linux/include/trace/events/sunrpc.h

844 lines
21 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 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM sunrpc
#if !defined(_TRACE_SUNRPC_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_SUNRPC_H
#include <linux/sunrpc/sched.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/sunrpc/svc_xprt.h>
#include <net/tcp_states.h>
#include <linux/net.h>
#include <linux/tracepoint.h>
DECLARE_EVENT_CLASS(rpc_task_status,
TP_PROTO(struct rpc_task *task),
TP_ARGS(task),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(int, status)
),
TP_fast_assign(
__entry->task_id = task->tk_pid;
__entry->client_id = task->tk_client->cl_clid;
__entry->status = task->tk_status;
),
TP_printk("task:%u@%u status=%d",
__entry->task_id, __entry->client_id,
__entry->status)
);
DEFINE_EVENT(rpc_task_status, rpc_call_status,
TP_PROTO(struct rpc_task *task),
TP_ARGS(task)
);
DEFINE_EVENT(rpc_task_status, rpc_bind_status,
TP_PROTO(struct rpc_task *task),
TP_ARGS(task)
);
TRACE_EVENT(rpc_connect_status,
TP_PROTO(const struct rpc_task *task),
TP_ARGS(task),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(int, status)
),
TP_fast_assign(
__entry->task_id = task->tk_pid;
__entry->client_id = task->tk_client->cl_clid;
__entry->status = task->tk_status;
),
TP_printk("task:%u@%u status=%d",
__entry->task_id, __entry->client_id,
__entry->status)
);
TRACE_EVENT(rpc_request,
TP_PROTO(const struct rpc_task *task),
TP_ARGS(task),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(int, version)
__field(bool, async)
__string(progname, task->tk_client->cl_program->name)
__string(procname, rpc_proc_name(task))
),
TP_fast_assign(
__entry->task_id = task->tk_pid;
__entry->client_id = task->tk_client->cl_clid;
__entry->version = task->tk_client->cl_vers;
__entry->async = RPC_IS_ASYNC(task);
__assign_str(progname, task->tk_client->cl_program->name)
__assign_str(procname, rpc_proc_name(task))
),
TP_printk("task:%u@%u %sv%d %s (%ssync)",
__entry->task_id, __entry->client_id,
__get_str(progname), __entry->version,
__get_str(procname), __entry->async ? "a": ""
)
);
DECLARE_EVENT_CLASS(rpc_task_running,
TP_PROTO(const struct rpc_task *task, const void *action),
TP_ARGS(task, action),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(const void *, action)
__field(unsigned long, runstate)
__field(int, status)
__field(unsigned short, flags)
),
TP_fast_assign(
__entry->client_id = task->tk_client ?
task->tk_client->cl_clid : -1;
__entry->task_id = task->tk_pid;
__entry->action = action;
__entry->runstate = task->tk_runstate;
__entry->status = task->tk_status;
__entry->flags = task->tk_flags;
),
SUNRPC: Fix oops when trace sunrpc_task events in nfs client When tracking sunrpc_task events in nfs client, the clnt pointer may be NULL. [ 139.269266] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [ 139.269915] IP: [<ffffffffa026f216>] ftrace_raw_event_rpc_task_running+0x86/0xf0 [sunrpc] [ 139.269915] PGD 1d293067 PUD 1d294067 PMD 0 [ 139.269915] Oops: 0000 [#1] SMP [ 139.269915] Modules linked in: nfsv4 dns_resolver nfs lockd sunrpc fscache sg ppdev e1000 serio_raw pcspkr parport_pc parport i2c_piix4 i2c_core microcode xfs libcrc32c sd_mod sr_mod cdrom ata_generic crc_t10dif crct10dif_common pata_acpi ahci libahci ata_piix libata dm_mirror dm_region_hash dm_log dm_mod [ 139.269915] CPU: 0 PID: 59 Comm: kworker/0:2 Not tainted 3.10.0-84.el7.x86_64 #1 [ 139.269915] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 139.269915] Workqueue: rpciod rpc_async_schedule [sunrpc] [ 139.269915] task: ffff88001b598000 ti: ffff88001b632000 task.ti: ffff88001b632000 [ 139.269915] RIP: 0010:[<ffffffffa026f216>] [<ffffffffa026f216>] ftrace_raw_event_rpc_task_running+0x86/0xf0 [sunrpc] [ 139.269915] RSP: 0018:ffff88001b633d70 EFLAGS: 00010206 [ 139.269915] RAX: ffff88001dfc5338 RBX: ffff88001cc37a00 RCX: ffff88001dfc5334 [ 139.269915] RDX: ffff88001dfc5338 RSI: 0000000000000000 RDI: ffff88001dfc533c [ 139.269915] RBP: ffff88001b633db0 R08: 000000000000002c R09: 000000000000000a [ 139.269915] R10: 0000000000062180 R11: 00000020759fb9dc R12: ffffffffa0292c20 [ 139.269915] R13: ffff88001dfc5334 R14: 0000000000000000 R15: 0000000000000000 [ 139.269915] FS: 0000000000000000(0000) GS:ffff88001fc00000(0000) knlGS:0000000000000000 [ 139.269915] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 139.269915] CR2: 0000000000000004 CR3: 000000001d290000 CR4: 00000000000006f0 [ 139.269915] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 139.269915] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 139.269915] Stack: [ 139.269915] 000000001b633d98 0000000000000246 ffff88001df1dc00 ffff88001cc37a00 [ 139.269915] ffff88001bc35e60 0000000000000000 ffff88001ffa0a48 ffff88001bc35ee0 [ 139.269915] ffff88001b633e08 ffffffffa02704b5 0000000000010000 ffff88001cc37a70 [ 139.269915] Call Trace: [ 139.269915] [<ffffffffa02704b5>] __rpc_execute+0x1d5/0x400 [sunrpc] [ 139.269915] [<ffffffffa0270706>] rpc_async_schedule+0x26/0x30 [sunrpc] [ 139.269915] [<ffffffff8107867b>] process_one_work+0x17b/0x460 [ 139.269915] [<ffffffff8107942b>] worker_thread+0x11b/0x400 [ 139.269915] [<ffffffff81079310>] ? rescuer_thread+0x3e0/0x3e0 [ 139.269915] [<ffffffff8107fc80>] kthread+0xc0/0xd0 [ 139.269915] [<ffffffff8107fbc0>] ? kthread_create_on_node+0x110/0x110 [ 139.269915] [<ffffffff815d122c>] ret_from_fork+0x7c/0xb0 [ 139.269915] [<ffffffff8107fbc0>] ? kthread_create_on_node+0x110/0x110 [ 139.269915] Code: 4c 8b 45 c8 48 8d 7d d0 89 4d c4 41 89 c9 b9 28 00 00 00 e8 9d b4 e9 e0 48 85 c0 49 89 c5 74 a2 48 89 c7 e8 9d 3f e9 e0 48 89 c2 <41> 8b 46 04 48 8b 7d d0 4c 89 e9 4c 89 e6 89 42 0c 0f b7 83 d4 [ 139.269915] RIP [<ffffffffa026f216>] ftrace_raw_event_rpc_task_running+0x86/0xf0 [sunrpc] [ 139.269915] RSP <ffff88001b633d70> [ 139.269915] CR2: 0000000000000004 [ 140.946406] ---[ end trace ba486328b98d7622 ]--- Signed-off-by: Ditang Chen <chendt.fnst@cn.fujitsu.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-03-07 13:27:57 +08:00
TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d action=%pf",
__entry->task_id, __entry->client_id,
__entry->flags,
__entry->runstate,
__entry->status,
__entry->action
)
);
DEFINE_EVENT(rpc_task_running, rpc_task_begin,
TP_PROTO(const struct rpc_task *task, const void *action),
TP_ARGS(task, action)
);
DEFINE_EVENT(rpc_task_running, rpc_task_run_action,
TP_PROTO(const struct rpc_task *task, const void *action),
TP_ARGS(task, action)
);
DEFINE_EVENT(rpc_task_running, rpc_task_complete,
TP_PROTO(const struct rpc_task *task, const void *action),
TP_ARGS(task, action)
);
DECLARE_EVENT_CLASS(rpc_task_queued,
TP_PROTO(const struct rpc_task *task, const struct rpc_wait_queue *q),
TP_ARGS(task, q),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(unsigned long, timeout)
__field(unsigned long, runstate)
__field(int, status)
__field(unsigned short, flags)
__string(q_name, rpc_qname(q))
),
TP_fast_assign(
__entry->client_id = task->tk_client ?
task->tk_client->cl_clid : -1;
__entry->task_id = task->tk_pid;
__entry->timeout = task->tk_timeout;
__entry->runstate = task->tk_runstate;
__entry->status = task->tk_status;
__entry->flags = task->tk_flags;
__assign_str(q_name, rpc_qname(q));
),
TP_printk("task:%u@%d flags=%4.4x state=%4.4lx status=%d timeout=%lu queue=%s",
__entry->task_id, __entry->client_id,
__entry->flags,
__entry->runstate,
__entry->status,
__entry->timeout,
__get_str(q_name)
)
);
DEFINE_EVENT(rpc_task_queued, rpc_task_sleep,
TP_PROTO(const struct rpc_task *task, const struct rpc_wait_queue *q),
TP_ARGS(task, q)
);
DEFINE_EVENT(rpc_task_queued, rpc_task_wakeup,
TP_PROTO(const struct rpc_task *task, const struct rpc_wait_queue *q),
TP_ARGS(task, q)
);
TRACE_EVENT(rpc_stats_latency,
TP_PROTO(
const struct rpc_task *task,
ktime_t backlog,
ktime_t rtt,
ktime_t execute
),
TP_ARGS(task, backlog, rtt, execute),
TP_STRUCT__entry(
__field(unsigned int, task_id)
__field(unsigned int, client_id)
__field(u32, xid)
__field(int, version)
__string(progname, task->tk_client->cl_program->name)
__string(procname, rpc_proc_name(task))
__field(unsigned long, backlog)
__field(unsigned long, rtt)
__field(unsigned long, execute)
),
TP_fast_assign(
__entry->client_id = task->tk_client->cl_clid;
__entry->task_id = task->tk_pid;
__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
__entry->version = task->tk_client->cl_vers;
__assign_str(progname, task->tk_client->cl_program->name)
__assign_str(procname, rpc_proc_name(task))
__entry->backlog = ktime_to_us(backlog);
__entry->rtt = ktime_to_us(rtt);
__entry->execute = ktime_to_us(execute);
),
TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu",
__entry->task_id, __entry->client_id, __entry->xid,
__get_str(progname), __entry->version, __get_str(procname),
__entry->backlog, __entry->rtt, __entry->execute)
);
/*
* First define the enums in the below macros to be exported to userspace
* via TRACE_DEFINE_ENUM().
*/
#undef EM
#undef EMe
#define EM(a, b) TRACE_DEFINE_ENUM(a);
#define EMe(a, b) TRACE_DEFINE_ENUM(a);
#define RPC_SHOW_SOCKET \
EM( SS_FREE, "FREE" ) \
EM( SS_UNCONNECTED, "UNCONNECTED" ) \
EM( SS_CONNECTING, "CONNECTING," ) \
EM( SS_CONNECTED, "CONNECTED," ) \
EMe(SS_DISCONNECTING, "DISCONNECTING" )
#define rpc_show_socket_state(state) \
__print_symbolic(state, RPC_SHOW_SOCKET)
RPC_SHOW_SOCKET
#define RPC_SHOW_SOCK \
EM( TCP_ESTABLISHED, "ESTABLISHED" ) \
EM( TCP_SYN_SENT, "SYN_SENT" ) \
EM( TCP_SYN_RECV, "SYN_RECV" ) \
EM( TCP_FIN_WAIT1, "FIN_WAIT1" ) \
EM( TCP_FIN_WAIT2, "FIN_WAIT2" ) \
EM( TCP_TIME_WAIT, "TIME_WAIT" ) \
EM( TCP_CLOSE, "CLOSE" ) \
EM( TCP_CLOSE_WAIT, "CLOSE_WAIT" ) \
EM( TCP_LAST_ACK, "LAST_ACK" ) \
EM( TCP_LISTEN, "LISTEN" ) \
EMe( TCP_CLOSING, "CLOSING" )
#define rpc_show_sock_state(state) \
__print_symbolic(state, RPC_SHOW_SOCK)
RPC_SHOW_SOCK
/*
* Now redefine the EM() and EMe() macros to map the enums to the strings
* that will be printed in the output.
*/
#undef EM
#undef EMe
#define EM(a, b) {a, b},
#define EMe(a, b) {a, b}
DECLARE_EVENT_CLASS(xs_socket_event,
TP_PROTO(
struct rpc_xprt *xprt,
struct socket *socket
),
TP_ARGS(xprt, socket),
TP_STRUCT__entry(
__field(unsigned int, socket_state)
__field(unsigned int, sock_state)
__field(unsigned long long, ino)
__string(dstaddr,
xprt->address_strings[RPC_DISPLAY_ADDR])
__string(dstport,
xprt->address_strings[RPC_DISPLAY_PORT])
),
TP_fast_assign(
struct inode *inode = SOCK_INODE(socket);
__entry->socket_state = socket->state;
__entry->sock_state = socket->sk->sk_state;
__entry->ino = (unsigned long long)inode->i_ino;
__assign_str(dstaddr,
xprt->address_strings[RPC_DISPLAY_ADDR]);
__assign_str(dstport,
xprt->address_strings[RPC_DISPLAY_PORT]);
),
TP_printk(
"socket:[%llu] dstaddr=%s/%s "
"state=%u (%s) sk_state=%u (%s)",
__entry->ino, __get_str(dstaddr), __get_str(dstport),
__entry->socket_state,
rpc_show_socket_state(__entry->socket_state),
__entry->sock_state,
rpc_show_sock_state(__entry->sock_state)
)
);
#define DEFINE_RPC_SOCKET_EVENT(name) \
DEFINE_EVENT(xs_socket_event, name, \
TP_PROTO( \
struct rpc_xprt *xprt, \
struct socket *socket \
), \
TP_ARGS(xprt, socket))
DECLARE_EVENT_CLASS(xs_socket_event_done,
TP_PROTO(
struct rpc_xprt *xprt,
struct socket *socket,
int error
),
TP_ARGS(xprt, socket, error),
TP_STRUCT__entry(
__field(int, error)
__field(unsigned int, socket_state)
__field(unsigned int, sock_state)
__field(unsigned long long, ino)
__string(dstaddr,
xprt->address_strings[RPC_DISPLAY_ADDR])
__string(dstport,
xprt->address_strings[RPC_DISPLAY_PORT])
),
TP_fast_assign(
struct inode *inode = SOCK_INODE(socket);
__entry->socket_state = socket->state;
__entry->sock_state = socket->sk->sk_state;
__entry->ino = (unsigned long long)inode->i_ino;
__entry->error = error;
__assign_str(dstaddr,
xprt->address_strings[RPC_DISPLAY_ADDR]);
__assign_str(dstport,
xprt->address_strings[RPC_DISPLAY_PORT]);
),
TP_printk(
"error=%d socket:[%llu] dstaddr=%s/%s "
"state=%u (%s) sk_state=%u (%s)",
__entry->error,
__entry->ino, __get_str(dstaddr), __get_str(dstport),
__entry->socket_state,
rpc_show_socket_state(__entry->socket_state),
__entry->sock_state,
rpc_show_sock_state(__entry->sock_state)
)
);
#define DEFINE_RPC_SOCKET_EVENT_DONE(name) \
DEFINE_EVENT(xs_socket_event_done, name, \
TP_PROTO( \
struct rpc_xprt *xprt, \
struct socket *socket, \
int error \
), \
TP_ARGS(xprt, socket, error))
DEFINE_RPC_SOCKET_EVENT(rpc_socket_state_change);
DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_connect);
DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_error);
DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection);
DEFINE_RPC_SOCKET_EVENT(rpc_socket_close);
DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown);
DECLARE_EVENT_CLASS(rpc_xprt_event,
TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
TP_ARGS(xprt, xid, status),
TP_STRUCT__entry(
__field(u32, xid)
__field(int, status)
__string(addr, xprt->address_strings[RPC_DISPLAY_ADDR])
__string(port, xprt->address_strings[RPC_DISPLAY_PORT])
),
TP_fast_assign(
__entry->xid = be32_to_cpu(xid);
__entry->status = status;
__assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]);
__assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]);
),
TP_printk("peer=[%s]:%s xid=0x%08x status=%d", __get_str(addr),
__get_str(port), __entry->xid,
__entry->status)
);
DEFINE_EVENT(rpc_xprt_event, xprt_timer,
TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
TP_ARGS(xprt, xid, status));
DEFINE_EVENT(rpc_xprt_event, xprt_lookup_rqst,
TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
TP_ARGS(xprt, xid, status));
DEFINE_EVENT(rpc_xprt_event, xprt_transmit,
TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
TP_ARGS(xprt, xid, status));
DEFINE_EVENT(rpc_xprt_event, xprt_complete_rqst,
TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status),
TP_ARGS(xprt, xid, status));
TRACE_EVENT(xprt_ping,
TP_PROTO(const struct rpc_xprt *xprt, int status),
TP_ARGS(xprt, status),
TP_STRUCT__entry(
__field(int, status)
__string(addr, xprt->address_strings[RPC_DISPLAY_ADDR])
__string(port, xprt->address_strings[RPC_DISPLAY_PORT])
),
TP_fast_assign(
__entry->status = status;
__assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]);
__assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]);
),
TP_printk("peer=[%s]:%s status=%d",
__get_str(addr), __get_str(port), __entry->status)
);
TRACE_EVENT(xs_tcp_data_ready,
TP_PROTO(struct rpc_xprt *xprt, int err, unsigned int total),
TP_ARGS(xprt, err, total),
TP_STRUCT__entry(
__field(int, err)
__field(unsigned int, total)
__string(addr, xprt ? xprt->address_strings[RPC_DISPLAY_ADDR] :
"(null)")
__string(port, xprt ? xprt->address_strings[RPC_DISPLAY_PORT] :
"(null)")
),
TP_fast_assign(
__entry->err = err;
__entry->total = total;
__assign_str(addr, xprt ?
xprt->address_strings[RPC_DISPLAY_ADDR] : "(null)");
__assign_str(port, xprt ?
xprt->address_strings[RPC_DISPLAY_PORT] : "(null)");
),
TP_printk("peer=[%s]:%s err=%d total=%u", __get_str(addr),
__get_str(port), __entry->err, __entry->total)
);
#define rpc_show_sock_xprt_flags(flags) \
__print_flags(flags, "|", \
{ TCP_RCV_LAST_FRAG, "TCP_RCV_LAST_FRAG" }, \
{ TCP_RCV_COPY_FRAGHDR, "TCP_RCV_COPY_FRAGHDR" }, \
{ TCP_RCV_COPY_XID, "TCP_RCV_COPY_XID" }, \
{ TCP_RCV_COPY_DATA, "TCP_RCV_COPY_DATA" }, \
{ TCP_RCV_READ_CALLDIR, "TCP_RCV_READ_CALLDIR" }, \
{ TCP_RCV_COPY_CALLDIR, "TCP_RCV_COPY_CALLDIR" }, \
{ TCP_RPC_REPLY, "TCP_RPC_REPLY" })
TRACE_EVENT(xs_tcp_data_recv,
TP_PROTO(struct sock_xprt *xs),
TP_ARGS(xs),
TP_STRUCT__entry(
__string(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR])
__string(port, xs->xprt.address_strings[RPC_DISPLAY_PORT])
__field(u32, xid)
__field(unsigned long, flags)
__field(unsigned long, copied)
__field(unsigned int, reclen)
__field(unsigned long, offset)
),
TP_fast_assign(
__assign_str(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]);
__assign_str(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]);
__entry->xid = be32_to_cpu(xs->tcp_xid);
__entry->flags = xs->tcp_flags;
__entry->copied = xs->tcp_copied;
__entry->reclen = xs->tcp_reclen;
__entry->offset = xs->tcp_offset;
),
TP_printk("peer=[%s]:%s xid=0x%08x flags=%s copied=%lu reclen=%u offset=%lu",
__get_str(addr), __get_str(port), __entry->xid,
rpc_show_sock_xprt_flags(__entry->flags),
__entry->copied, __entry->reclen, __entry->offset)
);
#define show_rqstp_flags(flags) \
__print_flags(flags, "|", \
{ (1UL << RQ_SECURE), "RQ_SECURE"}, \
{ (1UL << RQ_LOCAL), "RQ_LOCAL"}, \
{ (1UL << RQ_USEDEFERRAL), "RQ_USEDEFERRAL"}, \
{ (1UL << RQ_DROPME), "RQ_DROPME"}, \
{ (1UL << RQ_SPLICE_OK), "RQ_SPLICE_OK"}, \
sunrpc: convert to lockless lookup of queued server threads Testing has shown that the pool->sp_lock can be a bottleneck on a busy server. Every time data is received on a socket, the server must take that lock in order to dequeue a thread from the sp_threads list. Address this problem by eliminating the sp_threads list (which contains threads that are currently idle) and replacing it with a RQ_BUSY flag in svc_rqst. This allows us to walk the sp_all_threads list under the rcu_read_lock and find a suitable thread for the xprt by doing a test_and_set_bit. Note that we do still have a potential atomicity problem however with this approach. We don't want svc_xprt_do_enqueue to set the rqst->rq_xprt pointer unless a test_and_set_bit of RQ_BUSY returned zero (which indicates that the thread was idle). But, by the time we check that, the bit could be flipped by a waking thread. To address this, we acquire a new per-rqst spinlock (rq_lock) and take that before doing the test_and_set_bit. If that returns false, then we can set rq_xprt and drop the spinlock. Then, when the thread wakes up, it must set the bit under the same spinlock and can trust that if it was already set then the rq_xprt is also properly set. With this scheme, the case where we have an idle thread no longer needs to take the highly contended pool->sp_lock at all, and that removes the bottleneck. That still leaves one issue: What of the case where we walk the whole sp_all_threads list and don't find an idle thread? Because the search is lockess, it's possible for the queueing to race with a thread that is going to sleep. To address that, we queue the xprt and then search again. If we find an idle thread at that point, we can't attach the xprt to it directly since that might race with a different thread waking up and finding it. All we can do is wake the idle thread back up and let it attempt to find the now-queued xprt. Signed-off-by: Jeff Layton <jlayton@primarydata.com> Tested-by: Chris Worley <chris.worley@primarydata.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2014-11-22 03:19:30 +08:00
{ (1UL << RQ_VICTIM), "RQ_VICTIM"}, \
{ (1UL << RQ_BUSY), "RQ_BUSY"})
TRACE_EVENT(svc_recv,
TP_PROTO(struct svc_rqst *rqst, int len),
TP_ARGS(rqst, len),
TP_STRUCT__entry(
__field(u32, xid)
__field(int, len)
__field(unsigned long, flags)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->len = len;
__entry->flags = rqst->rq_flags;
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x len=%d flags=%s",
__get_str(addr), __entry->xid, __entry->len,
show_rqstp_flags(__entry->flags))
);
TRACE_EVENT(svc_process,
TP_PROTO(const struct svc_rqst *rqst, const char *name),
TP_ARGS(rqst, name),
TP_STRUCT__entry(
__field(u32, xid)
__field(u32, vers)
__field(u32, proc)
__string(service, name)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->vers = rqst->rq_vers;
__entry->proc = rqst->rq_proc;
__assign_str(service, name);
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u",
__get_str(addr), __entry->xid,
__get_str(service), __entry->vers, __entry->proc)
);
DECLARE_EVENT_CLASS(svc_rqst_event,
TP_PROTO(struct svc_rqst *rqst),
TP_ARGS(rqst),
TP_STRUCT__entry(
__field(u32, xid)
__field(unsigned long, flags)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->flags = rqst->rq_flags;
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x flags=%s",
__get_str(addr), __entry->xid,
show_rqstp_flags(__entry->flags))
);
DEFINE_EVENT(svc_rqst_event, svc_defer,
TP_PROTO(struct svc_rqst *rqst),
TP_ARGS(rqst));
DEFINE_EVENT(svc_rqst_event, svc_drop,
TP_PROTO(struct svc_rqst *rqst),
TP_ARGS(rqst));
DECLARE_EVENT_CLASS(svc_rqst_status,
TP_PROTO(struct svc_rqst *rqst, int status),
TP_ARGS(rqst, status),
TP_STRUCT__entry(
__field(u32, xid)
__field(int, status)
__field(unsigned long, flags)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->status = status;
__entry->flags = rqst->rq_flags;
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x status=%d flags=%s",
__get_str(addr), __entry->xid,
__entry->status, show_rqstp_flags(__entry->flags))
);
DEFINE_EVENT(svc_rqst_status, svc_send,
TP_PROTO(struct svc_rqst *rqst, int status),
TP_ARGS(rqst, status));
#define show_svc_xprt_flags(flags) \
__print_flags(flags, "|", \
{ (1UL << XPT_BUSY), "XPT_BUSY"}, \
{ (1UL << XPT_CONN), "XPT_CONN"}, \
{ (1UL << XPT_CLOSE), "XPT_CLOSE"}, \
{ (1UL << XPT_DATA), "XPT_DATA"}, \
{ (1UL << XPT_TEMP), "XPT_TEMP"}, \
{ (1UL << XPT_DEAD), "XPT_DEAD"}, \
{ (1UL << XPT_CHNGBUF), "XPT_CHNGBUF"}, \
{ (1UL << XPT_DEFERRED), "XPT_DEFERRED"}, \
{ (1UL << XPT_OLD), "XPT_OLD"}, \
{ (1UL << XPT_LISTENER), "XPT_LISTENER"}, \
{ (1UL << XPT_CACHE_AUTH), "XPT_CACHE_AUTH"}, \
{ (1UL << XPT_LOCAL), "XPT_LOCAL"}, \
{ (1UL << XPT_KILL_TEMP), "XPT_KILL_TEMP"}, \
{ (1UL << XPT_CONG_CTRL), "XPT_CONG_CTRL"})
TRACE_EVENT(svc_xprt_do_enqueue,
TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst),
TP_ARGS(xprt, rqst),
TP_STRUCT__entry(
__field(struct svc_xprt *, xprt)
__field(int, pid)
__field(unsigned long, flags)
__string(addr, xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xprt = xprt;
__entry->pid = rqst? rqst->rq_task->pid : 0;
__entry->flags = xprt->xpt_flags;
__assign_str(addr, xprt->xpt_remotebuf);
),
TP_printk("xprt=%p addr=%s pid=%d flags=%s",
__entry->xprt, __get_str(addr),
__entry->pid, show_svc_xprt_flags(__entry->flags))
);
DECLARE_EVENT_CLASS(svc_xprt_event,
TP_PROTO(struct svc_xprt *xprt),
TP_ARGS(xprt),
TP_STRUCT__entry(
__field(struct svc_xprt *, xprt)
__field(unsigned long, flags)
__string(addr, xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xprt = xprt;
__entry->flags = xprt->xpt_flags;
__assign_str(addr, xprt->xpt_remotebuf);
),
TP_printk("xprt=%p addr=%s flags=%s",
__entry->xprt, __get_str(addr),
show_svc_xprt_flags(__entry->flags))
);
DEFINE_EVENT(svc_xprt_event, svc_xprt_no_write_space,
TP_PROTO(struct svc_xprt *xprt),
TP_ARGS(xprt));
TRACE_EVENT(svc_xprt_dequeue,
TP_PROTO(struct svc_rqst *rqst),
TP_ARGS(rqst),
TP_STRUCT__entry(
__field(struct svc_xprt *, xprt)
__field(unsigned long, flags)
__field(unsigned long, wakeup)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xprt = rqst->rq_xprt;
__entry->flags = rqst->rq_xprt->xpt_flags;
__entry->wakeup = ktime_to_us(ktime_sub(ktime_get(),
rqst->rq_qtime));
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("xprt=%p addr=%s flags=%s wakeup-us=%lu",
__entry->xprt, __get_str(addr),
show_svc_xprt_flags(__entry->flags),
__entry->wakeup)
);
TRACE_EVENT(svc_wake_up,
TP_PROTO(int pid),
TP_ARGS(pid),
TP_STRUCT__entry(
__field(int, pid)
),
TP_fast_assign(
__entry->pid = pid;
),
TP_printk("pid=%d", __entry->pid)
);
TRACE_EVENT(svc_handle_xprt,
TP_PROTO(struct svc_xprt *xprt, int len),
TP_ARGS(xprt, len),
TP_STRUCT__entry(
__field(struct svc_xprt *, xprt)
__field(int, len)
__field(unsigned long, flags)
__string(addr, xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xprt = xprt;
__entry->len = len;
__entry->flags = xprt->xpt_flags;
__assign_str(addr, xprt->xpt_remotebuf);
),
TP_printk("xprt=%p addr=%s len=%d flags=%s",
__entry->xprt, __get_str(addr),
__entry->len, show_svc_xprt_flags(__entry->flags))
);
TRACE_EVENT(svc_stats_latency,
TP_PROTO(const struct svc_rqst *rqst),
TP_ARGS(rqst),
TP_STRUCT__entry(
__field(u32, xid)
__field(unsigned long, execute)
__string(addr, rqst->rq_xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqst->rq_xid);
__entry->execute = ktime_to_us(ktime_sub(ktime_get(),
rqst->rq_stime));
__assign_str(addr, rqst->rq_xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x execute-us=%lu",
__get_str(addr), __entry->xid, __entry->execute)
);
DECLARE_EVENT_CLASS(svc_deferred_event,
TP_PROTO(struct svc_deferred_req *dr),
TP_ARGS(dr),
TP_STRUCT__entry(
__field(u32, xid)
__string(addr, dr->xprt->xpt_remotebuf)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(*(__be32 *)(dr->args +
(dr->xprt_hlen>>2)));
__assign_str(addr, dr->xprt->xpt_remotebuf);
),
TP_printk("addr=%s xid=0x%08x", __get_str(addr), __entry->xid)
);
DEFINE_EVENT(svc_deferred_event, svc_drop_deferred,
TP_PROTO(struct svc_deferred_req *dr),
TP_ARGS(dr));
DEFINE_EVENT(svc_deferred_event, svc_revisit_deferred,
TP_PROTO(struct svc_deferred_req *dr),
TP_ARGS(dr));
#endif /* _TRACE_SUNRPC_H */
#include <trace/define_trace.h>