Revert for r277213:

FreeBSD developers need more time to review patches in the surrounding
areas like the TCP stack which are using MPSAFE callouts to restore
distribution of callouts on multiple CPUs.

Bump the __FreeBSD_version instead of reverting it.

Suggested by:		kmacy, adrian, glebius and kib
Differential Revision:	https://reviews.freebsd.org/D1438
This commit is contained in:
hselasky 2015-01-22 11:12:42 +00:00
parent 8925dffab1
commit c0aba3b50d
15 changed files with 1111 additions and 1048 deletions

View File

@ -1570,7 +1570,6 @@ MLINKS+=timeout.9 callout.9 \
timeout.9 callout_active.9 \
timeout.9 callout_deactivate.9 \
timeout.9 callout_drain.9 \
timeout.9 callout_drain_async.9 \
timeout.9 callout_handle_init.9 \
timeout.9 callout_init.9 \
timeout.9 callout_init_mtx.9 \

View File

@ -29,14 +29,13 @@
.\"
.\" $FreeBSD$
.\"
.Dd January 14, 2015
.Dd October 8, 2014
.Dt TIMEOUT 9
.Os
.Sh NAME
.Nm callout_active ,
.Nm callout_deactivate ,
.Nm callout_drain ,
.Nm callout_drain_async ,
.Nm callout_handle_init ,
.Nm callout_init ,
.Nm callout_init_mtx ,
@ -64,232 +63,279 @@
.In sys/systm.h
.Bd -literal
typedef void timeout_t (void *);
typedef void callout_func_t (void *);
.Ed
.Ft int
.Fn callout_active "struct callout *c"
.Ft void
.Fn callout_deactivate "struct callout *c"
.Ft int
.Fn callout_drain "struct callout *c"
.Ft void
.Fn callout_handle_init "struct callout_handle *handle"
.Bd -literal
struct callout_handle handle = CALLOUT_HANDLE_INITIALIZER(&handle);
.Ed
.Ft void
.Fn callout_init "struct callout *c" "int mpsafe"
.Ft void
.Fn callout_init_mtx "struct callout *c" "struct mtx *mtx" "int flags"
.Ft void
.Fn callout_init_rm "struct callout *c" "struct rmlock *rm" "int flags"
.Ft void
.Fn callout_init_rw "struct callout *c" "struct rwlock *rw" "int flags"
.Ft int
.Fn callout_pending "struct callout *c"
.Ft int
.Fn callout_reset "struct callout *c" "int ticks" "timeout_t *func" "void *arg"
.Ft int
.Fn callout_reset_curcpu "struct callout *c" "int ticks" "timeout_t *func" \
"void *arg"
.Ft int
.Fn callout_reset_on "struct callout *c" "int ticks" "timeout_t *func" \
"void *arg" "int cpu"
.Ft int
.Fn callout_reset_sbt "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "timeout_t *func" "void *arg" "int flags"
.Ft int
.Fn callout_reset_sbt_curcpu "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "timeout_t *func" "void *arg" "int flags"
.Ft int
.Fn callout_reset_sbt_on "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "timeout_t *func" "void *arg" "int cpu" "int flags"
.Ft int
.Fn callout_schedule "struct callout *c" "int ticks"
.Ft int
.Fn callout_schedule_curcpu "struct callout *c" "int ticks"
.Ft int
.Fn callout_schedule_on "struct callout *c" "int ticks" "int cpu"
.Ft int
.Fn callout_schedule_sbt "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "int flags"
.Ft int
.Fn callout_schedule_sbt_curcpu "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "int flags"
.Ft int
.Fn callout_schedule_sbt_on "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "int cpu" "int flags"
.Ft int
.Fn callout_stop "struct callout *c"
.Ft struct callout_handle
.Fn timeout "timeout_t *func" "void *arg" "int ticks"
.Ft void
.Fn untimeout "timeout_t *func" "void *arg" "struct callout_handle handle"
.Sh DESCRIPTION
The
.Nm callout
API is used to schedule a call to an arbitrary function at a specific
time in the future in a single-shot fashion.
Consumers of this API are required to allocate a
time in the future.
Consumers of this API are required to allocate a callout structure
.Pq struct callout
structure for each pending function invocation.
The
.Pq struct callout
structure stores the full state about any pending function call and
should be drained by a call to
.Fn callout_drain
for each pending function invocation.
This structure stores state about the pending function invocation including
the function to be called and the time at which the function should be invoked.
Pending function calls can be cancelled or rescheduled to a different time.
In addition,
a callout structure may be reused to schedule a new function call after a
scheduled call is completed.
.Pp
Callouts only provide a single-shot mode.
If a consumer requires a periodic timer,
it must explicitly reschedule each function call.
This is normally done by rescheduling the subsequent call within the called
function.
.Pp
Callout functions must not sleep.
They may not acquire sleepable locks,
wait on condition variables,
perform blocking allocation requests,
or invoke any other action that might sleep.
.Pp
Each callout structure must be initialized by
.Fn callout_init ,
.Fn callout_init_mtx ,
.Fn callout_init_rm ,
or
.Fn callout_drain_async
before freeing.
.Sh INITIALISATION
.Ft void
.Fn callout_handle_init "struct callout_handle *handle"
This function is deprecated and is used to prepare a
.Pq struct callout_handle
structure before it can be used the first time.
If this function is called on a pending timeout, the pending timeout
cannot be cancelled and the
.Fn untimeout
function will return as if there was no timeout pending.
.Pp
.Fn CALLOUT_HANDLE_INITIALIZER "&handle"
This macro is deprecated and can be used instead of
.Fn callout_handle_init
to assign the default state to the
.Pq struct callout_handle
structure when declaring static timeouts.
.Pp
.Ft void
.Fn callout_init "struct callout *c" "int mpsafe"
This function prepares a
.Pq struct callout
structure before it can be used.
This function should not be used when the callout is pending a timeout.
.Fn callout_init_rw
before it is passed to any of the other callout functions.
The
.Fn callout_init
function initializes a callout structure in
.Fa c
that is not associated with a specific lock.
If the
.Fa mpsafe
argument is non-zero, the callback function will be running unlocked.
Else the Giant mutex will be locked before calling the callback function.
argument is zero,
the callout structure is not considered to be
.Dq multi-processor safe ;
and the Giant lock will be acquired before calling the callout function
and released when the callout function returns.
.Pp
.Ft void
.Fn callout_init_mtx "struct callout *c" "struct mtx *mtx" "int flags"
This function prepares a
.Pq struct callout
structure before it can be used.
This function should not be used when the callout is pending a timeout.
The
.Fa mtx
argument should be non-zero and should specify a pointer to a valid
spinlock type of mutex or a valid regular non-sleepable mutex which
the callback subsystem should lock before calling the callback
function.
Valid
.Fn callout_init_mtx ,
.Fn callout_init_rm ,
and
.Fn callout_init_rw
functions initialize a callout structure in
.Fa c
that is associated with a specific lock.
The lock is specified by the
.Fa mtx ,
.Fa rm ,
or
.Fa rw
parameter.
The associated lock must be held while stopping or rescheduling the
callout.
The callout subsystem acquires the associated lock before calling the
callout function and releases it after the function returns.
If the callout was cancelled while the callout subsystem waited for the
associated lock,
the callout function is not called,
and the associated lock is released.
This ensures that stopping or rescheduling the callout will abort any
previously scheduled invocation.
.Pp
Only regular mutexes may be used with
.Fn callout_init_mtx ;
spin mutexes are not supported.
A sleepable read-mostly lock
.Po
one initialized with the
.Dv RM_SLEEPABLE
flag
.Pc
may not be used with
.Fn callout_init_rm .
Similarly, other sleepable lock types such as
.Xr sx 9
and
.Xr lockmgr 9
cannot be used with callouts because sleeping is not permitted in
the callout subsystem.
.Pp
These
.Fa flags
are:
may be specified for
.Fn callout_init_mtx ,
.Fn callout_init_rm ,
or
.Fn callout_init_rw :
.Bl -tag -width ".Dv CALLOUT_RETURNUNLOCKED"
.It Dv CALLOUT_RETURNUNLOCKED
It is assumed that the callout function has released the specified
mutex before returning.
Else the callout subsystem will release the specified mutex after the
callout function has returned.
The callout function will release the associated lock itself,
so the callout subsystem should not attempt to unlock it
after the callout function returns.
.It Dv CALLOUT_SHAREDLOCK
The lock is only acquired in read mode when running the callout handler.
This flag is ignored by
.Fn callout_init_mtx .
.El
.Pp
.Ft void
.Fn callout_init_rm "struct callout *c" "struct rmlock *rm" "int flags"
This function is the same like the
.Fn callout_init_mtx
function except it accepts a read-mostly type of lock.
The read-mostly lock must not be initialised with the
.Dv RM_SLEEPABLE
flag.
The function
.Fn callout_stop
cancels a callout
.Fa c
if it is currently pending.
If the callout is pending, then
.Fn callout_stop
returns a non-zero value.
If the callout is not set,
has already been serviced,
or is currently being serviced,
then zero will be returned.
If the callout has an associated lock,
then that lock must be held when this function is called.
.Pp
.Ft void
.Fn callout_init_rw "struct callout *c" "struct rwlock *rw" "int flags"
This function is the same like the
.Fn callout_init_mtx
function except it accepts a reader-writer type of lock.
.Sh SCHEDULING CALLOUTS
.Ft struct callout_handle
.Fn timeout "timeout_t *func" "void *arg" "int ticks"
This function is deprecated and schedules a call to the function given by the argument
.Fa func
to take place after
The function
.Fn callout_drain
is identical to
.Fn callout_stop
except that it will wait for the callout
.Fa c
to complete if it is already in progress.
This function MUST NOT be called while holding any
locks on which the callout might block, or deadlock will result.
Note that if the callout subsystem has already begun processing this
callout, then the callout function may be invoked before
.Fn callout_drain
returns.
However, the callout subsystem does guarantee that the callout will be
fully stopped before
.Fn callout_drain
returns.
.Pp
The
.Fn callout_reset
and
.Fn callout_schedule
function families schedule a future function invocation for callout
.Fa c .
If
.Fa c
already has a pending callout,
it is cancelled before the new invocation is scheduled.
These functions return a non-zero value if a pending callout was cancelled
and zero if there was no pending callout.
If the callout has an associated lock,
then that lock must be held when any of these functions are called.
.Pp
The time at which the callout function will be invoked is determined by
either the
.Fa ticks
argument or the
.Fa sbt ,
.Fa pr ,
and
.Fa flags
arguments.
When
.Fa ticks
is used,
the callout is scheduled to execute after
.Fa ticks Ns No /hz
seconds.
Non-positive values of
.Fa ticks
are silently converted to the value
.Sq 1 .
.Pp
The
.Fa func
argument should be a valid pointer to a function that takes a single
.Fa void *
argument.
Upon invocation, the
.Fa func
function will receive
.Fa arg
as its only argument.
The Giant lock is locked when the
.Fa arg
function is invoked and should not be unlocked by this function.
The returned value from
.Fn timeout
is a
.Ft struct callout_handle
structure which can be used in conjunction with the
.Fn untimeout
function to request that a scheduled timeout be cancelled.
As handles are recycled by the system, it is possible, although unlikely,
that a handle from one invocation of
.Fn timeout
may match the handle of another invocation of
.Fn timeout
if both calls used the same function pointer and argument, and the first
timeout is expired or canceled before the second call.
Please ensure that the function and argument pointers are unique when using this function.
.Pp
.Ft int
.Fn callout_reset "struct callout *c" "int ticks" "callout_func_t *func" "void *arg"
This function is used to schedule or re-schedule a callout.
This function at first stops the callout given by the
.Fa c
argument, if any.
Then it will start the callout given by the
.Fa c
argument.
The relative time until the timeout callback happens is given by the
.Fa ticks
argument.
The number of ticks in a second is defined by
.Dv hz
and can vary from system to system.
This function returns a non-zero value if the given callout was pending and
the callback function was prevented from being called.
Else a value of zero is returned.
If a lock is associated with the callout given by the
.Fa c
argument and it is exclusivly locked when this function is called this
function will always ensure that previous callback function, if any,
is never reached.
In other words the callout will be atomically restarted.
Else there is no such guarantee.
The callback function is given by the
.Fa func
argument and its function argument is given by the
.Fa arg
argument.
.Pp
.Ft int
.Fn callout_reset_curcpu "struct callout *c" "int ticks" "callout_func_t *func" \
"void *arg"
This function works the same like the
.Fn callout_reset
function except the callback function given by the
.Fa func
argument will be executed on the same CPU which called this function.
A change in the CPU selection can happen if the callout has a lock
associated with it and is locked when this function is called.
A change in the CPU selection cannot happen if this function is
re-scheduled inside a callout function.
Else the callback function given by the
.Fa func
argument will be executed on the same CPU like previously done.
.Pp
.Ft int
.Fn callout_reset_on "struct callout *c" "int ticks" "callout_func_t *func" \
"void *arg" "int cpu"
This function works the same like the
.Fn callout_reset
function except the callback function given by the
.Fa func
argument will be executed on the CPU given by the
.Fa cpu
argument.
A change in the CPU selection can happen if the callout has a lock
associated with it and is locked when this function is called.
A change in the CPU selection cannot happen if this function is
re-scheduled inside a callout function.
Else the callback function given by the
.Fa func
argument will be executed on the same CPU like previously done.
.Pp
.Ft int
.Fn callout_reset_sbt "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "callout_func_t *func" "void *arg" "int flags"
This function works the same like the
.Fn callout_reset
function except the relative or absolute time after which the timeout
callback should happen is given by the
.Fa sbt ,
.Fa pr ,
and
.Fa flags
arguments provide more control over the scheduled time including
support for higher resolution times,
specifying the precision of the scheduled time,
and setting an absolute deadline instead of a relative timeout.
The callout is scheduled to execute in a time window which begins at
the time specified in
.Fa sbt
argument and extends for the amount of time specified in the
.Fa pr
argument.
This function is used when you need high precision timeouts.
If the
and extends for the amount of time specified in
.Fa pr .
If
.Fa sbt
argument specifies a time in the past,
specifies a time in the past,
the window is adjusted to start at the current time.
A non-zero value for
.Fa pr
allows the callout subsystem to coalesce callouts scheduled close to each
other into fewer timer interrupts,
reducing processing overhead and power consumption.
The
These
.Fa flags
argument may be non-zero to adjust the interpretation of the
may be specified to adjust the interpretation of
.Fa sbt
and the
.Fa pr
arguments:
and
.Fa pr :
.Bl -tag -width ".Dv C_DIRECT_EXEC"
.It Dv C_ABSOLUTE
Handle the
.Fa sbt
argument as an absolute time since boot.
By default, the
By default,
.Fa sbt
argument is treated like a relative amount of time,
is treated as a relative amount of time,
similar to
.Fa ticks .
.It Dv C_DIRECT_EXEC
@ -301,7 +347,7 @@ Callout functions run in this context may use only spin mutexes for locking
and should be as small as possible because they run with absolute priority.
.It Fn C_PREL
Specifies relative event time precision as binary logarithm of time interval
divided by acceptable time deviation: 1 -- 1/2, 2 -- 1/4 and so on.
divided by acceptable time deviation: 1 -- 1/2, 2 -- 1/4, etc.
Note that the larger of
.Fa pr
or this value is used as the length of the time window.
@ -314,215 +360,65 @@ Align the timeouts to
calls if possible.
.El
.Pp
.Ft int
.Fn callout_reset_sbt_curcpu "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "callout_func_t *func" "void *arg" "int flags"
This function works the same like the
.Fn callout_reset_sbt
function except the callback function given by the
.Fa func
argument will be executed on the same CPU which called this function.
A change in the CPU selection can happen if the callout has a lock
associated with it and is locked when this function is called.
A change in the CPU selection cannot happen if this function is
re-scheduled inside a callout function.
Else the callback function given by the
.Fa func
argument will be executed on the same CPU like previously done.
.Pp
.Ft int
.Fn callout_reset_sbt_on "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "callout_func_t *func" "void *arg" "int cpu" "int flags"
This function works the same like the
.Fn callout_reset_sbt
function except the callback function given by the
.Fa func
argument will be executed on the CPU given by the
.Fa cpu
argument.
A change in the CPU selection can happen if the callout has a lock
associated with it and is locked when this function is called.
A change in the CPU selection cannot happen if this function is
re-scheduled inside a callout function.
Else the callback function given by the
.Fa func
argument will be executed on the same CPU like previously done.
.Pp
.Ft int
.Fn callout_schedule "struct callout *c" "int ticks"
This function works the same like the
The
.Fn callout_reset
function except it re-uses the callback function and the callback argument
already stored in the
.Pq struct callout
structure.
.Pp
.Ft int
.Fn callout_schedule_curcpu "struct callout *c" "int ticks"
This function works the same like the
.Fn callout_reset_curcpu
function except it re-uses the callback function and the callback argument
already stored in the
.Pq struct callout
structure.
.Pp
.Ft int
.Fn callout_schedule_on "struct callout *c" "int ticks" "int cpu"
This function works the same like the
.Fn callout_reset_on
function except it re-uses the callback function and the callback argument
already stored in the
.Pq struct callout
structure.
.Pp
.Ft int
.Fn callout_schedule_sbt "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "int flags"
This function works the same like the
.Fn callout_reset_sbt
function except it re-uses the callback function and the callback argument
already stored in the
.Pq struct callout
structure.
.Pp
.Ft int
.Fn callout_schedule_sbt_curcpu "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "int flags"
This function works the same like the
.Fn callout_reset_sbt_curcpu
function except it re-uses the callback function and the callback argument
already stored in the
.Pq struct callout
structure.
.Pp
.Ft int
.Fn callout_schedule_sbt_on "struct callout *c" "sbintime_t sbt" \
"sbintime_t pr" "int cpu" "int flags"
This function works the same like the
.Fn callout_reset_sbt_on
function except it re-uses the callback function and the callback argument
already stored in the
.Pq struct callout
structure.
.Sh CHECKING THE STATE OF CALLOUTS
.Ft int
.Fn callout_pending "struct callout *c"
This function returns non-zero if the callout pointed to by the
.Fa c
argument is pending for callback.
Else this function returns zero.
This function returns zero when inside the callout function if the
callout is not re-scheduled.
.Pp
.Ft int
.Fn callout_active "struct callout *c"
This function is deprecated and returns non-zero if the callout
pointed to by the
.Fa c
argument was scheduled in the past.
Else this function returns zero.
This function also returns zero after the
.Fn callout_deactivate
or the
.Fn callout_stop
or the
.Fn callout_drain
or the
.Fn callout_drain_async
function is called on the same callout as given by the
.Fa c
argument.
.Pp
.Ft void
.Fn callout_deactivate "struct callout *c"
This function is deprecated and ensures that subsequent calls to the
.Fn callout_activate
function returns zero until the callout is scheduled again.
.Sh STOPPING CALLOUTS
.Ft void
.Fn untimeout "timeout_t *func" "void *arg" "struct callout_handle handle"
This function is deprecated and cancels the timeout associated with the
.Fa handle
argument using the function pointed to by the
functions accept a
.Fa func
argument and having the
.Fa arg
arguments to validate the handle.
If the handle does not correspond to a timeout with
the function
.Fa func
taking the argument
.Fa arg
no action is taken. The
.Fa handle
must be initialised by a previous call to
.Fn timeout ,
.Fn callout_handle_init
or assigned the value of
.Fn CALLOUT_HANDLE_INITIALIZER "&handle"
before being passed to
.Fn untimeout .
The behavior of calling
.Fn untimeout
with an uninitialised handle
is undefined.
.Pp
.Ft int
.Fn callout_stop "struct callout *c"
This function is used to stop a timeout function invocation associated with the callout pointed to by the
.Fa c
argument, in a non-blocking fashion.
This function can be called multiple times in a row with no side effects, even if the callout is already stopped. This function however should not be called before the callout has been initialised.
This function returns a non-zero value if the given callout was pending and
the callback function was prevented from being called.
Else a value of zero is returned.
If a lock is associated with the callout given by the
.Fa c
argument and it is exclusivly locked when this function is called, the
.Fn callout_stop
function will always ensure that the callback function is never reached.
In other words the callout will be atomically stopped.
Else there is no such guarantee.
.Sh DRAINING CALLOUTS
.Ft int
.Fn callout_drain "struct callout *c"
This function works the same like the
.Fn callout_stop
function except it ensures that all callback functions have returned and there are no more references to the callout pointed to by the
.Fa c
argument inside the callout subsystem before it returns.
Also this function ensures that the lock, if any, associated with the
callout is no longer being used.
When this function returns, it is safe to free the callout structure pointed to by the
.Fa c
argument which identifies the function to be called when the time expires.
It must be a pointer to a function that takes a single
.Fa void *
argument.
.Pp
.Ft int
.Fn callout_drain_async "struct callout *c" "callout_func_t *fn" "void *arg"
This function is non-blocking and works the same like the
.Fn callout_stop
function except if it returns non-zero it means the callback function pointed to by the
.Fa fn
argument will be called back with the
Upon invocation,
.Fa func
will receive
.Fa arg
argument when all references to the callout pointed to by the
.Fa c
argument are gone.
If this function returns zero, it is safe to free the callout structure pointed to by the
.Fa c
argument right away.
.Sh CALLOUT FUNCTION RESTRICTIONS
Callout functions must not sleep.
They may not acquire sleepable locks, wait on condition variables,
perform blocking allocation requests, or invoke any other action that
might sleep.
.Sh CALLOUT SUBSYSTEM INTERNALS
The callout subsystem has its own set of spinlocks to protect its internal state.
The callout subsystem provides a softclock thread for each CPU in the
system.
Callouts are assigned to a single CPU and are executed by the
softclock thread for that CPU.
Initially, callouts are assigned to CPU 0.
as its only argument.
The
.Fn callout_schedule
functions reuse the
.Fa func
and
.Fa arg
arguments from the previous callout.
Note that one of the
.Fn callout_reset
functions must always be called to initialize
.Fa func
and
.Fa arg
before one of the
.Fn callout_schedule
functions can be used.
.Pp
The callout subsystem provides a softclock thread for each CPU in the system.
Callouts are assigned to a single CPU and are executed by the softclock thread
for that CPU.
Initially,
callouts are assigned to CPU 0.
The
.Fn callout_reset_on ,
.Fn callout_reset_sbt_on ,
.Fn callout_schedule_on
and
.Fn callout_schedule_sbt_on
functions assign the callout to CPU
.Fa cpu .
The
.Fn callout_reset_curcpu ,
.Fn callout_reset_sbt_curpu ,
.Fn callout_schedule_curcpu
and
.Fn callout_schedule_sbt_curcpu
functions assign the callout to the current CPU.
The
.Fn callout_reset ,
.Fn callout_reset_sbt ,
.Fn callout_schedule
and
.Fn callout_schedule_sbt
functions schedule the callout to execute in the softclock thread of the CPU
to which it is currently assigned.
.Pp
Softclock threads are not pinned to their respective CPUs by default.
The softclock thread for CPU 0 can be pinned to CPU 0 by setting the
.Va kern.pin_default_swi
@ -531,7 +427,50 @@ Softclock threads for CPUs other than zero can be pinned to their
respective CPUs by setting the
.Va kern.pin_pcpu_swi
loader tunable to a non-zero value.
.Sh "AVOIDING RACE CONDITIONS"
.Pp
The macros
.Fn callout_pending ,
.Fn callout_active
and
.Fn callout_deactivate
provide access to the current state of the callout.
The
.Fn callout_pending
macro checks whether a callout is
.Em pending ;
a callout is considered
.Em pending
when a timeout has been set but the time has not yet arrived.
Note that once the timeout time arrives and the callout subsystem
starts to process this callout,
.Fn callout_pending
will return
.Dv FALSE
even though the callout function may not have finished
.Pq or even begun
executing.
The
.Fn callout_active
macro checks whether a callout is marked as
.Em active ,
and the
.Fn callout_deactivate
macro clears the callout's
.Em active
flag.
The callout subsystem marks a callout as
.Em active
when a timeout is set and it clears the
.Em active
flag in
.Fn callout_stop
and
.Fn callout_drain ,
but it
.Em does not
clear it when a callout expires normally via the execution of the
callout function.
.Ss "Avoiding Race Conditions"
The callout subsystem invokes callout functions from its own thread
context.
Without some kind of synchronization,
@ -548,7 +487,7 @@ synchronization concerns.
The first approach is preferred as it is the simplest:
.Bl -enum -offset indent
.It
Callouts can be associated with a specific lock when they are initialised
Callouts can be associated with a specific lock when they are initialized
by
.Fn callout_init_mtx ,
.Fn callout_init_rm ,
@ -569,7 +508,7 @@ or
.Fn callout_schedule
functions to provide this safety.
.Pp
A callout initialised via
A callout initialized via
.Fn callout_init
with
.Fa mpsafe
@ -592,8 +531,9 @@ function families
.Pc
indicates whether or not the callout was removed.
If it is known that the callout was set and the callout function has
not yet executed, then a return value of zero indicates that the
callout function is about to be called.
not yet executed, then a return value of
.Dv FALSE
indicates that the callout function is about to be called.
For example:
.Bd -literal -offset indent
if (sc->sc_flags & SCFLG_CALLOUT_RUNNING) {
@ -649,14 +589,16 @@ The callout function should first check the
.Em pending
flag and return without action if
.Fn callout_pending
returns non-zero.
returns
.Dv TRUE .
This indicates that the callout was rescheduled using
.Fn callout_reset
just before the callout function was invoked.
If
.Fn callout_active
returns zero then the callout function should also return without
action.
returns
.Dv FALSE
then the callout function should also return without action.
This indicates that the callout has been stopped.
Finally, the callout function should call
.Fn callout_deactivate
@ -726,13 +668,129 @@ a callout should always be drained prior to destroying its associated lock
or releasing the storage for the callout structure.
.Sh LEGACY API
.Bf Sy
The
.Fn timeout
and
.Fn untimeout
functions are a legacy API that will be removed in a future release.
The functions below are a legacy API that will be removed in a future release.
New code should not use these routines.
.Ef
.Pp
The function
.Fn timeout
schedules a call to the function given by the argument
.Fa func
to take place after
.Fa ticks Ns No /hz
seconds.
Non-positive values of
.Fa ticks
are silently converted to the value
.Sq 1 .
.Fa func
should be a pointer to a function that takes a
.Fa void *
argument.
Upon invocation,
.Fa func
will receive
.Fa arg
as its only argument.
The return value from
.Fn timeout
is a
.Ft struct callout_handle
which can be used in conjunction with the
.Fn untimeout
function to request that a scheduled timeout be canceled.
.Pp
The function
.Fn callout_handle_init
can be used to initialize a handle to a state which will cause
any calls to
.Fn untimeout
with that handle to return with no side
effects.
.Pp
Assigning a callout handle the value of
.Fn CALLOUT_HANDLE_INITIALIZER
performs the same function as
.Fn callout_handle_init
and is provided for use on statically declared or global callout handles.
.Pp
The function
.Fn untimeout
cancels the timeout associated with
.Fa handle
using the
.Fa func
and
.Fa arg
arguments to validate the handle.
If the handle does not correspond to a timeout with
the function
.Fa func
taking the argument
.Fa arg
no action is taken.
.Fa handle
must be initialized by a previous call to
.Fn timeout ,
.Fn callout_handle_init ,
or assigned the value of
.Fn CALLOUT_HANDLE_INITIALIZER "&handle"
before being passed to
.Fn untimeout .
The behavior of calling
.Fn untimeout
with an uninitialized handle
is undefined.
.Pp
As handles are recycled by the system, it is possible (although unlikely)
that a handle from one invocation of
.Fn timeout
may match the handle of another invocation of
.Fn timeout
if both calls used the same function pointer and argument, and the first
timeout is expired or canceled before the second call.
The timeout facility offers O(1) running time for
.Fn timeout
and
.Fn untimeout .
Timeouts are executed from
.Fn softclock
with the
.Va Giant
lock held.
Thus they are protected from re-entrancy.
.Sh RETURN VALUES
The
.Fn callout_active
macro returns the state of a callout's
.Em active
flag.
.Pp
The
.Fn callout_pending
macro returns the state of a callout's
.Em pending
flag.
.Pp
The
.Fn callout_reset
and
.Fn callout_schedule
function families return non-zero if the callout was pending before the new
function invocation was scheduled.
.Pp
The
.Fn callout_stop
and
.Fn callout_drain
functions return non-zero if the callout was still pending when it was
called or zero otherwise.
The
.Fn timeout
function returns a
.Ft struct callout_handle
that can be passed to
.Fn untimeout .
.Sh HISTORY
The current timeout and untimeout routines are based on the work of
.An Adam M. Costello
@ -757,4 +815,4 @@ The current implementation replaces the long standing
.Bx
linked list
callout mechanism which offered O(n) insertion and removal running time
and did not generate or require handles for untimeout operations.
but did not generate or require handles for untimeout operations.

View File

@ -504,8 +504,7 @@ proc0_init(void *dummy __unused)
callout_init_mtx(&p->p_itcallout, &p->p_mtx, 0);
callout_init_mtx(&p->p_limco, &p->p_mtx, 0);
mtx_init(&td->td_slpmutex, "td_slpmutex", NULL, MTX_SPIN);
callout_init_mtx(&td->td_slpcallout, &td->td_slpmutex, 0);
callout_init(&td->td_slpcallout, CALLOUT_MPSAFE);
/* Create credentials. */
p->p_ucred = crget();

View File

@ -313,13 +313,15 @@ _cv_timedwait_sbt(struct cv *cvp, struct lock_object *lock, sbintime_t sbt,
DROP_GIANT();
sleepq_add(cvp, lock, cvp->cv_description, SLEEPQ_CONDVAR, 0);
sleepq_release(cvp);
sleepq_set_timeout_sbt(cvp, sbt, pr, flags);
if (lock != &Giant.lock_object) {
if (class->lc_flags & LC_SLEEPABLE)
sleepq_release(cvp);
WITNESS_SAVE(lock, lock_witness);
lock_state = class->lc_unlock(lock);
if (class->lc_flags & LC_SLEEPABLE)
sleepq_lock(cvp);
}
sleepq_lock(cvp);
rval = sleepq_timedwait(cvp, 0);
#ifdef KTRACE
@ -381,13 +383,15 @@ _cv_timedwait_sig_sbt(struct cv *cvp, struct lock_object *lock,
sleepq_add(cvp, lock, cvp->cv_description, SLEEPQ_CONDVAR |
SLEEPQ_INTERRUPTIBLE, 0);
sleepq_release(cvp);
sleepq_set_timeout_sbt(cvp, sbt, pr, flags);
if (lock != &Giant.lock_object) {
if (class->lc_flags & LC_SLEEPABLE)
sleepq_release(cvp);
WITNESS_SAVE(lock, lock_witness);
lock_state = class->lc_unlock(lock);
if (class->lc_flags & LC_SLEEPABLE)
sleepq_lock(cvp);
}
sleepq_lock(cvp);
rval = sleepq_timedwait_sig(cvp, 0);
#ifdef KTRACE

View File

@ -210,11 +210,9 @@ sleeplk(struct lock *lk, u_int flags, struct lock_object *ilk,
GIANT_SAVE();
sleepq_add(&lk->lock_object, NULL, wmesg, SLEEPQ_LK | (catch ?
SLEEPQ_INTERRUPTIBLE : 0), queue);
if ((flags & LK_TIMELOCK) && timo) {
sleepq_release(&lk->lock_object);
if ((flags & LK_TIMELOCK) && timo)
sleepq_set_timeout(&lk->lock_object, timo);
sleepq_lock(&lk->lock_object);
}
/*
* Decisional switch for real sleeping.
*/

View File

@ -93,6 +93,8 @@ SCHED_STAT_DEFINE_VAR(turnstile,
&DPCPU_NAME(sched_switch_stats[SWT_TURNSTILE]), "");
SCHED_STAT_DEFINE_VAR(sleepq,
&DPCPU_NAME(sched_switch_stats[SWT_SLEEPQ]), "");
SCHED_STAT_DEFINE_VAR(sleepqtimo,
&DPCPU_NAME(sched_switch_stats[SWT_SLEEPQTIMO]), "");
SCHED_STAT_DEFINE_VAR(relinquish,
&DPCPU_NAME(sched_switch_stats[SWT_RELINQUISH]), "");
SCHED_STAT_DEFINE_VAR(needresched,

View File

@ -236,16 +236,12 @@ _sleep(void *ident, struct lock_object *lock, int priority,
* return from cursig().
*/
sleepq_add(ident, lock, wmesg, sleepq_flags, 0);
if (sbt != 0)
sleepq_set_timeout_sbt(ident, sbt, pr, flags);
if (lock != NULL && class->lc_flags & LC_SLEEPABLE) {
sleepq_release(ident);
WITNESS_SAVE(lock, lock_witness);
lock_state = class->lc_unlock(lock);
if (sbt != 0)
sleepq_set_timeout_sbt(ident, sbt, pr, flags);
sleepq_lock(ident);
} else if (sbt != 0) {
sleepq_release(ident);
sleepq_set_timeout_sbt(ident, sbt, pr, flags);
sleepq_lock(ident);
}
if (sbt != 0 && catch)
@ -310,11 +306,8 @@ msleep_spin_sbt(void *ident, struct mtx *mtx, const char *wmesg,
* We put ourselves on the sleep queue and start our timeout.
*/
sleepq_add(ident, &mtx->lock_object, wmesg, SLEEPQ_SLEEP, 0);
if (sbt != 0) {
sleepq_release(ident);
if (sbt != 0)
sleepq_set_timeout_sbt(ident, sbt, pr, flags);
sleepq_lock(ident);
}
/*
* Can't call ktrace with any spin locks held so it can lock the

View File

@ -149,9 +149,6 @@ thread_ctor(void *mem, int size, void *arg, int flags)
audit_thread_alloc(td);
#endif
umtx_thread_alloc(td);
mtx_init(&td->td_slpmutex, "td_slpmutex", NULL, MTX_SPIN);
callout_init_mtx(&td->td_slpcallout, &td->td_slpmutex, 0);
return (0);
}
@ -165,10 +162,6 @@ thread_dtor(void *mem, int size, void *arg)
td = (struct thread *)mem;
/* make sure to drain any use of the "td->td_slpcallout" */
callout_drain(&td->td_slpcallout);
mtx_destroy(&td->td_slpmutex);
#ifdef INVARIANTS
/* Verify that this thread is in a safe state to free. */
switch (td->td_state) {
@ -551,6 +544,7 @@ thread_link(struct thread *td, struct proc *p)
LIST_INIT(&td->td_lprof[0]);
LIST_INIT(&td->td_lprof[1]);
sigqueue_init(&td->td_sigqueue, p);
callout_init(&td->td_slpcallout, CALLOUT_MPSAFE);
TAILQ_INSERT_TAIL(&p->p_threads, td, td_plist);
p->p_numthreads++;
}

File diff suppressed because it is too large Load Diff

View File

@ -152,8 +152,7 @@ static uma_zone_t sleepq_zone;
*/
static int sleepq_catch_signals(void *wchan, int pri);
static int sleepq_check_signals(void);
static int sleepq_check_timeout(struct thread *);
static void sleepq_stop_timeout(struct thread *);
static int sleepq_check_timeout(void);
#ifdef INVARIANTS
static void sleepq_dtor(void *mem, int size, void *arg);
#endif
@ -374,14 +373,17 @@ void
sleepq_set_timeout_sbt(void *wchan, sbintime_t sbt, sbintime_t pr,
int flags)
{
struct sleepqueue_chain *sc;
struct thread *td;
td = curthread;
mtx_lock_spin(&td->td_slpmutex);
sc = SC_LOOKUP(wchan);
mtx_assert(&sc->sc_lock, MA_OWNED);
MPASS(TD_ON_SLEEPQ(td));
MPASS(td->td_sleepqueue == NULL);
MPASS(wchan != NULL);
callout_reset_sbt_on(&td->td_slpcallout, sbt, pr,
sleepq_timeout, td, PCPU_GET(cpuid), flags | C_DIRECT_EXEC);
mtx_unlock_spin(&td->td_slpmutex);
}
/*
@ -557,8 +559,11 @@ sleepq_switch(void *wchan, int pri)
* Check to see if we timed out.
*/
static int
sleepq_check_timeout(struct thread *td)
sleepq_check_timeout(void)
{
struct thread *td;
td = curthread;
THREAD_LOCK_ASSERT(td, MA_OWNED);
/*
@ -568,18 +573,25 @@ sleepq_check_timeout(struct thread *td)
td->td_flags &= ~TDF_TIMEOUT;
return (EWOULDBLOCK);
}
return (0);
}
/*
* Atomically stop the timeout by using a mutex.
*/
static void
sleepq_stop_timeout(struct thread *td)
{
mtx_lock_spin(&td->td_slpmutex);
callout_stop(&td->td_slpcallout);
mtx_unlock_spin(&td->td_slpmutex);
/*
* If TDF_TIMOFAIL is set, the timeout ran after we had
* already been woken up.
*/
if (td->td_flags & TDF_TIMOFAIL)
td->td_flags &= ~TDF_TIMOFAIL;
/*
* If callout_stop() fails, then the timeout is running on
* another CPU, so synchronize with it to avoid having it
* accidentally wake up a subsequent sleep.
*/
else if (callout_stop(&td->td_slpcallout) == 0) {
td->td_flags |= TDF_TIMEOUT;
TD_SET_SLEEPING(td);
mi_switch(SW_INVOL | SWT_SLEEPQTIMO, NULL);
}
return (0);
}
/*
@ -652,11 +664,9 @@ sleepq_timedwait(void *wchan, int pri)
MPASS(!(td->td_flags & TDF_SINTR));
thread_lock(td);
sleepq_switch(wchan, pri);
rval = sleepq_check_timeout(td);
rval = sleepq_check_timeout();
thread_unlock(td);
sleepq_stop_timeout(td);
return (rval);
}
@ -667,18 +677,12 @@ sleepq_timedwait(void *wchan, int pri)
int
sleepq_timedwait_sig(void *wchan, int pri)
{
struct thread *td;
int rcatch, rvalt, rvals;
td = curthread;
rcatch = sleepq_catch_signals(wchan, pri);
rvalt = sleepq_check_timeout(td);
rvalt = sleepq_check_timeout();
rvals = sleepq_check_signals();
thread_unlock(td);
sleepq_stop_timeout(td);
thread_unlock(curthread);
if (rcatch)
return (rcatch);
if (rvals)
@ -885,49 +889,64 @@ sleepq_broadcast(void *wchan, int flags, int pri, int queue)
static void
sleepq_timeout(void *arg)
{
struct thread *td = arg;
int wakeup_swapper = 0;
struct sleepqueue_chain *sc;
struct sleepqueue *sq;
struct thread *td;
void *wchan;
int wakeup_swapper;
td = arg;
wakeup_swapper = 0;
CTR3(KTR_PROC, "sleepq_timeout: thread %p (pid %ld, %s)",
(void *)td, (long)td->td_proc->p_pid, (void *)td->td_name);
/* Handle the three cases which can happen */
/*
* First, see if the thread is asleep and get the wait channel if
* it is.
*/
thread_lock(td);
if (TD_ON_SLEEPQ(td)) {
if (TD_IS_SLEEPING(td)) {
struct sleepqueue_chain *sc;
struct sleepqueue *sq;
void *wchan;
/*
* Case I - thread is asleep and needs to be
* awoken:
*/
wchan = td->td_wchan;
sc = SC_LOOKUP(wchan);
THREAD_LOCKPTR_ASSERT(td, &sc->sc_lock);
sq = sleepq_lookup(wchan);
MPASS(sq != NULL);
td->td_flags |= TDF_TIMEOUT;
wakeup_swapper = sleepq_resume_thread(sq, td, 0);
} else {
/*
* Case II - cancel going to sleep by setting
* the timeout flag because the target thread
* is not asleep yet. It can be on another CPU
* in between sleepq_add() and one of the
* sleepq_*wait*() routines or it can be in
* sleepq_catch_signals().
*/
td->td_flags |= TDF_TIMEOUT;
}
} else {
/*
* Case III - thread is already woken up by a wakeup
* call and should not timeout. Nothing to do!
*/
if (TD_IS_SLEEPING(td) && TD_ON_SLEEPQ(td)) {
wchan = td->td_wchan;
sc = SC_LOOKUP(wchan);
THREAD_LOCKPTR_ASSERT(td, &sc->sc_lock);
sq = sleepq_lookup(wchan);
MPASS(sq != NULL);
td->td_flags |= TDF_TIMEOUT;
wakeup_swapper = sleepq_resume_thread(sq, td, 0);
thread_unlock(td);
if (wakeup_swapper)
kick_proc0();
return;
}
/*
* If the thread is on the SLEEPQ but isn't sleeping yet, it
* can either be on another CPU in between sleepq_add() and
* one of the sleepq_*wait*() routines or it can be in
* sleepq_catch_signals().
*/
if (TD_ON_SLEEPQ(td)) {
td->td_flags |= TDF_TIMEOUT;
thread_unlock(td);
return;
}
/*
* Now check for the edge cases. First, if TDF_TIMEOUT is set,
* then the other thread has already yielded to us, so clear
* the flag and resume it. If TDF_TIMEOUT is not set, then the
* we know that the other thread is not on a sleep queue, but it
* hasn't resumed execution yet. In that case, set TDF_TIMOFAIL
* to let it know that the timeout has already run and doesn't
* need to be canceled.
*/
if (td->td_flags & TDF_TIMEOUT) {
MPASS(TD_IS_SLEEPING(td));
td->td_flags &= ~TDF_TIMEOUT;
TD_CLR_SLEEPING(td);
wakeup_swapper = setrunnable(td);
} else
td->td_flags |= TDF_TIMOFAIL;
thread_unlock(td);
if (wakeup_swapper)
kick_proc0();

View File

@ -105,9 +105,7 @@ _wait_for_timeout_common(struct completion *c, long timeout, int flags)
if (c->done)
break;
sleepq_add(c, NULL, "completion", flags, 0);
sleepq_release(c);
sleepq_set_timeout(c, end - ticks);
sleepq_lock(c);
if (flags & SLEEPQ_INTERRUPTIBLE) {
if (sleepq_timedwait_sig(c, 0) != 0)
return (-ERESTARTSYS);

View File

@ -46,30 +46,19 @@ LIST_HEAD(callout_list, callout);
SLIST_HEAD(callout_slist, callout);
TAILQ_HEAD(callout_tailq, callout);
typedef void callout_func_t(void *);
struct callout_args {
sbintime_t time; /* absolute time for the event */
sbintime_t precision; /* delta allowed wrt opt */
void *arg; /* function argument */
callout_func_t *func; /* function to call */
int flags; /* flags passed to callout_reset() */
int cpu; /* CPU we're scheduled on */
};
struct callout {
union {
LIST_ENTRY(callout) le;
SLIST_ENTRY(callout) sle;
TAILQ_ENTRY(callout) tqe;
} c_links;
sbintime_t c_time; /* absolute time for the event */
sbintime_t c_time; /* ticks to the event */
sbintime_t c_precision; /* delta allowed wrt opt */
void *c_arg; /* function argument */
callout_func_t *c_func; /* function to call */
struct lock_object *c_lock; /* callback lock */
void (*c_func)(void *); /* function to call */
struct lock_object *c_lock; /* lock to handle */
int c_flags; /* state of this entry */
int c_cpu; /* CPU we're scheduled on */
volatile int c_cpu; /* CPU we're scheduled on */
};
#endif

View File

@ -45,12 +45,10 @@
#define CALLOUT_PENDING 0x0004 /* callout is waiting for timeout */
#define CALLOUT_MPSAFE 0x0008 /* callout handler is mp safe */
#define CALLOUT_RETURNUNLOCKED 0x0010 /* handler returns with mtx unlocked */
#define CALLOUT_UNUSED_5 0x0020 /* --available-- */
#define CALLOUT_DEFRESTART 0x0040 /* callout restart is deferred */
#define CALLOUT_SHAREDLOCK 0x0020 /* callout lock held in shared mode */
#define CALLOUT_DFRMIGRATION 0x0040 /* callout in deferred migration mode */
#define CALLOUT_PROCESSED 0x0080 /* callout in wheel or processing list? */
#define CALLOUT_DIRECT 0x0100 /* allow exec from hw int context */
#define CALLOUT_SET_LC(x) (((x) & 7) << 16) /* set lock class */
#define CALLOUT_GET_LC(x) (((x) >> 16) & 7) /* get lock class */
#define C_DIRECT_EXEC 0x0001 /* direct execution of callout */
#define C_PRELBITS 7
@ -67,8 +65,7 @@ struct callout_handle {
#ifdef _KERNEL
#define callout_active(c) ((c)->c_flags & CALLOUT_ACTIVE)
#define callout_deactivate(c) ((c)->c_flags &= ~CALLOUT_ACTIVE)
int callout_drain(struct callout *);
int callout_drain_async(struct callout *, callout_func_t *, void *);
#define callout_drain(c) _callout_stop_safe(c, 1)
void callout_init(struct callout *, int);
void _callout_init_lock(struct callout *, struct lock_object *, int);
#define callout_init_mtx(c, mtx, flags) \
@ -82,7 +79,7 @@ void _callout_init_lock(struct callout *, struct lock_object *, int);
NULL, (flags))
#define callout_pending(c) ((c)->c_flags & CALLOUT_PENDING)
int callout_reset_sbt_on(struct callout *, sbintime_t, sbintime_t,
callout_func_t *, void *, int, int);
void (*)(void *), void *, int, int);
#define callout_reset_sbt(c, sbt, pr, fn, arg, flags) \
callout_reset_sbt_on((c), (sbt), (pr), (fn), (arg), (c)->c_cpu, (flags))
#define callout_reset_sbt_curcpu(c, sbt, pr, fn, arg, flags) \
@ -106,7 +103,8 @@ int callout_schedule(struct callout *, int);
int callout_schedule_on(struct callout *, int, int);
#define callout_schedule_curcpu(c, on_tick) \
callout_schedule_on((c), (on_tick), PCPU_GET(cpuid))
int callout_stop(struct callout *);
#define callout_stop(c) _callout_stop_safe(c, 0)
int _callout_stop_safe(struct callout *, int);
void callout_process(sbintime_t now);
#endif

View File

@ -58,7 +58,7 @@
* in the range 5 to 9.
*/
#undef __FreeBSD_version
#define __FreeBSD_version 1100054 /* Master, propagated to newvers */
#define __FreeBSD_version 1100055 /* Master, propagated to newvers */
/*
* __FreeBSD_kernel__ indicates that this system uses the kernel of FreeBSD,

View File

@ -308,7 +308,6 @@ struct thread {
} td_uretoff; /* (k) Syscall aux returns. */
#define td_retval td_uretoff.tdu_retval
struct callout td_slpcallout; /* (h) Callout for sleep. */
struct mtx td_slpmutex; /* (h) Mutex for sleep callout */
struct trapframe *td_frame; /* (k) */
struct vm_object *td_kstack_obj;/* (a) Kstack object. */
vm_offset_t td_kstack; /* (a) Kernel VA of kstack. */
@ -365,7 +364,7 @@ do { \
#define TDF_ALLPROCSUSP 0x00000200 /* suspended by SINGLE_ALLPROC */
#define TDF_BOUNDARY 0x00000400 /* Thread suspended at user boundary */
#define TDF_ASTPENDING 0x00000800 /* Thread has some asynchronous events. */
#define TDF_UNUSED12 0x00001000 /* --available-- */
#define TDF_TIMOFAIL 0x00001000 /* Timeout from sleep after we were awake. */
#define TDF_SBDRY 0x00002000 /* Stop only on usermode boundary. */
#define TDF_UPIBLOCKED 0x00004000 /* Thread blocked on user PI mutex. */
#define TDF_NEEDSUSPCHK 0x00008000 /* Thread may need to suspend. */
@ -707,7 +706,7 @@ struct proc {
#define SWT_OWEPREEMPT 2 /* Switching due to opepreempt. */
#define SWT_TURNSTILE 3 /* Turnstile contention. */
#define SWT_SLEEPQ 4 /* Sleepq wait. */
#define SWT_UNUSED5 5 /* --available-- */
#define SWT_SLEEPQTIMO 5 /* Sleepq timeout wait. */
#define SWT_RELINQUISH 6 /* yield call. */
#define SWT_NEEDRESCHED 7 /* NEEDRESCHED was set. */
#define SWT_IDLE 8 /* Switching from the idle thread. */