summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/networking/netlink_mmap.txt339
-rw-r--r--include/linux/netfilter/nfnetlink.h11
-rw-r--r--include/linux/netlink.h11
-rw-r--r--include/linux/skbuff.h6
-rw-r--r--include/net/netfilter/nf_conntrack.h2
-rw-r--r--include/net/netfilter/nf_conntrack_expect.h4
-rw-r--r--include/uapi/linux/netlink.h32
-rw-r--r--include/uapi/linux/netlink_diag.h10
-rw-r--r--net/Kconfig9
-rw-r--r--net/core/skbuff.c30
-rw-r--r--net/ipv4/inet_diag.c6
-rw-r--r--net/ipv4/udp_diag.c4
-rw-r--r--net/netfilter/nf_conntrack_core.c8
-rw-r--r--net/netfilter/nf_conntrack_expect.c8
-rw-r--r--net/netfilter/nfnetlink.c20
-rw-r--r--net/netfilter/nfnetlink_log.c12
-rw-r--r--net/netfilter/nfnetlink_queue_core.c3
-rw-r--r--net/netlink/af_netlink.c836
-rw-r--r--net/netlink/af_netlink.h20
-rw-r--r--net/netlink/diag.c32
-rw-r--r--net/sched/cls_flow.c2
21 files changed, 1331 insertions, 74 deletions
diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt
new file mode 100644
index 00000000000..1c2dab40962
--- /dev/null
+++ b/Documentation/networking/netlink_mmap.txt
@@ -0,0 +1,339 @@
+This file documents how to use memory mapped I/O with netlink.
+
+Author: Patrick McHardy <kaber@trash.net>
+
+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, &params, sizeof(params));
+- setsockopt(fd, SOL_NETLINK, NETLINK_TX_RING, &params, 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
+processsed 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 contruction to
+use memory from the TX ring instead of (usually) a buffer declared on the
+stack and setting up the frame header approriately. 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
+<linux/netlink.h>.
+
+RX and TX rings
+----------------
+
+Each ring contains a number of continous memory blocks, containing frames of
+fixed size dependant 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 continous 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 continous 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 phsyically continous memory for a ring block,
+it will fall back to use physically discontinous 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
+--------------
+
+Kernel processing usually involves validation of the message received by
+user-space, then processing its contents. The kernel must assure that
+userspace is not able to modify the message contents after they have been
+validated. In order to do so, the message is copied from the ring frame
+to an allocated buffer if either of these conditions is false:
+
+- only a single mapping of the ring exists
+- the file descriptor is not shared between processes
+
+This means that for threaded programs, the kernel will fall back to copying.
+
+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, NETLINK_RX_RING, &req, sizeof(req)) < 0)
+ exit(1);
+ if (setsockopt(fd, NETLINK_TX_RING, &req, sizeof(req)) < 0)
+ exit(1)
+
+ /* Calculate size of each invididual 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)
+ <handle error>
+
+ /* 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/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index ecbb8e49591..cadb7402d7a 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -29,10 +29,13 @@ extern int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n);
extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
extern int nfnetlink_has_listeners(struct net *net, unsigned int group);
-extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group,
- int echo, gfp_t flags);
-extern int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error);
-extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags);
+extern struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size,
+ u32 dst_portid, gfp_t gfp_mask);
+extern int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
+ unsigned int group, int echo, gfp_t flags);
+extern int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error);
+extern int nfnetlink_unicast(struct sk_buff *skb, struct net *net,
+ u32 portid, int flags);
extern void nfnl_lock(__u8 subsys_id);
extern void nfnl_unlock(__u8 subsys_id);
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index e0f746b7b95..6358da5eeee 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -15,11 +15,18 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb)
return (struct nlmsghdr *)skb->data;
}
+enum netlink_skb_flags {
+ NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */
+ NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */
+ NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */
+};
+
struct netlink_skb_parms {
struct scm_creds creds; /* Skb credentials */
__u32 portid;
__u32 dst_group;
- struct sock *ssk;
+ __u32 flags;
+ struct sock *sk;
};
#define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb))
@@ -57,6 +64,8 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group)
extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group);
extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
extern int netlink_has_listeners(struct sock *sk, unsigned int group);
+extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
+ u32 dst_portid, gfp_t gfp_mask);
extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
__u32 group, gfp_t allocation);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f5bed7b3195..2e0ced1af3b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -651,6 +651,12 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
}
+extern struct sk_buff *__alloc_skb_head(gfp_t priority, int node);
+static inline struct sk_buff *alloc_skb_head(gfp_t priority)
+{
+ return __alloc_skb_head(priority, -1);
+}
+
extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
extern int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
extern struct sk_buff *skb_clone(struct sk_buff *skb,
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index caca0c4d6b4..644d9c223d2 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -184,7 +184,7 @@ extern int nf_conntrack_hash_check_insert(struct nf_conn *ct);
extern void nf_ct_delete_from_lists(struct nf_conn *ct);
extern void nf_ct_dying_timeout(struct nf_conn *ct);
-extern void nf_conntrack_flush_report(struct net *net, u32 pid, int report);
+extern void nf_conntrack_flush_report(struct net *net, u32 portid, int report);
extern bool nf_ct_get_tuplepr(const struct sk_buff *skb,
unsigned int nhoff, u_int16_t l3num,
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index cbbae7621e2..3f3aecbc863 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -88,7 +88,7 @@ nf_ct_find_expectation(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple);
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
- u32 pid, int report);
+ u32 portid, int report);
static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
{
nf_ct_unlink_expect_report(exp, 0, 0);
@@ -106,7 +106,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *, unsigned int, u_int8_t,
u_int8_t, const __be16 *, const __be16 *);
void nf_ct_expect_put(struct nf_conntrack_expect *exp);
int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
- u32 pid, int report);
+ u32 portid, int report);
static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect)
{
return nf_ct_expect_related_report(expect, 0, 0);
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 32a354f67ba..1a85940f8ab 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -1,6 +1,7 @@
#ifndef _UAPI__LINUX_NETLINK_H
#define _UAPI__LINUX_NETLINK_H
+#include <linux/kernel.h>
#include <linux/socket.h> /* for __kernel_sa_family_t */
#include <linux/types.h>
@@ -105,11 +106,42 @@ struct nlmsgerr {
#define NETLINK_PKTINFO 3
#define NETLINK_BROADCAST_ERROR 4
#define NETLINK_NO_ENOBUFS 5
+#define NETLINK_RX_RING 6
+#define NETLINK_TX_RING 7
struct nl_pktinfo {
__u32 group;
};
+struct nl_mmap_req {
+ unsigned int nm_block_size;
+ unsigned int nm_block_nr;
+ unsigned int nm_frame_size;
+ unsigned int nm_frame_nr;
+};
+
+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;
+};
+
+enum nl_mmap_status {
+ NL_MMAP_STATUS_UNUSED,
+ NL_MMAP_STATUS_RESERVED,
+ NL_MMAP_STATUS_VALID,
+ NL_MMAP_STATUS_COPY,
+ NL_MMAP_STATUS_SKIP,
+};
+
+#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))
+
#define NET_MAJOR 36 /* Major 36 is reserved for networking */
enum {
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index 88009a31cd0..4e31db4eea4 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -25,9 +25,18 @@ struct netlink_diag_msg {
__u32 ndiag_cookie[2];
};
+struct netlink_diag_ring {
+ __u32 ndr_block_size;
+ __u32 ndr_block_nr;
+ __u32 ndr_frame_size;
+ __u32 ndr_frame_nr;
+};
+
enum {
NETLINK_DIAG_MEMINFO,
NETLINK_DIAG_GROUPS,
+ NETLINK_DIAG_RX_RING,
+ NETLINK_DIAG_TX_RING,
__NETLINK_DIAG_MAX,
};
@@ -38,5 +47,6 @@ enum {
#define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */
#define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */
+#define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */
#endif
diff --git a/net/Kconfig b/net/Kconfig
index 2ddc9046868..1a2221630e6 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -23,6 +23,15 @@ menuconfig NET
if NET
+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 WANT_COMPAT_NETLINK_MESSAGES
bool
help
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a92d9e7d10f..898cf5c566f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -179,6 +179,33 @@ out:
*
*/
+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->data = NULL;
+ skb->truesize = sizeof(struct sk_buff);
+ atomic_set(&skb->users, 1);
+
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+ skb->mac_header = ~0U;
+#endif
+out:
+ return skb;
+}
+
/**
* __alloc_skb - allocate a network buffer
* @size: size to allocate
@@ -584,7 +611,8 @@ static void skb_release_head_state(struct sk_buff *skb)
static void skb_release_all(struct sk_buff *skb)
{
skb_release_head_state(skb);
- skb_release_data(skb);
+ if (likely(skb->data))
+ skb_release_data(skb);
}
/**
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8620408af57..5f648751fce 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -324,7 +324,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s
}
err = sk_diag_fill(sk, rep, req,
- sk_user_ns(NETLINK_CB(in_skb).ssk),
+ sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
@@ -630,7 +630,7 @@ static int inet_csk_diag_dump(struct sock *sk,
return 0;
return inet_csk_diag_fill(sk, skb, r,
- sk_user_ns(NETLINK_CB(cb->skb).ssk),
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
@@ -805,7 +805,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
}
err = inet_diag_fill_req(skb, sk, req,
- sk_user_ns(NETLINK_CB(cb->skb).ssk),
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, cb->nlh);
if (err < 0) {
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 369a781851a..7927db0a927 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -25,7 +25,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
return 0;
return inet_sk_diag_fill(sk, NULL, skb, req,
- sk_user_ns(NETLINK_CB(cb->skb).ssk),
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}
@@ -71,7 +71,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
goto out;
err = inet_sk_diag_fill(sk, NULL, rep, req,
- sk_user_ns(NETLINK_CB(in_skb).ssk),
+ sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0, nlh);
if (err < 0) {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 007e8c43d19..54ddc2f8e7c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1260,7 +1260,7 @@ void nf_ct_iterate_cleanup(struct net *net,
EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);
struct __nf_ct_flush_report {
- u32 pid;
+ u32 portid;
int report;
};
@@ -1275,7 +1275,7 @@ static int kill_report(struct nf_conn *i, void *data)
/* If we fail to deliver the event, death_by_timeout() will retry */
if (nf_conntrack_event_report(IPCT_DESTROY, i,
- fr->pid, fr->report) < 0)
+ fr->portid, fr->report) < 0)
return 1;
/* Avoid the delivery of the destroy event in death_by_timeout(). */
@@ -1298,10 +1298,10 @@ void nf_ct_free_hashtable(void *hash, unsigned int size)
}
EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
-void nf_conntrack_flush_report(struct net *net, u32 pid, int report)
+void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
{
struct __nf_ct_flush_report fr = {
- .pid = pid,
+ .portid = portid,
.report = report,
};
nf_ct_iterate_cleanup(net, kill_report, &fr);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 8c10e3db3d9..0adfdcc68ba 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -40,7 +40,7 @@ static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
- u32 pid, int report)
+ u32 portid, int report)
{
struct nf_conn_help *master_help = nfct_help(exp->master);
struct net *net = nf_ct_exp_net(exp);
@@ -54,7 +54,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
hlist_del(&exp->lnode);
master_help->expecting[exp->class]--;
- nf_ct_expect_event_report(IPEXP_DESTROY, exp, pid, report);
+ nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
nf_ct_expect_put(exp);
NF_CT_STAT_INC(net, expect_delete);
@@ -412,7 +412,7 @@ out:
}
int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
- u32 pid, int report)
+ u32 portid, int report)
{
int ret;
@@ -425,7 +425,7 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
if (ret < 0)
goto out;
spin_unlock_bh(&nf_conntrack_lock);
- nf_ct_expect_event_report(IPEXP_NEW, expect, pid, report);
+ nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
return ret;
out:
spin_unlock_bh(&nf_conntrack_lock);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index bc4c499adb1..572d87dc116 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -112,22 +112,30 @@ int nfnetlink_has_listeners(struct net *net, unsigned int group)
}
EXPORT_SYMBOL_GPL(nfnetlink_has_listeners);
-int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 pid,
+struct sk_buff *nfnetlink_alloc_skb(struct net *net, unsigned int size,
+ u32 dst_portid, gfp_t gfp_mask)
+{
+ return netlink_alloc_skb(net->nfnl, size, dst_portid, gfp_mask);
+}
+EXPORT_SYMBOL_GPL(nfnetlink_alloc_skb);
+
+int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid,
unsigned int group, int echo, gfp_t flags)
{
- return nlmsg_notify(net->nfnl, skb, pid, group, echo, flags);
+ return nlmsg_notify(net->nfnl, skb, portid, group, echo, flags);
}
EXPORT_SYMBOL_GPL(nfnetlink_send);
-int nfnetlink_set_err(struct net *net, u32 pid, u32 group, int error)
+int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error)
{
- return netlink_set_err(net->nfnl, pid, group, error);
+ return netlink_set_err(net->nfnl, portid, group, error);
}
EXPORT_SYMBOL_GPL(nfnetlink_set_err);
-int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u_int32_t pid, int flags)
+int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
+ int flags)
{
- return netlink_unicast(net->nfnl, skb, pid, flags);
+ return netlink_unicast(net->nfnl, skb, portid, flags);
}
EXPORT_SYMBOL_GPL(nfnetlink_unicast);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 1a0be2af1dd..d4199eb9b33 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -318,7 +318,7 @@ nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags)
}
static struct sk_buff *
-nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size)
+nfulnl_alloc_skb(u32 peer_portid, unsigned int inst_size, unsigned int pkt_size)
{
struct sk_buff *skb;
unsigned int n;
@@ -327,13 +327,14 @@ nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size)
* message. WARNING: has to be <= 128k due to slab restrictions */
n = max(inst_size, pkt_size);
- skb = alloc_skb(n, GFP_ATOMIC);
+ skb = nfnetlink_alloc_skb(&init_net, n, peer_portid, GFP_ATOMIC);
if (!skb) {
if (n > pkt_size) {
/* try to allocate only as much as we need for current
* packet */
- skb = alloc_skb(pkt_size, GFP_ATOMIC);
+ skb = nfnetlink_alloc_skb(&init_net, pkt_size,
+ peer_portid, GFP_ATOMIC);
if (!skb)
pr_err("nfnetlink_log: can't even alloc %u bytes\n",
pkt_size);
@@ -696,7 +697,8 @@ nfulnl_log_packet(u_int8_t pf,
}
if (!inst->skb) {
- inst->skb = nfulnl_alloc_skb(inst->nlbufsiz, size);
+ inst->skb = nfulnl_alloc_skb(inst->peer_portid, inst->nlbufsiz,
+ size);
if (!inst->skb)
goto alloc_failure;
}
@@ -824,7 +826,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb,
inst = instance_create(net, group_num,
NETLINK_CB(skb).portid,
- sk_user_ns(NETLINK_CB(skb).ssk));
+ sk_user_ns(NETLINK_CB(skb).sk));
if (IS_ERR(inst)) {
ret = PTR_ERR(inst);
goto out;
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 5e280b3e154..ef3cdb4bfee 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -339,7 +339,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
if (queue->flags & NFQA_CFG_F_CONNTRACK)
ct = nfqnl_ct_get(entskb, &size, &ctinfo);
- skb = alloc_skb(size, GFP_ATOMIC);
+ skb = nfnetlink_alloc_skb(&init_net, size, queue->peer_portid,
+ GFP_ATOMIC);
if (!skb)
return NULL;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index ce2e0064e7f..2a3e9ba814c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -3,6 +3,7 @@
*
* Authors: Alan Cox <alan@lxorguk.ukuu.org.uk>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
+ * Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -55,6 +56,8 @@
#include <linux/types.h>
#include <linux/audit.h>
#include <linux/mutex.h>
+#include <linux/vmalloc.h>
+#include <asm/cacheflush.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -68,6 +71,10 @@ struct listeners {
unsigned long masks[0];
};
+/* state bits */
+#define NETLINK_CONGESTED 0x0
+
+/* flags */
#define NETLINK_KERNEL_SOCKET 0x1
#define NETLINK_RECV_PKTINFO 0x2
#define NETLINK_BROADCAST_SEND_ERROR 0x4
@@ -84,6 +91,7 @@ EXPORT_SYMBOL_GPL(nl_table);
static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
static int netlink_dump(struct sock *sk);
+static void netlink_skb_destructor(struct sk_buff *skb);
DEFINE_RWLOCK(nl_table_lock);
EXPORT_SYMBOL_GPL(nl_table_lock);
@@ -103,6 +111,599 @@ static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u
return &hash->table[jhash_1word(portid, hash->rnd) & hash->mask];
}
+static void netlink_overrun(struct sock *sk)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+
+ if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
+ if (!test_and_set_bit(NETLINK_CONGESTED, &nlk_sk(sk)->state)) {
+ sk->sk_err = ENOBUFS;
+ sk->sk_error_report(sk);
+ }
+ }
+ atomic_inc(&sk->sk_drops);
+}
+
+static void netlink_rcv_wake(struct sock *sk)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+
+ if (skb_queue_empty(&sk->sk_receive_queue))
+ clear_bit(NETLINK_CONGESTED, &nlk->state);
+ if (!test_bit(NETLINK_CONGESTED, &nlk->state))
+ wake_up_interruptible(&nlk->wait);
+}
+
+#ifdef CONFIG_NETLINK_MMAP
+static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
+{
+ return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
+}
+
+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, *ptr;
+
+ 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] = ptr = 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 int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
+ bool closing, bool tx_ring)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+ struct netlink_ring *ring;
+ struct sk_buff_head *queue;
+ void **pg_vec = NULL;
+ unsigned int order = 0;
+ int err;
+
+ ring = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+ queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+
+ if (!closing) {
+ 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 (!IS_ALIGNED(req->nm_block_size, PAGE_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;
+ }
+
+ err = -EBUSY;
+ mutex_lock(&nlk->pg_vec_lock);
+ if (closing || atomic_read(&nlk->mapped) == 0) {
+ err = 0;
+ 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));
+ }
+ mutex_unlock(&nlk->pg_vec_lock);
+
+ if (pg_vec)
+ free_pg_vec(pg_vec, order, req->nm_block_nr);
+ return err;
+}
+
+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 0;
+}
+
+static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr)
+{
+#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_MSG_HDRLEN + hdr->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)
+{
+ hdr->nm_status = status;
+ flush_dcache_page(pgvec_to_page(hdr));
+ smp_wmb();
+}
+
+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 struct nl_mmap_hdr *
+netlink_previous_frame(const struct netlink_ring *ring,
+ enum nl_mmap_status status)
+{
+ unsigned int prev;
+
+ prev = ring->head ? ring->head - 1 : ring->frame_max;
+ return netlink_lookup_frame(ring, prev, 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, pos = head;
+ const struct nl_mmap_hdr *hdr;
+
+ do {
+ hdr = __netlink_lookup_frame(ring, pos);
+ 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_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 != NULL && 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);
+
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ if (nlk->rx_ring.pg_vec) {
+ netlink_forward_ring(&nlk->rx_ring);
+ if (!netlink_previous_frame(&nlk->rx_ring, NL_MMAP_STATUS_UNUSED))
+ 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 sock_iocb *siocb)
+{
+ struct netlink_sock *nlk = nlk_sk(sk);
+ struct netlink_ring *ring;
+ struct nl_mmap_hdr *hdr;
+ struct sk_buff *skb;
+ unsigned int maxlen;
+ bool excl = true;
+ int err = 0, len = 0;
+
+ /* Netlink messages are validated by the receiver before processing.
+ * In order to avoid userspace changing the contents of the message
+ * after validation, the socket and the ring may only be used by a
+ * single process, otherwise we fall back to copying.
+ */
+ if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 ||
+ atomic_read(&nlk->mapped) > 1)
+ excl = false;
+
+ mutex_lock(&nlk->pg_vec_lock);
+
+ ring = &nlk->tx_ring;
+ maxlen = ring->frame_size - NL_MMAP_HDRLEN;
+
+ do {
+ 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;
+ }
+ if (hdr->nm_len > maxlen) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ netlink_frame_flush_dcache(hdr);
+
+ if (likely(dst_portid == 0 && dst_group == 0 && excl)) {
+ skb = alloc_skb_head(GFP_KERNEL);
+ if (skb == NULL) {
+ err = -ENOBUFS;
+ goto out;
+ }
+ sock_hold(sk);
+ netlink_ring_setup_skb(skb, sk, ring, hdr);
+ NETLINK_CB(skb).flags |= NETLINK_SKB_TX;
+ __skb_put(skb, hdr->nm_len);
+ netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
+ atomic_inc(&ring->pending);
+ } else {
+ skb = alloc_skb(hdr->nm_len, GFP_KERNEL);
+ if (skb == NULL) {
+ err = -ENOBUFS;
+ goto out;
+ }
+ __skb_put(skb, hdr->nm_len);
+ memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->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 = siocb->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 = NETLINK_CB(skb).creds.uid;
+ hdr->nm_gid = NETLINK_CB(skb).creds.gid;
+ netlink_frame_flush_dcache(hdr);
+ 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 = NETLINK_CB(skb).creds.uid;
+ hdr->nm_gid = NETLINK_CB(skb).creds.gid;
+ netlink_set_status(hdr, NL_MMAP_STATUS_COPY);
+}
+
+#else /* CONFIG_NETLINK_MMAP */
+#define netlink_skb_is_mmaped(skb) false
+#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, siocb) 0
+#endif /* CONFIG_NETLINK_MMAP */
+
static void netlink_destroy_callback(struct netlink_callback *cb)
{
kfree_skb(cb->skb);
@@ -115,6 +716,53 @@ static void netlink_consume_callback(struct netlink_callback *cb)
kfree(cb);
}
+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->data = NULL;
+ }
+#endif
+ if (skb->sk != NULL)
+ sock_rfree(skb);
+}
+
+static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
+{
+ WARN_ON(skb->sk != NULL);
+ skb->sk = sk;
+ skb->destructor = netlink_skb_destructor;
+ atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+ sk_mem_charge(sk, skb->truesize);
+}
+
static void netlink_sock_destruct(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -128,6 +776,18 @@ 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, true, false);
+ memset(&req, 0, sizeof(req));
+ if (nlk->tx_ring.pg_vec)
+ netlink_set_ring(sk, &req, true, true);
+ }
+#endif /* CONFIG_NETLINK_MMAP */
if (!sock_flag(sk, SOCK_DEAD)) {
printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
@@ -391,6 +1051,9 @@ 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;
@@ -722,19 +1385,6 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
return 0;
}
-static void netlink_overrun(struct sock *sk)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
-
- if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
- if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
- sk->sk_err = ENOBUFS;
- sk->sk_error_report(sk);
- }
- }
- atomic_inc(&sk->sk_drops);
-}
-
static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)
{
struct sock *sock;
@@ -787,8 +1437,9 @@ 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(0, &nlk->state)) {
+ if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
+ test_bit(NETLINK_CONGESTED, &nlk->state)) &&
+ !netlink_skb_is_mmaped(skb)) {
DECLARE_WAITQUEUE(wait, current);
if (!*timeo) {
if (!ssk || netlink_is_kernel(ssk))
@@ -802,7 +1453,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
add_wait_queue(&nlk->wait, &wait);
if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- test_bit(0, &nlk->state)) &&
+ test_bit(NETLINK_CONGESTED, &nlk->state)) &&
!sock_flag(sk, SOCK_DEAD))
*timeo = schedule_timeout(*timeo);
@@ -816,7 +1467,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
}
return 1;
}
- skb_set_owner_r(skb, sk);
+ netlink_skb_set_owner_r(skb, sk);
return 0;
}
@@ -824,7 +1475,14 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = skb->len;
- skb_queue_tail(&sk->sk_receive_queue, 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);
sk->sk_data_ready(sk, len);
return len;
}
@@ -847,7 +1505,9 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
{
int delta;
- skb_orphan(skb);
+ WARN_ON(skb->sk != NULL);
+ if (netlink_skb_is_mmaped(skb))
+ return skb;
delta = skb->end - skb->tail;
if (delta * 2 < skb->truesize)
@@ -867,16 +1527,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
return skb;
}
-static void netlink_rcv_wake(struct sock *sk)
-{
- struct netlink_sock *nlk = nlk_sk(sk);
-
- if (skb_queue_empty(&sk->sk_receive_queue))
- clear_bit(0, &nlk->state);
- if (!test_bit(0, &nlk->state))
- wake_up_interruptible(&nlk->wait);
-}
-
static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
struct sock *ssk)
{
@@ -886,8 +1536,8 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
ret = -ECONNREFUSED;
if (nlk->netlink_rcv != NULL) {
ret = skb->len;
- skb_set_owner_r(skb, sk);
- NETLINK_CB(skb).ssk = ssk;
+ netlink_skb_set_owner_r(skb, sk);
+ NETLINK_CB(skb).sk = ssk;
nlk->netlink_rcv(skb);
consume_skb(skb);
} else {
@@ -933,6 +1583,69 @@ retry:
}
EXPORT_SYMBOL(netlink_unicast);
+struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
+ u32 dst_portid, gfp_t gfp_mask)
+{
+#ifdef CONFIG_NETLINK_MMAP
+ struct sock *sk = NULL;
+ struct sk_buff *skb;
+ struct netlink_ring *ring;
+ struct nl_mmap_hdr *hdr;
+ unsigned int maxlen;
+
+ 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;
+
+ 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;
+
+ maxlen = ring->frame_size - NL_MMAP_HDRLEN;
+ if (maxlen < 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);
+
int netlink_has_listeners(struct sock *sk, unsigned int group)
{
int res = 0;
@@ -957,8 +1670,8 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
struct netlink_sock *nlk = nlk_sk(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
- !test_bit(0, &nlk->state)) {
- skb_set_owner_r(skb, sk);
+ !test_bit(NETLINK_CONGESTED, &nlk->state)) {
+ netlink_skb_set_owner_r(skb, sk);
__netlink_sendskb(sk, skb);
return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
}
@@ -1193,7 +1906,8 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
if (level != SOL_NETLINK)
return -ENOPROTOOPT;
- if (optlen >= sizeof(int) &&
+ if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING &&
+ optlen >= sizeof(int) &&
get_user(val, (unsigned int __user *)optval))
return -EFAULT;
@@ -1235,13 +1949,32 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
case NETLINK_NO_ENOBUFS:
if (val) {
nlk->flags |= NETLINK_RECV_NO_ENOBUFS;
- clear_bit(0, &nlk->state);
+ clear_bit(NETLINK_CONGESTED, &nlk->state);
wake_up_interruptible(&nlk->wait);
} else {
nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS;
}
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, false,
+ optname == NETLINK_TX_RING);
+ break;
+ }
+#endif /* CONFIG_NETLINK_MMAP */
default:
err = -ENOPROTOOPT;
}
@@ -1352,6 +2085,13 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
goto out;
}
+ if (netlink_tx_is_mmaped(sk) &&
+ msg->msg_iov->iov_base == NULL) {
+ err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
+ siocb);
+ goto out;
+ }
+
err = -EMSGSIZE;
if (len > sk->sk_sndbuf - 32)
goto out;
@@ -1684,9 +2424,13 @@ static int netlink_dump(struct sock *sk)
alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
- skb = sock_rmalloc(sk, alloc_size, 0, GFP_KERNEL);
+ if (!netlink_rx_is_mmaped(sk) &&
+ atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+ goto errout_skb;
+ skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
if (!skb)
goto errout_skb;
+ netlink_skb_set_owner_r(skb, sk);
len = cb->dump(skb, cb);
@@ -1741,6 +2485,19 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
if (cb == NULL)
return -ENOBUFS;
+ /* 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) {
+ kfree(cb);
+ return -ENOBUFS;
+ }
+ } else
+ atomic_inc(&skb->users);
+
cb->dump = control->dump;
cb->done = control->done;
cb->nlh = nlh;
@@ -1801,7 +2558,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
if (err)
payload += nlmsg_len(nlh);
- skb = nlmsg_new(payload, GFP_KERNEL);
+ skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload),
+ NETLINK_CB(in_skb).portid, GFP_KERNEL);
if (!skb) {
struct sock *sk;
@@ -2067,7 +2825,7 @@ static const struct proto_ops netlink_ops = {
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = netlink_getname,
- .poll = datagram_poll,
+ .poll = netlink_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
@@ -2075,7 +2833,7 @@ static const struct proto_ops netlink_ops = {
.getsockopt = netlink_getsockopt,
.sendmsg = netlink_sendmsg,
.recvmsg = netlink_recvmsg,
- .mmap = sock_no_mmap,
+ .mmap = netlink_mmap,
.sendpage = sock_no_sendpage,
};
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index d9acb2a1d85..ed8522265f4 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -6,6 +6,20 @@
#define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8)
#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long))
+struct netlink_ring {
+ void **pg_vec;
+ unsigned int head;
+ unsigned int frames_per_block;
+ unsigned int frame_size;
+ unsigned int frame_max;
+
+ unsigned int pg_vec_order;
+ unsigned int pg_vec_pages;
+ unsigned int pg_vec_len;
+
+ atomic_t pending;
+};
+
struct netlink_sock {
/* struct sock has to be the first member of netlink_sock */
struct sock sk;
@@ -24,6 +38,12 @@ struct netlink_sock {
void (*netlink_rcv)(struct sk_buff *skb);
void (*netlink_bind)(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 */
};
static inline struct netlink_sock *nlk_sk(struct sock *sk)
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 5ffb1d1cf40..4e4aa471cd0 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -7,6 +7,34 @@
#include "af_netlink.h"
+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;
+}
+
static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
{
struct netlink_sock *nlk = nlk_sk(sk);
@@ -51,6 +79,10 @@ 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;
+
return nlmsg_end(skb, nlh);
out_nlmsg_trim:
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index aa36a8c8b33..7881e2fccbc 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -393,7 +393,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
return -EOPNOTSUPP;
if ((keymask & (FLOW_KEY_SKUID|FLOW_KEY_SKGID)) &&
- sk_user_ns(NETLINK_CB(in_skb).ssk) != &init_user_ns)
+ sk_user_ns(NETLINK_CB(in_skb).sk) != &init_user_ns)
return -EOPNOTSUPP;
}
generated by cgit v1.2.3-70-g09d2 (git 2.51.2) at 2025-11-04 00:05:18 +0000