From 568af6de058cb2b0c5b98d98ffcf37cdc6bc38a7 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 4 Mar 2017 19:53:47 +0100 Subject: netfilter: nf_tables: set pktinfo->thoff at AH header if found Phil Sutter reports that IPv6 AH header matching is broken. From userspace, nft generates bytecode that expects to find the AH header at NFT_PAYLOAD_TRANSPORT_HEADER both for IPv4 and IPv6. However, pktinfo->thoff is set to the inner header after the AH header in IPv6, while in IPv4 pktinfo->thoff points to the AH header indeed. This behaviour is inconsistent. This patch fixes this problem by updating ipv6_find_hdr() to get the IP6_FH_F_AUTH flag so this function stops at the AH header, so both IPv4 and IPv6 pktinfo->thoff point to the AH header. This is also inconsistent when trying to match encapsulated headers: 1) A packet that looks like IPv4 + AH + TCP dport 22 will *not* match. 2) A packet that looks like IPv6 + AH + TCP dport 22 will match. Reported-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_ipv6.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index d150b5066201..97983d1c05e4 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -9,12 +9,13 @@ nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, struct sk_buff *skb, const struct nf_hook_state *state) { + unsigned int flags = IP6_FH_F_AUTH; int protohdr, thoff = 0; unsigned short frag_off; nft_set_pktinfo(pkt, skb, state); - protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0) { nft_set_pktinfo_proto_unspec(pkt, skb); return; @@ -32,6 +33,7 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_IPV6) + unsigned int flags = IP6_FH_F_AUTH; struct ipv6hdr *ip6h, _ip6h; unsigned int thoff = 0; unsigned short frag_off; @@ -50,7 +52,7 @@ __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, if (pkt_len + sizeof(*ip6h) > skb->len) return -1; - protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); + protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0) return -1; -- cgit v1.2.3 From 505d3085d7120a9f4cd0d6ffaa876968854b3baa Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 9 Mar 2017 16:16:33 -0800 Subject: scripts/spelling.txt: add "overide" pattern and fix typo instances Fix typos and add the following to the scripts/spelling.txt: overide||override While we are here, fix the doubled "address" in the touched line Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt. Also, fix the comment block style in the touched hunks in drivers/media/dvb-frontends/drx39xyj/drx_driver.h. Link: http://lkml.kernel.org/r/1481573103-11329-21-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt | 2 +- drivers/block/paride/pcd.c | 2 +- drivers/block/paride/pd.c | 2 +- drivers/block/paride/pf.c | 2 +- drivers/block/paride/pg.c | 2 +- drivers/block/paride/pt.c | 2 +- drivers/media/dvb-frontends/drx39xyj/drx_driver.h | 8 +++----- drivers/net/ethernet/qlogic/qlge/qlge.h | 2 +- include/dt-bindings/sound/cs42l42.h | 2 +- include/net/irda/timer.h | 2 +- kernel/trace/trace_stack.c | 2 +- scripts/spelling.txt | 1 + tools/lguest/lguest.c | 2 +- tools/lib/bpf/Makefile | 2 +- tools/lib/traceevent/Makefile | 2 +- tools/lib/traceevent/event-parse.h | 2 +- 16 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/net') diff --git a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt index c3f6546ebac7..6a23ad9ac53a 100644 --- a/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt +++ b/Documentation/devicetree/bindings/regulator/ti-abb-regulator.txt @@ -45,7 +45,7 @@ Required Properties: Optional Properties: - reg-names: In addition to the required properties, the following are optional - "efuse-address" - Contains efuse base address used to pick up ABB info. - - "ldo-address" - Contains address of ABB LDO overide register address. + - "ldo-address" - Contains address of ABB LDO override register. "efuse-address" is required for this. - ti,ldovbb-vset-mask - Required if ldo-address is set, mask for LDO override register to provide override vset value. diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 10aed84244f5..939641d6e262 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -50,7 +50,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (46) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 644ba0888bd4..9cfd2e06a649 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -61,7 +61,7 @@ first drive found. - major You may use this parameter to overide the + major You may use this parameter to override the default major number (45) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index ed93e8badf56..14c5d32f5d8b 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -59,7 +59,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (47) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c index 5db955fe3a94..3b5882bfb736 100644 --- a/drivers/block/paride/pg.c +++ b/drivers/block/paride/pg.c @@ -84,7 +84,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (97) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c index 61fc6824299a..e815312a00ad 100644 --- a/drivers/block/paride/pt.c +++ b/drivers/block/paride/pt.c @@ -61,7 +61,7 @@ the slower the port i/o. In some cases, setting this to zero will speed up the device. (default -1) - major You may use this parameter to overide the + major You may use this parameter to override the default major number (96) that this driver will use. Be sure to change the device name as well. diff --git a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h index 7a681d8202c7..4442e478db72 100644 --- a/drivers/media/dvb-frontends/drx39xyj/drx_driver.h +++ b/drivers/media/dvb-frontends/drx39xyj/drx_driver.h @@ -256,8 +256,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner, * * The actual DAP implementation may be restricted to only one of the modes. * A compiler warning or error will be generated if the DAP implementation -* overides or cannot handle the mode defined below. -* +* overrides or cannot handle the mode defined below. */ #ifndef DRXDAP_SINGLE_MASTER #define DRXDAP_SINGLE_MASTER 1 @@ -272,7 +271,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner, * * This maximum size may be restricted by the actual DAP implementation. * A compiler warning or error will be generated if the DAP implementation -* overides or cannot handle the chunksize defined below. +* overrides or cannot handle the chunksize defined below. * * Beware that the DAP uses DRXDAP_MAX_WCHUNKSIZE to create a temporary data * buffer. Do not undefine or choose too large, unless your system is able to @@ -292,8 +291,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner, * * This maximum size may be restricted by the actual DAP implementation. * A compiler warning or error will be generated if the DAP implementation -* overides or cannot handle the chunksize defined below. -* +* overrides or cannot handle the chunksize defined below. */ #ifndef DRXDAP_MAX_RCHUNKSIZE #define DRXDAP_MAX_RCHUNKSIZE 60 diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 90b3b46f85cc..84ac50f92c9c 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -1162,7 +1162,7 @@ struct ob_mac_tso_iocb_rsp { struct ib_mac_iocb_rsp { u8 opcode; /* 0x20 */ u8 flags1; -#define IB_MAC_IOCB_RSP_OI 0x01 /* Overide intr delay */ +#define IB_MAC_IOCB_RSP_OI 0x01 /* Override intr delay */ #define IB_MAC_IOCB_RSP_I 0x02 /* Disable Intr Generation */ #define IB_MAC_CSUM_ERR_MASK 0x1c /* A mask to use for csum errs */ #define IB_MAC_IOCB_RSP_TE 0x04 /* Checksum error */ diff --git a/include/dt-bindings/sound/cs42l42.h b/include/dt-bindings/sound/cs42l42.h index 399a123aed58..db69d84ed7d1 100644 --- a/include/dt-bindings/sound/cs42l42.h +++ b/include/dt-bindings/sound/cs42l42.h @@ -20,7 +20,7 @@ #define CS42L42_HPOUT_LOAD_1NF 0 #define CS42L42_HPOUT_LOAD_10NF 1 -/* HPOUT Clamp to GND Overide */ +/* HPOUT Clamp to GND Override */ #define CS42L42_HPOUT_CLAMP_EN 0 #define CS42L42_HPOUT_CLAMP_DIS 1 diff --git a/include/net/irda/timer.h b/include/net/irda/timer.h index cb2615ccf761..d784f242cf7b 100644 --- a/include/net/irda/timer.h +++ b/include/net/irda/timer.h @@ -59,7 +59,7 @@ struct lap_cb; * Slot timer must never exceed 85 ms, and must always be at least 25 ms, * suggested to 75-85 msec by IrDA lite. This doesn't work with a lot of * devices, and other stackes uses a lot more, so it's best we do it as well - * (Note : this is the default value and sysctl overides it - Jean II) + * (Note : this is the default value and sysctl overrides it - Jean II) */ #define SLOT_TIMEOUT (90*HZ/1000) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 1d68b5b7ad41..5fb1f2c87e6b 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -65,7 +65,7 @@ void stack_trace_print(void) } /* - * When arch-specific code overides this function, the following + * When arch-specific code overrides this function, the following * data should be filled up, assuming stack_trace_max_lock is held to * prevent concurrent updates. * stack_trace_index[] diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 6dae4df472f6..0545f5a8cabe 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -734,6 +734,7 @@ oustanding||outstanding overaall||overall overhread||overhead overlaping||overlapping +overide||override overrided||overridden overriden||overridden overun||overrun diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c index 11c8d9bc762e..5d19fdf80292 100644 --- a/tools/lguest/lguest.c +++ b/tools/lguest/lguest.c @@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val) /* Allow writing to any other BAR, or expansion ROM */ iowrite(portoff, val, mask, &d->config_words[reg]); return true; - /* We let them overide latency timer and cacheline size */ + /* We let them override latency timer and cacheline size */ } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) { /* Only let them change the first two fields. */ if (mask == 0xFFFFFFFF) diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index e2efddf10231..1f5300e56b44 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -132,7 +132,7 @@ else Q = @ endif -# Disable command line variables (CFLAGS) overide from top +# Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. MAKEOVERRIDES= diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 47076b15eebe..9b8555ea3459 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -135,7 +135,7 @@ else Q = @ endif -# Disable command line variables (CFLAGS) overide from top +# Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. MAKEOVERRIDES= diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 66342804161c..0c03538df74c 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -140,7 +140,7 @@ struct pevent_plugin_option { * struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = { * { * .name = "option-name", - * .plugin_alias = "overide-file-name", (optional) + * .plugin_alias = "override-file-name", (optional) * .description = "description of option to show users", * }, * { -- cgit v1.2.3 From cdfbabfb2f0ce983fdaa42f20e5f7842178fc01e Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 9 Mar 2017 08:09:05 +0000 Subject: net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells Signed-off-by: David S. Miller --- crypto/af_alg.c | 9 ++- crypto/algif_hash.c | 9 ++- drivers/staging/lustre/lnet/lnet/lib-socket.c | 4 +- fs/dlm/lowcomms.c | 2 +- fs/ocfs2/cluster/tcp.c | 2 +- include/crypto/if_alg.h | 2 +- include/linux/net.h | 2 +- include/net/inet_common.h | 3 +- include/net/inet_connection_sock.h | 2 +- include/net/sctp/structs.h | 3 +- include/net/sock.h | 9 ++- net/atm/svc.c | 5 +- net/ax25/af_ax25.c | 3 +- net/bluetooth/l2cap_sock.c | 2 +- net/bluetooth/rfcomm/sock.c | 3 +- net/bluetooth/sco.c | 2 +- net/core/sock.c | 106 ++++++++++++++------------ net/decnet/af_decnet.c | 5 +- net/ipv4/af_inet.c | 5 +- net/ipv4/inet_connection_sock.c | 2 +- net/irda/af_irda.c | 5 +- net/iucv/af_iucv.c | 2 +- net/llc/af_llc.c | 4 +- net/netrom/af_netrom.c | 3 +- net/nfc/llcp_sock.c | 2 +- net/phonet/pep.c | 6 +- net/phonet/socket.c | 4 +- net/rds/tcp_listen.c | 2 +- net/rose/af_rose.c | 3 +- net/sctp/ipv6.c | 5 +- net/sctp/protocol.c | 5 +- net/sctp/socket.c | 4 +- net/smc/af_smc.c | 2 +- net/socket.c | 4 +- net/tipc/socket.c | 8 +- net/unix/af_unix.c | 5 +- net/vmw_vsock/af_vsock.c | 3 +- net/x25/af_x25.c | 3 +- 38 files changed, 142 insertions(+), 108 deletions(-) (limited to 'include/net') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index f5e18c2a4852..690deca17c35 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -266,7 +266,7 @@ unlock: return err; } -int af_alg_accept(struct sock *sk, struct socket *newsock) +int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern) { struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; @@ -281,7 +281,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) if (!type) goto unlock; - sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0); + sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern); err = -ENOMEM; if (!sk2) goto unlock; @@ -323,9 +323,10 @@ unlock: } EXPORT_SYMBOL_GPL(af_alg_accept); -static int alg_accept(struct socket *sock, struct socket *newsock, int flags) +static int alg_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { - return af_alg_accept(sock->sk, newsock); + return af_alg_accept(sock->sk, newsock, kern); } static const struct proto_ops alg_proto_ops = { diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 54fc90e8339c..5e92bd275ef3 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -239,7 +239,8 @@ unlock: return err ?: len; } -static int hash_accept(struct socket *sock, struct socket *newsock, int flags) +static int hash_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); @@ -260,7 +261,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags) if (err) return err; - err = af_alg_accept(ask->parent, newsock); + err = af_alg_accept(ask->parent, newsock, kern); if (err) return err; @@ -378,7 +379,7 @@ static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, } static int hash_accept_nokey(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { int err; @@ -386,7 +387,7 @@ static int hash_accept_nokey(struct socket *sock, struct socket *newsock, if (err) return err; - return hash_accept(sock, newsock, flags); + return hash_accept(sock, newsock, flags, kern); } static struct proto_ops algif_hash_ops_nokey = { diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c index b7b87ecefcdf..9fca8d225ee0 100644 --- a/drivers/staging/lustre/lnet/lnet/lib-socket.c +++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c @@ -532,7 +532,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock) newsock->ops = sock->ops; - rc = sock->ops->accept(sock, newsock, O_NONBLOCK); + rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false); if (rc == -EAGAIN) { /* Nothing ready, so wait for activity */ init_waitqueue_entry(&wait, current); @@ -540,7 +540,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock) set_current_state(TASK_INTERRUPTIBLE); schedule(); remove_wait_queue(sk_sleep(sock->sk), &wait); - rc = sock->ops->accept(sock, newsock, O_NONBLOCK); + rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false); } if (rc) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 7d398d300e97..9382db998ec9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con) newsock->type = con->sock->type; newsock->ops = con->sock->ops; - result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK); + result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true); if (result < 0) goto accept_err; diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 4348027384f5..d0ab7e56d0b4 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1863,7 +1863,7 @@ static int o2net_accept_one(struct socket *sock, int *more) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false); if (ret < 0) goto out; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index a2bfd7843f18..e2b9c6fe2714 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -73,7 +73,7 @@ int af_alg_unregister_type(const struct af_alg_type *type); int af_alg_release(struct socket *sock); void af_alg_release_parent(struct sock *sk); -int af_alg_accept(struct sock *sk, struct socket *newsock); +int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern); int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); diff --git a/include/linux/net.h b/include/linux/net.h index cd0c8bd0a1de..0620f5e18c96 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -146,7 +146,7 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags); + struct socket *newsock, int flags, bool kern); int (*getname) (struct socket *sock, struct sockaddr *addr, int *sockaddr_len, int peer); diff --git a/include/net/inet_common.h b/include/net/inet_common.h index b7952d55b9c0..f39ae697347f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -20,7 +20,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg); int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); -int inet_accept(struct socket *sock, struct socket *newsock, int flags); +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 826f198374f8..c7a577976bec 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -258,7 +258,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, return (unsigned long)min_t(u64, when, max_when); } -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern); int inet_csk_get_port(struct sock *sk, unsigned short snum); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a244db5e5ff7..07a0b128625a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -476,7 +476,8 @@ struct sctp_pf { int (*send_verify) (struct sctp_sock *, union sctp_addr *); int (*supported_addrs)(const struct sctp_sock *, __be16 *); struct sock *(*create_accept_sk) (struct sock *sk, - struct sctp_association *asoc); + struct sctp_association *asoc, + bool kern); int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr); void (*to_sk_saddr)(union sctp_addr *, struct sock *sk); void (*to_sk_daddr)(union sctp_addr *, struct sock *sk); diff --git a/include/net/sock.h b/include/net/sock.h index 5e5997654db6..03252d53975d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -236,6 +236,7 @@ struct sock_common { * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer + * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux @@ -430,7 +431,8 @@ struct sock { #endif kmemcheck_bitfield_begin(flags); - unsigned int sk_padding : 2, + unsigned int sk_padding : 1, + sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, sk_userlocks : 4, @@ -1015,7 +1017,8 @@ struct proto { int addr_len); int (*disconnect)(struct sock *sk, int flags); - struct sock * (*accept)(struct sock *sk, int flags, int *err); + struct sock * (*accept)(struct sock *sk, int flags, int *err, + bool kern); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); @@ -1573,7 +1576,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); -int sock_no_accept(struct socket *, struct socket *, int); +int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int *, int); unsigned int sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); diff --git a/net/atm/svc.c b/net/atm/svc.c index db9794ec61d8..5589de7086af 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -318,7 +318,8 @@ out: return error; } -static int svc_accept(struct socket *sock, struct socket *newsock, int flags) +static int svc_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; @@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk); - error = svc_create(sock_net(sk), newsock, 0, 0); + error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index a8e42cedf1db..b7c486752b3a 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1320,7 +1320,8 @@ out_release: return err; } -static int ax25_accept(struct socket *sock, struct socket *newsock, int flags) +static int ax25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f307b145ea54..507b80d59dec 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -301,7 +301,7 @@ done: } static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index aa1a814ceddc..ac3c650cb234 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -471,7 +471,8 @@ done: return err; } -static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags) +static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *nsk; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index e4e9a2da1e7e..728e0c8dc8e7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -627,7 +627,7 @@ done: } static int sco_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; diff --git a/net/core/sock.c b/net/core/sock.c index f6fd79f33097..a96d5f7a5734 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -197,66 +197,55 @@ EXPORT_SYMBOL(sk_net_capable); /* * Each address family might have different locking rules, so we have - * one slock key per address family: + * one slock key per address family and separate keys for internal and + * userspace sockets. */ static struct lock_class_key af_family_keys[AF_MAX]; +static struct lock_class_key af_family_kern_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket * locks is fast): */ + +#define _sock_locks(x) \ + x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \ + x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \ + x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \ + x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \ + x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \ + x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \ + x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \ + x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \ + x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \ + x "27" , x "28" , x "AF_CAN" , \ + x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \ + x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ + x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ + x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ + x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + static const char *const af_family_key_strings[AF_MAX+1] = { - "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , - "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", - "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , - "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" , - "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , - "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , - "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , - "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , - "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , - "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , - "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , - "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , - "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_KCM" , - "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC" , "sk_lock-AF_MAX" + _sock_locks("sk_lock-") }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { - "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , - "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", - "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , - "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" , - "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , - "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , - "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , - "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" , - "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , - "slock-27" , "slock-28" , "slock-AF_CAN" , - "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , - "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , - "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_KCM" , - "slock-AF_QIPCRTR", "slock-AF_SMC" , "slock-AF_MAX" + _sock_locks("slock-") }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { - "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , - "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", - "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , - "clock-AF_X25" , "clock-AF_INET6" , "clock-AF_ROSE" , - "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" , - "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" , - "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , - "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , - "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , - "clock-27" , "clock-28" , "clock-AF_CAN" , - "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , - "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , - "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_KCM" , - "clock-AF_QIPCRTR", "clock-AF_SMC" , "clock-AF_MAX" + _sock_locks("clock-") +}; + +static const char *const af_family_kern_key_strings[AF_MAX+1] = { + _sock_locks("k-sk_lock-") +}; +static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = { + _sock_locks("k-slock-") +}; +static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = { + _sock_locks("k-clock-") }; /* @@ -264,6 +253,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { * so split the lock classes by using a per-AF key: */ static struct lock_class_key af_callback_keys[AF_MAX]; +static struct lock_class_key af_kern_callback_keys[AF_MAX]; /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across @@ -1293,7 +1283,16 @@ lenout: */ static inline void sock_lock_init(struct sock *sk) { - sock_lock_init_class_and_name(sk, + if (sk->sk_kern_sock) + sock_lock_init_class_and_name( + sk, + af_family_kern_slock_key_strings[sk->sk_family], + af_family_kern_slock_keys + sk->sk_family, + af_family_kern_key_strings[sk->sk_family], + af_family_kern_keys + sk->sk_family); + else + sock_lock_init_class_and_name( + sk, af_family_slock_key_strings[sk->sk_family], af_family_slock_keys + sk->sk_family, af_family_key_strings[sk->sk_family], @@ -1399,6 +1398,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; + sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) @@ -2277,7 +2277,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2) } EXPORT_SYMBOL(sock_no_socketpair); -int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) +int sock_no_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { return -EOPNOTSUPP; } @@ -2481,7 +2482,14 @@ void sock_init_data(struct socket *sock, struct sock *sk) } rwlock_init(&sk->sk_callback_lock); - lockdep_set_class_and_name(&sk->sk_callback_lock, + if (sk->sk_kern_sock) + lockdep_set_class_and_name( + &sk->sk_callback_lock, + af_kern_callback_keys + sk->sk_family, + af_family_kern_clock_key_strings[sk->sk_family]); + else + lockdep_set_class_and_name( + &sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e6e79eda9763..7de5b40a5d0d 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1070,7 +1070,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) return skb == NULL ? ERR_PTR(err) : skb; } -static int dn_accept(struct socket *sock, struct socket *newsock, int flags) +static int dn_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct sk_buff *skb = NULL; @@ -1099,7 +1100,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) cb = DN_SKB_CB(skb); sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0); + newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern); if (newsk == NULL) { release_sock(sk); kfree_skb(skb); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5091f46826fa..6b1fc6e4278e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect); * Accept a pending connection. The TCP layer now gives BSD semantics. */ -int inet_accept(struct socket *sock, struct socket *newsock, int flags) +int inet_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk1 = sock->sk; int err = -EINVAL; - struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err); + struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern); if (!sk2) goto do_err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b4d5980ade3b..5e313c1ac94f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) /* * This will accept the next outstanding connection. */ -struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) +struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 81adc29a448d..8d77ad5cadaf 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -828,7 +828,8 @@ out: * Wait for incoming connection * */ -static int irda_accept(struct socket *sock, struct socket *newsock, int flags) +static int irda_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct irda_sock *new, *self = irda_sk(sk); @@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) struct sk_buff *skb = NULL; int err; - err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0); + err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern); if (err) return err; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 89bbde1081ce..84de7b6326dc 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -938,7 +938,7 @@ done: /* Accept a pending connection */ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *nsk; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 06186d608a27..cb4fff785cbf 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) * @sock: Socket which connections arrive on. * @newsock: Socket to move incoming connection to. * @flags: User specified operational flags. + * @kern: If the socket is kernel internal * * Accept a new incoming connection. * Returns 0 upon success, negative otherwise. */ -static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags) +static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk, *newsk; struct llc_sock *llc, *newllc; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 4bbf4526b885..ebf16f7f9089 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -765,7 +765,8 @@ out_release: return err; } -static int nr_accept(struct socket *sock, struct socket *newsock, int flags) +static int nr_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 879885b31cce..2ffb18e73df6 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, } static int llcp_sock_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { DECLARE_WAITQUEUE(wait, current); struct sock *sk = sock->sk, *new_sk; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 222bedcd9575..e81537991ddf 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout) sock_put(sk); } -static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) +static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, + bool kern) { struct pep_sock *pn = pep_sk(sk), *newpn; struct sock *newsk = NULL; @@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp) } /* Create a new to-be-accepted sock */ - newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, + kern); if (!newsk) { pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL); err = -ENOBUFS; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index a6c8da3ee893..64634e3ec2fc 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -305,7 +305,7 @@ out: } static int pn_socket_accept(struct socket *sock, struct socket *newsock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk; struct sock *newsk; @@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock, if (unlikely(sk->sk_state != TCP_LISTEN)) return -EINVAL; - newsk = sk->sk_prot->accept(sk, flags, &err); + newsk = sk->sk_prot->accept(sk, flags, &err, kern); if (!newsk) return err; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 2c69a508a693..507678853e6c 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock) new_sock->type = sock->type; new_sock->ops = sock->ops; - ret = sock->ops->accept(sock, new_sock, O_NONBLOCK); + ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index b8a1df2c9785..4a9729257023 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -871,7 +871,8 @@ out_release: return err; } -static int rose_accept(struct socket *sock, struct socket *newsock, int flags) +static int rose_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sk_buff *skb; struct sock *newsk; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 063baac5b9fe..961ee59f696a 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr) /* Create and initialize a new sk for the socket to be returned by accept(). */ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; struct ipv6_txoptions *opt; - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0); + newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); if (!newsk) goto out; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 1b6d4574d2b0..989a900383b5 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb) /* Create and initialize a new sk for the socket returned by accept(). */ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, - struct sctp_association *asoc) + struct sctp_association *asoc, + bool kern) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot, 0); + sk->sk_prot, kern); struct inet_sock *newinet; if (!newsk) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6f0a9be50f50..0f378ea2ae38 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4116,7 +4116,7 @@ static int sctp_disconnect(struct sock *sk, int flags) * descriptor will be returned from accept() to represent the newly * formed association. */ -static struct sock *sctp_accept(struct sock *sk, int flags, int *err) +static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern) { struct sctp_sock *sp; struct sctp_endpoint *ep; @@ -4151,7 +4151,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err) */ asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc); + newsk = sp->pf->create_accept_sk(sk, asoc, kern); if (!newsk) { error = -ENOMEM; goto out; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 85837ab90e89..093803786eac 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -944,7 +944,7 @@ out: } static int smc_accept(struct socket *sock, struct socket *new_sock, - int flags) + int flags, bool kern) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); diff --git a/net/socket.c b/net/socket.c index e0757e648c0c..e034fe4164be 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1506,7 +1506,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, if (err) goto out_fd; - err = sock->ops->accept(sock, newsock, sock->file->f_flags); + err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); if (err < 0) goto out_fd; @@ -3239,7 +3239,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) if (err < 0) goto done; - err = sock->ops->accept(sock, *newsock, flags); + err = sock->ops->accept(sock, *newsock, flags, true); if (err < 0) { sock_release(*newsock); *newsock = NULL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 43e4045e72bc..7130e73bd42c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk); static void tipc_write_space(struct sock *sk); static void tipc_sock_destruct(struct sock *sk); static int tipc_release(struct socket *sock); -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern); static void tipc_sk_timeout(unsigned long data); static int tipc_sk_publish(struct tipc_sock *tsk, uint scope, struct tipc_name_seq const *seq); @@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * * Returns 0 on success, errno otherwise */ -static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, + bool kern) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; @@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) buf = skb_peek(&sk->sk_receive_queue); - res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0); + res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern); if (res) goto exit; security_sk_clone(sock->sk, new_sock->sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ee37b390260a..928691c43408 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int); static int unix_stream_connect(struct socket *, struct sockaddr *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); -static int unix_accept(struct socket *, struct socket *, int); +static int unix_accept(struct socket *, struct socket *, int, bool); static int unix_getname(struct socket *, struct sockaddr *, int *, int); static unsigned int unix_poll(struct file *, struct socket *, poll_table *); static unsigned int unix_dgram_poll(struct file *, struct socket *, @@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old, set_bit(SOCK_PASSSEC, &new->flags); } -static int unix_accept(struct socket *sock, struct socket *newsock, int flags) +static int unix_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *tsk; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9192ead66751..9f770f33c100 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1250,7 +1250,8 @@ out: return err; } -static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) +static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *listener; int err; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index fd28a49dbe8f..8b911c29860e 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout) return rc; } -static int x25_accept(struct socket *sock, struct socket *newsock, int flags) +static int x25_accept(struct socket *sock, struct socket *newsock, int flags, + bool kern) { struct sock *sk = sock->sk; struct sock *newsk; -- cgit v1.2.3 From 10596608c4d62cb8c1c2b806debcbd32fe657e71 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Wed, 8 Mar 2017 22:54:18 +0800 Subject: netfilter: nf_tables: fix mismatch in big-endian system Currently, there are two different methods to store an u16 integer to the u32 data register. For example: u32 *dest = ®s->data[priv->dreg]; 1. *dest = 0; *(u16 *) dest = val_u16; 2. *dest = val_u16; For method 1, the u16 value will be stored like this, either in big-endian or little-endian system: 0 15 31 +-+-+-+-+-+-+-+-+-+-+-+-+ | Value | 0 | +-+-+-+-+-+-+-+-+-+-+-+-+ For method 2, in little-endian system, the u16 value will be the same as listed above. But in big-endian system, the u16 value will be stored like this: 0 15 31 +-+-+-+-+-+-+-+-+-+-+-+-+ | 0 | Value | +-+-+-+-+-+-+-+-+-+-+-+-+ So later we use "memcmp(®s->data[priv->sreg], data, 2);" to do compare in nft_cmp, nft_lookup expr ..., method 2 will get the wrong result in big-endian system, as 0~15 bits will always be zero. For the similar reason, when loading an u16 value from the u32 data register, we should use "*(u16 *) sreg;" instead of "(u16)*sreg;", the 2nd method will get the wrong value in the big-endian system. So introduce some wrapper functions to store/load an u8 or u16 integer to/from the u32 data register, and use them in the right place. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 29 +++++++++++++++++++++++++++ net/ipv4/netfilter/nft_masq_ipv4.c | 8 ++++---- net/ipv4/netfilter/nft_redir_ipv4.c | 8 ++++---- net/ipv6/netfilter/nft_masq_ipv6.c | 8 ++++---- net/ipv6/netfilter/nft_redir_ipv6.c | 8 ++++---- net/netfilter/nft_ct.c | 18 +++++++++-------- net/netfilter/nft_meta.c | 40 +++++++++++++++++++------------------ net/netfilter/nft_nat.c | 8 ++++---- 8 files changed, 80 insertions(+), 47 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2aa8a9d80fbe..70c5ca0c60b1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -103,6 +103,35 @@ struct nft_regs { }; }; +/* Store/load an u16 or u8 integer to/from the u32 data register. + * + * Note, when using concatenations, register allocation happens at 32-bit + * level. So for store instruction, pad the rest part with zero to avoid + * garbage values. + */ + +static inline void nft_reg_store16(u32 *dreg, u16 val) +{ + *dreg = 0; + *(u16 *)dreg = val; +} + +static inline void nft_reg_store8(u32 *dreg, u8 val) +{ + *dreg = 0; + *(u8 *)dreg = val; +} + +static inline u16 nft_reg_load16(u32 *sreg) +{ + return *(u16 *)sreg; +} + +static inline u8 nft_reg_load8(u32 *sreg) +{ + return *(u8 *)sreg; +} + static inline void nft_data_copy(u32 *dst, const struct nft_data *src, unsigned int len) { diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index a0ea8aad1bf1..f18677277119 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -26,10 +26,10 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); } regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt), &range, nft_out(pkt)); diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c index 1650ed23c15d..5120be1d3118 100644 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ b/net/ipv4/netfilter/nft_redir_ipv4.c @@ -26,10 +26,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr, memset(&mr, 0, sizeof(mr)); if (priv->sreg_proto_min) { - mr.range[0].min.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - mr.range[0].max.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + mr.range[0].min.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + mr.range[0].max.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index 6c5b5b1830a7..4146536e9c15 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -27,10 +27,10 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); } regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range, nft_out(pkt)); diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index f5ac080fc084..a27e424f690d 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -26,10 +26,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min], - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max], + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bf548a7a71ec..91585b5e5307 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -83,7 +83,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, switch (priv->key) { case NFT_CT_DIRECTION: - *dest = CTINFO2DIR(ctinfo); + nft_reg_store8(dest, CTINFO2DIR(ctinfo)); return; case NFT_CT_STATUS: *dest = ct->status; @@ -151,20 +151,22 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; } case NFT_CT_L3PROTOCOL: - *dest = nf_ct_l3num(ct); + nft_reg_store8(dest, nf_ct_l3num(ct)); return; case NFT_CT_PROTOCOL: - *dest = nf_ct_protonum(ct); + nft_reg_store8(dest, nf_ct_protonum(ct)); return; #ifdef CONFIG_NF_CONNTRACK_ZONES case NFT_CT_ZONE: { const struct nf_conntrack_zone *zone = nf_ct_zone(ct); + u16 zoneid; if (priv->dir < IP_CT_DIR_MAX) - *dest = nf_ct_zone_id(zone, priv->dir); + zoneid = nf_ct_zone_id(zone, priv->dir); else - *dest = zone->id; + zoneid = zone->id; + nft_reg_store16(dest, zoneid); return; } #endif @@ -183,10 +185,10 @@ static void nft_ct_get_eval(const struct nft_expr *expr, nf_ct_l3num(ct) == NFPROTO_IPV4 ? 4 : 16); return; case NFT_CT_PROTO_SRC: - *dest = (__force __u16)tuple->src.u.all; + nft_reg_store16(dest, (__force u16)tuple->src.u.all); return; case NFT_CT_PROTO_DST: - *dest = (__force __u16)tuple->dst.u.all; + nft_reg_store16(dest, (__force u16)tuple->dst.u.all); return; default: break; @@ -205,7 +207,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, const struct nft_ct *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; enum ip_conntrack_info ctinfo; - u16 value = regs->data[priv->sreg]; + u16 value = nft_reg_load16(®s->data[priv->sreg]); struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e1f5ca9b423b..7b60e01f38ff 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -45,16 +45,15 @@ void nft_meta_get_eval(const struct nft_expr *expr, *dest = skb->len; break; case NFT_META_PROTOCOL: - *dest = 0; - *(__be16 *)dest = skb->protocol; + nft_reg_store16(dest, (__force u16)skb->protocol); break; case NFT_META_NFPROTO: - *dest = nft_pf(pkt); + nft_reg_store8(dest, nft_pf(pkt)); break; case NFT_META_L4PROTO: if (!pkt->tprot_set) goto err; - *dest = pkt->tprot; + nft_reg_store8(dest, pkt->tprot); break; case NFT_META_PRIORITY: *dest = skb->priority; @@ -85,14 +84,12 @@ void nft_meta_get_eval(const struct nft_expr *expr, case NFT_META_IIFTYPE: if (in == NULL) goto err; - *dest = 0; - *(u16 *)dest = in->type; + nft_reg_store16(dest, in->type); break; case NFT_META_OIFTYPE: if (out == NULL) goto err; - *dest = 0; - *(u16 *)dest = out->type; + nft_reg_store16(dest, out->type); break; case NFT_META_SKUID: sk = skb_to_full_sk(skb); @@ -142,19 +139,19 @@ void nft_meta_get_eval(const struct nft_expr *expr, #endif case NFT_META_PKTTYPE: if (skb->pkt_type != PACKET_LOOPBACK) { - *dest = skb->pkt_type; + nft_reg_store8(dest, skb->pkt_type); break; } switch (nft_pf(pkt)) { case NFPROTO_IPV4: if (ipv4_is_multicast(ip_hdr(skb)->daddr)) - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); else - *dest = PACKET_BROADCAST; + nft_reg_store8(dest, PACKET_BROADCAST); break; case NFPROTO_IPV6: - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); break; case NFPROTO_NETDEV: switch (skb->protocol) { @@ -168,14 +165,14 @@ void nft_meta_get_eval(const struct nft_expr *expr, goto err; if (ipv4_is_multicast(iph->daddr)) - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); else - *dest = PACKET_BROADCAST; + nft_reg_store8(dest, PACKET_BROADCAST); break; } case htons(ETH_P_IPV6): - *dest = PACKET_MULTICAST; + nft_reg_store8(dest, PACKET_MULTICAST); break; default: WARN_ON_ONCE(1); @@ -230,7 +227,9 @@ void nft_meta_set_eval(const struct nft_expr *expr, { const struct nft_meta *meta = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; - u32 value = regs->data[meta->sreg]; + u32 *sreg = ®s->data[meta->sreg]; + u32 value = *sreg; + u8 pkt_type; switch (meta->key) { case NFT_META_MARK: @@ -240,9 +239,12 @@ void nft_meta_set_eval(const struct nft_expr *expr, skb->priority = value; break; case NFT_META_PKTTYPE: - if (skb->pkt_type != value && - skb_pkt_type_ok(value) && skb_pkt_type_ok(skb->pkt_type)) - skb->pkt_type = value; + pkt_type = nft_reg_load8(sreg); + + if (skb->pkt_type != pkt_type && + skb_pkt_type_ok(pkt_type) && + skb_pkt_type_ok(skb->pkt_type)) + skb->pkt_type = pkt_type; break; case NFT_META_NFTRACE: skb->nf_trace = !!value; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 19a7bf3236f9..439e0bd152a0 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr, } if (priv->sreg_proto_min) { - range.min_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_min]; - range.max_proto.all = - *(__be16 *)®s->data[priv->sreg_proto_max]; + range.min_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_min]); + range.max_proto.all = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg_proto_max]); range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } -- cgit v1.2.3 From 170a1fb9c01bc40b7e8fd57a32ac9a0e131ec5b6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sat, 11 Mar 2017 00:25:26 -0500 Subject: netfilter: Force fake conntrack entry to be at least 8 bytes aligned Since the nfct and nfctinfo have been combined, the nf_conn structure must be at least 8 bytes aligned, as the 3 LSB bits are used for the nfctinfo. But there's a fake nf_conn structure to denote untracked connections, which is created by a PER_CPU construct. This does not guarantee that it will be 8 bytes aligned and can break the logic in determining the correct nfctinfo. I triggered this on a 32bit machine with the following error: BUG: unable to handle kernel NULL pointer dereference at 00000af4 IP: nf_ct_deliver_cached_events+0x1b/0xfb *pdpt = 0000000031962001 *pde = 0000000000000000 Oops: 0000 [#1] SMP [Modules linked in: ip6t_REJECT nf_reject_ipv6 nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_filter ip6_tables ipv6 crc_ccitt ppdev r8169 parport_pc parport OK ] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.10.0-test+ #75 Hardware name: MSI MS-7823/CSM-H87M-G43 (MS-7823), BIOS V1.6 02/22/2014 task: c126ec00 task.stack: c1258000 EIP: nf_ct_deliver_cached_events+0x1b/0xfb EFLAGS: 00010202 CPU: 0 EAX: 0021cd01 EBX: 00000000 ECX: 27b0c767 EDX: 32bcb17a ESI: f34135c0 EDI: f34135c0 EBP: f2debd60 ESP: f2debd3c DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 CR0: 80050033 CR2: 00000af4 CR3: 309a0440 CR4: 001406f0 Call Trace: ? ipv6_skip_exthdr+0xac/0xcb ipv6_confirm+0x10c/0x119 [nf_conntrack_ipv6] nf_hook_slow+0x22/0xc7 nf_hook+0x9a/0xad [ipv6] ? ip6t_do_table+0x356/0x379 [ip6_tables] ? ip6_fragment+0x9e9/0x9e9 [ipv6] ip6_output+0xee/0x107 [ipv6] ? ip6_fragment+0x9e9/0x9e9 [ipv6] dst_output+0x36/0x4d [ipv6] NF_HOOK.constprop.37+0xb2/0xba [ipv6] ? icmp6_dst_alloc+0x2c/0xfd [ipv6] ? local_bh_enable+0x14/0x14 [ipv6] mld_sendpack+0x1c5/0x281 [ipv6] ? mark_held_locks+0x40/0x5c mld_ifc_timer_expire+0x1f6/0x21e [ipv6] call_timer_fn+0x135/0x283 ? detach_if_pending+0x55/0x55 ? mld_dad_timer_expire+0x3e/0x3e [ipv6] __run_timers+0x111/0x14b ? mld_dad_timer_expire+0x3e/0x3e [ipv6] run_timer_softirq+0x1c/0x36 __do_softirq+0x185/0x37c ? test_ti_thread_flag.constprop.19+0xd/0xd do_softirq_own_stack+0x22/0x28 irq_exit+0x5a/0xa4 smp_apic_timer_interrupt+0x2a/0x34 apic_timer_interrupt+0x37/0x3c By using DEFINE/DECLARE_PER_CPU_ALIGNED we can enforce at least 8 byte alignment as all cache line sizes are at least 8 bytes or more. Fixes: a9e419dc7be6 ("netfilter: merge ctinfo into nfct pointer storage area") Signed-off-by: Steven Rostedt (VMware) Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 +- net/netfilter/nf_conntrack_core.c | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index f540f9ad2af4..19605878da47 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -244,7 +244,7 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, u32 seq); /* Fake conntrack entry for untracked connections */ -DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked); +DECLARE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked); static inline struct nf_conn *nf_ct_untracked_get(void) { return raw_cpu_ptr(&nf_conntrack_untracked); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 071b97fcbefb..ffb78e5f7b70 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -181,7 +181,11 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; seqcount_t nf_conntrack_generation __read_mostly; -DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked); +/* nf_conn must be 8 bytes aligned, as the 3 LSB bits are used + * for the nfctinfo. We cheat by (ab)using the PER CPU cache line + * alignment to enforce this. + */ +DEFINE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked); EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); static unsigned int nf_conntrack_hash_rnd __read_mostly; -- cgit v1.2.3 From 04166f48d9593af4513ae06c0f966c0cee300a20 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 13 Mar 2017 13:24:03 +0100 Subject: Revert "netfilter: nf_tables: add flush field to struct nft_set_iter" This reverts commit 1f48ff6c5393aa7fe290faf5d633164f105b0aa7. This patch is not required anymore now that we keep a dummy list of set elements in the bitmap set implementation, so revert this before we forget this code has no clients. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 - net/netfilter/nf_tables_api.c | 4 ---- 2 files changed, 5 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 70c5ca0c60b1..0136028652bd 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -232,7 +232,6 @@ struct nft_set_elem { struct nft_set; struct nft_set_iter { u8 genmask; - bool flush; unsigned int count; unsigned int skip; int err; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5e0ccfd5bb37..434c739dfeca 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3145,7 +3145,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, iter.count = 0; iter.err = 0; iter.fn = nf_tables_bind_check_setelem; - iter.flush = false; set->ops->walk(ctx, set, &iter); if (iter.err < 0) @@ -3399,7 +3398,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.iter.count = 0; args.iter.err = 0; args.iter.fn = nf_tables_dump_setelem; - args.iter.flush = false; set->ops->walk(&ctx, set, &args.iter); nla_nest_end(skb, nest); @@ -3963,7 +3961,6 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct nft_set_iter iter = { .genmask = genmask, .fn = nft_flush_set, - .flush = true, }; set->ops->walk(&ctx, set, &iter); @@ -5114,7 +5111,6 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, iter.count = 0; iter.err = 0; iter.fn = nf_tables_loop_check_setelem; - iter.flush = false; set->ops->walk(ctx, set, &iter); if (iter.err < 0) -- cgit v1.2.3 From 16320f363ae128d9b9c70e60f00f2a572f57c23d Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 15 Mar 2017 09:32:15 +0800 Subject: vhost-vsock: add pkt cancel capability To allow canceling all packets of a connection. Reviewed-by: Stefan Hajnoczi Reviewed-by: Jorgen Hansen Signed-off-by: Peng Tao Signed-off-by: David S. Miller --- drivers/vhost/vsock.c | 41 +++++++++++++++++++++++++++++++++++++++++ include/net/af_vsock.h | 3 +++ 2 files changed, 44 insertions(+) (limited to 'include/net') diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index ce5e63d2c66a..44eed8eb0725 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -223,6 +223,46 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt) return len; } +static int +vhost_transport_cancel_pkt(struct vsock_sock *vsk) +{ + struct vhost_vsock *vsock; + struct virtio_vsock_pkt *pkt, *n; + int cnt = 0; + LIST_HEAD(freeme); + + /* Find the vhost_vsock according to guest context id */ + vsock = vhost_vsock_get(vsk->remote_addr.svm_cid); + if (!vsock) + return -ENODEV; + + spin_lock_bh(&vsock->send_pkt_list_lock); + list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) { + if (pkt->vsk != vsk) + continue; + list_move(&pkt->list, &freeme); + } + spin_unlock_bh(&vsock->send_pkt_list_lock); + + list_for_each_entry_safe(pkt, n, &freeme, list) { + if (pkt->reply) + cnt++; + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + if (cnt) { + struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; + int new_cnt; + + new_cnt = atomic_sub_return(cnt, &vsock->queued_replies); + if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num) + vhost_poll_queue(&tx_vq->poll); + } + + return 0; +} + static struct virtio_vsock_pkt * vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, unsigned int out, unsigned int in) @@ -675,6 +715,7 @@ static struct virtio_transport vhost_transport = { .release = virtio_transport_release, .connect = virtio_transport_connect, .shutdown = virtio_transport_shutdown, + .cancel_pkt = vhost_transport_cancel_pkt, .dgram_enqueue = virtio_transport_dgram_enqueue, .dgram_dequeue = virtio_transport_dgram_dequeue, diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index f2758964ce6f..f32ed9ac181a 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -100,6 +100,9 @@ struct vsock_transport { void (*destruct)(struct vsock_sock *); void (*release)(struct vsock_sock *); + /* Cancel all pending packets sent on vsock. */ + int (*cancel_pkt)(struct vsock_sock *vsk); + /* Connections. */ int (*connect)(struct vsock_sock *); -- cgit v1.2.3 From 1f904495b79003cd3d881de8731377d48fcbc7e3 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 18 Mar 2017 19:27:23 +0800 Subject: sctp: define dst_pending_confirm as a bit in sctp_transport As tp->dst_pending_confirm's value can only be set 0 or 1, this patch is to change to define it as a bit instead of __u32. Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 07a0b128625a..4f645198e9bd 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -753,6 +753,8 @@ struct sctp_transport { /* Is the Path MTU update pending on this tranport */ pmtu_pending:1, + dst_pending_confirm:1, /* need to confirm neighbour */ + /* Has this transport moved the ctsn since we last sacked */ sack_generation:1; u32 dst_cookie; @@ -806,8 +808,6 @@ struct sctp_transport { __u32 burst_limited; /* Holds old cwnd when max.burst is applied */ - __u32 dst_pending_confirm; /* need to confirm neighbour */ - /* Destination */ struct dst_entry *dst; /* Source address. */ -- cgit v1.2.3 From 1511949c61ec63e4b646c34d602ac6990b38ce30 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 20 Mar 2017 17:46:27 +0800 Subject: sctp: declare struct sctp_stream before using it sctp_stream_free uses struct sctp_stream as a param, but struct sctp_stream is defined after it's declaration. This patch is to declare struct sctp_stream before sctp_stream_free. Fixes: a83863174a61 ("sctp: prepare asoc stream for stream reconf") Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 4f645198e9bd..592decebac75 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -83,6 +83,7 @@ struct sctp_bind_addr; struct sctp_ulpq; struct sctp_ep_common; struct crypto_shash; +struct sctp_stream; #include -- cgit v1.2.3