diff options
author | Philippe Waroquiers <philippe.waroquiers@skynet.be> | 2018-11-03 20:18:15 +0100 |
---|---|---|
committer | Philippe Waroquiers <philippe.waroquiers@skynet.be> | 2018-12-16 21:24:29 +0100 |
commit | a65f68357f644cae11536bbb8a1699936ccf1368 (patch) | |
tree | b854564ce386c2daeb74dcd2281000856252e698 | |
parent | 76d2760bc38ada83f81087f16eb151ccc0176574 (diff) | |
download | binutils-a65f68357f644cae11536bbb8a1699936ccf1368.zip binutils-a65f68357f644cae11536bbb8a1699936ccf1368.tar.gz binutils-a65f68357f644cae11536bbb8a1699936ccf1368.tar.bz2 |
Factorize killing the children in linux-ptrace.c, and fix a 'process leak'.
Running the gdb testsuite under Valgrind started to fail after 100+ tests,
due to out of memory caused by lingering processes.
The lingering processes are caused by the combination
of a limitation in Valgrind signal handling when using PTRACE_TRACEME
and a (minor) bug in GDB.
The Valgrind limitation is : when a process is ptraced and raises
a signal, Valgrind will replace the raised signal by SIGSTOP as other
signals are masked by Valgrind when executing a system call.
Removing this limitation seems far to be trivial, valgrind signal
handling is very complex.
Due to this valgrind limitation, GDB linux_ptrace_test_ret_to_nx gets
a SIGSTOP signal instead of the expected SIGTRAP or SIGSEGV.
In such a case, linux_ptrace_test_ret_to_nx does an early return, but
does not kill the child (running under valgrind), child stays in a STOP-ped
state.
These lingering processes then eat the available system memory,
till launching a new process starts to fail.
This patch fixes the GDB minor bug by killing the child in case
linux_ptrace_test_ret_to_nx does an early return.
nat/linux-ptrace.c has 3 different logics to kill a child process.
So, this patch factorizes killing a child in the function kill_child.
The 3 different logics are:
* linux_ptrace_test_ret_to_nx is calling both kill (child, SIGKILL)
and ptrace (PTRACE_KILL, child, ...), and then is calling once
waitpid.
* linux_check_ptrace_features is calling ptrace (PTRACE_KILL, child, ...)
+ my_waitpid in a loop, as long as the waitpid status was WIFSTOPPED.
* linux_test_for_tracefork is calling once ptrace (PTRACE_KILL, child, ...)
+ my_waitpid.
The linux ptrace documentation indicates that PTRACE_KILL is deprecated,
and tells to not use it, as it might return success but not kill the tracee.
The documentation indicates to send SIGKILL directly.
I suspect that linux_ptrace_test_ret_to_nx calls both kill and ptrace just
to be sure ...
I suspect that linux_check_ptrace_features calls ptrace in a loop
to bypass the PTRACE_KILL limitation.
And it looks like linux_test_for_tracefork does not handle the PTRACE_KILL
limitation.
Also, 2 of the 3 logics are calling my_waitpid, which seems better,
as this is protecting the waitpid syscall against EINTR.
So, the logic in kill_child is just using kill (child, SIGKILL)
+ my_waitpid, and then does a few verifications to see everything worked
accordingly to the plan.
Tested on Debian/x86_64.
2018-12-16 Philippe Waroquiers <philippe.waroquiers@skynet.be>
* nat/linux-ptrace.c (kill_child): New function.
(linux_ptrace_test_ret_to_nx): Use kill_child instead of local code.
Add a call to kill_child in case of early return after fork.
(linux_check_ptrace_features): Use kill_child instead of local code.
(linux_test_for_tracefork): Likewise.
-rw-r--r-- | gdb/ChangeLog | 8 | ||||
-rw-r--r-- | gdb/nat/linux-ptrace.c | 77 |
2 files changed, 48 insertions, 37 deletions
diff --git a/gdb/ChangeLog b/gdb/ChangeLog index f3248cd..24d0e64 100644 --- a/gdb/ChangeLog +++ b/gdb/ChangeLog @@ -1,3 +1,11 @@ +2018-12-16 Philippe Waroquiers <philippe.waroquiers@skynet.be> + + * nat/linux-ptrace.c (kill_child): New function. + (linux_ptrace_test_ret_to_nx): Use kill_child instead of local code. + Add a call to kill_child in case of early return after fork. + (linux_check_ptrace_features): Use kill_child instead of local code. + (linux_test_for_tracefork): Likewise. + 2018-12-14 Tom Tromey <tom@tromey.com> * Makefile.in: Remove "alloca" comment. diff --git a/gdb/nat/linux-ptrace.c b/gdb/nat/linux-ptrace.c index 1f21ef0..49a1d01 100644 --- a/gdb/nat/linux-ptrace.c +++ b/gdb/nat/linux-ptrace.c @@ -79,6 +79,39 @@ EXTERN_C void linux_ptrace_test_ret_to_nx_instr (void); #endif /* defined __i386__ || defined __x86_64__ */ +/* Kill CHILD. WHO is used to report warnings. */ + +static void +kill_child (pid_t child, const char *who) +{ + pid_t got_pid; + int kill_status; + + if (kill (child, SIGKILL) != 0) + { + warning (_("%s: failed to kill child pid %ld %s\n"), + who, (long) child, safe_strerror (errno)); + return; + } + + errno = 0; + got_pid = my_waitpid (child, &kill_status, 0); + if (got_pid != child) + { + warning (_("%s: " + "kill waitpid returned %ld: %s"), + who, (long) got_pid, safe_strerror (errno)); + return; + } + if (!WIFSIGNALED (kill_status)) + { + warning (_("%s: " + "kill status %d is not WIFSIGNALED!"), + who, kill_status); + return; + } +} + /* Test broken off-trunk Linux kernel patchset for NX support on i386. It was removed in Fedora kernel 88fa1f0332d188795ed73d7ac2b1564e11a0b4cd. @@ -91,7 +124,7 @@ linux_ptrace_test_ret_to_nx (void) pid_t child, got_pid; gdb_byte *return_address, *pc; long l; - int status, kill_status; + int status; elf_gregset_t regs; return_address @@ -169,6 +202,7 @@ linux_ptrace_test_ret_to_nx (void) { warning (_("linux_ptrace_test_ret_to_nx: status %d is not WIFSTOPPED!"), status); + kill_child (child, "linux_ptrace_test_ret_to_nx"); return; } @@ -178,6 +212,7 @@ linux_ptrace_test_ret_to_nx (void) warning (_("linux_ptrace_test_ret_to_nx: " "WSTOPSIG %d is neither SIGTRAP nor SIGSEGV!"), (int) WSTOPSIG (status)); + kill_child (child, "linux_ptrace_test_ret_to_nx"); return; } @@ -195,26 +230,7 @@ linux_ptrace_test_ret_to_nx (void) # error "!__i386__ && !__x86_64__" #endif - kill (child, SIGKILL); - ptrace (PTRACE_KILL, child, (PTRACE_TYPE_ARG3) NULL, - (PTRACE_TYPE_ARG4) NULL); - - errno = 0; - got_pid = waitpid (child, &kill_status, 0); - if (got_pid != child) - { - warning (_("linux_ptrace_test_ret_to_nx: " - "PTRACE_KILL waitpid returned %ld: %s"), - (long) got_pid, safe_strerror (errno)); - return; - } - if (!WIFSIGNALED (kill_status)) - { - warning (_("linux_ptrace_test_ret_to_nx: " - "PTRACE_KILL status %d is not WIFSIGNALED!"), - status); - return; - } + kill_child (child, "linux_ptrace_test_ret_to_nx"); /* + 1 is there as x86* stops after the 'int3' instruction. */ if (WSTOPSIG (status) == SIGTRAP && pc == return_address + 1) @@ -352,16 +368,8 @@ linux_check_ptrace_features (void) linux_test_for_exitkill (child_pid); - /* Clean things up and kill any pending children. */ - do - { - ret = ptrace (PTRACE_KILL, child_pid, (PTRACE_TYPE_ARG3) 0, - (PTRACE_TYPE_ARG4) 0); - if (ret != 0) - warning (_("linux_check_ptrace_features: failed to kill child")); - my_waitpid (child_pid, &status, 0); - } - while (WIFSTOPPED (status)); + /* Kill child_pid. */ + kill_child (child_pid, "linux_check_ptrace_features"); } /* Determine if PTRACE_O_TRACESYSGOOD can be used to catch @@ -444,12 +452,7 @@ linux_test_for_tracefork (int child_pid) /* Do some cleanup and kill the grandchild. */ my_waitpid (second_pid, &second_status, 0); - ret = ptrace (PTRACE_KILL, second_pid, (PTRACE_TYPE_ARG3) 0, - (PTRACE_TYPE_ARG4) 0); - if (ret != 0) - warning (_("linux_test_for_tracefork: " - "failed to kill second child")); - my_waitpid (second_pid, &status, 0); + kill_child (second_pid, "linux_test_for_tracefork"); } } else |