| Message ID | 20181228010255.21406-3-adhemerval.zanella@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | General fixes and refactor for BZ#12683 | expand |
On 28/12/18 6:32 AM, Adhemerval Zanella wrote: > From: Adhemerval Zanella <adhemerval.zanella@linaro.com> > > With upcoming fix for BZ#12683, pthread cancellation does not act for: > > 1. If syscall is blocked but with some side effects already having > taken place (e.g. a partial read or write). > 2. After the syscall has returned. > > The main change is due the fact programs need to act in syscalls with > side-effects (for instance, to avoid leak of allocated resources or > handle partial read/write). > > This patch changes the NPTL testcase that assumes the old behavior and > also changes the tst-backtrace{5,6} to ignore the cancellable wrappers. > > Checked on i686-linux-gnu, x86_64-linux-gnu, x86_64-linux-gnux32, > aarch64-linux-gnu, arm-linux-gnueabihf, powerpc64le-linux-gnu, > powerpc-linux-gnu, sparcv9-linux-gnu, and sparc64-linux-gnu. > > * debug/tst-backtrace5.c (handle_signal): Avoid cancellable wrappers > in backtrace analysis. > * nptl/tst-cancel4.c (tf_write): Handle cancelled syscall with > side-effects. > (tf_send): Likewise. OK. Siddhesh
diff --git a/debug/tst-backtrace5.c b/debug/tst-backtrace5.c index 0e6fb1a024..dad741e12a 100644 --- a/debug/tst-backtrace5.c +++ b/debug/tst-backtrace5.c @@ -69,17 +69,18 @@ handle_signal (int signum) FAIL (); return; } - /* Do not check name for signal trampoline. */ - i = 2; - if (!match (symbols[i++], "read")) + + /* Do not check name for signal trampoline or cancellable syscall + wrappers (__syscall_cancel*). */ + for (; i < n - 1; i++) + if (match (symbols[i], "read")) + break; + if (i == n - 1) { - /* Perhaps symbols[2] is __kernel_vsyscall? */ - if (!match (symbols[i++], "read")) - { - FAIL (); - return; - } + FAIL (); + return; } + for (; i < n - 1; i++) if (!match (symbols[i], "fn")) { diff --git a/nptl/tst-cancel4.c b/nptl/tst-cancel4.c index 05325385b1..45b3d43c3b 100644 --- a/nptl/tst-cancel4.c +++ b/nptl/tst-cancel4.c @@ -166,6 +166,10 @@ tf_write (void *arg) char buf[WRITE_BUFFER_SIZE]; memset (buf, '\0', sizeof (buf)); s = write (fd, buf, sizeof (buf)); + /* The write can return a value higher than 0 (meaning partial write) + due to the SIGCANCEL, but the thread may still be pending + cancellation. */ + pthread_testcancel (); pthread_cleanup_pop (0); @@ -743,6 +747,10 @@ tf_send (void *arg) char mem[WRITE_BUFFER_SIZE]; send (tempfd2, mem, arg == NULL ? sizeof (mem) : 1, 0); + /* The send can return a value higher than 0 (meaning partial send) + due to the SIGCANCEL, but the thread may still be pending + cancellation. */ + pthread_testcancel (); pthread_cleanup_pop (0);
From: Adhemerval Zanella <adhemerval.zanella@linaro.com> With upcoming fix for BZ#12683, pthread cancellation does not act for: 1. If syscall is blocked but with some side effects already having taken place (e.g. a partial read or write). 2. After the syscall has returned. The main change is due the fact programs need to act in syscalls with side-effects (for instance, to avoid leak of allocated resources or handle partial read/write). This patch changes the NPTL testcase that assumes the old behavior and also changes the tst-backtrace{5,6} to ignore the cancellable wrappers. Checked on i686-linux-gnu, x86_64-linux-gnu, x86_64-linux-gnux32, aarch64-linux-gnu, arm-linux-gnueabihf, powerpc64le-linux-gnu, powerpc-linux-gnu, sparcv9-linux-gnu, and sparc64-linux-gnu. * debug/tst-backtrace5.c (handle_signal): Avoid cancellable wrappers in backtrace analysis. * nptl/tst-cancel4.c (tf_write): Handle cancelled syscall with side-effects. (tf_send): Likewise. --- ChangeLog | 6 ++++++ debug/tst-backtrace5.c | 19 ++++++++++--------- nptl/tst-cancel4.c | 8 ++++++++ 3 files changed, 24 insertions(+), 9 deletions(-) -- 2.17.1