From bbf8c67aa6ae8bd588f097510d887dad071f9f43 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 8 Jan 2026 19:38:36 +0800 Subject: tools: jobserver: Prevent deadlock caused by incorrect jobserver configuration and enhance error reporting When using GNU Make's jobserver feature in kernel builds, a bug in MAKEFLAGS propagation caused "--jobserver-auth=r,w" to reference an unintended file descriptor. This led to infinite loops in jobserver-exec's os.read() calls due to empty token. My shell opened /etc/passwd for some reason without closing it, and as a result, all child processes inherited this fd 3. $ ls -l /proc/self/fd total 0 lrwx------ 1 changbin changbin 64 Dec 25 13:03 0 -> /dev/pts/1 lrwx------ 1 changbin changbin 64 Dec 25 13:03 1 -> /dev/pts/1 lrwx------ 1 changbin changbin 64 Dec 25 13:03 2 -> /dev/pts/1 lr-x------ 1 changbin changbin 64 Dec 25 13:03 3 -> /etc/passwd lr-x------ 1 changbin changbin 64 Dec 25 13:03 4 -> /proc/1421383/fd In this case, the `make` should open a new file descriptor for jobserver control, but clearly, it did not do so and instead still passed fd 3 as "--jobserver-auth=3,4" in MAKEFLAGS. (The version of my gnu make is 4.3) This update ensures robustness against invalid jobserver configurations, even when `make` incorrectly pass non-pipe file descriptors. * Rejecting empty reads to prevent infinite loops on EOF. * Clearing `self.jobs` to avoid writing to incorrect files if invalid tokens are detected. * Printing detailed error messages to stderr to inform the user. Cc: Mauro Carvalho Chehab Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Changbin Du Signed-off-by: Jonathan Corbet Message-ID: <20260108113836.2976527-1-changbin.du@huawei.com> --- tools/lib/python/jobserver.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'tools/lib/python/jobserver.py') diff --git a/tools/lib/python/jobserver.py b/tools/lib/python/jobserver.py index a24f30ef4fa8..616411087725 100755 --- a/tools/lib/python/jobserver.py +++ b/tools/lib/python/jobserver.py @@ -91,6 +91,10 @@ class JobserverExec: while True: try: slot = os.read(self.reader, 8) + if not slot: + # Clear self.jobs to prevent us from probably writing incorrect file. + self.jobs = b"" + raise ValueError("unexpected empty token from jobserver fd, invalid '--jobserver-auth=' setting?") self.jobs += slot except (OSError, IOError) as e: if e.errno == errno.EWOULDBLOCK: @@ -105,7 +109,8 @@ class JobserverExec: # to sit here blocked on our child. self.claim = len(self.jobs) + 1 - except (KeyError, IndexError, ValueError, OSError, IOError): + except (KeyError, IndexError, ValueError, OSError, IOError) as e: + print(f"jobserver: warning: {repr(e)}", file=sys.stderr) # Any missing environment strings or bad fds should result in just # not being parallel. self.claim = None -- cgit v1.2.3