linux/net/rds/rds.h

1020 lines
31 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _RDS_RDS_H
#define _RDS_RDS_H
#include <net/sock.h>
#include <linux/scatterlist.h>
#include <linux/highmem.h>
#include <rdma/rdma_cm.h>
#include <linux/mutex.h>
#include <linux/rds.h>
#include <linux/rhashtable.h>
#include <linux/refcount.h>
#include <linux/in6.h>
#include "info.h"
/*
* RDS Network protocol version
*/
#define RDS_PROTOCOL_3_0 0x0300
#define RDS_PROTOCOL_3_1 0x0301
#define RDS_PROTOCOL_4_0 0x0400
#define RDS_PROTOCOL_4_1 0x0401
#define RDS_PROTOCOL_VERSION RDS_PROTOCOL_3_1
#define RDS_PROTOCOL_MAJOR(v) ((v) >> 8)
#define RDS_PROTOCOL_MINOR(v) ((v) & 255)
#define RDS_PROTOCOL(maj, min) (((maj) << 8) | min)
#define RDS_PROTOCOL_COMPAT_VERSION RDS_PROTOCOL_3_1
/* The following ports, 16385, 18634, 18635, are registered with IANA as
* the ports to be used for RDS over TCP and UDP. Currently, only RDS over
* TCP and RDS over IB/RDMA are implemented. 18634 is the historical value
* used for the RDMA_CM listener port. RDS/TCP uses port 16385. After
* IPv6 work, RDMA_CM also uses 16385 as the listener port. 18634 is kept
* to ensure compatibility with older RDS modules. Those ports are defined
* in each transport's header file.
*/
#define RDS_PORT 18634
#ifdef ATOMIC64_INIT
#define KERNEL_HAS_ATOMIC64
#endif
#ifdef RDS_DEBUG
#define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args)
#else
/* sigh, pr_debug() causes unused variable warnings */
static inline __printf(1, 2)
void rdsdebug(char *fmt, ...)
{
}
#endif
#define RDS_FRAG_SHIFT 12
#define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT))
/* Used to limit both RDMA and non-RDMA RDS message to 1MB */
#define RDS_MAX_MSG_SIZE ((unsigned int)(1 << 20))
#define RDS_CONG_MAP_BYTES (65536 / 8)
#define RDS_CONG_MAP_PAGES (PAGE_ALIGN(RDS_CONG_MAP_BYTES) / PAGE_SIZE)
#define RDS_CONG_MAP_PAGE_BITS (PAGE_SIZE * 8)
struct rds_cong_map {
struct rb_node m_rb_node;
struct in6_addr m_addr;
wait_queue_head_t m_waitq;
struct list_head m_conn_list;
unsigned long m_page_addrs[RDS_CONG_MAP_PAGES];
};
/*
* This is how we will track the connection state:
* A connection is always in one of the following
* states. Updates to the state are atomic and imply
* a memory barrier.
*/
enum {
RDS_CONN_DOWN = 0,
RDS_CONN_CONNECTING,
RDS_CONN_DISCONNECTING,
RDS_CONN_UP,
RDS: TCP: fix race windows in send-path quiescence by rds_tcp_accept_one() The send path needs to be quiesced before resetting callbacks from rds_tcp_accept_one(), and commit eb192840266f ("RDS:TCP: Synchronize rds_tcp_accept_one with rds_send_xmit when resetting t_sock") achieves this using the c_state and RDS_IN_XMIT bit following the pattern used by rds_conn_shutdown(). However this leaves the possibility of a race window as shown in the sequence below take t_conn_lock in rds_tcp_conn_connect send outgoing syn to peer drop t_conn_lock in rds_tcp_conn_connect incoming from peer triggers rds_tcp_accept_one, conn is marked CONNECTING wait for RDS_IN_XMIT to quiesce any rds_send_xmit threads call rds_tcp_reset_callbacks [.. race-window where incoming syn-ack can cause the conn to be marked UP from rds_tcp_state_change ..] lock_sock called from rds_tcp_reset_callbacks, and we set t_sock to null As soon as the conn is marked UP in the race-window above, rds_send_xmit() threads will proceed to rds_tcp_xmit and may encounter a null-pointer deref on the t_sock. Given that rds_tcp_state_change() is invoked in softirq context, whereas rds_tcp_reset_callbacks() is in workq context, and testing for RDS_IN_XMIT after lock_sock could result in a deadlock with tcp_sendmsg, this commit fixes the race by using a new c_state, RDS_TCP_RESETTING, which will prevent a transition to RDS_CONN_UP from rds_tcp_state_change(). Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-05 05:00:00 +08:00
RDS_CONN_RESETTING,
RDS_CONN_ERROR,
};
/* Bits for c_flags */
#define RDS_LL_SEND_FULL 0
#define RDS_RECONNECT_PENDING 1
#define RDS_IN_XMIT 2
#define RDS_RECV_REFILL 3
#define RDS_DESTROY_PENDING 4
/* Max number of multipaths per RDS connection. Must be a power of 2 */
#define RDS_MPATH_WORKERS 8
#define RDS_MPATH_HASH(rs, n) (jhash_1word((rs)->rs_bound_port, \
(rs)->rs_hash_initval) & ((n) - 1))
#define IS_CANONICAL(laddr, faddr) (htonl(laddr) < htonl(faddr))
/* Per mpath connection state */
struct rds_conn_path {
struct rds_connection *cp_conn;
struct rds_message *cp_xmit_rm;
unsigned long cp_xmit_sg;
unsigned int cp_xmit_hdr_off;
unsigned int cp_xmit_data_off;
unsigned int cp_xmit_atomic_sent;
unsigned int cp_xmit_rdma_sent;
unsigned int cp_xmit_data_sent;
spinlock_t cp_lock; /* protect msg queues */
u64 cp_next_tx_seq;
struct list_head cp_send_queue;
struct list_head cp_retrans;
u64 cp_next_rx_seq;
void *cp_transport_data;
atomic_t cp_state;
unsigned long cp_send_gen;
unsigned long cp_flags;
unsigned long cp_reconnect_jiffies;
struct delayed_work cp_send_w;
struct delayed_work cp_recv_w;
struct delayed_work cp_conn_w;
struct work_struct cp_down_w;
struct mutex cp_cm_lock; /* protect cp_state & cm */
wait_queue_head_t cp_waitq;
unsigned int cp_unacked_packets;
unsigned int cp_unacked_bytes;
unsigned int cp_index;
};
/* One rds_connection per RDS address pair */
struct rds_connection {
struct hlist_node c_hash_node;
struct in6_addr c_laddr;
struct in6_addr c_faddr;
int c_dev_if; /* ifindex used for this conn */
int c_bound_if; /* ifindex of c_laddr */
2015-10-01 04:54:07 +08:00
unsigned int c_loopback:1,
c_isv6:1,
c_ping_triggered:1,
c_pad_to_32:29;
int c_npaths;
struct rds_connection *c_passive;
struct rds_transport *c_trans;
struct rds_cong_map *c_lcong;
struct rds_cong_map *c_fcong;
/* Protocol version */
unsigned int c_proposed_version;
unsigned int c_version;
rds: tcp: correctly sequence cleanup on netns deletion. Commit 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") introduces a regression in rds-tcp netns cleanup. The cleanup_net(), (and thus rds_tcp_dev_event notification) is only called from put_net() when all netns refcounts go to 0, but this cannot happen if the rds_connection itself is holding a c_net ref that it expects to release in rds_tcp_kill_sock. Instead, the rds_tcp_kill_sock callback should make sure to tear down state carefully, ensuring that the socket teardown is only done after all data-structures and workqs that depend on it are quiesced. The original motivation for commit 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") was to resolve a race condition reported by syzkaller where workqs for tx/rx/connect were triggered after the namespace was deleted. Those worker threads should have been cancelled/flushed before socket tear-down and indeed, rds_conn_path_destroy() does try to sequence this by doing /* cancel cp_send_w */ /* cancel cp_recv_w */ /* flush cp_down_w */ /* free data structures */ Here the "flush cp_down_w" will trigger rds_conn_shutdown and thus invoke rds_tcp_conn_path_shutdown() to close the tcp socket, so that we ought to have satisfied the requirement that "socket-close is done after all other dependent state is quiesced". However, rds_conn_shutdown has a bug in that it *always* triggers the reconnect workq (and if connection is successful, we always restart tx/rx workqs so with the right timing, we risk the race conditions reported by syzkaller). Netns deletion is like module teardown- no need to restart a reconnect in this case. We can use the c_destroy_in_prog bit to avoid restarting the reconnect. Fixes: 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-01 03:11:28 +08:00
possible_net_t c_net;
/* TOS */
u8 c_tos;
struct list_head c_map_item;
unsigned long c_map_queued;
struct rds_conn_path *c_path;
wait_queue_head_t c_hs_waitq; /* handshake waitq */
2016-11-17 05:29:49 +08:00
u32 c_my_gen_num;
u32 c_peer_gen_num;
};
static inline
struct net *rds_conn_net(struct rds_connection *conn)
{
rds: tcp: correctly sequence cleanup on netns deletion. Commit 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") introduces a regression in rds-tcp netns cleanup. The cleanup_net(), (and thus rds_tcp_dev_event notification) is only called from put_net() when all netns refcounts go to 0, but this cannot happen if the rds_connection itself is holding a c_net ref that it expects to release in rds_tcp_kill_sock. Instead, the rds_tcp_kill_sock callback should make sure to tear down state carefully, ensuring that the socket teardown is only done after all data-structures and workqs that depend on it are quiesced. The original motivation for commit 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") was to resolve a race condition reported by syzkaller where workqs for tx/rx/connect were triggered after the namespace was deleted. Those worker threads should have been cancelled/flushed before socket tear-down and indeed, rds_conn_path_destroy() does try to sequence this by doing /* cancel cp_send_w */ /* cancel cp_recv_w */ /* flush cp_down_w */ /* free data structures */ Here the "flush cp_down_w" will trigger rds_conn_shutdown and thus invoke rds_tcp_conn_path_shutdown() to close the tcp socket, so that we ought to have satisfied the requirement that "socket-close is done after all other dependent state is quiesced". However, rds_conn_shutdown has a bug in that it *always* triggers the reconnect workq (and if connection is successful, we always restart tx/rx workqs so with the right timing, we risk the race conditions reported by syzkaller). Netns deletion is like module teardown- no need to restart a reconnect in this case. We can use the c_destroy_in_prog bit to avoid restarting the reconnect. Fixes: 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-01 03:11:28 +08:00
return read_pnet(&conn->c_net);
}
static inline
void rds_conn_net_set(struct rds_connection *conn, struct net *net)
{
rds: tcp: correctly sequence cleanup on netns deletion. Commit 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") introduces a regression in rds-tcp netns cleanup. The cleanup_net(), (and thus rds_tcp_dev_event notification) is only called from put_net() when all netns refcounts go to 0, but this cannot happen if the rds_connection itself is holding a c_net ref that it expects to release in rds_tcp_kill_sock. Instead, the rds_tcp_kill_sock callback should make sure to tear down state carefully, ensuring that the socket teardown is only done after all data-structures and workqs that depend on it are quiesced. The original motivation for commit 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") was to resolve a race condition reported by syzkaller where workqs for tx/rx/connect were triggered after the namespace was deleted. Those worker threads should have been cancelled/flushed before socket tear-down and indeed, rds_conn_path_destroy() does try to sequence this by doing /* cancel cp_send_w */ /* cancel cp_recv_w */ /* flush cp_down_w */ /* free data structures */ Here the "flush cp_down_w" will trigger rds_conn_shutdown and thus invoke rds_tcp_conn_path_shutdown() to close the tcp socket, so that we ought to have satisfied the requirement that "socket-close is done after all other dependent state is quiesced". However, rds_conn_shutdown has a bug in that it *always* triggers the reconnect workq (and if connection is successful, we always restart tx/rx workqs so with the right timing, we risk the race conditions reported by syzkaller). Netns deletion is like module teardown- no need to restart a reconnect in this case. We can use the c_destroy_in_prog bit to avoid restarting the reconnect. Fixes: 8edc3affc077 ("rds: tcp: Take explicit refcounts on struct net") Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-01 03:11:28 +08:00
write_pnet(&conn->c_net, net);
}
#define RDS_FLAG_CONG_BITMAP 0x01
#define RDS_FLAG_ACK_REQUIRED 0x02
#define RDS_FLAG_RETRANSMITTED 0x04
#define RDS_MAX_ADV_CREDIT 255
/* RDS_FLAG_PROBE_PORT is the reserved sport used for sending a ping
* probe to exchange control information before establishing a connection.
* Currently the control information that is exchanged is the number of
* supported paths. If the peer is a legacy (older kernel revision) peer,
* it would return a pong message without additional control information
* that would then alert the sender that the peer was an older rev.
*/
#define RDS_FLAG_PROBE_PORT 1
#define RDS_HS_PROBE(sport, dport) \
((sport == RDS_FLAG_PROBE_PORT && dport == 0) || \
(sport == 0 && dport == RDS_FLAG_PROBE_PORT))
/*
* Maximum space available for extension headers.
*/
#define RDS_HEADER_EXT_SPACE 16
struct rds_header {
__be64 h_sequence;
__be64 h_ack;
__be32 h_len;
__be16 h_sport;
__be16 h_dport;
u8 h_flags;
u8 h_credit;
u8 h_padding[4];
__sum16 h_csum;
u8 h_exthdr[RDS_HEADER_EXT_SPACE];
};
/*
* Reserved - indicates end of extensions
*/
#define RDS_EXTHDR_NONE 0
/*
* This extension header is included in the very
* first message that is sent on a new connection,
* and identifies the protocol level. This will help
* rolling updates if a future change requires breaking
* the protocol.
* NB: This is no longer true for IB, where we do a version
* negotiation during the connection setup phase (protocol
* version information is included in the RDMA CM private data).
*/
#define RDS_EXTHDR_VERSION 1
struct rds_ext_header_version {
__be32 h_version;
};
/*
* This extension header is included in the RDS message
* chasing an RDMA operation.
*/
#define RDS_EXTHDR_RDMA 2
struct rds_ext_header_rdma {
__be32 h_rdma_rkey;
};
/*
* This extension header tells the peer about the
* destination <R_Key,offset> of the requested RDMA
* operation.
*/
#define RDS_EXTHDR_RDMA_DEST 3
struct rds_ext_header_rdma_dest {
__be32 h_rdma_rkey;
__be32 h_rdma_offset;
};
/* Extension header announcing number of paths.
* Implicit length = 2 bytes.
*/
2016-11-17 05:29:49 +08:00
#define RDS_EXTHDR_NPATHS 5
#define RDS_EXTHDR_GEN_NUM 6
#define __RDS_EXTHDR_MAX 16 /* for now */
#define RDS_RX_MAX_TRACES (RDS_MSG_RX_DGRAM_TRACE_MAX + 1)
#define RDS_MSG_RX_HDR 0
#define RDS_MSG_RX_START 1
#define RDS_MSG_RX_END 2
#define RDS_MSG_RX_CMSG 3
/* The following values are whitelisted for usercopy */
struct rds_inc_usercopy {
rds_rdma_cookie_t rdma_cookie;
ktime_t rx_tstamp;
};
struct rds_incoming {
refcount_t i_refcount;
struct list_head i_item;
struct rds_connection *i_conn;
struct rds_conn_path *i_conn_path;
struct rds_header i_hdr;
unsigned long i_rx_jiffies;
struct in6_addr i_saddr;
struct rds_inc_usercopy i_usercopy;
u64 i_rx_lat_trace[RDS_RX_MAX_TRACES];
};
struct rds_mr {
struct rb_node r_rb_node;
struct kref r_kref;
u32 r_key;
/* A copy of the creation flags */
unsigned int r_use_once:1;
unsigned int r_invalidate:1;
unsigned int r_write:1;
struct rds_sock *r_sock; /* back pointer to the socket that owns us */
struct rds_transport *r_trans;
void *r_trans_private;
};
static inline rds_rdma_cookie_t rds_rdma_make_cookie(u32 r_key, u32 offset)
{
return r_key | (((u64) offset) << 32);
}
static inline u32 rds_rdma_cookie_key(rds_rdma_cookie_t cookie)
{
return cookie;
}
static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie)
{
return cookie >> 32;
}
/* atomic operation types */
#define RDS_ATOMIC_TYPE_CSWP 0
#define RDS_ATOMIC_TYPE_FADD 1
/*
* m_sock_item and m_conn_item are on lists that are serialized under
* conn->c_lock. m_sock_item has additional meaning in that once it is empty
* the message will not be put back on the retransmit list after being sent.
* messages that are canceled while being sent rely on this.
*
* m_inc is used by loopback so that it can pass an incoming message straight
* back up into the rx path. It embeds a wire header which is also used by
* the send path, which is kind of awkward.
*
* m_sock_item indicates the message's presence on a socket's send or receive
* queue. m_rs will point to that socket.
*
* m_daddr is used by cancellation to prune messages to a given destination.
*
* The RDS_MSG_ON_SOCK and RDS_MSG_ON_CONN flags are used to avoid lock
* nesting. As paths iterate over messages on a sock, or conn, they must
* also lock the conn, or sock, to remove the message from those lists too.
* Testing the flag to determine if the message is still on the lists lets
* us avoid testing the list_head directly. That means each path can use
* the message's list_head to keep it on a local list while juggling locks
* without confusing the other path.
*
* m_ack_seq is an optional field set by transports who need a different
* sequence number range to invalidate. They can use this in a callback
* that they pass to rds_send_drop_acked() to see if each message has been
* acked. The HAS_ACK_SEQ flag can be used to detect messages which haven't
* had ack_seq set yet.
*/
#define RDS_MSG_ON_SOCK 1
#define RDS_MSG_ON_CONN 2
#define RDS_MSG_HAS_ACK_SEQ 3
#define RDS_MSG_ACK_REQUIRED 4
#define RDS_MSG_RETRANSMITTED 5
#define RDS_MSG_MAPPED 6
#define RDS_MSG_PAGEVEC 7
2016-11-17 05:29:49 +08:00
#define RDS_MSG_FLUSH 8
struct rds_znotifier {
struct mmpin z_mmp;
u32 z_cookie;
};
struct rds_msg_zcopy_info {
struct list_head rs_zcookie_next;
union {
struct rds_znotifier znotif;
struct rds_zcopy_cookies zcookies;
};
};
struct rds_msg_zcopy_queue {
struct list_head zcookie_head;
spinlock_t lock; /* protects zcookie_head queue */
};
static inline void rds_message_zcopy_queue_init(struct rds_msg_zcopy_queue *q)
{
spin_lock_init(&q->lock);
INIT_LIST_HEAD(&q->zcookie_head);
}
net/rds: fix warn in rds_message_alloc_sgs redundant copy_from_user in rds_sendmsg system call expose rds to issue where rds_rdma_extra_size walk the rds iovec and and calculate the number pf pages (sgs) it need to add to the tail of rds message and later rds_cmsg_rdma_args copy the rds iovec again and re calculate the same number and get different result causing WARN_ON in rds_message_alloc_sgs. fix this by doing the copy_from_user only once per rds_sendmsg system call. When issue occur the below dump is seen: WARNING: CPU: 0 PID: 19789 at net/rds/message.c:316 rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 19789 Comm: syz-executor827 Not tainted 4.19.0-next-20181030+ #101 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x39d lib/dump_stack.c:113 panic+0x2ad/0x55c kernel/panic.c:188 __warn.cold.8+0x20/0x45 kernel/panic.c:540 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Code: c0 74 04 3c 03 7e 6c 44 01 ab 78 01 00 00 e8 2b 9e 35 fa 4c 89 e0 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 e8 14 9e 35 fa <0f> 0b 31 ff 44 89 ee e8 18 9f 35 fa 45 85 ed 75 1b e8 fe 9d 35 fa RSP: 0018:ffff8801c51b7460 EFLAGS: 00010293 RAX: ffff8801bc412080 RBX: ffff8801d7bf4040 RCX: ffffffff8749c9e6 RDX: 0000000000000000 RSI: ffffffff8749ca5c RDI: 0000000000000004 RBP: ffff8801c51b7490 R08: ffff8801bc412080 R09: ffffed003b5c5b67 R10: ffffed003b5c5b67 R11: ffff8801dae2db3b R12: 0000000000000000 R13: 000000000007165c R14: 000000000007165c R15: 0000000000000005 rds_cmsg_rdma_args+0x82d/0x1510 net/rds/rdma.c:623 rds_cmsg_send net/rds/send.c:971 [inline] rds_sendmsg+0x19a2/0x3180 net/rds/send.c:1273 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2117 __sys_sendmsg+0x11d/0x280 net/socket.c:2155 __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2162 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44a859 Code: e8 dc e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 6b cb fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1d4710ada8 EFLAGS: 00000297 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006dcc28 RCX: 000000000044a859 RDX: 0000000000000000 RSI: 0000000020001600 RDI: 0000000000000003 RBP: 00000000006dcc20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000297 R12: 00000000006dcc2c R13: 646e732f7665642f R14: 00007f1d4710b9c0 R15: 00000000006dcd2c Kernel Offset: disabled Rebooting in 86400 seconds.. Reported-by: syzbot+26de17458aeda9d305d8@syzkaller.appspotmail.com Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: shamir rabinovitch <shamir.rabinovitch@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-16 15:01:08 +08:00
struct rds_iov_vector {
struct rds_iovec *iov;
int len;
};
struct rds_iov_vector_arr {
struct rds_iov_vector *vec;
int len;
int indx;
int incr;
};
struct rds_message {
refcount_t m_refcount;
struct list_head m_sock_item;
struct list_head m_conn_item;
struct rds_incoming m_inc;
u64 m_ack_seq;
struct in6_addr m_daddr;
unsigned long m_flags;
/* Never access m_rs without holding m_rs_lock.
* Lock nesting is
* rm->m_rs_lock
* -> rs->rs_lock
*/
spinlock_t m_rs_lock;
wait_queue_head_t m_flush_wait;
struct rds_sock *m_rs;
/* cookie to send to remote, in rds header */
rds_rdma_cookie_t m_rdma_cookie;
unsigned int m_used_sgs;
unsigned int m_total_sgs;
void *m_final_op;
struct {
struct rm_atomic_op {
int op_type;
union {
struct {
uint64_t compare;
uint64_t swap;
uint64_t compare_mask;
uint64_t swap_mask;
} op_m_cswp;
struct {
uint64_t add;
uint64_t nocarry_mask;
} op_m_fadd;
};
u32 op_rkey;
u64 op_remote_addr;
unsigned int op_notify:1;
unsigned int op_recverr:1;
unsigned int op_mapped:1;
unsigned int op_silent:1;
unsigned int op_active:1;
struct scatterlist *op_sg;
struct rds_notifier *op_notifier;
struct rds_mr *op_rdma_mr;
} atomic;
struct rm_rdma_op {
u32 op_rkey;
u64 op_remote_addr;
unsigned int op_write:1;
unsigned int op_fence:1;
unsigned int op_notify:1;
unsigned int op_recverr:1;
unsigned int op_mapped:1;
unsigned int op_silent:1;
unsigned int op_active:1;
unsigned int op_bytes;
unsigned int op_nents;
unsigned int op_count;
struct scatterlist *op_sg;
struct rds_notifier *op_notifier;
struct rds_mr *op_rdma_mr;
u64 op_odp_addr;
struct rds_mr *op_odp_mr;
} rdma;
struct rm_data_op {
unsigned int op_active:1;
unsigned int op_nents;
unsigned int op_count;
rds: re-entry of rds_ib_xmit/rds_iw_xmit The BUG_ON at line 452/453 is triggered in function rds_send_xmit. 441 while (ret) { 442 tmp = min_t(int, ret, sg->length - 443 conn->c_xmit_data_off); 444 conn->c_xmit_data_off += tmp; 445 ret -= tmp; 446 if (conn->c_xmit_data_off == sg->length) { 447 conn->c_xmit_data_off = 0; 448 sg++; 449 conn->c_xmit_sg++; 450 if (ret != 0 && conn->c_xmit_sg == rm->data.op_nents) 451 printk(KERN_ERR "conn %p rm %p sg %p ret %d\n", conn, rm, sg, ret); 452 BUG_ON(ret != 0 && 453 conn->c_xmit_sg == rm->data.op_nents); 454 } 455 } it is complaining the total sent length is bigger that we want to send. rds_ib_xmit() is wrong for the second entry for the same rds_message returning wrong value. the sg and off passed by rds_send_xmit to rds_ib_xmit is based on scatterlist.offset/length, but the rds_ib_xmit action is based on scatterlist.dma_address/dma_length. in case dma_length is larger than length there is problem. for the 2nd and later entries of rds_ib_xmit for same rds_message, at least one of the following two is wrong: 1) the scatterlist to start with, the choosen one can far beyond the correct one. 2) the offset to start with within the scatterlist. fix: add op_dmasg and op_dmaoff to rm_data_op structure indicating the scatterlist and offset within the it to start with for rds_ib_xmit respectively. op_dmasg and op_dmaoff are initialized to zero when doing dma mapping for the first see of the message and are changed when filling send slots. the same applies to rds_iw_xmit too. Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2015-05-21 13:11:40 +08:00
unsigned int op_dmasg;
unsigned int op_dmaoff;
struct rds_znotifier *op_mmp_znotifier;
struct scatterlist *op_sg;
} data;
};
RDS: RDMA: Fix the NULL-ptr deref in rds_ib_get_mr Registration of a memory region(MR) through FRMR/fastreg(unlike FMR) needs a connection/qp. With a proxy qp, this dependency on connection will be removed, but that needs more infrastructure patches, which is a work in progress. As an intermediate fix, the get_mr returns EOPNOTSUPP when connection details are not populated. The MR registration through sendmsg() will continue to work even with fast registration, since connection in this case is formed upfront. This patch fixes the following crash: kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 4244 Comm: syzkaller468044 Not tainted 4.16.0-rc6+ #361 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:rds_ib_get_mr+0x5c/0x230 net/rds/ib_rdma.c:544 RSP: 0018:ffff8801b059f890 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff8801b07e1300 RCX: ffffffff8562d96e RDX: 000000000000000d RSI: 0000000000000001 RDI: 0000000000000068 RBP: ffff8801b059f8b8 R08: ffffed0036274244 R09: ffff8801b13a1200 R10: 0000000000000004 R11: ffffed0036274243 R12: ffff8801b13a1200 R13: 0000000000000001 R14: ffff8801ca09fa9c R15: 0000000000000000 FS: 00007f4d050af700(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4d050aee78 CR3: 00000001b0d9b006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __rds_rdma_map+0x710/0x1050 net/rds/rdma.c:271 rds_get_mr_for_dest+0x1d4/0x2c0 net/rds/rdma.c:357 rds_setsockopt+0x6cc/0x980 net/rds/af_rds.c:347 SYSC_setsockopt net/socket.c:1849 [inline] SyS_setsockopt+0x189/0x360 net/socket.c:1828 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x4456d9 RSP: 002b:00007f4d050aedb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00000000006dac3c RCX: 00000000004456d9 RDX: 0000000000000007 RSI: 0000000000000114 RDI: 0000000000000004 RBP: 00000000006dac38 R08: 00000000000000a0 R09: 0000000000000000 R10: 0000000020000380 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffbfb36d6f R14: 00007f4d050af9c0 R15: 0000000000000005 Code: fa 48 c1 ea 03 80 3c 02 00 0f 85 cc 01 00 00 4c 8b bb 80 04 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7f 68 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 9c 01 00 00 4d 8b 7f 68 48 b8 00 00 00 00 00 RIP: rds_ib_get_mr+0x5c/0x230 net/rds/ib_rdma.c:544 RSP: ffff8801b059f890 ---[ end trace 7e1cea13b85473b0 ]--- Reported-by: syzbot+b51c77ef956678a65834@syzkaller.appspotmail.com Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: Avinash Repaka <avinash.repaka@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-25 11:31:58 +08:00
struct rds_conn_path *m_conn_path;
};
/*
* The RDS notifier is used (optionally) to tell the application about
* completed RDMA operations. Rather than keeping the whole rds message
* around on the queue, we allocate a small notifier that is put on the
* socket's notifier_list. Notifications are delivered to the application
* through control messages.
*/
struct rds_notifier {
struct list_head n_list;
uint64_t n_user_token;
int n_status;
};
/* Available as part of RDS core, so doesn't need to participate
* in get_preferred transport etc
*/
#define RDS_TRANS_LOOP 3
/**
* struct rds_transport - transport specific behavioural hooks
*
* @xmit: .xmit is called by rds_send_xmit() to tell the transport to send
* part of a message. The caller serializes on the send_sem so this
* doesn't need to be reentrant for a given conn. The header must be
* sent before the data payload. .xmit must be prepared to send a
* message with no data payload. .xmit should return the number of
* bytes that were sent down the connection, including header bytes.
* Returning 0 tells the caller that it doesn't need to perform any
* additional work now. This is usually the case when the transport has
* filled the sending queue for its connection and will handle
* triggering the rds thread to continue the send when space becomes
* available. Returning -EAGAIN tells the caller to retry the send
* immediately. Returning -ENOMEM tells the caller to retry the send at
* some point in the future.
*
* @conn_shutdown: conn_shutdown stops traffic on the given connection. Once
* it returns the connection can not call rds_recv_incoming().
* This will only be called once after conn_connect returns
* non-zero success and will The caller serializes this with
* the send and connecting paths (xmit_* and conn_*). The
* transport is responsible for other serialization, including
* rds_recv_incoming(). This is called in process context but
* should try hard not to block.
*/
struct rds_transport {
char t_name[TRANSNAMSIZ];
struct list_head t_item;
struct module *t_owner;
unsigned int t_prefer_loopback:1,
t_mp_capable:1;
unsigned int t_type;
int (*laddr_check)(struct net *net, const struct in6_addr *addr,
__u32 scope_id);
int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp);
void (*conn_free)(void *data);
int (*conn_path_connect)(struct rds_conn_path *cp);
void (*conn_path_shutdown)(struct rds_conn_path *conn);
void (*xmit_path_prepare)(struct rds_conn_path *cp);
void (*xmit_path_complete)(struct rds_conn_path *cp);
int (*xmit)(struct rds_connection *conn, struct rds_message *rm,
unsigned int hdr_off, unsigned int sg, unsigned int off);
int (*xmit_rdma)(struct rds_connection *conn, struct rm_rdma_op *op);
int (*xmit_atomic)(struct rds_connection *conn, struct rm_atomic_op *op);
int (*recv_path)(struct rds_conn_path *cp);
int (*inc_copy_to_user)(struct rds_incoming *inc, struct iov_iter *to);
void (*inc_free)(struct rds_incoming *inc);
int (*cm_handle_connect)(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event, bool isv6);
int (*cm_initiate_connect)(struct rdma_cm_id *cm_id, bool isv6);
void (*cm_connect_complete)(struct rds_connection *conn,
struct rdma_cm_event *event);
unsigned int (*stats_info_copy)(struct rds_info_iterator *iter,
unsigned int avail);
void (*exit)(void);
void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg,
RDS: RDMA: Fix the NULL-ptr deref in rds_ib_get_mr Registration of a memory region(MR) through FRMR/fastreg(unlike FMR) needs a connection/qp. With a proxy qp, this dependency on connection will be removed, but that needs more infrastructure patches, which is a work in progress. As an intermediate fix, the get_mr returns EOPNOTSUPP when connection details are not populated. The MR registration through sendmsg() will continue to work even with fast registration, since connection in this case is formed upfront. This patch fixes the following crash: kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 4244 Comm: syzkaller468044 Not tainted 4.16.0-rc6+ #361 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:rds_ib_get_mr+0x5c/0x230 net/rds/ib_rdma.c:544 RSP: 0018:ffff8801b059f890 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff8801b07e1300 RCX: ffffffff8562d96e RDX: 000000000000000d RSI: 0000000000000001 RDI: 0000000000000068 RBP: ffff8801b059f8b8 R08: ffffed0036274244 R09: ffff8801b13a1200 R10: 0000000000000004 R11: ffffed0036274243 R12: ffff8801b13a1200 R13: 0000000000000001 R14: ffff8801ca09fa9c R15: 0000000000000000 FS: 00007f4d050af700(0000) GS:ffff8801db300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f4d050aee78 CR3: 00000001b0d9b006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: __rds_rdma_map+0x710/0x1050 net/rds/rdma.c:271 rds_get_mr_for_dest+0x1d4/0x2c0 net/rds/rdma.c:357 rds_setsockopt+0x6cc/0x980 net/rds/af_rds.c:347 SYSC_setsockopt net/socket.c:1849 [inline] SyS_setsockopt+0x189/0x360 net/socket.c:1828 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 RIP: 0033:0x4456d9 RSP: 002b:00007f4d050aedb8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036 RAX: ffffffffffffffda RBX: 00000000006dac3c RCX: 00000000004456d9 RDX: 0000000000000007 RSI: 0000000000000114 RDI: 0000000000000004 RBP: 00000000006dac38 R08: 00000000000000a0 R09: 0000000000000000 R10: 0000000020000380 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fffbfb36d6f R14: 00007f4d050af9c0 R15: 0000000000000005 Code: fa 48 c1 ea 03 80 3c 02 00 0f 85 cc 01 00 00 4c 8b bb 80 04 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7f 68 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 9c 01 00 00 4d 8b 7f 68 48 b8 00 00 00 00 00 RIP: rds_ib_get_mr+0x5c/0x230 net/rds/ib_rdma.c:544 RSP: ffff8801b059f890 ---[ end trace 7e1cea13b85473b0 ]--- Reported-by: syzbot+b51c77ef956678a65834@syzkaller.appspotmail.com Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: Avinash Repaka <avinash.repaka@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-25 11:31:58 +08:00
struct rds_sock *rs, u32 *key_ret,
struct rds_connection *conn,
u64 start, u64 length, int need_odp);
void (*sync_mr)(void *trans_private, int direction);
void (*free_mr)(void *trans_private, int invalidate);
void (*flush_mrs)(void);
rds: tcp: use rds_destroy_pending() to synchronize netns/module teardown and rds connection/workq management An rds_connection can get added during netns deletion between lines 528 and 529 of 506 static void rds_tcp_kill_sock(struct net *net) : /* code to pull out all the rds_connections that should be destroyed */ : 528 spin_unlock_irq(&rds_tcp_conn_lock); 529 list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) 530 rds_conn_destroy(tc->t_cpath->cp_conn); Such an rds_connection would miss out the rds_conn_destroy() loop (that cancels all pending work) and (if it was scheduled after netns deletion) could trigger the use-after-free. A similar race-window exists for the module unload path in rds_tcp_exit -> rds_tcp_destroy_conns Concurrency with netns deletion (rds_tcp_kill_sock()) must be handled by checking check_net() before enqueuing new work or adding new connections. Concurrency with module-unload is handled by maintaining a module specific flag that is set at the start of the module exit function, and must be checked before enqueuing new work or adding new connections. This commit refactors existing RDS_DESTROY_PENDING checks added by commit 3db6e0d172c9 ("rds: use RCU to synchronize work-enqueue with connection teardown") and consolidates all the concurrency checks listed above into the function rds_destroy_pending(). Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-03 20:26:51 +08:00
bool (*t_unloading)(struct rds_connection *conn);
u8 (*get_tos_map)(u8 tos);
};
/* Bind hash table key length. It is the sum of the size of a struct
* in6_addr, a scope_id and a port.
*/
#define RDS_BOUND_KEY_LEN \
(sizeof(struct in6_addr) + sizeof(__u32) + sizeof(__be16))
struct rds_sock {
struct sock rs_sk;
u64 rs_user_addr;
u64 rs_user_bytes;
/*
* bound_addr used for both incoming and outgoing, no INADDR_ANY
* support.
*/
struct rhash_head rs_bound_node;
u8 rs_bound_key[RDS_BOUND_KEY_LEN];
struct sockaddr_in6 rs_bound_sin6;
#define rs_bound_addr rs_bound_sin6.sin6_addr
#define rs_bound_addr_v4 rs_bound_sin6.sin6_addr.s6_addr32[3]
#define rs_bound_port rs_bound_sin6.sin6_port
#define rs_bound_scope_id rs_bound_sin6.sin6_scope_id
struct in6_addr rs_conn_addr;
#define rs_conn_addr_v4 rs_conn_addr.s6_addr32[3]
__be16 rs_conn_port;
struct rds_transport *rs_transport;
/*
* rds_sendmsg caches the conn it used the last time around.
* This helps avoid costly lookups.
*/
struct rds_connection *rs_conn;
/* flag indicating we were congested or not */
int rs_congested;
/* seen congestion (ENOBUFS) when sending? */
int rs_seen_congestion;
/* rs_lock protects all these adjacent members before the newline */
spinlock_t rs_lock;
struct list_head rs_send_queue;
u32 rs_snd_bytes;
int rs_rcv_bytes;
struct list_head rs_notify_queue; /* currently used for failed RDMAs */
/* Congestion wake_up. If rs_cong_monitor is set, we use cong_mask
* to decide whether the application should be woken up.
* If not set, we use rs_cong_track to find out whether a cong map
* update arrived.
*/
uint64_t rs_cong_mask;
uint64_t rs_cong_notify;
struct list_head rs_cong_list;
unsigned long rs_cong_track;
/*
* rs_recv_lock protects the receive queue, and is
* used to serialize with rds_release.
*/
rwlock_t rs_recv_lock;
struct list_head rs_recv_queue;
/* just for stats reporting */
struct list_head rs_item;
/* these have their own lock */
spinlock_t rs_rdma_lock;
struct rb_root rs_rdma_keys;
/* Socket options - in case there will be more */
unsigned char rs_recverr,
rs_cong_monitor;
u32 rs_hash_initval;
/* Socket receive path trace points*/
u8 rs_rx_traces;
u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX];
struct rds_msg_zcopy_queue rs_zcookie_queue;
u8 rs_tos;
};
static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk)
{
return container_of(sk, struct rds_sock, rs_sk);
}
static inline struct sock *rds_rs_to_sk(struct rds_sock *rs)
{
return &rs->rs_sk;
}
/*
* The stack assigns sk_sndbuf and sk_rcvbuf to twice the specified value
* to account for overhead. We don't account for overhead, we just apply
* the number of payload bytes to the specified value.
*/
static inline int rds_sk_sndbuf(struct rds_sock *rs)
{
return rds_rs_to_sk(rs)->sk_sndbuf / 2;
}
static inline int rds_sk_rcvbuf(struct rds_sock *rs)
{
return rds_rs_to_sk(rs)->sk_rcvbuf / 2;
}
struct rds_statistics {
uint64_t s_conn_reset;
uint64_t s_recv_drop_bad_checksum;
uint64_t s_recv_drop_old_seq;
uint64_t s_recv_drop_no_sock;
uint64_t s_recv_drop_dead_sock;
uint64_t s_recv_deliver_raced;
uint64_t s_recv_delivered;
uint64_t s_recv_queued;
uint64_t s_recv_immediate_retry;
uint64_t s_recv_delayed_retry;
uint64_t s_recv_ack_required;
uint64_t s_recv_rdma_bytes;
uint64_t s_recv_ping;
uint64_t s_send_queue_empty;
uint64_t s_send_queue_full;
uint64_t s_send_lock_contention;
uint64_t s_send_lock_queue_raced;
uint64_t s_send_immediate_retry;
uint64_t s_send_delayed_retry;
uint64_t s_send_drop_acked;
uint64_t s_send_ack_required;
uint64_t s_send_queued;
uint64_t s_send_rdma;
uint64_t s_send_rdma_bytes;
uint64_t s_send_pong;
uint64_t s_page_remainder_hit;
uint64_t s_page_remainder_miss;
uint64_t s_copy_to_user;
uint64_t s_copy_from_user;
uint64_t s_cong_update_queued;
uint64_t s_cong_update_received;
uint64_t s_cong_send_error;
uint64_t s_cong_send_blocked;
uint64_t s_recv_bytes_added_to_socket;
uint64_t s_recv_bytes_removed_from_socket;
uint64_t s_send_stuck_rm;
};
/* af_rds.c */
void rds_sock_addref(struct rds_sock *rs);
void rds_sock_put(struct rds_sock *rs);
void rds_wake_sk_sleep(struct rds_sock *rs);
static inline void __rds_wake_sk_sleep(struct sock *sk)
{
wait_queue_head_t *waitq = sk_sleep(sk);
if (!sock_flag(sk, SOCK_DEAD) && waitq)
wake_up(waitq);
}
extern wait_queue_head_t rds_poll_waitq;
/* bind.c */
int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
void rds_remove_bound(struct rds_sock *rs);
struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
__u32 scope_id);
int rds_bind_lock_init(void);
void rds_bind_lock_destroy(void);
/* cong.c */
int rds_cong_get_maps(struct rds_connection *conn);
void rds_cong_add_conn(struct rds_connection *conn);
void rds_cong_remove_conn(struct rds_connection *conn);
void rds_cong_set_bit(struct rds_cong_map *map, __be16 port);
void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port);
int rds_cong_wait(struct rds_cong_map *map, __be16 port, int nonblock, struct rds_sock *rs);
void rds_cong_queue_updates(struct rds_cong_map *map);
void rds_cong_map_updated(struct rds_cong_map *map, uint64_t);
int rds_cong_updated_since(unsigned long *recent);
void rds_cong_add_socket(struct rds_sock *);
void rds_cong_remove_socket(struct rds_sock *);
void rds_cong_exit(void);
struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);
/* connection.c */
2016-11-17 05:29:49 +08:00
extern u32 rds_gen_num;
int rds_conn_init(void);
void rds_conn_exit(void);
struct rds_connection *rds_conn_create(struct net *net,
const struct in6_addr *laddr,
const struct in6_addr *faddr,
struct rds_transport *trans,
u8 tos, gfp_t gfp,
int dev_if);
struct rds_connection *rds_conn_create_outgoing(struct net *net,
const struct in6_addr *laddr,
const struct in6_addr *faddr,
struct rds_transport *trans,
u8 tos, gfp_t gfp, int dev_if);
void rds_conn_shutdown(struct rds_conn_path *cpath);
void rds_conn_destroy(struct rds_connection *conn);
void rds_conn_drop(struct rds_connection *conn);
void rds_conn_path_drop(struct rds_conn_path *cpath, bool destroy);
void rds_conn_connect_if_down(struct rds_connection *conn);
void rds_conn_path_connect_if_down(struct rds_conn_path *cp);
void rds_check_all_paths(struct rds_connection *conn);
void rds_for_each_conn_info(struct socket *sock, unsigned int len,
struct rds_info_iterator *iter,
struct rds_info_lengths *lens,
int (*visitor)(struct rds_connection *, void *),
u64 *buffer,
size_t item_len);
__printf(2, 3)
void __rds_conn_path_error(struct rds_conn_path *cp, const char *, ...);
#define rds_conn_path_error(cp, fmt...) \
__rds_conn_path_error(cp, KERN_WARNING "RDS: " fmt)
static inline int
rds_conn_path_transition(struct rds_conn_path *cp, int old, int new)
{
return atomic_cmpxchg(&cp->cp_state, old, new) == old;
}
static inline int
rds_conn_transition(struct rds_connection *conn, int old, int new)
{
WARN_ON(conn->c_trans->t_mp_capable);
return rds_conn_path_transition(&conn->c_path[0], old, new);
}
static inline int
rds_conn_path_state(struct rds_conn_path *cp)
{
return atomic_read(&cp->cp_state);
}
static inline int
rds_conn_state(struct rds_connection *conn)
{
WARN_ON(conn->c_trans->t_mp_capable);
return rds_conn_path_state(&conn->c_path[0]);
}
static inline int
rds_conn_path_up(struct rds_conn_path *cp)
{
return atomic_read(&cp->cp_state) == RDS_CONN_UP;
}
static inline int
rds_conn_path_down(struct rds_conn_path *cp)
{
return atomic_read(&cp->cp_state) == RDS_CONN_DOWN;
}
static inline int
rds_conn_up(struct rds_connection *conn)
{
WARN_ON(conn->c_trans->t_mp_capable);
return rds_conn_path_up(&conn->c_path[0]);
}
static inline int
rds_conn_path_connecting(struct rds_conn_path *cp)
{
return atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING;
}
static inline int
rds_conn_connecting(struct rds_connection *conn)
{
WARN_ON(conn->c_trans->t_mp_capable);
return rds_conn_path_connecting(&conn->c_path[0]);
}
/* message.c */
struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp);
struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents);
int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from,
bool zcopy);
struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len);
void rds_message_populate_header(struct rds_header *hdr, __be16 sport,
__be16 dport, u64 seq);
int rds_message_add_extension(struct rds_header *hdr,
unsigned int type, const void *data, unsigned int len);
int rds_message_next_extension(struct rds_header *hdr,
unsigned int *pos, void *buf, unsigned int *buflen);
int rds_message_add_rdma_dest_extension(struct rds_header *hdr, u32 r_key, u32 offset);
int rds_message_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
void rds_message_inc_free(struct rds_incoming *inc);
void rds_message_addref(struct rds_message *rm);
void rds_message_put(struct rds_message *rm);
void rds_message_wait(struct rds_message *rm);
void rds_message_unmapped(struct rds_message *rm);
void rds_notify_msg_zcopy_purge(struct rds_msg_zcopy_queue *info);
static inline void rds_message_make_checksum(struct rds_header *hdr)
{
hdr->h_csum = 0;
hdr->h_csum = ip_fast_csum((void *) hdr, sizeof(*hdr) >> 2);
}
static inline int rds_message_verify_checksum(const struct rds_header *hdr)
{
return !hdr->h_csum || ip_fast_csum((void *) hdr, sizeof(*hdr) >> 2) == 0;
}
/* page.c */
int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
gfp_t gfp);
void rds_page_exit(void);
/* recv.c */
void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
struct in6_addr *saddr);
void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn,
struct in6_addr *saddr);
void rds_inc_put(struct rds_incoming *inc);
void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
struct in6_addr *daddr,
struct rds_incoming *inc, gfp_t gfp);
int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int msg_flags);
void rds_clear_recv_queue(struct rds_sock *rs);
int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msg);
void rds_inc_info_copy(struct rds_incoming *inc,
struct rds_info_iterator *iter,
__be32 saddr, __be32 daddr, int flip);
void rds6_inc_info_copy(struct rds_incoming *inc,
struct rds_info_iterator *iter,
struct in6_addr *saddr, struct in6_addr *daddr,
int flip);
/* send.c */
int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
void rds_send_path_reset(struct rds_conn_path *conn);
int rds_send_xmit(struct rds_conn_path *cp);
struct sockaddr_in;
void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest);
typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack);
void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
is_acked_func is_acked);
void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack,
is_acked_func is_acked);
void rds_send_ping(struct rds_connection *conn, int cp_index);
int rds_send_pong(struct rds_conn_path *cp, __be16 dport);
/* rdma.c */
void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force);
int rds_get_mr(struct rds_sock *rs, sockptr_t optval, int optlen);
int rds_get_mr_for_dest(struct rds_sock *rs, sockptr_t optval, int optlen);
int rds_free_mr(struct rds_sock *rs, sockptr_t optval, int optlen);
void rds_rdma_drop_keys(struct rds_sock *rs);
net/rds: fix warn in rds_message_alloc_sgs redundant copy_from_user in rds_sendmsg system call expose rds to issue where rds_rdma_extra_size walk the rds iovec and and calculate the number pf pages (sgs) it need to add to the tail of rds message and later rds_cmsg_rdma_args copy the rds iovec again and re calculate the same number and get different result causing WARN_ON in rds_message_alloc_sgs. fix this by doing the copy_from_user only once per rds_sendmsg system call. When issue occur the below dump is seen: WARNING: CPU: 0 PID: 19789 at net/rds/message.c:316 rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 19789 Comm: syz-executor827 Not tainted 4.19.0-next-20181030+ #101 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x39d lib/dump_stack.c:113 panic+0x2ad/0x55c kernel/panic.c:188 __warn.cold.8+0x20/0x45 kernel/panic.c:540 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Code: c0 74 04 3c 03 7e 6c 44 01 ab 78 01 00 00 e8 2b 9e 35 fa 4c 89 e0 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 e8 14 9e 35 fa <0f> 0b 31 ff 44 89 ee e8 18 9f 35 fa 45 85 ed 75 1b e8 fe 9d 35 fa RSP: 0018:ffff8801c51b7460 EFLAGS: 00010293 RAX: ffff8801bc412080 RBX: ffff8801d7bf4040 RCX: ffffffff8749c9e6 RDX: 0000000000000000 RSI: ffffffff8749ca5c RDI: 0000000000000004 RBP: ffff8801c51b7490 R08: ffff8801bc412080 R09: ffffed003b5c5b67 R10: ffffed003b5c5b67 R11: ffff8801dae2db3b R12: 0000000000000000 R13: 000000000007165c R14: 000000000007165c R15: 0000000000000005 rds_cmsg_rdma_args+0x82d/0x1510 net/rds/rdma.c:623 rds_cmsg_send net/rds/send.c:971 [inline] rds_sendmsg+0x19a2/0x3180 net/rds/send.c:1273 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2117 __sys_sendmsg+0x11d/0x280 net/socket.c:2155 __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2162 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44a859 Code: e8 dc e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 6b cb fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1d4710ada8 EFLAGS: 00000297 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006dcc28 RCX: 000000000044a859 RDX: 0000000000000000 RSI: 0000000020001600 RDI: 0000000000000003 RBP: 00000000006dcc20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000297 R12: 00000000006dcc2c R13: 646e732f7665642f R14: 00007f1d4710b9c0 R15: 00000000006dcd2c Kernel Offset: disabled Rebooting in 86400 seconds.. Reported-by: syzbot+26de17458aeda9d305d8@syzkaller.appspotmail.com Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: shamir rabinovitch <shamir.rabinovitch@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-16 15:01:08 +08:00
int rds_rdma_extra_size(struct rds_rdma_args *args,
struct rds_iov_vector *iov);
int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm,
struct cmsghdr *cmsg);
int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
net/rds: fix warn in rds_message_alloc_sgs redundant copy_from_user in rds_sendmsg system call expose rds to issue where rds_rdma_extra_size walk the rds iovec and and calculate the number pf pages (sgs) it need to add to the tail of rds message and later rds_cmsg_rdma_args copy the rds iovec again and re calculate the same number and get different result causing WARN_ON in rds_message_alloc_sgs. fix this by doing the copy_from_user only once per rds_sendmsg system call. When issue occur the below dump is seen: WARNING: CPU: 0 PID: 19789 at net/rds/message.c:316 rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 19789 Comm: syz-executor827 Not tainted 4.19.0-next-20181030+ #101 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x39d lib/dump_stack.c:113 panic+0x2ad/0x55c kernel/panic.c:188 __warn.cold.8+0x20/0x45 kernel/panic.c:540 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:rds_message_alloc_sgs+0x10c/0x160 net/rds/message.c:316 Code: c0 74 04 3c 03 7e 6c 44 01 ab 78 01 00 00 e8 2b 9e 35 fa 4c 89 e0 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d c3 e8 14 9e 35 fa <0f> 0b 31 ff 44 89 ee e8 18 9f 35 fa 45 85 ed 75 1b e8 fe 9d 35 fa RSP: 0018:ffff8801c51b7460 EFLAGS: 00010293 RAX: ffff8801bc412080 RBX: ffff8801d7bf4040 RCX: ffffffff8749c9e6 RDX: 0000000000000000 RSI: ffffffff8749ca5c RDI: 0000000000000004 RBP: ffff8801c51b7490 R08: ffff8801bc412080 R09: ffffed003b5c5b67 R10: ffffed003b5c5b67 R11: ffff8801dae2db3b R12: 0000000000000000 R13: 000000000007165c R14: 000000000007165c R15: 0000000000000005 rds_cmsg_rdma_args+0x82d/0x1510 net/rds/rdma.c:623 rds_cmsg_send net/rds/send.c:971 [inline] rds_sendmsg+0x19a2/0x3180 net/rds/send.c:1273 sock_sendmsg_nosec net/socket.c:622 [inline] sock_sendmsg+0xd5/0x120 net/socket.c:632 ___sys_sendmsg+0x7fd/0x930 net/socket.c:2117 __sys_sendmsg+0x11d/0x280 net/socket.c:2155 __do_sys_sendmsg net/socket.c:2164 [inline] __se_sys_sendmsg net/socket.c:2162 [inline] __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2162 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x44a859 Code: e8 dc e6 ff ff 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 6b cb fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f1d4710ada8 EFLAGS: 00000297 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000006dcc28 RCX: 000000000044a859 RDX: 0000000000000000 RSI: 0000000020001600 RDI: 0000000000000003 RBP: 00000000006dcc20 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000297 R12: 00000000006dcc2c R13: 646e732f7665642f R14: 00007f1d4710b9c0 R15: 00000000006dcd2c Kernel Offset: disabled Rebooting in 86400 seconds.. Reported-by: syzbot+26de17458aeda9d305d8@syzkaller.appspotmail.com Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: shamir rabinovitch <shamir.rabinovitch@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-12-16 15:01:08 +08:00
struct cmsghdr *cmsg,
struct rds_iov_vector *vec);
int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm,
struct cmsghdr *cmsg);
void rds_rdma_free_op(struct rm_rdma_op *ro);
void rds_atomic_free_op(struct rm_atomic_op *ao);
void rds_rdma_send_complete(struct rds_message *rm, int wc_status);
void rds_atomic_send_complete(struct rds_message *rm, int wc_status);
int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm,
struct cmsghdr *cmsg);
void __rds_put_mr_final(struct kref *kref);
rds: tcp: use rds_destroy_pending() to synchronize netns/module teardown and rds connection/workq management An rds_connection can get added during netns deletion between lines 528 and 529 of 506 static void rds_tcp_kill_sock(struct net *net) : /* code to pull out all the rds_connections that should be destroyed */ : 528 spin_unlock_irq(&rds_tcp_conn_lock); 529 list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) 530 rds_conn_destroy(tc->t_cpath->cp_conn); Such an rds_connection would miss out the rds_conn_destroy() loop (that cancels all pending work) and (if it was scheduled after netns deletion) could trigger the use-after-free. A similar race-window exists for the module unload path in rds_tcp_exit -> rds_tcp_destroy_conns Concurrency with netns deletion (rds_tcp_kill_sock()) must be handled by checking check_net() before enqueuing new work or adding new connections. Concurrency with module-unload is handled by maintaining a module specific flag that is set at the start of the module exit function, and must be checked before enqueuing new work or adding new connections. This commit refactors existing RDS_DESTROY_PENDING checks added by commit 3db6e0d172c9 ("rds: use RCU to synchronize work-enqueue with connection teardown") and consolidates all the concurrency checks listed above into the function rds_destroy_pending(). Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-03 20:26:51 +08:00
static inline bool rds_destroy_pending(struct rds_connection *conn)
{
return !check_net(rds_conn_net(conn)) ||
(conn->c_trans->t_unloading && conn->c_trans->t_unloading(conn));
}
enum {
ODP_NOT_NEEDED,
ODP_ZEROBASED,
ODP_VIRTUAL
};
/* stats.c */
DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats);
#define rds_stats_inc_which(which, member) do { \
per_cpu(which, get_cpu()).member++; \
put_cpu(); \
} while (0)
#define rds_stats_inc(member) rds_stats_inc_which(rds_stats, member)
#define rds_stats_add_which(which, member, count) do { \
per_cpu(which, get_cpu()).member += count; \
put_cpu(); \
} while (0)
#define rds_stats_add(member, count) rds_stats_add_which(rds_stats, member, count)
int rds_stats_init(void);
void rds_stats_exit(void);
void rds_stats_info_copy(struct rds_info_iterator *iter,
uint64_t *values, const char *const *names,
size_t nr);
/* sysctl.c */
int rds_sysctl_init(void);
void rds_sysctl_exit(void);
extern unsigned long rds_sysctl_sndbuf_min;
extern unsigned long rds_sysctl_sndbuf_default;
extern unsigned long rds_sysctl_sndbuf_max;
extern unsigned long rds_sysctl_reconnect_min_jiffies;
extern unsigned long rds_sysctl_reconnect_max_jiffies;
extern unsigned int rds_sysctl_max_unacked_packets;
extern unsigned int rds_sysctl_max_unacked_bytes;
extern unsigned int rds_sysctl_ping_enable;
extern unsigned long rds_sysctl_trace_flags;
extern unsigned int rds_sysctl_trace_level;
/* threads.c */
int rds_threads_init(void);
void rds_threads_exit(void);
extern struct workqueue_struct *rds_wq;
void rds_queue_reconnect(struct rds_conn_path *cp);
void rds_connect_worker(struct work_struct *);
void rds_shutdown_worker(struct work_struct *);
void rds_send_worker(struct work_struct *);
void rds_recv_worker(struct work_struct *);
void rds_connect_path_complete(struct rds_conn_path *conn, int curr);
void rds_connect_complete(struct rds_connection *conn);
int rds_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2);
/* transport.c */
void rds_trans_register(struct rds_transport *trans);
void rds_trans_unregister(struct rds_transport *trans);
struct rds_transport *rds_trans_get_preferred(struct net *net,
const struct in6_addr *addr,
__u32 scope_id);
void rds_trans_put(struct rds_transport *trans);
unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
unsigned int avail);
struct rds_transport *rds_trans_get(int t_type);
int rds_trans_init(void);
void rds_trans_exit(void);
#endif