#
319301 |
|
31-May-2017 |
ngie |
MFC r319056,r319058,r319059,r319060,r319061,r319078:
r319056:
tests/sys/file/ftruncate_test: use an exit code of 1 instead of -1 with err*(3).
An exit code of -1 is implementation defined -- it's best to stick with something well-defined (1).
r319058:
Create a deterministic file in the kyua sandbox, instead of a temporary file outside the kyua sandbox
This helps ensure that the file is removed at test exit, and as a side effect, cures a warning about umasks with Coverity.
r319059:
Use an exit code of 1 instead of -1 for reasons noted in r319056
r319060:
Use main(void) instead of main(argc __unused, argv __unused)
r319061:
Don't leak accept_fd on thread completion
CID: 1296068
r319078:
Tweak r319058 slightly
- Specify an explicit mode when using O_CREAT per open(2). - Fix the error message (add missing enclosing parentheses).
MFC with: r319058
|
#
298490 |
|
22-Apr-2016 |
ngie |
MFC r298024,r298196:
r298024:
Set test_argv to NULL, not 0, if not executing a specific test
r298196:
Minor cosmetic cleanup
- Remove spurious trailing whitespace in licensing header - Remove unnecessary semi-colon after comment
|
#
188483 |
|
11-Feb-2009 |
rwatson |
Add a regresion test to determine whether or not a file descriptor is allocated in a fork(2)-inheritable way at the beginning or end of an accept(2) system call. This test creates a test thread and blocks it in accept(2), then forks a child process which tests to see if the next available file descriptor is defined or not (EBADF vs EINVAL for ftruncate(2)).
This detects a regression introduced during the network stack locking work, in which a very narrow race during which fork(2) from one thread during accept(2) in a second thread lead to an extra inherited file descriptor turned into a very wide race ensuring that a descriptor was leaked into the child even though it hadn't been returned.
PR: kern/130348
|