1This directory contains the following litmus tests: 2 3CoRR+poonceonce+Once.litmus 4 Test of read-read coherence, that is, whether or not two 5 successive reads from the same variable are ordered. 6 7CoRW+poonceonce+Once.litmus 8 Test of read-write coherence, that is, whether or not a read 9 from a given variable followed by a write to that same variable 10 are ordered. 11 12CoWR+poonceonce+Once.litmus 13 Test of write-read coherence, that is, whether or not a write 14 to a given variable followed by a read from that same variable 15 are ordered. 16 17CoWW+poonceonce.litmus 18 Test of write-write coherence, that is, whether or not two 19 successive writes to the same variable are ordered. 20 21IRIW+mbonceonces+OnceOnce.litmus 22 Test of independent reads from independent writes with smp_mb() 23 between each pairs of reads. In other words, is smp_mb() 24 sufficient to cause two different reading processes to agree on 25 the order of a pair of writes, where each write is to a different 26 variable by a different process? 27 28IRIW+poonceonces+OnceOnce.litmus 29 Test of independent reads from independent writes with nothing 30 between each pairs of reads. In other words, is anything at all 31 needed to cause two different reading processes to agree on the 32 order of a pair of writes, where each write is to a different 33 variable by a different process? 34 35ISA2+poonceonces.litmus 36 As below, but with store-release replaced with WRITE_ONCE() 37 and load-acquire replaced with READ_ONCE(). 38 39ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus 40 Can a release-acquire chain order a prior store against 41 a later load? 42 43LB+ctrlonceonce+mbonceonce.litmus 44 Does a control dependency and an smp_mb() suffice for the 45 load-buffering litmus test, where each process reads from one 46 of two variables then writes to the other? 47 48LB+poacquireonce+pooncerelease.litmus 49 Does a release-acquire pair suffice for the load-buffering 50 litmus test, where each process reads from one of two variables then 51 writes to the other? 52 53LB+poonceonces.litmus 54 As above, but with store-release replaced with WRITE_ONCE() 55 and load-acquire replaced with READ_ONCE(). 56 57MP+onceassign+derefonce.litmus 58 As below, but with rcu_assign_pointer() and an rcu_dereference(). 59 60MP+polocks.litmus 61 As below, but with the second access of the writer process 62 and the first access of reader process protected by a lock. 63 64MP+poonceonces.litmus 65 As below, but without the smp_rmb() and smp_wmb(). 66 67MP+pooncerelease+poacquireonce.litmus 68 As below, but with a release-acquire chain. 69 70MP+porevlocks.litmus 71 As below, but with the first access of the writer process 72 and the second access of reader process protected by a lock. 73 74MP+wmbonceonce+rmbonceonce.litmus 75 Does a smp_wmb() (between the stores) and an smp_rmb() (between 76 the loads) suffice for the message-passing litmus test, where one 77 process writes data and then a flag, and the other process reads 78 the flag and then the data. (This is similar to the ISA2 tests, 79 but with two processes instead of three.) 80 81R+mbonceonces.litmus 82 This is the fully ordered (via smp_mb()) version of one of 83 the classic counterintuitive litmus tests that illustrates the 84 effects of store propagation delays. 85 86R+poonceonces.litmus 87 As above, but without the smp_mb() invocations. 88 89SB+mbonceonces.litmus 90 This is the fully ordered (again, via smp_mb() version of store 91 buffering, which forms the core of Dekker's mutual-exclusion 92 algorithm. 93 94SB+poonceonces.litmus 95 As above, but without the smp_mb() invocations. 96 97S+poonceonces.litmus 98 As below, but without the smp_wmb() and acquire load. 99 100S+wmbonceonce+poacquireonce.litmus 101 Can a smp_wmb(), instead of a release, and an acquire order 102 a prior store against a subsequent store? 103 104WRC+poonceonces+Once.litmus 105WRC+pooncerelease+rmbonceonce+Once.litmus 106 These two are members of an extension of the MP litmus-test class 107 in which the first write is moved to a separate process. 108 109Z6.0+pooncelock+pooncelock+pombonce.litmus 110 Is the ordering provided by a spin_unlock() and a subsequent 111 spin_lock() sufficient to make ordering apparent to accesses 112 by a process not holding the lock? 113 114Z6.0+pooncelock+poonceLock+pombonce.litmus 115 As above, but with smp_mb__after_spinlock() immediately 116 following the spin_lock(). 117 118Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus 119 Is the ordering provided by a release-acquire chain sufficient 120 to make ordering apparent to accesses by a process that does 121 not participate in that release-acquire chain? 122 123A great many more litmus tests are available here: 124 125 https://github.com/paulmckrcu/litmus 126