linux_dsm_epyc7002/include/linux/sunrpc/sched.h

297 lines
9.1 KiB
C
Raw Normal View History

/*
* linux/include/linux/sunrpc/sched.h
*
* Scheduling primitives for kernel Sun RPC.
*
* Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
*/
#ifndef _LINUX_SUNRPC_SCHED_H_
#define _LINUX_SUNRPC_SCHED_H_
#include <linux/timer.h>
#include <linux/ktime.h>
#include <linux/sunrpc/types.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#include <linux/sunrpc/xdr.h>
/*
* This is the actual RPC procedure call info.
*/
struct rpc_procinfo;
struct rpc_message {
struct rpc_procinfo * rpc_proc; /* Procedure information */
void * rpc_argp; /* Arguments */
void * rpc_resp; /* Result */
struct rpc_cred * rpc_cred; /* Credentials */
};
struct rpc_call_ops;
struct rpc_wait_queue;
struct rpc_wait {
struct list_head list; /* wait queue links */
struct list_head links; /* Links to related tasks */
struct list_head timer_list; /* Timer list */
unsigned long expires;
};
/*
* This is the RPC task struct
*/
struct rpc_task {
atomic_t tk_count; /* Reference count */
SUNRPC: Reorder rpc_task to put waitqueue related info in same cachelines Try to group all the data required by the waitqueues, their timers and timer callbacks into the same cachelines for performance. With this reordering, "pahole" reports the following structure on x86_64: struct rpc_task { atomic_t tk_count; /* 0 4 */ int tk_status; /* 4 4 */ struct list_head tk_task; /* 8 16 */ void (*tk_callback)(struct rpc_task *); /* 24 void (*tk_action)(struct rpc_task *); /* 32 long unsigned int tk_timeout; /* 40 8 */ long unsigned int tk_runstate; /* 48 8 */ struct rpc_wait_queue * tk_waitqueue; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ union { struct work_struct tk_work; /* 64 */ struct rpc_wait tk_wait; /* 56 */ } u; /* 64 64 */ /* --- cacheline 2 boundary (128 bytes) --- */ struct rpc_message tk_msg; /* 128 32 */ void * tk_calldata; /* 160 8 */ const struct rpc_call_ops * tk_ops; /* 168 8 */ struct rpc_clnt * tk_client; /* 176 8 */ struct rpc_rqst * tk_rqstp; /* 184 8 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct workqueue_struct * tk_workqueue; /* 192 8 */ ktime_t tk_start; /* 200 8 */ pid_t tk_owner; /* 208 4 */ short unsigned int tk_flags; /* 212 2 */ short unsigned int tk_timeouts; /* 214 2 */ short unsigned int tk_pid; /* 216 2 */ unsigned char tk_priority:2; /* 218: 6 1 */ unsigned char tk_garb_retry:2; /* 218: 4 1 */ unsigned char tk_cred_retry:2; /* 218: 2 1 */ unsigned char tk_rebind_retry:2; /* 218: 0 1 */ /* size: 224, cachelines: 4, members: 24 */ /* padding: 5 */ /* last cacheline: 32 bytes */ }; whereas on i386, it reports everything fitting into the 1st cacheline. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-02-26 02:49:16 +07:00
int tk_status; /* result of last operation */
struct list_head tk_task; /* global list of tasks */
/*
* callback to be executed after waking up
* action next procedure for async tasks
*/
void (*tk_callback)(struct rpc_task *);
void (*tk_action)(struct rpc_task *);
unsigned long tk_timeout; /* timeout for rpc_sleep() */
unsigned long tk_runstate; /* Task run status */
SUNRPC: Reorder rpc_task to put waitqueue related info in same cachelines Try to group all the data required by the waitqueues, their timers and timer callbacks into the same cachelines for performance. With this reordering, "pahole" reports the following structure on x86_64: struct rpc_task { atomic_t tk_count; /* 0 4 */ int tk_status; /* 4 4 */ struct list_head tk_task; /* 8 16 */ void (*tk_callback)(struct rpc_task *); /* 24 void (*tk_action)(struct rpc_task *); /* 32 long unsigned int tk_timeout; /* 40 8 */ long unsigned int tk_runstate; /* 48 8 */ struct rpc_wait_queue * tk_waitqueue; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ union { struct work_struct tk_work; /* 64 */ struct rpc_wait tk_wait; /* 56 */ } u; /* 64 64 */ /* --- cacheline 2 boundary (128 bytes) --- */ struct rpc_message tk_msg; /* 128 32 */ void * tk_calldata; /* 160 8 */ const struct rpc_call_ops * tk_ops; /* 168 8 */ struct rpc_clnt * tk_client; /* 176 8 */ struct rpc_rqst * tk_rqstp; /* 184 8 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct workqueue_struct * tk_workqueue; /* 192 8 */ ktime_t tk_start; /* 200 8 */ pid_t tk_owner; /* 208 4 */ short unsigned int tk_flags; /* 212 2 */ short unsigned int tk_timeouts; /* 214 2 */ short unsigned int tk_pid; /* 216 2 */ unsigned char tk_priority:2; /* 218: 6 1 */ unsigned char tk_garb_retry:2; /* 218: 4 1 */ unsigned char tk_cred_retry:2; /* 218: 2 1 */ unsigned char tk_rebind_retry:2; /* 218: 0 1 */ /* size: 224, cachelines: 4, members: 24 */ /* padding: 5 */ /* last cacheline: 32 bytes */ }; whereas on i386, it reports everything fitting into the 1st cacheline. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-02-26 02:49:16 +07:00
struct rpc_wait_queue *tk_waitqueue; /* RPC wait queue we're on */
union {
struct work_struct tk_work; /* Async task work queue */
struct rpc_wait tk_wait; /* RPC wait */
} u;
SUNRPC: Reorder rpc_task to put waitqueue related info in same cachelines Try to group all the data required by the waitqueues, their timers and timer callbacks into the same cachelines for performance. With this reordering, "pahole" reports the following structure on x86_64: struct rpc_task { atomic_t tk_count; /* 0 4 */ int tk_status; /* 4 4 */ struct list_head tk_task; /* 8 16 */ void (*tk_callback)(struct rpc_task *); /* 24 void (*tk_action)(struct rpc_task *); /* 32 long unsigned int tk_timeout; /* 40 8 */ long unsigned int tk_runstate; /* 48 8 */ struct rpc_wait_queue * tk_waitqueue; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ union { struct work_struct tk_work; /* 64 */ struct rpc_wait tk_wait; /* 56 */ } u; /* 64 64 */ /* --- cacheline 2 boundary (128 bytes) --- */ struct rpc_message tk_msg; /* 128 32 */ void * tk_calldata; /* 160 8 */ const struct rpc_call_ops * tk_ops; /* 168 8 */ struct rpc_clnt * tk_client; /* 176 8 */ struct rpc_rqst * tk_rqstp; /* 184 8 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct workqueue_struct * tk_workqueue; /* 192 8 */ ktime_t tk_start; /* 200 8 */ pid_t tk_owner; /* 208 4 */ short unsigned int tk_flags; /* 212 2 */ short unsigned int tk_timeouts; /* 214 2 */ short unsigned int tk_pid; /* 216 2 */ unsigned char tk_priority:2; /* 218: 6 1 */ unsigned char tk_garb_retry:2; /* 218: 4 1 */ unsigned char tk_cred_retry:2; /* 218: 2 1 */ unsigned char tk_rebind_retry:2; /* 218: 0 1 */ /* size: 224, cachelines: 4, members: 24 */ /* padding: 5 */ /* last cacheline: 32 bytes */ }; whereas on i386, it reports everything fitting into the 1st cacheline. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-02-26 02:49:16 +07:00
/*
* RPC call state
*/
struct rpc_message tk_msg; /* RPC call info */
void * tk_calldata; /* Caller private data */
const struct rpc_call_ops *tk_ops; /* Caller callbacks */
struct rpc_clnt * tk_client; /* RPC client */
struct rpc_xprt * tk_xprt; /* Transport */
SUNRPC: Reorder rpc_task to put waitqueue related info in same cachelines Try to group all the data required by the waitqueues, their timers and timer callbacks into the same cachelines for performance. With this reordering, "pahole" reports the following structure on x86_64: struct rpc_task { atomic_t tk_count; /* 0 4 */ int tk_status; /* 4 4 */ struct list_head tk_task; /* 8 16 */ void (*tk_callback)(struct rpc_task *); /* 24 void (*tk_action)(struct rpc_task *); /* 32 long unsigned int tk_timeout; /* 40 8 */ long unsigned int tk_runstate; /* 48 8 */ struct rpc_wait_queue * tk_waitqueue; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ union { struct work_struct tk_work; /* 64 */ struct rpc_wait tk_wait; /* 56 */ } u; /* 64 64 */ /* --- cacheline 2 boundary (128 bytes) --- */ struct rpc_message tk_msg; /* 128 32 */ void * tk_calldata; /* 160 8 */ const struct rpc_call_ops * tk_ops; /* 168 8 */ struct rpc_clnt * tk_client; /* 176 8 */ struct rpc_rqst * tk_rqstp; /* 184 8 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct workqueue_struct * tk_workqueue; /* 192 8 */ ktime_t tk_start; /* 200 8 */ pid_t tk_owner; /* 208 4 */ short unsigned int tk_flags; /* 212 2 */ short unsigned int tk_timeouts; /* 214 2 */ short unsigned int tk_pid; /* 216 2 */ unsigned char tk_priority:2; /* 218: 6 1 */ unsigned char tk_garb_retry:2; /* 218: 4 1 */ unsigned char tk_cred_retry:2; /* 218: 2 1 */ unsigned char tk_rebind_retry:2; /* 218: 0 1 */ /* size: 224, cachelines: 4, members: 24 */ /* padding: 5 */ /* last cacheline: 32 bytes */ }; whereas on i386, it reports everything fitting into the 1st cacheline. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-02-26 02:49:16 +07:00
struct rpc_rqst * tk_rqstp; /* RPC request */
struct workqueue_struct *tk_workqueue; /* Normally rpciod, but could
* be any workqueue
*/
ktime_t tk_start; /* RPC task init timestamp */
pid_t tk_owner; /* Process id for batching tasks */
unsigned short tk_flags; /* misc flags */
unsigned short tk_timeouts; /* maj timeouts */
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
unsigned short tk_pid; /* debugging aid */
#endif
unsigned char tk_priority : 2,/* Task priority */
tk_garb_retry : 2,
tk_cred_retry : 2,
tk_rebind_retry : 2;
};
typedef void (*rpc_action)(struct rpc_task *);
struct rpc_call_ops {
void (*rpc_call_prepare)(struct rpc_task *, void *);
void (*rpc_call_done)(struct rpc_task *, void *);
void (*rpc_count_stats)(struct rpc_task *, void *);
void (*rpc_release)(void *);
};
struct rpc_task_setup {
struct rpc_task *task;
struct rpc_clnt *rpc_client;
struct rpc_xprt *rpc_xprt;
const struct rpc_message *rpc_message;
const struct rpc_call_ops *callback_ops;
void *callback_data;
struct workqueue_struct *workqueue;
unsigned short flags;
signed char priority;
};
/*
* RPC task flags
*/
#define RPC_TASK_ASYNC 0x0001 /* is an async task */
#define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */
#define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */
#define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */
#define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */
#define RPC_TASK_KILLED 0x0100 /* task was killed */
#define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */
#define RPC_TASK_SOFTCONN 0x0400 /* Fail if can't connect */
#define RPC_TASK_SENT 0x0800 /* message was sent */
#define RPC_TASK_TIMEOUT 0x1000 /* fail with ETIMEDOUT on timeout */
#define RPC_TASK_NOCONNECT 0x2000 /* return ENOTCONN if not connected */
#define RPC_TASK_NO_RETRANS_TIMEOUT 0x4000 /* wait forever for a reply */
#define RPC_IS_ASYNC(t) ((t)->tk_flags & RPC_TASK_ASYNC)
#define RPC_IS_SWAPPER(t) ((t)->tk_flags & RPC_TASK_SWAPPER)
#define RPC_DO_ROOTOVERRIDE(t) ((t)->tk_flags & RPC_TASK_ROOTCREDS)
#define RPC_ASSASSINATED(t) ((t)->tk_flags & RPC_TASK_KILLED)
#define RPC_IS_SOFT(t) ((t)->tk_flags & (RPC_TASK_SOFT|RPC_TASK_TIMEOUT))
#define RPC_IS_SOFTCONN(t) ((t)->tk_flags & RPC_TASK_SOFTCONN)
#define RPC_WAS_SENT(t) ((t)->tk_flags & RPC_TASK_SENT)
#define RPC_TASK_RUNNING 0
#define RPC_TASK_QUEUED 1
#define RPC_TASK_ACTIVE 2
#define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
#define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
#define rpc_test_and_set_running(t) \
test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
#define rpc_clear_running(t) \
do { \
smp_mb__before_atomic(); \
clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate); \
smp_mb__after_atomic(); \
} while (0)
#define RPC_IS_QUEUED(t) test_bit(RPC_TASK_QUEUED, &(t)->tk_runstate)
#define rpc_set_queued(t) set_bit(RPC_TASK_QUEUED, &(t)->tk_runstate)
#define rpc_clear_queued(t) \
do { \
smp_mb__before_atomic(); \
clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate); \
smp_mb__after_atomic(); \
} while (0)
#define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
/*
* Task priorities.
* Note: if you change these, you must also change
* the task initialization definitions below.
*/
#define RPC_PRIORITY_LOW (-1)
#define RPC_PRIORITY_NORMAL (0)
#define RPC_PRIORITY_HIGH (1)
#define RPC_PRIORITY_PRIVILEGED (2)
#define RPC_NR_PRIORITY (1 + RPC_PRIORITY_PRIVILEGED - RPC_PRIORITY_LOW)
struct rpc_timer {
struct timer_list timer;
struct list_head list;
unsigned long expires;
};
/*
* RPC synchronization objects
*/
struct rpc_wait_queue {
spinlock_t lock;
struct list_head tasks[RPC_NR_PRIORITY]; /* task queue for each priority level */
pid_t owner; /* process id of last task serviced */
unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */
unsigned char priority; /* current priority */
unsigned char nr; /* # tasks remaining for cookie */
unsigned short qlen; /* total # tasks waiting in queue */
struct rpc_timer timer_list;
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
const char * name;
#endif
};
/*
* This is the # requests to send consecutively
* from a single cookie. The aim is to improve
* performance of NFS operations such as read/write.
*/
#define RPC_BATCH_COUNT 16
#define RPC_IS_PRIORITY(q) ((q)->maxpriority > 0)
/*
* Function prototypes
*/
struct rpc_task *rpc_new_task(const struct rpc_task_setup *);
struct rpc_task *rpc_run_task(const struct rpc_task_setup *);
struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req);
void rpc_put_task(struct rpc_task *);
SUNRPC: Close a race in __rpc_wait_for_completion_task() Although they run as rpciod background tasks, under normal operation (i.e. no SIGKILL), functions like nfs_sillyrename(), nfs4_proc_unlck() and nfs4_do_close() want to be fully synchronous. This means that when we exit, we want all references to the rpc_task to be gone, and we want any dentry references etc. held by that task to be released. For this reason these functions call __rpc_wait_for_completion_task(), followed by rpc_put_task() in the expectation that the latter will be releasing the last reference to the rpc_task, and thus ensuring that the callback_ops->rpc_release() has been called synchronously. This patch fixes a race which exists due to the fact that rpciod calls rpc_complete_task() (in order to wake up the callers of __rpc_wait_for_completion_task()) and then subsequently calls rpc_put_task() without ensuring that these two steps are done atomically. In order to avoid adding new spin locks, the patch uses the existing waitqueue spin lock to order the rpc_task reference count releases between the waiting process and rpciod. The common case where nobody is waiting for completion is optimised for by checking if the RPC_TASK_ASYNC flag is cleared and/or if the rpc_task reference count is 1: in those cases we drop trying to grab the spin lock, and immediately free up the rpc_task. Those few processes that need to put the rpc_task from inside an asynchronous context and that do not care about ordering are given a new helper: rpc_put_task_async(). Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-02-22 02:05:41 +07:00
void rpc_put_task_async(struct rpc_task *);
void rpc_exit_task(struct rpc_task *);
void rpc_exit(struct rpc_task *, int);
void rpc_release_calldata(const struct rpc_call_ops *, void *);
void rpc_killall_tasks(struct rpc_clnt *);
void rpc_execute(struct rpc_task *);
void rpc_init_priority_wait_queue(struct rpc_wait_queue *, const char *);
void rpc_init_wait_queue(struct rpc_wait_queue *, const char *);
void rpc_destroy_wait_queue(struct rpc_wait_queue *);
void rpc_sleep_on(struct rpc_wait_queue *, struct rpc_task *,
rpc_action action);
void rpc_sleep_on_priority(struct rpc_wait_queue *,
struct rpc_task *,
rpc_action action,
int priority);
void rpc_wake_up_queued_task(struct rpc_wait_queue *,
struct rpc_task *);
void rpc_wake_up(struct rpc_wait_queue *);
struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *);
struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
struct rpc_wait_queue *,
bool (*)(struct rpc_task *, void *),
void *);
struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *,
bool (*)(struct rpc_task *, void *),
void *);
void rpc_wake_up_status(struct rpc_wait_queue *, int);
void rpc_delay(struct rpc_task *, unsigned long);
void * rpc_malloc(struct rpc_task *, size_t);
void rpc_free(void *);
int rpciod_up(void);
void rpciod_down(void);
sched: Allow wait_on_bit_action() functions to support a timeout It is currently not possible for various wait_on_bit functions to implement a timeout. While the "action" function that is called to do the waiting could certainly use schedule_timeout(), there is no way to carry forward the remaining timeout after a false wake-up. As false-wakeups a clearly possible at least due to possible hash collisions in bit_waitqueue(), this is a real problem. The 'action' function is currently passed a pointer to the word containing the bit being waited on. No current action functions use this pointer. So changing it to something else will be a little noisy but will have no immediate effect. This patch changes the 'action' function to take a pointer to the "struct wait_bit_key", which contains a pointer to the word containing the bit so nothing is really lost. It also adds a 'private' field to "struct wait_bit_key", which is initialized to zero. An action function can now implement a timeout with something like static int timed_out_waiter(struct wait_bit_key *key) { unsigned long waited; if (key->private == 0) { key->private = jiffies; if (key->private == 0) key->private -= 1; } waited = jiffies - key->private; if (waited > 10 * HZ) return -EAGAIN; schedule_timeout(waited - 10 * HZ); return 0; } If any other need for context in a waiter were found it would be easy to use ->private for some other purpose, or even extend "struct wait_bit_key". My particular need is to support timeouts in nfs_release_page() to avoid deadlocks with loopback mounted NFS. While wait_on_bit_timeout() would be a cleaner interface, it will not meet my need. I need the timeout to be sensitive to the state of the connection with the server, which could change. So I need to use an 'action' interface. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: David Howells <dhowells@redhat.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051604.28027.41257.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 12:16:04 +07:00
int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *);
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
struct net;
void rpc_show_tasks(struct net *);
#endif
int rpc_init_mempool(void);
void rpc_destroy_mempool(void);
extern struct workqueue_struct *rpciod_workqueue;
extern struct workqueue_struct *xprtiod_workqueue;
void rpc_prepare_task(struct rpc_task *task);
static inline int rpc_wait_for_completion_task(struct rpc_task *task)
{
return __rpc_wait_for_completion_task(task, NULL);
}
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS)
static inline const char * rpc_qname(const struct rpc_wait_queue *q)
{
return ((q && q->name) ? q->name : "unknown");
}
static inline void rpc_assign_waitqueue_name(struct rpc_wait_queue *q,
const char *name)
{
q->name = name;
}
#else
static inline void rpc_assign_waitqueue_name(struct rpc_wait_queue *q,
const char *name)
{
}
#endif
#if IS_ENABLED(CONFIG_SUNRPC_SWAP)
int rpc_clnt_swap_activate(struct rpc_clnt *clnt);
void rpc_clnt_swap_deactivate(struct rpc_clnt *clnt);
#else
static inline int
rpc_clnt_swap_activate(struct rpc_clnt *clnt)
{
return -EINVAL;
}
static inline void
rpc_clnt_swap_deactivate(struct rpc_clnt *clnt)
{
}
#endif /* CONFIG_SUNRPC_SWAP */
#endif /* _LINUX_SUNRPC_SCHED_H_ */