diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt deleted file mode 100644 index 54f10478e8e3..000000000000 --- a/Documentation/networking/netlink_mmap.txt +++ /dev/null @@ -1,332 +0,0 @@ -This file documents how to use memory mapped I/O with netlink. - -Author: Patrick McHardy - -Overview --------- - -Memory mapped netlink I/O can be used to increase throughput and decrease -overhead of unicast receive and transmit operations. Some netlink subsystems -require high throughput, these are mainly the netfilter subsystems -nfnetlink_queue and nfnetlink_log, but it can also help speed up large -dump operations of f.i. the routing database. - -Memory mapped netlink I/O used two circular ring buffers for RX and TX which -are mapped into the processes address space. - -The RX ring is used by the kernel to directly construct netlink messages into -user-space memory without copying them as done with regular socket I/O, -additionally as long as the ring contains messages no recvmsg() or poll() -syscalls have to be issued by user-space to get more message. - -The TX ring is used to process messages directly from user-space memory, the -kernel processes all messages contained in the ring using a single sendmsg() -call. - -Usage overview --------------- - -In order to use memory mapped netlink I/O, user-space needs three main changes: - -- ring setup -- conversion of the RX path to get messages from the ring instead of recvmsg() -- conversion of the TX path to construct messages into the ring - -Ring setup is done using setsockopt() to provide the ring parameters to the -kernel, then a call to mmap() to map the ring into the processes address space: - -- setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, ¶ms, sizeof(params)); -- setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, ¶ms, sizeof(params)); -- ring = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0) - -Usage of either ring is optional, but even if only the RX ring is used the -mapping still needs to be writable in order to update the frame status after -processing. - -Conversion of the reception path involves calling poll() on the file -descriptor, once the socket is readable the frames from the ring are -processed in order until no more messages are available, as indicated by -a status word in the frame header. - -On kernel side, in order to make use of memory mapped I/O on receive, the -originating netlink subsystem needs to support memory mapped I/O, otherwise -it will use an allocated socket buffer as usual and the contents will be - copied to the ring on transmission, nullifying most of the performance gains. -Dumps of kernel databases automatically support memory mapped I/O. - -Conversion of the transmit path involves changing message construction to -use memory from the TX ring instead of (usually) a buffer declared on the -stack and setting up the frame header appropriately. Optionally poll() can -be used to wait for free frames in the TX ring. - -Structured and definitions for using memory mapped I/O are contained in -. - -RX and TX rings ----------------- - -Each ring contains a number of continuous memory blocks, containing frames of -fixed size dependent on the parameters used for ring setup. - -Ring: [ block 0 ] - [ frame 0 ] - [ frame 1 ] - [ block 1 ] - [ frame 2 ] - [ frame 3 ] - ... - [ block n ] - [ frame 2 * n ] - [ frame 2 * n + 1 ] - -The blocks are only visible to the kernel, from the point of view of user-space -the ring just contains the frames in a continuous memory zone. - -The ring parameters used for setting up the ring are defined as follows: - -struct nl_mmap_req { - unsigned int nm_block_size; - unsigned int nm_block_nr; - unsigned int nm_frame_size; - unsigned int nm_frame_nr; -}; - -Frames are grouped into blocks, where each block is a continuous region of memory -and holds nm_block_size / nm_frame_size frames. The total number of frames in -the ring is nm_frame_nr. The following invariants hold: - -- frames_per_block = nm_block_size / nm_frame_size - -- nm_frame_nr = frames_per_block * nm_block_nr - -Some parameters are constrained, specifically: - -- nm_block_size must be a multiple of the architectures memory page size. - The getpagesize() function can be used to get the page size. - -- nm_frame_size must be equal or larger to NL_MMAP_HDRLEN, IOW a frame must be - able to hold at least the frame header - -- nm_frame_size must be smaller or equal to nm_block_size - -- nm_frame_size must be a multiple of NL_MMAP_MSG_ALIGNMENT - -- nm_frame_nr must equal the actual number of frames as specified above. - -When the kernel can't allocate physically continuous memory for a ring block, -it will fall back to use physically discontinuous memory. This might affect -performance negatively, in order to avoid this the nm_frame_size parameter -should be chosen to be as small as possible for the required frame size and -the number of blocks should be increased instead. - -Ring frames ------------- - -Each frames contain a frame header, consisting of a synchronization word and some -meta-data, and the message itself. - -Frame: [ header message ] - -The frame header is defined as follows: - -struct nl_mmap_hdr { - unsigned int nm_status; - unsigned int nm_len; - __u32 nm_group; - /* credentials */ - __u32 nm_pid; - __u32 nm_uid; - __u32 nm_gid; -}; - -- nm_status is used for synchronizing processing between the kernel and user- - space and specifies ownership of the frame as well as the operation to perform - -- nm_len contains the length of the message contained in the data area - -- nm_group specified the destination multicast group of message - -- nm_pid, nm_uid and nm_gid contain the netlink pid, UID and GID of the sending - process. These values correspond to the data available using SOCK_PASSCRED in - the SCM_CREDENTIALS cmsg. - -The possible values in the status word are: - -- NL_MMAP_STATUS_UNUSED: - RX ring: frame belongs to the kernel and contains no message - for user-space. Approriate action is to invoke poll() - to wait for new messages. - - TX ring: frame belongs to user-space and can be used for - message construction. - -- NL_MMAP_STATUS_RESERVED: - RX ring only: frame is currently used by the kernel for message - construction and contains no valid message yet. - Appropriate action is to invoke poll() to wait for - new messages. - -- NL_MMAP_STATUS_VALID: - RX ring: frame contains a valid message. Approriate action is - to process the message and release the frame back to - the kernel by setting the status to - NL_MMAP_STATUS_UNUSED or queue the frame by setting the - status to NL_MMAP_STATUS_SKIP. - - TX ring: the frame contains a valid message from user-space to - be processed by the kernel. After completing processing - the kernel will release the frame back to user-space by - setting the status to NL_MMAP_STATUS_UNUSED. - -- NL_MMAP_STATUS_COPY: - RX ring only: a message is ready to be processed but could not be - stored in the ring, either because it exceeded the - frame size or because the originating subsystem does - not support memory mapped I/O. Appropriate action is - to invoke recvmsg() to receive the message and release - the frame back to the kernel by setting the status to - NL_MMAP_STATUS_UNUSED. - -- NL_MMAP_STATUS_SKIP: - RX ring only: user-space queued the message for later processing, but - processed some messages following it in the ring. The - kernel should skip this frame when looking for unused - frames. - -The data area of a frame begins at a offset of NL_MMAP_HDRLEN relative to the -frame header. - -TX limitations --------------- - -As of Jan 2015 the message is always copied from the ring frame to an -allocated buffer due to unresolved security concerns. -See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX."). - -Example -------- - -Ring setup: - - unsigned int block_size = 16 * getpagesize(); - struct nl_mmap_req req = { - .nm_block_size = block_size, - .nm_block_nr = 64, - .nm_frame_size = 16384, - .nm_frame_nr = 64 * block_size / 16384, - }; - unsigned int ring_size; - void *rx_ring, *tx_ring; - - /* Configure ring parameters */ - if (setsockopt(fd, SOL_NETLINK, NETLINK_RX_RING, &req, sizeof(req)) < 0) - exit(1); - if (setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &req, sizeof(req)) < 0) - exit(1) - - /* Calculate size of each individual ring */ - ring_size = req.nm_block_nr * req.nm_block_size; - - /* Map RX/TX rings. The TX ring is located after the RX ring */ - rx_ring = mmap(NULL, 2 * ring_size, PROT_READ | PROT_WRITE, - MAP_SHARED, fd, 0); - if ((long)rx_ring == -1L) - exit(1); - tx_ring = rx_ring + ring_size: - -Message reception: - -This example assumes some ring parameters of the ring setup are available. - - unsigned int frame_offset = 0; - struct nl_mmap_hdr *hdr; - struct nlmsghdr *nlh; - unsigned char buf[16384]; - ssize_t len; - - while (1) { - struct pollfd pfds[1]; - - pfds[0].fd = fd; - pfds[0].events = POLLIN | POLLERR; - pfds[0].revents = 0; - - if (poll(pfds, 1, -1) < 0 && errno != -EINTR) - exit(1); - - /* Check for errors. Error handling omitted */ - if (pfds[0].revents & POLLERR) - - - /* If no new messages, poll again */ - if (!(pfds[0].revents & POLLIN)) - continue; - - /* Process all frames */ - while (1) { - /* Get next frame header */ - hdr = rx_ring + frame_offset; - - if (hdr->nm_status == NL_MMAP_STATUS_VALID) { - /* Regular memory mapped frame */ - nlh = (void *)hdr + NL_MMAP_HDRLEN; - len = hdr->nm_len; - - /* Release empty message immediately. May happen - * on error during message construction. - */ - if (len == 0) - goto release; - } else if (hdr->nm_status == NL_MMAP_STATUS_COPY) { - /* Frame queued to socket receive queue */ - len = recv(fd, buf, sizeof(buf), MSG_DONTWAIT); - if (len <= 0) - break; - nlh = buf; - } else - /* No more messages to process, continue polling */ - break; - - process_msg(nlh); -release: - /* Release frame back to the kernel */ - hdr->nm_status = NL_MMAP_STATUS_UNUSED; - - /* Advance frame offset to next frame */ - frame_offset = (frame_offset + frame_size) % ring_size; - } - } - -Message transmission: - -This example assumes some ring parameters of the ring setup are available. -A single message is constructed and transmitted, to send multiple messages -at once they would be constructed in consecutive frames before a final call -to sendto(). - - unsigned int frame_offset = 0; - struct nl_mmap_hdr *hdr; - struct nlmsghdr *nlh; - struct sockaddr_nl addr = { - .nl_family = AF_NETLINK, - }; - - hdr = tx_ring + frame_offset; - if (hdr->nm_status != NL_MMAP_STATUS_UNUSED) - /* No frame available. Use poll() to avoid. */ - exit(1); - - nlh = (void *)hdr + NL_MMAP_HDRLEN; - - /* Build message */ - build_message(nlh); - - /* Fill frame header: length and status need to be set */ - hdr->nm_len = nlh->nlmsg_len; - hdr->nm_status = NL_MMAP_STATUS_VALID; - - if (sendto(fd, NULL, 0, 0, &addr, sizeof(addr)) < 0) - exit(1); - - /* Advance frame offset to next frame */ - frame_offset = (frame_offset + frame_size) % ring_size; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f095155d8749..0dba4e4ed2be 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -107,8 +107,10 @@ struct nlmsgerr { #define NETLINK_PKTINFO 3 #define NETLINK_BROADCAST_ERROR 4 #define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ #define NETLINK_RX_RING 6 #define NETLINK_TX_RING 7 +#endif #define NETLINK_LISTEN_ALL_NSID 8 #define NETLINK_LIST_MEMBERSHIPS 9 #define NETLINK_CAP_ACK 10 @@ -134,6 +136,7 @@ struct nl_mmap_hdr { __u32 nm_gid; }; +#ifndef __KERNEL__ enum nl_mmap_status { NL_MMAP_STATUS_UNUSED, NL_MMAP_STATUS_RESERVED, @@ -145,6 +148,7 @@ enum nl_mmap_status { #define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO #define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) #define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif #define NET_MAJOR 36 /* Major 36 is reserved for networking */ diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index f2159d30d1f5..d79399394b46 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -48,6 +48,8 @@ enum { #define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */ #define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */ +#ifndef __KERNEL__ #define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */ +#endif #endif diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig index 2c5e95e9bfbd..5d6e8c05b3d4 100644 --- a/net/netlink/Kconfig +++ b/net/netlink/Kconfig @@ -2,15 +2,6 @@ # Netlink Sockets # -config NETLINK_MMAP - bool "NETLINK: mmaped IO" - ---help--- - This option enables support for memory mapped netlink IO. This - reduces overhead by avoiding copying data between kernel- and - userspace. - - If unsure, say N. - config NETLINK_DIAG tristate "NETLINK: socket monitoring interface" default n diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f1ffb34e253f..85aa6ef86dfd 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -225,7 +225,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, dev_hold(dev); - if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head)) + if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); @@ -300,610 +300,8 @@ static void netlink_rcv_wake(struct sock *sk) wake_up_interruptible(&nlk->wait); } -#ifdef CONFIG_NETLINK_MMAP -static bool netlink_rx_is_mmaped(struct sock *sk) -{ - return nlk_sk(sk)->rx_ring.pg_vec != NULL; -} - -static bool netlink_tx_is_mmaped(struct sock *sk) -{ - return nlk_sk(sk)->tx_ring.pg_vec != NULL; -} - -static __pure struct page *pgvec_to_page(const void *addr) -{ - if (is_vmalloc_addr(addr)) - return vmalloc_to_page(addr); - else - return virt_to_page(addr); -} - -static void free_pg_vec(void **pg_vec, unsigned int order, unsigned int len) -{ - unsigned int i; - - for (i = 0; i < len; i++) { - if (pg_vec[i] != NULL) { - if (is_vmalloc_addr(pg_vec[i])) - vfree(pg_vec[i]); - else - free_pages((unsigned long)pg_vec[i], order); - } - } - kfree(pg_vec); -} - -static void *alloc_one_pg_vec_page(unsigned long order) -{ - void *buffer; - gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | - __GFP_NOWARN | __GFP_NORETRY; - - buffer = (void *)__get_free_pages(gfp_flags, order); - if (buffer != NULL) - return buffer; - - buffer = vzalloc((1 << order) * PAGE_SIZE); - if (buffer != NULL) - return buffer; - - gfp_flags &= ~__GFP_NORETRY; - return (void *)__get_free_pages(gfp_flags, order); -} - -static void **alloc_pg_vec(struct netlink_sock *nlk, - struct nl_mmap_req *req, unsigned int order) -{ - unsigned int block_nr = req->nm_block_nr; - unsigned int i; - void **pg_vec; - - pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL); - if (pg_vec == NULL) - return NULL; - - for (i = 0; i < block_nr; i++) { - pg_vec[i] = alloc_one_pg_vec_page(order); - if (pg_vec[i] == NULL) - goto err1; - } - - return pg_vec; -err1: - free_pg_vec(pg_vec, order, block_nr); - return NULL; -} - - -static void -__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec, - unsigned int order) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct sk_buff_head *queue; - struct netlink_ring *ring; - - queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; - ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring; - - spin_lock_bh(&queue->lock); - - ring->frame_max = req->nm_frame_nr - 1; - ring->head = 0; - ring->frame_size = req->nm_frame_size; - ring->pg_vec_pages = req->nm_block_size / PAGE_SIZE; - - swap(ring->pg_vec_len, req->nm_block_nr); - swap(ring->pg_vec_order, order); - swap(ring->pg_vec, pg_vec); - - __skb_queue_purge(queue); - spin_unlock_bh(&queue->lock); - - WARN_ON(atomic_read(&nlk->mapped)); - - if (pg_vec) - free_pg_vec(pg_vec, order, req->nm_block_nr); -} - -static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, - bool tx_ring) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring; - void **pg_vec = NULL; - unsigned int order = 0; - - ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring; - - if (atomic_read(&nlk->mapped)) - return -EBUSY; - if (atomic_read(&ring->pending)) - return -EBUSY; - - if (req->nm_block_nr) { - if (ring->pg_vec != NULL) - return -EBUSY; - - if ((int)req->nm_block_size <= 0) - return -EINVAL; - if (!PAGE_ALIGNED(req->nm_block_size)) - return -EINVAL; - if (req->nm_frame_size < NL_MMAP_HDRLEN) - return -EINVAL; - if (!IS_ALIGNED(req->nm_frame_size, NL_MMAP_MSG_ALIGNMENT)) - return -EINVAL; - - ring->frames_per_block = req->nm_block_size / - req->nm_frame_size; - if (ring->frames_per_block == 0) - return -EINVAL; - if (ring->frames_per_block * req->nm_block_nr != - req->nm_frame_nr) - return -EINVAL; - - order = get_order(req->nm_block_size); - pg_vec = alloc_pg_vec(nlk, req, order); - if (pg_vec == NULL) - return -ENOMEM; - } else { - if (req->nm_frame_nr) - return -EINVAL; - } - - mutex_lock(&nlk->pg_vec_lock); - if (atomic_read(&nlk->mapped) == 0) { - __netlink_set_ring(sk, req, tx_ring, pg_vec, order); - mutex_unlock(&nlk->pg_vec_lock); - return 0; - } - - mutex_unlock(&nlk->pg_vec_lock); - - if (pg_vec) - free_pg_vec(pg_vec, order, req->nm_block_nr); - - return -EBUSY; -} - -static void netlink_mm_open(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct socket *sock = file->private_data; - struct sock *sk = sock->sk; - - if (sk) - atomic_inc(&nlk_sk(sk)->mapped); -} - -static void netlink_mm_close(struct vm_area_struct *vma) -{ - struct file *file = vma->vm_file; - struct socket *sock = file->private_data; - struct sock *sk = sock->sk; - - if (sk) - atomic_dec(&nlk_sk(sk)->mapped); -} - -static const struct vm_operations_struct netlink_mmap_ops = { - .open = netlink_mm_open, - .close = netlink_mm_close, -}; - -static int netlink_mmap(struct file *file, struct socket *sock, - struct vm_area_struct *vma) -{ - struct sock *sk = sock->sk; - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring; - unsigned long start, size, expected; - unsigned int i; - int err = -EINVAL; - - if (vma->vm_pgoff) - return -EINVAL; - - mutex_lock(&nlk->pg_vec_lock); - - expected = 0; - for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) { - if (ring->pg_vec == NULL) - continue; - expected += ring->pg_vec_len * ring->pg_vec_pages * PAGE_SIZE; - } - - if (expected == 0) - goto out; - - size = vma->vm_end - vma->vm_start; - if (size != expected) - goto out; - - start = vma->vm_start; - for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) { - if (ring->pg_vec == NULL) - continue; - - for (i = 0; i < ring->pg_vec_len; i++) { - struct page *page; - void *kaddr = ring->pg_vec[i]; - unsigned int pg_num; - - for (pg_num = 0; pg_num < ring->pg_vec_pages; pg_num++) { - page = pgvec_to_page(kaddr); - err = vm_insert_page(vma, start, page); - if (err < 0) - goto out; - start += PAGE_SIZE; - kaddr += PAGE_SIZE; - } - } - } - - atomic_inc(&nlk->mapped); - vma->vm_ops = &netlink_mmap_ops; - err = 0; -out: - mutex_unlock(&nlk->pg_vec_lock); - return err; -} - -static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len) -{ -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 - struct page *p_start, *p_end; - - /* First page is flushed through netlink_{get,set}_status */ - p_start = pgvec_to_page(hdr + PAGE_SIZE); - p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1); - while (p_start <= p_end) { - flush_dcache_page(p_start); - p_start++; - } -#endif -} - -static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr) -{ - smp_rmb(); - flush_dcache_page(pgvec_to_page(hdr)); - return hdr->nm_status; -} - -static void netlink_set_status(struct nl_mmap_hdr *hdr, - enum nl_mmap_status status) -{ - smp_mb(); - hdr->nm_status = status; - flush_dcache_page(pgvec_to_page(hdr)); -} - -static struct nl_mmap_hdr * -__netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos) -{ - unsigned int pg_vec_pos, frame_off; - - pg_vec_pos = pos / ring->frames_per_block; - frame_off = pos % ring->frames_per_block; - - return ring->pg_vec[pg_vec_pos] + (frame_off * ring->frame_size); -} - -static struct nl_mmap_hdr * -netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos, - enum nl_mmap_status status) -{ - struct nl_mmap_hdr *hdr; - - hdr = __netlink_lookup_frame(ring, pos); - if (netlink_get_status(hdr) != status) - return NULL; - - return hdr; -} - -static struct nl_mmap_hdr * -netlink_current_frame(const struct netlink_ring *ring, - enum nl_mmap_status status) -{ - return netlink_lookup_frame(ring, ring->head, status); -} - -static void netlink_increment_head(struct netlink_ring *ring) -{ - ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0; -} - -static void netlink_forward_ring(struct netlink_ring *ring) -{ - unsigned int head = ring->head; - const struct nl_mmap_hdr *hdr; - - do { - hdr = __netlink_lookup_frame(ring, ring->head); - if (hdr->nm_status == NL_MMAP_STATUS_UNUSED) - break; - if (hdr->nm_status != NL_MMAP_STATUS_SKIP) - break; - netlink_increment_head(ring); - } while (ring->head != head); -} - -static bool netlink_has_valid_frame(struct netlink_ring *ring) -{ - unsigned int head = ring->head, pos = head; - const struct nl_mmap_hdr *hdr; - - do { - hdr = __netlink_lookup_frame(ring, pos); - if (hdr->nm_status == NL_MMAP_STATUS_VALID) - return true; - pos = pos != 0 ? pos - 1 : ring->frame_max; - } while (pos != head); - - return false; -} - -static bool netlink_dump_space(struct netlink_sock *nlk) -{ - struct netlink_ring *ring = &nlk->rx_ring; - struct nl_mmap_hdr *hdr; - unsigned int n; - - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); - if (hdr == NULL) - return false; - - n = ring->head + ring->frame_max / 2; - if (n > ring->frame_max) - n -= ring->frame_max; - - hdr = __netlink_lookup_frame(ring, n); - - return hdr->nm_status == NL_MMAP_STATUS_UNUSED; -} - -static unsigned int netlink_poll(struct file *file, struct socket *sock, - poll_table *wait) -{ - struct sock *sk = sock->sk; - struct netlink_sock *nlk = nlk_sk(sk); - unsigned int mask; - int err; - - if (nlk->rx_ring.pg_vec != NULL) { - /* Memory mapped sockets don't call recvmsg(), so flow control - * for dumps is performed here. A dump is allowed to continue - * if at least half the ring is unused. - */ - while (nlk->cb_running && netlink_dump_space(nlk)) { - err = netlink_dump(sk); - if (err < 0) { - sk->sk_err = -err; - sk->sk_error_report(sk); - break; - } - } - netlink_rcv_wake(sk); - } - - mask = datagram_poll(file, sock, wait); - - /* We could already have received frames in the normal receive - * queue, that will show up as NL_MMAP_STATUS_COPY in the ring, - * so if mask contains pollin/etc already, there's no point - * walking the ring. - */ - if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) { - spin_lock_bh(&sk->sk_receive_queue.lock); - if (nlk->rx_ring.pg_vec) { - if (netlink_has_valid_frame(&nlk->rx_ring)) - mask |= POLLIN | POLLRDNORM; - } - spin_unlock_bh(&sk->sk_receive_queue.lock); - } - - spin_lock_bh(&sk->sk_write_queue.lock); - if (nlk->tx_ring.pg_vec) { - if (netlink_current_frame(&nlk->tx_ring, NL_MMAP_STATUS_UNUSED)) - mask |= POLLOUT | POLLWRNORM; - } - spin_unlock_bh(&sk->sk_write_queue.lock); - - return mask; -} - -static struct nl_mmap_hdr *netlink_mmap_hdr(struct sk_buff *skb) -{ - return (struct nl_mmap_hdr *)(skb->head - NL_MMAP_HDRLEN); -} - -static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk, - struct netlink_ring *ring, - struct nl_mmap_hdr *hdr) -{ - unsigned int size; - void *data; - - size = ring->frame_size - NL_MMAP_HDRLEN; - data = (void *)hdr + NL_MMAP_HDRLEN; - - skb->head = data; - skb->data = data; - skb_reset_tail_pointer(skb); - skb->end = skb->tail + size; - skb->len = 0; - - skb->destructor = netlink_skb_destructor; - NETLINK_CB(skb).flags |= NETLINK_SKB_MMAPED; - NETLINK_CB(skb).sk = sk; -} - -static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg, - u32 dst_portid, u32 dst_group, - struct scm_cookie *scm) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring; - struct nl_mmap_hdr *hdr; - struct sk_buff *skb; - unsigned int maxlen; - int err = 0, len = 0; - - mutex_lock(&nlk->pg_vec_lock); - - ring = &nlk->tx_ring; - maxlen = ring->frame_size - NL_MMAP_HDRLEN; - - do { - unsigned int nm_len; - - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID); - if (hdr == NULL) { - if (!(msg->msg_flags & MSG_DONTWAIT) && - atomic_read(&nlk->tx_ring.pending)) - schedule(); - continue; - } - - nm_len = ACCESS_ONCE(hdr->nm_len); - if (nm_len > maxlen) { - err = -EINVAL; - goto out; - } - - netlink_frame_flush_dcache(hdr, nm_len); - - skb = alloc_skb(nm_len, GFP_KERNEL); - if (skb == NULL) { - err = -ENOBUFS; - goto out; - } - __skb_put(skb, nm_len); - memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); - - netlink_increment_head(ring); - - NETLINK_CB(skb).portid = nlk->portid; - NETLINK_CB(skb).dst_group = dst_group; - NETLINK_CB(skb).creds = scm->creds; - - err = security_netlink_send(sk, skb); - if (err) { - kfree_skb(skb); - goto out; - } - - if (unlikely(dst_group)) { - atomic_inc(&skb->users); - netlink_broadcast(sk, skb, dst_portid, dst_group, - GFP_KERNEL); - } - err = netlink_unicast(sk, skb, dst_portid, - msg->msg_flags & MSG_DONTWAIT); - if (err < 0) - goto out; - len += err; - - } while (hdr != NULL || - (!(msg->msg_flags & MSG_DONTWAIT) && - atomic_read(&nlk->tx_ring.pending))); - - if (len > 0) - err = len; -out: - mutex_unlock(&nlk->pg_vec_lock); - return err; -} - -static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb) -{ - struct nl_mmap_hdr *hdr; - - hdr = netlink_mmap_hdr(skb); - hdr->nm_len = skb->len; - hdr->nm_group = NETLINK_CB(skb).dst_group; - hdr->nm_pid = NETLINK_CB(skb).creds.pid; - hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); - hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); - netlink_frame_flush_dcache(hdr, hdr->nm_len); - netlink_set_status(hdr, NL_MMAP_STATUS_VALID); - - NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED; - kfree_skb(skb); -} - -static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb) -{ - struct netlink_sock *nlk = nlk_sk(sk); - struct netlink_ring *ring = &nlk->rx_ring; - struct nl_mmap_hdr *hdr; - - spin_lock_bh(&sk->sk_receive_queue.lock); - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); - if (hdr == NULL) { - spin_unlock_bh(&sk->sk_receive_queue.lock); - kfree_skb(skb); - netlink_overrun(sk); - return; - } - netlink_increment_head(ring); - __skb_queue_tail(&sk->sk_receive_queue, skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); - - hdr->nm_len = skb->len; - hdr->nm_group = NETLINK_CB(skb).dst_group; - hdr->nm_pid = NETLINK_CB(skb).creds.pid; - hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid); - hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid); - netlink_set_status(hdr, NL_MMAP_STATUS_COPY); -} - -#else /* CONFIG_NETLINK_MMAP */ -#define netlink_rx_is_mmaped(sk) false -#define netlink_tx_is_mmaped(sk) false -#define netlink_mmap sock_no_mmap -#define netlink_poll datagram_poll -#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm) 0 -#endif /* CONFIG_NETLINK_MMAP */ - static void netlink_skb_destructor(struct sk_buff *skb) { -#ifdef CONFIG_NETLINK_MMAP - struct nl_mmap_hdr *hdr; - struct netlink_ring *ring; - struct sock *sk; - - /* If a packet from the kernel to userspace was freed because of an - * error without being delivered to userspace, the kernel must reset - * the status. In the direction userspace to kernel, the status is - * always reset here after the packet was processed and freed. - */ - if (netlink_skb_is_mmaped(skb)) { - hdr = netlink_mmap_hdr(skb); - sk = NETLINK_CB(skb).sk; - - if (NETLINK_CB(skb).flags & NETLINK_SKB_TX) { - netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED); - ring = &nlk_sk(sk)->tx_ring; - } else { - if (!(NETLINK_CB(skb).flags & NETLINK_SKB_DELIVERED)) { - hdr->nm_len = 0; - netlink_set_status(hdr, NL_MMAP_STATUS_VALID); - } - ring = &nlk_sk(sk)->rx_ring; - } - - WARN_ON(atomic_read(&ring->pending) == 0); - atomic_dec(&ring->pending); - sock_put(sk); - - skb->head = NULL; - } -#endif if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) @@ -937,18 +335,6 @@ static void netlink_sock_destruct(struct sock *sk) } skb_queue_purge(&sk->sk_receive_queue); -#ifdef CONFIG_NETLINK_MMAP - if (1) { - struct nl_mmap_req req; - - memset(&req, 0, sizeof(req)); - if (nlk->rx_ring.pg_vec) - __netlink_set_ring(sk, &req, false, NULL, 0); - memset(&req, 0, sizeof(req)); - if (nlk->tx_ring.pg_vec) - __netlink_set_ring(sk, &req, true, NULL, 0); - } -#endif /* CONFIG_NETLINK_MMAP */ if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); @@ -1194,9 +580,6 @@ static int __netlink_create(struct net *net, struct socket *sock, mutex_init(nlk->cb_mutex); } init_waitqueue_head(&nlk->wait); -#ifdef CONFIG_NETLINK_MMAP - mutex_init(&nlk->pg_vec_lock); -#endif sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; @@ -1728,8 +1111,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, nlk = nlk_sk(sk); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state)) && - !netlink_skb_is_mmaped(skb)) { + test_bit(NETLINK_S_CONGESTED, &nlk->state))) { DECLARE_WAITQUEUE(wait, current); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) @@ -1767,14 +1149,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) netlink_deliver_tap(skb); -#ifdef CONFIG_NETLINK_MMAP - if (netlink_skb_is_mmaped(skb)) - netlink_queue_mmaped_skb(sk, skb); - else if (netlink_rx_is_mmaped(sk)) - netlink_ring_set_copied(sk, skb); - else -#endif /* CONFIG_NETLINK_MMAP */ - skb_queue_tail(&sk->sk_receive_queue, skb); + skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } @@ -1798,9 +1173,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) int delta; WARN_ON(skb->sk != NULL); - if (netlink_skb_is_mmaped(skb)) - return skb; - delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; @@ -1880,71 +1252,6 @@ struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, unsigned int ldiff, u32 dst_portid, gfp_t gfp_mask) { -#ifdef CONFIG_NETLINK_MMAP - unsigned int maxlen, linear_size; - struct sock *sk = NULL; - struct sk_buff *skb; - struct netlink_ring *ring; - struct nl_mmap_hdr *hdr; - - sk = netlink_getsockbyportid(ssk, dst_portid); - if (IS_ERR(sk)) - goto out; - - ring = &nlk_sk(sk)->rx_ring; - /* fast-path without atomic ops for common case: non-mmaped receiver */ - if (ring->pg_vec == NULL) - goto out_put; - - /* We need to account the full linear size needed as a ring - * slot cannot have non-linear parts. - */ - linear_size = size + ldiff; - if (ring->frame_size - NL_MMAP_HDRLEN < linear_size) - goto out_put; - - skb = alloc_skb_head(gfp_mask); - if (skb == NULL) - goto err1; - - spin_lock_bh(&sk->sk_receive_queue.lock); - /* check again under lock */ - if (ring->pg_vec == NULL) - goto out_free; - - /* check again under lock */ - maxlen = ring->frame_size - NL_MMAP_HDRLEN; - if (maxlen < linear_size) - goto out_free; - - netlink_forward_ring(ring); - hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED); - if (hdr == NULL) - goto err2; - - netlink_ring_setup_skb(skb, sk, ring, hdr); - netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED); - atomic_inc(&ring->pending); - netlink_increment_head(ring); - - spin_unlock_bh(&sk->sk_receive_queue.lock); - return skb; - -err2: - kfree_skb(skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); - netlink_overrun(sk); -err1: - sock_put(sk); - return NULL; - -out_free: - kfree_skb(skb); - spin_unlock_bh(&sk->sk_receive_queue.lock); -out_put: - sock_put(sk); -out: -#endif return alloc_skb(size, gfp_mask); } EXPORT_SYMBOL_GPL(__netlink_alloc_skb); @@ -2225,8 +1532,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_NETLINK) return -ENOPROTOOPT; - if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING && - optlen >= sizeof(int) && + if (optlen >= sizeof(int) && get_user(val, (unsigned int __user *)optval)) return -EFAULT; @@ -2279,25 +1585,6 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, } err = 0; break; -#ifdef CONFIG_NETLINK_MMAP - case NETLINK_RX_RING: - case NETLINK_TX_RING: { - struct nl_mmap_req req; - - /* Rings might consume more memory than queue limits, require - * CAP_NET_ADMIN. - */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (optlen < sizeof(req)) - return -EINVAL; - if (copy_from_user(&req, optval, sizeof(req))) - return -EFAULT; - err = netlink_set_ring(sk, &req, - optname == NETLINK_TX_RING); - break; - } -#endif /* CONFIG_NETLINK_MMAP */ case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; @@ -2467,18 +1754,6 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) smp_rmb(); } - /* It's a really convoluted way for userland to ask for mmaped - * sendmsg(), but that's what we've got... - */ - if (netlink_tx_is_mmaped(sk) && - iter_is_iovec(&msg->msg_iter) && - msg->msg_iter.nr_segs == 1 && - msg->msg_iter.iov->iov_base == NULL) { - err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, - &scm); - goto out; - } - err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; @@ -2794,8 +2069,7 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } - if (!netlink_rx_is_mmaped(sk) && - atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; /* NLMSG_GOODSIZE is small to avoid high order allocations being @@ -2831,8 +2105,7 @@ static int netlink_dump(struct sock *sk) * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ - if (!netlink_rx_is_mmaped(sk)) - skb_reserve(skb, skb_tailroom(skb) - alloc_size); + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); @@ -2884,16 +2157,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct netlink_sock *nlk; int ret; - /* Memory mapped dump requests need to be copied to avoid looping - * on the pending state in netlink_mmap_sendmsg() while the CB hold - * a reference to the skb. - */ - if (netlink_skb_is_mmaped(skb)) { - skb = skb_copy(skb, GFP_KERNEL); - if (skb == NULL) - return -ENOBUFS; - } else - atomic_inc(&skb->users); + atomic_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { @@ -3241,7 +2505,7 @@ static const struct proto_ops netlink_ops = { .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, - .poll = netlink_poll, + .poll = datagram_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, @@ -3249,7 +2513,7 @@ static const struct proto_ops netlink_ops = { .getsockopt = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, - .mmap = netlink_mmap, + .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 14437d9b1965..e68ef9ccd703 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -44,12 +44,6 @@ struct netlink_sock { int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); struct module *module; -#ifdef CONFIG_NETLINK_MMAP - struct mutex pg_vec_lock; - struct netlink_ring rx_ring; - struct netlink_ring tx_ring; - atomic_t mapped; -#endif /* CONFIG_NETLINK_MMAP */ struct rhash_head node; struct rcu_head rcu; @@ -60,15 +54,6 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } -static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb) -{ -#ifdef CONFIG_NETLINK_MMAP - return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; -#else - return false; -#endif /* CONFIG_NETLINK_MMAP */ -} - struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 3ee63a3cff30..8dd836a8dd60 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -8,41 +8,6 @@ #include "af_netlink.h" -#ifdef CONFIG_NETLINK_MMAP -static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type, - struct sk_buff *nlskb) -{ - struct netlink_diag_ring ndr; - - ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT; - ndr.ndr_block_nr = ring->pg_vec_len; - ndr.ndr_frame_size = ring->frame_size; - ndr.ndr_frame_nr = ring->frame_max + 1; - - return nla_put(nlskb, nl_type, sizeof(ndr), &ndr); -} - -static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb) -{ - struct netlink_sock *nlk = nlk_sk(sk); - int ret; - - mutex_lock(&nlk->pg_vec_lock); - ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb); - if (!ret) - ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING, - nlskb); - mutex_unlock(&nlk->pg_vec_lock); - - return ret; -} -#else -static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb) -{ - return 0; -} -#endif - static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb) { struct netlink_sock *nlk = nlk_sk(sk); @@ -87,10 +52,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO)) goto out_nlmsg_trim; - if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) && - sk_diag_put_rings_cfg(sk, skb)) - goto out_nlmsg_trim; - nlmsg_end(skb, nlh); return 0;