1.\" Copyright (c) 2007 Stephan Uphoff <ups@FreeBSD.org> 2.\" Copyright (c) 2006 Gleb Smirnoff <glebius@FreeBSD.org> 3.\" All rights reserved. 4.\" 5.\" Redistribution and use in source and binary forms, with or without 6.\" modification, are permitted provided that the following conditions 7.\" are met: 8.\" 1. Redistributions of source code must retain the above copyright 9.\" notice, this list of conditions and the following disclaimer. 10.\" 2. Redistributions in binary form must reproduce the above copyright 11.\" notice, this list of conditions and the following disclaimer in the 12.\" documentation and/or other materials provided with the distribution. 13.\" 14.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND 15.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 16.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 17.\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE 18.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 19.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 20.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 21.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 22.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 23.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 24.\" SUCH DAMAGE. 25.\" 26.\" $FreeBSD$ 27.\" 28.\" Based on rwlock.9 man page 29.Dd December 27, 2019 30.Dt RMLOCK 9 31.Os 32.Sh NAME 33.Nm rmlock , 34.Nm rm_init , 35.Nm rm_init_flags , 36.Nm rm_destroy , 37.Nm rm_rlock , 38.Nm rm_try_rlock , 39.Nm rm_wlock , 40.Nm rm_runlock , 41.Nm rm_wunlock , 42.Nm rm_wowned , 43.Nm rm_sleep , 44.Nm rm_assert , 45.Nm RM_SYSINIT , 46.Nm RM_SYSINIT_FLAGS , 47.Nm rms_init , 48.Nm rms_destroy , 49.Nm rms_rlock , 50.Nm rms_wlock , 51.Nm rms_runlock , 52.Nm rms_wunlock 53.Nd kernel reader/writer lock optimized for read-mostly access patterns 54.Sh SYNOPSIS 55.In sys/param.h 56.In sys/lock.h 57.In sys/rmlock.h 58.Ft void 59.Fn rm_init "struct rmlock *rm" "const char *name" 60.Ft void 61.Fn rm_init_flags "struct rmlock *rm" "const char *name" "int opts" 62.Ft void 63.Fn rm_destroy "struct rmlock *rm" 64.Ft void 65.Fn rm_rlock "struct rmlock *rm" "struct rm_priotracker* tracker" 66.Ft int 67.Fn rm_try_rlock "struct rmlock *rm" "struct rm_priotracker* tracker" 68.Ft void 69.Fn rm_wlock "struct rmlock *rm" 70.Ft void 71.Fn rm_runlock "struct rmlock *rm" "struct rm_priotracker* tracker" 72.Ft void 73.Fn rm_wunlock "struct rmlock *rm" 74.Ft int 75.Fn rm_wowned "const struct rmlock *rm" 76.Ft int 77.Fn rm_sleep "void *wchan" "struct rmlock *rm" "int priority" "const char *wmesg" "int timo" 78.Pp 79.Cd "options INVARIANTS" 80.Cd "options INVARIANT_SUPPORT" 81.Ft void 82.Fn rm_assert "struct rmlock *rm" "int what" 83.In sys/kernel.h 84.Fn RM_SYSINIT "name" "struct rmlock *rm" "const char *desc" 85.Fn RM_SYSINIT_FLAGS "name" "struct rmlock *rm" "const char *desc" "int flags" 86.Ft void 87.Fn rms_init "struct rmslock *rms" "const char *name" 88.Ft void 89.Fn rms_destroy "struct rmslock *rms" 90.Ft void 91.Fn rms_rlock "struct rmslock *rms" 92.Ft void 93.Fn rms_wlock "struct rmslock *rms" 94.Ft void 95.Fn rms_runlock "struct rmslock *rms" 96.Ft void 97.Fn rms_wunlock "struct rmslock *rms" 98.Sh DESCRIPTION 99Read-mostly locks allow shared access to protected data by multiple threads, 100or exclusive access by a single thread. 101The threads with shared access are known as 102.Em readers 103since they only read the protected data. 104A thread with exclusive access is known as a 105.Em writer 106since it can modify protected data. 107.Pp 108Read-mostly locks are designed to be efficient for locks almost exclusively 109used as reader locks and as such should be used for protecting data that 110rarely changes. 111Acquiring an exclusive lock after the lock has been locked for shared access 112is an expensive operation. 113.Pp 114Normal read-mostly locks are similar to 115.Xr rwlock 9 116locks and follow the same lock ordering rules as 117.Xr rwlock 9 118locks. 119Read-mostly locks have full priority propagation like mutexes. 120Unlike 121.Xr rwlock 9 , 122read-mostly locks propagate priority to both readers and writers. 123This is implemented via the 124.Va rm_priotracker 125structure argument supplied to 126.Fn rm_rlock 127and 128.Fn rm_runlock . 129Readers can recurse if the lock is initialized with the 130.Dv RM_RECURSE 131option; 132however, writers are never allowed to recurse. 133.Pp 134Sleeping for writers can be allowed by passing 135.Dv RM_SLEEPABLE 136to 137.Fn rm_init_flags . 138It changes lock ordering rules to the same as for 139.Xr sx 9 140locks. 141They do not propagate priority to writers, but they do propagate priority to 142readers. Note that readers are not permitted to sleep regardless of the flag. 143.Pp 144Sleepable read-mostly locks (created with 145.Fn rms_init ) 146allow sleeping for both readers and writers, but don't do priority propagation 147for either. They follow 148.Xr sx 9 149lock ordering. 150.Ss Macros and Functions 151.Bl -tag -width indent 152.It Fn rm_init "struct rmlock *rm" "const char *name" 153Initialize the read-mostly lock 154.Fa rm . 155The 156.Fa name 157description is used solely for debugging purposes. 158This function must be called before any other operations 159on the lock. 160.It Fn rm_init_flags "struct rmlock *rm" "const char *name" "int opts" 161Similar to 162.Fn rm_init , 163initialize the read-mostly lock 164.Fa rm 165with a set of optional flags. 166The 167.Fa opts 168arguments contains one or more of the following flags: 169.Bl -tag -width ".Dv RM_NOWITNESS" 170.It Dv RM_NOWITNESS 171Instruct 172.Xr witness 4 173to ignore this lock. 174.It Dv RM_RECURSE 175Allow threads to recursively acquire shared locks for 176.Fa rm . 177.It Dv RM_SLEEPABLE 178Create a sleepable read-mostly lock. 179.It Dv RM_NEW 180If the kernel has been compiled with 181.Cd "option INVARIANTS" , 182.Fn rm_init_flags 183will assert that the 184.Fa rm 185has not been initialized multiple times without intervening calls to 186.Fn rm_destroy 187unless this option is specified. 188.El 189.It Fn rm_rlock "struct rmlock *rm" "struct rm_priotracker* tracker" 190Lock 191.Fa rm 192as a reader using 193.Fa tracker 194to track read owners of a lock for priority propagation. 195This data structure is only used internally by 196.Nm 197and must persist until 198.Fn rm_runlock 199has been called. 200This data structure can be allocated on the stack since 201readers cannot sleep. 202If any thread holds this lock exclusively, the current thread blocks, 203and its priority is propagated to the exclusive holder. 204If the lock was initialized with the 205.Dv RM_RECURSE 206option the 207.Fn rm_rlock 208function can be called when the current thread has already acquired reader 209access on 210.Fa rm . 211.It Fn rm_try_rlock "struct rmlock *rm" "struct rm_priotracker* tracker" 212Try to lock 213.Fa rm 214as a reader. 215.Fn rm_try_rlock 216will return 0 if the lock cannot be acquired immediately; 217otherwise, 218the lock will be acquired and a non-zero value will be returned. 219Note that 220.Fn rm_try_rlock 221may fail even while the lock is not currently held by a writer. 222If the lock was initialized with the 223.Dv RM_RECURSE 224option, 225.Fn rm_try_rlock 226will succeed if the current thread has already acquired reader access. 227.It Fn rm_wlock "struct rmlock *rm" 228Lock 229.Fa rm 230as a writer. 231If there are any shared owners of the lock, the current thread blocks. 232The 233.Fn rm_wlock 234function cannot be called recursively. 235.It Fn rm_runlock "struct rmlock *rm" "struct rm_priotracker* tracker" 236This function releases a shared lock previously acquired by 237.Fn rm_rlock . 238The 239.Fa tracker 240argument must match the 241.Fa tracker 242argument used for acquiring the shared lock 243.It Fn rm_wunlock "struct rmlock *rm" 244This function releases an exclusive lock previously acquired by 245.Fn rm_wlock . 246.It Fn rm_destroy "struct rmlock *rm" 247This functions destroys a lock previously initialized with 248.Fn rm_init . 249The 250.Fa rm 251lock must be unlocked. 252.It Fn rm_wowned "const struct rmlock *rm" 253This function returns a non-zero value if the current thread owns an 254exclusive lock on 255.Fa rm . 256.It Fn rm_sleep "void *wchan" "struct rmlock *rm" "int priority" "const char *wmesg" "int timo" 257This function atomically releases 258.Fa rm 259while waiting for an event. 260The 261.Fa rm 262lock must be exclusively locked. 263For more details on the parameters to this function, 264see 265.Xr sleep 9 . 266.It Fn rm_assert "struct rmlock *rm" "int what" 267This function asserts that the 268.Fa rm 269lock is in the state specified by 270.Fa what . 271If the assertions are not true and the kernel is compiled with 272.Cd "options INVARIANTS" 273and 274.Cd "options INVARIANT_SUPPORT" , 275the kernel will panic. 276Currently the following base assertions are supported: 277.Bl -tag -width ".Dv RA_UNLOCKED" 278.It Dv RA_LOCKED 279Assert that current thread holds either a shared or exclusive lock 280of 281.Fa rm . 282.It Dv RA_RLOCKED 283Assert that current thread holds a shared lock of 284.Fa rm . 285.It Dv RA_WLOCKED 286Assert that current thread holds an exclusive lock of 287.Fa rm . 288.It Dv RA_UNLOCKED 289Assert that current thread holds neither a shared nor exclusive lock of 290.Fa rm . 291.El 292.Pp 293In addition, one of the following optional flags may be specified with 294.Dv RA_LOCKED , 295.Dv RA_RLOCKED , 296or 297.Dv RA_WLOCKED : 298.Bl -tag -width ".Dv RA_NOTRECURSED" 299.It Dv RA_RECURSED 300Assert that the current thread holds a recursive lock of 301.Fa rm . 302.It Dv RA_NOTRECURSED 303Assert that the current thread does not hold a recursive lock of 304.Fa rm . 305.El 306.El 307.Bl -tag -width indent 308.It Fn rms_init "struct rmslock *rms" "const char *name" 309Initialize the sleepable read-mostly lock 310.Fa rms . 311The 312.Fa name 313description is used as 314.Fa wmesg 315parameter to the 316.Xr msleep 9 317routine. 318This function must be called before any other operations on the lock. 319.It Fn rms_rlock "struct rmlock *rm" 320Lock 321.Fa rms 322as a reader. 323If any thread holds this lock exclusively, the current thread blocks. 324.It Fn rms_wlock "struct rmslock *rms" 325Lock 326.Fa rms 327as a writer. 328If the lock is already taken, the current thread blocks. 329The 330.Fn rms_wlock 331function cannot be called recursively. 332.It Fn rms_runlock "struct rmslock *rms" 333This function releases a shared lock previously acquired by 334.Fn rms_rlock . 335.It Fn rms_wunlock "struct rmslock *rms" 336This function releases an exclusive lock previously acquired by 337.Fn rms_wlock . 338.It Fn rms_destroy "struct rmslock *rms" 339This functions destroys a lock previously initialized with 340.Fn rms_init . 341The 342.Fa rms 343lock must be unlocked. 344.Sh SEE ALSO 345.Xr locking 9 , 346.Xr mutex 9 , 347.Xr panic 9 , 348.Xr rwlock 9 , 349.Xr sema 9 , 350.Xr sleep 9 , 351.Xr sx 9 352.Sh HISTORY 353These 354functions appeared in 355.Fx 7.0 . 356.Sh AUTHORS 357.An -nosplit 358The 359.Nm 360facility was written by 361.An "Stephan Uphoff" . 362This manual page was written by 363.An "Gleb Smirnoff" 364for rwlock and modified to reflect rmlock by 365.An "Stephan Uphoff" . 366.Sh BUGS 367The 368.Nm 369implementation is currently not optimized for single processor systems. 370.Pp 371.Fn rm_try_rlock 372can fail transiently even when there is no writer, while another reader 373updates the state on the local CPU. 374.Pp 375The 376.Nm 377implementation uses a single per CPU list shared by all 378rmlocks in the system. 379If rmlocks become popular, hashing to multiple per CPU queues may 380be needed to speed up the writer lock process. 381