From fc1e3980044f0f812252f5f164a8350376d62eb7 Mon Sep 17 00:00:00 2001 From: Gautam Menghani Date: Sun, 31 Jul 2022 14:55:29 +0530 Subject: [PATCH 1/3] selftests/seccomp: Check CAP_SYS_ADMIN capability in the test mode_filter_without_nnp In the "mode_filter_without_nnp" test in seccomp_bpf, there is currently a TODO which asks to check the capability CAP_SYS_ADMIN instead of euid. This patch adds support to check if the calling process has the flag CAP_SYS_ADMIN, and also if this flag has CAP_EFFECTIVE set. Signed-off-by: Gautam Menghani Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220731092529.28760-1-gautammenghani201@gmail.com --- tools/testing/selftests/seccomp/seccomp_bpf.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4ae6c8991307..9c2f448bb3a9 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -392,6 +392,8 @@ TEST(mode_filter_without_nnp) .filter = filter, }; long ret; + cap_t cap = cap_get_proc(); + cap_flag_value_t is_cap_sys_admin = 0; ret = prctl(PR_GET_NO_NEW_PRIVS, 0, NULL, 0, 0); ASSERT_LE(0, ret) { @@ -400,8 +402,8 @@ TEST(mode_filter_without_nnp) errno = 0; ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog, 0, 0); /* Succeeds with CAP_SYS_ADMIN, fails without */ - /* TODO(wad) check caps not euid */ - if (geteuid()) { + cap_get_flag(cap, CAP_SYS_ADMIN, CAP_EFFECTIVE, &is_cap_sys_admin); + if (!is_cap_sys_admin) { EXPECT_EQ(-1, ret); EXPECT_EQ(EACCES, errno); } else { From a1140cb215fa13dcec06d12ba0c3ee105633b7c4 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 23 Aug 2022 08:45:32 -0700 Subject: [PATCH 2/3] seccomp: Move copy_seccomp() to no failure path. Our syzbot instance reported memory leaks in do_seccomp() [0], similar to the report [1]. It shows that we miss freeing struct seccomp_filter and some objects included in it. We can reproduce the issue with the program below [2] which calls one seccomp() and two clone() syscalls. The first clone()d child exits earlier than its parent and sends a signal to kill it during the second clone(), more precisely before the fatal_signal_pending() test in copy_process(). When the parent receives the signal, it has to destroy the embryonic process and return -EINTR to user space. In the failure path, we have to call seccomp_filter_release() to decrement the filter's refcount. Initially, we called it in free_task() called from the failure path, but the commit 3a15fb6ed92c ("seccomp: release filter after task is fully dead") moved it to release_task() to notify user space as early as possible that the filter is no longer used. To keep the change and current seccomp refcount semantics, let's move copy_seccomp() just after the signal check and add a WARN_ON_ONCE() in free_task() for future debugging. [0]: unreferenced object 0xffff8880063add00 (size 256): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.914s) hex dump (first 32 bytes): 01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00 ................ ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ................ backtrace: do_seccomp (./include/linux/slab.h:600 ./include/linux/slab.h:733 kernel/seccomp.c:666 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffffc90000035000 (size 4096): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 00 00 00 00 05 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: __vmalloc_node_range (mm/vmalloc.c:3226) __vmalloc_node (mm/vmalloc.c:3261 (discriminator 4)) bpf_prog_alloc_no_stats (kernel/bpf/core.c:91) bpf_prog_alloc (kernel/bpf/core.c:129) bpf_prog_create_from_user (net/core/filter.c:1414) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffff888003fa1000 (size 1024): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: bpf_prog_alloc_no_stats (./include/linux/slab.h:600 ./include/linux/slab.h:733 kernel/bpf/core.c:95) bpf_prog_alloc (kernel/bpf/core.c:129) bpf_prog_create_from_user (net/core/filter.c:1414) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffff888006360240 (size 16): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 16 bytes): 01 00 37 00 76 65 72 6c e0 83 01 06 80 88 ff ff ..7.verl........ backtrace: bpf_prog_store_orig_filter (net/core/filter.c:1137) bpf_prog_create_from_user (net/core/filter.c:1428) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) unreferenced object 0xffff8880060183e0 (size 8): comm "repro_seccomp", pid 230, jiffies 4294687090 (age 9.915s) hex dump (first 8 bytes): 06 00 00 00 00 00 ff 7f ........ backtrace: kmemdup (mm/util.c:129) bpf_prog_store_orig_filter (net/core/filter.c:1144) bpf_prog_create_from_user (net/core/filter.c:1428) do_seccomp (kernel/seccomp.c:671 kernel/seccomp.c:708 kernel/seccomp.c:1871 kernel/seccomp.c:1991) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [1]: https://syzkaller.appspot.com/bug?id=2809bb0ac77ad9aa3f4afe42d6a610aba594a987 [2]: #define _GNU_SOURCE #include #include #include #include #include #include void main(void) { struct sock_filter filter[] = { BPF_STMT(BPF_RET | BPF_K, SECCOMP_RET_ALLOW), }; struct sock_fprog fprog = { .len = sizeof(filter) / sizeof(filter[0]), .filter = filter, }; long i, pid; syscall(__NR_seccomp, SECCOMP_SET_MODE_FILTER, 0, &fprog); for (i = 0; i < 2; i++) { pid = syscall(__NR_clone, CLONE_NEWNET | SIGKILL, NULL, NULL, 0); if (pid == 0) return; } } Fixes: 3a15fb6ed92c ("seccomp: release filter after task is fully dead") Reported-by: syzbot+ab17848fe269b573eb71@syzkaller.appspotmail.com Reported-by: Ayushman Dutta Suggested-by: Kees Cook Signed-off-by: Kuniyuki Iwashima Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220823154532.82913-1-kuniyu@amazon.com --- kernel/fork.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 08969f5aa38d..844dfdc8c639 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -535,6 +535,9 @@ void put_task_stack(struct task_struct *tsk) void free_task(struct task_struct *tsk) { +#ifdef CONFIG_SECCOMP + WARN_ON_ONCE(tsk->seccomp.filter); +#endif release_user_cpus_ptr(tsk); scs_release(tsk); @@ -2406,12 +2409,6 @@ static __latent_entropy struct task_struct *copy_process( spin_lock(¤t->sighand->siglock); - /* - * Copy seccomp details explicitly here, in case they were changed - * before holding sighand lock. - */ - copy_seccomp(p); - rv_task_fork(p); rseq_fork(p, clone_flags); @@ -2428,6 +2425,14 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_cancel_cgroup; } + /* No more failure paths after this point. */ + + /* + * Copy seccomp details explicitly here, in case they were changed + * before holding sighand lock. + */ + copy_seccomp(p); + init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); From b9069728a70c23dad00684eb994a3f5295f127cf Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 1 Dec 2022 23:39:53 -0800 Subject: [PATCH 3/3] seccomp: document the "filter_count" field Add missing kernel-doc for the 'filter_count' field in struct seccomp. seccomp.h:40: warning: Function parameter or member 'filter_count' not described in 'seccomp' Fixes: c818c03b661c ("seccomp: Report number of loaded filters in /proc/$pid/status") Signed-off-by: Randy Dunlap Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221202073953.14677-1-rdunlap@infradead.org --- include/linux/seccomp.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index d31d76be4982..175079552f68 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -27,6 +27,7 @@ struct seccomp_filter; * * @mode: indicates one of the valid values above for controlled * system calls available to a process. + * @filter_count: number of seccomp filters * @filter: must always point to a valid seccomp-filter or NULL as it is * accessed without locking during system call entry. *