printf(seq, " svlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->svlan_id, pkt_dev->svlan_p, + pkt_dev->svlan_cfi); + + if (pkt_dev->tos) + seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos); + + if (pkt_dev->traffic_class) + seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); - if (pkt_dev->flags & F_IPV6) - seq_printf(seq, "IPV6 "); - - if (pkt_dev->flags & F_IPSRC_RND) - seq_printf(seq, "IPSRC_RND "); - - if (pkt_dev->flags & F_IPDST_RND) - seq_printf(seq, "IPDST_RND "); - - if (pkt_dev->flags & F_TXSIZE_RND) - seq_printf(seq, "TXSIZE_RND "); - - if (pkt_dev->flags & F_UDPSRC_RND) - seq_printf(seq, "UDPSRC_RND "); - - if (pkt_dev->flags & F_UDPDST_RND) - seq_printf(seq, "UDPDST_RND "); - - if (pkt_dev->flags & F_MACSRC_RND) - seq_printf(seq, "MACSRC_RND "); - - if (pkt_dev->flags & F_MACDST_RND) - seq_printf(seq, "MACDST_RND "); - - - seq_puts(seq, "\n"); - - sa = pkt_dev->started_at; - stopped = pkt_dev->stopped_at; - if (pkt_dev->running) - stopped = now; /* not really stopped, more like last-running-at */ - - seq_printf(seq, "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", - (unsigned long long) pkt_dev->sofar, - (unsigned long long) pkt_dev->errors, - (unsigned long long) sa, - (unsigned long long) stopped, - (unsigned long long) pkt_dev->idle_acc); - - seq_printf(seq, " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", + if (pkt_dev->node >= 0) + seq_printf(seq, " node: %d\n", pkt_dev->node); + + seq_puts(seq, " Flags: "); + + if (pkt_dev->flags & F_IPV6) + seq_puts(seq, "IPV6 "); + + if (pkt_dev->flags & F_IPSRC_RND) + seq_puts(seq, "IPSRC_RND "); + + if (pkt_dev->flags & F_IPDST_RND) + seq_puts(seq, "IPDST_RND "); + + if (pkt_dev->flags & F_TXSIZE_RND) + seq_puts(seq, "TXSIZE_RND "); + + if (pkt_dev->flags & F_UDPSRC_RND) + seq_puts(seq, "UDPSRC_RND "); + + if (pkt_dev->flags & F_UDPDST_RND) + seq_puts(seq, "UDPDST_RND "); + + if (pkt_dev->flags & F_UDPCSUM) + seq_puts(seq, "UDPCSUM "); + + if (pkt_dev->flags & F_MPLS_RND) + seq_puts(seq, "MPLS_RND "); + + if (pkt_dev->flags & F_QUEUE_MAP_RND) + seq_puts(seq, "QUEUE_MAP_RND "); + + if (pkt_dev->flags & F_QUEUE_MAP_CPU) + seq_puts(seq, "QUEUE_MAP_CPU "); + + if (pkt_dev->cflows) { + if (pkt_dev->flags & F_FLOW_SEQ) + seq_puts(seq, "FLOW_SEQ "); /*in sequence flows*/ + else + seq_puts(seq, "FLOW_RND "); + } + +#ifdef CONFIG_XFRM + if (pkt_dev->flags & F_IPSEC_ON) { + seq_puts(seq, "IPSEC "); + if (pkt_dev->spi) + seq_printf(seq, "spi:%u", pkt_dev->spi); + } +#endif + + if (pkt_dev->flags & F_MACSRC_RND) + seq_puts(seq, "MACSRC_RND "); + + if (pkt_dev->flags & F_MACDST_RND) + seq_puts(seq, "MACDST_RND "); + + if (pkt_dev->flags & F_VID_RND) + seq_puts(seq, "VID_RND "); + + if (pkt_dev->flags & F_SVID_RND) + seq_puts(seq, "SVID_RND "); + + if (pkt_dev->flags & F_NODE) + seq_puts(seq, "NODE_ALLOC "); + + seq_puts(seq, "\n"); + + /* not really stopped, more like last-running-at */ + stopped = pkt_dev->running ? ktime_get() : pkt_dev->stopped_at; + idle = pkt_dev->idle_acc; + do_div(idle, NSEC_PER_USEC); + + seq_printf(seq, + "Current:\n pkts-sofar: %llu errors: %llu\n", + (unsigned long long)pkt_dev->sofar, + (unsigned long long)pkt_dev->errors); + + seq_printf(seq, + " started: %lluus stopped: %lluus idle: %lluus\n", + (unsigned long long) ktime_to_us(pkt_dev->started_at), + (unsigned long long) ktime_to_us(stopped), + (unsigned long long) idle); + + seq_printf(seq, + " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", pkt_dev->seq_num, pkt_dev->cur_dst_mac_offset, pkt_dev->cur_src_mac_offset); - if(pkt_dev->flags & F_IPV6) { - char b1[128], b2[128]; - fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); - seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); - } - else - seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", - pkt_dev->cur_saddr, pkt_dev->cur_daddr); + if (pkt_dev->flags & F_IPV6) { + seq_printf(seq, " cur_saddr: %pI6c cur_daddr: %pI6c\n", + &pkt_dev->cur_in6_saddr, + &pkt_dev->cur_in6_daddr); + } else + seq_printf(seq, " cur_saddr: %pI4 cur_daddr: %pI4\n", + &pkt_dev->cur_saddr, &pkt_dev->cur_daddr); - - seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", + seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src); - seq_printf(seq, " flows: %u\n", pkt_dev->nflows); + seq_printf(seq, " cur_queue_map: %u\n", pkt_dev->cur_queue_map); + + seq_printf(seq, " flows: %u\n", pkt_dev->nflows); if (pkt_dev->result[0]) - seq_printf(seq, "Result: %s\n", pkt_dev->result); + seq_printf(seq, "Result: %s\n", pkt_dev->result); else - seq_printf(seq, "Result: Idle\n"); + seq_puts(seq, "Result: Idle\n"); return 0; } -static int count_trail_chars(const char __user *user_buffer, unsigned int maxlen) +static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, + __u32 *num) +{ + int i = 0; + *num = 0; + + for (; i < maxlen; i++) { + int value; + char c; + *num <<= 4; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + value = hex_to_bin(c); + if (value >= 0) + *num |= value; + else + break; + } + return i; +} + +static int count_trail_chars(const char __user * user_buffer, + unsigned int maxlen) { int i; for (i = 0; i < maxlen; i++) { - char c; - if (get_user(c, &user_buffer[i])) - return -EFAULT; - switch (c) { + char c; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + switch (c) { case '\"': case '\n': case '\r': @@ -700,40 +762,40 @@ static int count_trail_chars(const char __user *user_buffer, unsigned int maxlen break; default: goto done; - }; + } } done: return i; } -static unsigned long num_arg(const char __user *user_buffer, unsigned long maxlen, - unsigned long *num) +static long num_arg(const char __user *user_buffer, unsigned long maxlen, + unsigned long *num) { - int i = 0; + int i; *num = 0; - - for(; i < maxlen; i++) { - char c; - if (get_user(c, &user_buffer[i])) - return -EFAULT; - if ((c >= '0') && (c <= '9')) { + + for (i = 0; i < maxlen; i++) { + char c; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + if ((c >= '0') && (c <= '9')) { *num *= 10; - *num += c -'0'; + *num += c - '0'; } else break; } return i; } -static int strn_len(const char __user *user_buffer, unsigned int maxlen) +static int strn_len(const char __user * user_buffer, unsigned int maxlen) { - int i = 0; + int i; - for(; i < maxlen; i++) { - char c; - if (get_user(c, &user_buffer[i])) - return -EFAULT; - switch (c) { + for (i = 0; i < maxlen; i++) { + char c; + if (get_user(c, &user_buffer[i])) + return -EFAULT; + switch (c) { case '\"': case '\n': case '\r': @@ -743,122 +805,166 @@ static int strn_len(const char __user *user_buffer, unsigned int maxlen) break; default: break; - }; + } } done_str: + return i; +} + +static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) +{ + unsigned int n = 0; + char c; + ssize_t i = 0; + int len; + + pkt_dev->nr_labels = 0; + do { + __u32 tmp; + len = hex32_arg(&buffer[i], 8, &tmp); + if (len <= 0) + return len; + pkt_dev->labels[n] = htonl(tmp); + if (pkt_dev->labels[n] & MPLS_STACK_BOTTOM) + pkt_dev->flags |= F_MPLS_RND; + i += len; + if (get_user(c, &buffer[i])) + return -EFAULT; + i++; + n++; + if (n >= MAX_MPLS_LABELS) + return -E2BIG; + } while (c == ','); + pkt_dev->nr_labels = n; return i; } -static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer, - size_t count, loff_t *offset) +static ssize_t pktgen_if_write(struct file *file, + const char __user * user_buffer, size_t count, + loff_t * offset) { - struct seq_file *seq = (struct seq_file *) file->private_data; - struct pktgen_dev *pkt_dev = seq->private; - int i = 0, max, len; + struct seq_file *seq = file->private_data; + struct pktgen_dev *pkt_dev = seq->private; + int i, max, len; char name[16], valstr[32]; unsigned long value = 0; - char* pg_result = NULL; - int tmp = 0; + char *pg_result = NULL; + int tmp = 0; char buf[128]; - - pg_result = &(pkt_dev->result[0]); - + + pg_result = &(pkt_dev->result[0]); + if (count < 1) { - printk("pktgen: wrong command format\n"); + pr_warning("wrong command format\n"); return -EINVAL; } - - max = count - i; - tmp = count_trail_chars(&user_buffer[i], max); - if (tmp < 0) { - printk("pktgen: illegal format\n"); - return tmp; + + max = count; + tmp = count_trail_chars(user_buffer, max); + if (tmp < 0) { + pr_warning("illegal format\n"); + return tmp; } - i += tmp; - + i = tmp; + /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) { return len; } + if (len < 0) + return len; + memset(name, 0, sizeof(name)); - if (copy_from_user(name, &user_buffer[i], len) ) + if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; i += len; - - max = count -i; + + max = count - i; len = count_trail_chars(&user_buffer[i], max); - if (len < 0) - return len; - + if (len < 0) + return len; + i += len; if (debug) { - char tb[count + 1]; - if (copy_from_user(tb, user_buffer, count)) + size_t copy = min_t(size_t, count, 1023); + char tb[copy + 1]; + if (copy_from_user(tb, user_buffer, copy)) return -EFAULT; - tb[count] = 0; - printk("pktgen: %s,%lu buffer -:%s:-\n", name, - (unsigned long) count, tb); - } + tb[copy] = 0; + pr_debug("%s,%lu buffer -:%s:-\n", + name, (unsigned long)count, tb); + } if (!strcmp(name, "min_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value < 14+20+8) - value = 14+20+8; - if (value != pkt_dev->min_pkt_size) { - pkt_dev->min_pkt_size = value; - pkt_dev->cur_pkt_size = value; - } - sprintf(pg_result, "OK: min_pkt_size=%u", pkt_dev->min_pkt_size); + if (value < 14 + 20 + 8) + value = 14 + 20 + 8; + if (value != pkt_dev->min_pkt_size) { + pkt_dev->min_pkt_size = value; + pkt_dev->cur_pkt_size = value; + } + sprintf(pg_result, "OK: min_pkt_size=%u", + pkt_dev->min_pkt_size); return count; } - if (!strcmp(name, "max_pkt_size")) { + if (!strcmp(name, "max_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value < 14+20+8) - value = 14+20+8; - if (value != pkt_dev->max_pkt_size) { - pkt_dev->max_pkt_size = value; - pkt_dev->cur_pkt_size = value; - } - sprintf(pg_result, "OK: max_pkt_size=%u", pkt_dev->max_pkt_size); + if (value < 14 + 20 + 8) + value = 14 + 20 + 8; + if (value != pkt_dev->max_pkt_size) { + pkt_dev->max_pkt_size = value; + pkt_dev->cur_pkt_size = value; + } + sprintf(pg_result, "OK: max_pkt_size=%u", + pkt_dev->max_pkt_size); return count; } - /* Shortcut for min = max */ + /* Shortcut for min = max */ if (!strcmp(name, "pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value < 14+20+8) - value = 14+20+8; - if (value != pkt_dev->min_pkt_size) { - pkt_dev->min_pkt_size = value; - pkt_dev->max_pkt_size = value; - pkt_dev->cur_pkt_size = value; - } + if (value < 14 + 20 + 8) + value = 14 + 20 + 8; + if (value != pkt_dev->min_pkt_size) { + pkt_dev->min_pkt_size = value; + pkt_dev->max_pkt_size = value; + pkt_dev->cur_pkt_size = value; + } sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size); return count; } - if (!strcmp(name, "debug")) { + if (!strcmp(name, "debug")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - debug = value; + debug = value; sprintf(pg_result, "OK: debug=%u", debug); return count; } - if (!strcmp(name, "frags")) { + if (!strcmp(name, "frags")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; pkt_dev->nfrags = value; sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags); @@ -866,403 +972,510 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer } if (!strcmp(name, "delay")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value == 0x7FFFFFFF) { - pkt_dev->delay_us = 0x7FFFFFFF; - pkt_dev->delay_ns = 0; - } else { - pkt_dev->delay_us = value / 1000; - pkt_dev->delay_ns = value % 1000; - } - sprintf(pg_result, "OK: delay=%u", 1000*pkt_dev->delay_us+pkt_dev->delay_ns); + if (value == 0x7FFFFFFF) + pkt_dev->delay = ULLONG_MAX; + else + pkt_dev->delay = (u64)value; + + sprintf(pg_result, "OK: delay=%llu", + (unsigned long long) pkt_dev->delay); return count; } - if (!strcmp(name, "udp_src_min")) { + if (!strcmp(name, "rate")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value != pkt_dev->udp_src_min) { - pkt_dev->udp_src_min = value; - pkt_dev->cur_udp_src = value; - } + if (!value) + return len; + pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value; + if (debug) + pr_info("Delay set at: %llu ns\n", pkt_dev->delay); + + sprintf(pg_result, "OK: rate=%lu", value); + return count; + } + if (!strcmp(name, "ratep")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + if (!value) + return len; + pkt_dev->delay = NSEC_PER_SEC/value; + if (debug) + pr_info("Delay set at: %llu ns\n", pkt_dev->delay); + + sprintf(pg_result, "OK: rate=%lu", value); + return count; + } + if (!strcmp(name, "udp_src_min")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + if (value != pkt_dev->udp_src_min) { + pkt_dev->udp_src_min = value; + pkt_dev->cur_udp_src = value; + } sprintf(pg_result, "OK: udp_src_min=%u", pkt_dev->udp_src_min); return count; } - if (!strcmp(name, "udp_dst_min")) { + if (!strcmp(name, "udp_dst_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value != pkt_dev->udp_dst_min) { - pkt_dev->udp_dst_min = value; - pkt_dev->cur_udp_dst = value; - } + if (value != pkt_dev->udp_dst_min) { + pkt_dev->udp_dst_min = value; + pkt_dev->cur_udp_dst = value; + } sprintf(pg_result, "OK: udp_dst_min=%u", pkt_dev->udp_dst_min); return count; } - if (!strcmp(name, "udp_src_max")) { + if (!strcmp(name, "udp_src_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value != pkt_dev->udp_src_max) { - pkt_dev->udp_src_max = value; - pkt_dev->cur_udp_src = value; - } + if (value != pkt_dev->udp_src_max) { + pkt_dev->udp_src_max = value; + pkt_dev->cur_udp_src = value; + } sprintf(pg_result, "OK: udp_src_max=%u", pkt_dev->udp_src_max); return count; } - if (!strcmp(name, "udp_dst_max")) { + if (!strcmp(name, "udp_dst_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; - if (value != pkt_dev->udp_dst_max) { - pkt_dev->udp_dst_max = value; - pkt_dev->cur_udp_dst = value; - } + if (value != pkt_dev->udp_dst_max) { + pkt_dev->udp_dst_max = value; + pkt_dev->cur_udp_dst = value; + } sprintf(pg_result, "OK: udp_dst_max=%u", pkt_dev->udp_dst_max); return count; } if (!strcmp(name, "clone_skb")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + if ((value > 0) && + (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) + return -ENOTSUPP; i += len; - pkt_dev->clone_skb = value; - + pkt_dev->clone_skb = value; + sprintf(pg_result, "OK: clone_skb=%d", pkt_dev->clone_skb); return count; } if (!strcmp(name, "count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; pkt_dev->count = value; sprintf(pg_result, "OK: count=%llu", - (unsigned long long) pkt_dev->count); + (unsigned long long)pkt_dev->count); return count; } if (!strcmp(name, "src_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; if (pkt_dev->src_mac_count != value) { - pkt_dev->src_mac_count = value; - pkt_dev->cur_src_mac_offset = 0; - } - sprintf(pg_result, "OK: src_mac_count=%d", pkt_dev->src_mac_count); + pkt_dev->src_mac_count = value; + pkt_dev->cur_src_mac_offset = 0; + } + sprintf(pg_result, "OK: src_mac_count=%d", + pkt_dev->src_mac_count); return count; } if (!strcmp(name, "dst_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; if (pkt_dev->dst_mac_count != value) { - pkt_dev->dst_mac_count = value; - pkt_dev->cur_dst_mac_offset = 0; - } - sprintf(pg_result, "OK: dst_mac_count=%d", pkt_dev->dst_mac_count); + pkt_dev->dst_mac_count = value; + pkt_dev->cur_dst_mac_offset = 0; + } + sprintf(pg_result, "OK: dst_mac_count=%d", + pkt_dev->dst_mac_count); + return count; + } + if (!strcmp(name, "node")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + + if (node_possible(value)) { + pkt_dev->node = value; + sprintf(pg_result, "OK: node=%d", pkt_dev->node); + if (pkt_dev->page) { + put_page(pkt_dev->page); + pkt_dev->page = NULL; + } + } + else + sprintf(pg_result, "ERROR: node not possible"); return count; } if (!strcmp(name, "flag")) { - char f[32]; - memset(f, 0, 32); + char f[32]; + memset(f, 0, 32); len = strn_len(&user_buffer[i], sizeof(f) - 1); - if (len < 0) { return len; } + if (len < 0) + return len; + if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; i += len; - if (strcmp(f, "IPSRC_RND") == 0) - pkt_dev->flags |= F_IPSRC_RND; - - else if (strcmp(f, "!IPSRC_RND") == 0) - pkt_dev->flags &= ~F_IPSRC_RND; - - else if (strcmp(f, "TXSIZE_RND") == 0) - pkt_dev->flags |= F_TXSIZE_RND; - - else if (strcmp(f, "!TXSIZE_RND") == 0) - pkt_dev->flags &= ~F_TXSIZE_RND; - - else if (strcmp(f, "IPDST_RND") == 0) - pkt_dev->flags |= F_IPDST_RND; - - else if (strcmp(f, "!IPDST_RND") == 0) - pkt_dev->flags &= ~F_IPDST_RND; - - else if (strcmp(f, "UDPSRC_RND") == 0) - pkt_dev->flags |= F_UDPSRC_RND; - - else if (strcmp(f, "!UDPSRC_RND") == 0) - pkt_dev->flags &= ~F_UDPSRC_RND; - - else if (strcmp(f, "UDPDST_RND") == 0) - pkt_dev->flags |= F_UDPDST_RND; - - else if (strcmp(f, "!UDPDST_RND") == 0) - pkt_dev->flags &= ~F_UDPDST_RND; - - else if (strcmp(f, "MACSRC_RND") == 0) - pkt_dev->flags |= F_MACSRC_RND; - - else if (strcmp(f, "!MACSRC_RND") == 0) - pkt_dev->flags &= ~F_MACSRC_RND; - - else if (strcmp(f, "MACDST_RND") == 0) - pkt_dev->flags |= F_MACDST_RND; - - else if (strcmp(f, "!MACDST_RND") == 0) - pkt_dev->flags &= ~F_MACDST_RND; - - else { - sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", - f, - "IPSRC_RND, IPDST_RND, TXSIZE_RND, UDPSRC_RND, UDPDST_RND, MACSRC_RND, MACDST_RND\n"); - return count; - } + if (strcmp(f, "IPSRC_RND") == 0) + pkt_dev->flags |= F_IPSRC_RND; + + else if (strcmp(f, "!IPSRC_RND") == 0) + pkt_dev->flags &= ~F_IPSRC_RND; + + else if (strcmp(f, "TXSIZE_RND") == 0) + pkt_dev->flags |= F_TXSIZE_RND; + + else if (strcmp(f, "!TXSIZE_RND") == 0) + pkt_dev->flags &= ~F_TXSIZE_RND; + + else if (strcmp(f, "IPDST_RND") == 0) + pkt_dev->flags |= F_IPDST_RND; + + else if (strcmp(f, "!IPDST_RND") == 0) + pkt_dev->flags &= ~F_IPDST_RND; + + else if (strcmp(f, "UDPSRC_RND") == 0) + pkt_dev->flags |= F_UDPSRC_RND; + + else if (strcmp(f, "!UDPSRC_RND") == 0) + pkt_dev->flags &= ~F_UDPSRC_RND; + + else if (strcmp(f, "UDPDST_RND") == 0) + pkt_dev->flags |= F_UDPDST_RND; + + else if (strcmp(f, "!UDPDST_RND") == 0) + pkt_dev->flags &= ~F_UDPDST_RND; + + else if (strcmp(f, "MACSRC_RND") == 0) + pkt_dev->flags |= F_MACSRC_RND; + + else if (strcmp(f, "!MACSRC_RND") == 0) + pkt_dev->flags &= ~F_MACSRC_RND; + + else if (strcmp(f, "MACDST_RND") == 0) + pkt_dev->flags |= F_MACDST_RND; + + else if (strcmp(f, "!MACDST_RND") == 0) + pkt_dev->flags &= ~F_MACDST_RND; + + else if (strcmp(f, "MPLS_RND") == 0) + pkt_dev->flags |= F_MPLS_RND; + + else if (strcmp(f, "!MPLS_RND") == 0) + pkt_dev->flags &= ~F_MPLS_RND; + + else if (strcmp(f, "VID_RND") == 0) + pkt_dev->flags |= F_VID_RND; + + else if (strcmp(f, "!VID_RND") == 0) + pkt_dev->flags &= ~F_VID_RND; + + else if (strcmp(f, "SVID_RND") == 0) + pkt_dev->flags |= F_SVID_RND; + + else if (strcmp(f, "!SVID_RND") == 0) + pkt_dev->flags &= ~F_SVID_RND; + + else if (strcmp(f, "FLOW_SEQ") == 0) + pkt_dev->flags |= F_FLOW_SEQ; + + else if (strcmp(f, "QUEUE_MAP_RND") == 0) + pkt_dev->flags |= F_QUEUE_MAP_RND; + + else if (strcmp(f, "!QUEUE_MAP_RND") == 0) + pkt_dev->flags &= ~F_QUEUE_MAP_RND; + + else if (strcmp(f, "QUEUE_MAP_CPU") == 0) + pkt_dev->flags |= F_QUEUE_MAP_CPU; + + else if (strcmp(f, "!QUEUE_MAP_CPU") == 0) + pkt_dev->flags &= ~F_QUEUE_MAP_CPU; +#ifdef CONFIG_XFRM + else if (strcmp(f, "IPSEC") == 0) + pkt_dev->flags |= F_IPSEC_ON; +#endif + + else if (strcmp(f, "!IPV6") == 0) + pkt_dev->flags &= ~F_IPV6; + + else if (strcmp(f, "NODE_ALLOC") == 0) + pkt_dev->flags |= F_NODE; + + else if (strcmp(f, "!NODE_ALLOC") == 0) + pkt_dev->flags &= ~F_NODE; + + else if (strcmp(f, "UDPCSUM") == 0) + pkt_dev->flags |= F_UDPCSUM; + + else if (strcmp(f, "!UDPCSUM") == 0) + pkt_dev->flags &= ~F_UDPCSUM; + + else { + sprintf(pg_result, + "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, " + "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); return count; } if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1); - if (len < 0) { return len; } + if (len < 0) + return len; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->dst_min) != 0) { - memset(pkt_dev->dst_min, 0, sizeof(pkt_dev->dst_min)); - strncpy(pkt_dev->dst_min, buf, len); - pkt_dev->daddr_min = in_aton(pkt_dev->dst_min); - pkt_dev->cur_daddr = pkt_dev->daddr_min; - } - if(debug) - printk("pktgen: dst_min set to: %s\n", pkt_dev->dst_min); - i += len; + buf[len] = 0; + if (strcmp(buf, pkt_dev->dst_min) != 0) { + memset(pkt_dev->dst_min, 0, sizeof(pkt_dev->dst_min)); + strncpy(pkt_dev->dst_min, buf, len); + pkt_dev->daddr_min = in_aton(pkt_dev->dst_min); + pkt_dev->cur_daddr = pkt_dev->daddr_min; + } + if (debug) + pr_debug("dst_min set to: %s\n", pkt_dev->dst_min); + i += len; sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min); return count; } if (!strcmp(name, "dst_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1); - if (len < 0) { return len; } + if (len < 0) + return len; + - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->dst_max) != 0) { - memset(pkt_dev->dst_max, 0, sizeof(pkt_dev->dst_max)); - strncpy(pkt_dev->dst_max, buf, len); - pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); - pkt_dev->cur_daddr = pkt_dev->daddr_max; - } - if(debug) - printk("pktgen: dst_max set to: %s\n", pkt_dev->dst_max); + buf[len] = 0; + if (strcmp(buf, pkt_dev->dst_max) != 0) { + memset(pkt_dev->dst_max, 0, sizeof(pkt_dev->dst_max)); + strncpy(pkt_dev->dst_max, buf, len); + pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); + pkt_dev->cur_daddr = pkt_dev->daddr_max; + } + if (debug) + pr_debug("dst_max set to: %s\n", pkt_dev->dst_max); i += len; sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max); return count; } if (!strcmp(name, "dst6")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; - scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr; - if(debug) - printk("pktgen: dst6 set to: %s\n", buf); + if (debug) + pr_debug("dst6 set to: %s\n", buf); - i += len; + i += len; sprintf(pg_result, "OK: dst6=%s", buf); return count; } if (!strcmp(name, "dst6_min")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; - scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->min_in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->min_in6_daddr); - if(debug) - printk("pktgen: dst6_min set to: %s\n", buf); + pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr; + if (debug) + pr_debug("dst6_min set to: %s\n", buf); - i += len; + i += len; sprintf(pg_result, "OK: dst6_min=%s", buf); return count; } if (!strcmp(name, "dst6_max")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; - scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->max_in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr); - if(debug) - printk("pktgen: dst6_max set to: %s\n", buf); + if (debug) + pr_debug("dst6_max set to: %s\n", buf); - i += len; + i += len; sprintf(pg_result, "OK: dst6_max=%s", buf); return count; } if (!strcmp(name, "src6")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); - if (len < 0) return len; + if (len < 0) + return len; pkt_dev->flags |= F_IPV6; - if (copy_from_user(buf, &user_buffer[i], len)) + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; + buf[len] = 0; - scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_saddr.s6_addr); + in6_pton(buf, -1, pkt_dev->in6_saddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr); - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); + pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr; - if(debug) - printk("pktgen: src6 set to: %s\n", buf); - - i += len; + if (debug) + pr_debug("src6 set to: %s\n", buf); + + i += len; sprintf(pg_result, "OK: src6=%s", buf); return count; } if (!strcmp(name, "src_min")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1); - if (len < 0) { return len; } - if (copy_from_user(buf, &user_buffer[i], len)) + if (len < 0) + return len; + + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->src_min) != 0) { - memset(pkt_dev->src_min, 0, sizeof(pkt_dev->src_min)); - strncpy(pkt_dev->src_min, buf, len); - pkt_dev->saddr_min = in_aton(pkt_dev->src_min); - pkt_dev->cur_saddr = pkt_dev->saddr_min; - } - if(debug) - printk("pktgen: src_min set to: %s\n", pkt_dev->src_min); + buf[len] = 0; + if (strcmp(buf, pkt_dev->src_min) != 0) { + memset(pkt_dev->src_min, 0, sizeof(pkt_dev->src_min)); + strncpy(pkt_dev->src_min, buf, len); + pkt_dev->saddr_min = in_aton(pkt_dev->src_min); + pkt_dev->cur_saddr = pkt_dev->saddr_min; + } + if (debug) + pr_debug("src_min set to: %s\n", pkt_dev->src_min); i += len; sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min); return count; } if (!strcmp(name, "src_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1); - if (len < 0) { return len; } - if (copy_from_user(buf, &user_buffer[i], len)) + if (len < 0) + return len; + + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; - buf[len] = 0; - if (strcmp(buf, pkt_dev->src_max) != 0) { - memset(pkt_dev->src_max, 0, sizeof(pkt_dev->src_max)); - strncpy(pkt_dev->src_max, buf, len); - pkt_dev->saddr_max = in_aton(pkt_dev->src_max); - pkt_dev->cur_saddr = pkt_dev->saddr_max; - } - if(debug) - printk("pktgen: src_max set to: %s\n", pkt_dev->src_max); + buf[len] = 0; + if (strcmp(buf, pkt_dev->src_max) != 0) { + memset(pkt_dev->src_max, 0, sizeof(pkt_dev->src_max)); + strncpy(pkt_dev->src_max, buf, len); + pkt_dev->saddr_max = in_aton(pkt_dev->src_max); + pkt_dev->cur_saddr = pkt_dev->saddr_max; + } + if (debug) + pr_debug("src_max set to: %s\n", pkt_dev->src_max); i += len; sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max); return count; } if (!strcmp(name, "dst_mac")) { - char *v = valstr; - unsigned char old_dmac[ETH_ALEN]; - unsigned char *m = pkt_dev->dst_mac; - memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN); - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { return len; } + if (len < 0) + return len; + memset(valstr, 0, sizeof(valstr)); - if( copy_from_user(valstr, &user_buffer[i], len)) + if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - - for(*m = 0;*v && m < pkt_dev->dst_mac + 6; v++) { - if (*v >= '0' && *v <= '9') { - *m *= 16; - *m += *v - '0'; - } - if (*v >= 'A' && *v <= 'F') { - *m *= 16; - *m += *v - 'A' + 10; - } - if (*v >= 'a' && *v <= 'f') { - *m *= 16; - *m += *v - 'a' + 10; - } - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->dst_mac)) + return -EINVAL; /* Set up Dest MAC */ - if (compare_ether_addr(old_dmac, pkt_dev->dst_mac)) - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); - - sprintf(pg_result, "OK: dstmac"); + ether_addr_copy(&pkt_dev->hh[0], pkt_dev->dst_mac); + + sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac); return count; } if (!strcmp(name, "src_mac")) { - char *v = valstr; - unsigned char *m = pkt_dev->src_mac; - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { return len; } + if (len < 0) + return len; + memset(valstr, 0, sizeof(valstr)); - if( copy_from_user(valstr, &user_buffer[i], len)) + if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - for(*m = 0;*v && m < pkt_dev->src_mac + 6; v++) { - if (*v >= '0' && *v <= '9') { - *m *= 16; - *m += *v - '0'; - } - if (*v >= 'A' && *v <= 'F') { - *m *= 16; - *m += *v - 'A' + 10; - } - if (*v >= 'a' && *v <= 'f') { - *m *= 16; - *m += *v - 'a' + 10; - } - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->src_mac)) + return -EINVAL; + /* Set up Src MAC */ + ether_addr_copy(&pkt_dev->hh[6], pkt_dev->src_mac); - sprintf(pg_result, "OK: srcmac"); + sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac); return count; } - if (!strcmp(name, "clear_counters")) { - pktgen_clear_counters(pkt_dev); - sprintf(pg_result, "OK: Clearing counters.\n"); - return count; - } + if (!strcmp(name, "clear_counters")) { + pktgen_clear_counters(pkt_dev); + sprintf(pg_result, "OK: Clearing counters.\n"); + return count; + } if (!strcmp(name, "flows")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; if (value > MAX_CFLOWS) value = MAX_CFLOWS; @@ -1271,270 +1484,549 @@ static ssize_t pktgen_if_write(struct file *file, const char __user *user_buffer sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows); return count; } +#ifdef CONFIG_XFRM + if (!strcmp(name, "spi")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + i += len; + pkt_dev->spi = value; + sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); + return count; + } +#endif if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { return len; } + if (len < 0) + return len; + i += len; pkt_dev->lflow = value; sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow); return count; } - + + if (!strcmp(name, "queue_map_min")) { + len = num_arg(&user_buffer[i], 5, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->queue_map_min = value; + sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min); + return count; + } + + if (!strcmp(name, "queue_map_max")) { + len = num_arg(&user_buffer[i], 5, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->queue_map_max = value; + sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max); + return count; + } + + if (!strcmp(name, "mpls")) { + unsigned int n, cnt; + + len = get_labels(&user_buffer[i], pkt_dev); + if (len < 0) + return len; + i += len; + cnt = sprintf(pg_result, "OK: mpls="); + for (n = 0; n < pkt_dev->nr_labels; n++) + cnt += sprintf(pg_result + cnt, + "%08x%s", ntohl(pkt_dev->labels[n]), + n == pkt_dev->nr_labels-1 ? "" : ","); + + if (pkt_dev->nr_labels && pkt_dev->vlan_id != 0xffff) { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + pr_debug("VLAN/SVLAN auto turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) + return len; + + i += len; + if (value <= 4095) { + pkt_dev->vlan_id = value; /* turn on VLAN */ + + if (debug) + pr_debug("VLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + pr_debug("MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + pr_debug("VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_p = value; + sprintf(pg_result, "OK: vlan_p=%u", pkt_dev->vlan_p); + } else { + sprintf(pg_result, "ERROR: vlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "vlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_cfi = value; + sprintf(pg_result, "OK: vlan_cfi=%u", pkt_dev->vlan_cfi); + } else { + sprintf(pg_result, "ERROR: vlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "svlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) { + pkt_dev->svlan_id = value; /* turn on SVLAN */ + + if (debug) + pr_debug("SVLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + pr_debug("MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + pr_debug("VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "svlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_p = value; + sprintf(pg_result, "OK: svlan_p=%u", pkt_dev->svlan_p); + } else { + sprintf(pg_result, "ERROR: svlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "svlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_cfi = value; + sprintf(pg_result, "OK: svlan_cfi=%u", pkt_dev->svlan_cfi); + } else { + sprintf(pg_result, "ERROR: svlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "tos")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) + return len; + + i += len; + if (len == 2) { + pkt_dev->tos = tmp_value; + sprintf(pg_result, "OK: tos=0x%02x", pkt_dev->tos); + } else { + sprintf(pg_result, "ERROR: tos must be 00-ff"); + } + return count; + } + + if (!strcmp(name, "traffic_class")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) + return len; + + i += len; + if (len == 2) { + pkt_dev->traffic_class = tmp_value; + sprintf(pg_result, "OK: traffic_class=0x%02x", pkt_dev->traffic_class); + } else { + sprintf(pg_result, "ERROR: traffic_class must be 00-ff"); + } + return count; + } + + if (!strcmp(name, "skb_priority")) { + len = num_arg(&user_buffer[i], 9, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->skb_priority = value; + sprintf(pg_result, "OK: skb_priority=%i", + pkt_dev->skb_priority); + return count; + } + sprintf(pkt_dev->result, "No such parameter \"%s\"", name); return -EINVAL; } static int pktgen_if_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_if_show, PDE(inode)->data); + return single_open(file, pktgen_if_show, PDE_DATA(inode)); } -static struct file_operations pktgen_if_fops = { - .owner = THIS_MODULE, - .open = pktgen_if_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pktgen_if_write, - .release = single_release, +static const struct file_operations pktgen_if_fops = { + .owner = THIS_MODULE, + .open = pktgen_if_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pktgen_if_write, + .release = single_release, }; static int pktgen_thread_show(struct seq_file *seq, void *v) { - struct pktgen_thread *t = seq->private; - struct pktgen_dev *pkt_dev = NULL; + struct pktgen_thread *t = seq->private; + const struct pktgen_dev *pkt_dev; BUG_ON(!t); - seq_printf(seq, "Name: %s max_before_softirq: %d\n", - t->name, t->max_before_softirq); + seq_puts(seq, "Running: "); + + if_lock(t); + list_for_each_entry(pkt_dev, &t->if_list, list) + if (pkt_dev->running) + seq_printf(seq, "%s ", pkt_dev->odevname); - seq_printf(seq, "Running: "); - - if_lock(t); - for(pkt_dev = t->if_list;pkt_dev; pkt_dev = pkt_dev->next) - if(pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->ifname); - - seq_printf(seq, "\nStopped: "); + seq_puts(seq, "\nStopped: "); - for(pkt_dev = t->if_list;pkt_dev; pkt_dev = pkt_dev->next) - if(!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->ifname); + list_for_each_entry(pkt_dev, &t->if_list, list) + if (!pkt_dev->running) + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); else - seq_printf(seq, "\nResult: NA\n"); + seq_puts(seq, "\nResult: NA\n"); - if_unlock(t); + if_unlock(t); return 0; } static ssize_t pktgen_thread_write(struct file *file, - const char __user *user_buffer, - size_t count, loff_t *offset) + const char __user * user_buffer, + size_t count, loff_t * offset) { - struct seq_file *seq = (struct seq_file *) file->private_data; - struct pktgen_thread *t = seq->private; - int i = 0, max, len, ret; + struct seq_file *seq = file->private_data; + struct pktgen_thread *t = seq->private; + int i, max, len, ret; char name[40]; - char *pg_result; - unsigned long value = 0; + char *pg_result; if (count < 1) { - // sprintf(pg_result, "Wrong command format"); + // sprintf(pg_result, "Wrong command format"); return -EINVAL; } - max = count - i; - len = count_trail_chars(&user_buffer[i], max); - if (len < 0) + max = count; + len = count_trail_chars(user_buffer, max); + if (len < 0) return len; - i += len; + i = len; /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) + if (len < 0) return len; - + memset(name, 0, sizeof(name)); if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; i += len; - max = count -i; + max = count - i; len = count_trail_chars(&user_buffer[i], max); - if (len < 0) + if (len < 0) return len; i += len; if (debug) - printk("pktgen: t=%s, count=%lu\n", name, - (unsigned long) count); + pr_debug("t=%s, count=%lu\n", name, (unsigned long)count); - if(!t) { - printk("pktgen: ERROR: No thread\n"); + if (!t) { + pr_err("ERROR: No thread\n"); ret = -EINVAL; goto out; } pg_result = &(t->result[0]); - if (!strcmp(name, "add_device")) { - char f[32]; - memset(f, 0, 32); + if (!strcmp(name, "add_device")) { + char f[32]; + memset(f, 0, 32); len = strn_len(&user_buffer[i], sizeof(f) - 1); - if (len < 0) { - ret = len; + if (len < 0) { + ret = len; goto out; } - if( copy_from_user(f, &user_buffer[i], len) ) + if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; i += len; - thread_lock(); - pktgen_add_device(t, f); - thread_unlock(); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + mutex_lock(&pktgen_thread_lock); + ret = pktgen_add_device(t, f); + mutex_unlock(&pktgen_thread_lock); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } - if (!strcmp(name, "rem_device_all")) { - thread_lock(); - t->control |= T_REMDEV; - thread_unlock(); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ + if (!strcmp(name, "rem_device_all")) { + mutex_lock(&pktgen_thread_lock); + t->control |= T_REMDEVALL; + mutex_unlock(&pktgen_thread_lock); + schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ ret = count; - sprintf(pg_result, "OK: rem_device_all"); + sprintf(pg_result, "OK: rem_device_all"); goto out; } - if (!strcmp(name, "max_before_softirq")) { - len = num_arg(&user_buffer[i], 10, &value); - thread_lock(); - t->max_before_softirq = value; - thread_unlock(); - ret = count; - sprintf(pg_result, "OK: max_before_softirq=%lu", value); + if (!strcmp(name, "max_before_softirq")) { + sprintf(pg_result, "OK: Note! max_before_softirq is obsoleted -- Do not use"); + ret = count; goto out; } ret = -EINVAL; - out: - +out: return ret; } static int pktgen_thread_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_thread_show, PDE(inode)->data); + return single_open(file, pktgen_thread_show, PDE_DATA(inode)); } -static struct file_operations pktgen_thread_fops = { - .owner = THIS_MODULE, - .open = pktgen_thread_open, - .read = seq_read, - .llseek = seq_lseek, - .write = pktgen_thread_write, - .release = single_release, +static const struct file_operations pktgen_thread_fops = { + .owner = THIS_MODULE, + .open = pktgen_thread_open, + .read = seq_read, + .llseek = seq_lseek, + .write = pktgen_thread_write, + .release = single_release, }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char* ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, + const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); - t = pktgen_threads; - - while (t) { - pkt_dev = pktgen_find_dev(t, ifname); + list_for_each_entry(t, &pn->pktgen_threads, th_list) { + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { - if(remove) { - if_lock(t); - pktgen_remove_device(t, pkt_dev); - if_unlock(t); - } + if (remove) { + if_lock(t); + pkt_dev->removal_mark = 1; + t->control |= T_REMDEV; + if_unlock(t); + } break; } - t = t->next; } - return pkt_dev; + return pkt_dev; } -static struct pktgen_dev *pktgen_NN_threads(const char* ifname, int remove) +/* + * mark a device for removal + */ +static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname) { struct pktgen_dev *pkt_dev = NULL; - thread_lock(); - pkt_dev = __pktgen_NN_threads(ifname, remove); - thread_unlock(); - return pkt_dev; + const int max_tries = 10, msec_per_try = 125; + int i = 0; + + mutex_lock(&pktgen_thread_lock); + pr_debug("%s: marking %s for removal\n", __func__, ifname); + + while (1) { + + pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE); + if (pkt_dev == NULL) + break; /* success */ + + mutex_unlock(&pktgen_thread_lock); + pr_debug("%s: waiting for %s to disappear....\n", + __func__, ifname); + schedule_timeout_interruptible(msecs_to_jiffies(msec_per_try)); + mutex_lock(&pktgen_thread_lock); + + if (++i >= max_tries) { + pr_err("%s: timed out after waiting %d msec for device %s to be removed\n", + __func__, msec_per_try * i, ifname); + break; + } + + } + + mutex_unlock(&pktgen_thread_lock); } -static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) +static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev) { - struct net_device *dev = (struct net_device *)(ptr); + struct pktgen_thread *t; + + list_for_each_entry(t, &pn->pktgen_threads, th_list) { + struct pktgen_dev *pkt_dev; + + list_for_each_entry(pkt_dev, &t->if_list, list) { + if (pkt_dev->odev != dev) + continue; + + proc_remove(pkt_dev->entry); + + pkt_dev->entry = proc_create_data(dev->name, 0600, + pn->proc_dir, + &pktgen_if_fops, + pkt_dev); + if (!pkt_dev->entry) + pr_err("can't move proc entry for '%s'\n", + dev->name); + break; + } + } +} + +static int pktgen_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); + + if (pn->pktgen_exiting) + return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { - case NETDEV_CHANGEADDR: - case NETDEV_GOING_DOWN: - case NETDEV_DOWN: - case NETDEV_UP: - /* Ignore for now */ + case NETDEV_CHANGENAME: + pktgen_change_name(pn, dev); break; - + case NETDEV_UNREGISTER: - pktgen_NN_threads(dev->name, REMOVE); + pktgen_mark_device(pn, dev->name); break; - }; + } return NOTIFY_DONE; } +static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, + const char *ifname) +{ + char b[IFNAMSIZ+5]; + int i; + + for (i = 0; ifname[i] != '@'; i++) { + if (i == IFNAMSIZ) + break; + + b[i] = ifname[i]; + } + b[i] = 0; + + return dev_get_by_name(pn->net, b); +} + + /* Associate pktgen_dev with a device. */ -static struct net_device* pktgen_setup_dev(struct pktgen_dev *pkt_dev) { +static int pktgen_setup_dev(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) +{ struct net_device *odev; + int err; /* Clean old setups */ - if (pkt_dev->odev) { dev_put(pkt_dev->odev); - pkt_dev->odev = NULL; - } - - odev = dev_get_by_name(pkt_dev->ifname); + pkt_dev->odev = NULL; + } + odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname); if (!odev) { - printk("pktgen: no such netdevice: \"%s\"\n", pkt_dev->ifname); - goto out; + pr_err("no such netdevice: \"%s\"\n", ifname); + return -ENODEV; } + if (odev->type != ARPHRD_ETHER) { - printk("pktgen: not an ethernet device: \"%s\"\n", pkt_dev->ifname); - goto out_put; - } - if (!netif_running(odev)) { - printk("pktgen: device is down: \"%s\"\n", pkt_dev->ifname); - goto out_put; + pr_err("not an ethernet device: \"%s\"\n", ifname); + err = -EINVAL; + } else if (!netif_running(odev)) { + pr_err("device is down: \"%s\"\n", ifname); + err = -ENETDOWN; + } else { + pkt_dev->odev = odev; + return 0; } - pkt_dev->odev = odev; - - return pkt_dev->odev; -out_put: dev_put(odev); -out: - return NULL; - + return err; } /* Read pkt_dev from the interface and set up internal pktgen_dev @@ -1542,89 +2034,109 @@ out: */ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) { - /* Try once more, just in case it works now. */ - if (!pkt_dev->odev) - pktgen_setup_dev(pkt_dev); - - if (!pkt_dev->odev) { - printk("pktgen: ERROR: pkt_dev->odev == NULL in setup_inject.\n"); - sprintf(pkt_dev->result, "ERROR: pkt_dev->odev == NULL in setup_inject.\n"); - return; - } - - /* Default to the interface's mac if not explicitly set. */ + int ntxq; - if (is_zero_ether_addr(pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); + if (!pkt_dev->odev) { + pr_err("ERROR: pkt_dev->odev == NULL in setup_inject\n"); + sprintf(pkt_dev->result, + "ERROR: pkt_dev->odev == NULL in setup_inject.\n"); + return; + } - /* Set up Dest MAC */ - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); + /* make sure that we don't pick a non-existing transmit queue */ + ntxq = pkt_dev->odev->real_num_tx_queues; - /* Set up pkt size */ - pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; - - if(pkt_dev->flags & F_IPV6) { - /* - * Skip this automatic address setting until locks or functions - * gets exported - */ + if (ntxq <= pkt_dev->queue_map_min) { + pr_warning("WARNING: Requested queue_map_min (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); + pkt_dev->queue_map_min = (ntxq ?: 1) - 1; + } + if (pkt_dev->queue_map_max >= ntxq) { + pr_warning("WARNING: Requested queue_map_max (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); + pkt_dev->queue_map_max = (ntxq ?: 1) - 1; + } -#ifdef NOTNOW - int i, set = 0, err=1; + /* Default to the interface's mac if not explicitly set. */ + + if (is_zero_ether_addr(pkt_dev->src_mac)) + ether_addr_copy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr); + + /* Set up Dest MAC */ + ether_addr_copy(&(pkt_dev->hh[0]), pkt_dev->dst_mac); + + if (pkt_dev->flags & F_IPV6) { + int i, set = 0, err = 1; struct inet6_dev *idev; - for(i=0; i< IN6_ADDR_HSIZE; i++) - if(pkt_dev->cur_in6_saddr.s6_addr[i]) { + if (pkt_dev->min_pkt_size == 0) { + pkt_dev->min_pkt_size = 14 + sizeof(struct ipv6hdr) + + sizeof(struct udphdr) + + sizeof(struct pktgen_hdr) + + pkt_dev->pkt_overhead; + } + + for (i = 0; i < IN6_ADDR_HSIZE; i++) + if (pkt_dev->cur_in6_saddr.s6_addr[i]) { set = 1; break; } - if(!set) { - + if (!set) { + /* * Use linklevel address if unconfigured. * * use ipv6_get_lladdr if/when it's get exported */ - - read_lock(&addrconf_lock); - if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { + rcu_read_lock(); + idev = __in6_dev_get(pkt_dev->odev); + if (idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &ifp->addr); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if ((ifp->scope & IFA_LINK) && + !(ifp->flags & IFA_F_TENTATIVE)) { + pkt_dev->cur_in6_saddr = ifp->addr; err = 0; break; } } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); - if(err) printk("pktgen: ERROR: IPv6 link address not availble.\n"); + rcu_read_unlock(); + if (err) + pr_err("ERROR: IPv6 link address not available\n"); } -#endif - } - else { + } else { + if (pkt_dev->min_pkt_size == 0) { + pkt_dev->min_pkt_size = 14 + sizeof(struct iphdr) + + sizeof(struct udphdr) + + sizeof(struct pktgen_hdr) + + pkt_dev->pkt_overhead; + } + pkt_dev->saddr_min = 0; pkt_dev->saddr_max = 0; if (strlen(pkt_dev->src_min) == 0) { - - struct in_device *in_dev; + + struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(pkt_dev->odev); if (in_dev) { if (in_dev->ifa_list) { - pkt_dev->saddr_min = in_dev->ifa_list->ifa_address; + pkt_dev->saddr_min = + in_dev->ifa_list->ifa_address; pkt_dev->saddr_max = pkt_dev->saddr_min; } } rcu_read_unlock(); - } - else { + } else { pkt_dev->saddr_min = in_aton(pkt_dev->src_min); pkt_dev->saddr_max = in_aton(pkt_dev->src_max); } @@ -1632,167 +2144,308 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pkt_dev->daddr_min = in_aton(pkt_dev->dst_min); pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); } - /* Initialize current values. */ - pkt_dev->cur_dst_mac_offset = 0; - pkt_dev->cur_src_mac_offset = 0; - pkt_dev->cur_saddr = pkt_dev->saddr_min; - pkt_dev->cur_daddr = pkt_dev->daddr_min; - pkt_dev->cur_udp_dst = pkt_dev->udp_dst_min; - pkt_dev->cur_udp_src = pkt_dev->udp_src_min; + /* Initialize current values. */ + pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; + if (pkt_dev->min_pkt_size > pkt_dev->max_pkt_size) + pkt_dev->max_pkt_size = pkt_dev->min_pkt_size; + + pkt_dev->cur_dst_mac_offset = 0; + pkt_dev->cur_src_mac_offset = 0; + pkt_dev->cur_saddr = pkt_dev->saddr_min; + pkt_dev->cur_daddr = pkt_dev->daddr_min; + pkt_dev->cur_udp_dst = pkt_dev->udp_dst_min; + pkt_dev->cur_udp_src = pkt_dev->udp_src_min; pkt_dev->nflows = 0; } -static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us) -{ - __u64 start; - __u64 now; - start = now = getCurUs(); - printk(KERN_INFO "sleeping for %d\n", (int)(spin_until_us - now)); - while (now < spin_until_us) { - /* TODO: optimize sleeping behavior */ - if (spin_until_us - now > jiffies_to_usecs(1)+1) - schedule_timeout_interruptible(1); - else if (spin_until_us - now > 100) { - do_softirq(); - if (!pkt_dev->running) - return; - if (need_resched()) +static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) +{ + ktime_t start_time, end_time; + s64 remaining; + struct hrtimer_sleeper t; + + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_set_expires(&t.timer, spin_until); + + remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); + if (remaining <= 0) { + pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); + return; + } + + start_time = ktime_get(); + if (remaining < 100000) { + /* for small delays (<100us), just loop until limit is reached */ + do { + end_time = ktime_get(); + } while (ktime_compare(end_time, spin_until) < 0); + } else { + /* see do_nanosleep */ + hrtimer_init_sleeper(&t, current); + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) schedule(); + + hrtimer_cancel(&t.timer); + } while (t.task && pkt_dev->running && !signal_pending(current)); + __set_current_state(TASK_RUNNING); + end_time = ktime_get(); + } + + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); + pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); +} + +static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) +{ + pkt_dev->pkt_overhead = 0; + pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32); + pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev); + pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); +} + +static inline int f_seen(const struct pktgen_dev *pkt_dev, int flow) +{ + return !!(pkt_dev->flows[flow].flags & F_INIT); +} + +static inline int f_pick(struct pktgen_dev *pkt_dev) +{ + int flow = pkt_dev->curfl; + + if (pkt_dev->flags & F_FLOW_SEQ) { + if (pkt_dev->flows[flow].count >= pkt_dev->lflow) { + /* reset time */ + pkt_dev->flows[flow].count = 0; + pkt_dev->flows[flow].flags = 0; + pkt_dev->curfl += 1; + if (pkt_dev->curfl >= pkt_dev->cflows) + pkt_dev->curfl = 0; /*reset */ } + } else { + flow = prandom_u32() % pkt_dev->cflows; + pkt_dev->curfl = flow; - now = getCurUs(); + if (pkt_dev->flows[flow].count > pkt_dev->lflow) { + pkt_dev->flows[flow].count = 0; + pkt_dev->flows[flow].flags = 0; + } } - pkt_dev->idle_acc += now - start; + return pkt_dev->curfl; } +#ifdef CONFIG_XFRM +/* If there was already an IPSEC SA, we keep it as is, else + * we go look for it ... +*/ +#define DUMMY_MARK 0 +static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) +{ + struct xfrm_state *x = pkt_dev->flows[flow].x; + struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); + if (!x) { + + if (pkt_dev->spi) { + /* We need as quick as possible to find the right SA + * Searching with minimum criteria to archieve this. + */ + x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); + } else { + /* slow path: we dont already have xfrm_state */ + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + (xfrm_address_t *)&pkt_dev->cur_daddr, + (xfrm_address_t *)&pkt_dev->cur_saddr, + AF_INET, + pkt_dev->ipsmode, + pkt_dev->ipsproto, 0); + } + if (x) { + pkt_dev->flows[flow].x = x; + set_pkt_overhead(pkt_dev); + pkt_dev->pkt_overhead += x->props.header_len; + } + + } +} +#endif +static void set_cur_queue_map(struct pktgen_dev *pkt_dev) +{ + + if (pkt_dev->flags & F_QUEUE_MAP_CPU) + pkt_dev->cur_queue_map = smp_processor_id(); + + else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) { + __u16 t; + if (pkt_dev->flags & F_QUEUE_MAP_RND) { + t = prandom_u32() % + (pkt_dev->queue_map_max - + pkt_dev->queue_map_min + 1) + + pkt_dev->queue_map_min; + } else { + t = pkt_dev->cur_queue_map + 1; + if (t > pkt_dev->queue_map_max) + t = pkt_dev->queue_map_min; + } + pkt_dev->cur_queue_map = t; + } + pkt_dev->cur_queue_map = pkt_dev->cur_queue_map % pkt_dev->odev->real_num_tx_queues; +} + /* Increment/randomize headers according to flags and current values * for IP src/dest, UDP src/dst port, MAC-Addr src/dst */ -static void mod_cur_headers(struct pktgen_dev *pkt_dev) { - __u32 imn; - __u32 imx; - int flow = 0; - - if(pkt_dev->cflows) { - flow = pktgen_random() % pkt_dev->cflows; - - if (pkt_dev->flows[flow].count > pkt_dev->lflow) - pkt_dev->flows[flow].count = 0; - } +static void mod_cur_headers(struct pktgen_dev *pkt_dev) +{ + __u32 imn; + __u32 imx; + int flow = 0; + if (pkt_dev->cflows) + flow = f_pick(pkt_dev); /* Deal with source MAC */ - if (pkt_dev->src_mac_count > 1) { - __u32 mc; - __u32 tmp; - - if (pkt_dev->flags & F_MACSRC_RND) - mc = pktgen_random() % (pkt_dev->src_mac_count); - else { - mc = pkt_dev->cur_src_mac_offset++; - if (pkt_dev->cur_src_mac_offset > pkt_dev->src_mac_count) - pkt_dev->cur_src_mac_offset = 0; - } - - tmp = pkt_dev->src_mac[5] + (mc & 0xFF); - pkt_dev->hh[11] = tmp; - tmp = (pkt_dev->src_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[10] = tmp; - tmp = (pkt_dev->src_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[9] = tmp; - tmp = (pkt_dev->src_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[8] = tmp; - tmp = (pkt_dev->src_mac[1] + (tmp >> 8)); - pkt_dev->hh[7] = tmp; - } - - /* Deal with Destination MAC */ - if (pkt_dev->dst_mac_count > 1) { - __u32 mc; - __u32 tmp; - - if (pkt_dev->flags & F_MACDST_RND) - mc = pktgen_random() % (pkt_dev->dst_mac_count); - - else { - mc = pkt_dev->cur_dst_mac_offset++; - if (pkt_dev->cur_dst_mac_offset > pkt_dev->dst_mac_count) { - pkt_dev->cur_dst_mac_offset = 0; - } - } - - tmp = pkt_dev->dst_mac[5] + (mc & 0xFF); - pkt_dev->hh[5] = tmp; - tmp = (pkt_dev->dst_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[4] = tmp; - tmp = (pkt_dev->dst_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[3] = tmp; - tmp = (pkt_dev->dst_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); - pkt_dev->hh[2] = tmp; - tmp = (pkt_dev->dst_mac[1] + (tmp >> 8)); - pkt_dev->hh[1] = tmp; - } - - if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { - if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = ((pktgen_random() % (pkt_dev->udp_src_max - pkt_dev->udp_src_min)) + pkt_dev->udp_src_min); - - else { + if (pkt_dev->src_mac_count > 1) { + __u32 mc; + __u32 tmp; + + if (pkt_dev->flags & F_MACSRC_RND) + mc = prandom_u32() % pkt_dev->src_mac_count; + else { + mc = pkt_dev->cur_src_mac_offset++; + if (pkt_dev->cur_src_mac_offset >= + pkt_dev->src_mac_count) + pkt_dev->cur_src_mac_offset = 0; + } + + tmp = pkt_dev->src_mac[5] + (mc & 0xFF); + pkt_dev->hh[11] = tmp; + tmp = (pkt_dev->src_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[10] = tmp; + tmp = (pkt_dev->src_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[9] = tmp; + tmp = (pkt_dev->src_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[8] = tmp; + tmp = (pkt_dev->src_mac[1] + (tmp >> 8)); + pkt_dev->hh[7] = tmp; + } + + /* Deal with Destination MAC */ + if (pkt_dev->dst_mac_count > 1) { + __u32 mc; + __u32 tmp; + + if (pkt_dev->flags & F_MACDST_RND) + mc = prandom_u32() % pkt_dev->dst_mac_count; + + else { + mc = pkt_dev->cur_dst_mac_offset++; + if (pkt_dev->cur_dst_mac_offset >= + pkt_dev->dst_mac_count) { + pkt_dev->cur_dst_mac_offset = 0; + } + } + + tmp = pkt_dev->dst_mac[5] + (mc & 0xFF); + pkt_dev->hh[5] = tmp; + tmp = (pkt_dev->dst_mac[4] + ((mc >> 8) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[4] = tmp; + tmp = (pkt_dev->dst_mac[3] + ((mc >> 16) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[3] = tmp; + tmp = (pkt_dev->dst_mac[2] + ((mc >> 24) & 0xFF) + (tmp >> 8)); + pkt_dev->hh[2] = tmp; + tmp = (pkt_dev->dst_mac[1] + (tmp >> 8)); + pkt_dev->hh[1] = tmp; + } + + if (pkt_dev->flags & F_MPLS_RND) { + unsigned int i; + for (i = 0; i < pkt_dev->nr_labels; i++) + if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM) + pkt_dev->labels[i] = MPLS_STACK_BOTTOM | + ((__force __be32)prandom_u32() & + htonl(0x000fffff)); + } + + if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_id = prandom_u32() & (4096 - 1); + } + + if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_id = prandom_u32() & (4096 - 1); + } + + if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { + if (pkt_dev->flags & F_UDPSRC_RND) + pkt_dev->cur_udp_src = prandom_u32() % + (pkt_dev->udp_src_max - pkt_dev->udp_src_min) + + pkt_dev->udp_src_min; + + else { pkt_dev->cur_udp_src++; if (pkt_dev->cur_udp_src >= pkt_dev->udp_src_max) pkt_dev->cur_udp_src = pkt_dev->udp_src_min; - } - } - - if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { - if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = ((pktgen_random() % (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min)) + pkt_dev->udp_dst_min); - } - else { + } + } + + if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { + if (pkt_dev->flags & F_UDPDST_RND) { + pkt_dev->cur_udp_dst = prandom_u32() % + (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) + + pkt_dev->udp_dst_min; + } else { pkt_dev->cur_udp_dst++; - if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) + if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) pkt_dev->cur_udp_dst = pkt_dev->udp_dst_min; - } - } + } + } if (!(pkt_dev->flags & F_IPV6)) { - if ((imn = ntohl(pkt_dev->saddr_min)) < (imx = ntohl(pkt_dev->saddr_max))) { + imn = ntohl(pkt_dev->saddr_min); + imx = ntohl(pkt_dev->saddr_max); + if (imn < imx) { __u32 t; - if (pkt_dev->flags & F_IPSRC_RND) - t = ((pktgen_random() % (imx - imn)) + imn); + if (pkt_dev->flags & F_IPSRC_RND) + t = prandom_u32() % (imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; - if (t > imx) { + if (t > imx) t = imn; - } + } pkt_dev->cur_saddr = htonl(t); } - - if (pkt_dev->cflows && pkt_dev->flows[flow].count != 0) { + + if (pkt_dev->cflows && f_seen(pkt_dev, flow)) { pkt_dev->cur_daddr = pkt_dev->flows[flow].cur_daddr; } else { - - if ((imn = ntohl(pkt_dev->daddr_min)) < (imx = ntohl(pkt_dev->daddr_max))) { + imn = ntohl(pkt_dev->daddr_min); + imx = ntohl(pkt_dev->daddr_max); + if (imn < imx) { __u32 t; + __be32 s; if (pkt_dev->flags & F_IPDST_RND) { - t = ((pktgen_random() % (imx - imn)) + imn); - t = htonl(t); - - while( LOOPBACK(t) || MULTICAST(t) || BADCLASS(t) || ZERONET(t) || LOCAL_MCAST(t) ) { - t = ((pktgen_random() % (imx - imn)) + imn); - t = htonl(t); - } - pkt_dev->cur_daddr = t; - } - - else { + do { + t = prandom_u32() % + (imx - imn) + imn; + s = htonl(t); + } while (ipv4_is_loopback(s) || + ipv4_is_multicast(s) || + ipv4_is_lbcast(s) || + ipv4_is_zeronet(s) || + ipv4_is_local_multicast(s)); + pkt_dev->cur_daddr = s; + } else { t = ntohl(pkt_dev->cur_daddr); t++; if (t > imx) { @@ -1801,1254 +2454,1378 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) { pkt_dev->cur_daddr = htonl(t); } } - if(pkt_dev->cflows) { - pkt_dev->flows[flow].cur_daddr = pkt_dev->cur_daddr; + if (pkt_dev->cflows) { + pkt_dev->flows[flow].flags |= F_INIT; + pkt_dev->flows[flow].cur_daddr = + pkt_dev->cur_daddr; +#ifdef CONFIG_XFRM + if (pkt_dev->flags & F_IPSEC_ON) + get_ipsec_sa(pkt_dev, flow); +#endif pkt_dev->nflows++; } } - } - else /* IPV6 * */ - { - if(pkt_dev->min_in6_daddr.s6_addr32[0] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[1] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[2] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[3] == 0); - else { + } else { /* IPV6 * */ + + if (!ipv6_addr_any(&pkt_dev->min_in6_daddr)) { int i; /* Only random destinations yet */ - for(i=0; i < 4; i++) { + for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - ((pktgen_random() | - pkt_dev->min_in6_daddr.s6_addr32[i]) & - pkt_dev->max_in6_daddr.s6_addr32[i]); + (((__force __be32)prandom_u32() | + pkt_dev->min_in6_daddr.s6_addr32[i]) & + pkt_dev->max_in6_daddr.s6_addr32[i]); } - } + } } - if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { - __u32 t; - if (pkt_dev->flags & F_TXSIZE_RND) { - t = ((pktgen_random() % (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size)) - + pkt_dev->min_pkt_size); - } - else { + if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { + __u32 t; + if (pkt_dev->flags & F_TXSIZE_RND) { + t = prandom_u32() % + (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size) + + pkt_dev->min_pkt_size; + } else { t = pkt_dev->cur_pkt_size + 1; - if (t > pkt_dev->max_pkt_size) + if (t > pkt_dev->max_pkt_size) t = pkt_dev->min_pkt_size; - } - pkt_dev->cur_pkt_size = t; - } + } + pkt_dev->cur_pkt_size = t; + } + + set_cur_queue_map(pkt_dev); pkt_dev->flows[flow].count++; } -static struct sk_buff *fill_packet_ipv4(struct net_device *odev, - struct pktgen_dev *pkt_dev) +#ifdef CONFIG_XFRM +static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { + + [RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */ +}; + +static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { - struct sk_buff *skb = NULL; - __u8 *eth; - struct udphdr *udph; - int datalen, iplen; - struct iphdr *iph; - struct pktgen_hdr *pgh = NULL; - - /* Update any of the values, used when we're incrementing various - * fields. + struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; + int err = 0; + struct net *net = dev_net(pkt_dev->odev); + + if (!x) + return 0; + /* XXX: we dont support tunnel mode for now until + * we resolve the dst issue */ + if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0)) + return 0; + + /* But when user specify an valid SPI, transformation + * supports both transport/tunnel mode + ESP/AH type. */ - mod_cur_headers(pkt_dev); + if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0)) + skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF; + + rcu_read_lock_bh(); + err = x->outer_mode->output(x, skb); + rcu_read_unlock_bh(); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); + goto error; + } + err = x->type->output(x, skb); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); + goto error; + } + spin_lock_bh(&x->lock); + x->curlft.bytes += skb->len; + x->curlft.packets++; + spin_unlock_bh(&x->lock); +error: + return err; +} - datalen = (odev->hard_header_len + 16) & ~0xf; - skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen, GFP_ATOMIC); - if (!skb) { - sprintf(pkt_dev->result, "No memory"); - return NULL; +static void free_SAs(struct pktgen_dev *pkt_dev) +{ + if (pkt_dev->cflows) { + /* let go of the SAs if we have them */ + int i; + for (i = 0; i < pkt_dev->cflows; i++) { + struct xfrm_state *x = pkt_dev->flows[i].x; + if (x) { + xfrm_state_put(x); + pkt_dev->flows[i].x = NULL; + } + } } +} - skb_reserve(skb, datalen); +static int process_ipsec(struct pktgen_dev *pkt_dev, + struct sk_buff *skb, __be16 protocol) +{ + if (pkt_dev->flags & F_IPSEC_ON) { + struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; + int nhead = 0; + if (x) { + int ret; + __u8 *eth; + struct iphdr *iph; + + nhead = x->props.header_len - skb_headroom(skb); + if (nhead > 0) { + ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); + if (ret < 0) { + pr_err("Error expanding ipsec packet %d\n", + ret); + goto err; + } + } - /* Reserve for ethernet and IP header */ - eth = (__u8 *) skb_push(skb, 14); - iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)); - udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + /* ipsec is not expecting ll header */ + skb_pull(skb, ETH_HLEN); + ret = pktgen_output_ipsec(skb, pkt_dev); + if (ret) { + pr_err("Error creating ipsec packet %d\n", ret); + goto err; + } + /* restore ll */ + eth = (__u8 *) skb_push(skb, ETH_HLEN); + memcpy(eth, pkt_dev->hh, 12); + *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); + } + } + return 1; +err: + kfree_skb(skb); + return 0; +} +#endif - memcpy(eth, pkt_dev->hh, 12); - *(u16*)ð[12] = __constant_htons(ETH_P_IP); +static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev) +{ + unsigned int i; + for (i = 0; i < pkt_dev->nr_labels; i++) + *mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM; - datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8; /* Eth + IPh + UDPh */ - if (datalen < sizeof(struct pktgen_hdr)) - datalen = sizeof(struct pktgen_hdr); - - udph->source = htons(pkt_dev->cur_udp_src); - udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + 8); /* DATA + udphdr */ - udph->check = 0; /* No checksum */ + mpls--; + *mpls |= MPLS_STACK_BOTTOM; +} - iph->ihl = 5; - iph->version = 4; - iph->ttl = 32; - iph->tos = 0; - iph->protocol = IPPROTO_UDP; /* UDP */ - iph->saddr = pkt_dev->cur_saddr; - iph->daddr = pkt_dev->cur_daddr; - iph->frag_off = 0; - iplen = 20 + 8 + datalen; - iph->tot_len = htons(iplen); - iph->check = 0; - iph->check = ip_fast_csum((void *) iph, iph->ihl); - skb->protocol = __constant_htons(ETH_P_IP); - skb->mac.raw = ((u8 *)iph) - 14; - skb->dev = odev; - skb->pkt_type = PACKET_HOST; +static inline __be16 build_tci(unsigned int id, unsigned int cfi, + unsigned int prio) +{ + return htons(id | (cfi << 12) | (prio << 13)); +} + +static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, + int datalen) +{ + struct timeval timestamp; + struct pktgen_hdr *pgh; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { + pgh = (struct pktgen_hdr *)skb_put(skb, sizeof(*pgh)); + datalen -= sizeof(*pgh); + + if (pkt_dev->nfrags <= 0) { + memset(skb_put(skb, datalen), 0, datalen); + } else { int frags = pkt_dev->nfrags; - int i; + int i, len; + int frag_len; + - pgh = (struct pktgen_hdr*)(((char*)(udph)) + 8); - if (frags > MAX_SKB_FRAGS) frags = MAX_SKB_FRAGS; - if (datalen > frags*PAGE_SIZE) { - skb_put(skb, datalen-frags*PAGE_SIZE); - datalen = frags*PAGE_SIZE; + len = datalen - frags * PAGE_SIZE; + if (len > 0) { + memset(skb_put(skb, len), 0, len); + datalen = frags * PAGE_SIZE; } i = 0; + frag_len = (datalen/frags) < PAGE_SIZE ? + (datalen/frags) : PAGE_SIZE; while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; + if (unlikely(!pkt_dev->page)) { + int node = numa_node_id(); + + if (pkt_dev->node >= 0 && (pkt_dev->flags & F_NODE)) + node = pkt_dev->node; + pkt_dev->page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!pkt_dev->page) + break; + } + get_page(pkt_dev->page); + skb_frag_set_page(skb, i, pkt_dev->page); skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; + /*last fragment, fill rest of data*/ + if (i == (frags - 1)) + skb_frag_size_set(&skb_shinfo(skb)->frags[i], + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE)); + else + skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len); + datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]); i++; skb_shinfo(skb)->nr_frags = i; } + } - while (i < frags) { - int rem; + /* Stamp the time, and sequence number, + * convert them to network byte order + */ + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); - if (i == 0) - break; + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); +} - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; +static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, + struct pktgen_dev *pkt_dev, + unsigned int extralen) +{ + struct sk_buff *skb = NULL; + unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen + + pkt_dev->pkt_overhead; - skb_shinfo(skb)->frags[i - 1].size -= rem; + if (pkt_dev->flags & F_NODE) { + int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id(); - skb_shinfo(skb)->frags[i] = skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; + skb = __alloc_skb(NET_SKB_PAD + size, GFP_NOWAIT, 0, node); + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; } + } else { + skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } - /* Stamp the time, and sequence number, convert them to network byte order */ - - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - pkt_dev->seq_num++; - return skb; } -/* - * scan_ip6, fmt_ip taken from dietlibc-0.21 - * Author Felix von Leitner <felix-dietlibc@fefe.de> - * - * Slightly modified for kernel. - * Should be candidate for net/ipv4/utils.c - * --ro - */ - -static unsigned int scan_ip6(const char *s,char ip[16]) +static struct sk_buff *fill_packet_ipv4(struct net_device *odev, + struct pktgen_dev *pkt_dev) { - unsigned int i; - unsigned int len=0; - unsigned long u; - char suffix[16]; - unsigned int prefixlen=0; - unsigned int suffixlen=0; - __u32 tmp; - - for (i=0; i<16; i++) ip[i]=0; - - for (;;) { - if (*s == ':') { - len++; - if (s[1] == ':') { /* Found "::", skip to part 2 */ - s+=2; - len++; - break; - } - s++; - } - { - char *tmp; - u=simple_strtoul(s,&tmp,16); - i=tmp-s; - } + struct sk_buff *skb = NULL; + __u8 *eth; + struct udphdr *udph; + int datalen, iplen; + struct iphdr *iph; + __be16 protocol = htons(ETH_P_IP); + __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ + u16 queue_map; - if (!i) return 0; - if (prefixlen==12 && s[i]=='.') { + if (pkt_dev->nr_labels) + protocol = htons(ETH_P_MPLS_UC); - /* the last 4 bytes may be written as IPv4 address */ + if (pkt_dev->vlan_id != 0xffff) + protocol = htons(ETH_P_8021Q); - tmp = in_aton(s); - memcpy((struct in_addr*)(ip+12), &tmp, sizeof(tmp)); - return i+len; - } - ip[prefixlen++] = (u >> 8); - ip[prefixlen++] = (u & 255); - s += i; len += i; - if (prefixlen==16) - return len; + /* Update any of the values, used when we're incrementing various + * fields. + */ + mod_cur_headers(pkt_dev); + queue_map = pkt_dev->cur_queue_map; + + datalen = (odev->hard_header_len + 16) & ~0xf; + + skb = pktgen_alloc_skb(odev, pkt_dev, datalen); + if (!skb) { + sprintf(pkt_dev->result, "No memory"); + return NULL; } -/* part 2, after "::" */ - for (;;) { - if (*s == ':') { - if (suffixlen==0) - break; - s++; - len++; - } else if (suffixlen!=0) - break; - { - char *tmp; - u=simple_strtol(s,&tmp,16); - i=tmp-s; - } - if (!i) { - if (*s) len--; - break; - } - if (suffixlen+prefixlen<=12 && s[i]=='.') { - tmp = in_aton(s); - memcpy((struct in_addr*)(suffix+suffixlen), &tmp, sizeof(tmp)); - suffixlen+=4; - len+=strlen(s); - break; + prefetchw(skb->data); + skb_reserve(skb, datalen); + + /* Reserve for ethernet and IP header */ + eth = (__u8 *) skb_push(skb, 14); + mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); + if (pkt_dev->nr_labels) + mpls_push(mpls, pkt_dev); + + if (pkt_dev->vlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = build_tci(pkt_dev->svlan_id, + pkt_dev->svlan_cfi, + pkt_dev->svlan_p); + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = htons(ETH_P_8021Q); } - suffix[suffixlen++] = (u >> 8); - suffix[suffixlen++] = (u & 255); - s += i; len += i; - if (prefixlen+suffixlen==16) - break; + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = build_tci(pkt_dev->vlan_id, + pkt_dev->vlan_cfi, + pkt_dev->vlan_p); + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = htons(ETH_P_IP); } - for (i=0; i<suffixlen; i++) - ip[16-suffixlen+i] = suffix[i]; - return len; -} -static char tohex(char hexdigit) { - return hexdigit>9?hexdigit+'a'-10:hexdigit+'0'; -} + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr)); -static int fmt_xlong(char* s,unsigned int i) { - char* bak=s; - *s=tohex((i>>12)&0xf); if (s!=bak || *s!='0') ++s; - *s=tohex((i>>8)&0xf); if (s!=bak || *s!='0') ++s; - *s=tohex((i>>4)&0xf); if (s!=bak || *s!='0') ++s; - *s=tohex(i&0xf); - return s-bak+1; -} + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); + skb_set_queue_mapping(skb, queue_map); + skb->priority = pkt_dev->skb_priority; -static unsigned int fmt_ip6(char *s,const char ip[16]) { - unsigned int len; - unsigned int i; - unsigned int temp; - unsigned int compressing; - int j; - - len = 0; compressing = 0; - for (j=0; j<16; j+=2) { - -#ifdef V4MAPPEDPREFIX - if (j==12 && !memcmp(ip,V4mappedprefix,12)) { - inet_ntoa_r(*(struct in_addr*)(ip+12),s); - temp=strlen(s); - return len+temp; - } -#endif - temp = ((unsigned long) (unsigned char) ip[j] << 8) + - (unsigned long) (unsigned char) ip[j+1]; - if (temp == 0) { - if (!compressing) { - compressing=1; - if (j==0) { - *s++=':'; ++len; - } - } - } else { - if (compressing) { - compressing=0; - *s++=':'; ++len; - } - i = fmt_xlong(s,temp); len += i; s += i; - if (j<14) { - *s++ = ':'; - ++len; - } - } - } - if (compressing) { - *s++=':'; ++len; + memcpy(eth, pkt_dev->hh, 12); + *(__be16 *) & eth[12] = protocol; + + /* Eth + IPh + UDPh + mpls */ + datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 - + pkt_dev->pkt_overhead; + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) + datalen = sizeof(struct pktgen_hdr); + + udph->source = htons(pkt_dev->cur_udp_src); + udph->dest = htons(pkt_dev->cur_udp_dst); + udph->len = htons(datalen + 8); /* DATA + udphdr */ + udph->check = 0; + + iph->ihl = 5; + iph->version = 4; + iph->ttl = 32; + iph->tos = pkt_dev->tos; + iph->protocol = IPPROTO_UDP; /* UDP */ + iph->saddr = pkt_dev->cur_saddr; + iph->daddr = pkt_dev->cur_daddr; + iph->id = htons(pkt_dev->ip_id); + pkt_dev->ip_id++; + iph->frag_off = 0; + iplen = 20 + 8 + datalen; + iph->tot_len = htons(iplen); + ip_send_check(iph); + skb->protocol = protocol; + skb->dev = odev; + skb->pkt_type = PACKET_HOST; + + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum = 0; + udp4_hwcsum(skb, udph->source, udph->dest); + } else { + __wsum csum = udp_csum(skb); + + /* add protocol-dependent pseudo-header */ + udph->check = csum_tcpudp_magic(udph->source, udph->dest, + datalen + 8, IPPROTO_UDP, csum); + + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; } - *s=0; - return len; + + pktgen_finalize_skb(pkt_dev, skb, datalen); + +#ifdef CONFIG_XFRM + if (!process_ipsec(pkt_dev, skb, protocol)) + return NULL; +#endif + + return skb; } -static struct sk_buff *fill_packet_ipv6(struct net_device *odev, - struct pktgen_dev *pkt_dev) +static struct sk_buff *fill_packet_ipv6(struct net_device *odev, + struct pktgen_dev *pkt_dev) { struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; - int datalen; + int datalen, udplen; struct ipv6hdr *iph; - struct pktgen_hdr *pgh = NULL; + __be16 protocol = htons(ETH_P_IPV6); + __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ + u16 queue_map; + + if (pkt_dev->nr_labels) + protocol = htons(ETH_P_MPLS_UC); + + if (pkt_dev->vlan_id != 0xffff) + protocol = htons(ETH_P_8021Q); /* Update any of the values, used when we're incrementing various * fields. */ mod_cur_headers(pkt_dev); + queue_map = pkt_dev->cur_queue_map; - skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16, GFP_ATOMIC); + skb = pktgen_alloc_skb(odev, pkt_dev, 16); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ eth = (__u8 *) skb_push(skb, 14); - iph = (struct ipv6hdr *)skb_put(skb, sizeof(struct ipv6hdr)); - udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); + if (pkt_dev->nr_labels) + mpls_push(mpls, pkt_dev); + + if (pkt_dev->vlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = build_tci(pkt_dev->svlan_id, + pkt_dev->svlan_cfi, + pkt_dev->svlan_p); + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = build_tci(pkt_dev->vlan_id, + pkt_dev->vlan_cfi, + pkt_dev->vlan_p); + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = htons(ETH_P_IPV6); + } + + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); + skb_set_queue_mapping(skb, queue_map); + skb->priority = pkt_dev->skb_priority; memcpy(eth, pkt_dev->hh, 12); - *(u16*)ð[12] = __constant_htons(ETH_P_IPV6); + *(__be16 *) ð[12] = protocol; - datalen = pkt_dev->cur_pkt_size-14- - sizeof(struct ipv6hdr)-sizeof(struct udphdr); /* Eth + IPh + UDPh */ + /* Eth + IPh + UDPh + mpls */ + datalen = pkt_dev->cur_pkt_size - 14 - + sizeof(struct ipv6hdr) - sizeof(struct udphdr) - + pkt_dev->pkt_overhead; - if (datalen < sizeof(struct pktgen_hdr)) { + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); - if (net_ratelimit()) - printk(KERN_INFO "pktgen: increased datalen to %d\n", datalen); + net_info_ratelimited("increased datalen to %d\n", datalen); } + udplen = datalen + sizeof(struct udphdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + sizeof(struct udphdr)); - udph->check = 0; /* No checksum */ + udph->len = htons(udplen); + udph->check = 0; + + *(__be32 *) iph = htonl(0x60000000); /* Version + flow */ - *(u32*)iph = __constant_htonl(0x60000000); /* Version + flow */ + if (pkt_dev->traffic_class) { + /* Version + traffic class + flow (0) */ + *(__be32 *)iph |= htonl(0x60000000 | (pkt_dev->traffic_class << 20)); + } iph->hop_limit = 32; - iph->payload_len = htons(sizeof(struct udphdr) + datalen); + iph->payload_len = htons(udplen); iph->nexthdr = IPPROTO_UDP; - ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); - ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); + iph->daddr = pkt_dev->cur_in6_daddr; + iph->saddr = pkt_dev->cur_in6_saddr; - skb->mac.raw = ((u8 *)iph) - 14; - skb->protocol = __constant_htons(ETH_P_IPV6); + skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { - int frags = pkt_dev->nfrags; - int i; - - pgh = (struct pktgen_hdr*)(((char*)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags*PAGE_SIZE) { - skb_put(skb, datalen-frags*PAGE_SIZE); - datalen = frags*PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V6_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); + } else { + __wsum csum = udp_csum(skb); - skb_shinfo(skb)->frags[i - 1].size -= rem; + /* add protocol-dependent pseudo-header */ + udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); - skb_shinfo(skb)->frags[i] = skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; } - /* Stamp the time, and sequence number, convert them to network byte order */ - /* should we update cloned packets too ? */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - pkt_dev->seq_num++; - + pktgen_finalize_skb(pkt_dev, skb, datalen); + return skb; } -static inline struct sk_buff *fill_packet(struct net_device *odev, +static struct sk_buff *fill_packet(struct net_device *odev, struct pktgen_dev *pkt_dev) { - if(pkt_dev->flags & F_IPV6) + if (pkt_dev->flags & F_IPV6) return fill_packet_ipv6(odev, pkt_dev); else return fill_packet_ipv4(odev, pkt_dev); } -static void pktgen_clear_counters(struct pktgen_dev *pkt_dev) +static void pktgen_clear_counters(struct pktgen_dev *pkt_dev) { - pkt_dev->seq_num = 1; - pkt_dev->idle_acc = 0; + pkt_dev->seq_num = 1; + pkt_dev->idle_acc = 0; pkt_dev->sofar = 0; - pkt_dev->tx_bytes = 0; - pkt_dev->errors = 0; + pkt_dev->tx_bytes = 0; + pkt_dev->errors = 0; } /* Set up structure for sending pkts, clear counters */ static void pktgen_run(struct pktgen_thread *t) { - struct pktgen_dev *pkt_dev = NULL; + struct pktgen_dev *pkt_dev; int started = 0; - PG_DEBUG(printk("pktgen: entering pktgen_run. %p\n", t)); + func_enter(); if_lock(t); - for (pkt_dev = t->if_list; pkt_dev; pkt_dev = pkt_dev->next ) { + list_for_each_entry(pkt_dev, &t->if_list, list) { /* * setup odev and create initial packet. */ pktgen_setup_inject(pkt_dev); - if(pkt_dev->odev) { + if (pkt_dev->odev) { pktgen_clear_counters(pkt_dev); - pkt_dev->running = 1; /* Cranke yeself! */ + pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; - pkt_dev->started_at = getCurUs(); - pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */ - pkt_dev->next_tx_ns = 0; - + pkt_dev->started_at = pkt_dev->next_tx = ktime_get(); + + set_pkt_overhead(pkt_dev); + strcpy(pkt_dev->result, "Starting"); started++; - } - else + } else strcpy(pkt_dev->result, "Error starting"); } if_unlock(t); - if(started) t->control &= ~(T_STOP); + if (started) + t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(void) +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) { - struct pktgen_thread *t = pktgen_threads; + struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_stop_all_threads.\n")); + func_enter(); - thread_lock(); - while(t) { - pktgen_stop(t); - t = t->next; - } - thread_unlock(); + mutex_lock(&pktgen_thread_lock); + + list_for_each_entry(t, &pn->pktgen_threads, th_list) + t->control |= T_STOP; + + mutex_unlock(&pktgen_thread_lock); } -static int thread_is_running(struct pktgen_thread *t ) +static int thread_is_running(const struct pktgen_thread *t) { - struct pktgen_dev *next; - int res = 0; + const struct pktgen_dev *pkt_dev; - for(next=t->if_list; next; next=next->next) { - if(next->running) { - res = 1; - break; - } - } - return res; + list_for_each_entry(pkt_dev, &t->if_list, list) + if (pkt_dev->running) + return 1; + return 0; } -static int pktgen_wait_thread_run(struct pktgen_thread *t ) +static int pktgen_wait_thread_run(struct pktgen_thread *t) { - if_lock(t); + if_lock(t); - while(thread_is_running(t)) { + while (thread_is_running(t)) { - if_unlock(t); + if_unlock(t); - msleep_interruptible(100); + msleep_interruptible(100); - if (signal_pending(current)) - goto signal; - if_lock(t); - } - if_unlock(t); - return 1; - signal: - return 0; + if (signal_pending(current)) + goto signal; + if_lock(t); + } + if_unlock(t); + return 1; +signal: + return 0; } -static int pktgen_wait_all_threads_run(void) +static int pktgen_wait_all_threads_run(struct pktgen_net *pn) { - struct pktgen_thread *t = pktgen_threads; + struct pktgen_thread *t; int sig = 1; - - while (t) { + + mutex_lock(&pktgen_thread_lock); + + list_for_each_entry(t, &pn->pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); - if( sig == 0 ) break; - thread_lock(); - t=t->next; - thread_unlock(); - } - if(sig == 0) { - thread_lock(); - while (t) { - t->control |= (T_STOP); - t=t->next; - } - thread_unlock(); + if (sig == 0) + break; } + + if (sig == 0) + list_for_each_entry(t, &pn->pktgen_threads, th_list) + t->control |= (T_STOP); + + mutex_unlock(&pktgen_thread_lock); return sig; } -static void pktgen_run_all_threads(void) +static void pktgen_run_all_threads(struct pktgen_net *pn) { - struct pktgen_thread *t = pktgen_threads; + struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_run_all_threads.\n")); + func_enter(); - thread_lock(); + mutex_lock(&pktgen_thread_lock); - while(t) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_RUN); - t = t->next; - } - thread_unlock(); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ - - pktgen_wait_all_threads_run(); -} + mutex_unlock(&pktgen_thread_lock); + /* Propagate thread->control */ + schedule_timeout_interruptible(msecs_to_jiffies(125)); -static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) + pktgen_wait_all_threads_run(pn); +} + +static void pktgen_reset_all_threads(struct pktgen_net *pn) { - __u64 total_us, bps, mbps, pps, idle; - char *p = pkt_dev->result; + struct pktgen_thread *t; - total_us = pkt_dev->stopped_at - pkt_dev->started_at; + func_enter(); - idle = pkt_dev->idle_acc; + mutex_lock(&pktgen_thread_lock); - p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", - (unsigned long long) total_us, - (unsigned long long)(total_us - idle), - (unsigned long long) idle, - (unsigned long long) pkt_dev->sofar, - pkt_dev->cur_pkt_size, nr_frags); + list_for_each_entry(t, &pn->pktgen_threads, th_list) + t->control |= (T_REMDEVALL); - pps = pkt_dev->sofar * USEC_PER_SEC; + mutex_unlock(&pktgen_thread_lock); - while ((total_us >> 32) != 0) { - pps >>= 1; - total_us >>= 1; - } + /* Propagate thread->control */ + schedule_timeout_interruptible(msecs_to_jiffies(125)); - do_div(pps, total_us); - - bps = pps * 8 * pkt_dev->cur_pkt_size; + pktgen_wait_all_threads_run(pn); +} - mbps = bps; - do_div(mbps, 1000000); - p += sprintf(p, " %llupps %lluMb/sec (%llubps) errors: %llu", - (unsigned long long) pps, - (unsigned long long) mbps, - (unsigned long long) bps, - (unsigned long long) pkt_dev->errors); +static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) +{ + __u64 bps, mbps, pps; + char *p = pkt_dev->result; + ktime_t elapsed = ktime_sub(pkt_dev->stopped_at, + pkt_dev->started_at); + ktime_t idle = ns_to_ktime(pkt_dev->idle_acc); + + p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", + (unsigned long long)ktime_to_us(elapsed), + (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)), + (unsigned long long)ktime_to_us(idle), + (unsigned long long)pkt_dev->sofar, + pkt_dev->cur_pkt_size, nr_frags); + + pps = div64_u64(pkt_dev->sofar * NSEC_PER_SEC, + ktime_to_ns(elapsed)); + + bps = pps * 8 * pkt_dev->cur_pkt_size; + + mbps = bps; + do_div(mbps, 1000000); + p += sprintf(p, " %llupps %lluMb/sec (%llubps) errors: %llu", + (unsigned long long)pps, + (unsigned long long)mbps, + (unsigned long long)bps, + (unsigned long long)pkt_dev->errors); } - /* Set stopped-at timer, remove from running list, do counters & statistics */ - -static int pktgen_stop_device(struct pktgen_dev *pkt_dev) +static int pktgen_stop_device(struct pktgen_dev *pkt_dev) { - - if (!pkt_dev->running) { - printk("pktgen: interface: %s is already stopped\n", pkt_dev->ifname); - return -EINVAL; - } + int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1; - pkt_dev->stopped_at = getCurUs(); - pkt_dev->running = 0; + if (!pkt_dev->running) { + pr_warning("interface: %s is already stopped\n", + pkt_dev->odevname); + return -EINVAL; + } - show_results(pkt_dev, skb_shinfo(pkt_dev->skb)->nr_frags); + kfree_skb(pkt_dev->skb); + pkt_dev->skb = NULL; + pkt_dev->stopped_at = ktime_get(); + pkt_dev->running = 0; - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + show_results(pkt_dev, nr_frags); - pkt_dev->skb = NULL; - - return 0; + return 0; } -static struct pktgen_dev *next_to_run(struct pktgen_thread *t ) +static struct pktgen_dev *next_to_run(struct pktgen_thread *t) { - struct pktgen_dev *next, *best = NULL; - + struct pktgen_dev *pkt_dev, *best = NULL; + if_lock(t); - for(next=t->if_list; next ; next=next->next) { - if(!next->running) continue; - if(best == NULL) best=next; - else if ( next->next_tx_us < best->next_tx_us) - best = next; + list_for_each_entry(pkt_dev, &t->if_list, list) { + if (!pkt_dev->running) + continue; + if (best == NULL) + best = pkt_dev; + else if (ktime_compare(pkt_dev->next_tx, best->next_tx) < 0) + best = pkt_dev; } if_unlock(t); - return best; + return best; } -static void pktgen_stop(struct pktgen_thread *t) { - struct pktgen_dev *next = NULL; +static void pktgen_stop(struct pktgen_thread *t) +{ + struct pktgen_dev *pkt_dev; - PG_DEBUG(printk("pktgen: entering pktgen_stop.\n")); + func_enter(); - if_lock(t); + if_lock(t); - for(next=t->if_list; next; next=next->next) - pktgen_stop_device(next); + list_for_each_entry(pkt_dev, &t->if_list, list) { + pktgen_stop_device(pkt_dev); + } - if_unlock(t); + if_unlock(t); } -static void pktgen_rem_all_ifs(struct pktgen_thread *t) +/* + * one of our devices needs to be removed - find it + * and remove it + */ +static void pktgen_rem_one_if(struct pktgen_thread *t) { - struct pktgen_dev *cur, *next = NULL; - - /* Remove all devices, free mem */ - - if_lock(t); + struct list_head *q, *n; + struct pktgen_dev *cur; + + func_enter(); + + if_lock(t); + + list_for_each_safe(q, n, &t->if_list) { + cur = list_entry(q, struct pktgen_dev, list); + + if (!cur->removal_mark) + continue; + + kfree_skb(cur->skb); + cur->skb = NULL; - for(cur=t->if_list; cur; cur=next) { - next = cur->next; pktgen_remove_device(t, cur); + + break; } - if_unlock(t); + if_unlock(t); } -static void pktgen_rem_thread(struct pktgen_thread *t) +static void pktgen_rem_all_ifs(struct pktgen_thread *t) { - /* Remove from the thread list */ + struct list_head *q, *n; + struct pktgen_dev *cur; - struct pktgen_thread *tmp = pktgen_threads; + func_enter(); - remove_proc_entry(t->name, pg_proc_dir); + /* Remove all devices, free mem */ - thread_lock(); + if_lock(t); - if (tmp == t) - pktgen_threads = tmp->next; - else { - while (tmp) { - if (tmp->next == t) { - tmp->next = t->next; - t->next = NULL; - break; - } - tmp = tmp->next; - } + list_for_each_safe(q, n, &t->if_list) { + cur = list_entry(q, struct pktgen_dev, list); + + kfree_skb(cur->skb); + cur->skb = NULL; + + pktgen_remove_device(t, cur); } - thread_unlock(); + + if_unlock(t); } -static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) +static void pktgen_rem_thread(struct pktgen_thread *t) { - struct net_device *odev = NULL; - __u64 idle_start = 0; - int ret; + /* Remove from the thread list */ + remove_proc_entry(t->tsk->comm, t->net->proc_dir); +} - odev = pkt_dev->odev; - - if (pkt_dev->delay_us || pkt_dev->delay_ns) { - u64 now; +static void pktgen_resched(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_get(); + schedule(); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); +} - now = getCurUs(); - if (now < pkt_dev->next_tx_us) - spin(pkt_dev, pkt_dev->next_tx_us); +static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_get(); - /* This is max DELAY, this has special meaning of - * "never transmit" - */ - if (pkt_dev->delay_us == 0x7FFFFFFF) { - pkt_dev->next_tx_us = getCurUs() + pkt_dev->delay_us; - pkt_dev->next_tx_ns = pkt_dev->delay_ns; - goto out; - } + while (atomic_read(&(pkt_dev->skb->users)) != 1) { + if (signal_pending(current)) + break; + + if (need_resched()) + pktgen_resched(pkt_dev); + else + cpu_relax(); } - - if (netif_queue_stopped(odev) || need_resched()) { - idle_start = getCurUs(); - - if (!netif_running(odev)) { - pktgen_stop_device(pkt_dev); - goto out; - } - if (need_resched()) - schedule(); - - pkt_dev->idle_acc += getCurUs() - idle_start; - - if (netif_queue_stopped(odev)) { - pkt_dev->next_tx_us = getCurUs(); /* TODO */ - pkt_dev->next_tx_ns = 0; - goto out; /* Try the next interface */ - } + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); +} + +static void pktgen_xmit(struct pktgen_dev *pkt_dev) +{ + struct net_device *odev = pkt_dev->odev; + netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *) + = odev->netdev_ops->ndo_start_xmit; + struct netdev_queue *txq; + u16 queue_map; + int ret; + + /* If device is offline, then don't send */ + if (unlikely(!netif_running(odev) || !netif_carrier_ok(odev))) { + pktgen_stop_device(pkt_dev); + return; } - - if (pkt_dev->last_ok || !pkt_dev->skb) { - if ((++pkt_dev->clone_count >= pkt_dev->clone_skb ) || (!pkt_dev->skb)) { - /* build a new pkt */ - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); - - pkt_dev->skb = fill_packet(odev, pkt_dev); - if (pkt_dev->skb == NULL) { - printk("pktgen: ERROR: couldn't allocate skb in fill_packet.\n"); - schedule(); - pkt_dev->clone_count--; /* back out increment, OOM */ - goto out; - } - pkt_dev->allocated_skbs++; - pkt_dev->clone_count = 0; /* reset counter */ - } + + /* This is max DELAY, this has special meaning of + * "never transmit" + */ + if (unlikely(pkt_dev->delay == ULLONG_MAX)) { + pkt_dev->next_tx = ktime_add_ns(ktime_get(), ULONG_MAX); + return; } - - spin_lock_bh(&odev->xmit_lock); - if (!netif_queue_stopped(odev)) { - - atomic_inc(&(pkt_dev->skb->users)); -retry_now: - ret = odev->hard_start_xmit(pkt_dev->skb, odev); - if (likely(ret == NETDEV_TX_OK)) { - pkt_dev->last_ok = 1; - pkt_dev->sofar++; - pkt_dev->seq_num++; - pkt_dev->tx_bytes += pkt_dev->cur_pkt_size; - - } else if (ret == NETDEV_TX_LOCKED - && (odev->features & NETIF_F_LLTX)) { - cpu_relax(); - goto retry_now; - } else { /* Retry it next time */ - - atomic_dec(&(pkt_dev->skb->users)); - - if (debug && net_ratelimit()) - printk(KERN_INFO "pktgen: Hard xmit error\n"); - - pkt_dev->errors++; - pkt_dev->last_ok = 0; + + /* If no skb or clone count exhausted then get new one */ + if (!pkt_dev->skb || (pkt_dev->last_ok && + ++pkt_dev->clone_count >= pkt_dev->clone_skb)) { + /* build a new pkt */ + kfree_skb(pkt_dev->skb); + + pkt_dev->skb = fill_packet(odev, pkt_dev); + if (pkt_dev->skb == NULL) { + pr_err("ERROR: couldn't allocate skb in fill_packet\n"); + schedule(); + pkt_dev->clone_count--; /* back out increment, OOM */ + return; } + pkt_dev->last_pkt_size = pkt_dev->skb->len; + pkt_dev->allocated_skbs++; + pkt_dev->clone_count = 0; /* reset counter */ + } - pkt_dev->next_tx_us = getCurUs(); - pkt_dev->next_tx_ns = 0; + if (pkt_dev->delay && pkt_dev->last_ok) + spin(pkt_dev, pkt_dev->next_tx); - pkt_dev->next_tx_us += pkt_dev->delay_us; - pkt_dev->next_tx_ns += pkt_dev->delay_ns; + queue_map = skb_get_queue_mapping(pkt_dev->skb); + txq = netdev_get_tx_queue(odev, queue_map); - if (pkt_dev->next_tx_ns > 1000) { - pkt_dev->next_tx_us++; - pkt_dev->next_tx_ns -= 1000; - } - } + local_bh_disable(); + + HARD_TX_LOCK(odev, txq, smp_processor_id()); - else { /* Retry it next time */ - pkt_dev->last_ok = 0; - pkt_dev->next_tx_us = getCurUs(); /* TODO */ - pkt_dev->next_tx_ns = 0; - } + if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) { + ret = NETDEV_TX_BUSY; + pkt_dev->last_ok = 0; + goto unlock; + } + atomic_inc(&(pkt_dev->skb->users)); + ret = (*xmit)(pkt_dev->skb, odev); + + switch (ret) { + case NETDEV_TX_OK: + txq_trans_update(txq); + pkt_dev->last_ok = 1; + pkt_dev->sofar++; + pkt_dev->seq_num++; + pkt_dev->tx_bytes += pkt_dev->last_pkt_size; + break; + case NET_XMIT_DROP: + case NET_XMIT_CN: + case NET_XMIT_POLICED: + /* skb has been consumed */ + pkt_dev->errors++; + break; + default: /* Drivers are not supposed to return other values! */ + net_info_ratelimited("%s xmit error: %d\n", + pkt_dev->odevname, ret); + pkt_dev->errors++; + /* fallthru */ + case NETDEV_TX_LOCKED: + case NETDEV_TX_BUSY: + /* Retry it next time */ + atomic_dec(&(pkt_dev->skb->users)); + pkt_dev->last_ok = 0; + } +unlock: + HARD_TX_UNLOCK(odev, txq); + + local_bh_enable(); - spin_unlock_bh(&odev->xmit_lock); - /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { - if (atomic_read(&(pkt_dev->skb->users)) != 1) { - idle_start = getCurUs(); - while (atomic_read(&(pkt_dev->skb->users)) != 1) { - if (signal_pending(current)) { - break; - } - schedule(); - } - pkt_dev->idle_acc += getCurUs() - idle_start; - } - + pktgen_wait_for_skb(pkt_dev); + /* Done with this */ pktgen_stop_device(pkt_dev); - } - out:; - } + } +} -/* +/* * Main loop of the thread goes here */ -static void pktgen_thread_worker(struct pktgen_thread *t) +static int pktgen_thread_worker(void *arg) { DEFINE_WAIT(wait); - struct pktgen_dev *pkt_dev = NULL; + struct pktgen_thread *t = arg; + struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - sigset_t tmpsig; - u32 max_before_softirq; - u32 tx_since_softirq = 0; - - daemonize("pktgen/%d", cpu); - - /* Block all signals except SIGKILL, SIGSTOP and SIGTERM */ - - spin_lock_irq(¤t->sighand->siglock); - tmpsig = current->blocked; - siginitsetinv(¤t->blocked, - sigmask(SIGKILL) | - sigmask(SIGSTOP)| - sigmask(SIGTERM)); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - /* Migrate to the right CPU */ - set_cpus_allowed(current, cpumask_of_cpu(cpu)); - if (smp_processor_id() != cpu) - BUG(); + BUG_ON(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); + complete(&t->start_done); - t->control &= ~(T_TERMINATE); - t->control &= ~(T_RUN); - t->control &= ~(T_STOP); - t->control &= ~(T_REMDEV); - - t->pid = current->pid; + pr_debug("starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current)); - PG_DEBUG(printk("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid)); + set_current_state(TASK_INTERRUPTIBLE); - max_before_softirq = t->max_before_softirq; - - __set_current_state(TASK_INTERRUPTIBLE); - mb(); + set_freezable(); - while (1) { - - __set_current_state(TASK_RUNNING); + while (!kthread_should_stop()) { + pkt_dev = next_to_run(t); - /* - * Get next dev to xmit -- if any. - */ + if (unlikely(!pkt_dev && t->control == 0)) { + if (t->net->pktgen_exiting) + break; + wait_event_interruptible_timeout(t->queue, + t->control != 0, + HZ/10); + try_to_freeze(); + continue; + } - pkt_dev = next_to_run(t); - - if (pkt_dev) { + __set_current_state(TASK_RUNNING); + if (likely(pkt_dev)) { pktgen_xmit(pkt_dev); - /* - * We like to stay RUNNING but must also give - * others fair share. - */ - - tx_since_softirq += pkt_dev->last_ok; - - if (tx_since_softirq > max_before_softirq) { - if (local_softirq_pending()) - do_softirq(); - tx_since_softirq = 0; - } - } else { - prepare_to_wait(&(t->queue), &wait, TASK_INTERRUPTIBLE); - schedule_timeout(HZ/10); - finish_wait(&(t->queue), &wait); + if (need_resched()) + pktgen_resched(pkt_dev); + else + cpu_relax(); } - /* - * Back from sleep, either due to the timeout or signal. - * We check if we have any "posted" work for us. - */ - - if (t->control & T_TERMINATE || signal_pending(current)) - /* we received a request to terminate ourself */ - break; - - - if(t->control & T_STOP) { + if (t->control & T_STOP) { pktgen_stop(t); t->control &= ~(T_STOP); } - if(t->control & T_RUN) { + if (t->control & T_RUN) { pktgen_run(t); t->control &= ~(T_RUN); } - if(t->control & T_REMDEV) { + if (t->control & T_REMDEVALL) { pktgen_rem_all_ifs(t); + t->control &= ~(T_REMDEVALL); + } + + if (t->control & T_REMDEV) { + pktgen_rem_one_if(t); t->control &= ~(T_REMDEV); } - if (need_resched()) - schedule(); - } + try_to_freeze(); + + set_current_state(TASK_INTERRUPTIBLE); + } + + pr_debug("%s stopping all device\n", t->tsk->comm); + pktgen_stop(t); - PG_DEBUG(printk("pktgen: %s stopping all device\n", t->name)); - pktgen_stop(t); + pr_debug("%s removing all device\n", t->tsk->comm); + pktgen_rem_all_ifs(t); - PG_DEBUG(printk("pktgen: %s removing all device\n", t->name)); - pktgen_rem_all_ifs(t); + pr_debug("%s removing thread\n", t->tsk->comm); + pktgen_rem_thread(t); - PG_DEBUG(printk("pktgen: %s removing thread.\n", t->name)); - pktgen_rem_thread(t); + /* Wait for kthread_stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + + return 0; } -static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char* ifname) +static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, + const char *ifname, bool exact) { - struct pktgen_dev *pkt_dev = NULL; - if_lock(t); + struct pktgen_dev *p, *pkt_dev = NULL; + size_t len = strlen(ifname); - for(pkt_dev=t->if_list; pkt_dev; pkt_dev = pkt_dev->next ) { - if (strncmp(pkt_dev->ifname, ifname, IFNAMSIZ) == 0) { - break; - } - } + if_lock(t); + list_for_each_entry(p, &t->if_list, list) + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } + pkt_dev = p; + break; + } - if_unlock(t); - PG_DEBUG(printk("pktgen: find_dev(%s) returning %p\n", ifname,pkt_dev)); - return pkt_dev; + if_unlock(t); + pr_debug("find_dev(%s) returning %p\n", ifname, pkt_dev); + return pkt_dev; } -/* - * Adds a dev at front of if_list. +/* + * Adds a dev at front of if_list. */ -static int add_dev_to_thread(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) +static int add_dev_to_thread(struct pktgen_thread *t, + struct pktgen_dev *pkt_dev) { int rv = 0; - - if_lock(t); - - if (pkt_dev->pg_thread) { - printk("pktgen: ERROR: already assigned to a thread.\n"); - rv = -EBUSY; - goto out; - } - pkt_dev->next =t->if_list; t->if_list=pkt_dev; - pkt_dev->pg_thread = t; + + if_lock(t); + + if (pkt_dev->pg_thread) { + pr_err("ERROR: already assigned to a thread\n"); + rv = -EBUSY; + goto out; + } + + list_add(&pkt_dev->list, &t->if_list); + pkt_dev->pg_thread = t; pkt_dev->running = 0; - out: - if_unlock(t); - return rv; +out: + if_unlock(t); + return rv; } /* Called under thread lock */ -static int pktgen_add_device(struct pktgen_thread *t, const char* ifname) +static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { - struct pktgen_dev *pkt_dev; - struct proc_dir_entry *pe; - + struct pktgen_dev *pkt_dev; + int err; + int node = cpu_to_node(t->cpu); + /* We don't allow a device to be on several threads */ - pkt_dev = __pktgen_NN_threads(ifname, FIND); + pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND); if (pkt_dev) { - printk("pktgen: ERROR: interface already used.\n"); - return -EBUSY; - } + pr_err("ERROR: interface already used\n"); + return -EBUSY; + } - pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node); if (!pkt_dev) return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS*sizeof(struct flow_state)); + strcpy(pkt_dev->odevname, ifname); + pkt_dev->flows = vzalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; } - memset(pkt_dev->flows, 0, MAX_CFLOWS*sizeof(struct flow_state)); - pkt_dev->min_pkt_size = ETH_ZLEN; - pkt_dev->max_pkt_size = ETH_ZLEN; + pkt_dev->removal_mark = 0; pkt_dev->nfrags = 0; - pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->delay_us = pg_delay_d / 1000; - pkt_dev->delay_ns = pg_delay_d % 1000; + pkt_dev->delay = pg_delay_d; pkt_dev->count = pg_count_d; pkt_dev->sofar = 0; - pkt_dev->udp_src_min = 9; /* sink port */ + pkt_dev->udp_src_min = 9; /* sink port */ pkt_dev->udp_src_max = 9; pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; - - strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); - - if (! pktgen_setup_dev(pkt_dev)) { - printk("pktgen: ERROR: pktgen_setup_dev failed.\n"); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -ENODEV; - } - - pe = create_proc_entry(ifname, 0600, pg_proc_dir); - if (!pe) { - printk("pktgen: cannot create %s/%s procfs entry.\n", + pkt_dev->vlan_p = 0; + pkt_dev->vlan_cfi = 0; + pkt_dev->vlan_id = 0xffff; + pkt_dev->svlan_p = 0; + pkt_dev->svlan_cfi = 0; + pkt_dev->svlan_id = 0xffff; + pkt_dev->node = -1; + + err = pktgen_setup_dev(t->net, pkt_dev, ifname); + if (err) + goto out1; + if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) + pkt_dev->clone_skb = pg_clone_skb_d; + + pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, + &pktgen_if_fops, pkt_dev); + if (!pkt_dev->entry) { + pr_err("cannot create %s/%s procfs entry\n", PG_PROC_DIR, ifname); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -EINVAL; + err = -EINVAL; + goto out2; } - pe->proc_fops = &pktgen_if_fops; - pe->data = pkt_dev; +#ifdef CONFIG_XFRM + pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; + pkt_dev->ipsproto = IPPROTO_ESP; + + /* xfrm tunnel mode needs additional dst to extract outter + * ip header protocol/ttl/id field, here creat a phony one. + * instead of looking for a valid rt, which definitely hurting + * performance under such circumstance. + */ + pkt_dev->dstops.family = AF_INET; + pkt_dev->dst.dev = pkt_dev->odev; + dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false); + pkt_dev->dst.child = &pkt_dev->dst; + pkt_dev->dst.ops = &pkt_dev->dstops; +#endif return add_dev_to_thread(t, pkt_dev); +out2: + dev_put(pkt_dev->odev); +out1: +#ifdef CONFIG_XFRM + free_SAs(pkt_dev); +#endif + vfree(pkt_dev->flows); + kfree(pkt_dev); + return err; } -static struct pktgen_thread * __init pktgen_find_thread(const char* name) +static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) { - struct pktgen_thread *t = NULL; + struct pktgen_thread *t; + struct proc_dir_entry *pe; + struct task_struct *p; - thread_lock(); + t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, + cpu_to_node(cpu)); + if (!t) { + pr_err("ERROR: out of memory, can't create new thread\n"); + return -ENOMEM; + } - t = pktgen_threads; - while (t) { - if (strcmp(t->name, name) == 0) - break; + spin_lock_init(&t->if_lock); + t->cpu = cpu; - t = t->next; - } - thread_unlock(); - return t; -} + INIT_LIST_HEAD(&t->if_list); -static int __init pktgen_create_thread(const char* name, int cpu) -{ - struct pktgen_thread *t = NULL; - struct proc_dir_entry *pe; + list_add_tail(&t->th_list, &pn->pktgen_threads); + init_completion(&t->start_done); - if (strlen(name) > 31) { - printk("pktgen: ERROR: Thread name cannot be more than 31 characters.\n"); - return -EINVAL; - } - - if (pktgen_find_thread(name)) { - printk("pktgen: ERROR: thread: %s already exists\n", name); - return -EINVAL; - } - - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); - if (!t) { - printk("pktgen: ERROR: out of memory, can't create new thread.\n"); - return -ENOMEM; - } - - strcpy(t->name, name); - spin_lock_init(&t->if_lock); - t->cpu = cpu; - - pe = create_proc_entry(t->name, 0600, pg_proc_dir); - if (!pe) { - printk("pktgen: cannot create %s/%s procfs entry.\n", - PG_PROC_DIR, t->name); - kfree(t); - return -EINVAL; - } - - pe->proc_fops = &pktgen_thread_fops; - pe->data = t; + p = kthread_create_on_node(pktgen_thread_worker, + t, + cpu_to_node(cpu), + "kpktgend_%d", cpu); + if (IS_ERR(p)) { + pr_err("kernel_thread() failed for cpu %d\n", t->cpu); + list_del(&t->th_list); + kfree(t); + return PTR_ERR(p); + } + kthread_bind(p, cpu); + t->tsk = p; - t->next = pktgen_threads; - pktgen_threads = t; + pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, + &pktgen_thread_fops, t); + if (!pe) { + pr_err("cannot create %s/%s procfs entry\n", + PG_PROC_DIR, t->tsk->comm); + kthread_stop(p); + list_del(&t->th_list); + kfree(t); + return -EINVAL; + } - if (kernel_thread((void *) pktgen_thread_worker, (void *) t, - CLONE_FS | CLONE_FILES | CLONE_SIGHAND) < 0) - printk("pktgen: kernel_thread() failed for cpu %d\n", t->cpu); + t->net = pn; + wake_up_process(p); + wait_for_completion(&t->start_done); return 0; } -/* - * Removes a device from the thread if_list. +/* + * Removes a device from the thread if_list. */ -static void _rem_dev_from_if_list(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) +static void _rem_dev_from_if_list(struct pktgen_thread *t, + struct pktgen_dev *pkt_dev) { - struct pktgen_dev *i, *prev = NULL; - - i = t->if_list; + struct list_head *q, *n; + struct pktgen_dev *p; - while(i) { - if(i == pkt_dev) { - if(prev) prev->next = i->next; - else t->if_list = NULL; - break; - } - prev = i; - i=i->next; + list_for_each_safe(q, n, &t->if_list) { + p = list_entry(q, struct pktgen_dev, list); + if (p == pkt_dev) + list_del(&p->list); } } -static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) +static int pktgen_remove_device(struct pktgen_thread *t, + struct pktgen_dev *pkt_dev) { + pr_debug("remove_device pkt_dev=%p\n", pkt_dev); - PG_DEBUG(printk("pktgen: remove_device pkt_dev=%p\n", pkt_dev)); + if (pkt_dev->running) { + pr_warning("WARNING: trying to remove a running interface, stopping it now\n"); + pktgen_stop_device(pkt_dev); + } - if (pkt_dev->running) { - printk("pktgen:WARNING: trying to remove a running interface, stopping it now.\n"); - pktgen_stop_device(pkt_dev); - } - - /* Dis-associate from the interface */ + /* Dis-associate from the interface */ if (pkt_dev->odev) { dev_put(pkt_dev->odev); - pkt_dev->odev = NULL; - } - + pkt_dev->odev = NULL; + } + /* And update the thread if_list */ _rem_dev_from_if_list(t, pkt_dev); - /* Clean up proc file system */ - - remove_proc_entry(pkt_dev->ifname, pg_proc_dir); + if (pkt_dev->entry) + proc_remove(pkt_dev->entry); - if (pkt_dev->flows) - vfree(pkt_dev->flows); +#ifdef CONFIG_XFRM + free_SAs(pkt_dev); +#endif + vfree(pkt_dev->flows); + if (pkt_dev->page) + put_page(pkt_dev->page); kfree(pkt_dev); - return 0; + return 0; } -static int __init pg_init(void) +static int __net_init pg_net_init(struct net *net) { - int cpu; + struct pktgen_net *pn = net_generic(net, pg_net_id); struct proc_dir_entry *pe; - - printk(version); - - pg_proc_dir = proc_mkdir(PG_PROC_DIR, proc_net); - if (!pg_proc_dir) + int cpu, ret = 0; + + pn->net = net; + INIT_LIST_HEAD(&pn->pktgen_threads); + pn->pktgen_exiting = false; + pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net); + if (!pn->proc_dir) { + pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; - pg_proc_dir->owner = THIS_MODULE; + } + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); + if (pe == NULL) { + pr_err("cannot create %s procfs entry\n", PGCTRL); + ret = -EINVAL; + goto remove; + } - pe = create_proc_entry(PGCTRL, 0600, pg_proc_dir); - if (pe == NULL) { - printk("pktgen: ERROR: cannot create %s procfs entry.\n", PGCTRL); - proc_net_remove(PG_PROC_DIR); - return -EINVAL; - } + for_each_online_cpu(cpu) { + int err; - pe->proc_fops = &pktgen_fops; - pe->data = NULL; + err = pktgen_create_thread(cpu, pn); + if (err) + pr_warn("Cannot create thread for cpu %d (%d)\n", + cpu, err); + } - /* Register us to receive netdevice events */ - register_netdevice_notifier(&pktgen_notifier_block); - - for_each_online_cpu(cpu) { - char buf[30]; + if (list_empty(&pn->pktgen_threads)) { + pr_err("Initialization failed for all threads\n"); + ret = -ENODEV; + goto remove_entry; + } - sprintf(buf, "kpktgend_%i", cpu); - pktgen_create_thread(buf, cpu); - } - return 0; + return 0; + +remove_entry: + remove_proc_entry(PGCTRL, pn->proc_dir); +remove: + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); + return ret; } -static void __exit pg_cleanup(void) +static void __net_exit pg_net_exit(struct net *net) { - wait_queue_head_t queue; - init_waitqueue_head(&queue); + struct pktgen_net *pn = net_generic(net, pg_net_id); + struct pktgen_thread *t; + struct list_head *q, *n; + LIST_HEAD(list); - /* Stop all interfaces & threads */ + /* Stop all interfaces & threads */ + pn->pktgen_exiting = true; - while (pktgen_threads) { - struct pktgen_thread *t = pktgen_threads; - pktgen_threads->control |= (T_TERMINATE); + mutex_lock(&pktgen_thread_lock); + list_splice_init(&pn->pktgen_threads, &list); + mutex_unlock(&pktgen_thread_lock); - wait_event_interruptible_timeout(queue, (t != pktgen_threads), HZ); - } + list_for_each_safe(q, n, &list) { + t = list_entry(q, struct pktgen_thread, th_list); + list_del(&t->th_list); + kthread_stop(t->tsk); + kfree(t); + } - /* Un-register us from receiving netdevice events */ - unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pn->proc_dir); + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); +} + +static struct pernet_operations pg_net_ops = { + .init = pg_net_init, + .exit = pg_net_exit, + .id = &pg_net_id, + .size = sizeof(struct pktgen_net), +}; - /* Clean up proc file system */ - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(PG_PROC_DIR); +static int __init pg_init(void) +{ + int ret = 0; + + pr_info("%s", version); + ret = register_pernet_subsys(&pg_net_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&pktgen_notifier_block); + if (ret) + unregister_pernet_subsys(&pg_net_ops); + + return ret; } +static void __exit pg_cleanup(void) +{ + unregister_netdevice_notifier(&pktgen_notifier_block); + unregister_pernet_subsys(&pg_net_ops); +} module_init(pg_init); module_exit(pg_cleanup); -MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se"); +MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se>"); MODULE_DESCRIPTION("Packet Generator tool"); MODULE_LICENSE("GPL"); +MODULE_VERSION(VERSION); module_param(pg_count_d, int, 0); +MODULE_PARM_DESC(pg_count_d, "Default number of packets to inject"); module_param(pg_delay_d, int, 0); +MODULE_PARM_DESC(pg_delay_d, "Default delay between packets (nanoseconds)"); module_param(pg_clone_skb_d, int, 0); +MODULE_PARM_DESC(pg_clone_skb_d, "Default number of copies of the same packet"); module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Enable debugging of pktgen module"); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c new file mode 100644 index 00000000000..d3027a73fd4 --- /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[] __initdata = { + { 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_kern 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 b8203de5ff0..467f326126e 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -15,6 +15,8 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/tcp.h> +#include <linux/vmalloc.h> #include <net/request_sock.h> @@ -25,34 +27,40 @@ * but then some measure against one socket starving all other sockets * would be needed. * - * It was 128 by default. Experiments with real servers show, that + * The minimum value of it is 128. Experiments with real servers show that * it is absolutely not enough even at 100conn/sec. 256 cures most - * of problems. This value is adjusted to 128 for very small machines - * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). - * Further increasing requires to change hash table size. + * of problems. + * This value is adjusted to 128 for low memory machines, + * and it will increase in proportion to the memory of machine. + * Note : Dont forget somaxconn that may limit backlog too. */ int sysctl_max_syn_backlog = 256; +EXPORT_SYMBOL(sysctl_max_syn_backlog); int reqsk_queue_alloc(struct request_sock_queue *queue, - const int nr_table_entries) + unsigned int nr_table_entries) { - const int lopt_size = sizeof(struct listen_sock) + - nr_table_entries * sizeof(struct request_sock *); - struct listen_sock *lopt = kmalloc(lopt_size, GFP_KERNEL); - + size_t lopt_size = sizeof(struct listen_sock); + struct listen_sock *lopt; + + nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); + nr_table_entries = max_t(u32, nr_table_entries, 8); + nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); + lopt_size += nr_table_entries * sizeof(struct request_sock *); + if (lopt_size > PAGE_SIZE) + lopt = vzalloc(lopt_size); + else + lopt = kzalloc(lopt_size, GFP_KERNEL); if (lopt == NULL) return -ENOMEM; - memset(lopt, 0, lopt_size); - - for (lopt->max_qlen_log = 6; - (1 << lopt->max_qlen_log) < sysctl_max_syn_backlog; + for (lopt->max_qlen_log = 3; + (1 << lopt->max_qlen_log) < nr_table_entries; lopt->max_qlen_log++); get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); rwlock_init(&queue->syn_wait_lock); - queue->rskq_accept_head = queue->rskq_accept_head = NULL; - queue->rskq_defer_accept = 0; + queue->rskq_accept_head = NULL; lopt->nr_table_entries = nr_table_entries; write_lock_bh(&queue->syn_wait_lock); @@ -62,15 +70,48 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, return 0; } -EXPORT_SYMBOL(reqsk_queue_alloc); +void __reqsk_queue_destroy(struct request_sock_queue *queue) +{ + struct listen_sock *lopt; + size_t lopt_size; + + /* + * this is an error recovery path only + * no locking needed and the lopt is not NULL + */ + + lopt = queue->listen_opt; + lopt_size = sizeof(struct listen_sock) + + lopt->nr_table_entries * sizeof(struct request_sock *); + + if (lopt_size > PAGE_SIZE) + vfree(lopt); + else + kfree(lopt); +} + +static inline struct listen_sock *reqsk_queue_yank_listen_sk( + struct request_sock_queue *queue) +{ + struct listen_sock *lopt; + + write_lock_bh(&queue->syn_wait_lock); + lopt = queue->listen_opt; + queue->listen_opt = NULL; + write_unlock_bh(&queue->syn_wait_lock); + + return lopt; +} void reqsk_queue_destroy(struct request_sock_queue *queue) { /* make all the listen_opt local to us */ struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); + size_t lopt_size = sizeof(struct listen_sock) + + lopt->nr_table_entries * sizeof(struct request_sock *); if (lopt->qlen != 0) { - int i; + unsigned int i; for (i = 0; i < lopt->nr_table_entries; i++) { struct request_sock *req; @@ -83,8 +124,101 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) } } - BUG_TRAP(lopt->qlen == 0); - kfree(lopt); + WARN_ON(lopt->qlen != 0); + if (lopt_size > PAGE_SIZE) + vfree(lopt); + else + kfree(lopt); } -EXPORT_SYMBOL(reqsk_queue_destroy); +/* + * This function is called to set a Fast Open socket's "fastopen_rsk" field + * to NULL when a TFO socket no longer needs to access the request_sock. + * This happens only after 3WHS has been either completed or aborted (e.g., + * RST is received). + * + * Before TFO, a child socket is created only after 3WHS is completed, + * hence it never needs to access the request_sock. things get a lot more + * complex with TFO. A child socket, accepted or not, has to access its + * request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts, + * until 3WHS is either completed or aborted. Afterwards the req will stay + * until either the child socket is accepted, or in the rare case when the + * listener is closed before the child is accepted. + * + * In short, a request socket is only freed after BOTH 3WHS has completed + * (or aborted) and the child socket has been accepted (or listener closed). + * When a child socket is accepted, its corresponding req->sk is set to + * NULL since it's no longer needed. More importantly, "req->sk == NULL" + * will be used by the code below to determine if a child socket has been + * accepted or not, and the check is protected by the fastopenq->lock + * described below. + * + * Note that fastopen_rsk is only accessed from the child socket's context + * with its socket lock held. But a request_sock (req) can be accessed by + * both its child socket through fastopen_rsk, and a listener socket through + * icsk_accept_queue.rskq_accept_head. To protect the access a simple spin + * lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created. + * only in the rare case when both the listener and the child locks are held, + * e.g., in inet_csk_listen_stop() do we not need to acquire the lock. + * The lock also protects other fields such as fastopenq->qlen, which is + * decremented by this function when fastopen_rsk is no longer needed. + * + * Note that another solution was to simply use the existing socket lock + * from the listener. But first socket lock is difficult to use. It is not + * a simple spin lock - one must consider sock_owned_by_user() and arrange + * to use sk_add_backlog() stuff. But what really makes it infeasible is the + * locking hierarchy violation. E.g., inet_csk_listen_stop() may try to + * acquire a child's lock while holding listener's socket lock. A corner + * case might also exist in tcp_v4_hnd_req() that will trigger this locking + * order. + * + * When a TFO req is created, it needs to sock_hold its listener to prevent + * the latter data structure from going away. + * + * This function also sets "treq->listener" to NULL and unreference listener + * socket. treq->listener is used by the listener so it is protected by the + * fastopenq->lock in this function. + */ +void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, + bool reset) +{ + struct sock *lsk = tcp_rsk(req)->listener; + struct fastopen_queue *fastopenq = + inet_csk(lsk)->icsk_accept_queue.fastopenq; + + tcp_sk(sk)->fastopen_rsk = NULL; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen--; + tcp_rsk(req)->listener = NULL; + if (req->sk) /* the child socket hasn't been accepted yet */ + goto out; + + if (!reset || lsk->sk_state != TCP_LISTEN) { + /* If the listener has been closed don't bother with the + * special RST handling below. + */ + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); + reqsk_free(req); + return; + } + /* Wait for 60secs before removing a req that has triggered RST. + * This is a simple defense against TFO spoofing attack - by + * counting the req against fastopen.max_qlen, and disabling + * TFO when the qlen exceeds max_qlen. + * + * For more details see CoNext'11 "TCP Fast Open" paper. + */ + req->expires = jiffies + 60*HZ; + if (fastopenq->rskq_rst_head == NULL) + fastopenq->rskq_rst_head = req; + else + fastopenq->rskq_rst_tail->dl_next = req; + + req->dl_next = NULL; + fastopenq->rskq_rst_tail = req; + fastopenq->qlen++; +out: + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); +} diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8700379685e..1063996f831 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -16,13 +16,11 @@ * Vitaly E. Lavrov RTA_OK arithmetics was wrong. */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> -#include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> @@ -35,10 +33,13 @@ #include <linux/skbuff.h> #include <linux/init.h> #include <linux/security.h> +#include <linux/mutex.h> +#include <linux/if_addr.h> +#include <linux/if_bridge.h> +#include <linux/pci.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/string.h> #include <linux/inet.h> #include <linux/netdevice.h> @@ -49,104 +50,567 @@ #include <net/udp.h> #include <net/sock.h> #include <net/pkt_sched.h> -#include <net/netlink.h> +#include <net/fib_rules.h> +#include <net/rtnetlink.h> +#include <net/net_namespace.h> + +struct rtnl_link { + rtnl_doit_func doit; + rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; +}; -DECLARE_MUTEX(rtnl_sem); +static DEFINE_MUTEX(rtnl_mutex); void rtnl_lock(void) { - rtnl_shlock(); + mutex_lock(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_lock); -int rtnl_lock_interruptible(void) +void __rtnl_unlock(void) { - return down_interruptible(&rtnl_sem); + mutex_unlock(&rtnl_mutex); } - + void rtnl_unlock(void) { - rtnl_shunlock(); - + /* This fellow will unlock it for us. */ netdev_run_todo(); } +EXPORT_SYMBOL(rtnl_unlock); + +int rtnl_trylock(void) +{ + return mutex_trylock(&rtnl_mutex); +} +EXPORT_SYMBOL(rtnl_trylock); + +int rtnl_is_locked(void) +{ + return mutex_is_locked(&rtnl_mutex); +} +EXPORT_SYMBOL(rtnl_is_locked); + +#ifdef CONFIG_PROVE_LOCKING +int lockdep_rtnl_is_held(void) +{ + return lockdep_is_held(&rtnl_mutex); +} +EXPORT_SYMBOL(lockdep_rtnl_is_held); +#endif /* #ifdef CONFIG_PROVE_LOCKING */ + +static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; + +static inline int rtm_msgindex(int msgtype) +{ + int msgindex = msgtype - RTM_BASE; + + /* + * msgindex < 0 implies someone tried to register a netlink + * control code. msgindex >= RTM_NR_MSGTYPES may indicate that + * the message type has not been added to linux/rtnetlink.h + */ + BUG_ON(msgindex < 0 || msgindex >= RTM_NR_MSGTYPES); + + return msgindex; +} + +static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + + if (tab == NULL || tab[msgindex].doit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab[msgindex].doit; +} -int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len) +static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) { - memset(tb, 0, sizeof(struct rtattr*)*maxattr); + struct rtnl_link *tab; - while (RTA_OK(rta, len)) { - unsigned flavor = rta->rta_type; - if (flavor && flavor <= maxattr) - tb[flavor-1] = rta; - rta = RTA_NEXT(rta, len); + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + + if (tab == NULL || tab[msgindex].dumpit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab[msgindex].dumpit; +} + +static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + + if (tab == NULL || tab[msgindex].calcit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab[msgindex].calcit; +} + +/** + * __rtnl_register - Register a rtnetlink message type + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * @doit: Function pointer called for each request message + * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @calcit: Function pointer to calc size of dump message + * + * Registers the specified function pointers (at least one of them has + * to be non-NULL) to be called whenever a request message for the + * specified protocol family and message type is received. + * + * The special protocol family PF_UNSPEC may be used to define fallback + * function pointers for the case when no entry for the specific protocol + * family exists. + * + * Returns 0 on success or a negative error code. + */ +int __rtnl_register(int protocol, int msgtype, + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) +{ + struct rtnl_link *tab; + int msgindex; + + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); + msgindex = rtm_msgindex(msgtype); + + tab = rtnl_msg_handlers[protocol]; + if (tab == NULL) { + tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL); + if (tab == NULL) + return -ENOBUFS; + + rtnl_msg_handlers[protocol] = tab; } + + if (doit) + tab[msgindex].doit = doit; + + if (dumpit) + tab[msgindex].dumpit = dumpit; + + if (calcit) + tab[msgindex].calcit = calcit; + return 0; } +EXPORT_SYMBOL_GPL(__rtnl_register); -struct sock *rtnl; +/** + * rtnl_register - Register a rtnetlink message type + * + * Identical to __rtnl_register() but panics on failure. This is useful + * as failure of this function is very unlikely, it can only happen due + * to lack of memory when allocating the chain to store all message + * handlers for a protocol. Meant for use in init functions where lack + * of memory implies no sense in continuing. + */ +void rtnl_register(int protocol, int msgtype, + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) +{ + if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0) + panic("Unable to register rtnetlink message handler, " + "protocol = %d, message type = %d\n", + protocol, msgtype); +} +EXPORT_SYMBOL_GPL(rtnl_register); + +/** + * rtnl_unregister - Unregister a rtnetlink message type + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * + * Returns 0 on success or a negative error code. + */ +int rtnl_unregister(int protocol, int msgtype) +{ + int msgindex; + + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); + msgindex = rtm_msgindex(msgtype); + + if (rtnl_msg_handlers[protocol] == NULL) + return -ENOENT; -struct rtnetlink_link * rtnetlink_links[NPROTO]; + rtnl_msg_handlers[protocol][msgindex].doit = NULL; + rtnl_msg_handlers[protocol][msgindex].dumpit = NULL; -static const int rtm_min[RTM_NR_FAMILIES] = + return 0; +} +EXPORT_SYMBOL_GPL(rtnl_unregister); + +/** + * rtnl_unregister_all - Unregister all rtnetlink message type of a protocol + * @protocol : Protocol family or PF_UNSPEC + * + * Identical to calling rtnl_unregster() for all registered message types + * of a certain protocol family. + */ +void rtnl_unregister_all(int protocol) { - [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), - [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), - [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWNEIGH)] = NLMSG_LENGTH(sizeof(struct ndmsg)), - [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)), - [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_NEWNEIGHTBL)] = NLMSG_LENGTH(sizeof(struct ndtmsg)), -}; + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); -static const int rta_max[RTM_NR_FAMILIES] = -{ - [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, - [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, - [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, - [RTM_FAM(RTM_NEWNEIGH)] = NDA_MAX, - [RTM_FAM(RTM_NEWRULE)] = RTA_MAX, - [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, - [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, - [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, - [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, - [RTM_FAM(RTM_NEWNEIGHTBL)] = NDTA_MAX, -}; + kfree(rtnl_msg_handlers[protocol]); + rtnl_msg_handlers[protocol] = NULL; +} +EXPORT_SYMBOL_GPL(rtnl_unregister_all); + +static LIST_HEAD(link_ops); + +static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind) +{ + const struct rtnl_link_ops *ops; + + list_for_each_entry(ops, &link_ops, list) { + if (!strcmp(ops->kind, kind)) + return ops; + } + return NULL; +} + +/** + * __rtnl_link_register - Register rtnl_link_ops with rtnetlink. + * @ops: struct rtnl_link_ops * to register + * + * The caller must hold the rtnl_mutex. This function should be used + * by drivers that create devices during module initialization. It + * must be called before registering the devices. + * + * Returns 0 on success or a negative error code. + */ +int __rtnl_link_register(struct rtnl_link_ops *ops) +{ + if (rtnl_link_ops_get(ops->kind)) + return -EEXIST; + + if (!ops->dellink) + ops->dellink = unregister_netdevice_queue; + + list_add_tail(&ops->list, &link_ops); + return 0; +} +EXPORT_SYMBOL_GPL(__rtnl_link_register); + +/** + * rtnl_link_register - Register rtnl_link_ops with rtnetlink. + * @ops: struct rtnl_link_ops * to register + * + * Returns 0 on success or a negative error code. + */ +int rtnl_link_register(struct rtnl_link_ops *ops) +{ + int err; + + rtnl_lock(); + err = __rtnl_link_register(ops); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL_GPL(rtnl_link_register); + +static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) +{ + struct net_device *dev; + LIST_HEAD(list_kill); + + for_each_netdev(net, dev) { + if (dev->rtnl_link_ops == ops) + ops->dellink(dev, &list_kill); + } + unregister_netdevice_many(&list_kill); +} + +/** + * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. + * @ops: struct rtnl_link_ops * to unregister + * + * The caller must hold the rtnl_mutex. + */ +void __rtnl_link_unregister(struct rtnl_link_ops *ops) +{ + struct net *net; + + for_each_net(net) { + __rtnl_kill_links(net, ops); + } + list_del(&ops->list); +} +EXPORT_SYMBOL_GPL(__rtnl_link_unregister); + +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + +/** + * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. + * @ops: struct rtnl_link_ops * to unregister + */ +void rtnl_link_unregister(struct rtnl_link_ops *ops) +{ + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); + __rtnl_link_unregister(ops); + rtnl_unlock(); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL_GPL(rtnl_link_unregister); -void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) +static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) { - struct rtattr *rta; - int size = RTA_LENGTH(attrlen); + struct net_device *master_dev; + const struct rtnl_link_ops *ops; - rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size)); - rta->rta_type = attrtype; - rta->rta_len = size; - memcpy(RTA_DATA(rta), data, attrlen); - memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops || !ops->get_slave_size) + return 0; + /* IFLA_INFO_SLAVE_DATA + nested data */ + return nla_total_size(sizeof(struct nlattr)) + + ops->get_slave_size(master_dev, dev); } -size_t rtattr_strlcpy(char *dest, const struct rtattr *rta, size_t size) +static size_t rtnl_link_get_size(const struct net_device *dev) { - size_t ret = RTA_PAYLOAD(rta); - char *src = RTA_DATA(rta); + const struct rtnl_link_ops *ops = dev->rtnl_link_ops; + size_t size; + + if (!ops) + return 0; + + size = nla_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */ + nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */ + + if (ops->get_size) + /* IFLA_INFO_DATA + nested data */ + size += nla_total_size(sizeof(struct nlattr)) + + ops->get_size(dev); - if (ret > 0 && src[ret - 1] == '\0') - ret--; - if (size > 0) { - size_t len = (ret >= size) ? size - 1 : ret; - memset(dest, 0, size); - memcpy(dest, src, len); + if (ops->get_xstats_size) + /* IFLA_INFO_XSTATS */ + size += nla_total_size(ops->get_xstats_size(dev)); + + size += rtnl_link_get_slave_info_data_size(dev); + + return size; +} + +static LIST_HEAD(rtnl_af_ops); + +static const struct rtnl_af_ops *rtnl_af_lookup(const int family) +{ + const struct rtnl_af_ops *ops; + + list_for_each_entry(ops, &rtnl_af_ops, list) { + if (ops->family == family) + return ops; } - return ret; + + return NULL; +} + +/** + * rtnl_af_register - Register rtnl_af_ops with rtnetlink. + * @ops: struct rtnl_af_ops * to register + * + * Returns 0 on success or a negative error code. + */ +void rtnl_af_register(struct rtnl_af_ops *ops) +{ + rtnl_lock(); + list_add_tail(&ops->list, &rtnl_af_ops); + rtnl_unlock(); } +EXPORT_SYMBOL_GPL(rtnl_af_register); -int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) +/** + * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. + * @ops: struct rtnl_af_ops * to unregister + * + * The caller must hold the rtnl_mutex. + */ +void __rtnl_af_unregister(struct rtnl_af_ops *ops) +{ + list_del(&ops->list); +} +EXPORT_SYMBOL_GPL(__rtnl_af_unregister); + +/** + * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. + * @ops: struct rtnl_af_ops * to unregister + */ +void rtnl_af_unregister(struct rtnl_af_ops *ops) { + rtnl_lock(); + __rtnl_af_unregister(ops); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(rtnl_af_unregister); + +static size_t rtnl_link_get_af_size(const struct net_device *dev) +{ + struct rtnl_af_ops *af_ops; + size_t size; + + /* IFLA_AF_SPEC */ + size = nla_total_size(sizeof(struct nlattr)); + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->get_link_af_size) { + /* AF_* + nested data */ + size += nla_total_size(sizeof(struct nlattr)) + + af_ops->get_link_af_size(dev); + } + } + + return size; +} + +static bool rtnl_have_link_slave_info(const struct net_device *dev) +{ + struct net_device *master_dev; + + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (master_dev && master_dev->rtnl_link_ops) + return true; + return false; +} + +static int rtnl_link_slave_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + struct net_device *master_dev; + const struct rtnl_link_ops *ops; + struct nlattr *slave_data; + int err; + + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops) + return 0; + if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0) + return -EMSGSIZE; + if (ops->fill_slave_info) { + slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA); + if (!slave_data) + return -EMSGSIZE; + err = ops->fill_slave_info(skb, master_dev, dev); + if (err < 0) + goto err_cancel_slave_data; + nla_nest_end(skb, slave_data); + } + return 0; + +err_cancel_slave_data: + nla_nest_cancel(skb, slave_data); + return err; +} + +static int rtnl_link_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct rtnl_link_ops *ops = dev->rtnl_link_ops; + struct nlattr *data; + int err; + + if (!ops) + return 0; + if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0) + return -EMSGSIZE; + if (ops->fill_xstats) { + err = ops->fill_xstats(skb, dev); + if (err < 0) + return err; + } + if (ops->fill_info) { + data = nla_nest_start(skb, IFLA_INFO_DATA); + if (data == NULL) + return -EMSGSIZE; + err = ops->fill_info(skb, dev); + if (err < 0) + goto err_cancel_data; + nla_nest_end(skb, data); + } + return 0; + +err_cancel_data: + nla_nest_cancel(skb, data); + return err; +} + +static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) +{ + struct nlattr *linkinfo; + int err = -EMSGSIZE; + + linkinfo = nla_nest_start(skb, IFLA_LINKINFO); + if (linkinfo == NULL) + goto out; + + err = rtnl_link_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + err = rtnl_link_slave_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + nla_nest_end(skb, linkinfo); + return 0; + +err_cancel_link: + nla_nest_cancel(skb, linkinfo); +out: + return err; +} + +int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) +{ + struct sock *rtnl = net->rtnl; int err = 0; NETLINK_CB(skb).dst_group = group; @@ -158,56 +622,395 @@ int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) return err; } +int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) +{ + struct sock *rtnl = net->rtnl; + + return nlmsg_unicast(rtnl, skb, pid); +} +EXPORT_SYMBOL(rtnl_unicast); + +void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, + struct nlmsghdr *nlh, gfp_t flags) +{ + struct sock *rtnl = net->rtnl; + int report = 0; + + if (nlh) + report = nlmsg_report(nlh); + + nlmsg_notify(rtnl, skb, pid, group, report, flags); +} +EXPORT_SYMBOL(rtnl_notify); + +void rtnl_set_sk_err(struct net *net, u32 group, int error) +{ + struct sock *rtnl = net->rtnl; + + netlink_set_err(rtnl, 0, group, error); +} +EXPORT_SYMBOL(rtnl_set_sk_err); + int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { - struct rtattr *mx = (struct rtattr*)skb->tail; - int i; + struct nlattr *mx; + int i, valid = 0; + + mx = nla_nest_start(skb, RTA_METRICS); + if (mx == NULL) + return -ENOBUFS; + + for (i = 0; i < RTAX_MAX; i++) { + if (metrics[i]) { + valid++; + if (nla_put_u32(skb, i+1, metrics[i])) + goto nla_put_failure; + } + } + + if (!valid) { + nla_nest_cancel(skb, mx); + return 0; + } + + return nla_nest_end(skb, mx); + +nla_put_failure: + nla_nest_cancel(skb, mx); + return -EMSGSIZE; +} +EXPORT_SYMBOL(rtnetlink_put_metrics); + +int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, + long expires, u32 error) +{ + struct rta_cacheinfo ci = { + .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse), + .rta_used = dst->__use, + .rta_clntref = atomic_read(&(dst->__refcnt)), + .rta_error = error, + .rta_id = id, + }; + + if (expires) { + unsigned long clock; + + clock = jiffies_to_clock_t(abs(expires)); + clock = min_t(unsigned long, clock, INT_MAX); + ci.rta_expires = (expires > 0) ? clock : -clock; + } + return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); +} +EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); + +static void set_operstate(struct net_device *dev, unsigned char transition) +{ + unsigned char operstate = dev->operstate; + + switch (transition) { + case IF_OPER_UP: + if ((operstate == IF_OPER_DORMANT || + operstate == IF_OPER_UNKNOWN) && + !netif_dormant(dev)) + operstate = IF_OPER_UP; + break; - RTA_PUT(skb, RTA_METRICS, 0, NULL); - for (i=0; i<RTAX_MAX; i++) { - if (metrics[i]) - RTA_PUT(skb, i+1, sizeof(u32), metrics+i); + case IF_OPER_DORMANT: + if (operstate == IF_OPER_UP || + operstate == IF_OPER_UNKNOWN) + operstate = IF_OPER_DORMANT; + break; } - mx->rta_len = skb->tail - (u8*)mx; - if (mx->rta_len == RTA_LENGTH(0)) - skb_trim(skb, (u8*)mx - skb->data); + + if (dev->operstate != operstate) { + write_lock_bh(&dev_base_lock); + dev->operstate = operstate; + write_unlock_bh(&dev_base_lock); + netdev_state_change(dev); + } +} + +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + +static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, + const struct ifinfomsg *ifm) +{ + unsigned int flags = ifm->ifi_flags; + + /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ + if (ifm->ifi_change) + flags = (flags & ifm->ifi_change) | + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); + + return flags; +} + +static void copy_rtnl_link_stats(struct rtnl_link_stats *a, + const struct rtnl_link_stats64 *b) +{ + a->rx_packets = b->rx_packets; + a->tx_packets = b->tx_packets; + a->rx_bytes = b->rx_bytes; + a->tx_bytes = b->tx_bytes; + a->rx_errors = b->rx_errors; + a->tx_errors = b->tx_errors; + a->rx_dropped = b->rx_dropped; + a->tx_dropped = b->tx_dropped; + + a->multicast = b->multicast; + a->collisions = b->collisions; + + a->rx_length_errors = b->rx_length_errors; + a->rx_over_errors = b->rx_over_errors; + a->rx_crc_errors = b->rx_crc_errors; + a->rx_frame_errors = b->rx_frame_errors; + a->rx_fifo_errors = b->rx_fifo_errors; + a->rx_missed_errors = b->rx_missed_errors; + + a->tx_aborted_errors = b->tx_aborted_errors; + a->tx_carrier_errors = b->tx_carrier_errors; + a->tx_fifo_errors = b->tx_fifo_errors; + a->tx_heartbeat_errors = b->tx_heartbeat_errors; + a->tx_window_errors = b->tx_window_errors; + + a->rx_compressed = b->rx_compressed; + a->tx_compressed = b->tx_compressed; +} + +static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) +{ + memcpy(v, b, sizeof(*b)); +} + +/* All VF info */ +static inline int rtnl_vfinfo_size(const struct net_device *dev, + u32 ext_filter_mask) +{ + if (dev->dev.parent && dev_is_pci(dev->dev.parent) && + (ext_filter_mask & RTEXT_FILTER_VF)) { + int num_vfs = dev_num_vf(dev->dev.parent); + size_t size = nla_total_size(sizeof(struct nlattr)); + size += nla_total_size(num_vfs * sizeof(struct nlattr)); + size += num_vfs * + (nla_total_size(sizeof(struct ifla_vf_mac)) + + nla_total_size(sizeof(struct ifla_vf_vlan)) + + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_rate))); + return size; + } else + return 0; +} + +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) +{ + size_t port_size = nla_total_size(4) /* PORT_VF */ + + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ + + nla_total_size(sizeof(struct ifla_port_vsi)) + /* PORT_VSI_TYPE */ + + nla_total_size(PORT_UUID_MAX) /* PORT_INSTANCE_UUID */ + + nla_total_size(PORT_UUID_MAX) /* PORT_HOST_UUID */ + + nla_total_size(1) /* PROT_VDP_REQUEST */ + + nla_total_size(2); /* PORT_VDP_RESPONSE */ + size_t vf_ports_size = nla_total_size(sizeof(struct nlattr)); + size_t vf_port_size = nla_total_size(sizeof(struct nlattr)) + + port_size; + size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + + port_size; + + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) + return 0; + if (dev_num_vf(dev->dev.parent)) + return port_self_size + vf_ports_size + + vf_port_size * dev_num_vf(dev->dev.parent); + else + return port_self_size; +} + +static noinline size_t if_nlmsg_size(const struct net_device *dev, + u32 ext_filter_mask) +{ + return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(IFALIASZ) /* IFLA_IFALIAS */ + + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */ + + nla_total_size(sizeof(struct rtnl_link_ifmap)) + + nla_total_size(sizeof(struct rtnl_link_stats)) + + nla_total_size(sizeof(struct rtnl_link_stats64)) + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */ + + nla_total_size(4) /* IFLA_TXQLEN */ + + nla_total_size(4) /* IFLA_WEIGHT */ + + nla_total_size(4) /* IFLA_MTU */ + + nla_total_size(4) /* IFLA_LINK */ + + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(1) /* IFLA_CARRIER */ + + nla_total_size(4) /* IFLA_PROMISCUITY */ + + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + + 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 */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ +} + +static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct nlattr *vf_ports; + struct nlattr *vf_port; + int vf; + int err; + + vf_ports = nla_nest_start(skb, IFLA_VF_PORTS); + if (!vf_ports) + return -EMSGSIZE; + + for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) { + vf_port = nla_nest_start(skb, IFLA_VF_PORT); + if (!vf_port) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_PORT_VF, vf)) + goto nla_put_failure; + err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb); + if (err == -EMSGSIZE) + goto nla_put_failure; + if (err) { + nla_nest_cancel(skb, vf_port); + continue; + } + nla_nest_end(skb, vf_port); + } + + nla_nest_end(skb, vf_ports); + return 0; -rtattr_failure: - skb_trim(skb, (u8*)mx - skb->data); - return -1; +nla_put_failure: + nla_nest_cancel(skb, vf_ports); + return -EMSGSIZE; } +static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct nlattr *port_self; + int err; + + port_self = nla_nest_start(skb, IFLA_PORT_SELF); + if (!port_self) + return -EMSGSIZE; -static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, - int type, u32 pid, u32 seq, u32 change, - unsigned int flags) + err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb); + if (err) { + nla_nest_cancel(skb, port_self); + return (err == -EMSGSIZE) ? err : 0; + } + + nla_nest_end(skb, port_self); + + return 0; +} + +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; + int err; - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*r), flags); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = change; + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) + return 0; - RTA_PUT(skb, IFLA_IFNAME, strlen(dev->name)+1, dev->name); + err = rtnl_port_self_fill(skb, dev); + if (err) + return err; - if (1) { - u32 txqlen = dev->tx_queue_len; - RTA_PUT(skb, IFLA_TXQLEN, sizeof(txqlen), &txqlen); + if (dev_num_vf(dev->dev.parent)) { + err = rtnl_vf_ports_fill(skb, dev); + if (err) + return err; } - if (1) { - u32 weight = dev->weight; - RTA_PUT(skb, IFLA_WEIGHT, sizeof(weight), &weight); + return 0; +} + +static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) +{ + int err; + struct netdev_phys_port_id ppid; + + err = dev_get_phys_port_id(dev, &ppid); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; } + if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id)) + return -EMSGSIZE; + + return 0; +} + +static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, + int type, u32 pid, u32 seq, u32 change, + unsigned int flags, u32 ext_filter_mask) +{ + struct ifinfomsg *ifm; + struct nlmsghdr *nlh; + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats; + struct nlattr *attr, *af_spec; + struct rtnl_af_ops *af_ops; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); + + ASSERT_RTNL(); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_UNSPEC; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = change; + + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || + nla_put_u8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN) || + nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u32(skb, IFLA_GROUP, dev->group) || + nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || + nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || +#ifdef CONFIG_RPS + nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || +#endif + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink)) || + (upper_dev && + nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || + nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(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_u32(skb, IFLA_CARRIER_CHANGES, + atomic_read(&dev->carrier_changes))) + goto nla_put_failure; + if (1) { struct rtnl_link_ifmap map = { .mem_start = dev->mem_start, @@ -217,125 +1020,500 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, .dma = dev->dma, .port = dev->if_port, }; - RTA_PUT(skb, IFLA_MAP, sizeof(map), &map); + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) + goto nla_put_failure; } if (dev->addr_len) { - RTA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - RTA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); + if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) || + nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast)) + goto nla_put_failure; } - if (1) { - u32 mtu = dev->mtu; - RTA_PUT(skb, IFLA_MTU, sizeof(mtu), &mtu); + if (rtnl_phys_port_id_fill(skb, dev)) + goto nla_put_failure; + + attr = nla_reserve(skb, IFLA_STATS, + sizeof(struct rtnl_link_stats)); + if (attr == NULL) + goto nla_put_failure; + + stats = dev_get_stats(dev, &temp); + copy_rtnl_link_stats(nla_data(attr), stats); + + attr = nla_reserve(skb, IFLA_STATS64, + sizeof(struct rtnl_link_stats64)); + if (attr == NULL) + goto nla_put_failure; + copy_rtnl_link_stats64(nla_data(attr), stats); + + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && + nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) + goto nla_put_failure; + + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent + && (ext_filter_mask & RTEXT_FILTER_VF)) { + int i; + + struct nlattr *vfinfo, *vf; + int num_vfs = dev_num_vf(dev->dev.parent); + + vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); + if (!vfinfo) + goto nla_put_failure; + for (i = 0; i < num_vfs; i++) { + struct ifla_vf_info ivi; + struct ifla_vf_mac vf_mac; + struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; + struct ifla_vf_tx_rate vf_tx_rate; + struct ifla_vf_spoofchk vf_spoofchk; + struct ifla_vf_link_state vf_linkstate; + + /* + * Not all SR-IOV capable drivers support the + * spoofcheck query. Preset to -1 so the user + * space tool can detect that the driver didn't + * report anything. + */ + ivi.spoofchk = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); + /* The default value for VF link state is "auto" + * IFLA_VF_LINK_STATE_AUTO which equals zero + */ + ivi.linkstate = 0; + if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) + break; + vf_mac.vf = + vf_vlan.vf = + vf_rate.vf = + vf_tx_rate.vf = + vf_spoofchk.vf = + vf_linkstate.vf = ivi.vf; + + memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); + vf_vlan.vlan = ivi.vlan; + vf_vlan.qos = ivi.qos; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; + vf_spoofchk.setting = ivi.spoofchk; + vf_linkstate.link_state = ivi.linkstate; + vf = nla_nest_start(skb, IFLA_VF_INFO); + if (!vf) { + nla_nest_cancel(skb, vfinfo); + goto nla_put_failure; + } + if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || + nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || + nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), + &vf_tx_rate) || + nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), + &vf_spoofchk) || + nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), + &vf_linkstate)) + goto nla_put_failure; + nla_nest_end(skb, vf); + } + nla_nest_end(skb, vfinfo); } - if (dev->ifindex != dev->iflink) { - u32 iflink = dev->iflink; - RTA_PUT(skb, IFLA_LINK, sizeof(iflink), &iflink); - } + if (rtnl_port_fill(skb, dev, ext_filter_mask)) + goto nla_put_failure; - if (dev->qdisc_sleeping) - RTA_PUT(skb, IFLA_QDISC, - strlen(dev->qdisc_sleeping->ops->id) + 1, - dev->qdisc_sleeping->ops->id); - - if (dev->master) { - u32 master = dev->master->ifindex; - RTA_PUT(skb, IFLA_MASTER, sizeof(master), &master); + if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { + if (rtnl_link_fill(skb, dev) < 0) + goto nla_put_failure; } - if (dev->get_stats) { - unsigned long *stats = (unsigned long*)dev->get_stats(dev); - if (stats) { - struct rtattr *a; - __u32 *s; - int i; - int n = sizeof(struct rtnl_link_stats)/4; + if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) + goto nla_put_failure; + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->fill_link_af) { + struct nlattr *af; + int err; + + if (!(af = nla_nest_start(skb, af_ops->family))) + goto nla_put_failure; - a = __RTA_PUT(skb, IFLA_STATS, n*4); - s = RTA_DATA(a); - for (i=0; i<n; i++) - s[i] = stats[i]; + err = af_ops->fill_link_af(skb, dev); + + /* + * Caller may return ENODATA to indicate that there + * was no data to be dumped. This is not an error, it + * means we should trim the attribute header and + * continue. + */ + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + goto nla_put_failure; + + nla_nest_end(skb, af); } } - nlh->nlmsg_len = skb->tail - b; - return skb->len; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + nla_nest_end(skb, af_spec); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; } -static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +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 }, + [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, + [IFLA_MTU] = { .type = NLA_U32 }, + [IFLA_LINK] = { .type = NLA_U32 }, + [IFLA_MASTER] = { .type = NLA_U32 }, + [IFLA_CARRIER] = { .type = NLA_U8 }, + [IFLA_TXQLEN] = { .type = NLA_U32 }, + [IFLA_WEIGHT] = { .type = NLA_U32 }, + [IFLA_OPERSTATE] = { .type = NLA_U8 }, + [IFLA_LINKMODE] = { .type = NLA_U8 }, + [IFLA_LINKINFO] = { .type = NLA_NESTED }, + [IFLA_NET_NS_PID] = { .type = NLA_U32 }, + [IFLA_NET_NS_FD] = { .type = NLA_U32 }, + [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, + [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, + [IFLA_VF_PORTS] = { .type = NLA_NESTED }, + [IFLA_PORT_SELF] = { .type = NLA_NESTED }, + [IFLA_AF_SPEC] = { .type = NLA_NESTED }, + [IFLA_EXT_MASK] = { .type = NLA_U32 }, + [IFLA_PROMISCUITY] = { .type = NLA_U32 }, + [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 */ +}; + +static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { + [IFLA_INFO_KIND] = { .type = NLA_STRING }, + [IFLA_INFO_DATA] = { .type = NLA_NESTED }, + [IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING }, + [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { + [IFLA_VF_INFO] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { + [IFLA_VF_MAC] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_rate) }, + [IFLA_VF_LINK_STATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_link_state) }, +}; + +static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { + [IFLA_PORT_VF] = { .type = NLA_U32 }, + [IFLA_PORT_PROFILE] = { .type = NLA_STRING, + .len = PORT_PROFILE_MAX }, + [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_port_vsi)}, + [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY, + .len = PORT_UUID_MAX }, + [IFLA_PORT_HOST_UUID] = { .type = NLA_STRING, + .len = PORT_UUID_MAX }, + [IFLA_PORT_REQUEST] = { .type = NLA_U8, }, + [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, +}; + +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { - int idx; - int s_idx = cb->args[0]; + 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; + int err; + int hdrlen; - read_lock(&dev_base_lock); - for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { - if (idx < s_idx) - continue; - if (rtnetlink_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) - break; + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + cb->seq = net->dev_base_seq; + + /* A hack to preserve kernel<->userspace interface. + * The correct header is ifinfomsg. It is consistent with rtnl_getlink. + * However, before Linux v3.9 the code here assumed rtgenmsg and that's + * what iproute2 < v3.9.0 used. + * We can detect the old iproute2. Even including the IFLA_EXT_MASK + * attribute, its netlink message is shorter than struct ifinfomsg. + */ + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); } - read_unlock(&dev_base_lock); - cb->args[0] = idx; + + 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; + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 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; } -static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len) { - struct ifinfomsg *ifm = NLMSG_DATA(nlh); - struct rtattr **ida = arg; - struct net_device *dev; - int err, send_addr_notify = 0; + return nla_parse(tb, IFLA_MAX, head, len, ifla_policy); +} +EXPORT_SYMBOL(rtnl_nla_parse_ifla); - if (ifm->ifi_index >= 0) - dev = dev_get_by_index(ifm->ifi_index); - else if (ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; +struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) +{ + struct net *net; + /* Examine the link attributes and figure out which + * network namespace we are talking about. + */ + if (tb[IFLA_NET_NS_PID]) + net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); + else if (tb[IFLA_NET_NS_FD]) + net = get_net_ns_by_fd(nla_get_u32(tb[IFLA_NET_NS_FD])); + else + net = get_net(src_net); + return net; +} +EXPORT_SYMBOL(rtnl_link_get_net); - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) +static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) +{ + if (dev) { + if (tb[IFLA_ADDRESS] && + nla_len(tb[IFLA_ADDRESS]) < dev->addr_len) return -EINVAL; - dev = dev_get_by_name(ifname); - } else - return -EINVAL; - if (!dev) - return -ENODEV; + if (tb[IFLA_BROADCAST] && + nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) + return -EINVAL; + } - err = -EINVAL; + if (tb[IFLA_AF_SPEC]) { + struct nlattr *af; + int rem, err; + + nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { + const struct rtnl_af_ops *af_ops; - if (ifm->ifi_flags) - dev_change_flags(dev, ifm->ifi_flags); + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + return -EAFNOSUPPORT; - if (ida[IFLA_MAP - 1]) { + if (!af_ops->set_link_af) + return -EOPNOTSUPP; + + if (af_ops->validate_link_af) { + err = af_ops->validate_link_af(dev, af); + if (err < 0) + return err; + } + } + } + + return 0; +} + +static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) +{ + int rem, err = -EINVAL; + struct nlattr *vf; + const struct net_device_ops *ops = dev->netdev_ops; + + nla_for_each_nested(vf, attr, rem) { + switch (nla_type(vf)) { + case IFLA_VF_MAC: { + struct ifla_vf_mac *ivm; + ivm = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_mac) + err = ops->ndo_set_vf_mac(dev, ivm->vf, + ivm->mac); + break; + } + case IFLA_VF_VLAN: { + struct ifla_vf_vlan *ivv; + ivv = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_vlan) + err = ops->ndo_set_vf_vlan(dev, ivv->vf, + ivv->vlan, + ivv->qos); + break; + } + case IFLA_VF_TX_RATE: { + struct ifla_vf_tx_rate *ivt; + struct ifla_vf_info ivf; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_get_vf_config) + err = ops->ndo_get_vf_config(dev, ivt->vf, + &ivf); + if (err) + break; + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivf.min_tx_rate, + ivt->rate); + break; + } + case IFLA_VF_RATE: { + struct ifla_vf_rate *ivt; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivt->min_tx_rate, + ivt->max_tx_rate); + break; + } + case IFLA_VF_SPOOFCHK: { + struct ifla_vf_spoofchk *ivs; + ivs = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_spoofchk) + err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, + ivs->setting); + break; + } + case IFLA_VF_LINK_STATE: { + struct ifla_vf_link_state *ivl; + ivl = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_link_state) + err = ops->ndo_set_vf_link_state(dev, ivl->vf, + ivl->link_state); + break; + } + default: + err = -EINVAL; + break; + } + if (err) + break; + } + return err; +} + +static int do_set_master(struct net_device *dev, int ifindex) +{ + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops; + int err; + + if (upper_dev) { + if (upper_dev->ifindex == ifindex) + return 0; + ops = upper_dev->netdev_ops; + if (ops->ndo_del_slave) { + err = ops->ndo_del_slave(upper_dev, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + + if (ifindex) { + upper_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!upper_dev) + return -EINVAL; + ops = upper_dev->netdev_ops; + if (ops->ndo_add_slave) { + err = ops->ndo_add_slave(upper_dev, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + return 0; +} + +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, + struct nlattr **tb, char *ifname, int modified) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int err; + + if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) { + struct net *net = rtnl_link_get_net(dev_net(dev), tb); + if (IS_ERR(net)) { + err = PTR_ERR(net); + goto errout; + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + err = -EPERM; + goto errout; + } + err = dev_change_net_namespace(dev, net, ifname); + put_net(net); + if (err) + goto errout; + modified = 1; + } + + if (tb[IFLA_MAP]) { struct rtnl_link_ifmap *u_map; struct ifmap k_map; - if (!dev->set_config) { + if (!ops->ndo_set_config) { err = -EOPNOTSUPP; - goto out; + goto errout; } if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout; } - - if (ida[IFLA_MAP - 1]->rta_len != RTA_LENGTH(sizeof(*u_map))) - goto out; - - u_map = RTA_DATA(ida[IFLA_MAP - 1]); + u_map = nla_data(tb[IFLA_MAP]); k_map.mem_start = (unsigned long) u_map->mem_start; k_map.mem_end = (unsigned long) u_map->mem_end; k_map.base_addr = (unsigned short) u_map->base_addr; @@ -343,100 +1521,667 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) k_map.dma = (unsigned char) u_map->dma; k_map.port = (unsigned char) u_map->port; - err = dev->set_config(dev, &k_map); + err = ops->ndo_set_config(dev, &k_map); + if (err < 0) + goto errout; - if (err) - goto out; + modified = 1; } - if (ida[IFLA_ADDRESS - 1]) { - if (!dev->set_mac_address) { - err = -EOPNOTSUPP; - goto out; - } - if (!netif_device_present(dev)) { - err = -ENODEV; - goto out; - } - if (ida[IFLA_ADDRESS - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; + if (tb[IFLA_ADDRESS]) { + struct sockaddr *sa; + int len; - err = dev->set_mac_address(dev, RTA_DATA(ida[IFLA_ADDRESS - 1])); + len = sizeof(sa_family_t) + dev->addr_len; + sa = kmalloc(len, GFP_KERNEL); + if (!sa) { + err = -ENOMEM; + goto errout; + } + sa->sa_family = dev->type; + memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), + dev->addr_len); + err = dev_set_mac_address(dev, sa); + kfree(sa); if (err) - goto out; - send_addr_notify = 1; + goto errout; + modified = 1; } - if (ida[IFLA_BROADCAST - 1]) { - if (ida[IFLA_BROADCAST - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; - memcpy(dev->broadcast, RTA_DATA(ida[IFLA_BROADCAST - 1]), - dev->addr_len); - send_addr_notify = 1; + if (tb[IFLA_MTU]) { + err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + if (err < 0) + goto errout; + modified = 1; } - if (ida[IFLA_MTU - 1]) { - if (ida[IFLA_MTU - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - err = dev_set_mtu(dev, *((u32 *) RTA_DATA(ida[IFLA_MTU - 1]))); + if (tb[IFLA_GROUP]) { + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + modified = 1; + } + + /* + * Interface selected by interface index but interface + * name provided implies that a name change has been + * requested. + */ + if (ifm->ifi_index > 0 && ifname[0]) { + err = dev_change_name(dev, ifname); + if (err < 0) + goto errout; + modified = 1; + } + + if (tb[IFLA_IFALIAS]) { + err = dev_set_alias(dev, nla_data(tb[IFLA_IFALIAS]), + nla_len(tb[IFLA_IFALIAS])); + if (err < 0) + goto errout; + modified = 1; + } + if (tb[IFLA_BROADCAST]) { + nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + } + + if (ifm->ifi_flags || ifm->ifi_change) { + err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm)); + if (err < 0) + goto errout; + } + + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); if (err) - goto out; + goto errout; + modified = 1; + } + if (tb[IFLA_CARRIER]) { + err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); + if (err) + goto errout; + modified = 1; } - if (ida[IFLA_TXQLEN - 1]) { - if (ida[IFLA_TXQLEN - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; + if (tb[IFLA_TXQLEN]) + dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); + + if (tb[IFLA_OPERSTATE]) + set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); - dev->tx_queue_len = *((u32 *) RTA_DATA(ida[IFLA_TXQLEN - 1])); + if (tb[IFLA_LINKMODE]) { + write_lock_bh(&dev_base_lock); + dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); + write_unlock_bh(&dev_base_lock); } - if (ida[IFLA_WEIGHT - 1]) { - if (ida[IFLA_WEIGHT - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; + if (tb[IFLA_VFINFO_LIST]) { + struct nlattr *attr; + int rem; + nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) { + if (nla_type(attr) != IFLA_VF_INFO) { + err = -EINVAL; + goto errout; + } + err = do_setvfinfo(dev, attr); + if (err < 0) + goto errout; + modified = 1; + } + } + err = 0; - dev->weight = *((u32 *) RTA_DATA(ida[IFLA_WEIGHT - 1])); + if (tb[IFLA_VF_PORTS]) { + struct nlattr *port[IFLA_PORT_MAX+1]; + struct nlattr *attr; + int vf; + int rem; + + err = -EOPNOTSUPP; + if (!ops->ndo_set_vf_port) + goto errout; + + nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) { + if (nla_type(attr) != IFLA_VF_PORT) + continue; + err = nla_parse_nested(port, IFLA_PORT_MAX, + attr, ifla_port_policy); + if (err < 0) + goto errout; + if (!port[IFLA_PORT_VF]) { + err = -EOPNOTSUPP; + goto errout; + } + vf = nla_get_u32(port[IFLA_PORT_VF]); + err = ops->ndo_set_vf_port(dev, vf, port); + if (err < 0) + goto errout; + modified = 1; + } } + err = 0; - if (ifm->ifi_index >= 0 && ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; + if (tb[IFLA_PORT_SELF]) { + struct nlattr *port[IFLA_PORT_MAX+1]; - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - goto out; - err = dev_change_name(dev, ifname); - if (err) - goto out; + err = nla_parse_nested(port, IFLA_PORT_MAX, + tb[IFLA_PORT_SELF], ifla_port_policy); + if (err < 0) + goto errout; + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_port) + err = ops->ndo_set_vf_port(dev, PORT_SELF_VF, port); + if (err < 0) + goto errout; + modified = 1; } + if (tb[IFLA_AF_SPEC]) { + struct nlattr *af; + int rem; + + nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { + const struct rtnl_af_ops *af_ops; + + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + BUG(); + + err = af_ops->set_link_af(dev, af); + if (err < 0) + goto errout; + + modified = 1; + } + } err = 0; +errout: + if (err < 0 && modified) + net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n", + dev->name); + + return err; +} + +static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + int err; + struct nlattr *tb[IFLA_MAX+1]; + char ifname[IFNAMSIZ]; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + goto errout; + + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + else + ifname[0] = '\0'; + + err = -EINVAL; + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else if (tb[IFLA_IFNAME]) + dev = __dev_get_by_name(net, ifname); + else + goto errout; + + if (dev == NULL) { + err = -ENODEV; + goto errout; + } + + err = validate_linkmsg(dev, tb); + if (err < 0) + goto errout; + + err = do_setlink(skb, dev, ifm, tb, ifname, 0); +errout: + return err; +} + +static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + const struct rtnl_link_ops *ops; + struct net_device *dev; + struct ifinfomsg *ifm; + char ifname[IFNAMSIZ]; + struct nlattr *tb[IFLA_MAX+1]; + int err; + LIST_HEAD(list_kill); + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + return err; + + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else if (tb[IFLA_IFNAME]) + dev = __dev_get_by_name(net, ifname); + else + return -EINVAL; + + if (!dev) + return -ENODEV; + + ops = dev->rtnl_link_ops; + if (!ops) + return -EOPNOTSUPP; + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + return 0; +} + +int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) +{ + unsigned int old_flags; + int err; + + old_flags = dev->flags; + if (ifm && (ifm->ifi_flags || ifm->ifi_change)) { + err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm)); + if (err < 0) + return err; + } + + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + + __dev_notify_flags(dev, old_flags, ~0U); + return 0; +} +EXPORT_SYMBOL(rtnl_configure_link); + +struct net_device *rtnl_create_link(struct net *net, + char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) +{ + int err; + struct net_device *dev; + unsigned int num_tx_queues = 1; + unsigned int num_rx_queues = 1; + + if (tb[IFLA_NUM_TX_QUEUES]) + num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); + else if (ops->get_num_tx_queues) + num_tx_queues = ops->get_num_tx_queues(); + + if (tb[IFLA_NUM_RX_QUEUES]) + num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]); + else if (ops->get_num_rx_queues) + num_rx_queues = ops->get_num_rx_queues(); + + err = -ENOMEM; + dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup, + num_tx_queues, num_rx_queues); + if (!dev) + goto err; + + dev_net_set(dev, net); + dev->rtnl_link_ops = ops; + dev->rtnl_link_state = RTNL_LINK_INITIALIZING; + + if (tb[IFLA_MTU]) + dev->mtu = nla_get_u32(tb[IFLA_MTU]); + if (tb[IFLA_ADDRESS]) { + memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), + nla_len(tb[IFLA_ADDRESS])); + dev->addr_assign_type = NET_ADDR_SET; + } + if (tb[IFLA_BROADCAST]) + memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]), + nla_len(tb[IFLA_BROADCAST])); + if (tb[IFLA_TXQLEN]) + dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); + if (tb[IFLA_OPERSTATE]) + set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); + if (tb[IFLA_LINKMODE]) + dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); + if (tb[IFLA_GROUP]) + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + + return dev; + +err: + return ERR_PTR(err); +} +EXPORT_SYMBOL(rtnl_create_link); + +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, + struct ifinfomsg *ifm, + struct nlattr **tb) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + if (dev->group == group) { + err = do_setlink(skb, dev, ifm, tb, NULL, 0); + if (err < 0) + return err; + } + } + + return 0; +} + +static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + const struct rtnl_link_ops *ops; + const struct rtnl_link_ops *m_ops = NULL; + struct net_device *dev; + struct net_device *master_dev = NULL; + struct ifinfomsg *ifm; + char kind[MODULE_NAME_LEN]; + char ifname[IFNAMSIZ]; + struct nlattr *tb[IFLA_MAX+1]; + struct nlattr *linkinfo[IFLA_INFO_MAX+1]; + int err; + +#ifdef CONFIG_MODULES +replay: +#endif + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + return err; + + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + else + ifname[0] = '\0'; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else { + if (ifname[0]) + dev = __dev_get_by_name(net, ifname); + else + dev = NULL; + } + + if (dev) { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + m_ops = master_dev->rtnl_link_ops; + } + + err = validate_linkmsg(dev, tb); + if (err < 0) + return err; + + if (tb[IFLA_LINKINFO]) { + err = nla_parse_nested(linkinfo, IFLA_INFO_MAX, + tb[IFLA_LINKINFO], ifla_info_policy); + if (err < 0) + return err; + } else + memset(linkinfo, 0, sizeof(linkinfo)); + + if (linkinfo[IFLA_INFO_KIND]) { + nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind)); + ops = rtnl_link_ops_get(kind); + } else { + kind[0] = '\0'; + ops = NULL; + } + + if (1) { + struct nlattr *attr[ops ? ops->maxtype + 1 : 0]; + struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0]; + struct nlattr **data = NULL; + struct nlattr **slave_data = NULL; + struct net *dest_net; + + if (ops) { + if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) { + err = nla_parse_nested(attr, ops->maxtype, + linkinfo[IFLA_INFO_DATA], + ops->policy); + if (err < 0) + return err; + data = attr; + } + if (ops->validate) { + err = ops->validate(tb, data); + if (err < 0) + return err; + } + } + + if (m_ops) { + if (m_ops->slave_maxtype && + linkinfo[IFLA_INFO_SLAVE_DATA]) { + err = nla_parse_nested(slave_attr, + m_ops->slave_maxtype, + linkinfo[IFLA_INFO_SLAVE_DATA], + m_ops->slave_policy); + if (err < 0) + return err; + slave_data = slave_attr; + } + if (m_ops->slave_validate) { + err = m_ops->slave_validate(tb, slave_data); + if (err < 0) + return err; + } + } + + if (dev) { + int modified = 0; + + if (nlh->nlmsg_flags & NLM_F_EXCL) + return -EEXIST; + if (nlh->nlmsg_flags & NLM_F_REPLACE) + return -EOPNOTSUPP; + + if (linkinfo[IFLA_INFO_DATA]) { + if (!ops || ops != dev->rtnl_link_ops || + !ops->changelink) + return -EOPNOTSUPP; + + err = ops->changelink(dev, tb, data); + if (err < 0) + return err; + modified = 1; + } + + if (linkinfo[IFLA_INFO_SLAVE_DATA]) { + if (!m_ops || !m_ops->slave_changelink) + return -EOPNOTSUPP; + + err = m_ops->slave_changelink(master_dev, dev, + tb, slave_data); + if (err < 0) + return err; + modified = 1; + } + + return do_setlink(skb, dev, ifm, tb, ifname, modified); + } + + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) + return rtnl_group_changelink(skb, net, + nla_get_u32(tb[IFLA_GROUP]), + ifm, tb); + return -ENODEV; + } + + if (tb[IFLA_MAP] || tb[IFLA_MASTER] || tb[IFLA_PROTINFO]) + return -EOPNOTSUPP; + + if (!ops) { +#ifdef CONFIG_MODULES + if (kind[0]) { + __rtnl_unlock(); + request_module("rtnl-link-%s", kind); + rtnl_lock(); + ops = rtnl_link_ops_get(kind); + if (ops) + goto replay; + } +#endif + return -EOPNOTSUPP; + } + + if (!ifname[0]) + snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); + + dest_net = rtnl_link_get_net(net, tb); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + + dev = rtnl_create_link(dest_net, ifname, ops, tb); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out; + } + + dev->ifindex = ifm->ifi_index; + + if (ops->newlink) { + err = ops->newlink(net, dev, tb, data); + /* Drivers should call free_netdev() in ->destructor + * and unregister it on failure after registration + * so that device could be finally freed in rtnl_unlock. + */ + if (err < 0) { + /* If device is not registered at all, free it now */ + if (dev->reg_state == NETREG_UNINITIALIZED) + free_netdev(dev); + goto out; + } + } else { + err = register_netdevice(dev); + if (err < 0) { + free_netdev(dev); + goto out; + } + } + err = rtnl_configure_link(dev, ifm); + if (err < 0) + unregister_netdevice(dev); out: - if (send_addr_notify) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + put_net(dest_net); + return err; + } +} + +static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + char ifname[IFNAMSIZ]; + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *dev = NULL; + struct sk_buff *nskb; + int err; + u32 ext_filter_mask = 0; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + return err; + + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else if (tb[IFLA_IFNAME]) + dev = __dev_get_by_name(net, ifname); + else + return -EINVAL; + + if (dev == NULL) + return -ENODEV; + + nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); + if (nskb == NULL) + return -ENOBUFS; + + err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, + nlh->nlmsg_seq, 0, 0, ext_filter_mask); + if (err < 0) { + /* -EMSGSIZE implies BUG in if_nlmsg_size */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(nskb); + } else + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); - dev_put(dev); return err; } -static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) +static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + u16 min_ifinfo_dump_size = 0; + int hdrlen; + + /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ + hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + if (!ext_filter_mask) + return NLMSG_GOODSIZE; + /* + * traverse the list of net devices and compute the minimum + * buffer size based upon the filter mask. + */ + list_for_each_entry(dev, &net->dev_base_head, dev_list) { + min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, + if_nlmsg_size(dev, + ext_filter_mask)); + } + + return min_ifinfo_dump_size; +} + +static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; if (s_idx == 0) s_idx = 1; - for (idx=1; idx<NPROTO; idx++) { + for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { int type = cb->nlh->nlmsg_type-RTM_BASE; if (idx < s_idx || idx == PF_PACKET) continue; - if (rtnetlink_links[idx] == NULL || - rtnetlink_links[idx][type].dumpit == NULL) + if (rtnl_msg_handlers[idx] == NULL || + rtnl_msg_handlers[idx][type].dumpit == NULL) continue; - if (idx > s_idx) + if (idx > s_idx) { memset(&cb->args[0], 0, sizeof(cb->args)); - if (rtnetlink_links[idx][type].dumpit(skb, cb)) + cb->prev_seq = 0; + cb->seq = 0; + } + if (rtnl_msg_handlers[idx][type].dumpit(skb, cb)) break; } cb->family = idx; @@ -444,178 +2189,742 @@ static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + size_t if_info_size; + + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags); + if (skb == NULL) + goto errout; + + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); + if (err < 0) { + /* -EMSGSIZE implies BUG in if_nlmsg_size() */ + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + goto errout; + } + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); + return; +errout: + if (err < 0) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); +} +EXPORT_SYMBOL(rtmsg_ifinfo); + +static int nlmsg_populate_fdb_fill(struct sk_buff *skb, + struct net_device *dev, + u8 *addr, u32 pid, u32 seq, + int type, unsigned int flags, + int nlflags) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = flags; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dev->ifindex; + ndm->ndm_state = NUD_PERMANENT; + + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_fdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); +} + +static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) { + struct net *net = dev_net(dev); struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + - sizeof(struct rtnl_link_ifmap) + - sizeof(struct rtnl_link_stats) + 128); + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_KERNEL); + skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); if (!skb) - return; + goto errout; - if (rtnetlink_fill_ifinfo(skb, dev, type, current->pid, 0, change, 0) < 0) { + err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_KERNEL); + + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } -/* Protected by RTNL sempahore. */ -static struct rtattr **rta_buf; -static int rtattr_max; +/** + * ndo_dflt_fdb_add - default netdevice operation to add an FDB entry + */ +int ndo_dflt_fdb_add(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 flags) +{ + int err = -EINVAL; + + /* If aging addresses are supported device will need to + * implement its own handler for this. + */ + if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { + pr_info("%s: FDB only supports static addresses\n", dev->name); + return err; + } -/* Process one rtnetlink message. */ + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) + err = dev_uc_add_excl(dev, addr); + else if (is_multicast_ether_addr(addr)) + err = dev_mc_add_excl(dev, addr); + + /* Only return duplicate errors if NLM_F_EXCL is set */ + if (err == -EEXIST && !(flags & NLM_F_EXCL)) + err = 0; -static __inline__ int -rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) + return err; +} +EXPORT_SYMBOL(ndo_dflt_fdb_add); + +static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct rtnetlink_link *link; - struct rtnetlink_link *link_tab; - int sz_idx, kind; - int min_len; - int family; - int type; + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; + struct net_device *dev; + u8 *addr; int err; - /* Only requests are handled by kernel now */ - if (!(nlh->nlmsg_flags&NLM_F_REQUEST)) - return 0; + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; - type = nlh->nlmsg_type; + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n"); + return -EINVAL; + } - /* A control message: ignore them */ - if (type < RTM_BASE) - return 0; + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n"); + return -ENODEV; + } - /* Unknown message: reply with EINVAL */ - if (type > RTM_MAX) - goto err_inval; + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n"); + return -EINVAL; + } - type -= RTM_BASE; + addr = nla_data(tb[NDA_LLADDR]); - /* All the messages must have at least 1 byte length */ - if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg))) - return 0; + err = -EOPNOTSUPP; + + /* Support fdb on master device the net/bridge default case */ + if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && + (dev->priv_flags & IFF_BRIDGE_PORT)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; - family = ((struct rtgenmsg*)NLMSG_DATA(nlh))->rtgen_family; - if (family >= NPROTO) { - *errp = -EAFNOSUPPORT; - return -1; + err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags); + if (err) + goto out; + else + ndm->ndm_flags &= ~NTF_MASTER; } - link_tab = rtnetlink_links[family]; - if (link_tab == NULL) - link_tab = rtnetlink_links[PF_UNSPEC]; - link = &link_tab[type]; + /* Embedded bridge, macvlan, and any other device support */ + if ((ndm->ndm_flags & NTF_SELF)) { + if (dev->netdev_ops->ndo_fdb_add) + err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr, + nlh->nlmsg_flags); + else + err = ndo_dflt_fdb_add(ndm, tb, dev, addr, + nlh->nlmsg_flags); + + if (!err) { + rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH); + ndm->ndm_flags &= ~NTF_SELF; + } + } +out: + return err; +} - sz_idx = type>>2; - kind = type&3; +/** + * ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry + */ +int ndo_dflt_fdb_del(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr) +{ + int err = -EOPNOTSUPP; - if (kind != 2 && security_netlink_recv(skb)) { - *errp = -EPERM; - return -1; + /* If aging addresses are supported device will need to + * implement its own handler for this. + */ + if (!(ndm->ndm_state & NUD_PERMANENT)) { + pr_info("%s: FDB only supports static addresses\n", dev->name); + return -EINVAL; } - if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { - if (link->dumpit == NULL) - link = &(rtnetlink_links[PF_UNSPEC][type]); + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) + err = dev_uc_del(dev, addr); + else if (is_multicast_ether_addr(addr)) + err = dev_mc_del(dev, addr); + else + err = -EINVAL; - if (link->dumpit == NULL) - goto err_inval; + return err; +} +EXPORT_SYMBOL(ndo_dflt_fdb_del); + +static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; + struct net_device *dev; + int err = -EINVAL; + __u8 *addr; - if ((*errp = netlink_dump_start(rtnl, skb, nlh, - link->dumpit, NULL)) != 0) { - return -1; + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(tb[NDA_LLADDR]); + + err = -EOPNOTSUPP; + + /* Support fdb on master device the net/bridge default case */ + if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && + (dev->priv_flags & IFF_BRIDGE_PORT)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; + + if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del(ndm, tb, dev, addr); + + if (err) + goto out; + else + ndm->ndm_flags &= ~NTF_MASTER; + } + + /* Embedded bridge, macvlan, and any other device support */ + if (ndm->ndm_flags & NTF_SELF) { + if (dev->netdev_ops->ndo_fdb_del) + err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); + else + err = ndo_dflt_fdb_del(ndm, tb, dev, addr); + + if (!err) { + rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); + ndm->ndm_flags &= ~NTF_SELF; } + } +out: + return err; +} - netlink_queue_skip(nlh, skb); - return -1; +static int nlmsg_populate_fdb(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int *idx, + struct netdev_hw_addr_list *list) +{ + struct netdev_hw_addr *ha; + int err; + u32 portid, seq; + + portid = NETLINK_CB(cb->skb).portid; + seq = cb->nlh->nlmsg_seq; + + list_for_each_entry(ha, &list->list, list) { + if (*idx < cb->args[0]) + goto skip; + + err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, + portid, seq, + RTM_NEWNEIGH, NTF_SELF, + NLM_F_MULTI); + if (err < 0) + return err; +skip: + *idx += 1; } + return 0; +} + +/** + * ndo_dflt_fdb_dump - default netdevice operation to dump an FDB table. + * @nlh: netlink message header + * @dev: netdevice + * + * Default netdevice operation to dump the existing unicast address list. + * Returns number of addresses from list put in skb. + */ +int ndo_dflt_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int idx) +{ + int err; + + netif_addr_lock_bh(dev); + err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc); + if (err) + goto out; + nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); +out: + netif_addr_unlock_bh(dev); + return idx; +} +EXPORT_SYMBOL(ndo_dflt_fdb_dump); + +static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx = 0; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->priv_flags & IFF_BRIDGE_PORT) { + struct net_device *br_dev; + const struct net_device_ops *ops; + + br_dev = netdev_master_upper_dev_get(dev); + ops = br_dev->netdev_ops; + if (ops->ndo_fdb_dump) + idx = ops->ndo_fdb_dump(skb, cb, dev, idx); + } + + if (dev->netdev_ops->ndo_fdb_dump) + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx); + else + idx = ndo_dflt_fdb_dump(skb, cb, dev, idx); + } + rcu_read_unlock(); + + cb->args[0] = idx; + return skb->len; +} + +int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u16 mode) +{ + struct nlmsghdr *nlh; + struct ifinfomsg *ifm; + struct nlattr *br_afspec; + u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); + if (nlh == NULL) + return -EMSGSIZE; + + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_BRIDGE; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = 0; + + + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u8(skb, IFLA_OPERSTATE, operstate) || + (br_dev && + nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink))) + goto nla_put_failure; + + br_afspec = nla_nest_start(skb, IFLA_AF_SPEC); + if (!br_afspec) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) || + nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) { + nla_nest_cancel(skb, br_afspec); + goto nla_put_failure; + } + nla_nest_end(skb, br_afspec); + + return nlmsg_end(skb, nlh); +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} +EXPORT_SYMBOL(ndo_dflt_bridge_getlink); + +static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx = 0; + u32 portid = NETLINK_CB(cb->skb).portid; + u32 seq = cb->nlh->nlmsg_seq; + struct nlattr *extfilt; + u32 filter_mask = 0; + + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), + IFLA_EXT_MASK); + if (extfilt) + filter_mask = nla_get_u32(extfilt); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + const struct net_device_ops *ops = dev->netdev_ops; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + if (idx >= cb->args[0] && + br_dev->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev, filter_mask) < 0) + break; + idx++; + } + + if (ops->ndo_bridge_getlink) { + if (idx >= cb->args[0] && + ops->ndo_bridge_getlink(skb, portid, seq, dev, + filter_mask) < 0) + break; + idx++; + } + } + rcu_read_unlock(); + cb->args[0] = idx; + + return skb->len; +} + +static inline size_t bridge_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(sizeof(u32)) /* IFLA_MASTER */ + + nla_total_size(sizeof(u32)) /* IFLA_MTU */ + + nla_total_size(sizeof(u32)) /* IFLA_LINK */ + + nla_total_size(sizeof(u32)) /* IFLA_OPERSTATE */ + + nla_total_size(sizeof(u8)) /* IFLA_PROTINFO */ + + nla_total_size(sizeof(struct nlattr)) /* IFLA_AF_SPEC */ + + nla_total_size(sizeof(u16)) /* IFLA_BRIDGE_FLAGS */ + + nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_MODE */ +} + +static int rtnl_bridge_notify(struct net_device *dev, u16 flags) +{ + struct net *net = dev_net(dev); + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + struct sk_buff *skb; + int err = -EOPNOTSUPP; + + skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC); + if (!skb) { + err = -ENOMEM; + goto errout; + } + + if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && + br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + if (err < 0) + goto errout; + } + + if ((flags & BRIDGE_FLAGS_SELF) && + dev->netdev_ops->ndo_bridge_getlink) { + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + if (err < 0) + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); + return 0; +errout: + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); + return err; +} + +static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; - memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *))); + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; - min_len = rtm_min[sz_idx]; - if (nlh->nlmsg_len < min_len) - goto err_inval; + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; - if (nlh->nlmsg_len > min_len) { - int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); - struct rtattr *attr = (void*)nlh + NLMSG_ALIGN(min_len); + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > rta_max[sz_idx]) - goto err_inval; - rta_buf[flavor-1] = attr; + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; } - attr = RTA_NEXT(attr, attrlen); } } - if (link->doit == NULL) - link = &(rtnetlink_links[PF_UNSPEC][type]); - if (link->doit == NULL) - goto err_inval; - err = link->doit(skb, nlh, (void *)&rta_buf[0]); + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) { + err = -EOPNOTSUPP; + goto out; + } + + err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_setlink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh); - *errp = err; + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: return err; +} + +static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; + + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; -err_inval: - *errp = -EINVAL; - return -1; + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; + + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; + } + } + } + + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_dellink) { + err = -EOPNOTSUPP; + goto out; + } + + err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_dellink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: + return err; } -static void rtnetlink_rcv(struct sock *sk, int len) +/* Process one rtnetlink message. */ + +static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { - unsigned int qlen = 0; + struct net *net = sock_net(skb->sk); + rtnl_doit_func doit; + int sz_idx, kind; + int family; + int type; + int err; - do { + type = nlh->nlmsg_type; + if (type > RTM_MAX) + return -EOPNOTSUPP; + + type -= RTM_BASE; + + /* All the messages must have at least 1 byte length */ + if (nlmsg_len(nlh) < sizeof(struct rtgenmsg)) + return 0; + + family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; + sz_idx = type>>2; + kind = type&3; + + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { + struct sock *rtnl; + rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; + u16 min_dump_alloc = 0; + + dumpit = rtnl_get_dumpit(family, type); + if (dumpit == NULL) + return -EOPNOTSUPP; + calcit = rtnl_get_calcit(family, type); + if (calcit) + min_dump_alloc = calcit(skb, nlh); + + __rtnl_unlock(); + rtnl = net->rtnl; + { + struct netlink_dump_control c = { + .dump = dumpit, + .min_dump_alloc = min_dump_alloc, + }; + err = netlink_dump_start(rtnl, skb, nlh, &c); + } rtnl_lock(); - netlink_run_queue(sk, &qlen, &rtnetlink_rcv_msg); - up(&rtnl_sem); + return err; + } + + doit = rtnl_get_doit(family, type); + if (doit == NULL) + return -EOPNOTSUPP; - netdev_run_todo(); - } while (qlen); + return doit(skb, nlh); } -static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = +static void rtnetlink_rcv(struct sk_buff *skb) { - [RTM_GETLINK - RTM_BASE] = { .dumpit = rtnetlink_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, - [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, - [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, - [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, -}; + rtnl_lock(); + netlink_rcv_skb(skb, &rtnetlink_rcv_msg); + rtnl_unlock(); +} static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + switch (event) { - case NETDEV_UNREGISTER: - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); - break; - case NETDEV_REGISTER: - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); - break; case NETDEV_UP: case NETDEV_DOWN: - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); - break; + case NETDEV_PRE_UP: + case NETDEV_POST_INIT: + case NETDEV_REGISTER: case NETDEV_CHANGE: + case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: + case NETDEV_UNREGISTER: + case NETDEV_UNREGISTER_FINAL: + case NETDEV_RELEASE: + case NETDEV_JOIN: break; default: - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); break; } return NOTIFY_DONE; @@ -625,35 +2934,57 @@ static struct notifier_block rtnetlink_dev_notifier = { .notifier_call = rtnetlink_event, }; -void __init rtnetlink_init(void) + +static int __net_init rtnetlink_net_init(struct net *net) { - int i; + struct sock *sk; + struct netlink_kernel_cfg cfg = { + .groups = RTNLGRP_MAX, + .input = rtnetlink_rcv, + .cb_mutex = &rtnl_mutex, + .flags = NL_CFG_F_NONROOT_RECV, + }; + + sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg); + if (!sk) + return -ENOMEM; + net->rtnl = sk; + return 0; +} - rtattr_max = 0; - for (i = 0; i < ARRAY_SIZE(rta_max); i++) - if (rta_max[i] > rtattr_max) - rtattr_max = rta_max[i]; - rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL); - if (!rta_buf) - panic("rtnetlink_init: cannot allocate rta_buf\n"); +static void __net_exit rtnetlink_net_exit(struct net *net) +{ + netlink_kernel_release(net->rtnl); + net->rtnl = NULL; +} - rtnl = netlink_kernel_create(NETLINK_ROUTE, RTNLGRP_MAX, rtnetlink_rcv, - THIS_MODULE); - if (rtnl == NULL) +static struct pernet_operations rtnetlink_net_ops = { + .init = rtnetlink_net_init, + .exit = rtnetlink_net_exit, +}; + +void __init rtnetlink_init(void) +{ + if (register_pernet_subsys(&rtnetlink_net_ops)) panic("rtnetlink_init: cannot initialize rtnetlink\n"); - netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV); + register_netdevice_notifier(&rtnetlink_dev_notifier); - rtnetlink_links[PF_UNSPEC] = link_rtnetlink_table; - rtnetlink_links[PF_PACKET] = link_rtnetlink_table; + + rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, + rtnl_dump_ifinfo, rtnl_calcit); + rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL); + + rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); + rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); + + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); + + rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL); + rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } -EXPORT_SYMBOL(__rta_fill); -EXPORT_SYMBOL(rtattr_strlcpy); -EXPORT_SYMBOL(rtattr_parse); -EXPORT_SYMBOL(rtnetlink_links); -EXPORT_SYMBOL(rtnetlink_put_metrics); -EXPORT_SYMBOL(rtnl); -EXPORT_SYMBOL(rtnl_lock); -EXPORT_SYMBOL(rtnl_lock_interruptible); -EXPORT_SYMBOL(rtnl_sem); -EXPORT_SYMBOL(rtnl_unlock); diff --git a/net/core/scm.c b/net/core/scm.c index 649d01ef35b..b442e7e25e6 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -24,8 +24,11 @@ #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/security.h> +#include <linux/pid_namespace.h> +#include <linux/pid.h> +#include <linux/nsproxy.h> +#include <linux/slab.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <net/protocol.h> @@ -33,20 +36,29 @@ #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> +#include <net/cls_cgroup.h> /* - * Only allow a user to send credentials, that they could set with + * Only allow a user to send credentials, that they could set with * setu(g)id. */ static __inline__ int scm_check_creds(struct ucred *creds) { - if ((creds->pid == current->tgid || capable(CAP_SYS_ADMIN)) && - ((creds->uid == current->uid || creds->uid == current->euid || - creds->uid == current->suid) || capable(CAP_SETUID)) && - ((creds->gid == current->gid || creds->gid == current->egid || - creds->gid == current->sgid) || capable(CAP_SETGID))) { + const struct cred *cred = current_cred(); + kuid_t uid = make_kuid(cred->user_ns, creds->uid); + kgid_t gid = make_kgid(cred->user_ns, creds->gid); + + if (!uid_valid(uid) || !gid_valid(gid)) + return -EINVAL; + + if ((creds->pid == task_tgid_vnr(current) || + ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && + ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || + uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) && + ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || + gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) { return 0; } return -EPERM; @@ -74,22 +86,23 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) return -ENOMEM; *fplp = fpl; fpl->count = 0; + fpl->max = SCM_MAX_FD; } fpp = &fpl->fp[fpl->count]; - if (fpl->count + num > SCM_MAX_FD) + if (fpl->count + num > fpl->max) return -EINVAL; - + /* * Verify the descriptors and increment the usage count. */ - + for (i=0; i< num; i++) { int fd = fdp[i]; struct file *file; - if (fd < 0 || !(file = fget(fd))) + if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; *fpp++ = file; fpl->count++; @@ -109,6 +122,7 @@ void __scm_destroy(struct scm_cookie *scm) kfree(fpl); } } +EXPORT_SYMBOL(__scm_destroy); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) { @@ -123,7 +137,7 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) /* The first check was omitted in <= 2.2.5. The reasoning was that parser checks cmsg_len in any case, so that additional check would be work duplication. - But if cmsg_level is not SOL_SOCKET, we do not check + But if cmsg_level is not SOL_SOCKET, we do not check for too short ancillary data object at all! Oops. OK, let's add it... */ @@ -136,18 +150,45 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) switch (cmsg->cmsg_type) { case SCM_RIGHTS: + if (!sock->ops || sock->ops->family != PF_UNIX) + goto error; err=scm_fp_copy(cmsg, &p->fp); if (err<0) goto error; break; case SCM_CREDENTIALS: + { + struct ucred creds; + kuid_t uid; + kgid_t gid; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred))) goto error; - memcpy(&p->creds, CMSG_DATA(cmsg), sizeof(struct ucred)); - err = scm_check_creds(&p->creds); + memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred)); + err = scm_check_creds(&creds); if (err) goto error; + + p->creds.pid = creds.pid; + if (!p->pid || pid_vnr(p->pid) != creds.pid) { + struct pid *pid; + err = -ESRCH; + pid = find_get_pid(creds.pid); + if (!pid) + goto error; + put_pid(p->pid); + p->pid = pid; + } + + err = -EINVAL; + uid = make_kuid(current_user_ns(), creds.uid); + gid = make_kgid(current_user_ns(), creds.gid); + if (!uid_valid(uid) || !gid_valid(gid)) + goto error; + + p->creds.uid = uid; + p->creds.gid = gid; break; + } default: goto error; } @@ -159,15 +200,17 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->fp = NULL; } return 0; - + error: scm_destroy(p); return err; } +EXPORT_SYMBOL(__scm_send); int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) { - struct cmsghdr __user *cm = (struct cmsghdr __user *)msg->msg_control; + struct cmsghdr __user *cm + = (__force struct cmsghdr __user *)msg->msg_control; struct cmsghdr cmhdr; int cmlen = CMSG_LEN(len); int err; @@ -189,20 +232,24 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) err = -EFAULT; if (copy_to_user(cm, &cmhdr, sizeof cmhdr)) - goto out; + goto out; if (copy_to_user(CMSG_DATA(cm), data, cmlen - sizeof(struct cmsghdr))) goto out; cmlen = CMSG_SPACE(len); + if (msg->msg_controllen < cmlen) + cmlen = msg->msg_controllen; msg->msg_control += cmlen; msg->msg_controllen -= cmlen; err = 0; out: return err; } +EXPORT_SYMBOL(put_cmsg); void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { - struct cmsghdr __user *cm = (struct cmsghdr __user*)msg->msg_control; + struct cmsghdr __user *cm + = (__force struct cmsghdr __user*)msg->msg_control; int fdmax = 0; int fdnum = scm->fp->count; @@ -222,13 +269,16 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) if (fdnum < fdmax) fdmax = fdnum; - for (i=0, cmfptr=(int __user *)CMSG_DATA(cm); i<fdmax; i++, cmfptr++) + for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax; + i++, cmfptr++) { + struct socket *sock; int new_fd; err = security_file_receive(fp[i]); if (err) break; - err = get_unused_fd(); + err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & msg->msg_flags + ? O_CLOEXEC : 0); if (err < 0) break; new_fd = err; @@ -238,15 +288,18 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ - get_file(fp[i]); - fd_install(new_fd, fp[i]); + sock = sock_from_file(fp[i], &err); + if (sock) { + sock_update_netprioidx(sock->sk); + sock_update_classid(sock->sk); + } + fd_install(new_fd, get_file(fp[i])); } if (i > 0) { int cmlen = CMSG_LEN(i*sizeof(int)); - if (!err) - err = put_user(SOL_SOCKET, &cm->cmsg_level); + err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) @@ -266,6 +319,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) */ __scm_destroy(scm); } +EXPORT_SYMBOL(scm_detach_fds); struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) { @@ -275,17 +329,13 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) if (!fpl) return NULL; - new_fpl = kmalloc(sizeof(*fpl), GFP_KERNEL); + new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]), + GFP_KERNEL); if (new_fpl) { - for (i=fpl->count-1; i>=0; i--) + for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); - memcpy(new_fpl, fpl, sizeof(*fpl)); + new_fpl->max = new_fpl->count; } return new_fpl; } - -EXPORT_SYMBOL(__scm_destroy); -EXPORT_SYMBOL(__scm_send); -EXPORT_SYMBOL(put_cmsg); -EXPORT_SYMBOL(scm_detach_fds); EXPORT_SYMBOL(scm_fp_dup); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c new file mode 100644 index 00000000000..ba71212f025 --- /dev/null +++ b/net/core/secure_seq.c @@ -0,0 +1,173 @@ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/cryptohash.h> +#include <linux/module.h> +#include <linux/cache.h> +#include <linux/random.h> +#include <linux/hrtimer.h> +#include <linux/ktime.h> +#include <linux/string.h> +#include <linux/net.h> + +#include <net/secure_seq.h> + +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) +#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) + +static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; + +static __always_inline void net_secret_init(void) +{ + net_get_random_once(net_secret, sizeof(net_secret)); +} +#endif + +#ifdef CONFIG_INET +static u32 seq_scale(u32 seq) +{ + /* + * As close as possible to RFC 793, which + * suggests using a 250 kHz clock. + * Further reading shows this assumes 2 Mb/s networks. + * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. + * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but + * we also need to limit the resolution so that the u32 seq + * overlaps less than one time per MSL (2 minutes). + * Choosing a clock of 64 ns period is OK. (period of 274 s) + */ + return seq + (ktime_to_ns(ktime_get_real()) >> 6); +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + net_secret_init(); + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32)daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return seq_scale(hash[0]); +} +EXPORT_SYMBOL(secure_tcpv6_sequence_number); + +u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + net_secret_init(); + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32) daddr[i]; + secret[4] = net_secret[4] + (__force u32)dport; + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return hash[0]; +} +EXPORT_SYMBOL(secure_ipv6_port_ephemeral); +#endif + +#ifdef CONFIG_INET + +__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + net_secret_init(); + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return seq_scale(hash[0]); +} + +u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + net_secret_init(); + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = (__force u32)dport ^ net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} +EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); +#endif + +#if IS_ENABLED(CONFIG_IP_DCCP) +u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + + net_secret_init(); + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccp_sequence_number); + +#if IS_ENABLED(CONFIG_IPV6) +u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + u32 i; + + net_secret_init(); + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccpv6_sequence_number); +#endif +#endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d0732e9c856..c1a33033cbe 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1,11 +1,9 @@ /* * Routines having to do with the 'struct sk_buff' memory handlers. * - * Authors: Alan Cox <iiitac@pyr.swan.ac.uk> + * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Florian La Roche <rzsfl@rz.uni-sb.de> * - * Version: $Id: skbuff.c,v 1.90 2001/11/07 05:56:19 davem Exp $ - * * Fixes: * Alan Cox : Fixed the worst of the load * balancer bugs. @@ -38,78 +36,114 @@ * The functions in this file will not compile correctly with gcc 2.4.x */ -#include <linux/config.h> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> -#include <linux/sched.h> +#include <linux/kmemcheck.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> #endif #include <linux/string.h> #include <linux/skbuff.h> +#include <linux/splice.h> #include <linux/cache.h> #include <linux/rtnetlink.h> #include <linux/init.h> -#include <linux/highmem.h> +#include <linux/scatterlist.h> +#include <linux/errqueue.h> +#include <linux/prefetch.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/ip6_checksum.h> #include <net/xfrm.h> #include <asm/uaccess.h> -#include <asm/system.h> - -static kmem_cache_t *skbuff_head_cache __read_mostly; -static kmem_cache_t *skbuff_fclone_cache __read_mostly; +#include <trace/events/skb.h> +#include <linux/highmem.h> -/* - * Keep out-of-line to prevent kernel bloat. - * __builtin_return_address is not used because it is not always - * reliable. - */ +struct kmem_cache *skbuff_head_cache __read_mostly; +static struct kmem_cache *skbuff_fclone_cache __read_mostly; /** - * skb_over_panic - private function - * @skb: buffer - * @sz: size - * @here: address + * skb_panic - private function for out-of-line support + * @skb: buffer + * @sz: size + * @addr: address + * @msg: skb_over_panic or skb_under_panic * - * Out of line support code for skb_put(). Not user callable. + * Out-of-line support for skb_put() and skb_push(). + * Called via the wrapper skb_over_panic() or skb_under_panic(). + * Keep out of line to prevent kernel bloat. + * __builtin_return_address is not used because it is not always reliable. */ -void skb_over_panic(struct sk_buff *skb, int sz, void *here) +static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, + const char msg[]) { - printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%p end:%p dev:%s\n", - here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end, - skb->dev ? skb->dev->name : "<NULL>"); + pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", + msg, addr, skb->len, sz, skb->head, skb->data, + (unsigned long)skb->tail, (unsigned long)skb->end, + skb->dev ? skb->dev->name : "<NULL>"); BUG(); } -/** - * skb_under_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_push(). Not user callable. +static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) +{ + skb_panic(skb, sz, addr, __func__); +} + +static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) +{ + skb_panic(skb, sz, addr, __func__); +} + +/* + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free */ +#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ + __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) -void skb_under_panic(struct sk_buff *skb, int sz, void *here) +static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, + unsigned long ip, bool *pfmemalloc) { - printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%p end:%p dev:%s\n", - here, skb->len, sz, skb->head, skb->data, skb->tail, skb->end, - skb->dev ? skb->dev->name : "<NULL>"); - BUG(); + void *obj; + bool ret_pfmemalloc = false; + + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; + + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few @@ -118,150 +152,343 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) * */ +struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node) +{ + struct sk_buff *skb; + + /* Get the HEAD */ + skb = kmem_cache_alloc_node(skbuff_head_cache, + gfp_mask & ~__GFP_DMA, node); + if (!skb) + goto out; + + /* + * Only clear those fields we need to clear, not those that we will + * actually initialise below. Hence, don't put any more fields after + * the tail pointer in struct sk_buff! + */ + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->head = NULL; + skb->truesize = sizeof(struct sk_buff); + atomic_set(&skb->users, 1); + + skb->mac_header = (typeof(skb->mac_header))~0U; +out: + return skb; +} + /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask - * @fclone: allocate from fclone cache instead of head cache - * and allocate a cloned (child) skb + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback + * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a - * tail room of size bytes. The object has a reference count of one. - * The return is the buffer. On a failure the return is %NULL. + * tail room of at least size bytes. The object has a reference count + * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int fclone) + int flags, int node) { + struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + bool pfmemalloc; + + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; + + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ - skb = kmem_cache_alloc(fclone ? skbuff_fclone_cache : skbuff_head_cache, - gfp_mask & ~__GFP_DMA); + skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); if (!skb) goto out; + prefetchw(skb); - /* Get the DATA. Size must match skb_add_mtu(). */ + /* We do our best to align skb_shared_info on a separate cache + * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives + * aligned memory blocks, unless SLUB/SLAB debug is enabled. + * Both skb->head and skb_shared_info are cache line aligned. + */ size = SKB_DATA_ALIGN(size); - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; + /* kmalloc(size) might give us more room than requested. + * Put skb_shared_info exactly at the end of allocated zone, + * to allow max possible filling before reallocation. + */ + size = SKB_WITH_OVERHEAD(ksize(data)); + prefetchw(data + size); - memset(skb, 0, offsetof(struct sk_buff, truesize)); - skb->truesize = size + sizeof(struct sk_buff); + /* + * Only clear those fields we need to clear, not those that we will + * actually initialise below. Hence, don't put any more fields after + * the tail pointer in struct sk_buff! + */ + memset(skb, 0, offsetof(struct sk_buff, tail)); + /* Account for allocated memory : skb + skb->head */ + skb->truesize = SKB_TRUESIZE(size); + skb->pfmemalloc = pfmemalloc; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; - skb->tail = data; - skb->end = data + size; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; + /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); 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) { + kmemcheck_annotate_variable(shinfo->destructor_arg); + + if (flags & SKB_ALLOC_FCLONE) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); + kmemcheck_annotate_bitfield(child, flags1); + kmemcheck_annotate_bitfield(child, flags2); skb->fclone = SKB_FCLONE_ORIG; atomic_set(fclone_ref, 1); child->fclone = SKB_FCLONE_UNAVAILABLE; + child->pfmemalloc = pfmemalloc; } out: return skb; nodata: - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(cache, skb); skb = NULL; goto out; } +EXPORT_SYMBOL(__alloc_skb); /** - * alloc_skb_from_cache - allocate a network buffer - * @cp: kmem_cache from which to allocate the data area - * (object size must be big enough for @size bytes + skb overheads) - * @size: size to allocate - * @gfp_mask: allocation mask - * - * Allocate a new &sk_buff. The returned buffer has no headroom and - * tail room of size bytes. The object has a reference count of one. - * The return is the buffer. On a failure the return is %NULL. + * build_skb - build a network buffer + * @data: data buffer provided by caller + * @frag_size: size of fragment, or 0 if head was kmalloced * - * Buffers may only be allocated from interrupts using a @gfp_mask of - * %GFP_ATOMIC. + * Allocate a new &sk_buff. Caller provides space holding head and + * skb_shared_info. @data must have been allocated by kmalloc() only if + * @frag_size is 0, otherwise data should come from the page allocator. + * The return is the new skb buffer. + * On a failure the return is %NULL, and @data is not freed. + * Notes : + * Before IO, driver allocates only data buffer where NIC put incoming frame + * Driver should add room at head (NET_SKB_PAD) and + * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) + * After IO, driver calls build_skb(), to allocate sk_buff and populate it + * before giving packet to stack. + * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, - unsigned int size, - gfp_t gfp_mask) +struct sk_buff *build_skb(void *data, unsigned int frag_size) { + struct skb_shared_info *shinfo; struct sk_buff *skb; - u8 *data; + unsigned int size = frag_size ? : ksize(data); - /* Get the HEAD */ - skb = kmem_cache_alloc(skbuff_head_cache, - gfp_mask & ~__GFP_DMA); + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); if (!skb) - goto out; + return NULL; - /* Get the DATA. */ - size = SKB_DATA_ALIGN(size); - data = kmem_cache_alloc(cp, gfp_mask); - if (!data) - goto nodata; + size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - memset(skb, 0, offsetof(struct sk_buff, truesize)); - skb->truesize = size + sizeof(struct sk_buff); + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->truesize = SKB_TRUESIZE(size); + skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; - skb->tail = data; - skb->end = data + size; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; + + /* make sure we initialize shinfo sequentially */ + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); + atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); - 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; -out: return skb; -nodata: - kmem_cache_free(skbuff_head_cache, skb); - skb = NULL; - goto out; } +EXPORT_SYMBOL(build_skb); +struct netdev_alloc_cache { + struct page_frag frag; + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_count every time we allocate a fragment. + */ + unsigned int pagecnt_bias; +}; +static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -static void skb_drop_fraglist(struct sk_buff *skb) +static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + struct netdev_alloc_cache *nc; + void *data = NULL; + int order; + unsigned long flags; - skb_shinfo(skb)->frag_list = NULL; + local_irq_save(flags); + nc = &__get_cpu_var(netdev_alloc_cache); + if (unlikely(!nc->frag.page)) { +refill: + for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) { + gfp_t gfp = gfp_mask; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN; + nc->frag.page = alloc_pages(gfp, order); + if (likely(nc->frag.page)) + break; + if (--order < 0) + goto end; + } + nc->frag.size = PAGE_SIZE << order; +recycle: + atomic_set(&nc->frag.page->_count, NETDEV_PAGECNT_MAX_BIAS); + nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS; + nc->frag.offset = 0; + } - do { - struct sk_buff *this = list; - list = list->next; - kfree_skb(this); - } while (list); + if (nc->frag.offset + fragsz > nc->frag.size) { + /* avoid unnecessary locked operations if possible */ + if ((atomic_read(&nc->frag.page->_count) == nc->pagecnt_bias) || + atomic_sub_and_test(nc->pagecnt_bias, &nc->frag.page->_count)) + goto recycle; + goto refill; + } + + data = page_address(nc->frag.page) + nc->frag.offset; + nc->frag.offset += fragsz; + nc->pagecnt_bias--; +end: + local_irq_restore(flags); + return data; +} + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); +} +EXPORT_SYMBOL(netdev_alloc_frag); + +/** + * __netdev_alloc_skb - allocate an skbuff for rx on a specific device + * @dev: network device to receive on + * @length: length to allocate + * @gfp_mask: get_free_pages mask, passed to alloc_skb + * + * Allocate a new &sk_buff and assign it a usage count of one. The + * buffer has unspecified headroom built in. Users should allocate + * the headroom they think they need without accounting for the + * built in space. The built in space is used for optimisations. + * + * %NULL is returned if there is no free memory. + */ +struct sk_buff *__netdev_alloc_skb(struct net_device *dev, + unsigned int length, gfp_t gfp_mask) +{ + struct sk_buff *skb = NULL; + unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { + void *data; + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __netdev_alloc_frag(fragsz, gfp_mask); + + if (likely(data)) { + skb = build_skb(data, fragsz); + if (unlikely(!skb)) + put_page(virt_to_head_page(data)); + } + } else { + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, + SKB_ALLOC_RX, NUMA_NO_NODE); + } + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; + } + return skb; +} +EXPORT_SYMBOL(__netdev_alloc_skb); + +void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, + int size, unsigned int truesize) +{ + skb_fill_page_desc(skb, i, page, off, size); + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; +} +EXPORT_SYMBOL(skb_add_rx_frag); + +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, + unsigned int truesize) +{ + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + skb_frag_size_add(frag, size); + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; +} +EXPORT_SYMBOL(skb_coalesce_rx_frag); + +static void skb_drop_list(struct sk_buff **listp) +{ + kfree_skb_list(*listp); + *listp = NULL; +} + +static inline void skb_drop_fraglist(struct sk_buff *skb) +{ + skb_drop_list(&skb_shinfo(skb)->frag_list); } static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; - for (list = skb_shinfo(skb)->frag_list; list; list = list->next) + skb_walk_frags(skb, list) skb_get(list); } -void skb_release_data(struct sk_buff *skb) +static void skb_free_head(struct sk_buff *skb) +{ + if (skb->head_frag) + put_page(virt_to_head_page(skb->head)); + else + kfree(skb->head); +} + +static void skb_release_data(struct sk_buff *skb) { if (!skb->cloned || !atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, @@ -269,25 +496,36 @@ void skb_release_data(struct sk_buff *skb) if (skb_shinfo(skb)->nr_frags) { int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); + } + + /* + * If skb buf is from userspace, we need to notify the caller + * the lower device DMA has done; + */ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + struct ubuf_info *uarg; + + uarg = skb_shinfo(skb)->destructor_arg; + if (uarg->callback) + uarg->callback(uarg, true); } - if (skb_shinfo(skb)->frag_list) + if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); - kfree(skb->head); + skb_free_head(skb); } } /* * Free an skbuff by memory without cleaning the state. */ -void kfree_skbmem(struct sk_buff *skb) +static void kfree_skbmem(struct sk_buff *skb) { struct sk_buff *other; atomic_t *fclone_ref; - skb_release_data(skb); switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: kmem_cache_free(skbuff_head_cache, skb); @@ -311,21 +549,12 @@ void kfree_skbmem(struct sk_buff *skb) if (atomic_dec_and_test(fclone_ref)) kmem_cache_free(skbuff_fclone_cache, other); break; - }; + } } -/** - * __kfree_skb - private function - * @skb: buffer - * - * Free an sk_buff. Release anything attached to the buffer. - * Clean the state. This is an internal helper function. Users should - * always call kfree_skb - */ - -void __kfree_skb(struct sk_buff *skb) +static void skb_release_head_state(struct sk_buff *skb) { - dst_release(skb->dst); + skb_dst_drop(skb); #ifdef CONFIG_XFRM secpath_put(skb->sp); #endif @@ -333,15 +562,12 @@ void __kfree_skb(struct sk_buff *skb) WARN_ON(in_irq()); skb->destructor(skb); } -#ifdef CONFIG_NETFILTER +#if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb->nfct); -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - nf_conntrack_put_reasm(skb->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); #endif -#endif /* XXX: IS this still necessary? - JHS */ #ifdef CONFIG_NET_SCHED skb->tc_index = 0; @@ -349,9 +575,268 @@ void __kfree_skb(struct sk_buff *skb) skb->tc_verd = 0; #endif #endif +} + +/* Free everything but the sk_buff shell. */ +static void skb_release_all(struct sk_buff *skb) +{ + skb_release_head_state(skb); + if (likely(skb->head)) + skb_release_data(skb); +} + +/** + * __kfree_skb - private function + * @skb: buffer + * + * Free an sk_buff. Release anything attached to the buffer. + * Clean the state. This is an internal helper function. Users should + * always call kfree_skb + */ +void __kfree_skb(struct sk_buff *skb) +{ + skb_release_all(skb); kfree_skbmem(skb); } +EXPORT_SYMBOL(__kfree_skb); + +/** + * kfree_skb - free an sk_buff + * @skb: buffer to free + * + * Drop a reference to the buffer and free it if the usage count has + * hit zero. + */ +void kfree_skb(struct sk_buff *skb) +{ + if (unlikely(!skb)) + return; + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + trace_kfree_skb(skb, __builtin_return_address(0)); + __kfree_skb(skb); +} +EXPORT_SYMBOL(kfree_skb); + +void kfree_skb_list(struct sk_buff *segs) +{ + while (segs) { + struct sk_buff *next = segs->next; + + kfree_skb(segs); + segs = next; + } +} +EXPORT_SYMBOL(kfree_skb_list); + +/** + * skb_tx_error - report an sk_buff xmit error + * @skb: buffer that triggered an error + * + * Report xmit error if a device callback is tracking this skb. + * skb must be freed afterwards. + */ +void skb_tx_error(struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + struct ubuf_info *uarg; + + uarg = skb_shinfo(skb)->destructor_arg; + if (uarg->callback) + uarg->callback(uarg, false); + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + } +} +EXPORT_SYMBOL(skb_tx_error); + +/** + * consume_skb - free an skbuff + * @skb: buffer to free + * + * Drop a ref to the buffer and free it if the usage count has hit zero + * Functions identically to kfree_skb, but kfree_skb assumes that the frame + * is being dropped after a failure and notes that + */ +void consume_skb(struct sk_buff *skb) +{ + if (unlikely(!skb)) + return; + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + trace_consume_skb(skb); + __kfree_skb(skb); +} +EXPORT_SYMBOL(consume_skb); + +static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +{ + new->tstamp = old->tstamp; + new->dev = old->dev; + new->transport_header = old->transport_header; + new->network_header = old->network_header; + new->mac_header = old->mac_header; + new->inner_protocol = old->inner_protocol; + new->inner_transport_header = old->inner_transport_header; + new->inner_network_header = old->inner_network_header; + new->inner_mac_header = old->inner_mac_header; + skb_dst_copy(new, old); + skb_copy_hash(new, old); + new->ooo_okay = old->ooo_okay; + new->no_fcs = old->no_fcs; + new->encapsulation = old->encapsulation; + new->encap_hdr_csum = old->encap_hdr_csum; + new->csum_valid = old->csum_valid; + new->csum_complete_sw = old->csum_complete_sw; +#ifdef CONFIG_XFRM + new->sp = secpath_get(old->sp); +#endif + memcpy(new->cb, old->cb, sizeof(old->cb)); + new->csum = old->csum; + new->ignore_df = old->ignore_df; + new->pkt_type = old->pkt_type; + new->ip_summed = old->ip_summed; + skb_copy_queue_mapping(new, old); + new->priority = old->priority; +#if IS_ENABLED(CONFIG_IP_VS) + new->ipvs_property = old->ipvs_property; +#endif + new->pfmemalloc = old->pfmemalloc; + new->protocol = old->protocol; + new->mark = old->mark; + new->skb_iif = old->skb_iif; + __nf_copy(new, old); +#ifdef CONFIG_NET_SCHED + new->tc_index = old->tc_index; +#ifdef CONFIG_NET_CLS_ACT + new->tc_verd = old->tc_verd; +#endif +#endif + new->vlan_proto = old->vlan_proto; + new->vlan_tci = old->vlan_tci; + + skb_copy_secmark(new, old); + +#ifdef CONFIG_NET_RX_BUSY_POLL + new->napi_id = old->napi_id; +#endif +} + +/* + * You should not add any new code to this function. Add it to + * __copy_skb_header above instead. + */ +static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) +{ +#define C(x) n->x = skb->x + + n->next = n->prev = NULL; + n->sk = NULL; + __copy_skb_header(n, skb); + + C(len); + C(data_len); + C(mac_len); + n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; + n->cloned = 1; + n->nohdr = 0; + n->destructor = NULL; + C(tail); + C(end); + C(head); + C(head_frag); + C(data); + C(truesize); + atomic_set(&n->users, 1); + + atomic_inc(&(skb_shinfo(skb)->dataref)); + skb->cloned = 1; + + return n; +#undef C +} + +/** + * skb_morph - morph one skb into another + * @dst: the skb to receive the contents + * @src: the skb to supply the contents + * + * This is identical to skb_clone except that the target skb is + * supplied by the user. + * + * The target skb is returned upon exit. + */ +struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) +{ + skb_release_all(dst); + return __skb_clone(dst, src); +} +EXPORT_SYMBOL_GPL(skb_morph); + +/** + * skb_copy_ubufs - copy userspace skb frags buffers to kernel + * @skb: the skb to modify + * @gfp_mask: allocation priority + * + * This must be called on SKBTX_DEV_ZEROCOPY skb. + * It will copy all frags into kernel and drop the reference + * to userspace pages. + * + * If this function is called from an interrupt gfp_mask() must be + * %GFP_ATOMIC. + * + * Returns 0 on success or a negative error code on failure + * to allocate kernel memory to copy to. + */ +int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) +{ + int i; + int num_frags = skb_shinfo(skb)->nr_frags; + struct page *page, *head = NULL; + struct ubuf_info *uarg = skb_shinfo(skb)->destructor_arg; + + for (i = 0; i < num_frags; i++) { + u8 *vaddr; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; + + page = alloc_page(gfp_mask); + if (!page) { + while (head) { + struct page *next = (struct page *)page_private(head); + put_page(head); + head = next; + } + return -ENOMEM; + } + vaddr = kmap_atomic(skb_frag_page(f)); + memcpy(page_address(page), + vaddr + f->page_offset, skb_frag_size(f)); + kunmap_atomic(vaddr); + set_page_private(page, (unsigned long)head); + head = page; + } + + /* skb frags release userspace buffers */ + for (i = 0; i < num_frags; i++) + skb_frag_unref(skb, i); + + uarg->callback(uarg, false); + + /* skb frags point to kernel buffers */ + for (i = num_frags - 1; i >= 0; i--) { + __skb_fill_page_desc(skb, i, head, 0, + skb_shinfo(skb)->frags[i].size); + head = (struct page *)page_private(head); + } + + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + return 0; +} +EXPORT_SYMBOL_GPL(skb_copy_ubufs); /** * skb_clone - duplicate an sk_buff @@ -371,6 +856,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; + if (skb_orphan_frags(skb, gfp_mask)) + return NULL; + n = skb + 1; if (skb->fclone == SKB_FCLONE_ORIG && n->fclone == SKB_FCLONE_UNAVAILABLE) { @@ -378,133 +866,51 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->fclone = SKB_FCLONE_CLONE; atomic_inc(fclone_ref); } else { + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; + + kmemcheck_annotate_bitfield(n, flags1); + kmemcheck_annotate_bitfield(n, flags2); n->fclone = SKB_FCLONE_UNAVAILABLE; } -#define C(x) n->x = skb->x - - n->next = n->prev = NULL; - n->sk = NULL; - C(tstamp); - C(dev); - C(h); - C(nh); - C(mac); - C(dst); - dst_clone(skb->dst); - C(sp); -#ifdef CONFIG_INET - secpath_get(skb->sp); -#endif - memcpy(n->cb, skb->cb, sizeof(skb->cb)); - C(len); - C(data_len); - C(csum); - C(local_df); - n->cloned = 1; - n->nohdr = 0; - C(pkt_type); - C(ip_summed); - C(priority); - C(protocol); - n->destructor = NULL; -#ifdef CONFIG_NETFILTER - C(nfmark); - C(nfct); - nf_conntrack_get(skb->nfct); - C(nfctinfo); -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - C(nfct_reasm); - nf_conntrack_get_reasm(skb->nfct_reasm); -#endif -#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) - C(ipvs_property); -#endif -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - C(nfct_reasm); - nf_conntrack_get_reasm(skb->nfct_reasm); -#endif -#ifdef CONFIG_BRIDGE_NETFILTER - C(nf_bridge); - nf_bridge_get(skb->nf_bridge); -#endif -#endif /*CONFIG_NETFILTER*/ -#ifdef CONFIG_NET_SCHED - C(tc_index); -#ifdef CONFIG_NET_CLS_ACT - n->tc_verd = SET_TC_VERD(skb->tc_verd,0); - n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd); - n->tc_verd = CLR_TC_MUNGED(n->tc_verd); - C(input_dev); -#endif + return __skb_clone(n, skb); +} +EXPORT_SYMBOL(skb_clone); -#endif - C(truesize); - atomic_set(&n->users, 1); - C(head); - C(data); - C(tail); - C(end); +static void skb_headers_offset_update(struct sk_buff *skb, int off) +{ + /* Only adjust this if it actually is csum_start rather than csum */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb->csum_start += off; + /* {transport,network,mac}_header and tail are relative to skb->head */ + skb->transport_header += off; + skb->network_header += off; + if (skb_mac_header_was_set(skb)) + skb->mac_header += off; + skb->inner_transport_header += off; + skb->inner_network_header += off; + skb->inner_mac_header += off; +} - atomic_inc(&(skb_shinfo(skb)->dataref)); - skb->cloned = 1; +static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +{ + __copy_skb_header(new, old); - return n; + skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; + skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; + skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } -static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { - /* - * Shift between the two data areas in bytes - */ - unsigned long offset = new->data - old->data; - - new->sk = NULL; - new->dev = old->dev; - new->priority = old->priority; - new->protocol = old->protocol; - new->dst = dst_clone(old->dst); -#ifdef CONFIG_INET - new->sp = secpath_get(old->sp); -#endif - new->h.raw = old->h.raw + offset; - new->nh.raw = old->nh.raw + offset; - new->mac.raw = old->mac.raw + offset; - memcpy(new->cb, old->cb, sizeof(old->cb)); - new->local_df = old->local_df; - new->fclone = SKB_FCLONE_UNAVAILABLE; - new->pkt_type = old->pkt_type; - new->tstamp = old->tstamp; - new->destructor = NULL; -#ifdef CONFIG_NETFILTER - new->nfmark = old->nfmark; - new->nfct = old->nfct; - nf_conntrack_get(old->nfct); - new->nfctinfo = old->nfctinfo; -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) - new->nfct_reasm = old->nfct_reasm; - nf_conntrack_get_reasm(old->nfct_reasm); -#endif -#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) - new->ipvs_property = old->ipvs_property; -#endif -#ifdef CONFIG_BRIDGE_NETFILTER - new->nf_bridge = old->nf_bridge; - nf_bridge_get(old->nf_bridge); -#endif -#endif -#ifdef CONFIG_NET_SCHED -#ifdef CONFIG_NET_CLS_ACT - new->tc_verd = old->tc_verd; -#endif - new->tc_index = old->tc_index; -#endif - atomic_set(&new->users, 1); - skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size; - skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs; + if (skb_pfmemalloc(skb)) + return SKB_ALLOC_RX; + return 0; } /** @@ -526,12 +932,11 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb->data - skb->head; - /* - * Allocate the copy buffer - */ - struct sk_buff *n = alloc_skb(skb->end - skb->head + skb->data_len, - gfp_mask); + int headerlen = skb_headroom(skb); + unsigned int size = skb_end_offset(skb) + skb->data_len; + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); + if (!n) return NULL; @@ -539,8 +944,6 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) skb_reserve(n, headerlen); /* Set the tail pointer and length */ skb_put(n, skb->len); - n->csum = skb->csum; - n->ip_summed = skb->ip_summed; if (skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)) BUG(); @@ -548,12 +951,16 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) copy_skb_header(n, skb); return n; } - +EXPORT_SYMBOL(skb_copy); /** - * pskb_copy - create copy of an sk_buff with private head. + * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy + * @headroom: headroom of new skb * @gfp_mask: allocation priority + * @fclone: if true allocate the copy of the skb from the fclone + * cache instead of the head cache; it is recommended to set this + * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when @@ -563,39 +970,43 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) * The returned buffer has a reference count of 1. */ -struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) +struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, + gfp_t gfp_mask, bool fclone) { - /* - * Allocate the copy buffer - */ - struct sk_buff *n = alloc_skb(skb->end - skb->head, gfp_mask); + unsigned int size = skb_headlen(skb) + headroom; + int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); + struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ - skb_reserve(n, skb->data - skb->head); + skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ - memcpy(n->data, skb->data, n->len); - n->csum = skb->csum; - n->ip_summed = skb->ip_summed; + skb_copy_from_linear_data(skb, n->data, n->len); + n->truesize += skb->data_len; n->data_len = skb->data_len; n->len = skb->len; if (skb_shinfo(skb)->nr_frags) { int i; + if (skb_orphan_frags(skb, gfp_mask)) { + kfree_skb(n); + n = NULL; + goto out; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; - get_page(skb_shinfo(n)->frags[i].page); + skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; } - if (skb_shinfo(skb)->frag_list) { + if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } @@ -604,6 +1015,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) out: return n; } +EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff @@ -612,8 +1024,8 @@ out: * @ntail: room to add at tail * @gfp_mask: allocation priority * - * Expands (or creates identical copy, if &nhead and &ntail are zero) - * header of skb. &sk_buff itself is not changed. &sk_buff MUST have + * Expands (or creates identical copy, if @nhead and @ntail are zero) + * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * @@ -626,48 +1038,77 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, { int i; u8 *data; - int size = nhead + (skb->end - skb->head) + ntail; + int size = nhead + skb_end_offset(skb) + ntail; long off; + BUG_ON(nhead < 0); + if (skb_shared(skb)) BUG(); size = SKB_DATA_ALIGN(size); - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; + size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be - * optimized for the cases when header is void. */ - memcpy(data + nhead, skb->head, skb->tail - skb->head); - memcpy(data + size, skb->end, sizeof(struct skb_shared_info)); + * optimized for the cases when header is void. + */ + memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - get_page(skb_shinfo(skb)->frags[i].page); + memcpy((struct skb_shared_info *)(data + size), + skb_shinfo(skb), + offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); - if (skb_shinfo(skb)->frag_list) - skb_clone_fraglist(skb); + /* + * if shinfo is shared we must drop the old head gracefully, but if it + * is not we can just drop the old head and let the existing refcount + * be since all we did is relocate the values + */ + if (skb_cloned(skb)) { + /* copy this zero copy skb frags */ + if (skb_orphan_frags(skb, gfp_mask)) + goto nofrags; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + skb_frag_ref(skb, i); - skb_release_data(skb); + if (skb_has_frag_list(skb)) + skb_clone_fraglist(skb); + skb_release_data(skb); + } else { + skb_free_head(skb); + } off = (data + nhead) - skb->head; skb->head = data; - skb->end = data + size; + skb->head_frag = 0; skb->data += off; - skb->tail += off; - skb->mac.raw += off; - skb->h.raw += off; - skb->nh.raw += off; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + skb->end = size; + off = nhead; +#else + skb->end = skb->head + size; +#endif + skb->tail += off; + skb_headers_offset_update(skb, nhead); skb->cloned = 0; + skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; +nofrags: + kfree(data); nodata: return -ENOMEM; } +EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ @@ -688,7 +1129,7 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) } return skb2; } - +EXPORT_SYMBOL(skb_realloc_headroom); /** * skb_copy_expand - copy and expand sk_buff @@ -707,9 +1148,6 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) * * You must pass %GFP_ATOMIC as the allocation priority if this function * is called from an interrupt. - * - * BUG ALERT: ip_summed is not copied. Why does this work? Is it used - * only by netfilter in the cases when checksum is recalculated? --ANK */ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, @@ -718,8 +1156,10 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask); + struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); + int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; if (!n) @@ -730,7 +1170,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* Set the tail pointer and length */ skb_put(n, skb->len); - head_copy_len = skb_headroom(skb); + head_copy_len = oldheadroom; head_copy_off = 0; if (newheadroom <= head_copy_len) head_copy_len = newheadroom; @@ -744,8 +1184,11 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, copy_skb_header(n, skb); + skb_headers_offset_update(n, newheadroom - oldheadroom); + return n; } +EXPORT_SYMBOL(skb_copy_expand); /** * skb_pad - zero pad the tail of an skb @@ -756,73 +1199,223 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * - * May return NULL in out of memory cases. + * May return error in out of memory cases. The skb is freed on error. */ - -struct sk_buff *skb_pad(struct sk_buff *skb, int pad) + +int skb_pad(struct sk_buff *skb, int pad) { - struct sk_buff *nskb; - + int err; + int ntail; + /* If the skbuff is non linear tailroom is always zero.. */ - if (skb_tailroom(skb) >= pad) { + if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); - return skb; + return 0; + } + + ntail = skb->data_len + pad - (skb->end - skb->tail); + if (likely(skb_cloned(skb) || ntail > 0)) { + err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); + if (unlikely(err)) + goto free_skb; } - - nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad, GFP_ATOMIC); + + /* FIXME: The use of this function with non-linear skb's really needs + * to be audited. + */ + err = skb_linearize(skb); + if (unlikely(err)) + goto free_skb; + + memset(skb->data + skb->len, 0, pad); + return 0; + +free_skb: kfree_skb(skb); - if (nskb) - memset(nskb->data+nskb->len, 0, pad); - return nskb; -} - -/* Trims skb to length len. It can change skb pointers, if "realloc" is 1. - * If realloc==0 and trimming is impossible without change of data, - * it is BUG(). + return err; +} +EXPORT_SYMBOL(skb_pad); + +/** + * pskb_put - add data to the tail of a potentially fragmented buffer + * @skb: start of the buffer to use + * @tail: tail fragment of the buffer to use + * @len: amount of data to add + * + * This function extends the used data area of the potentially + * fragmented buffer. @tail must be the last fragment of @skb -- or + * @skb itself. If this would exceed the total buffer size the kernel + * will panic. A pointer to the first byte of the extra data is + * returned. */ -int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc) +unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) +{ + if (tail != skb) { + skb->data_len += len; + skb->len += len; + } + return skb_put(tail, len); +} +EXPORT_SYMBOL_GPL(pskb_put); + +/** + * skb_put - add data to a buffer + * @skb: buffer to use + * @len: amount of data to add + * + * This function extends the used data area of the buffer. If this would + * exceed the total buffer size the kernel will panic. A pointer to the + * first byte of the extra data is returned. + */ +unsigned char *skb_put(struct sk_buff *skb, unsigned int len) { + unsigned char *tmp = skb_tail_pointer(skb); + SKB_LINEAR_ASSERT(skb); + skb->tail += len; + skb->len += len; + if (unlikely(skb->tail > skb->end)) + skb_over_panic(skb, len, __builtin_return_address(0)); + return tmp; +} +EXPORT_SYMBOL(skb_put); + +/** + * skb_push - add data to the start of a buffer + * @skb: buffer to use + * @len: amount of data to add + * + * This function extends the used data area of the buffer at the buffer + * start. If this would exceed the total buffer headroom the kernel will + * panic. A pointer to the first byte of the extra data is returned. + */ +unsigned char *skb_push(struct sk_buff *skb, unsigned int len) +{ + skb->data -= len; + skb->len += len; + if (unlikely(skb->data<skb->head)) + skb_under_panic(skb, len, __builtin_return_address(0)); + return skb->data; +} +EXPORT_SYMBOL(skb_push); + +/** + * skb_pull - remove data from the start of a buffer + * @skb: buffer to use + * @len: amount of data to remove + * + * This function removes data from the start of a buffer, returning + * the memory to the headroom. A pointer to the next data in the buffer + * is returned. Once the data has been pulled future pushes will overwrite + * the old data. + */ +unsigned char *skb_pull(struct sk_buff *skb, unsigned int len) +{ + return skb_pull_inline(skb, len); +} +EXPORT_SYMBOL(skb_pull); + +/** + * skb_trim - remove end from a buffer + * @skb: buffer to alter + * @len: new length + * + * Cut the length of a buffer down by removing data from the tail. If + * the buffer is already under the length specified it is not modified. + * The skb must be linear. + */ +void skb_trim(struct sk_buff *skb, unsigned int len) +{ + if (skb->len > len) + __skb_trim(skb, len); +} +EXPORT_SYMBOL(skb_trim); + +/* Trims skb to length len. It can change skb pointers. + */ + +int ___pskb_trim(struct sk_buff *skb, unsigned int len) +{ + struct sk_buff **fragp; + struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; + int err; - for (i = 0; i < nfrags; i++) { - int end = offset + skb_shinfo(skb)->frags[i].size; - if (end > len) { - if (skb_cloned(skb)) { - BUG_ON(!realloc); - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - return -ENOMEM; - } - if (len <= offset) { - put_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->nr_frags--; - } else { - skb_shinfo(skb)->frags[i].size = len - offset; - } + if (skb_cloned(skb) && + unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) + return err; + + i = 0; + if (offset >= len) + goto drop_pages; + + for (; i < nfrags; i++) { + int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (end < len) { + offset = end; + continue; + } + + skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); + +drop_pages: + skb_shinfo(skb)->nr_frags = i; + + for (; i < nfrags; i++) + skb_frag_unref(skb, i); + + if (skb_has_frag_list(skb)) + skb_drop_fraglist(skb); + goto done; + } + + for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); + fragp = &frag->next) { + int end = offset + frag->len; + + if (skb_shared(frag)) { + struct sk_buff *nfrag; + + nfrag = skb_clone(frag, GFP_ATOMIC); + if (unlikely(!nfrag)) + return -ENOMEM; + + nfrag->next = frag->next; + consume_skb(frag); + frag = nfrag; + *fragp = frag; + } + + if (end < len) { + offset = end; + continue; } - offset = end; + + if (end > len && + unlikely((err = pskb_trim(frag, len - offset)))) + return err; + + if (frag->next) + skb_drop_list(&frag->next); + break; } - if (offset < len) { +done: + if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { - if (len <= skb_headlen(skb)) { - skb->len = len; - skb->data_len = 0; - skb->tail = skb->data + len; - if (skb_shinfo(skb)->frag_list && !skb_cloned(skb)) - skb_drop_fraglist(skb); - } else { - skb->data_len -= skb->len - len; - skb->len = len; - } + skb->len = len; + skb->data_len = 0; + skb_set_tail_pointer(skb, len); } return 0; } +EXPORT_SYMBOL(___pskb_trim); /** * __pskb_pull_tail - advance tail of skb header @@ -863,21 +1456,23 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) return NULL; } - if (skb_copy_bits(skb, skb_headlen(skb), skb->tail, delta)) + if (skb_copy_bits(skb, skb_headlen(skb), skb_tail_pointer(skb), delta)) BUG(); /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ - if (!skb_shinfo(skb)->frag_list) + if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size >= eat) + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size >= eat) goto pull_pages; - eat -= skb_shinfo(skb)->frags[i].size; + eat -= size; } /* If we need update frag list, we are in troubles. @@ -916,8 +1511,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) insp = list; } if (!pskb_pull(list, eat)) { - if (clone) - kfree_skb(clone); + kfree_skb(clone); return NULL; } break; @@ -941,14 +1535,16 @@ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); - eat -= skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size <= eat) { + skb_frag_unref(skb, i); + eat -= size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; if (eat) { skb_shinfo(skb)->frags[k].page_offset += eat; - skb_shinfo(skb)->frags[k].size -= eat; + skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); eat = 0; } k++; @@ -959,15 +1555,30 @@ pull_pages: skb->tail += delta; skb->data_len -= delta; - return skb->tail; + return skb_tail_pointer(skb); } +EXPORT_SYMBOL(__pskb_pull_tail); -/* Copy some data bits from skb to kernel buffer. */ - +/** + * skb_copy_bits - copy bits from skb to kernel buffer + * @skb: source skb + * @offset: offset in source + * @to: destination buffer + * @len: number of bytes to copy + * + * Copy the specified number of bytes from the source skb to the + * destination buffer. + * + * CAUTION ! : + * If its prototype is ever changed, + * check arch/{*}/net/{*}.S files, + * since it is called from BPF assembly code. + */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { - int i, copy; int start = skb_headlen(skb); + struct sk_buff *frag_iter; + int i, copy; if (offset > (int)skb->len - len) goto fault; @@ -976,7 +1587,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) if ((copy = start - offset) > 0) { if (copy > len) copy = len; - memcpy(to, skb->data + offset, copy); + skb_copy_from_linear_data_offset(skb, offset, to, copy); if ((len -= copy) == 0) return 0; offset += copy; @@ -985,21 +1596,22 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u8 *vaddr; if (copy > len) copy = len; - vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + vaddr = kmap_atomic(skb_frag_page(f)); memcpy(to, - vaddr + skb_shinfo(skb)->frags[i].page_offset+ - offset - start, copy); - kunmap_skb_frag(vaddr); + vaddr + f->page_offset + offset - start, + copy); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1009,35 +1621,235 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_bits(list, offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - to += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_bits(frag_iter, offset - start, to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; } + start = end; } + if (!len) return 0; fault: return -EFAULT; } +EXPORT_SYMBOL(skb_copy_bits); + +/* + * Callback from splice_to_pipe(), if we need to release some pages + * at the end of the spd in case we error'ed out in filling the pipe. + */ +static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) +{ + put_page(spd->pages[i]); +} + +static struct page *linear_to_page(struct page *page, unsigned int *len, + unsigned int *offset, + struct sock *sk) +{ + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + return NULL; + + *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); + + memcpy(page_address(pfrag->page) + pfrag->offset, + page_address(page) + *offset, *len); + *offset = pfrag->offset; + pfrag->offset += *len; + + return pfrag->page; +} + +static bool spd_can_coalesce(const struct splice_pipe_desc *spd, + struct page *page, + unsigned int offset) +{ + return spd->nr_pages && + spd->pages[spd->nr_pages - 1] == page && + (spd->partial[spd->nr_pages - 1].offset + + spd->partial[spd->nr_pages - 1].len == offset); +} + +/* + * Fill page/offset/length into spd, if it can hold more pages. + */ +static bool spd_fill_page(struct splice_pipe_desc *spd, + struct pipe_inode_info *pipe, struct page *page, + unsigned int *len, unsigned int offset, + bool linear, + struct sock *sk) +{ + if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) + return true; + + if (linear) { + page = linear_to_page(page, len, &offset, sk); + if (!page) + return true; + } + if (spd_can_coalesce(spd, page, offset)) { + spd->partial[spd->nr_pages - 1].len += *len; + return false; + } + get_page(page); + spd->pages[spd->nr_pages] = page; + spd->partial[spd->nr_pages].len = *len; + spd->partial[spd->nr_pages].offset = offset; + spd->nr_pages++; + + return false; +} + +static bool __splice_segment(struct page *page, unsigned int poff, + unsigned int plen, unsigned int *off, + unsigned int *len, + struct splice_pipe_desc *spd, bool linear, + struct sock *sk, + struct pipe_inode_info *pipe) +{ + if (!*len) + return true; + + /* skip this segment if already processed */ + if (*off >= plen) { + *off -= plen; + return false; + } + + /* ignore any bits we already processed */ + poff += *off; + plen -= *off; + *off = 0; + + do { + unsigned int flen = min(*len, plen); + + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) + return true; + poff += flen; + plen -= flen; + *len -= flen; + } while (*len && plen); + + return false; +} + +/* + * Map linear and fragment data from the skb to spd. It reports true if the + * pipe is full or if we already spliced the requested length. + */ +static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, + unsigned int *offset, unsigned int *len, + struct splice_pipe_desc *spd, struct sock *sk) +{ + int seg; + + /* map the linear part : + * If skb->head_frag is set, this 'linear' part is backed by a + * fragment, and if the head is not shared with any clones then + * we can avoid a copy since we own the head portion of this page. + */ + if (__splice_segment(virt_to_page(skb->data), + (unsigned long) skb->data & (PAGE_SIZE - 1), + skb_headlen(skb), + offset, len, spd, + skb_head_is_locked(skb), + sk, pipe)) + return true; + + /* + * then map the fragments + */ + for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { + const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; + + if (__splice_segment(skb_frag_page(f), + f->page_offset, skb_frag_size(f), + offset, len, spd, false, sk, pipe)) + return true; + } + + return false; +} + +/* + * Map data from the skb to a pipe. Should handle both the linear part, + * the fragments, and the frag list. It does NOT handle frag lists within + * the frag list, if such a thing exists. We'd probably need to recurse to + * handle that cleanly. + */ +int skb_splice_bits(struct sk_buff *skb, unsigned int offset, + struct pipe_inode_info *pipe, unsigned int tlen, + unsigned int flags) +{ + struct partial_page partial[MAX_SKB_FRAGS]; + struct page *pages[MAX_SKB_FRAGS]; + struct splice_pipe_desc spd = { + .pages = pages, + .partial = partial, + .nr_pages_max = MAX_SKB_FRAGS, + .flags = flags, + .ops = &nosteal_pipe_buf_ops, + .spd_release = sock_spd_release, + }; + struct sk_buff *frag_iter; + struct sock *sk = skb->sk; + int ret = 0; + + /* + * __skb_splice_bits() only fails if the output has no room left, + * so no point in going over the frag_list for the error case. + */ + if (__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk)) + goto done; + else if (!tlen) + goto done; + + /* + * now see if we have a frag_list to map + */ + skb_walk_frags(skb, frag_iter) { + if (!tlen) + break; + if (__skb_splice_bits(frag_iter, pipe, &offset, &tlen, &spd, sk)) + break; + } + +done: + if (spd.nr_pages) { + /* + * Drop the socket lock, otherwise we have reverse + * locking dependencies between sk_lock and i_mutex + * here as compared to sendfile(). We enter here + * with the socket lock held, and splice_to_pipe() will + * grab the pipe inode lock. For sendfile() emulation, + * we call into ->sendpage() with the i_mutex lock held + * and networking will grab the socket lock. + */ + release_sock(sk); + ret = splice_to_pipe(pipe, &spd); + lock_sock(sk); + } + + return ret; +} /** * skb_store_bits - store bits from kernel buffer to skb @@ -1051,10 +1863,11 @@ fault: * traversing fragment lists and such. */ -int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) +int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { - int i, copy; int start = skb_headlen(skb); + struct sk_buff *frag_iter; + int i, copy; if (offset > (int)skb->len - len) goto fault; @@ -1062,7 +1875,7 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) if ((copy = start - offset) > 0) { if (copy > len) copy = len; - memcpy(skb->data + offset, from, copy); + skb_copy_to_linear_data_offset(skb, offset, from, copy); if ((len -= copy) == 0) return 0; offset += copy; @@ -1073,19 +1886,19 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); - end = start + frag->size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u8 *vaddr; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); memcpy(vaddr + frag->page_offset + offset - start, from, copy); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1095,28 +1908,24 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_store_bits(list, offset - start, - from, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - from += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_store_bits(frag_iter, offset - start, + from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from += copy; } + start = end; } if (!len) return 0; @@ -1124,23 +1933,22 @@ int skb_store_bits(const struct sk_buff *skb, int offset, void *from, int len) fault: return -EFAULT; } - EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ - -unsigned int skb_checksum(const struct sk_buff *skb, int offset, - int len, unsigned int csum) +__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, + __wsum csum, const struct skb_checksum_ops *ops) { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ if (copy > 0) { if (copy > len) copy = len; - csum = csum_partial(skb->data + offset, copy, csum); + csum = ops->update(skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; @@ -1149,22 +1957,22 @@ unsigned int skb_checksum(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { - unsigned int csum2; + __wsum csum2; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); - csum2 = csum_partial(vaddr + frag->page_offset + - offset - start, copy, 0); - kunmap_skb_frag(vaddr); - csum = csum_block_add(csum, csum2, pos); + vaddr = kmap_atomic(skb_frag_page(frag)); + csum2 = ops->update(vaddr + frag->page_offset + + offset - start, copy, 0); + kunmap_atomic(vaddr); + csum = ops->combine(csum, csum2, pos, copy); if (!(len -= copy)) return csum; offset += copy; @@ -1173,42 +1981,52 @@ unsigned int skb_checksum(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - BUG_TRAP(start <= offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - unsigned int csum2; - if (copy > len) - copy = len; - csum2 = skb_checksum(list, offset - start, - copy, 0); - csum = csum_block_add(csum, csum2, pos); - if ((len -= copy) == 0) - return csum; - offset += copy; - pos += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + __wsum csum2; + if (copy > len) + copy = len; + csum2 = __skb_checksum(frag_iter, offset - start, + copy, 0, ops); + csum = ops->combine(csum, csum2, pos, copy); + if ((len -= copy) == 0) + return csum; + offset += copy; + pos += copy; } + start = end; } BUG_ON(len); return csum; } +EXPORT_SYMBOL(__skb_checksum); + +__wsum skb_checksum(const struct sk_buff *skb, int offset, + int len, __wsum csum) +{ + const struct skb_checksum_ops ops = { + .update = csum_partial_ext, + .combine = csum_block_add_ext, + }; + + return __skb_checksum(skb, offset, len, csum, &ops); +} +EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ -unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, - u8 *to, int len, unsigned int csum) +__wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, + u8 *to, int len, __wsum csum) { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int pos = 0; /* Copy header. */ @@ -1227,22 +2045,22 @@ unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; - BUG_TRAP(start <= offset + len); + WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { - unsigned int csum2; + __wsum csum2; u8 *vaddr; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); csum2 = csum_partial_copy_nocheck(vaddr + frag->page_offset + offset - start, to, copy, 0); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) return csum; @@ -1253,61 +2071,157 @@ unsigned int skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + __wsum csum2; + int end; - for (; list; list = list->next) { - unsigned int csum2; - int end; - - BUG_TRAP(start <= offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - csum2 = skb_copy_and_csum_bits(list, - offset - start, - to, copy, 0); - csum = csum_block_add(csum, csum2, pos); - if ((len -= copy) == 0) - return csum; - offset += copy; - to += copy; - pos += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + csum2 = skb_copy_and_csum_bits(frag_iter, + offset - start, + to, copy, 0); + csum = csum_block_add(csum, csum2, pos); + if ((len -= copy) == 0) + return csum; + offset += copy; + to += copy; + pos += copy; } + start = end; } BUG_ON(len); return csum; } +EXPORT_SYMBOL(skb_copy_and_csum_bits); + + /** + * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() + * @from: source buffer + * + * Calculates the amount of linear headroom needed in the 'to' skb passed + * into skb_zerocopy(). + */ +unsigned int +skb_zerocopy_headlen(const struct sk_buff *from) +{ + unsigned int hlen = 0; + + if (!from->head_frag || + skb_headlen(from) < L1_CACHE_BYTES || + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + hlen = skb_headlen(from); + + if (skb_has_frag_list(from)) + hlen = from->len; + + return hlen; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); + +/** + * skb_zerocopy - Zero copy skb to skb + * @to: destination buffer + * @from: source buffer + * @len: number of bytes to copy from source buffer + * @hlen: size of linear headroom in destination buffer + * + * Copies up to `len` bytes from `from` to `to` by creating references + * to the frags in the source buffer. + * + * The `hlen` as calculated by skb_zerocopy_headlen() specifies the + * headroom in the `to` buffer. + * + * Return value: + * 0: everything is OK + * -ENOMEM: couldn't orphan frags of @from due to lack of memory + * -EFAULT: skb_copy_bits() found some problem with skb geometry + */ +int +skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) +{ + int i, j = 0; + int plen = 0; /* length of skb->head fragment */ + int ret; + struct page *page; + unsigned int offset; + + BUG_ON(!from->head_frag && !hlen); + + /* dont bother with small payloads */ + if (len <= skb_tailroom(to)) + return skb_copy_bits(from, 0, skb_put(to, len), len); + + if (hlen) { + ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + if (unlikely(ret)) + return ret; + len -= hlen; + } else { + plen = min_t(int, skb_headlen(from), len); + if (plen) { + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + __skb_fill_page_desc(to, 0, page, offset, plen); + get_page(page); + j = 1; + len -= plen; + } + } + + to->truesize += len + plen; + to->len += len + plen; + to->data_len += len + plen; + + if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { + skb_tx_error(from); + return -ENOMEM; + } + + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + if (!len) + break; + skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; + skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); + len -= skb_shinfo(to)->frags[j].size; + skb_frag_ref(to, j); + j++; + } + skb_shinfo(to)->nr_frags = j; + + return 0; +} +EXPORT_SYMBOL_GPL(skb_zerocopy); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { - unsigned int csum; + __wsum csum; long csstart; - if (skb->ip_summed == CHECKSUM_HW) - csstart = skb->h.raw - skb->data; + if (skb->ip_summed == CHECKSUM_PARTIAL) + csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); BUG_ON(csstart > skb_headlen(skb)); - memcpy(to, skb->data, csstart); + skb_copy_from_linear_data(skb, to, csstart); csum = 0; if (csstart != skb->len) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart, 0); - if (skb->ip_summed == CHECKSUM_HW) { - long csstuff = csstart + skb->csum; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + long csstuff = csstart + skb->csum_offset; - *((unsigned short *)(to + csstuff)) = csum_fold(csum); + *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } +EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue @@ -1328,6 +2242,7 @@ struct sk_buff *skb_dequeue(struct sk_buff_head *list) spin_unlock_irqrestore(&list->lock, flags); return result; } +EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue @@ -1347,6 +2262,7 @@ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) spin_unlock_irqrestore(&list->lock, flags); return result; } +EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge - empty a list @@ -1362,6 +2278,7 @@ void skb_queue_purge(struct sk_buff_head *list) while ((skb = skb_dequeue(list)) != NULL) kfree_skb(skb); } +EXPORT_SYMBOL(skb_queue_purge); /** * skb_queue_head - queue a buffer at the list head @@ -1382,6 +2299,7 @@ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail @@ -1402,6 +2320,7 @@ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list @@ -1421,6 +2340,7 @@ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer @@ -1437,10 +2357,10 @@ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head unsigned long flags; spin_lock_irqsave(&list->lock, flags); - __skb_append(old, newsk, list); + __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } - +EXPORT_SYMBOL(skb_append); /** * skb_insert - insert a buffer @@ -1462,19 +2382,7 @@ void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head __skb_insert(newsk, old->prev, old, list); spin_unlock_irqrestore(&list->lock, flags); } - -#if 0 -/* - * Tune the memory allocator for a new MTU size. - */ -void skb_add_mtu(int mtu) -{ - /* Must match allocation in alloc_skb */ - mtu = SKB_DATA_ALIGN(mtu) + sizeof(struct skb_shared_info); - - kmem_add_cache_size(mtu); -} -#endif +EXPORT_SYMBOL(skb_insert); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, @@ -1482,8 +2390,8 @@ static inline void skb_split_inside_header(struct sk_buff *skb, { int i; - memcpy(skb_put(skb1, pos - len), skb->data + len, pos - len); - + skb_copy_from_linear_data_offset(skb, len, skb_put(skb1, pos - len), + pos - len); /* And move data appendix as is. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; @@ -1494,7 +2402,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb, skb1->len += skb1->data_len; skb->data_len = 0; skb->len = len; - skb->tail = skb->data + len; + skb_set_tail_pointer(skb, len); } static inline void skb_split_no_header(struct sk_buff *skb, @@ -1510,7 +2418,7 @@ static inline void skb_split_no_header(struct sk_buff *skb, skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { - int size = skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; @@ -1524,10 +2432,10 @@ static inline void skb_split_no_header(struct sk_buff *skb, * where splitting is expensive. * 2. Split is accurately. We make this. */ - get_page(skb_shinfo(skb)->frags[i].page); + skb_frag_ref(skb, i); skb_shinfo(skb1)->frags[0].page_offset += len - pos; - skb_shinfo(skb1)->frags[0].size -= len - pos; - skb_shinfo(skb)->frags[i].size = len - pos; + skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); + skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; @@ -1548,11 +2456,156 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + skb_shinfo(skb1)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } +EXPORT_SYMBOL(skb_split); + +/* Shifting from/to a cloned skb is a no-go. + * + * Caller cannot keep skb_shinfo related pointers past calling here! + */ +static int skb_prepare_for_shift(struct sk_buff *skb) +{ + return skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); +} + +/** + * skb_shift - Shifts paged data partially from skb to another + * @tgt: buffer into which tail data gets added + * @skb: buffer from which the paged data comes from + * @shiftlen: shift up to this many bytes + * + * Attempts to shift up to shiftlen worth of bytes, which may be less than + * the length of the skb, from skb to tgt. Returns number bytes shifted. + * It's up to caller to free skb if everything was shifted. + * + * If @tgt runs out of frags, the whole operation is aborted. + * + * Skb cannot include anything else but paged data while tgt is allowed + * to have non-paged data as well. + * + * TODO: full sized shift could be optimized but that would need + * specialized skb free'er to handle frags without up-to-date nr_frags. + */ +int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) +{ + int from, to, merge, todo; + struct skb_frag_struct *fragfrom, *fragto; + + BUG_ON(shiftlen > skb->len); + BUG_ON(skb_headlen(skb)); /* Would corrupt stream */ + + todo = shiftlen; + from = 0; + to = skb_shinfo(tgt)->nr_frags; + fragfrom = &skb_shinfo(skb)->frags[from]; + + /* Actual merge is delayed until the point when we know we can + * commit all, so that we don't have to undo partial changes + */ + if (!to || + !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), + fragfrom->page_offset)) { + merge = -1; + } else { + merge = to - 1; + + todo -= skb_frag_size(fragfrom); + if (todo < 0) { + if (skb_prepare_for_shift(skb) || + skb_prepare_for_shift(tgt)) + return 0; + + /* All previous frag pointers might be stale! */ + fragfrom = &skb_shinfo(skb)->frags[from]; + fragto = &skb_shinfo(tgt)->frags[merge]; + + skb_frag_size_add(fragto, shiftlen); + skb_frag_size_sub(fragfrom, shiftlen); + fragfrom->page_offset += shiftlen; + + goto onlymerged; + } + + from++; + } + + /* Skip full, not-fitting skb to avoid expensive operations */ + if ((shiftlen == skb->len) && + (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) + return 0; + + if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) + return 0; + + while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { + if (to == MAX_SKB_FRAGS) + return 0; + + fragfrom = &skb_shinfo(skb)->frags[from]; + fragto = &skb_shinfo(tgt)->frags[to]; + + if (todo >= skb_frag_size(fragfrom)) { + *fragto = *fragfrom; + todo -= skb_frag_size(fragfrom); + from++; + to++; + + } else { + __skb_frag_ref(fragfrom); + fragto->page = fragfrom->page; + fragto->page_offset = fragfrom->page_offset; + skb_frag_size_set(fragto, todo); + + fragfrom->page_offset += todo; + skb_frag_size_sub(fragfrom, todo); + todo = 0; + + to++; + break; + } + } + + /* Ready to "commit" this state change to tgt */ + skb_shinfo(tgt)->nr_frags = to; + + if (merge >= 0) { + fragfrom = &skb_shinfo(skb)->frags[0]; + fragto = &skb_shinfo(tgt)->frags[merge]; + + skb_frag_size_add(fragto, skb_frag_size(fragfrom)); + __skb_frag_unref(fragfrom); + } + + /* Reposition in the original skb */ + to = 0; + while (from < skb_shinfo(skb)->nr_frags) + skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; + skb_shinfo(skb)->nr_frags = to; + + BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); + +onlymerged: + /* Most likely the tgt won't ever need its checksum anymore, skb on + * the other hand might need it if it needs to be resent + */ + tgt->ip_summed = CHECKSUM_PARTIAL; + skb->ip_summed = CHECKSUM_PARTIAL; + + /* Yak, is it really working this way? Some helper please? */ + skb->len -= shiftlen; + skb->data_len -= shiftlen; + skb->truesize -= shiftlen; + tgt->len += shiftlen; + tgt->data_len += shiftlen; + tgt->truesize += shiftlen; + + return shiftlen; +} /** * skb_prepare_seq_read - Prepare a sequential read of skb data @@ -1573,6 +2626,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; } +EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data @@ -1580,22 +2634,22 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, * @data: destination pointer for data to be returned * @st: state variable * - * Reads a block of skb data at &consumed relative to the + * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns - * the head of the data block to &data and returns the length + * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data - * returned, i.e. &consumed is typically set to the number + * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * - * Note: The size of each block of data returned can be arbitary, + * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy seqeuental * reads of potentially non linear data. * - * Note: Fragment lists within fragments are not implemented + * Note 2: Fragment lists within fragments are not implemented * at the moment, state->root_skb could be replaced with * a stack for this purpose. */ @@ -1605,14 +2659,19 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; - if (unlikely(abs_offset >= st->upper_offset)) + if (unlikely(abs_offset >= st->upper_offset)) { + if (st->frag_data) { + kunmap_atomic(st->frag_data); + st->frag_data = NULL; + } return 0; + } next_skb: - block_limit = skb_headlen(st->cur_skb); + block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; - if (abs_offset < block_limit) { - *data = st->cur_skb->data + abs_offset; + if (abs_offset < block_limit && !st->frag_data) { + *data = st->cur_skb->data + (abs_offset - st->stepped_offset); return block_limit - abs_offset; } @@ -1621,11 +2680,11 @@ next_skb: while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; - block_limit = frag->size + st->stepped_offset; + block_limit = skb_frag_size(frag) + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) - st->frag_data = kmap_skb_frag(frag); + st->frag_data = kmap_atomic(skb_frag_page(frag)); *data = (u8 *) st->frag_data + frag->page_offset + (abs_offset - st->stepped_offset); @@ -1634,26 +2693,32 @@ next_skb: } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->frag_idx++; - st->stepped_offset += frag->size; + st->stepped_offset += skb_frag_size(frag); } - if (st->cur_skb->next) { - st->cur_skb = st->cur_skb->next; + if (st->frag_data) { + kunmap_atomic(st->frag_data); + st->frag_data = NULL; + } + + if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { + st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; - } else if (st->root_skb == st->cur_skb && - skb_shinfo(st->root_skb)->frag_list) { - st->cur_skb = skb_shinfo(st->root_skb)->frag_list; + } else if (st->cur_skb->next) { + st->cur_skb = st->cur_skb->next; + st->frag_idx = 0; goto next_skb; } return 0; } +EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data @@ -1665,8 +2730,9 @@ next_skb: void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); } +EXPORT_SYMBOL(skb_abort_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) @@ -1699,16 +2765,20 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config, struct ts_state *state) { + unsigned int ret; + config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state)); - return textsearch_find(config, state); + ret = textsearch_find(config, state); + return (ret <= to - from ? ret : UINT_MAX); } +EXPORT_SYMBOL(skb_find_text); /** - * skb_append_datato_frags: - append the user data to a skb + * skb_append_datato_frags - append the user data to a skb * @sk: sock structure * @skb: skb structure to be appened with user data. * @getfrag: call back function to be used for getting the user data @@ -1723,52 +2793,37 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length) { - int frg_cnt = 0; - skb_frag_t *frag = NULL; - struct page *page = NULL; - int copy, left; + int frg_cnt = skb_shinfo(skb)->nr_frags; + int copy; int offset = 0; int ret; + struct page_frag *pfrag = ¤t->task_frag; do { /* Return error if we don't have space for new frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; if (frg_cnt >= MAX_SKB_FRAGS) - return -EFAULT; + return -EMSGSIZE; - /* allocate a new page for next frag */ - page = alloc_pages(sk->sk_allocation, 0); - - /* If alloc_page fails just return failure and caller will - * free previous allocated pages by doing kfree_skb() - */ - if (page == NULL) + if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; - /* initialize the next frag */ - sk->sk_sndmsg_page = page; - sk->sk_sndmsg_off = 0; - skb_fill_page_desc(skb, frg_cnt, page, 0, 0); - skb->truesize += PAGE_SIZE; - atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc); - - /* get the new initialized frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; - frag = &skb_shinfo(skb)->frags[frg_cnt - 1]; - /* copy the user data to page */ - left = PAGE_SIZE - frag->page_offset; - copy = (length > left)? left : length; + copy = min_t(int, length, pfrag->size - pfrag->offset); - ret = getfrag(from, (page_address(frag->page) + - frag->page_offset + frag->size), - offset, copy, 0, skb); + ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, + offset, copy, 0, skb); if (ret < 0) return -EFAULT; /* copy was successful so update the size parameters */ - sk->sk_sndmsg_off += copy; - frag->size += copy; + skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset, + copy); + frg_cnt++; + pfrag->offset += copy; + get_page(pfrag->page); + + skb->truesize += copy; + atomic_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; @@ -1778,56 +2833,1129 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, return 0; } +EXPORT_SYMBOL(skb_append_datato_frags); + +/** + * skb_pull_rcsum - pull skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_pull on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_pull unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) +{ + BUG_ON(len > skb->len); + skb->len -= len; + BUG_ON(skb->len < skb->data_len); + skb_postpull_rcsum(skb, skb->data, len); + return skb->data += len; +} +EXPORT_SYMBOL_GPL(skb_pull_rcsum); + +/** + * skb_segment - Perform protocol segmentation on skb. + * @head_skb: buffer to segment + * @features: features for the output path (see dev->features) + * + * This function performs segmentation on the given skb. It returns + * a pointer to the first in a list of new skbs for the segments. + * In case of error it returns ERR_PTR(err). + */ +struct sk_buff *skb_segment(struct sk_buff *head_skb, + netdev_features_t features) +{ + struct sk_buff *segs = NULL; + struct sk_buff *tail = NULL; + struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; + skb_frag_t *frag = skb_shinfo(head_skb)->frags; + unsigned int mss = skb_shinfo(head_skb)->gso_size; + unsigned int doffset = head_skb->data - skb_mac_header(head_skb); + struct sk_buff *frag_skb = head_skb; + unsigned int offset = doffset; + unsigned int tnl_hlen = skb_tnl_header_len(head_skb); + unsigned int headroom; + unsigned int len; + __be16 proto; + bool csum; + int sg = !!(features & NETIF_F_SG); + int nfrags = skb_shinfo(head_skb)->nr_frags; + int err = -ENOMEM; + int i = 0; + int pos; + int dummy; + + __skb_push(head_skb, doffset); + proto = skb_network_protocol(head_skb, &dummy); + if (unlikely(!proto)) + return ERR_PTR(-EINVAL); + + csum = !head_skb->encap_hdr_csum && + !!can_checksum_protocol(features, proto); + + headroom = skb_headroom(head_skb); + pos = skb_headlen(head_skb); + + do { + struct sk_buff *nskb; + skb_frag_t *nskb_frag; + int hsize; + int size; + + len = head_skb->len - offset; + if (len > mss) + len = mss; + + hsize = skb_headlen(head_skb) - offset; + if (hsize < 0) + hsize = 0; + if (hsize > len || !sg) + hsize = len; + + if (!hsize && i >= nfrags && skb_headlen(list_skb) && + (skb_headlen(list_skb) == len || sg)) { + BUG_ON(skb_headlen(list_skb) > len); + + i = 0; + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; + pos += skb_headlen(list_skb); + + while (pos < offset + len) { + BUG_ON(i >= nfrags); + + size = skb_frag_size(frag); + if (pos + size > offset + len) + break; + + i++; + pos += size; + frag++; + } + + nskb = skb_clone(list_skb, GFP_ATOMIC); + list_skb = list_skb->next; + + if (unlikely(!nskb)) + goto err; + + if (unlikely(pskb_trim(nskb, len))) { + kfree_skb(nskb); + goto err; + } + + hsize = skb_end_offset(nskb); + if (skb_cow_head(nskb, doffset + headroom)) { + kfree_skb(nskb); + goto err; + } + + nskb->truesize += skb_end_offset(nskb) - hsize; + skb_release_head_state(nskb); + __skb_push(nskb, doffset); + } else { + nskb = __alloc_skb(hsize + doffset + headroom, + GFP_ATOMIC, skb_alloc_rx_flag(head_skb), + NUMA_NO_NODE); + + if (unlikely(!nskb)) + goto err; + + skb_reserve(nskb, headroom); + __skb_put(nskb, doffset); + } + + if (segs) + tail->next = nskb; + else + segs = nskb; + tail = nskb; + + __copy_skb_header(nskb, head_skb); + nskb->mac_len = head_skb->mac_len; + + skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); + + skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, + nskb->data - tnl_hlen, + doffset + tnl_hlen); + + if (nskb->len == len + doffset) + goto perform_csum_check; + + if (!sg) { + nskb->ip_summed = CHECKSUM_NONE; + nskb->csum = skb_copy_and_csum_bits(head_skb, offset, + skb_put(nskb, len), + len, 0); + SKB_GSO_CB(nskb)->csum_start = + skb_headroom(nskb) + doffset; + continue; + } + + nskb_frag = skb_shinfo(nskb)->frags; + + skb_copy_from_linear_data_offset(head_skb, offset, + skb_put(nskb, hsize), hsize); + + skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags & + SKBTX_SHARED_FRAG; + + while (pos < offset + len) { + if (i >= nfrags) { + BUG_ON(skb_headlen(list_skb)); + + i = 0; + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; + + BUG_ON(!nfrags); + + list_skb = list_skb->next; + } + + if (unlikely(skb_shinfo(nskb)->nr_frags >= + MAX_SKB_FRAGS)) { + net_warn_ratelimited( + "skb_segment: too many frags: %u %u\n", + pos, mss); + goto err; + } + + if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC))) + goto err; + + *nskb_frag = *frag; + __skb_frag_ref(nskb_frag); + size = skb_frag_size(nskb_frag); + + if (pos < offset) { + nskb_frag->page_offset += offset - pos; + skb_frag_size_sub(nskb_frag, offset - pos); + } + + skb_shinfo(nskb)->nr_frags++; + + if (pos + size <= offset + len) { + i++; + frag++; + pos += size; + } else { + skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); + goto skip_fraglist; + } + + nskb_frag++; + } + +skip_fraglist: + nskb->data_len = len - hsize; + nskb->len += nskb->data_len; + nskb->truesize += nskb->data_len; + +perform_csum_check: + if (!csum) { + nskb->csum = skb_checksum(nskb, doffset, + nskb->len - doffset, 0); + nskb->ip_summed = CHECKSUM_NONE; + SKB_GSO_CB(nskb)->csum_start = + skb_headroom(nskb) + doffset; + } + } while ((offset += len) < head_skb->len); + + return segs; + +err: + kfree_skb_list(segs); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(skb_segment); + +int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); + unsigned int offset = skb_gro_offset(skb); + unsigned int headlen = skb_headlen(skb); + struct sk_buff *nskb, *lp, *p = *head; + unsigned int len = skb_gro_len(skb); + unsigned int delta_truesize; + unsigned int headroom; + + if (unlikely(p->len + len >= 65536)) + return -E2BIG; + + lp = NAPI_GRO_CB(p)->last; + pinfo = skb_shinfo(lp); + + if (headlen <= offset) { + skb_frag_t *frag; + skb_frag_t *frag2; + int i = skbinfo->nr_frags; + int nr_frags = pinfo->nr_frags + i; + + if (nr_frags > MAX_SKB_FRAGS) + goto merge; + + offset -= headlen; + pinfo->nr_frags = nr_frags; + skbinfo->nr_frags = 0; + + frag = pinfo->frags + nr_frags; + frag2 = skbinfo->frags + i; + do { + *--frag = *--frag2; + } while (--i); + + frag->page_offset += offset; + skb_frag_size_sub(frag, offset); + + /* all fragments truesize : remove (head size + sk_buff) */ + delta_truesize = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); + + skb->truesize -= skb->data_len; + skb->len -= skb->data_len; + skb->data_len = 0; + + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; + goto done; + } else if (skb->head_frag) { + int nr_frags = pinfo->nr_frags; + skb_frag_t *frag = pinfo->frags + nr_frags; + struct page *page = virt_to_head_page(skb->head); + unsigned int first_size = headlen - offset; + unsigned int first_offset; + + if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) + goto merge; + + first_offset = skb->data - + (unsigned char *)page_address(page) + + offset; + + pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; + + frag->page.p = page; + frag->page_offset = first_offset; + skb_frag_size_set(frag, first_size); + + memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); + /* We dont need to clear skbinfo->nr_frags here */ + + delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; + goto done; + } + if (pinfo->frag_list) + goto merge; + if (skb_gro_len(p) != pinfo->gso_size) + return -E2BIG; + + headroom = skb_headroom(p); + nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); + if (unlikely(!nskb)) + return -ENOMEM; + + __copy_skb_header(nskb, p); + nskb->mac_len = p->mac_len; + + skb_reserve(nskb, headroom); + __skb_put(nskb, skb_gro_offset(p)); + + skb_set_mac_header(nskb, skb_mac_header(p) - p->data); + skb_set_network_header(nskb, skb_network_offset(p)); + skb_set_transport_header(nskb, skb_transport_offset(p)); + + __skb_pull(p, skb_gro_offset(p)); + memcpy(skb_mac_header(nskb), skb_mac_header(p), + p->data - skb_mac_header(p)); + + skb_shinfo(nskb)->frag_list = p; + skb_shinfo(nskb)->gso_size = pinfo->gso_size; + pinfo->gso_size = 0; + skb_header_release(p); + NAPI_GRO_CB(nskb)->last = p; + + nskb->data_len += p->len; + nskb->truesize += p->truesize; + nskb->len += p->len; + + *head = nskb; + nskb->next = p->next; + p->next = NULL; + + p = nskb; + +merge: + delta_truesize = skb->truesize; + if (offset > headlen) { + unsigned int eat = offset - headlen; + + skbinfo->frags[0].page_offset += eat; + skb_frag_size_sub(&skbinfo->frags[0], eat); + skb->data_len -= eat; + skb->len -= eat; + offset = headlen; + } + + __skb_pull(skb, offset); + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + NAPI_GRO_CB(p)->last = skb; + skb_header_release(skb); + lp = p; + +done: + NAPI_GRO_CB(p)->count++; + p->data_len += len; + p->truesize += delta_truesize; + p->len += len; + if (lp != p) { + lp->data_len += len; + lp->truesize += delta_truesize; + lp->len += len; + } + NAPI_GRO_CB(skb)->same_flow = 1; + return 0; +} +EXPORT_SYMBOL_GPL(skb_gro_receive); void __init skb_init(void) { skbuff_head_cache = kmem_cache_create("skbuff_head_cache", sizeof(struct sk_buff), 0, - SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!skbuff_head_cache) - panic("cannot create skbuff cache"); - + SLAB_HWCACHE_ALIGN|SLAB_PANIC, + NULL); skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", (2*sizeof(struct sk_buff)) + sizeof(atomic_t), 0, - SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!skbuff_fclone_cache) - panic("cannot create skbuff cache"); + SLAB_HWCACHE_ALIGN|SLAB_PANIC, + NULL); } -EXPORT_SYMBOL(___pskb_trim); -EXPORT_SYMBOL(__kfree_skb); -EXPORT_SYMBOL(__pskb_pull_tail); -EXPORT_SYMBOL(__alloc_skb); -EXPORT_SYMBOL(pskb_copy); -EXPORT_SYMBOL(pskb_expand_head); -EXPORT_SYMBOL(skb_checksum); -EXPORT_SYMBOL(skb_clone); -EXPORT_SYMBOL(skb_clone_fraglist); -EXPORT_SYMBOL(skb_copy); -EXPORT_SYMBOL(skb_copy_and_csum_bits); -EXPORT_SYMBOL(skb_copy_and_csum_dev); -EXPORT_SYMBOL(skb_copy_bits); -EXPORT_SYMBOL(skb_copy_expand); -EXPORT_SYMBOL(skb_over_panic); -EXPORT_SYMBOL(skb_pad); -EXPORT_SYMBOL(skb_realloc_headroom); -EXPORT_SYMBOL(skb_under_panic); -EXPORT_SYMBOL(skb_dequeue); -EXPORT_SYMBOL(skb_dequeue_tail); -EXPORT_SYMBOL(skb_insert); -EXPORT_SYMBOL(skb_queue_purge); -EXPORT_SYMBOL(skb_queue_head); -EXPORT_SYMBOL(skb_queue_tail); -EXPORT_SYMBOL(skb_unlink); -EXPORT_SYMBOL(skb_append); -EXPORT_SYMBOL(skb_split); -EXPORT_SYMBOL(skb_prepare_seq_read); -EXPORT_SYMBOL(skb_seq_read); -EXPORT_SYMBOL(skb_abort_seq_read); -EXPORT_SYMBOL(skb_find_text); -EXPORT_SYMBOL(skb_append_datato_frags); +/** + * skb_to_sgvec - Fill a scatter-gather list from a socket buffer + * @skb: Socket buffer containing the buffers to be mapped + * @sg: The scatter-gather list to map into + * @offset: The offset into the buffer's contents to start mapping + * @len: Length of buffer space to be mapped + * + * Fill the specified scatter-gather list with mappings/pointers into a + * region of the buffer space attached to a socket buffer. + */ +static int +__skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + struct sk_buff *frag_iter; + int elt = 0; + + if (copy > 0) { + if (copy > len) + copy = len; + sg_set_buf(sg, skb->data + offset, copy); + elt++; + if ((len -= copy) == 0) + return elt; + offset += copy; + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + if ((copy = end - offset) > 0) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + if (copy > len) + copy = len; + sg_set_page(&sg[elt], skb_frag_page(frag), copy, + frag->page_offset+offset-start); + elt++; + if (!(len -= copy)) + return elt; + offset += copy; + } + start = end; + } + + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + elt += __skb_to_sgvec(frag_iter, sg+elt, offset - start, + copy); + if ((len -= copy) == 0) + return elt; + offset += copy; + } + start = end; + } + BUG_ON(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); + + sg_mark_end(&sg[nsg - 1]); + + return nsg; +} +EXPORT_SYMBOL_GPL(skb_to_sgvec); + +/** + * skb_cow_data - Check that a socket buffer's data buffers are writable + * @skb: The socket buffer to check. + * @tailbits: Amount of trailing space to be added + * @trailer: Returned pointer to the skb where the @tailbits space begins + * + * Make sure that the data buffers attached to a socket buffer are + * writable. If they are not, private copies are made of the data buffers + * and the socket buffer is set to use these instead. + * + * If @tailbits is given, make sure that there is space to write @tailbits + * bytes of data beyond current end of socket buffer. @trailer will be + * set to point to the skb in which this space begins. + * + * The number of scatterlist elements required to completely map the + * COW'd and extended socket buffer will be returned. + */ +int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) +{ + int copyflag; + int elt; + struct sk_buff *skb1, **skb_p; + + /* If skb is cloned or its head is paged, reallocate + * head pulling out all the pages (pages are considered not writable + * at the moment even if they are anonymous). + */ + if ((skb_cloned(skb) || skb_shinfo(skb)->nr_frags) && + __pskb_pull_tail(skb, skb_pagelen(skb)-skb_headlen(skb)) == NULL) + return -ENOMEM; + + /* Easy case. Most of packets will go this way. */ + if (!skb_has_frag_list(skb)) { + /* A little of trouble, not enough of space for trailer. + * This should not happen, when stack is tuned to generate + * good frames. OK, on miss we reallocate and reserve even more + * space, 128 bytes is fair. */ + + if (skb_tailroom(skb) < tailbits && + pskb_expand_head(skb, 0, tailbits-skb_tailroom(skb)+128, GFP_ATOMIC)) + return -ENOMEM; + + /* Voila! */ + *trailer = skb; + return 1; + } + + /* Misery. We are in troubles, going to mincer fragments... */ + + elt = 1; + skb_p = &skb_shinfo(skb)->frag_list; + copyflag = 0; + + while ((skb1 = *skb_p) != NULL) { + int ntail = 0; + + /* The fragment is partially pulled by someone, + * this can happen on input. Copy it and everything + * after it. */ + + if (skb_shared(skb1)) + copyflag = 1; + + /* If the skb is the last, worry about trailer. */ + + if (skb1->next == NULL && tailbits) { + if (skb_shinfo(skb1)->nr_frags || + skb_has_frag_list(skb1) || + skb_tailroom(skb1) < tailbits) + ntail = tailbits + 128; + } + + if (copyflag || + skb_cloned(skb1) || + ntail || + skb_shinfo(skb1)->nr_frags || + skb_has_frag_list(skb1)) { + struct sk_buff *skb2; + + /* Fuck, we are miserable poor guys... */ + if (ntail == 0) + skb2 = skb_copy(skb1, GFP_ATOMIC); + else + skb2 = skb_copy_expand(skb1, + skb_headroom(skb1), + ntail, + GFP_ATOMIC); + if (unlikely(skb2 == NULL)) + return -ENOMEM; + + if (skb1->sk) + skb_set_owner_w(skb2, skb1->sk); + + /* Looking around. Are we still alive? + * OK, link new skb, drop old one */ + + skb2->next = skb1->next; + *skb_p = skb2; + kfree_skb(skb1); + skb1 = skb2; + } + elt++; + *trailer = skb1; + skb_p = &skb1->next; + } + + return elt; +} +EXPORT_SYMBOL_GPL(skb_cow_data); + +static void sock_rmem_free(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); +} + +/* + * Note: We dont mem charge error packets (no sk_forward_alloc changes) + */ +int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) +{ + if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= + (unsigned int)sk->sk_rcvbuf) + return -ENOMEM; + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = sock_rmem_free; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); + + /* before exiting rcu section, make sure dst is refcounted */ + skb_dst_force(skb); + + skb_queue_tail(&sk->sk_error_queue, skb); + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + return 0; +} +EXPORT_SYMBOL(sock_queue_err_skb); + +void skb_tstamp_tx(struct sk_buff *orig_skb, + struct skb_shared_hwtstamps *hwtstamps) +{ + struct sock *sk = orig_skb->sk; + struct sock_exterr_skb *serr; + struct sk_buff *skb; + int err; + + if (!sk) + return; + + if (hwtstamps) { + *skb_hwtstamps(orig_skb) = + *hwtstamps; + } else { + /* + * no hardware time stamps available, + * so keep the shared tx_flags and only + * store software time stamp + */ + orig_skb->tstamp = ktime_get_real(); + } + + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) + return; + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; + + err = sock_queue_err_skb(sk, skb); + + if (err) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(skb_tstamp_tx); + +void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) +{ + struct sock *sk = skb->sk; + struct sock_exterr_skb *serr; + int err; + + skb->wifi_acked_valid = 1; + skb->wifi_acked = acked; + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; + + err = sock_queue_err_skb(sk, skb); + if (err) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); + + +/** + * skb_partial_csum_set - set up and verify partial csum values for packet + * @skb: the skb to set + * @start: the number of bytes after skb->data to start checksumming. + * @off: the offset from start to place the checksum. + * + * For untrusted partially-checksummed packets, we need to make sure the values + * for skb->csum_start and skb->csum_offset are valid so we don't oops. + * + * This function checks and sets those values and skb->ip_summed: if this + * returns false you should drop the packet. + */ +bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) +{ + if (unlikely(start > skb_headlen(skb)) || + unlikely((int)start + off > skb_headlen(skb) - 2)) { + net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", + start, off, skb_headlen(skb)); + return false; + } + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + start; + skb->csum_offset = off; + skb_set_transport_header(skb, start); + return true; +} +EXPORT_SYMBOL_GPL(skb_partial_csum_set); + +static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) +{ + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + 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_ipv4(struct sk_buff *skb, bool recalculate) +{ + unsigned int off; + bool fragment; + __sum16 *csum; + int err; + + fragment = false; + + err = skb_maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + 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: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + __sum16 *csum; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; + + if (!done || fragment) + 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: + return err; +} + +/** + * skb_checksum_setup - set up partial checksum offset + * @skb: the skb to set up + * @recalculate: if true the pseudo-header checksum will be recalculated + */ +int skb_checksum_setup(struct sk_buff *skb, bool recalculate) +{ + int err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + err = skb_checksum_setup_ipv4(skb, recalculate); + break; + + case htons(ETH_P_IPV6): + err = skb_checksum_setup_ipv6(skb, recalculate); + break; + + default: + err = -EPROTO; + break; + } + + return err; +} +EXPORT_SYMBOL(skb_checksum_setup); + +void __skb_warn_lro_forwarding(const struct sk_buff *skb) +{ + net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", + skb->dev->name); +} +EXPORT_SYMBOL(__skb_warn_lro_forwarding); + +void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) +{ + if (head_stolen) { + skb_release_head_state(skb); + kmem_cache_free(skbuff_head_cache, skb); + } else { + __kfree_skb(skb); + } +} +EXPORT_SYMBOL(kfree_skb_partial); + +/** + * skb_try_coalesce - try to merge skb to prior one + * @to: prior buffer + * @from: buffer to add + * @fragstolen: pointer to boolean + * @delta_truesize: how much more was allocated than was requested + */ +bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, + bool *fragstolen, int *delta_truesize) +{ + int i, delta, len = from->len; + + *fragstolen = false; + + if (skb_cloned(to)) + return false; + + if (len <= skb_tailroom(to)) { + BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); + *delta_truesize = 0; + return true; + } + + if (skb_has_frag_list(to) || skb_has_frag_list(from)) + return false; + + if (skb_headlen(from) != 0) { + struct page *page; + unsigned int offset; + + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + return false; + + if (skb_head_is_locked(from)) + return false; + + delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + + skb_fill_page_desc(to, skb_shinfo(to)->nr_frags, + page, offset, skb_headlen(from)); + *fragstolen = true; + } else { + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) + return false; + + delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); + } + + WARN_ON_ONCE(delta < len); + + memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags, + skb_shinfo(from)->frags, + skb_shinfo(from)->nr_frags * sizeof(skb_frag_t)); + skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags; + + if (!skb_cloned(from)) + skb_shinfo(from)->nr_frags = 0; + + /* if the skb is not cloned this does nothing + * since we set nr_frags to 0. + */ + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) + skb_frag_ref(from, i); + + to->truesize += delta; + to->len += len; + to->data_len += len; + + *delta_truesize = delta; + return true; +} +EXPORT_SYMBOL(skb_try_coalesce); + +/** + * skb_scrub_packet - scrub an skb + * + * @skb: buffer to clean + * @xnet: packet is crossing netns + * + * skb_scrub_packet can be used after encapsulating or decapsulting a packet + * into/from a tunnel. Some information have to be cleared during these + * operations. + * skb_scrub_packet can also be used to clean a skb before injecting it in + * another namespace (@xnet == true). We have to clear all information in the + * skb that could impact namespace isolation. + */ +void skb_scrub_packet(struct sk_buff *skb, bool xnet) +{ + if (xnet) + skb_orphan(skb); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->skb_iif = 0; + skb->ignore_df = 0; + skb_dst_drop(skb); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); + nf_reset_trace(skb); +} +EXPORT_SYMBOL_GPL(skb_scrub_packet); + +/** + * skb_gso_transport_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_transport_seglen is used to determine the real size of the + * individual segments, including Layer4 headers (TCP/UDP). + * + * The MAC/L2 or network (IP, IPv6) headers are not accounted for. + */ +unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; +} +EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index 6e00811d44b..026e01f7027 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -7,8 +7,6 @@ * handler for protocols to use and generic option handler. * * - * Version: $Id: sock.c,v 1.117 2002/02/01 22:01:03 davem Exp $ - * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> @@ -34,7 +32,7 @@ * Alan Cox : TCP ack handling is buggy, the DESTROY timer * was buggy. Put a remove_sock() in the handler * for memory when we hit 0. Also altered the timer - * code. The ACK stuff can wait and needs major + * code. The ACK stuff can wait and needs major * TCP layer surgery. * Alan Cox : Fixed TCP ack bug, removed remove sock * and fixed timer/inet_bh race. @@ -91,9 +89,11 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> -#include <linux/config.h> #include <linux/errno.h> +#include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> @@ -112,42 +112,273 @@ #include <linux/poll.h> #include <linux/tcp.h> #include <linux/init.h> +#include <linux/highmem.h> +#include <linux/user_namespace.h> +#include <linux/static_key.h> +#include <linux/memcontrol.h> +#include <linux/prefetch.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> +#include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> +#include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> +#include <net/cls_cgroup.h> +#include <net/netprio_cgroup.h> #include <linux/filter.h> +#include <trace/events/sock.h> + #ifdef CONFIG_INET #include <net/tcp.h> #endif +#include <net/busy_poll.h> + +static DEFINE_MUTEX(proto_list_mutex); +static LIST_HEAD(proto_list); + +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + +#ifdef CONFIG_MEMCG_KMEM +int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) +{ + struct proto *proto; + int ret = 0; + + mutex_lock(&proto_list_mutex); + list_for_each_entry(proto, &proto_list, node) { + if (proto->init_cgroup) { + ret = proto->init_cgroup(memcg, ss); + if (ret) + goto out; + } + } + + mutex_unlock(&proto_list_mutex); + return ret; +out: + list_for_each_entry_continue_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(memcg); + mutex_unlock(&proto_list_mutex); + return ret; +} + +void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) +{ + struct proto *proto; + + mutex_lock(&proto_list_mutex); + list_for_each_entry_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(memcg); + mutex_unlock(&proto_list_mutex); +} +#endif + +/* + * Each address family might have different locking rules, so we have + * one slock key per address family: + */ +static struct lock_class_key af_family_keys[AF_MAX]; +static struct lock_class_key af_family_slock_keys[AF_MAX]; + +#if defined(CONFIG_MEMCG_KMEM) +struct static_key memcg_socket_limit_enabled; +EXPORT_SYMBOL(memcg_socket_limit_enabled); +#endif + +/* + * Make lock validator output more readable. (we pre-construct these + * strings build-time, so that runtime initialization of socket + * locks is fast): + */ +static const char *const af_family_key_strings[AF_MAX+1] = { + "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , + "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", + "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , + "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" , + "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , + "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , + "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , + "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , + "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , + "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , + "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , + "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , + "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , + "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_MAX" +}; +static const char *const af_family_slock_key_strings[AF_MAX+1] = { + "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , + "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", + "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , + "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" , + "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , + "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , + "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , + "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" , + "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , + "slock-27" , "slock-28" , "slock-AF_CAN" , + "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , + "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , + "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , + "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_MAX" +}; +static const char *const af_family_clock_key_strings[AF_MAX+1] = { + "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , + "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", + "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , + "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" , + "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" , + "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" , + "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , + "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , + "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , + "clock-27" , "clock-28" , "clock-AF_CAN" , + "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , + "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , + "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , + "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_MAX" +}; + +/* + * sk_callback_lock locking rules are per-address-family, + * so split the lock classes by using a per-AF key: + */ +static struct lock_class_key af_callback_keys[AF_MAX]; + /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 -#define _SK_MEM_OVERHEAD (sizeof(struct sk_buff) + 256) +#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) /* Run time adjustable parameters. */ -__u32 sysctl_wmem_max = SK_WMEM_MAX; -__u32 sysctl_rmem_max = SK_RMEM_MAX; -__u32 sysctl_wmem_default = SK_WMEM_MAX; -__u32 sysctl_rmem_default = SK_RMEM_MAX; +__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +EXPORT_SYMBOL(sysctl_wmem_max); +__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +EXPORT_SYMBOL(sysctl_rmem_max); +__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; + +/* Maximal space eaten by iovec or ancillary data plus some space */ +int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); +EXPORT_SYMBOL(sysctl_optmem_max); + +struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(memalloc_socks); + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. + * It's the responsibility of the admin to adjust min_free_kbytes + * to meet the requirements + */ +void sk_set_memalloc(struct sock *sk) +{ + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + static_key_slow_inc(&memalloc_socks); +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +void sk_clear_memalloc(struct sock *sk) +{ + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + static_key_slow_dec(&memalloc_socks); + + /* + * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward + * progress of swapping. However, if SOCK_MEMALLOC is cleared while + * it has rmem allocations there is a risk that the user of the + * socket cannot make forward progress due to exceeding the rmem + * limits. By rights, sk_clear_memalloc() should only be called + * on sockets being torn down but warn and reset the accounting if + * that assumption breaks. + */ + if (WARN_ON(sk->sk_forward_alloc)) + sk_mem_reclaim(sk); +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + unsigned long pflags = current->flags; + + /* these should have been dropped before queueing */ + BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); + + current->flags |= PF_MEMALLOC; + ret = sk->sk_backlog_rcv(sk, skb); + tsk_restore_flags(current, pflags, PF_MEMALLOC); -/* Maximal space eaten by iovec or ancilliary data plus some space */ -int sysctl_optmem_max = sizeof(unsigned long)*(2*UIO_MAXIOV + 512); + return ret; +} +EXPORT_SYMBOL(__sk_backlog_rcv); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -157,7 +388,20 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) return -EINVAL; if (copy_from_user(&tv, optval, sizeof(tv))) return -EFAULT; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) + return -EDOM; + + if (tv.tv_sec < 0) { + static int warned __read_mostly; + *timeo_p = 0; + if (warned < 10 && net_ratelimit()) { + warned++; + pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", + __func__, current->comm, task_pid_nr(current)); + } + return 0; + } *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; @@ -170,22 +414,250 @@ static void sock_warn_obsolete_bsdism(const char *name) { static int warned; static char warncomm[TASK_COMM_LEN]; - if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); - printk(KERN_WARNING "process `%s' is using obsolete " - "%s SO_BSDCOMPAT\n", warncomm, name); + if (strcmp(warncomm, current->comm) && warned < 5) { + strcpy(warncomm, current->comm); + pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", + warncomm, name); warned++; } } -static void sock_disable_timestamp(struct sock *sk) -{ - if (sock_flag(sk, SOCK_TIMESTAMP)) { - sock_reset_flag(sk, SOCK_TIMESTAMP); - net_disable_timestamp(); +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + +static void sock_disable_timestamp(struct sock *sk, unsigned long flags) +{ + if (sk->sk_flags & flags) { + sk->sk_flags &= ~flags; + if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP)) + net_disable_timestamp(); + } +} + + +int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + int err; + int skb_len; + unsigned long flags; + struct sk_buff_head *list = &sk->sk_receive_queue; + + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { + atomic_inc(&sk->sk_drops); + trace_sock_rcvqueue_full(sk, skb); + return -ENOMEM; + } + + err = sk_filter(sk, skb); + if (err) + return err; + + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { + atomic_inc(&sk->sk_drops); + return -ENOBUFS; + } + + skb->dev = NULL; + skb_set_owner_r(skb, sk); + + /* Cache the SKB length before we tack it onto the receive + * queue. Once it is added it no longer belongs to us and + * may be freed by other threads of control pulling packets + * from the queue. + */ + skb_len = skb->len; + + /* we escape from rcu protected region, make sure we dont leak + * a norefcounted dst + */ + skb_dst_force(skb); + + spin_lock_irqsave(&list->lock, flags); + skb->dropcount = atomic_read(&sk->sk_drops); + __skb_queue_tail(list, skb); + spin_unlock_irqrestore(&list->lock, flags); + + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_data_ready(sk); + return 0; +} +EXPORT_SYMBOL(sock_queue_rcv_skb); + +int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) +{ + int rc = NET_RX_SUCCESS; + + if (sk_filter(sk, skb)) + goto discard_and_relse; + + skb->dev = NULL; + + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + goto discard_and_relse; + } + if (nested) + bh_lock_sock_nested(sk); + else + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + /* + * trylock + unlock semantics: + */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); + + rc = sk_backlog_rcv(sk, skb); + + mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + bh_unlock_sock(sk); + atomic_inc(&sk->sk_drops); + goto discard_and_relse; + } + + bh_unlock_sock(sk); +out: + sock_put(sk); + return rc; +discard_and_relse: + kfree_skb(skb); + goto out; +} +EXPORT_SYMBOL(sk_receive_skb); + +struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) +{ + struct dst_entry *dst = __sk_dst_get(sk); + + if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + sk_tx_queue_clear(sk); + RCU_INIT_POINTER(sk->sk_dst_cache, NULL); + dst_release(dst); + return NULL; + } + + return dst; +} +EXPORT_SYMBOL(__sk_dst_check); + +struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) +{ + struct dst_entry *dst = sk_dst_get(sk); + + if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + sk_dst_reset(sk); + dst_release(dst); + return NULL; + } + + return dst; +} +EXPORT_SYMBOL(sk_dst_check); + +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + char devname[IFNAMSIZ]; + int index; + + /* Sorry... */ + ret = -EPERM; + if (!ns_capable(net->user_ns, CAP_NET_RAW)) + goto out; + + ret = -EINVAL; + if (optlen < 0) + goto out; + + /* Bind this socket to a particular device like "eth0", + * as specified in the passed interface name. If the + * name is "" or the option length is zero the socket + * is not bound. + */ + if (optlen > IFNAMSIZ - 1) + optlen = IFNAMSIZ - 1; + memset(devname, 0, sizeof(devname)); + + ret = -EFAULT; + if (copy_from_user(devname, optval, optlen)) + goto out; + + index = 0; + if (devname[0] != '\0') { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, devname); + if (dev) + index = dev->ifindex; + rcu_read_unlock(); + ret = -ENODEV; + if (!dev) + goto out; + } + + lock_sock(sk); + sk->sk_bound_dev_if = index; + sk_dst_reset(sk); + release_sock(sk); + + ret = 0; + +out: +#endif + + return ret; +} + +static int sock_getbindtodevice(struct sock *sk, char __user *optval, + int __user *optlen, int len) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + char devname[IFNAMSIZ]; + + if (sk->sk_bound_dev_if == 0) { + len = 0; + goto zero; } + + ret = -EINVAL; + if (len < IFNAMSIZ) + goto out; + + ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); + if (ret) + goto out; + + len = strlen(devname) + 1; + + ret = -EFAULT; + if (copy_to_user(optval, devname, len)) + goto out; + +zero: + ret = -EFAULT; + if (put_user(len, optlen)) + goto out; + + ret = 0; + +out: +#endif + + return ret; } +static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) +{ + if (valbool) + sock_set_flag(sk, bit); + else + sock_reset_flag(sk, bit); +} /* * This is meant for all protocols to use and covers goings on @@ -193,482 +665,677 @@ static void sock_disable_timestamp(struct sock *sk) */ int sock_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { - struct sock *sk=sock->sk; - struct sk_filter *filter; + struct sock *sk = sock->sk; int val; int valbool; struct linger ling; int ret = 0; - + /* * Options without arguments */ -#ifdef SO_DONTLINGER /* Compatibility item... */ - if (optname == SO_DONTLINGER) { - lock_sock(sk); - sock_reset_flag(sk, SOCK_LINGER); - release_sock(sk); - return 0; - } -#endif - - if(optlen<sizeof(int)) - return(-EINVAL); - + if (optname == SO_BINDTODEVICE) + return sock_setbindtodevice(sk, optval, optlen); + + if (optlen < sizeof(int)) + return -EINVAL; + if (get_user(val, (int __user *)optval)) return -EFAULT; - - valbool = val?1:0; + + valbool = val ? 1 : 0; lock_sock(sk); - switch(optname) - { - case SO_DEBUG: - if(val && !capable(CAP_NET_ADMIN)) - { - ret = -EACCES; - } - else if (valbool) - sock_set_flag(sk, SOCK_DBG); - else - sock_reset_flag(sk, SOCK_DBG); - break; - case SO_REUSEADDR: - sk->sk_reuse = valbool; - break; - case SO_TYPE: - case SO_ERROR: - ret = -ENOPROTOOPT; - break; - case SO_DONTROUTE: - if (valbool) - sock_set_flag(sk, SOCK_LOCALROUTE); - else - sock_reset_flag(sk, SOCK_LOCALROUTE); - break; - case SO_BROADCAST: - sock_valbool_flag(sk, SOCK_BROADCAST, valbool); - break; - case SO_SNDBUF: - /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_wmem_max) - val = sysctl_wmem_max; + switch (optname) { + case SO_DEBUG: + if (val && !capable(CAP_NET_ADMIN)) + ret = -EACCES; + else + sock_valbool_flag(sk, SOCK_DBG, valbool); + break; + case SO_REUSEADDR: + sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + break; + case SO_REUSEPORT: + sk->sk_reuseport = valbool; + break; + case SO_TYPE: + case SO_PROTOCOL: + case SO_DOMAIN: + case SO_ERROR: + ret = -ENOPROTOOPT; + break; + case SO_DONTROUTE: + sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); + break; + case SO_BROADCAST: + sock_valbool_flag(sk, SOCK_BROADCAST, valbool); + break; + case SO_SNDBUF: + /* Don't error on this BSD doesn't and if you think + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: - sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - if ((val * 2) < SOCK_MIN_SNDBUF) - sk->sk_sndbuf = SOCK_MIN_SNDBUF; - else - sk->sk_sndbuf = val * 2; + sk->sk_userlocks |= SOCK_SNDBUF_LOCK; + sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + /* Wake up sending tasks if we upped the value. */ + sk->sk_write_space(sk); + break; - /* - * Wake up sending tasks if we - * upped the value. - */ - sk->sk_write_space(sk); + case SO_SNDBUFFORCE: + if (!capable(CAP_NET_ADMIN)) { + ret = -EPERM; break; + } + goto set_sndbuf; - case SO_SNDBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - goto set_sndbuf; - - case SO_RCVBUF: - /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_rmem_max) - val = sysctl_rmem_max; + case SO_RCVBUF: + /* Don't error on this BSD doesn't and if you think + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_rmem_max); set_rcvbuf: - sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - /* FIXME: is this lower bound the right one? */ - if ((val * 2) < SOCK_MIN_RCVBUF) - sk->sk_rcvbuf = SOCK_MIN_RCVBUF; - else - sk->sk_rcvbuf = val * 2; - break; + sk->sk_userlocks |= SOCK_RCVBUF_LOCK; + /* + * We double it on the way in to account for + * "struct sk_buff" etc. overhead. Applications + * assume that the SO_RCVBUF setting they make will + * allow that much actual data to be received on that + * socket. + * + * Applications are unaware that "struct sk_buff" and + * other overheads allocate from the receive buffer + * during socket buffer allocation. + * + * And after considering the possible alternatives, + * returning the value we actually used in getsockopt + * is the most desirable behavior. + */ + sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); + break; - case SO_RCVBUFFORCE: - if (!capable(CAP_NET_ADMIN)) { - ret = -EPERM; - break; - } - goto set_rcvbuf; + case SO_RCVBUFFORCE: + if (!capable(CAP_NET_ADMIN)) { + ret = -EPERM; + break; + } + goto set_rcvbuf; - case SO_KEEPALIVE: + case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) - tcp_set_keepalive(sk, valbool); + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) + tcp_set_keepalive(sk, valbool); #endif - sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); - break; - - case SO_OOBINLINE: - sock_valbool_flag(sk, SOCK_URGINLINE, valbool); - break; - - case SO_NO_CHECK: - sk->sk_no_check = valbool; + sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); + break; + + case SO_OOBINLINE: + sock_valbool_flag(sk, SOCK_URGINLINE, valbool); + break; + + case SO_NO_CHECK: + sk->sk_no_check_tx = valbool; + break; + + case SO_PRIORITY: + if ((val >= 0 && val <= 6) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + sk->sk_priority = val; + else + ret = -EPERM; + break; + + case SO_LINGER: + if (optlen < sizeof(ling)) { + ret = -EINVAL; /* 1003.1g */ break; - - case SO_PRIORITY: - if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) - sk->sk_priority = val; - else - ret = -EPERM; + } + if (copy_from_user(&ling, optval, sizeof(ling))) { + ret = -EFAULT; break; - - case SO_LINGER: - if(optlen<sizeof(ling)) { - ret = -EINVAL; /* 1003.1g */ - break; - } - if (copy_from_user(&ling,optval,sizeof(ling))) { - ret = -EFAULT; - break; - } - if (!ling.l_onoff) - sock_reset_flag(sk, SOCK_LINGER); - else { + } + if (!ling.l_onoff) + sock_reset_flag(sk, SOCK_LINGER); + else { #if (BITS_PER_LONG == 32) - if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) - sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; - else + if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) + sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; + else #endif - sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; - sock_set_flag(sk, SOCK_LINGER); - } - break; - - case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); - break; - - case SO_PASSCRED: - if (valbool) - set_bit(SOCK_PASSCRED, &sock->flags); + sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; + sock_set_flag(sk, SOCK_LINGER); + } + break; + + case SO_BSDCOMPAT: + sock_warn_obsolete_bsdism("setsockopt"); + break; + + case SO_PASSCRED: + if (valbool) + set_bit(SOCK_PASSCRED, &sock->flags); + else + clear_bit(SOCK_PASSCRED, &sock->flags); + break; + + case SO_TIMESTAMP: + case SO_TIMESTAMPNS: + if (valbool) { + if (optname == SO_TIMESTAMP) + sock_reset_flag(sk, SOCK_RCVTSTAMPNS); else - clear_bit(SOCK_PASSCRED, &sock->flags); - break; - - case SO_TIMESTAMP: - if (valbool) { - sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk); - } else - sock_reset_flag(sk, SOCK_RCVTSTAMP); - break; - - case SO_RCVLOWAT: - if (val < 0) - val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; - break; - - case SO_RCVTIMEO: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); - break; + sock_set_flag(sk, SOCK_RCVTSTAMPNS); + sock_set_flag(sk, SOCK_RCVTSTAMP); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); + } else { + sock_reset_flag(sk, SOCK_RCVTSTAMP); + sock_reset_flag(sk, SOCK_RCVTSTAMPNS); + } + break; - case SO_SNDTIMEO: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + case SO_TIMESTAMPING: + if (val & ~SOF_TIMESTAMPING_MASK) { + ret = -EINVAL; break; - -#ifdef CONFIG_NETDEVICES - case SO_BINDTODEVICE: - { - char devname[IFNAMSIZ]; - - /* Sorry... */ - if (!capable(CAP_NET_RAW)) { - ret = -EPERM; + } + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, + val & SOF_TIMESTAMPING_TX_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE, + val & SOF_TIMESTAMPING_TX_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE, + val & SOF_TIMESTAMPING_RX_HARDWARE); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, + val & SOF_TIMESTAMPING_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, + val & SOF_TIMESTAMPING_SYS_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE, + val & SOF_TIMESTAMPING_RAW_HARDWARE); + break; + + case SO_RCVLOWAT: + if (val < 0) + val = INT_MAX; + sk->sk_rcvlowat = val ? : 1; + break; + + case SO_RCVTIMEO: + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); + break; + + case SO_SNDTIMEO: + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + break; + + case SO_ATTACH_FILTER: + ret = -EINVAL; + if (optlen == sizeof(struct sock_fprog)) { + struct sock_fprog fprog; + + ret = -EFAULT; + if (copy_from_user(&fprog, optval, sizeof(fprog))) break; - } - /* Bind this socket to a particular device like "eth0", - * as specified in the passed interface name. If the - * name is "" or the option length is zero the socket - * is not bound. - */ - - if (!valbool) { - sk->sk_bound_dev_if = 0; - } else { - if (optlen > IFNAMSIZ) - optlen = IFNAMSIZ; - if (copy_from_user(devname, optval, optlen)) { - ret = -EFAULT; - break; - } + ret = sk_attach_filter(&fprog, sk); + } + break; + + case SO_DETACH_FILTER: + ret = sk_detach_filter(sk); + break; + + case SO_LOCK_FILTER: + if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) + ret = -EPERM; + else + sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); + break; + + case SO_PASSSEC: + if (valbool) + set_bit(SOCK_PASSSEC, &sock->flags); + else + clear_bit(SOCK_PASSSEC, &sock->flags); + break; + case SO_MARK: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + ret = -EPERM; + else + sk->sk_mark = val; + break; - /* Remove any cached route for this socket. */ - sk_dst_reset(sk); - - if (devname[0] == '\0') { - sk->sk_bound_dev_if = 0; - } else { - struct net_device *dev = dev_get_by_name(devname); - if (!dev) { - ret = -ENODEV; - break; - } - sk->sk_bound_dev_if = dev->ifindex; - dev_put(dev); - } - } - break; + /* We implement the SO_SNDLOWAT etc to + not be settable (1003.1g 5.3) */ + case SO_RXQ_OVFL: + sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); + break; + + case SO_WIFI_STATUS: + sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); + break; + + case SO_PEEK_OFF: + if (sock->ops->set_peek_off) + ret = sock->ops->set_peek_off(sk, val); + else + ret = -EOPNOTSUPP; + break; + + case SO_NOFCS: + sock_valbool_flag(sk, SOCK_NOFCS, valbool); + break; + + case SO_SELECT_ERR_QUEUE: + sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); + break; + +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_BUSY_POLL: + /* allow unprivileged users to decrease the value */ + if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) + ret = -EPERM; + else { + if (val < 0) + ret = -EINVAL; + else + sk->sk_ll_usec = val; } + break; #endif + case SO_MAX_PACING_RATE: + sk->sk_max_pacing_rate = val; + sk->sk_pacing_rate = min(sk->sk_pacing_rate, + sk->sk_max_pacing_rate); + break; - case SO_ATTACH_FILTER: - ret = -EINVAL; - if (optlen == sizeof(struct sock_fprog)) { - struct sock_fprog fprog; - - ret = -EFAULT; - if (copy_from_user(&fprog, optval, sizeof(fprog))) - break; - - ret = sk_attach_filter(&fprog, sk); - } - break; - - case SO_DETACH_FILTER: - spin_lock_bh(&sk->sk_lock.slock); - filter = sk->sk_filter; - if (filter) { - sk->sk_filter = NULL; - spin_unlock_bh(&sk->sk_lock.slock); - sk_filter_release(sk, filter); - break; - } - spin_unlock_bh(&sk->sk_lock.slock); - ret = -ENONET; - break; - - /* We implement the SO_SNDLOWAT etc to - not be settable (1003.1g 5.3) */ - default: - ret = -ENOPROTOOPT; - break; - } + default: + ret = -ENOPROTOOPT; + break; + } release_sock(sk); return ret; } +EXPORT_SYMBOL(sock_setsockopt); + +static void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) +{ + ucred->pid = pid_vnr(pid); + ucred->uid = ucred->gid = -1; + if (cred) { + struct user_namespace *current_ns = current_user_ns(); + + ucred->uid = from_kuid_munged(current_ns, cred->euid); + ucred->gid = from_kgid_munged(current_ns, cred->egid); + } +} int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; - - union - { - int val; - struct linger ling; + + union { + int val; + struct linger ling; struct timeval tm; } v; - - unsigned int lv = sizeof(int); + + int lv = sizeof(int); int len; - - if(get_user(len,optlen)) - return -EFAULT; - if(len < 0) + + if (get_user(len, optlen)) + return -EFAULT; + if (len < 0) return -EINVAL; - - switch(optname) - { - case SO_DEBUG: - v.val = sock_flag(sk, SOCK_DBG); - break; - - case SO_DONTROUTE: - v.val = sock_flag(sk, SOCK_LOCALROUTE); - break; - - case SO_BROADCAST: - v.val = !!sock_flag(sk, SOCK_BROADCAST); - break; - case SO_SNDBUF: - v.val = sk->sk_sndbuf; - break; - - case SO_RCVBUF: - v.val = sk->sk_rcvbuf; - break; + memset(&v, 0, sizeof(v)); + + switch (optname) { + case SO_DEBUG: + v.val = sock_flag(sk, SOCK_DBG); + break; + + case SO_DONTROUTE: + v.val = sock_flag(sk, SOCK_LOCALROUTE); + break; + + case SO_BROADCAST: + v.val = sock_flag(sk, SOCK_BROADCAST); + break; + + case SO_SNDBUF: + v.val = sk->sk_sndbuf; + break; + + case SO_RCVBUF: + v.val = sk->sk_rcvbuf; + break; + + case SO_REUSEADDR: + v.val = sk->sk_reuse; + break; + + case SO_REUSEPORT: + v.val = sk->sk_reuseport; + break; + + case SO_KEEPALIVE: + v.val = sock_flag(sk, SOCK_KEEPOPEN); + break; + + case SO_TYPE: + v.val = sk->sk_type; + break; + + case SO_PROTOCOL: + v.val = sk->sk_protocol; + break; + + case SO_DOMAIN: + v.val = sk->sk_family; + break; + + case SO_ERROR: + v.val = -sock_error(sk); + if (v.val == 0) + v.val = xchg(&sk->sk_err_soft, 0); + break; + + case SO_OOBINLINE: + v.val = sock_flag(sk, SOCK_URGINLINE); + break; + + case SO_NO_CHECK: + v.val = sk->sk_no_check_tx; + break; + + case SO_PRIORITY: + v.val = sk->sk_priority; + break; + + case SO_LINGER: + lv = sizeof(v.ling); + v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); + v.ling.l_linger = sk->sk_lingertime / HZ; + break; + + case SO_BSDCOMPAT: + sock_warn_obsolete_bsdism("getsockopt"); + break; + + case SO_TIMESTAMP: + v.val = sock_flag(sk, SOCK_RCVTSTAMP) && + !sock_flag(sk, SOCK_RCVTSTAMPNS); + break; + + case SO_TIMESTAMPNS: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); + break; + + case SO_TIMESTAMPING: + v.val = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_TX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_TX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_RX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)) + v.val |= SOF_TIMESTAMPING_SYS_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RAW_HARDWARE; + break; + + case SO_RCVTIMEO: + lv = sizeof(struct timeval); + if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { + v.tm.tv_sec = 0; + v.tm.tv_usec = 0; + } else { + v.tm.tv_sec = sk->sk_rcvtimeo / HZ; + v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; + } + break; + + case SO_SNDTIMEO: + lv = sizeof(struct timeval); + if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { + v.tm.tv_sec = 0; + v.tm.tv_usec = 0; + } else { + v.tm.tv_sec = sk->sk_sndtimeo / HZ; + v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; + } + break; - case SO_REUSEADDR: - v.val = sk->sk_reuse; - break; + case SO_RCVLOWAT: + v.val = sk->sk_rcvlowat; + break; - case SO_KEEPALIVE: - v.val = !!sock_flag(sk, SOCK_KEEPOPEN); - break; + case SO_SNDLOWAT: + v.val = 1; + break; - case SO_TYPE: - v.val = sk->sk_type; - break; + case SO_PASSCRED: + v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); + break; - case SO_ERROR: - v.val = -sock_error(sk); - if(v.val==0) - v.val = xchg(&sk->sk_err_soft, 0); - break; + case SO_PEERCRED: + { + struct ucred peercred; + if (len > sizeof(peercred)) + len = sizeof(peercred); + cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + if (copy_to_user(optval, &peercred, len)) + return -EFAULT; + goto lenout; + } - case SO_OOBINLINE: - v.val = !!sock_flag(sk, SOCK_URGINLINE); - break; - - case SO_NO_CHECK: - v.val = sk->sk_no_check; - break; + case SO_PEERNAME: + { + char address[128]; + + if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) + return -ENOTCONN; + if (lv < len) + return -EINVAL; + if (copy_to_user(optval, address, len)) + return -EFAULT; + goto lenout; + } - case SO_PRIORITY: - v.val = sk->sk_priority; - break; - - case SO_LINGER: - lv = sizeof(v.ling); - v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); - v.ling.l_linger = sk->sk_lingertime / HZ; - break; - - case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); - break; + /* Dubious BSD thing... Probably nobody even uses it, but + * the UNIX standard wants it for whatever reason... -DaveM + */ + case SO_ACCEPTCONN: + v.val = sk->sk_state == TCP_LISTEN; + break; - case SO_TIMESTAMP: - v.val = sock_flag(sk, SOCK_RCVTSTAMP); - break; + case SO_PASSSEC: + v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); + break; - case SO_RCVTIMEO: - lv=sizeof(struct timeval); - if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_rcvtimeo / HZ; - v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ; - } - break; + case SO_PEERSEC: + return security_socket_getpeersec_stream(sock, optval, optlen, len); - case SO_SNDTIMEO: - lv=sizeof(struct timeval); - if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_sndtimeo / HZ; - v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ; - } - break; + case SO_MARK: + v.val = sk->sk_mark; + break; - case SO_RCVLOWAT: - v.val = sk->sk_rcvlowat; - break; + case SO_RXQ_OVFL: + v.val = sock_flag(sk, SOCK_RXQ_OVFL); + break; - case SO_SNDLOWAT: - v.val=1; - break; + case SO_WIFI_STATUS: + v.val = sock_flag(sk, SOCK_WIFI_STATUS); + break; - case SO_PASSCRED: - v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; - break; + case SO_PEEK_OFF: + if (!sock->ops->set_peek_off) + return -EOPNOTSUPP; - case SO_PEERCRED: - if (len > sizeof(sk->sk_peercred)) - len = sizeof(sk->sk_peercred); - if (copy_to_user(optval, &sk->sk_peercred, len)) - return -EFAULT; - goto lenout; - - case SO_PEERNAME: - { - char address[128]; - - if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2)) - return -ENOTCONN; - if (lv < len) - return -EINVAL; - if (copy_to_user(optval, address, len)) - return -EFAULT; - goto lenout; - } + v.val = sk->sk_peek_off; + break; + case SO_NOFCS: + v.val = sock_flag(sk, SOCK_NOFCS); + break; - /* Dubious BSD thing... Probably nobody even uses it, but - * the UNIX standard wants it for whatever reason... -DaveM - */ - case SO_ACCEPTCONN: - v.val = sk->sk_state == TCP_LISTEN; - break; + case SO_BINDTODEVICE: + return sock_getbindtodevice(sk, optval, optlen, len); + + case SO_GET_FILTER: + len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + if (len < 0) + return len; + + goto lenout; + + case SO_LOCK_FILTER: + v.val = sock_flag(sk, SOCK_FILTER_LOCKED); + break; + + case SO_BPF_EXTENSIONS: + v.val = bpf_tell_extensions(); + break; + + case SO_SELECT_ERR_QUEUE: + v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); + break; - case SO_PEERSEC: - return security_socket_getpeersec(sock, optval, optlen, len); +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_BUSY_POLL: + v.val = sk->sk_ll_usec; + break; +#endif + + case SO_MAX_PACING_RATE: + v.val = sk->sk_max_pacing_rate; + break; - default: - return(-ENOPROTOOPT); + default: + return -ENOPROTOOPT; } + if (len > lv) len = lv; if (copy_to_user(optval, &v, len)) return -EFAULT; lenout: - if (put_user(len, optlen)) - return -EFAULT; - return 0; + if (put_user(len, optlen)) + return -EFAULT; + return 0; } -/** - * sk_alloc - All socket objects are allocated here - * @family: protocol family - * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) - * @prot: struct proto associated with this new sock instance - * @zero_it: if we should zero the newly allocated sock +/* + * Initialize an sk_lock. + * + * (We also register the sk_lock with the lock validator.) */ -struct sock *sk_alloc(int family, gfp_t priority, - struct proto *prot, int zero_it) +static inline void sock_lock_init(struct sock *sk) { - struct sock *sk = NULL; - kmem_cache_t *slab = prot->slab; + sock_lock_init_class_and_name(sk, + af_family_slock_key_strings[sk->sk_family], + af_family_slock_keys + sk->sk_family, + af_family_key_strings[sk->sk_family], + af_family_keys + sk->sk_family); +} - if (slab != NULL) - sk = kmem_cache_alloc(slab, priority); - else - sk = kmalloc(prot->obj_size, priority); +/* + * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, + * even temporarly, because of RCU lookups. sk_node should also be left as is. + * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end + */ +static void sock_copy(struct sock *nsk, const struct sock *osk) +{ +#ifdef CONFIG_SECURITY_NETWORK + void *sptr = nsk->sk_security; +#endif + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); - if (sk) { - if (zero_it) { - memset(sk, 0, prot->obj_size); - sk->sk_family = family; - /* - * See comment in struct sock definition to understand - * why we need sk_prot_creator -acme - */ - sk->sk_prot = sk->sk_prot_creator = prot; - sock_lock_init(sk); + memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + +#ifdef CONFIG_SECURITY_NETWORK + nsk->sk_security = sptr; + security_sk_clone(osk, nsk); +#endif +} + +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) +{ + unsigned long nulls1, nulls2; + + nulls1 = offsetof(struct sock, __sk_common.skc_node.next); + nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next); + if (nulls1 > nulls2) + swap(nulls1, nulls2); + + if (nulls1 != 0) + memset((char *)sk, 0, nulls1); + memset((char *)sk + nulls1 + sizeof(void *), 0, + nulls2 - nulls1 - sizeof(void *)); + memset((char *)sk + nulls2 + sizeof(void *), 0, + size - nulls2 - sizeof(void *)); +} +EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls); + +static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, + int family) +{ + struct sock *sk; + struct kmem_cache *slab; + + slab = prot->slab; + if (slab != NULL) { + sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO); + if (!sk) + return sk; + if (priority & __GFP_ZERO) { + if (prot->clear_sk) + prot->clear_sk(sk, prot->obj_size); + else + sk_prot_clear_nulls(sk, prot->obj_size); } - + } else + sk = kmalloc(prot->obj_size, priority); + + if (sk != NULL) { + kmemcheck_annotate_bitfield(sk, flags); + if (security_sk_alloc(sk, family, priority)) goto out_free; if (!try_module_get(prot->owner)) - goto out_free; + goto out_free_sec; + sk_tx_queue_clear(sk); } + return sk; +out_free_sec: + security_sk_free(sk); out_free: if (slab != NULL) kmem_cache_free(slab, sk); @@ -677,68 +1344,183 @@ out_free: return NULL; } -void sk_free(struct sock *sk) +static void sk_prot_free(struct proto *prot, struct sock *sk) +{ + struct kmem_cache *slab; + struct module *owner; + + owner = prot->owner; + slab = prot->slab; + + security_sk_free(sk); + if (slab != NULL) + kmem_cache_free(slab, sk); + else + kfree(sk); + module_put(owner); +} + +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) +void sock_update_netprioidx(struct sock *sk) +{ + if (in_interrupt()) + return; + + sk->sk_cgrp_prioidx = task_netprioidx(current); +} +EXPORT_SYMBOL_GPL(sock_update_netprioidx); +#endif + +/** + * sk_alloc - All socket objects are allocated here + * @net: the applicable net namespace + * @family: protocol family + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * @prot: struct proto associated with this new sock instance + */ +struct sock *sk_alloc(struct net *net, int family, gfp_t priority, + struct proto *prot) +{ + struct sock *sk; + + sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family); + if (sk) { + sk->sk_family = family; + /* + * See comment in struct sock definition to understand + * why we need sk_prot_creator -acme + */ + sk->sk_prot = sk->sk_prot_creator = prot; + sock_lock_init(sk); + sock_net_set(sk, get_net(net)); + atomic_set(&sk->sk_wmem_alloc, 1); + + sock_update_classid(sk); + sock_update_netprioidx(sk); + } + + return sk; +} +EXPORT_SYMBOL(sk_alloc); + +static void __sk_free(struct sock *sk) { struct sk_filter *filter; - struct module *owner = sk->sk_prot_creator->owner; if (sk->sk_destruct) sk->sk_destruct(sk); - filter = sk->sk_filter; + filter = rcu_dereference_check(sk->sk_filter, + atomic_read(&sk->sk_wmem_alloc) == 0); if (filter) { - sk_filter_release(sk, filter); - sk->sk_filter = NULL; + sk_filter_uncharge(sk, filter); + RCU_INIT_POINTER(sk->sk_filter, NULL); } - sock_disable_timestamp(sk); + sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); if (atomic_read(&sk->sk_omem_alloc)) - printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", - __FUNCTION__, atomic_read(&sk->sk_omem_alloc)); + pr_debug("%s: optmem leakage (%d bytes) detected\n", + __func__, atomic_read(&sk->sk_omem_alloc)); - security_sk_free(sk); - if (sk->sk_prot_creator->slab != NULL) - kmem_cache_free(sk->sk_prot_creator->slab, sk); - else - kfree(sk); - module_put(owner); + if (sk->sk_peer_cred) + put_cred(sk->sk_peer_cred); + put_pid(sk->sk_peer_pid); + put_net(sock_net(sk)); + sk_prot_free(sk->sk_prot_creator, sk); +} + +void sk_free(struct sock *sk) +{ + /* + * We subtract one from sk_wmem_alloc and can know if + * some packets are still in some tx queue. + * If not null, sock_wfree() will call __sk_free(sk) later + */ + if (atomic_dec_and_test(&sk->sk_wmem_alloc)) + __sk_free(sk); +} +EXPORT_SYMBOL(sk_free); + +/* + * Last sock_put should drop reference to sk->sk_net. It has already + * been dropped in sk_change_net. Taking reference to stopping namespace + * is not an option. + * Take reference to a socket to remove it from hash _alive_ and after that + * destroy it in the context of init_net. + */ +void sk_release_kernel(struct sock *sk) +{ + if (sk == NULL || sk->sk_socket == NULL) + return; + + sock_hold(sk); + sock_release(sk->sk_socket); + release_net(sock_net(sk)); + sock_net_set(sk, get_net(&init_net)); + sock_put(sk); +} +EXPORT_SYMBOL(sk_release_kernel); + +static void sk_update_clone(const struct sock *sk, struct sock *newsk) +{ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_update_memcg(newsk); } -struct sock *sk_clone(const struct sock *sk, const gfp_t priority) +/** + * sk_clone_lock - clone a socket, and lock its clone + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { - struct sock *newsk = sk_alloc(sk->sk_family, priority, sk->sk_prot, 0); + struct sock *newsk; + newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family); if (newsk != NULL) { struct sk_filter *filter; - memcpy(newsk, sk, sk->sk_prot->obj_size); + sock_copy(newsk, sk); /* SANITY */ + get_net(sock_net(newsk)); sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); + newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; + newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); - atomic_set(&newsk->sk_wmem_alloc, 0); + /* + * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) + */ + atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); skb_queue_head_init(&newsk->sk_receive_queue); skb_queue_head_init(&newsk->sk_write_queue); +#ifdef CONFIG_NET_DMA + skb_queue_head_init(&newsk->sk_async_wait_queue); +#endif - rwlock_init(&newsk->sk_dst_lock); + spin_lock_init(&newsk->sk_dst_lock); rwlock_init(&newsk->sk_callback_lock); + lockdep_set_class_and_name(&newsk->sk_callback_lock, + af_callback_keys + newsk->sk_family, + af_family_clock_key_strings[newsk->sk_family]); newsk->sk_dst_cache = NULL; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; newsk->sk_send_head = NULL; - newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; sock_reset_flag(newsk, SOCK_DONE); skb_queue_head_init(&newsk->sk_error_queue); - filter = newsk->sk_filter; + filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) sk_filter_charge(newsk, filter); @@ -746,6 +1528,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; + bh_unlock_sock(newsk); sk_free(newsk); newsk = NULL; goto out; @@ -753,6 +1536,11 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_err = 0; newsk->sk_priority = 0; + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&newsk->sk_refcnt, 2); /* @@ -767,80 +1555,138 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) * to be taken into account in all callers. -acme */ sk_refcnt_debug_inc(newsk); - newsk->sk_socket = NULL; - newsk->sk_sleep = NULL; + sk_set_socket(newsk, NULL); + newsk->sk_wq = NULL; + + sk_update_clone(sk, newsk); if (newsk->sk_prot->sockets_allocated) - atomic_inc(newsk->sk_prot->sockets_allocated); + sk_sockets_allocated_inc(newsk); + + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); } out: return newsk; } - -EXPORT_SYMBOL_GPL(sk_clone); - -void __init sk_init(void) -{ - if (num_physpages <= 4096) { - sysctl_wmem_max = 32767; - sysctl_rmem_max = 32767; - sysctl_wmem_default = 32767; - sysctl_rmem_default = 32767; - } else if (num_physpages >= 131072) { - sysctl_wmem_max = 131071; - sysctl_rmem_max = 131071; +EXPORT_SYMBOL_GPL(sk_clone_lock); + +void sk_setup_caps(struct sock *sk, struct dst_entry *dst) +{ + __sk_dst_set(sk, dst); + sk->sk_route_caps = dst->dev->features; + if (sk->sk_route_caps & NETIF_F_GSO) + sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; + sk->sk_route_caps &= ~sk->sk_route_nocaps; + if (sk_can_gso(sk)) { + if (dst->header_len) { + sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + } else { + sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; + sk->sk_gso_max_size = dst->dev->gso_max_size; + sk->sk_gso_max_segs = dst->dev->gso_max_segs; + } } } +EXPORT_SYMBOL_GPL(sk_setup_caps); /* * Simple resource managers for sockets. */ -/* - * Write buffer destructor automatically called from kfree_skb. +/* + * Write buffer destructor automatically called from kfree_skb. */ void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + unsigned int len = skb->truesize; - /* In case it might be waiting for more memory. */ - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); - if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) + if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { + /* + * Keep a reference on sk_wmem_alloc, this will be released + * after sk_write_space() call + */ + atomic_sub(len - 1, &sk->sk_wmem_alloc); sk->sk_write_space(sk); - sock_put(sk); + len = 1; + } + /* + * if sk_wmem_alloc reaches 0, we must finish what sk_free() + * could not do because of in-flight packets + */ + if (atomic_sub_and_test(len, &sk->sk_wmem_alloc)) + __sk_free(sk); +} +EXPORT_SYMBOL(sock_wfree); + +void skb_orphan_partial(struct sk_buff *skb) +{ + /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, + * so we do not completely orphan skb, but transfert all + * accounted bytes but one, to avoid unexpected reorders. + */ + if (skb->destructor == sock_wfree +#ifdef CONFIG_INET + || skb->destructor == tcp_wfree +#endif + ) { + atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); + skb->truesize = 1; + } else { + skb_orphan(skb); + } } +EXPORT_SYMBOL(skb_orphan_partial); -/* - * Read buffer destructor automatically called from kfree_skb. +/* + * Read buffer destructor automatically called from kfree_skb. */ void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + unsigned int len = skb->truesize; - atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + atomic_sub(len, &sk->sk_rmem_alloc); + sk_mem_uncharge(sk, len); } +EXPORT_SYMBOL(sock_rfree); +void sock_edemux(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + +#ifdef CONFIG_INET + if (sk->sk_state == TCP_TIME_WAIT) + inet_twsk_put(inet_twsk(sk)); + else +#endif + sock_put(sk); +} +EXPORT_SYMBOL(sock_edemux); -int sock_i_uid(struct sock *sk) +kuid_t sock_i_uid(struct sock *sk) { - int uid; + kuid_t uid; - read_lock(&sk->sk_callback_lock); - uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); + uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; + read_unlock_bh(&sk->sk_callback_lock); return uid; } +EXPORT_SYMBOL(sock_i_uid); unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } +EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. @@ -849,7 +1695,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { - struct sk_buff * skb = alloc_skb(size, priority); + struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -857,33 +1703,18 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, } return NULL; } +EXPORT_SYMBOL(sock_wmalloc); /* - * Allocate a skb from the socket's receive buffer. - */ -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - gfp_t priority) -{ - if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - skb_set_owner_r(skb, sk); - return skb; - } - } - return NULL; -} - -/* * Allocate a memory block from the socket's option memory buffer. - */ + */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - if ((unsigned)size <= sysctl_optmem_max && + if ((unsigned int)size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc - * might sleep. + * might sleep. */ atomic_add(size, &sk->sk_omem_alloc); mem = kmalloc(size, priority); @@ -893,6 +1724,7 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) } return NULL; } +EXPORT_SYMBOL(sock_kmalloc); /* * Free an option memory block. @@ -902,11 +1734,12 @@ void sock_kfree_s(struct sock *sk, void *mem, int size) kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } +EXPORT_SYMBOL(sock_kfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ -static long sock_wait_for_wmem(struct sock * sk, long timeo) +static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); @@ -917,7 +1750,7 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; if (sk->sk_shutdown & SEND_SHUTDOWN) @@ -926,7 +1759,7 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) break; timeo = schedule_timeout(timeo); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeo; } @@ -935,22 +1768,25 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) * Generic send/receive buffer handlers */ -static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, - unsigned long header_len, - unsigned long data_len, - int noblock, int *errcode) +struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, + unsigned long data_len, int noblock, + int *errcode, int max_page_order) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; + unsigned long chunk; gfp_t gfp_mask; long timeo; int err; + int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; + struct page *page; + int i; - gfp_mask = sk->sk_allocation; - if (gfp_mask & __GFP_WAIT) - gfp_mask |= __GFP_REPEAT; + err = -EMSGSIZE; + if (npages > MAX_SKB_FRAGS) + goto failure; timeo = sock_sndtimeo(sk, noblock); - while (1) { + while (!skb) { err = sock_error(sk); if (err != 0) goto failure; @@ -959,54 +1795,54 @@ static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { - skb = alloc_skb(header_len, sk->sk_allocation); - if (skb) { - int npages; - int i; - - /* No pages, we're done... */ - if (!data_len) - break; - - npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; - skb->truesize += data_len; - skb_shinfo(skb)->nr_frags = npages; - for (i = 0; i < npages; i++) { - struct page *page; - skb_frag_t *frag; - - page = alloc_pages(sk->sk_allocation, 0); - if (!page) { - err = -ENOBUFS; - skb_shinfo(skb)->nr_frags = i; - kfree_skb(skb); - goto failure; - } - - frag = &skb_shinfo(skb)->frags[i]; - frag->page = page; - frag->page_offset = 0; - frag->size = (data_len >= PAGE_SIZE ? - PAGE_SIZE : - data_len); - data_len -= PAGE_SIZE; - } + if (atomic_read(&sk->sk_wmem_alloc) >= sk->sk_sndbuf) { + set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = -EAGAIN; + if (!timeo) + goto failure; + if (signal_pending(current)) + goto interrupted; + timeo = sock_wait_for_wmem(sk, timeo); + continue; + } - /* Full success... */ - break; - } - err = -ENOBUFS; + err = -ENOBUFS; + gfp_mask = sk->sk_allocation; + if (gfp_mask & __GFP_WAIT) + gfp_mask |= __GFP_REPEAT; + + skb = alloc_skb(header_len, gfp_mask); + if (!skb) goto failure; + + skb->truesize += data_len; + + for (i = 0; npages > 0; i++) { + int order = max_page_order; + + while (order) { + if (npages >= 1 << order) { + page = alloc_pages(sk->sk_allocation | + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, + order); + if (page) + goto fill_page; + } + order--; + } + page = alloc_page(sk->sk_allocation); + if (!page) + goto failure; +fill_page: + chunk = min_t(unsigned long, data_len, + PAGE_SIZE << order); + skb_fill_page_desc(skb, i, page, 0, chunk); + data_len -= chunk; + npages -= 1 << order; } - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - err = -EAGAIN; - if (!timeo) - goto failure; - if (signal_pending(current)) - goto interrupted; - timeo = sock_wait_for_wmem(sk, timeo); } skb_set_owner_w(skb, sk); @@ -1015,33 +1851,96 @@ static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, interrupted: err = sock_intr_errno(timeo); failure: + kfree_skb(skb); *errcode = err; return NULL; } +EXPORT_SYMBOL(sock_alloc_send_pskb); -struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, +struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { - return sock_alloc_send_pskb(sk, size, 0, noblock, errcode); + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); +} +EXPORT_SYMBOL(sock_alloc_send_skb); + +/* On 32bit arches, an skb frag is limited to 2^15 */ +#define SKB_FRAG_PAGE_ORDER get_order(32768) + +/** + * skb_page_frag_refill - check that a page_frag contains enough room + * @sz: minimum size of the fragment we want to get + * @pfrag: pointer to page_frag + * @prio: priority for memory allocation + * + * Note: While this allocator tries to use high order pages, there is + * no guarantee that allocations succeed. Therefore, @sz MUST be + * less or equal than PAGE_SIZE. + */ +bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) +{ + int order; + + if (pfrag->page) { + if (atomic_read(&pfrag->page->_count) == 1) { + pfrag->offset = 0; + return true; + } + if (pfrag->offset + sz <= pfrag->size) + return true; + put_page(pfrag->page); + } + + order = SKB_FRAG_PAGE_ORDER; + do { + gfp_t gfp = prio; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + pfrag->page = alloc_pages(gfp, order); + if (likely(pfrag->page)) { + pfrag->offset = 0; + pfrag->size = PAGE_SIZE << order; + return true; + } + } while (--order >= 0); + + return false; +} +EXPORT_SYMBOL(skb_page_frag_refill); + +bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) +{ + if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) + return true; + + sk_enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return false; } +EXPORT_SYMBOL(sk_page_frag_refill); static void __lock_sock(struct sock *sk) + __releases(&sk->sk_lock.slock) + __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); - for(;;) { + for (;;) { prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_bh(&sk->sk_lock.slock); schedule(); spin_lock_bh(&sk->sk_lock.slock); - if(!sock_owned_by_user(sk)) + if (!sock_owned_by_user(sk)) break; } finish_wait(&sk->sk_lock.wq, &wait); } static void __release_sock(struct sock *sk) + __releases(&sk->sk_lock.slock) + __acquires(&sk->sk_lock.slock) { struct sk_buff *skb = sk->sk_backlog.head; @@ -1052,8 +1951,10 @@ static void __release_sock(struct sock *sk) do { struct sk_buff *next = skb->next; + prefetch(next); + WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; - sk->sk_backlog_rcv(sk, skb); + sk_backlog_rcv(sk, skb); /* * We are in process context here with softirqs @@ -1067,7 +1968,13 @@ static void __release_sock(struct sock *sk) } while (skb != NULL); bh_lock_sock(sk); - } while((skb = sk->sk_backlog.head) != NULL); + } while ((skb = sk->sk_backlog.head) != NULL); + + /* + * Doing the zeroing here guarantee we can not loop forever + * while a wild producer attempts to flood us. + */ + sk->sk_backlog.len = 0; } /** @@ -1085,16 +1992,120 @@ int sk_wait_data(struct sock *sk, long *timeo) int rc; DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; } - EXPORT_SYMBOL(sk_wait_data); +/** + * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated + * @sk: socket + * @size: memory size to allocate + * @kind: allocation type + * + * If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means + * rmem allocation. This function assumes that protocols which have + * memory_pressure use sk_wmem_queued as write buffer accounting. + */ +int __sk_mem_schedule(struct sock *sk, int size, int kind) +{ + struct proto *prot = sk->sk_prot; + int amt = sk_mem_pages(size); + long allocated; + int parent_status = UNDER_LIMIT; + + sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + + allocated = sk_memory_allocated_add(sk, amt, &parent_status); + + /* Under limit. */ + if (parent_status == UNDER_LIMIT && + allocated <= sk_prot_mem_limits(sk, 0)) { + sk_leave_memory_pressure(sk); + return 1; + } + + /* Under pressure. (we or our parents) */ + if ((parent_status > SOFT_LIMIT) || + allocated > sk_prot_mem_limits(sk, 1)) + sk_enter_memory_pressure(sk); + + /* Over hard limit (we or our parents) */ + if ((parent_status == OVER_LIMIT) || + (allocated > sk_prot_mem_limits(sk, 2))) + goto suppress_allocation; + + /* guarantee minimum buffer size under pressure */ + if (kind == SK_MEM_RECV) { + if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0]) + return 1; + + } else { /* SK_MEM_SEND */ + if (sk->sk_type == SOCK_STREAM) { + if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) + return 1; + } else if (atomic_read(&sk->sk_wmem_alloc) < + prot->sysctl_wmem[0]) + return 1; + } + + if (sk_has_memory_pressure(sk)) { + int alloc; + + if (!sk_under_memory_pressure(sk)) + return 1; + alloc = sk_sockets_allocated_read_positive(sk); + if (sk_prot_mem_limits(sk, 2) > alloc * + sk_mem_pages(sk->sk_wmem_queued + + atomic_read(&sk->sk_rmem_alloc) + + sk->sk_forward_alloc)) + return 1; + } + +suppress_allocation: + + if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) { + sk_stream_moderate_sndbuf(sk); + + /* Fail only if socket is _under_ its sndbuf. + * In this case we cannot block, so that we have to fail. + */ + if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) + return 1; + } + + trace_sock_exceed_buf_limit(sk, prot, allocated); + + /* Alas. Undo changes. */ + sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; + + sk_memory_allocated_sub(sk, amt); + + return 0; +} +EXPORT_SYMBOL(__sk_mem_schedule); + +/** + * __sk_reclaim - reclaim memory_allocated + * @sk: socket + */ +void __sk_mem_reclaim(struct sock *sk) +{ + sk_memory_allocated_sub(sk, + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); + sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; + + if (sk_under_memory_pressure(sk) && + (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) + sk_leave_memory_pressure(sk); +} +EXPORT_SYMBOL(__sk_mem_reclaim); + + /* * Set of default routines for initialising struct proto_ops when * the protocol does not support a particular function. In certain @@ -1106,78 +2117,92 @@ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_bind); -int sock_no_connect(struct socket *sock, struct sockaddr *saddr, +int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_accept); -int sock_no_getname(struct socket *sock, struct sockaddr *saddr, +int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int *len, int peer) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getname); -unsigned int sock_no_poll(struct file * file, struct socket *sock, poll_table *pt) +unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt) { return 0; } +EXPORT_SYMBOL(sock_no_poll); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_setsockopt); int sock_no_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getsockopt); int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } +EXPORT_SYMBOL(sock_no_mmap); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1191,6 +2216,7 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz kunmap(page); return res; } +EXPORT_SYMBOL(sock_no_sendpage); /* * Default Socket Callbacks @@ -1198,47 +2224,61 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz static void sock_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_all(sk->sk_sleep); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); - sk_wake_async(sk,0,POLL_ERR); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLERR); + sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); + rcu_read_unlock(); } -static void sock_def_readable(struct sock *sk, int len) +static void sock_def_readable(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); - sk_wake_async(sk,1,POLL_IN); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI | + POLLRDNORM | POLLRDBAND); + sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); + rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | + POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) - sk_wake_async(sk, 2, POLL_OUT); + sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) @@ -1250,8 +2290,9 @@ void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) if (send_sigurg(&sk->sk_socket->file->f_owner)) - sk_wake_async(sk, 3, POLL_PRI); + sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } +EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) @@ -1259,15 +2300,13 @@ void sk_reset_timer(struct sock *sk, struct timer_list* timer, if (!mod_timer(timer, expires)) sock_hold(sk); } - EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) __sock_put(sk); } - EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) @@ -1275,29 +2314,34 @@ void sock_init_data(struct socket *sock, struct sock *sk) skb_queue_head_init(&sk->sk_receive_queue); skb_queue_head_init(&sk->sk_write_queue); skb_queue_head_init(&sk->sk_error_queue); +#ifdef CONFIG_NET_DMA + skb_queue_head_init(&sk->sk_async_wait_queue); +#endif sk->sk_send_head = NULL; init_timer(&sk->sk_timer); - + sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; sk->sk_sndbuf = sysctl_wmem_default; sk->sk_state = TCP_CLOSE; - sk->sk_socket = sock; + sk_set_socket(sk, sock); sock_set_flag(sk, SOCK_ZAPPED); - if(sock) - { + if (sock) { sk->sk_type = sock->type; - sk->sk_sleep = &sock->wait; + sk->sk_wq = sock->wq; sock->sk = sk; } else - sk->sk_sleep = NULL; + sk->sk_wq = NULL; - rwlock_init(&sk->sk_dst_lock); + spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); + lockdep_set_class_and_name(&sk->sk_callback_lock, + af_callback_keys + sk->sk_family, + af_family_clock_key_strings[sk->sk_family]); sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; @@ -1305,68 +2349,202 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + sk->sk_peek_off = -1; - sk->sk_peercred.pid = 0; - sk->sk_peercred.uid = -1; - sk->sk_peercred.gid = -1; + sk->sk_peer_pid = NULL; + sk->sk_peer_cred = NULL; sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; - sk->sk_stamp.tv_sec = -1L; - sk->sk_stamp.tv_usec = -1L; + sk->sk_stamp = ktime_set(-1L, 0); + +#ifdef CONFIG_NET_RX_BUSY_POLL + sk->sk_napi_id = 0; + sk->sk_ll_usec = sysctl_net_busy_read; +#endif + sk->sk_max_pacing_rate = ~0U; + sk->sk_pacing_rate = ~0U; + /* + * Before updating sk_refcnt, we must commit prior changes to memory + * (Documentation/RCU/rculist_nulls.txt for details) + */ + smp_wmb(); atomic_set(&sk->sk_refcnt, 1); + atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data); -void fastcall lock_sock(struct sock *sk) +void lock_sock_nested(struct sock *sk, int subclass) { might_sleep(); - spin_lock_bh(&(sk->sk_lock.slock)); - if (sk->sk_lock.owner) + spin_lock_bh(&sk->sk_lock.slock); + if (sk->sk_lock.owned) __lock_sock(sk); - sk->sk_lock.owner = (void *)1; - spin_unlock_bh(&(sk->sk_lock.slock)); + sk->sk_lock.owned = 1; + spin_unlock(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); + local_bh_enable(); } +EXPORT_SYMBOL(lock_sock_nested); -EXPORT_SYMBOL(lock_sock); - -void fastcall release_sock(struct sock *sk) +void release_sock(struct sock *sk) { - spin_lock_bh(&(sk->sk_lock.slock)); + /* + * The sk_lock has mutex_unlock() semantics: + */ + mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + + spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); - sk->sk_lock.owner = NULL; - if (waitqueue_active(&(sk->sk_lock.wq))) - wake_up(&(sk->sk_lock.wq)); - spin_unlock_bh(&(sk->sk_lock.slock)); + + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ + if (sk->sk_prot->release_cb) + sk->sk_prot->release_cb(sk); + + sock_release_ownership(sk); + if (waitqueue_active(&sk->sk_lock.wq)) + wake_up(&sk->sk_lock.wq); + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken + * sk_lock.slock locked, owned = 0, BH disabled + * return true if slow path is taken + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +bool lock_sock_fast(struct sock *sk) +{ + might_sleep(); + spin_lock_bh(&sk->sk_lock.slock); + + if (!sk->sk_lock.owned) + /* + * Note : We must disable BH + */ + return false; + + __lock_sock(sk); + sk->sk_lock.owned = 1; + spin_unlock(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + local_bh_enable(); + return true; +} +EXPORT_SYMBOL(lock_sock_fast); + int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) -{ +{ + struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); - if (sk->sk_stamp.tv_sec == -1) + sock_enable_timestamp(sk, SOCK_TIMESTAMP); + tv = ktime_to_timeval(sk->sk_stamp); + if (tv.tv_sec == -1) return -ENOENT; - if (sk->sk_stamp.tv_sec == 0) - do_gettimeofday(&sk->sk_stamp); - return copy_to_user(userstamp, &sk->sk_stamp, sizeof(struct timeval)) ? - -EFAULT : 0; -} + if (tv.tv_sec == 0) { + sk->sk_stamp = ktime_get_real(); + tv = ktime_to_timeval(sk->sk_stamp); + } + return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0; +} EXPORT_SYMBOL(sock_get_timestamp); -void sock_enable_timestamp(struct sock *sk) -{ - if (!sock_flag(sk, SOCK_TIMESTAMP)) { - sock_set_flag(sk, SOCK_TIMESTAMP); - net_enable_timestamp(); +int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) +{ + struct timespec ts; + if (!sock_flag(sk, SOCK_TIMESTAMP)) + sock_enable_timestamp(sk, SOCK_TIMESTAMP); + ts = ktime_to_timespec(sk->sk_stamp); + if (ts.tv_sec == -1) + return -ENOENT; + if (ts.tv_sec == 0) { + sk->sk_stamp = ktime_get_real(); + ts = ktime_to_timespec(sk->sk_stamp); + } + return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0; +} +EXPORT_SYMBOL(sock_get_timestampns); + +void sock_enable_timestamp(struct sock *sk, int flag) +{ + if (!sock_flag(sk, flag)) { + unsigned long previous_flags = sk->sk_flags; + + sock_set_flag(sk, flag); + /* + * we just set one of the two flags which require net + * time stamping, but time stamping might have been on + * already because of the other one + */ + if (!(previous_flags & SK_FLAGS_TIMESTAMP)) + net_enable_timestamp(); + } +} + +int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, + int level, int type) +{ + struct sock_exterr_skb *serr; + struct sk_buff *skb, *skb2; + int copied, err; + + err = -EAGAIN; + skb = skb_dequeue(&sk->sk_error_queue); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + serr = SKB_EXT_ERR(skb); + put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + + msg->msg_flags |= MSG_ERRQUEUE; + err = copied; + + /* Reset and regenerate socket error */ + spin_lock_bh(&sk->sk_error_queue.lock); + sk->sk_err = 0; + if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { + sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; + spin_unlock_bh(&sk->sk_error_queue.lock); + sk->sk_error_report(sk); + } else + spin_unlock_bh(&sk->sk_error_queue.lock); + +out_free_skb: + kfree_skb(skb); +out: + return err; } -EXPORT_SYMBOL(sock_enable_timestamp); +EXPORT_SYMBOL(sock_recv_errqueue); /* * Get a socket option on an socket. @@ -1382,9 +2560,22 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_getsockopt); +#ifdef CONFIG_COMPAT +int compat_sock_common_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + + if (sk->sk_prot->compat_getsockopt != NULL) + return sk->sk_prot->compat_getsockopt(sk, level, optname, + optval, optlen); + return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); +} +EXPORT_SYMBOL(compat_sock_common_getsockopt); +#endif + int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -1398,22 +2589,34 @@ int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = addr_len; return err; } - EXPORT_SYMBOL(sock_common_recvmsg); /* * Set socket options on an inet socket. */ int sock_common_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_setsockopt); +#ifdef CONFIG_COMPAT +int compat_sock_common_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + + if (sk->sk_prot->compat_setsockopt != NULL) + return sk->sk_prot->compat_setsockopt(sk, level, optname, + optval, optlen); + return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); +} +EXPORT_SYMBOL(compat_sock_common_setsockopt); +#endif + void sk_common_release(struct sock *sk) { if (sk->sk_prot->destroy) @@ -1446,96 +2649,194 @@ void sk_common_release(struct sock *sk) xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + sock_put(sk); } - EXPORT_SYMBOL(sk_common_release); -static DEFINE_RWLOCK(proto_list_lock); -static LIST_HEAD(proto_list); +#ifdef CONFIG_PROC_FS +#define PROTO_INUSE_NR 64 /* should be enough for the first time */ +struct prot_inuse { + int val[PROTO_INUSE_NR]; +}; -int proto_register(struct proto *prot, int alloc_slab) +static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); + +#ifdef CONFIG_NET_NS +void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) +{ + __this_cpu_add(net->core.inuse->val[prot->inuse_idx], val); +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_add); + +int sock_prot_inuse_get(struct net *net, struct proto *prot) +{ + int cpu, idx = prot->inuse_idx; + int res = 0; + + for_each_possible_cpu(cpu) + res += per_cpu_ptr(net->core.inuse, cpu)->val[idx]; + + return res >= 0 ? res : 0; +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_get); + +static int __net_init sock_inuse_init_net(struct net *net) +{ + net->core.inuse = alloc_percpu(struct prot_inuse); + return net->core.inuse ? 0 : -ENOMEM; +} + +static void __net_exit sock_inuse_exit_net(struct net *net) +{ + free_percpu(net->core.inuse); +} + +static struct pernet_operations net_inuse_ops = { + .init = sock_inuse_init_net, + .exit = sock_inuse_exit_net, +}; + +static __init int net_inuse_init(void) +{ + if (register_pernet_subsys(&net_inuse_ops)) + panic("Cannot initialize net inuse counters"); + + return 0; +} + +core_initcall(net_inuse_init); +#else +static DEFINE_PER_CPU(struct prot_inuse, prot_inuse); + +void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) +{ + __this_cpu_add(prot_inuse.val[prot->inuse_idx], val); +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_add); + +int sock_prot_inuse_get(struct net *net, struct proto *prot) +{ + int cpu, idx = prot->inuse_idx; + int res = 0; + + for_each_possible_cpu(cpu) + res += per_cpu(prot_inuse, cpu).val[idx]; + + return res >= 0 ? res : 0; +} +EXPORT_SYMBOL_GPL(sock_prot_inuse_get); +#endif + +static void assign_proto_idx(struct proto *prot) +{ + prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); + + if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { + pr_err("PROTO_INUSE_NR exhausted\n"); + return; + } + + set_bit(prot->inuse_idx, proto_inuse_idx); +} + +static void release_proto_idx(struct proto *prot) +{ + if (prot->inuse_idx != PROTO_INUSE_NR - 1) + clear_bit(prot->inuse_idx, proto_inuse_idx); +} +#else +static inline void assign_proto_idx(struct proto *prot) +{ +} + +static inline void release_proto_idx(struct proto *prot) { - char *request_sock_slab_name = NULL; - char *timewait_sock_slab_name; - int rc = -ENOBUFS; +} +#endif +int proto_register(struct proto *prot, int alloc_slab) +{ if (alloc_slab) { prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0, - SLAB_HWCACHE_ALIGN, NULL, NULL); + SLAB_HWCACHE_ALIGN | prot->slab_flags, + NULL); if (prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", - prot->name); + pr_crit("%s: Can't create sock SLAB cache!\n", + prot->name); goto out; } if (prot->rsk_prot != NULL) { - static const char mask[] = "request_sock_%s"; - - request_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL); - if (request_sock_slab_name == NULL) + prot->rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name); + if (prot->rsk_prot->slab_name == NULL) goto out_free_sock_slab; - sprintf(request_sock_slab_name, mask, prot->name); - prot->rsk_prot->slab = kmem_cache_create(request_sock_slab_name, + prot->rsk_prot->slab = kmem_cache_create(prot->rsk_prot->slab_name, prot->rsk_prot->obj_size, 0, - SLAB_HWCACHE_ALIGN, NULL, NULL); + SLAB_HWCACHE_ALIGN, NULL); if (prot->rsk_prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n", - prot->name); + pr_crit("%s: Can't create request sock SLAB cache!\n", + prot->name); goto out_free_request_sock_slab_name; } } if (prot->twsk_prot != NULL) { - static const char mask[] = "tw_sock_%s"; + prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); - timewait_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL); - - if (timewait_sock_slab_name == NULL) + if (prot->twsk_prot->twsk_slab_name == NULL) goto out_free_request_sock_slab; - sprintf(timewait_sock_slab_name, mask, prot->name); prot->twsk_prot->twsk_slab = - kmem_cache_create(timewait_sock_slab_name, + kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); + 0, + SLAB_HWCACHE_ALIGN | + prot->slab_flags, + NULL); if (prot->twsk_prot->twsk_slab == NULL) goto out_free_timewait_sock_slab_name; } } - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); list_add(&prot->node, &proto_list); - write_unlock(&proto_list_lock); - rc = 0; -out: - return rc; + assign_proto_idx(prot); + mutex_unlock(&proto_list_mutex); + return 0; + out_free_timewait_sock_slab_name: - kfree(timewait_sock_slab_name); + kfree(prot->twsk_prot->twsk_slab_name); out_free_request_sock_slab: if (prot->rsk_prot && prot->rsk_prot->slab) { kmem_cache_destroy(prot->rsk_prot->slab); prot->rsk_prot->slab = NULL; } out_free_request_sock_slab_name: - kfree(request_sock_slab_name); + if (prot->rsk_prot) + kfree(prot->rsk_prot->slab_name); out_free_sock_slab: kmem_cache_destroy(prot->slab); prot->slab = NULL; - goto out; +out: + return -ENOBUFS; } - EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); + release_proto_idx(prot); list_del(&prot->node); - write_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); if (prot->slab != NULL) { kmem_cache_destroy(prot->slab); @@ -1543,86 +2844,63 @@ void proto_unregister(struct proto *prot) } if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) { - const char *name = kmem_cache_name(prot->rsk_prot->slab); - kmem_cache_destroy(prot->rsk_prot->slab); - kfree(name); + kfree(prot->rsk_prot->slab_name); prot->rsk_prot->slab = NULL; } 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_prot->twsk_slab); - kfree(name); + kfree(prot->twsk_prot->twsk_slab_name); prot->twsk_prot->twsk_slab = NULL; } } - EXPORT_SYMBOL(proto_unregister); #ifdef CONFIG_PROC_FS -static inline struct proto *__proto_head(void) -{ - return list_entry(proto_list.next, struct proto, node); -} - -static inline struct proto *proto_head(void) -{ - return list_empty(&proto_list) ? NULL : __proto_head(); -} - -static inline struct proto *proto_next(struct proto *proto) -{ - return proto->node.next == &proto_list ? NULL : - list_entry(proto->node.next, struct proto, node); -} - -static inline struct proto *proto_get_idx(loff_t pos) -{ - struct proto *proto; - loff_t i = 0; - - list_for_each_entry(proto, &proto_list, node) - if (i++ == pos) - goto out; - - proto = NULL; -out: - return proto; -} - static void *proto_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(proto_list_mutex) { - read_lock(&proto_list_lock); - return *pos ? proto_get_idx(*pos - 1) : SEQ_START_TOKEN; + mutex_lock(&proto_list_mutex); + return seq_list_start_head(&proto_list, *pos); } static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - ++*pos; - return v == SEQ_START_TOKEN ? proto_head() : proto_next(v); + return seq_list_next(v, &proto_list, pos); } static void proto_seq_stop(struct seq_file *seq, void *v) + __releases(proto_list_mutex) { - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } +static long sock_prot_memory_allocated(struct proto *proto) +{ + return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; +} + +static char *sock_prot_memory_pressure(struct proto *proto) +{ + return proto->memory_pressure != NULL ? + proto_memory_pressure(proto) ? "yes" : "no" : "NI"; +} static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { - seq_printf(seq, "%-9s %4u %6d %6d %-3s %6u %-3s %-10s " + + seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, - proto->sockets_allocated != NULL ? atomic_read(proto->sockets_allocated) : -1, - proto->memory_allocated != NULL ? atomic_read(proto->memory_allocated) : -1, - proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI", + sock_prot_inuse_get(seq_file_net(seq), proto), + sock_prot_memory_allocated(proto), + sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), @@ -1649,7 +2927,7 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto) static int proto_seq_show(struct seq_file *seq, void *v) { - if (v == SEQ_START_TOKEN) + if (v == &proto_list) seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s", "protocol", "size", @@ -1661,11 +2939,11 @@ static int proto_seq_show(struct seq_file *seq, void *v) "module", "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n"); else - proto_seq_printf(seq, v); + proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; } -static struct seq_operations proto_seq_ops = { +static const struct seq_operations proto_seq_ops = { .start = proto_seq_start, .next = proto_seq_next, .stop = proto_seq_stop, @@ -1674,57 +2952,42 @@ static struct seq_operations proto_seq_ops = { static int proto_seq_open(struct inode *inode, struct file *file) { - return seq_open(file, &proto_seq_ops); + return seq_open_net(inode, file, &proto_seq_ops, + sizeof(struct seq_net_private)); } -static struct file_operations proto_seq_fops = { +static const struct file_operations proto_seq_fops = { .owner = THIS_MODULE, .open = proto_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_net, +}; + +static __net_init int proto_init_net(struct net *net) +{ + if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops)) + return -ENOMEM; + + return 0; +} + +static __net_exit void proto_exit_net(struct net *net) +{ + remove_proc_entry("protocols", net->proc_net); +} + + +static __net_initdata struct pernet_operations proto_net_ops = { + .init = proto_init_net, + .exit = proto_exit_net, }; static int __init proto_init(void) { - /* register /proc/net/protocols */ - return proc_net_fops_create("protocols", S_IRUGO, &proto_seq_fops) == NULL ? -ENOBUFS : 0; + return register_pernet_subsys(&proto_net_ops); } subsys_initcall(proto_init); #endif /* PROC_FS */ - -EXPORT_SYMBOL(sk_alloc); -EXPORT_SYMBOL(sk_free); -EXPORT_SYMBOL(sk_send_sigurg); -EXPORT_SYMBOL(sock_alloc_send_skb); -EXPORT_SYMBOL(sock_init_data); -EXPORT_SYMBOL(sock_kfree_s); -EXPORT_SYMBOL(sock_kmalloc); -EXPORT_SYMBOL(sock_no_accept); -EXPORT_SYMBOL(sock_no_bind); -EXPORT_SYMBOL(sock_no_connect); -EXPORT_SYMBOL(sock_no_getname); -EXPORT_SYMBOL(sock_no_getsockopt); -EXPORT_SYMBOL(sock_no_ioctl); -EXPORT_SYMBOL(sock_no_listen); -EXPORT_SYMBOL(sock_no_mmap); -EXPORT_SYMBOL(sock_no_poll); -EXPORT_SYMBOL(sock_no_recvmsg); -EXPORT_SYMBOL(sock_no_sendmsg); -EXPORT_SYMBOL(sock_no_sendpage); -EXPORT_SYMBOL(sock_no_setsockopt); -EXPORT_SYMBOL(sock_no_shutdown); -EXPORT_SYMBOL(sock_no_socketpair); -EXPORT_SYMBOL(sock_rfree); -EXPORT_SYMBOL(sock_setsockopt); -EXPORT_SYMBOL(sock_wfree); -EXPORT_SYMBOL(sock_wmalloc); -EXPORT_SYMBOL(sock_i_uid); -EXPORT_SYMBOL(sock_i_ino); -EXPORT_SYMBOL(sysctl_optmem_max); -#ifdef CONFIG_SYSCTL -EXPORT_SYMBOL(sysctl_rmem_max); -EXPORT_SYMBOL(sysctl_wmem_max); -#endif diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c new file mode 100644 index 00000000000..a4216a4c957 --- /dev/null +++ b/net/core/sock_diag.c @@ -0,0 +1,231 @@ +#include <linux/mutex.h> +#include <linux/socket.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/net_namespace.h> +#include <linux/module.h> +#include <net/sock.h> + +#include <linux/inet_diag.h> +#include <linux/sock_diag.h> + +static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; +static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); +static DEFINE_MUTEX(sock_diag_table_mutex); + +int sock_diag_check_cookie(void *sk, __u32 *cookie) +{ + if ((cookie[0] != INET_DIAG_NOCOOKIE || + cookie[1] != INET_DIAG_NOCOOKIE) && + ((u32)(unsigned long)sk != cookie[0] || + (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1])) + return -ESTALE; + else + return 0; +} +EXPORT_SYMBOL_GPL(sock_diag_check_cookie); + +void sock_diag_save_cookie(void *sk, __u32 *cookie) +{ + cookie[0] = (u32)(unsigned long)sk; + cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); +} +EXPORT_SYMBOL_GPL(sock_diag_save_cookie); + +int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) +{ + u32 mem[SK_MEMINFO_VARS]; + + mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); + mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); + mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; + mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); + mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + + return nla_put(skb, attrtype, sizeof(mem), &mem); +} +EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); + +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, + struct sk_buff *skb, int attrtype) +{ + struct sock_fprog_kern *fprog; + struct sk_filter *filter; + struct nlattr *attr; + unsigned int flen; + int err = 0; + + if (!may_report_filterinfo) { + nla_reserve(skb, attrtype, 0); + return 0; + } + + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (!filter) + goto out; + + fprog = filter->orig_prog; + flen = sk_filter_proglen(fprog); + + attr = nla_reserve(skb, attrtype, flen); + if (attr == NULL) { + err = -EMSGSIZE; + goto out; + } + + memcpy(nla_data(attr), fprog->filter, flen); +out: + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(sock_diag_put_filterinfo); + +void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +{ + mutex_lock(&sock_diag_table_mutex); + inet_rcv_compat = fn; + mutex_unlock(&sock_diag_table_mutex); +} +EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); + +void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +{ + mutex_lock(&sock_diag_table_mutex); + inet_rcv_compat = NULL; + mutex_unlock(&sock_diag_table_mutex); +} +EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); + +int sock_diag_register(const struct sock_diag_handler *hndl) +{ + int err = 0; + + if (hndl->family >= AF_MAX) + return -EINVAL; + + mutex_lock(&sock_diag_table_mutex); + if (sock_diag_handlers[hndl->family]) + err = -EBUSY; + else + sock_diag_handlers[hndl->family] = hndl; + mutex_unlock(&sock_diag_table_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(sock_diag_register); + +void sock_diag_unregister(const struct sock_diag_handler *hnld) +{ + int family = hnld->family; + + if (family >= AF_MAX) + return; + + mutex_lock(&sock_diag_table_mutex); + BUG_ON(sock_diag_handlers[family] != hnld); + sock_diag_handlers[family] = NULL; + mutex_unlock(&sock_diag_table_mutex); +} +EXPORT_SYMBOL_GPL(sock_diag_unregister); + +static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + int err; + struct sock_diag_req *req = nlmsg_data(nlh); + const struct sock_diag_handler *hndl; + + if (nlmsg_len(nlh) < sizeof(*req)) + return -EINVAL; + + if (req->sdiag_family >= AF_MAX) + return -EINVAL; + + if (sock_diag_handlers[req->sdiag_family] == NULL) + request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, req->sdiag_family); + + mutex_lock(&sock_diag_table_mutex); + hndl = sock_diag_handlers[req->sdiag_family]; + if (hndl == NULL) + err = -ENOENT; + else + err = hndl->dump(skb, nlh); + mutex_unlock(&sock_diag_table_mutex); + + return err; +} + +static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + int ret; + + switch (nlh->nlmsg_type) { + case TCPDIAG_GETSOCK: + case DCCPDIAG_GETSOCK: + if (inet_rcv_compat == NULL) + request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, AF_INET); + + mutex_lock(&sock_diag_table_mutex); + if (inet_rcv_compat != NULL) + ret = inet_rcv_compat(skb, nlh); + else + ret = -EOPNOTSUPP; + mutex_unlock(&sock_diag_table_mutex); + + return ret; + case SOCK_DIAG_BY_FAMILY: + return __sock_diag_rcv_msg(skb, nlh); + default: + return -EINVAL; + } +} + +static DEFINE_MUTEX(sock_diag_mutex); + +static void sock_diag_rcv(struct sk_buff *skb) +{ + mutex_lock(&sock_diag_mutex); + netlink_rcv_skb(skb, &sock_diag_rcv_msg); + mutex_unlock(&sock_diag_mutex); +} + +static int __net_init diag_net_init(struct net *net) +{ + struct netlink_kernel_cfg cfg = { + .input = sock_diag_rcv, + }; + + net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); + return net->diag_nlsk == NULL ? -ENOMEM : 0; +} + +static void __net_exit diag_net_exit(struct net *net) +{ + netlink_kernel_release(net->diag_nlsk); + net->diag_nlsk = NULL; +} + +static struct pernet_operations diag_net_ops = { + .init = diag_net_init, + .exit = diag_net_exit, +}; + +static int __init sock_diag_init(void) +{ + return register_pernet_subsys(&diag_net_ops); +} + +static void __exit sock_diag_exit(void) +{ + unregister_pernet_subsys(&diag_net_ops); +} + +module_init(sock_diag_init); +module_exit(sock_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG); diff --git a/net/core/stream.c b/net/core/stream.c index 35e25259fd9..301c05f2606 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -9,7 +9,7 @@ * * Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br> * (from old tcp.c code) - * Alan Cox <alan@redhat.com> (Borrowed comments 8-)) + * Alan Cox <alan@lxorguk.ukuu.org.uk> (Borrowed comments 8-)) */ #include <linux/module.h> @@ -28,17 +28,21 @@ void sk_stream_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; + struct socket_wq *wq; - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { + if (sk_stream_is_writeable(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); - if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) - sock_wake_async(sock, 2, POLL_OUT); + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLOUT | + POLLWRNORM | POLLWRBAND); + if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) + sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); + rcu_read_unlock(); } } - EXPORT_SYMBOL(sk_stream_write_space); /** @@ -65,18 +69,17 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) if (signal_pending(tsk)) return sock_intr_errno(*timeo_p); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, !sk->sk_err && - !((1 << sk->sk_state) & + !((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); return 0; } - EXPORT_SYMBOL(sk_stream_wait_connect); /** @@ -95,16 +98,15 @@ void sk_stream_wait_close(struct sock *sk, long timeout) DEFINE_WAIT(wait); do { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk))) break; } while (!signal_pending(current) && timeout); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); } } - EXPORT_SYMBOL(sk_stream_wait_close); /** @@ -120,12 +122,12 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2; + current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; @@ -139,10 +141,10 @@ 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, ¤t_timeo, !sk->sk_err && - !(sk->sk_shutdown & SEND_SHUTDOWN) && - sk_stream_memory_free(sk) && - vm_wait); + sk_wait_event(sk, ¤t_timeo, sk->sk_err || + (sk->sk_shutdown & SEND_SHUTDOWN) || + (sk_stream_memory_free(sk) && + !vm_wait)); sk->sk_write_pending--; if (vm_wait) { @@ -156,7 +158,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) *timeo_p = current_timeo; } out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; do_error: @@ -169,19 +171,8 @@ do_interrupted: err = sock_intr_errno(*timeo_p); goto out; } - EXPORT_SYMBOL(sk_stream_wait_memory); -void sk_stream_rfree(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - sk->sk_forward_alloc += skb->truesize; -} - -EXPORT_SYMBOL(sk_stream_rfree); - int sk_stream_error(struct sock *sk, int flags, int err) { if (err == -EPIPE) @@ -190,81 +181,8 @@ int sk_stream_error(struct sock *sk, int flags, int err) send_sig(SIGPIPE, current, 0); return err; } - EXPORT_SYMBOL(sk_stream_error); -void __sk_stream_mem_reclaim(struct sock *sk) -{ - if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM) { - atomic_sub(sk->sk_forward_alloc / SK_STREAM_MEM_QUANTUM, - sk->sk_prot->memory_allocated); - sk->sk_forward_alloc &= SK_STREAM_MEM_QUANTUM - 1; - if (*sk->sk_prot->memory_pressure && - (atomic_read(sk->sk_prot->memory_allocated) < - sk->sk_prot->sysctl_mem[0])) - *sk->sk_prot->memory_pressure = 0; - } -} - -EXPORT_SYMBOL(__sk_stream_mem_reclaim); - -int sk_stream_mem_schedule(struct sock *sk, int size, int kind) -{ - int amt = sk_stream_pages(size); - - sk->sk_forward_alloc += amt * SK_STREAM_MEM_QUANTUM; - atomic_add(amt, sk->sk_prot->memory_allocated); - - /* Under limit. */ - if (atomic_read(sk->sk_prot->memory_allocated) < sk->sk_prot->sysctl_mem[0]) { - if (*sk->sk_prot->memory_pressure) - *sk->sk_prot->memory_pressure = 0; - return 1; - } - - /* Over hard limit. */ - if (atomic_read(sk->sk_prot->memory_allocated) > sk->sk_prot->sysctl_mem[2]) { - sk->sk_prot->enter_memory_pressure(); - goto suppress_allocation; - } - - /* Under pressure. */ - if (atomic_read(sk->sk_prot->memory_allocated) > sk->sk_prot->sysctl_mem[1]) - sk->sk_prot->enter_memory_pressure(); - - if (kind) { - if (atomic_read(&sk->sk_rmem_alloc) < sk->sk_prot->sysctl_rmem[0]) - return 1; - } else if (sk->sk_wmem_queued < sk->sk_prot->sysctl_wmem[0]) - return 1; - - if (!*sk->sk_prot->memory_pressure || - sk->sk_prot->sysctl_mem[2] > atomic_read(sk->sk_prot->sockets_allocated) * - sk_stream_pages(sk->sk_wmem_queued + - atomic_read(&sk->sk_rmem_alloc) + - sk->sk_forward_alloc)) - return 1; - -suppress_allocation: - - if (!kind) { - sk_stream_moderate_sndbuf(sk); - - /* Fail only if socket is _under_ its sndbuf. - * In this case we cannot block, so that we have to fail. - */ - if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) - return 1; - } - - /* Alas. Undo changes. */ - sk->sk_forward_alloc -= amt * SK_STREAM_MEM_QUANTUM; - atomic_sub(amt, sk->sk_prot->memory_allocated); - return 0; -} - -EXPORT_SYMBOL(sk_stream_mem_schedule); - void sk_stream_kill_queues(struct sock *sk) { /* First the read buffer. */ @@ -274,18 +192,17 @@ void sk_stream_kill_queues(struct sock *sk) __skb_queue_purge(&sk->sk_error_queue); /* Next, the write queue. */ - BUG_TRAP(skb_queue_empty(&sk->sk_write_queue)); + WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ - sk_stream_mem_reclaim(sk); + sk_mem_reclaim(sk); - BUG_TRAP(!sk->sk_wmem_queued); - BUG_TRAP(!sk->sk_forward_alloc); + WARN_ON(sk->sk_wmem_queued); + WARN_ON(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket * have gone away, only the net layer knows can touch it. */ } - EXPORT_SYMBOL(sk_stream_kill_queues); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 2f278c8e474..cf9cd13509a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -7,128 +7,428 @@ #include <linux/mm.h> #include <linux/sysctl.h> -#include <linux/config.h> #include <linux/module.h> #include <linux/socket.h> +#include <linux/netdevice.h> +#include <linux/ratelimit.h> +#include <linux/vmalloc.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/kmemleak.h> + +#include <net/ip.h> #include <net/sock.h> +#include <net/net_ratelimit.h> +#include <net/busy_poll.h> +#include <net/pkt_sched.h> + +static int zero = 0; +static int one = 1; +static int ushort_max = USHRT_MAX; + +#ifdef CONFIG_RPS +static int rps_sock_flow_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int orig_size, size; + int ret, i; + struct ctl_table tmp = { + .data = &size, + .maxlen = sizeof(size), + .mode = table->mode + }; + struct rps_sock_flow_table *orig_sock_table, *sock_table; + static DEFINE_MUTEX(sock_flow_mutex); + + mutex_lock(&sock_flow_mutex); + + orig_sock_table = rcu_dereference_protected(rps_sock_flow_table, + lockdep_is_held(&sock_flow_mutex)); + size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; + + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + if (write) { + if (size) { + if (size > 1<<30) { + /* Enforce limit to prevent overflow */ + mutex_unlock(&sock_flow_mutex); + return -EINVAL; + } + size = roundup_pow_of_two(size); + if (size != orig_size) { + sock_table = + vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); + if (!sock_table) { + mutex_unlock(&sock_flow_mutex); + return -ENOMEM; + } + + sock_table->mask = size - 1; + } else + sock_table = orig_sock_table; + + for (i = 0; i < size; i++) + sock_table->ents[i] = RPS_NO_CPU; + } else + sock_table = NULL; + + if (sock_table != orig_sock_table) { + rcu_assign_pointer(rps_sock_flow_table, sock_table); + if (sock_table) + static_key_slow_inc(&rps_needed); + if (orig_sock_table) { + static_key_slow_dec(&rps_needed); + synchronize_rcu(); + vfree(orig_sock_table); + } + } + } + + mutex_unlock(&sock_flow_mutex); + + return ret; +} +#endif /* CONFIG_RPS */ + +#ifdef CONFIG_NET_FLOW_LIMIT +static DEFINE_MUTEX(flow_limit_update_mutex); + +static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct sd_flow_limit *cur; + struct softnet_data *sd; + cpumask_var_t mask; + int i, len, ret = 0; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + if (write) { + ret = cpumask_parse_user(buffer, *lenp, mask); + if (ret) + goto done; + + mutex_lock(&flow_limit_update_mutex); + len = sizeof(*cur) + netdev_flow_limit_table_len; + for_each_possible_cpu(i) { + sd = &per_cpu(softnet_data, i); + cur = rcu_dereference_protected(sd->flow_limit, + lockdep_is_held(&flow_limit_update_mutex)); + if (cur && !cpumask_test_cpu(i, mask)) { + RCU_INIT_POINTER(sd->flow_limit, NULL); + synchronize_rcu(); + kfree(cur); + } else if (!cur && cpumask_test_cpu(i, mask)) { + cur = kzalloc_node(len, GFP_KERNEL, + cpu_to_node(i)); + if (!cur) { + /* not unwinding previous changes */ + ret = -ENOMEM; + goto write_unlock; + } + cur->num_buckets = netdev_flow_limit_table_len; + rcu_assign_pointer(sd->flow_limit, cur); + } + } +write_unlock: + mutex_unlock(&flow_limit_update_mutex); + } else { + char kbuf[128]; + + if (*ppos || !*lenp) { + *lenp = 0; + goto done; + } + + cpumask_clear(mask); + rcu_read_lock(); + for_each_possible_cpu(i) { + sd = &per_cpu(softnet_data, i); + if (rcu_dereference(sd->flow_limit)) + cpumask_set_cpu(i, mask); + } + rcu_read_unlock(); + + len = min(sizeof(kbuf) - 1, *lenp); + len = cpumask_scnprintf(kbuf, len, mask); + if (!len) { + *lenp = 0; + goto done; + } + if (len < *lenp) + kbuf[len++] = '\n'; + if (copy_to_user(buffer, kbuf, len)) { + ret = -EFAULT; + goto done; + } + *lenp = len; + *ppos += len; + } -#ifdef CONFIG_SYSCTL +done: + free_cpumask_var(mask); + return ret; +} -extern int netdev_max_backlog; -extern int weight_p; +static int flow_limit_table_len_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned int old, *ptr; + int ret; -extern __u32 sysctl_wmem_max; -extern __u32 sysctl_rmem_max; + mutex_lock(&flow_limit_update_mutex); -extern int sysctl_core_destroy_delay; + ptr = table->data; + old = *ptr; + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (!ret && write && !is_power_of_2(*ptr)) { + *ptr = old; + ret = -EINVAL; + } -#ifdef CONFIG_NET_DIVERT -extern char sysctl_divert_version[]; -#endif /* CONFIG_NET_DIVERT */ + mutex_unlock(&flow_limit_update_mutex); + return ret; +} +#endif /* CONFIG_NET_FLOW_LIMIT */ -ctl_table core_table[] = { +#ifdef CONFIG_NET_SCHED +static int set_default_qdisc(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + char id[IFNAMSIZ]; + struct ctl_table tbl = { + .data = id, + .maxlen = IFNAMSIZ, + }; + int ret; + + qdisc_get_default(id, IFNAMSIZ); + + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) + ret = qdisc_set_default(id); + return ret; +} +#endif + +static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { - .ctl_name = NET_CORE_WMEM_MAX, .procname = "wmem_max", .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { - .ctl_name = NET_CORE_RMEM_MAX, .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { - .ctl_name = NET_CORE_WMEM_DEFAULT, .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { - .ctl_name = NET_CORE_RMEM_DEFAULT, .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { - .ctl_name = NET_CORE_DEV_WEIGHT, .procname = "dev_weight", .data = &weight_p, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_MAX_BACKLOG, .procname = "netdev_max_backlog", .data = &netdev_max_backlog, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec + }, +#ifdef CONFIG_BPF_JIT + { + .procname = "bpf_jit_enable", + .data = &bpf_jit_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif + { + .procname = "netdev_tstamp_prequeue", + .data = &netdev_tstamp_prequeue, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_MSG_COST, .procname = "message_cost", - .data = &net_msg_cost, + .data = &net_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { - .ctl_name = NET_CORE_MSG_BURST, .procname = "message_burst", - .data = &net_msg_burst, + .data = &net_ratelimit_state.burst, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { - .ctl_name = NET_CORE_OPTMEM_MAX, .procname = "optmem_max", .data = &sysctl_optmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, -#ifdef CONFIG_NET_DIVERT +#ifdef CONFIG_RPS { - .ctl_name = NET_CORE_DIVERT_VERSION, - .procname = "divert_version", - .data = (void *)sysctl_divert_version, - .maxlen = 32, - .mode = 0444, - .proc_handler = &proc_dostring + .procname = "rps_sock_flow_entries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = rps_sock_flow_sysctl }, -#endif /* CONFIG_NET_DIVERT */ -#endif /* CONFIG_NET */ +#endif +#ifdef CONFIG_NET_FLOW_LIMIT { - .ctl_name = NET_CORE_SOMAXCONN, - .procname = "somaxconn", - .data = &sysctl_somaxconn, + .procname = "flow_limit_cpu_bitmap", + .mode = 0644, + .proc_handler = flow_limit_cpu_sysctl + }, + { + .procname = "flow_limit_table_len", + .data = &netdev_flow_limit_table_len, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = flow_limit_table_len_sysctl + }, +#endif /* CONFIG_NET_FLOW_LIMIT */ +#ifdef CONFIG_NET_RX_BUSY_POLL + { + .procname = "busy_poll", + .data = &sysctl_net_busy_poll, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "busy_read", + .data = &sysctl_net_busy_read, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif +#ifdef CONFIG_NET_SCHED + { + .procname = "default_qdisc", + .mode = 0644, + .maxlen = IFNAMSIZ, + .proc_handler = set_default_qdisc }, +#endif +#endif /* CONFIG_NET */ { - .ctl_name = NET_CORE_BUDGET, .procname = "netdev_budget", .data = &netdev_budget, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec + }, + { + .procname = "warnings", + .data = &net_msg_warn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; -#endif +static struct ctl_table netns_core_table[] = { + { + .procname = "somaxconn", + .data = &init_net.core.sysctl_somaxconn, + .maxlen = sizeof(int), + .mode = 0644, + .extra1 = &zero, + .extra2 = &ushort_max, + .proc_handler = proc_dointvec_minmax + }, + { } +}; + +static __net_init int sysctl_core_net_init(struct net *net) +{ + struct ctl_table *tbl; + + net->core.sysctl_somaxconn = SOMAXCONN; + + tbl = netns_core_table; + if (!net_eq(net, &init_net)) { + tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); + if (tbl == NULL) + goto err_dup; + + tbl[0].data = &net->core.sysctl_somaxconn; + + /* Don't export any sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) { + tbl[0].procname = NULL; + } + } + + net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl); + if (net->core.sysctl_hdr == NULL) + goto err_reg; + + return 0; + +err_reg: + if (tbl != netns_core_table) + kfree(tbl); +err_dup: + return -ENOMEM; +} + +static __net_exit void sysctl_core_net_exit(struct net *net) +{ + struct ctl_table *tbl; + + tbl = net->core.sysctl_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->core.sysctl_hdr); + BUG_ON(tbl == netns_core_table); + kfree(tbl); +} + +static __net_initdata struct pernet_operations sysctl_core_ops = { + .init = sysctl_core_net_init, + .exit = sysctl_core_net_exit, +}; + +static __init int sysctl_core_init(void) +{ + register_net_sysctl(&init_net, "net/core", net_core_table); + return register_pernet_subsys(&sysctl_core_ops); +} + +fs_initcall(sysctl_core_init); diff --git a/net/core/timestamping.c b/net/core/timestamping.c new file mode 100644 index 00000000000..6521dfd8b7c --- /dev/null +++ b/net/core/timestamping.c @@ -0,0 +1,134 @@ +/* + * PTP 1588 clock support - support for timestamping in PHY devices + * + * Copyright (C) 2010 OMICRON electronics GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * 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. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#include <linux/errqueue.h> +#include <linux/phy.h> +#include <linux/ptp_classify.h> +#include <linux/skbuff.h> +#include <linux/export.h> + +static unsigned int classify(const struct sk_buff *skb) +{ + if (likely(skb->dev && skb->dev->phydev && + skb->dev->phydev->drv)) + return ptp_classify_raw(skb); + else + return PTP_CLASS_NONE; +} + +void skb_clone_tx_timestamp(struct sk_buff *skb) +{ + struct phy_device *phydev; + struct sk_buff *clone; + struct sock *sk = skb->sk; + unsigned int type; + + if (!sk) + return; + + type = classify(skb); + + switch (type) { + case PTP_CLASS_V1_IPV4: + case PTP_CLASS_V1_IPV6: + case PTP_CLASS_V2_IPV4: + case PTP_CLASS_V2_IPV6: + case PTP_CLASS_V2_L2: + case PTP_CLASS_V2_VLAN: + phydev = skb->dev->phydev; + 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); + } + break; + default: + break; + } +} +EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); + +void skb_complete_tx_timestamp(struct sk_buff *skb, + struct skb_shared_hwtstamps *hwtstamps) +{ + struct sock *sk = skb->sk; + struct sock_exterr_skb *serr; + int err; + + if (!hwtstamps) { + sock_put(sk); + kfree_skb(skb); + return; + } + + *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); +} +EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); + +bool skb_defer_rx_timestamp(struct sk_buff *skb) +{ + struct phy_device *phydev; + unsigned int type; + + if (skb_headroom(skb) < ETH_HLEN) + return false; + __skb_push(skb, ETH_HLEN); + + type = classify(skb); + + __skb_pull(skb, ETH_HLEN); + + switch (type) { + case PTP_CLASS_V1_IPV4: + case PTP_CLASS_V1_IPV6: + case PTP_CLASS_V2_IPV4: + case PTP_CLASS_V2_IPV6: + case PTP_CLASS_V2_L2: + case PTP_CLASS_V2_VLAN: + phydev = skb->dev->phydev; + if (likely(phydev->drv->rxtstamp)) + return phydev->drv->rxtstamp(phydev, skb, type); + break; + default: + break; + } + + return false; +} +EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp); diff --git a/net/core/tso.c b/net/core/tso.c new file mode 100644 index 00000000000..8c3203c585b --- /dev/null +++ b/net/core/tso.c @@ -0,0 +1,77 @@ +#include <linux/export.h> +#include <net/ip.h> +#include <net/tso.h> + +/* Calculate expected number of TX descriptors */ +int tso_count_descs(struct sk_buff *skb) +{ + /* The Marvell Way */ + return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags; +} +EXPORT_SYMBOL(tso_count_descs); + +void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso, + int size, bool is_last) +{ + struct iphdr *iph; + struct tcphdr *tcph; + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + int mac_hdr_len = skb_network_offset(skb); + + memcpy(hdr, skb->data, hdr_len); + iph = (struct iphdr *)(hdr + mac_hdr_len); + iph->id = htons(tso->ip_id); + iph->tot_len = htons(size + hdr_len - mac_hdr_len); + tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb)); + tcph->seq = htonl(tso->tcp_seq); + tso->ip_id++; + + if (!is_last) { + /* Clear all special flags for not last packet */ + tcph->psh = 0; + tcph->fin = 0; + tcph->rst = 0; + } +} +EXPORT_SYMBOL(tso_build_hdr); + +void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size) +{ + tso->tcp_seq += size; + tso->size -= size; + tso->data += size; + + if ((tso->size == 0) && + (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; + + /* Move to next segment */ + tso->size = frag->size; + tso->data = page_address(frag->page.p) + frag->page_offset; + tso->next_frag_idx++; + } +} +EXPORT_SYMBOL(tso_build_data); + +void tso_start(struct sk_buff *skb, struct tso_t *tso) +{ + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + + tso->ip_id = ntohs(ip_hdr(skb)->id); + tso->tcp_seq = ntohl(tcp_hdr(skb)->seq); + tso->next_frag_idx = 0; + + /* Build first data */ + tso->size = skb_headlen(skb) - hdr_len; + tso->data = skb->data + hdr_len; + if ((tso->size == 0) && + (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; + + /* Move to next segment */ + tso->size = frag->size; + tso->data = page_address(frag->page.p) + frag->page_offset; + tso->next_frag_idx++; + } +} +EXPORT_SYMBOL(tso_start); diff --git a/net/core/user_dma.c b/net/core/user_dma.c new file mode 100644 index 00000000000..1b5fefdb819 --- /dev/null +++ b/net/core/user_dma.c @@ -0,0 +1,131 @@ +/* + * Copyright(c) 2004 - 2006 Intel Corporation. All rights reserved. + * Portions based on net/core/datagram.c and copyrighted by their authors. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * 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. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 + * Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * The full GNU General Public License is included in this distribution in the + * file called COPYING. + */ + +/* + * This code allows the net stack to make use of a DMA engine for + * skb to iovec copies. + */ + +#include <linux/dmaengine.h> +#include <linux/socket.h> +#include <linux/export.h> +#include <net/tcp.h> +#include <net/netdma.h> + +#define NET_DMA_DEFAULT_COPYBREAK 4096 + +int sysctl_tcp_dma_copybreak = NET_DMA_DEFAULT_COPYBREAK; +EXPORT_SYMBOL(sysctl_tcp_dma_copybreak); + +/** + * dma_skb_copy_datagram_iovec - Copy a datagram to an iovec. + * @skb - buffer to copy + * @offset - offset in the buffer to start copying from + * @iovec - io vector to copy to + * @len - amount of data to copy from buffer to iovec + * @pinned_list - locked iovec buffer data + * + * Note: the iovec is modified during the copy. + */ +int dma_skb_copy_datagram_iovec(struct dma_chan *chan, + struct sk_buff *skb, int offset, struct iovec *to, + size_t len, struct dma_pinned_list *pinned_list) +{ + int start = skb_headlen(skb); + int i, copy = start - offset; + struct sk_buff *frag_iter; + dma_cookie_t cookie = 0; + + /* Copy header. */ + if (copy > 0) { + if (copy > len) + copy = len; + cookie = dma_memcpy_to_iovec(chan, to, pinned_list, + skb->data + offset, copy); + if (cookie < 0) + goto fault; + len -= copy; + if (len == 0) + goto end; + offset += copy; + } + + /* Copy paged appendix. Hmm... why does this look so complicated? */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(frag); + copy = end - offset; + if (copy > 0) { + struct page *page = skb_frag_page(frag); + + if (copy > len) + copy = len; + + cookie = dma_memcpy_pg_to_iovec(chan, to, pinned_list, page, + frag->page_offset + offset - start, copy); + if (cookie < 0) + goto fault; + len -= copy; + if (len == 0) + goto end; + offset += copy; + } + start = end; + } + + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + copy = end - offset; + if (copy > 0) { + if (copy > len) + copy = len; + cookie = dma_skb_copy_datagram_iovec(chan, frag_iter, + offset - start, + to, copy, + pinned_list); + if (cookie < 0) + goto fault; + len -= copy; + if (len == 0) + goto end; + offset += copy; + } + start = end; + } + +end: + if (!len) { + skb->dma_cookie = cookie; + return cookie; + } + +fault: + return -EFAULT; +} diff --git a/net/core/utils.c b/net/core/utils.c index ac1d1fcf867..eed34338736 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -3,7 +3,8 @@ * * Authors: * net_random Alan Cox - * net_ratelimit Andy Kleen + * net_ratelimit Andi Kleen + * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * @@ -16,145 +17,34 @@ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/random.h> #include <linux/percpu.h> #include <linux/init.h> +#include <linux/ratelimit.h> + +#include <net/sock.h> +#include <net/net_ratelimit.h> #include <asm/byteorder.h> -#include <asm/system.h> #include <asm/uaccess.h> -/* - This is a maximally equidistributed combined Tausworthe generator - based on code from GNU Scientific Library 1.5 (30 Jun 2004) - - x_n = (s1_n ^ s2_n ^ s3_n) - - s1_{n+1} = (((s1_n & 4294967294) <<12) ^ (((s1_n <<13) ^ s1_n) >>19)) - s2_{n+1} = (((s2_n & 4294967288) << 4) ^ (((s2_n << 2) ^ s2_n) >>25)) - s3_{n+1} = (((s3_n & 4294967280) <<17) ^ (((s3_n << 3) ^ s3_n) >>11)) - - The period of this generator is about 2^88. - - From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe - Generators", Mathematics of Computation, 65, 213 (1996), 203--213. - - This is available on the net from L'Ecuyer's home page, +int net_msg_warn __read_mostly = 1; +EXPORT_SYMBOL(net_msg_warn); - http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps - ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps - - There is an erratum in the paper "Tables of Maximally - Equidistributed Combined LFSR Generators", Mathematics of - Computation, 68, 225 (1999), 261--269: - http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps - - ... the k_j most significant bits of z_j must be non- - zero, for each j. (Note: this restriction also applies to the - computer code given in [4], but was mistakenly not mentioned in - that paper.) - - This affects the seeding procedure by imposing the requirement - s1 > 1, s2 > 7, s3 > 15. - -*/ -struct nrnd_state { - u32 s1, s2, s3; -}; - -static DEFINE_PER_CPU(struct nrnd_state, net_rand_state); - -static u32 __net_random(struct nrnd_state *state) -{ -#define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b) - - state->s1 = TAUSWORTHE(state->s1, 13, 19, 4294967294UL, 12); - state->s2 = TAUSWORTHE(state->s2, 2, 25, 4294967288UL, 4); - state->s3 = TAUSWORTHE(state->s3, 3, 11, 4294967280UL, 17); - - return (state->s1 ^ state->s2 ^ state->s3); -} - -static void __net_srandom(struct nrnd_state *state, unsigned long s) -{ - if (s == 0) - s = 1; /* default seed is 1 */ - -#define LCG(n) (69069 * n) - state->s1 = LCG(s); - state->s2 = LCG(state->s1); - state->s3 = LCG(state->s2); - - /* "warm it up" */ - __net_random(state); - __net_random(state); - __net_random(state); - __net_random(state); - __net_random(state); - __net_random(state); -} - - -unsigned long net_random(void) -{ - unsigned long r; - struct nrnd_state *state = &get_cpu_var(net_rand_state); - r = __net_random(state); - put_cpu_var(state); - return r; -} - - -void net_srandom(unsigned long entropy) -{ - struct nrnd_state *state = &get_cpu_var(net_rand_state); - __net_srandom(state, state->s1^entropy); - put_cpu_var(state); -} - -void __init net_random_init(void) -{ - int i; - - for (i = 0; i < NR_CPUS; i++) { - struct nrnd_state *state = &per_cpu(net_rand_state,i); - __net_srandom(state, i+jiffies); - } -} - -static int net_random_reseed(void) -{ - int i; - unsigned long seed[NR_CPUS]; - - get_random_bytes(seed, sizeof(seed)); - for (i = 0; i < NR_CPUS; i++) { - struct nrnd_state *state = &per_cpu(net_rand_state,i); - __net_srandom(state, seed[i]); - } - return 0; -} -late_initcall(net_random_reseed); - -int net_msg_cost = 5*HZ; -int net_msg_burst = 10; - -/* +DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); +/* * All net warning printk()s should be guarded by this function. - */ + */ int net_ratelimit(void) { - return __printk_ratelimit(net_msg_cost, net_msg_burst); + return __ratelimit(&net_ratelimit_state); } - -EXPORT_SYMBOL(net_random); EXPORT_SYMBOL(net_ratelimit); -EXPORT_SYMBOL(net_srandom); /* * Convert an ASCII string to binary IP. @@ -169,14 +59,11 @@ __be32 in_aton(const char *str) int i; l = 0; - for (i = 0; i < 4; i++) - { + for (i = 0; i < 4; i++) { l <<= 8; - if (*str != '\0') - { + if (*str != '\0') { val = 0; - while (*str != '\0' && *str != '.' && *str != '\n') - { + while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; @@ -186,7 +73,317 @@ __be32 in_aton(const char *str) str++; } } - return(htonl(l)); + return htonl(l); } - EXPORT_SYMBOL(in_aton); + +#define IN6PTON_XDIGIT 0x00010000 +#define IN6PTON_DIGIT 0x00020000 +#define IN6PTON_COLON_MASK 0x00700000 +#define IN6PTON_COLON_1 0x00100000 /* single : requested */ +#define IN6PTON_COLON_2 0x00200000 /* second : requested */ +#define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ +#define IN6PTON_DOT 0x00800000 /* . */ +#define IN6PTON_DELIM 0x10000000 +#define IN6PTON_NULL 0x20000000 /* first/tail */ +#define IN6PTON_UNKNOWN 0x40000000 + +static inline int xdigit2bin(char c, int delim) +{ + int val; + + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == ':') + return IN6PTON_COLON_MASK; + if (c == '.') + return IN6PTON_DOT; + + val = hex_to_bin(c); + if (val >= 0) + return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); + + if (delim == -1) + return IN6PTON_DELIM; + return IN6PTON_UNKNOWN; +} + +/** + * in4_pton - convert an IPv4 address from literal to binary representation + * @src: the start of the IPv4 address string + * @srclen: the length of the string, -1 means strlen(src) + * @dst: the binary (u8[4] array) representation of the IPv4 address + * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter + * @end: A pointer to the end of the parsed string will be placed here + * + * Return one on success, return zero when any error occurs + * and @end will point to the end of the parsed string. + * + */ +int in4_pton(const char *src, int srclen, + u8 *dst, + int delim, const char **end) +{ + const char *s; + u8 *d; + u8 dbuf[4]; + int ret = 0; + int i; + int w = 0; + + if (srclen < 0) + srclen = strlen(src); + s = src; + d = dbuf; + i = 0; + while(1) { + int c; + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) { + goto out; + } + if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) { + if (w == 0) + goto out; + *d++ = w & 0xff; + w = 0; + i++; + if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { + if (i != 4) + goto out; + break; + } + goto cont; + } + w = (w * 10) + c; + if ((w & 0xffff) > 255) { + goto out; + } +cont: + if (i >= 4) + goto out; + s++; + srclen--; + } + ret = 1; + memcpy(dst, dbuf, sizeof(dbuf)); +out: + if (end) + *end = s; + return ret; +} +EXPORT_SYMBOL(in4_pton); + +/** + * in6_pton - convert an IPv6 address from literal to binary representation + * @src: the start of the IPv6 address string + * @srclen: the length of the string, -1 means strlen(src) + * @dst: the binary (u8[16] array) representation of the IPv6 address + * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter + * @end: A pointer to the end of the parsed string will be placed here + * + * Return one on success, return zero when any error occurs + * and @end will point to the end of the parsed string. + * + */ +int in6_pton(const char *src, int srclen, + u8 *dst, + int delim, const char **end) +{ + const char *s, *tok = NULL; + u8 *d, *dc = NULL; + u8 dbuf[16]; + int ret = 0; + int i; + int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; + int w = 0; + + memset(dbuf, 0, sizeof(dbuf)); + + s = src; + d = dbuf; + if (srclen < 0) + srclen = strlen(src); + + while (1) { + int c; + + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & state)) + goto out; + if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { + /* process one 16-bit word */ + if (!(state & IN6PTON_NULL)) { + *d++ = (w >> 8) & 0xff; + *d++ = w & 0xff; + } + w = 0; + if (c & IN6PTON_DELIM) { + /* We've processed last word */ + break; + } + /* + * COLON_1 => XDIGIT + * COLON_2 => XDIGIT|DELIM + * COLON_1_2 => COLON_2 + */ + switch (state & IN6PTON_COLON_MASK) { + case IN6PTON_COLON_2: + dc = d; + state = IN6PTON_XDIGIT | IN6PTON_DELIM; + if (dc - dbuf >= sizeof(dbuf)) + state |= IN6PTON_NULL; + break; + case IN6PTON_COLON_1|IN6PTON_COLON_1_2: + state = IN6PTON_XDIGIT | IN6PTON_COLON_2; + break; + case IN6PTON_COLON_1: + state = IN6PTON_XDIGIT; + break; + case IN6PTON_COLON_1_2: + state = IN6PTON_COLON_2; + break; + default: + state = 0; + } + tok = s + 1; + goto cont; + } + + if (c & IN6PTON_DOT) { + ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); + if (ret > 0) { + d += 4; + break; + } + goto out; + } + + w = (w << 4) | (0xff & c); + state = IN6PTON_COLON_1 | IN6PTON_DELIM; + if (!(w & 0xf000)) { + state |= IN6PTON_XDIGIT; + } + if (!dc && d + 2 < dbuf + sizeof(dbuf)) { + state |= IN6PTON_COLON_1_2; + state &= ~IN6PTON_DELIM; + } + if (d + 2 >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); + } +cont: + if ((dc && d + 4 < dbuf + sizeof(dbuf)) || + d + 4 == dbuf + sizeof(dbuf)) { + state |= IN6PTON_DOT; + } + if (d >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); + } + s++; + srclen--; + } + + i = 15; d--; + + if (dc) { + while(d >= dc) + dst[i--] = *d--; + while(i >= dc - dbuf) + dst[i--] = 0; + while(i >= 0) + dst[i--] = *d--; + } else + memcpy(dst, dbuf, sizeof(dbuf)); + + ret = 1; +out: + if (end) + *end = s; + return ret; +} +EXPORT_SYMBOL(in6_pton); + +void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, + __be32 from, __be32 to, int pseudohdr) +{ + __be32 diff[] = { ~from, to }; + if (skb->ip_summed != CHECKSUM_PARTIAL) { + *sum = csum_fold(csum_partial(diff, sizeof(diff), + ~csum_unfold(*sum))); + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + skb->csum = ~csum_partial(diff, sizeof(diff), + ~skb->csum); + } else if (pseudohdr) + *sum = ~csum_fold(csum_partial(diff, sizeof(diff), + csum_unfold(*sum))); +} +EXPORT_SYMBOL(inet_proto_csum_replace4); + +void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, + const __be32 *from, const __be32 *to, + int pseudohdr) +{ + __be32 diff[] = { + ~from[0], ~from[1], ~from[2], ~from[3], + to[0], to[1], to[2], to[3], + }; + if (skb->ip_summed != CHECKSUM_PARTIAL) { + *sum = csum_fold(csum_partial(diff, sizeof(diff), + ~csum_unfold(*sum))); + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + skb->csum = ~csum_partial(diff, sizeof(diff), + ~skb->csum); + } else if (pseudohdr) + *sum = ~csum_fold(csum_partial(diff, sizeof(diff), + csum_unfold(*sum))); +} +EXPORT_SYMBOL(inet_proto_csum_replace16); + +struct __net_random_once_work { + struct work_struct work; + struct static_key *key; +}; + +static void __net_random_once_deferred(struct work_struct *w) +{ + struct __net_random_once_work *work = + container_of(w, struct __net_random_once_work, work); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); + kfree(work); +} + +static void __net_random_once_disable_jump(struct static_key *key) +{ + struct __net_random_once_work *w; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (!w) + return; + + INIT_WORK(&w->work, __net_random_once_deferred); + w->key = key; + schedule_work(&w->work); +} + +bool __net_get_random_once(void *buf, int nbytes, bool *done, + struct static_key *once_key) +{ + static DEFINE_SPINLOCK(lock); + unsigned long flags; + + spin_lock_irqsave(&lock, flags); + if (*done) { + spin_unlock_irqrestore(&lock, flags); + return false; + } + + get_random_bytes(buf, nbytes); + *done = true; + spin_unlock_irqrestore(&lock, flags); + + __net_random_once_disable_jump(once_key); + + return true; +} +EXPORT_SYMBOL(__net_get_random_once); diff --git a/net/core/wireless.c b/net/core/wireless.c deleted file mode 100644 index 2add7ed609e..00000000000 --- a/net/core/wireless.c +++ /dev/null @@ -1,1542 +0,0 @@ -/* - * This file implement the Wireless Extensions APIs. - * - * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> - * Copyright (c) 1997-2005 Jean Tourrilhes, All Rights Reserved. - * - * (As all part of the Linux kernel, this file is GPL) - */ - -/************************** DOCUMENTATION **************************/ -/* - * API definition : - * -------------- - * See <linux/wireless.h> for details of the APIs and the rest. - * - * History : - * ------- - * - * v1 - 5.12.01 - Jean II - * o Created this file. - * - * v2 - 13.12.01 - Jean II - * o Move /proc/net/wireless stuff from net/core/dev.c to here - * o Make Wireless Extension IOCTLs go through here - * o Added iw_handler handling ;-) - * o Added standard ioctl description - * o Initial dumb commit strategy based on orinoco.c - * - * v3 - 19.12.01 - Jean II - * o Make sure we don't go out of standard_ioctl[] in ioctl_standard_call - * o Add event dispatcher function - * o Add event description - * o Propagate events as rtnetlink IFLA_WIRELESS option - * o Generate event on selected SET requests - * - * v4 - 18.04.02 - Jean II - * o Fix stupid off by one in iw_ioctl_description : IW_ESSID_MAX_SIZE + 1 - * - * v5 - 21.06.02 - Jean II - * o Add IW_PRIV_TYPE_ADDR in priv_type_size (+cleanup) - * o Reshuffle IW_HEADER_TYPE_XXX to map IW_PRIV_TYPE_XXX changes - * o Add IWEVCUSTOM for driver specific event/scanning token - * o Turn on WE_STRICT_WRITE by default + kernel warning - * o Fix WE_STRICT_WRITE in ioctl_export_private() (32 => iw_num) - * o Fix off-by-one in test (extra_size <= IFNAMSIZ) - * - * v6 - 9.01.03 - Jean II - * o Add common spy support : iw_handler_set_spy(), wireless_spy_update() - * o Add enhanced spy support : iw_handler_set_thrspy() and event. - * o Add WIRELESS_EXT version display in /proc/net/wireless - * - * v6 - 18.06.04 - Jean II - * o Change get_spydata() method for added safety - * o Remove spy #ifdef, they are always on -> cleaner code - * o Allow any size GET request if user specifies length > max - * and if request has IW_DESCR_FLAG_NOMAX flag or is SIOCGIWPRIV - * o Start migrating get_wireless_stats to struct iw_handler_def - * o Add wmb() in iw_handler_set_spy() for non-coherent archs/cpus - * Based on patch from Pavel Roskin <proski@gnu.org> : - * o Fix kernel data leak to user space in private handler handling - * - * v7 - 18.3.05 - Jean II - * o Remove (struct iw_point *)->pointer from events and streams - * o Remove spy_offset from struct iw_handler_def - * o Start deprecating dev->get_wireless_stats, output a warning - * o If IW_QUAL_DBM is set, show dBm values in /proc/net/wireless - * o Don't loose INVALID/DBM flags when clearing UPDATED flags (iwstats) - */ - -/***************************** INCLUDES *****************************/ - -#include <linux/config.h> /* Not needed ??? */ -#include <linux/module.h> -#include <linux/types.h> /* off_t */ -#include <linux/netdevice.h> /* struct ifreq, dev_get_by_name() */ -#include <linux/proc_fs.h> -#include <linux/rtnetlink.h> /* rtnetlink stuff */ -#include <linux/seq_file.h> -#include <linux/init.h> /* for __init */ -#include <linux/if_arp.h> /* ARPHRD_ETHER */ -#include <linux/etherdevice.h> /* compare_ether_addr */ - -#include <linux/wireless.h> /* Pretty obvious */ -#include <net/iw_handler.h> /* New driver API */ - -#include <asm/uaccess.h> /* copy_to_user() */ - -/**************************** CONSTANTS ****************************/ - -/* Debugging stuff */ -#undef WE_IOCTL_DEBUG /* Debug IOCTL API */ -#undef WE_EVENT_DEBUG /* Debug Event dispatcher */ -#undef WE_SPY_DEBUG /* Debug enhanced spy support */ - -/* Options */ -#define WE_EVENT_NETLINK /* Propagate events using rtnetlink */ -#define WE_SET_EVENT /* Generate an event on some set commands */ - -/************************* GLOBAL VARIABLES *************************/ -/* - * You should not use global variables, because of re-entrancy. - * On our case, it's only const, so it's OK... - */ -/* - * Meta-data about all the standard Wireless Extension request we - * know about. - */ -static const struct iw_ioctl_description standard_ioctl[] = { - [SIOCSIWCOMMIT - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWNAME - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_CHAR, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWNWID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWNWID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWFREQ - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_FREQ, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWFREQ - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_FREQ, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWMODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_UINT, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWMODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_UINT, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWSENS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWSENS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWRANGE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWRANGE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_range), - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWPRIV - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWPRIV - SIOCIWFIRST] = { /* (handled directly by us) */ - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCSIWSTATS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_NULL, - }, - [SIOCGIWSTATS - SIOCIWFIRST] = { /* (handled directly by us) */ - .header_type = IW_HEADER_TYPE_NULL, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct sockaddr), - .max_tokens = IW_MAX_SPY, - }, - [SIOCGIWSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct sockaddr) + - sizeof(struct iw_quality), - .max_tokens = IW_MAX_SPY, - }, - [SIOCSIWTHRSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct iw_thrspy), - .min_tokens = 1, - .max_tokens = 1, - }, - [SIOCGIWTHRSPY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct iw_thrspy), - .min_tokens = 1, - .max_tokens = 1, - }, - [SIOCSIWAP - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [SIOCGIWAP - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWMLME - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_mlme), - .max_tokens = sizeof(struct iw_mlme), - }, - [SIOCGIWAPLIST - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = sizeof(struct sockaddr) + - sizeof(struct iw_quality), - .max_tokens = IW_MAX_AP, - .flags = IW_DESCR_FLAG_NOMAX, - }, - [SIOCSIWSCAN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = 0, - .max_tokens = sizeof(struct iw_scan_req), - }, - [SIOCGIWSCAN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_SCAN_MAX_DATA, - .flags = IW_DESCR_FLAG_NOMAX, - }, - [SIOCSIWESSID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, - .flags = IW_DESCR_FLAG_EVENT, - }, - [SIOCGIWESSID - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, - .flags = IW_DESCR_FLAG_DUMP, - }, - [SIOCSIWNICKN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, - }, - [SIOCGIWNICKN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, - }, - [SIOCSIWRATE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWRATE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWRTS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWRTS - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWFRAG - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWFRAG - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWTXPOW - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWTXPOW - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWRETRY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWRETRY - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWENCODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ENCODING_TOKEN_MAX, - .flags = IW_DESCR_FLAG_EVENT | IW_DESCR_FLAG_RESTRICT, - }, - [SIOCGIWENCODE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_ENCODING_TOKEN_MAX, - .flags = IW_DESCR_FLAG_DUMP | IW_DESCR_FLAG_RESTRICT, - }, - [SIOCSIWPOWER - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWPOWER - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWGENIE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [SIOCGIWGENIE - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [SIOCSIWAUTH - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCGIWAUTH - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, - }, - [SIOCSIWENCODEEXT - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_encode_ext), - .max_tokens = sizeof(struct iw_encode_ext) + - IW_ENCODING_TOKEN_MAX, - }, - [SIOCGIWENCODEEXT - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_encode_ext), - .max_tokens = sizeof(struct iw_encode_ext) + - IW_ENCODING_TOKEN_MAX, - }, - [SIOCSIWPMKSA - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .min_tokens = sizeof(struct iw_pmksa), - .max_tokens = sizeof(struct iw_pmksa), - }, -}; -static const int standard_ioctl_num = (sizeof(standard_ioctl) / - sizeof(struct iw_ioctl_description)); - -/* - * Meta-data about all the additional standard Wireless Extension events - * we know about. - */ -static const struct iw_ioctl_description standard_event[] = { - [IWEVTXDROP - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [IWEVQUAL - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_QUAL, - }, - [IWEVCUSTOM - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_CUSTOM_MAX, - }, - [IWEVREGISTERED - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [IWEVEXPIRED - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_ADDR, - }, - [IWEVGENIE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [IWEVMICHAELMICFAILURE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_michaelmicfailure), - }, - [IWEVASSOCREQIE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [IWEVASSOCRESPIE - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = IW_GENERIC_IE_MAX, - }, - [IWEVPMKIDCAND - IWEVFIRST] = { - .header_type = IW_HEADER_TYPE_POINT, - .token_size = 1, - .max_tokens = sizeof(struct iw_pmkid_cand), - }, -}; -static const int standard_event_num = (sizeof(standard_event) / - sizeof(struct iw_ioctl_description)); - -/* Size (in bytes) of the various private data types */ -static const char iw_priv_type_size[] = { - 0, /* IW_PRIV_TYPE_NONE */ - 1, /* IW_PRIV_TYPE_BYTE */ - 1, /* IW_PRIV_TYPE_CHAR */ - 0, /* Not defined */ - sizeof(__u32), /* IW_PRIV_TYPE_INT */ - sizeof(struct iw_freq), /* IW_PRIV_TYPE_FLOAT */ - sizeof(struct sockaddr), /* IW_PRIV_TYPE_ADDR */ - 0, /* Not defined */ -}; - -/* Size (in bytes) of various events */ -static const int event_type_size[] = { - IW_EV_LCP_LEN, /* IW_HEADER_TYPE_NULL */ - 0, - IW_EV_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ - 0, - IW_EV_UINT_LEN, /* IW_HEADER_TYPE_UINT */ - IW_EV_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ - IW_EV_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ - 0, - IW_EV_POINT_LEN, /* Without variable payload */ - IW_EV_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ - IW_EV_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ -}; - -/************************ COMMON SUBROUTINES ************************/ -/* - * Stuff that may be used in various place or doesn't fit in one - * of the section below. - */ - -/* ---------------------------------------------------------------- */ -/* - * Return the driver handler associated with a specific Wireless Extension. - * Called from various place, so make sure it remains efficient. - */ -static inline iw_handler get_handler(struct net_device *dev, - unsigned int cmd) -{ - /* Don't "optimise" the following variable, it will crash */ - unsigned int index; /* *MUST* be unsigned */ - - /* Check if we have some wireless handlers defined */ - if(dev->wireless_handlers == NULL) - return NULL; - - /* Try as a standard command */ - index = cmd - SIOCIWFIRST; - if(index < dev->wireless_handlers->num_standard) - return dev->wireless_handlers->standard[index]; - - /* Try as a private command */ - index = cmd - SIOCIWFIRSTPRIV; - if(index < dev->wireless_handlers->num_private) - return dev->wireless_handlers->private[index]; - - /* Not found */ - return NULL; -} - -/* ---------------------------------------------------------------- */ -/* - * Get statistics out of the driver - */ -static inline struct iw_statistics *get_wireless_stats(struct net_device *dev) -{ - /* New location */ - if((dev->wireless_handlers != NULL) && - (dev->wireless_handlers->get_wireless_stats != NULL)) - return dev->wireless_handlers->get_wireless_stats(dev); - - /* Old location, field to be removed in next WE */ - if(dev->get_wireless_stats) { - static int printed_message; - - if (!printed_message++) - printk(KERN_DEBUG "%s (WE) : Driver using old /proc/net/wireless support, please fix driver !\n", - dev->name); - - return dev->get_wireless_stats(dev); - } - - /* Not found */ - return (struct iw_statistics *) NULL; -} - -/* ---------------------------------------------------------------- */ -/* - * Call the commit handler in the driver - * (if exist and if conditions are right) - * - * Note : our current commit strategy is currently pretty dumb, - * but we will be able to improve on that... - * The goal is to try to agreagate as many changes as possible - * before doing the commit. Drivers that will define a commit handler - * are usually those that need a reset after changing parameters, so - * we want to minimise the number of reset. - * A cool idea is to use a timer : at each "set" command, we re-set the - * timer, when the timer eventually fires, we call the driver. - * Hopefully, more on that later. - * - * Also, I'm waiting to see how many people will complain about the - * netif_running(dev) test. I'm open on that one... - * Hopefully, the driver will remember to do a commit in "open()" ;-) - */ -static inline int call_commit_handler(struct net_device * dev) -{ - if((netif_running(dev)) && - (dev->wireless_handlers->standard[0] != NULL)) { - /* Call the commit handler on the driver */ - return dev->wireless_handlers->standard[0](dev, NULL, - NULL, NULL); - } else - return 0; /* Command completed successfully */ -} - -/* ---------------------------------------------------------------- */ -/* - * Calculate size of private arguments - */ -static inline int get_priv_size(__u16 args) -{ - int num = args & IW_PRIV_SIZE_MASK; - int type = (args & IW_PRIV_TYPE_MASK) >> 12; - - return num * iw_priv_type_size[type]; -} - -/* ---------------------------------------------------------------- */ -/* - * Re-calculate the size of private arguments - */ -static inline int adjust_priv_size(__u16 args, - union iwreq_data * wrqu) -{ - int num = wrqu->data.length; - int max = args & IW_PRIV_SIZE_MASK; - int type = (args & IW_PRIV_TYPE_MASK) >> 12; - - /* Make sure the driver doesn't goof up */ - if (max < num) - num = max; - - return num * iw_priv_type_size[type]; -} - - -/******************** /proc/net/wireless SUPPORT ********************/ -/* - * The /proc/net/wireless file is a human readable user-space interface - * exporting various wireless specific statistics from the wireless devices. - * This is the most popular part of the Wireless Extensions ;-) - * - * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). - * The content of the file is basically the content of "struct iw_statistics". - */ - -#ifdef CONFIG_PROC_FS - -/* ---------------------------------------------------------------- */ -/* - * Print one entry (line) of /proc/net/wireless - */ -static __inline__ void wireless_seq_printf_stats(struct seq_file *seq, - struct net_device *dev) -{ - /* Get stats from the driver */ - struct iw_statistics *stats = get_wireless_stats(dev); - - if (stats) { - seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " - "%6d %6d %6d\n", - dev->name, stats->status, stats->qual.qual, - stats->qual.updated & IW_QUAL_QUAL_UPDATED - ? '.' : ' ', - ((__s32) stats->qual.level) - - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), - stats->qual.updated & IW_QUAL_LEVEL_UPDATED - ? '.' : ' ', - ((__s32) stats->qual.noise) - - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), - stats->qual.updated & IW_QUAL_NOISE_UPDATED - ? '.' : ' ', - stats->discard.nwid, stats->discard.code, - stats->discard.fragment, stats->discard.retries, - stats->discard.misc, stats->miss.beacon); - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; - } -} - -/* ---------------------------------------------------------------- */ -/* - * Print info for /proc/net/wireless (print all entries) - */ -static int wireless_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_printf(seq, "Inter-| sta-| Quality | Discarded " - "packets | Missed | WE\n" - " face | tus | link level noise | nwid " - "crypt frag retry misc | beacon | %d\n", - WIRELESS_EXT); - else - wireless_seq_printf_stats(seq, v); - return 0; -} - -static struct seq_operations wireless_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = wireless_seq_show, -}; - -static int wireless_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &wireless_seq_ops); -} - -static struct file_operations wireless_seq_fops = { - .owner = THIS_MODULE, - .open = wireless_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -int __init wireless_proc_init(void) -{ - /* Create /proc/net/wireless entry */ - if (!proc_net_fops_create("wireless", S_IRUGO, &wireless_seq_fops)) - return -ENOMEM; - - return 0; -} -#endif /* CONFIG_PROC_FS */ - -/************************** IOCTL SUPPORT **************************/ -/* - * The original user space API to configure all those Wireless Extensions - * is through IOCTLs. - * In there, we check if we need to call the new driver API (iw_handler) - * or just call the driver ioctl handler. - */ - -/* ---------------------------------------------------------------- */ -/* - * Allow programatic access to /proc/net/wireless even if /proc - * doesn't exist... Also more efficient... - */ -static inline int dev_iwstats(struct net_device *dev, struct ifreq *ifr) -{ - /* Get stats from the driver */ - struct iw_statistics *stats; - - stats = get_wireless_stats(dev); - if (stats != (struct iw_statistics *) NULL) { - struct iwreq * wrq = (struct iwreq *)ifr; - - /* Copy statistics to the user buffer */ - if(copy_to_user(wrq->u.data.pointer, stats, - sizeof(struct iw_statistics))) - return -EFAULT; - - /* Check if we need to clear the updated flag */ - if(wrq->u.data.flags != 0) - stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; - return 0; - } else - return -EOPNOTSUPP; -} - -/* ---------------------------------------------------------------- */ -/* - * Export the driver private handler definition - * They will be picked up by tools like iwpriv... - */ -static inline int ioctl_export_private(struct net_device * dev, - struct ifreq * ifr) -{ - struct iwreq * iwr = (struct iwreq *) ifr; - - /* Check if the driver has something to export */ - if((dev->wireless_handlers->num_private_args == 0) || - (dev->wireless_handlers->private_args == NULL)) - return -EOPNOTSUPP; - - /* Check NULL pointer */ - if(iwr->u.data.pointer == NULL) - return -EFAULT; - - /* Check if there is enough buffer up there */ - if(iwr->u.data.length < dev->wireless_handlers->num_private_args) { - /* User space can't know in advance how large the buffer - * needs to be. Give it a hint, so that we can support - * any size buffer we want somewhat efficiently... */ - iwr->u.data.length = dev->wireless_handlers->num_private_args; - return -E2BIG; - } - - /* Set the number of available ioctls. */ - iwr->u.data.length = dev->wireless_handlers->num_private_args; - - /* Copy structure to the user buffer. */ - if (copy_to_user(iwr->u.data.pointer, - dev->wireless_handlers->private_args, - sizeof(struct iw_priv_args) * iwr->u.data.length)) - return -EFAULT; - - return 0; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a standard Wireless Extension handler. - * We do various checks and also take care of moving data between - * user space and kernel space. - */ -static inline int ioctl_standard_call(struct net_device * dev, - struct ifreq * ifr, - unsigned int cmd, - iw_handler handler) -{ - struct iwreq * iwr = (struct iwreq *) ifr; - const struct iw_ioctl_description * descr; - struct iw_request_info info; - int ret = -EINVAL; - - /* Get the description of the IOCTL */ - if((cmd - SIOCIWFIRST) >= standard_ioctl_num) - return -EOPNOTSUPP; - descr = &(standard_ioctl[cmd - SIOCIWFIRST]); - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Found standard handler for 0x%04X\n", - ifr->ifr_name, cmd); - printk(KERN_DEBUG "%s (WE) : Header type : %d, Token type : %d, size : %d, token : %d\n", dev->name, descr->header_type, descr->token_type, descr->token_size, descr->max_tokens); -#endif /* WE_IOCTL_DEBUG */ - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have a pointer to user space data or not */ - if(descr->header_type != IW_HEADER_TYPE_POINT) { - - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, &(iwr->u), NULL); - -#ifdef WE_SET_EVENT - /* Generate an event to notify listeners of the change */ - if((descr->flags & IW_DESCR_FLAG_EVENT) && - ((ret == 0) || (ret == -EIWCOMMIT))) - wireless_send_event(dev, cmd, &(iwr->u), NULL); -#endif /* WE_SET_EVENT */ - } else { - char * extra; - int extra_size; - int user_length = 0; - int err; - - /* Calculate space needed by arguments. Always allocate - * for max space. Easier, and won't last long... */ - extra_size = descr->max_tokens * descr->token_size; - - /* Check what user space is giving us */ - if(IW_IS_SET(cmd)) { - /* Check NULL pointer */ - if((iwr->u.data.pointer == NULL) && - (iwr->u.data.length != 0)) - return -EFAULT; - /* Check if number of token fits within bounds */ - if(iwr->u.data.length > descr->max_tokens) - return -E2BIG; - if(iwr->u.data.length < descr->min_tokens) - return -EINVAL; - } else { - /* Check NULL pointer */ - if(iwr->u.data.pointer == NULL) - return -EFAULT; - /* Save user space buffer size for checking */ - user_length = iwr->u.data.length; - - /* Don't check if user_length > max to allow forward - * compatibility. The test user_length < min is - * implied by the test at the end. */ - - /* Support for very large requests */ - if((descr->flags & IW_DESCR_FLAG_NOMAX) && - (user_length > descr->max_tokens)) { - /* Allow userspace to GET more than max so - * we can support any size GET requests. - * There is still a limit : -ENOMEM. */ - extra_size = user_length * descr->token_size; - /* Note : user_length is originally a __u16, - * and token_size is controlled by us, - * so extra_size won't get negative and - * won't overflow... */ - } - } - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Malloc %d bytes\n", - dev->name, extra_size); -#endif /* WE_IOCTL_DEBUG */ - - /* Create the kernel buffer */ - extra = kmalloc(extra_size, GFP_KERNEL); - if (extra == NULL) { - return -ENOMEM; - } - - /* If it is a SET, get all the extra data in here */ - if(IW_IS_SET(cmd) && (iwr->u.data.length != 0)) { - err = copy_from_user(extra, iwr->u.data.pointer, - iwr->u.data.length * - descr->token_size); - if (err) { - kfree(extra); - return -EFAULT; - } -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Got %d bytes\n", - dev->name, - iwr->u.data.length * descr->token_size); -#endif /* WE_IOCTL_DEBUG */ - } - - /* Call the handler */ - ret = handler(dev, &info, &(iwr->u), extra); - - /* If we have something to return to the user */ - if (!ret && IW_IS_GET(cmd)) { - /* Check if there is enough buffer up there */ - if(user_length < iwr->u.data.length) { - kfree(extra); - return -E2BIG; - } - - err = copy_to_user(iwr->u.data.pointer, extra, - iwr->u.data.length * - descr->token_size); - if (err) - ret = -EFAULT; -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Wrote %d bytes\n", - dev->name, - iwr->u.data.length * descr->token_size); -#endif /* WE_IOCTL_DEBUG */ - } - -#ifdef WE_SET_EVENT - /* Generate an event to notify listeners of the change */ - if((descr->flags & IW_DESCR_FLAG_EVENT) && - ((ret == 0) || (ret == -EIWCOMMIT))) { - if(descr->flags & IW_DESCR_FLAG_RESTRICT) - /* If the event is restricted, don't - * export the payload */ - wireless_send_event(dev, cmd, &(iwr->u), NULL); - else - wireless_send_event(dev, cmd, &(iwr->u), - extra); - } -#endif /* WE_SET_EVENT */ - - /* Cleanup - I told you it wasn't that long ;-) */ - kfree(extra); - } - - /* Call commit handler if needed and defined */ - if(ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - /* Here, we will generate the appropriate event if needed */ - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Wrapper to call a private Wireless Extension handler. - * We do various checks and also take care of moving data between - * user space and kernel space. - * It's not as nice and slimline as the standard wrapper. The cause - * is struct iw_priv_args, which was not really designed for the - * job we are going here. - * - * IMPORTANT : This function prevent to set and get data on the same - * IOCTL and enforce the SET/GET convention. Not doing it would be - * far too hairy... - * If you need to set and get data at the same time, please don't use - * a iw_handler but process it in your ioctl handler (i.e. use the - * old driver API). - */ -static inline int ioctl_private_call(struct net_device * dev, - struct ifreq * ifr, - unsigned int cmd, - iw_handler handler) -{ - struct iwreq * iwr = (struct iwreq *) ifr; - const struct iw_priv_args * descr = NULL; - struct iw_request_info info; - int extra_size = 0; - int i; - int ret = -EINVAL; - - /* Get the description of the IOCTL */ - for(i = 0; i < dev->wireless_handlers->num_private_args; i++) - if(cmd == dev->wireless_handlers->private_args[i].cmd) { - descr = &(dev->wireless_handlers->private_args[i]); - break; - } - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Found private handler for 0x%04X\n", - ifr->ifr_name, cmd); - if(descr) { - printk(KERN_DEBUG "%s (WE) : Name %s, set %X, get %X\n", - dev->name, descr->name, - descr->set_args, descr->get_args); - } -#endif /* WE_IOCTL_DEBUG */ - - /* Compute the size of the set/get arguments */ - if(descr != NULL) { - if(IW_IS_SET(cmd)) { - int offset = 0; /* For sub-ioctls */ - /* Check for sub-ioctl handler */ - if(descr->name[0] == '\0') - /* Reserve one int for sub-ioctl index */ - offset = sizeof(__u32); - - /* Size of set arguments */ - extra_size = get_priv_size(descr->set_args); - - /* Does it fits in iwr ? */ - if((descr->set_args & IW_PRIV_SIZE_FIXED) && - ((extra_size + offset) <= IFNAMSIZ)) - extra_size = 0; - } else { - /* Size of get arguments */ - extra_size = get_priv_size(descr->get_args); - - /* Does it fits in iwr ? */ - if((descr->get_args & IW_PRIV_SIZE_FIXED) && - (extra_size <= IFNAMSIZ)) - extra_size = 0; - } - } - - /* Prepare the call */ - info.cmd = cmd; - info.flags = 0; - - /* Check if we have a pointer to user space data or not. */ - if(extra_size == 0) { - /* No extra arguments. Trivial to handle */ - ret = handler(dev, &info, &(iwr->u), (char *) &(iwr->u)); - } else { - char * extra; - int err; - - /* Check what user space is giving us */ - if(IW_IS_SET(cmd)) { - /* Check NULL pointer */ - if((iwr->u.data.pointer == NULL) && - (iwr->u.data.length != 0)) - return -EFAULT; - - /* Does it fits within bounds ? */ - if(iwr->u.data.length > (descr->set_args & - IW_PRIV_SIZE_MASK)) - return -E2BIG; - } else { - /* Check NULL pointer */ - if(iwr->u.data.pointer == NULL) - return -EFAULT; - } - -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Malloc %d bytes\n", - dev->name, extra_size); -#endif /* WE_IOCTL_DEBUG */ - - /* Always allocate for max space. Easier, and won't last - * long... */ - extra = kmalloc(extra_size, GFP_KERNEL); - if (extra == NULL) { - return -ENOMEM; - } - - /* If it is a SET, get all the extra data in here */ - if(IW_IS_SET(cmd) && (iwr->u.data.length != 0)) { - err = copy_from_user(extra, iwr->u.data.pointer, - extra_size); - if (err) { - kfree(extra); - return -EFAULT; - } -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Got %d elem\n", - dev->name, iwr->u.data.length); -#endif /* WE_IOCTL_DEBUG */ - } - - /* Call the handler */ - ret = handler(dev, &info, &(iwr->u), extra); - - /* If we have something to return to the user */ - if (!ret && IW_IS_GET(cmd)) { - - /* Adjust for the actual length if it's variable, - * avoid leaking kernel bits outside. */ - if (!(descr->get_args & IW_PRIV_SIZE_FIXED)) { - extra_size = adjust_priv_size(descr->get_args, - &(iwr->u)); - } - - err = copy_to_user(iwr->u.data.pointer, extra, - extra_size); - if (err) - ret = -EFAULT; -#ifdef WE_IOCTL_DEBUG - printk(KERN_DEBUG "%s (WE) : Wrote %d elem\n", - dev->name, iwr->u.data.length); -#endif /* WE_IOCTL_DEBUG */ - } - - /* Cleanup - I told you it wasn't that long ;-) */ - kfree(extra); - } - - - /* Call commit handler if needed and defined */ - if(ret == -EIWCOMMIT) - ret = call_commit_handler(dev); - - return ret; -} - -/* ---------------------------------------------------------------- */ -/* - * Main IOCTl dispatcher. Called from the main networking code - * (dev_ioctl() in net/core/dev.c). - * Check the type of IOCTL and call the appropriate wrapper... - */ -int wireless_process_ioctl(struct ifreq *ifr, unsigned int cmd) -{ - struct net_device *dev; - iw_handler handler; - - /* Permissions are already checked in dev_ioctl() before calling us. - * The copy_to/from_user() of ifr is also dealt with in there */ - - /* Make sure the device exist */ - if ((dev = __dev_get_by_name(ifr->ifr_name)) == NULL) - return -ENODEV; - - /* A bunch of special cases, then the generic case... - * Note that 'cmd' is already filtered in dev_ioctl() with - * (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) */ - switch(cmd) - { - case SIOCGIWSTATS: - /* Get Wireless Stats */ - return dev_iwstats(dev, ifr); - - case SIOCGIWPRIV: - /* Check if we have some wireless handlers defined */ - if(dev->wireless_handlers != NULL) { - /* We export to user space the definition of - * the private handler ourselves */ - return ioctl_export_private(dev, ifr); - } - // ## Fall-through for old API ## - default: - /* Generic IOCTL */ - /* Basic check */ - if (!netif_device_present(dev)) - return -ENODEV; - /* New driver API : try to find the handler */ - handler = get_handler(dev, cmd); - if(handler != NULL) { - /* Standard and private are not the same */ - if(cmd < SIOCIWFIRSTPRIV) - return ioctl_standard_call(dev, - ifr, - cmd, - handler); - else - return ioctl_private_call(dev, - ifr, - cmd, - handler); - } - /* Old driver API : call driver ioctl handler */ - if (dev->do_ioctl) { - return dev->do_ioctl(dev, ifr, cmd); - } - return -EOPNOTSUPP; - } - /* Not reached */ - return -EINVAL; -} - -/************************* EVENT PROCESSING *************************/ -/* - * Process events generated by the wireless layer or the driver. - * Most often, the event will be propagated through rtnetlink - */ - -#ifdef WE_EVENT_NETLINK -/* "rtnl" is defined in net/core/rtnetlink.c, but we need it here. - * It is declared in <linux/rtnetlink.h> */ - -/* ---------------------------------------------------------------- */ -/* - * Fill a rtnetlink message with our event data. - * Note that we propage only the specified event and don't dump the - * current wireless config. Dumping the wireless config is far too - * expensive (for each parameter, the driver need to query the hardware). - */ -static inline int rtnetlink_fill_iwinfo(struct sk_buff * skb, - struct net_device * dev, - int type, - char * event, - int event_len) -{ - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(*r)); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev->flags; - r->ifi_change = 0; /* Wireless changes don't affect those flags */ - - /* Add the wireless events in the netlink packet */ - RTA_PUT(skb, IFLA_WIRELESS, - event_len, event); - - nlh->nlmsg_len = skb->tail - b; - return skb->len; - -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; -} - -/* ---------------------------------------------------------------- */ -/* - * Create and broadcast and send it on the standard rtnetlink socket - * This is a pure clone rtmsg_ifinfo() in net/core/rtnetlink.c - * Andrzej Krzysztofowicz mandated that I used a IFLA_XXX field - * within a RTM_NEWLINK event. - */ -static inline void rtmsg_iwinfo(struct net_device * dev, - char * event, - int event_len) -{ - struct sk_buff *skb; - int size = NLMSG_GOODSIZE; - - skb = alloc_skb(size, GFP_ATOMIC); - if (!skb) - return; - - if (rtnetlink_fill_iwinfo(skb, dev, RTM_NEWLINK, - event, event_len) < 0) { - kfree_skb(skb); - return; - } - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_ATOMIC); -} -#endif /* WE_EVENT_NETLINK */ - -/* ---------------------------------------------------------------- */ -/* - * Main event dispatcher. Called from other parts and drivers. - * Send the event on the appropriate channels. - * May be called from interrupt context. - */ -void wireless_send_event(struct net_device * dev, - unsigned int cmd, - union iwreq_data * wrqu, - char * extra) -{ - const struct iw_ioctl_description * descr = NULL; - int extra_len = 0; - struct iw_event *event; /* Mallocated whole event */ - int event_len; /* Its size */ - int hdr_len; /* Size of the event header */ - int wrqu_off = 0; /* Offset in wrqu */ - /* Don't "optimise" the following variable, it will crash */ - unsigned cmd_index; /* *MUST* be unsigned */ - - /* Get the description of the Event */ - if(cmd <= SIOCIWLAST) { - cmd_index = cmd - SIOCIWFIRST; - if(cmd_index < standard_ioctl_num) - descr = &(standard_ioctl[cmd_index]); - } else { - cmd_index = cmd - IWEVFIRST; - if(cmd_index < standard_event_num) - descr = &(standard_event[cmd_index]); - } - /* Don't accept unknown events */ - if(descr == NULL) { - /* Note : we don't return an error to the driver, because - * the driver would not know what to do about it. It can't - * return an error to the user, because the event is not - * initiated by a user request. - * The best the driver could do is to log an error message. - * We will do it ourselves instead... - */ - printk(KERN_ERR "%s (WE) : Invalid/Unknown Wireless Event (0x%04X)\n", - dev->name, cmd); - return; - } -#ifdef WE_EVENT_DEBUG - printk(KERN_DEBUG "%s (WE) : Got event 0x%04X\n", - dev->name, cmd); - printk(KERN_DEBUG "%s (WE) : Header type : %d, Token type : %d, size : %d, token : %d\n", dev->name, descr->header_type, descr->token_type, descr->token_size, descr->max_tokens); -#endif /* WE_EVENT_DEBUG */ - - /* Check extra parameters and set extra_len */ - if(descr->header_type == IW_HEADER_TYPE_POINT) { - /* Check if number of token fits within bounds */ - if(wrqu->data.length > descr->max_tokens) { - printk(KERN_ERR "%s (WE) : Wireless Event too big (%d)\n", dev->name, wrqu->data.length); - return; - } - if(wrqu->data.length < descr->min_tokens) { - printk(KERN_ERR "%s (WE) : Wireless Event too small (%d)\n", dev->name, wrqu->data.length); - return; - } - /* Calculate extra_len - extra is NULL for restricted events */ - if(extra != NULL) - extra_len = wrqu->data.length * descr->token_size; - /* Always at an offset in wrqu */ - wrqu_off = IW_EV_POINT_OFF; -#ifdef WE_EVENT_DEBUG - printk(KERN_DEBUG "%s (WE) : Event 0x%04X, tokens %d, extra_len %d\n", dev->name, cmd, wrqu->data.length, extra_len); -#endif /* WE_EVENT_DEBUG */ - } - - /* Total length of the event */ - hdr_len = event_type_size[descr->header_type]; - event_len = hdr_len + extra_len; - -#ifdef WE_EVENT_DEBUG - printk(KERN_DEBUG "%s (WE) : Event 0x%04X, hdr_len %d, wrqu_off %d, event_len %d\n", dev->name, cmd, hdr_len, wrqu_off, event_len); -#endif /* WE_EVENT_DEBUG */ - - /* Create temporary buffer to hold the event */ - event = kmalloc(event_len, GFP_ATOMIC); - if(event == NULL) - return; - - /* Fill event */ - event->len = event_len; - event->cmd = cmd; - memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); - if(extra != NULL) - memcpy(((char *) event) + hdr_len, extra, extra_len); - -#ifdef WE_EVENT_NETLINK - /* rtnetlink event channel */ - rtmsg_iwinfo(dev, (char *) event, event_len); -#endif /* WE_EVENT_NETLINK */ - - /* Cleanup */ - kfree(event); - - return; /* Always success, I guess ;-) */ -} - -/********************** ENHANCED IWSPY SUPPORT **********************/ -/* - * In the old days, the driver was handling spy support all by itself. - * Now, the driver can delegate this task to Wireless Extensions. - * It needs to use those standard spy iw_handler in struct iw_handler_def, - * push data to us via wireless_spy_update() and include struct iw_spy_data - * in its private part (and export it in net_device->wireless_data->spy_data). - * One of the main advantage of centralising spy support here is that - * it becomes much easier to improve and extend it without having to touch - * the drivers. One example is the addition of the Spy-Threshold events. - */ - -/* ---------------------------------------------------------------- */ -/* - * Return the pointer to the spy data in the driver. - * Because this is called on the Rx path via wireless_spy_update(), - * we want it to be efficient... - */ -static inline struct iw_spy_data * get_spydata(struct net_device *dev) -{ - /* This is the new way */ - if(dev->wireless_data) - return(dev->wireless_data->spy_data); - return NULL; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : set Spy List - */ -int iw_handler_set_spy(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct sockaddr * address = (struct sockaddr *) extra; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - /* Disable spy collection while we copy the addresses. - * While we copy addresses, any call to wireless_spy_update() - * will NOP. This is OK, as anyway the addresses are changing. */ - spydata->spy_number = 0; - - /* We want to operate without locking, because wireless_spy_update() - * most likely will happen in the interrupt handler, and therefore - * have its own locking constraints and needs performance. - * The rtnl_lock() make sure we don't race with the other iw_handlers. - * This make sure wireless_spy_update() "see" that the spy list - * is temporarily disabled. */ - wmb(); - - /* Are there are addresses to copy? */ - if(wrqu->data.length > 0) { - int i; - - /* Copy addresses */ - for(i = 0; i < wrqu->data.length; i++) - memcpy(spydata->spy_address[i], address[i].sa_data, - ETH_ALEN); - /* Reset stats */ - memset(spydata->spy_stat, 0, - sizeof(struct iw_quality) * IW_MAX_SPY); - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "iw_handler_set_spy() : wireless_data %p, spydata %p, num %d\n", dev->wireless_data, spydata, wrqu->data.length); - for (i = 0; i < wrqu->data.length; i++) - printk(KERN_DEBUG - "%02X:%02X:%02X:%02X:%02X:%02X \n", - spydata->spy_address[i][0], - spydata->spy_address[i][1], - spydata->spy_address[i][2], - spydata->spy_address[i][3], - spydata->spy_address[i][4], - spydata->spy_address[i][5]); -#endif /* WE_SPY_DEBUG */ - } - - /* Make sure above is updated before re-enabling */ - wmb(); - - /* Enable addresses */ - spydata->spy_number = wrqu->data.length; - - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : get Spy List - */ -int iw_handler_get_spy(struct net_device * dev, - struct iw_request_info * info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct sockaddr * address = (struct sockaddr *) extra; - int i; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - wrqu->data.length = spydata->spy_number; - - /* Copy addresses. */ - for(i = 0; i < spydata->spy_number; i++) { - memcpy(address[i].sa_data, spydata->spy_address[i], ETH_ALEN); - address[i].sa_family = AF_UNIX; - } - /* Copy stats to the user buffer (just after). */ - if(spydata->spy_number > 0) - memcpy(extra + (sizeof(struct sockaddr) *spydata->spy_number), - spydata->spy_stat, - sizeof(struct iw_quality) * spydata->spy_number); - /* Reset updated flags. */ - for(i = 0; i < spydata->spy_number; i++) - spydata->spy_stat[i].updated &= ~IW_QUAL_ALL_UPDATED; - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : set spy threshold - */ -int iw_handler_set_thrspy(struct net_device * dev, - struct iw_request_info *info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct iw_thrspy * threshold = (struct iw_thrspy *) extra; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - /* Just do it */ - memcpy(&(spydata->spy_thr_low), &(threshold->low), - 2 * sizeof(struct iw_quality)); - - /* Clear flag */ - memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "iw_handler_set_thrspy() : low %d ; high %d\n", spydata->spy_thr_low.level, spydata->spy_thr_high.level); -#endif /* WE_SPY_DEBUG */ - - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Standard Wireless Handler : get spy threshold - */ -int iw_handler_get_thrspy(struct net_device * dev, - struct iw_request_info *info, - union iwreq_data * wrqu, - char * extra) -{ - struct iw_spy_data * spydata = get_spydata(dev); - struct iw_thrspy * threshold = (struct iw_thrspy *) extra; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return -EOPNOTSUPP; - - /* Just do it */ - memcpy(&(threshold->low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); - - return 0; -} - -/*------------------------------------------------------------------*/ -/* - * Prepare and send a Spy Threshold event - */ -static void iw_send_thrspy_event(struct net_device * dev, - struct iw_spy_data * spydata, - unsigned char * address, - struct iw_quality * wstats) -{ - union iwreq_data wrqu; - struct iw_thrspy threshold; - - /* Init */ - wrqu.data.length = 1; - wrqu.data.flags = 0; - /* Copy address */ - memcpy(threshold.addr.sa_data, address, ETH_ALEN); - threshold.addr.sa_family = ARPHRD_ETHER; - /* Copy stats */ - memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); - /* Copy also thresholds */ - memcpy(&(threshold.low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "iw_send_thrspy_event() : address %02X:%02X:%02X:%02X:%02X:%02X, level %d, up = %d\n", - threshold.addr.sa_data[0], - threshold.addr.sa_data[1], - threshold.addr.sa_data[2], - threshold.addr.sa_data[3], - threshold.addr.sa_data[4], - threshold.addr.sa_data[5], threshold.qual.level); -#endif /* WE_SPY_DEBUG */ - - /* Send event to user space */ - wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); -} - -/* ---------------------------------------------------------------- */ -/* - * Call for the driver to update the spy data. - * For now, the spy data is a simple array. As the size of the array is - * small, this is good enough. If we wanted to support larger number of - * spy addresses, we should use something more efficient... - */ -void wireless_spy_update(struct net_device * dev, - unsigned char * address, - struct iw_quality * wstats) -{ - struct iw_spy_data * spydata = get_spydata(dev); - int i; - int match = -1; - - /* Make sure driver is not buggy or using the old API */ - if(!spydata) - return; - -#ifdef WE_SPY_DEBUG - printk(KERN_DEBUG "wireless_spy_update() : wireless_data %p, spydata %p, address %02X:%02X:%02X:%02X:%02X:%02X\n", dev->wireless_data, spydata, address[0], address[1], address[2], address[3], address[4], address[5]); -#endif /* WE_SPY_DEBUG */ - - /* Update all records that match */ - for(i = 0; i < spydata->spy_number; i++) - if(!compare_ether_addr(address, spydata->spy_address[i])) { - memcpy(&(spydata->spy_stat[i]), wstats, - sizeof(struct iw_quality)); - match = i; - } - - /* Generate an event if we cross the spy threshold. - * To avoid event storms, we have a simple hysteresis : we generate - * event only when we go under the low threshold or above the - * high threshold. */ - if(match >= 0) { - if(spydata->spy_thr_under[match]) { - if(wstats->level > spydata->spy_thr_high.level) { - spydata->spy_thr_under[match] = 0; - iw_send_thrspy_event(dev, spydata, - address, wstats); - } - } else { - if(wstats->level < spydata->spy_thr_low.level) { - spydata->spy_thr_under[match] = 1; - iw_send_thrspy_event(dev, spydata, - address, wstats); - } - } - } -} - -EXPORT_SYMBOL(iw_handler_get_spy); -EXPORT_SYMBOL(iw_handler_get_thrspy); -EXPORT_SYMBOL(iw_handler_set_spy); -EXPORT_SYMBOL(iw_handler_set_thrspy); -EXPORT_SYMBOL(wireless_send_event); -EXPORT_SYMBOL(wireless_spy_update); |