From 0b8d616fb5a8ffa307b1d3af37f55c15dae14f28 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 9 Oct 2019 13:48:09 +0200 Subject: taskstats: fix data-race When assiging and testing taskstats in taskstats_exit() there's a race when setting up and reading sig->stats when a thread-group with more than one thread exits: write to 0xffff8881157bbe10 of 8 bytes by task 7951 on cpu 0: taskstats_tgid_alloc kernel/taskstats.c:567 [inline] taskstats_exit+0x6b7/0x717 kernel/taskstats.c:596 do_exit+0x2c2/0x18e0 kernel/exit.c:864 do_group_exit+0xb4/0x1c0 kernel/exit.c:983 get_signal+0x2a2/0x1320 kernel/signal.c:2734 do_signal+0x3b/0xc00 arch/x86/kernel/signal.c:815 exit_to_usermode_loop+0x250/0x2c0 arch/x86/entry/common.c:159 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline] syscall_return_slowpath arch/x86/entry/common.c:274 [inline] do_syscall_64+0x2d7/0x2f0 arch/x86/entry/common.c:299 entry_SYSCALL_64_after_hwframe+0x44/0xa9 read to 0xffff8881157bbe10 of 8 bytes by task 7949 on cpu 1: taskstats_tgid_alloc kernel/taskstats.c:559 [inline] taskstats_exit+0xb2/0x717 kernel/taskstats.c:596 do_exit+0x2c2/0x18e0 kernel/exit.c:864 do_group_exit+0xb4/0x1c0 kernel/exit.c:983 __do_sys_exit_group kernel/exit.c:994 [inline] __se_sys_exit_group kernel/exit.c:992 [inline] __x64_sys_exit_group+0x2e/0x30 kernel/exit.c:992 do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fix this by using smp_load_acquire() and smp_store_release(). Reported-by: syzbot+c5d03165a1bd1dead0c1@syzkaller.appspotmail.com Fixes: 34ec12349c8a ("taskstats: cleanup ->signal->stats allocation") Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner Acked-by: Marco Elver Reviewed-by: Will Deacon Reviewed-by: Andrea Parri Reviewed-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20191009114809.8643-1-christian.brauner@ubuntu.com --- kernel/taskstats.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 13a0f2e6ebc2..e2ac0e37c4ae 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; - struct taskstats *stats; + struct taskstats *stats_new, *stats; - if (sig->stats || thread_group_empty(tsk)) - goto ret; + /* Pairs with smp_store_release() below. */ + stats = smp_load_acquire(&sig->stats); + if (stats || thread_group_empty(tsk)) + return stats; /* No problem if kmem_cache_zalloc() fails */ - stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); - if (!sig->stats) { - sig->stats = stats; - stats = NULL; + stats = sig->stats; + if (!stats) { + /* + * Pairs with smp_store_release() above and order the + * kmem_cache_zalloc(). + */ + smp_store_release(&sig->stats, stats_new); + stats = stats_new; + stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); - if (stats) - kmem_cache_free(taskstats_cache, stats); -ret: - return sig->stats; + if (stats_new) + kmem_cache_free(taskstats_cache, stats_new); + + return stats; } /* Send pid data out on exit */ -- cgit v1.3-14-g43fede From 43cf75d96409a20ef06b756877a2e72b10a026fc Mon Sep 17 00:00:00 2001 From: chenqiwu Date: Thu, 19 Dec 2019 14:29:53 +0800 Subject: exit: panic before exit_mm() on global init exit Currently, when global init and all threads in its thread-group have exited we panic via: do_exit() -> exit_notify() -> forget_original_parent() -> find_child_reaper() This makes it hard to extract a useable coredump for global init from a kernel crashdump because by the time we panic exit_mm() will have already released global init's mm. This patch moves the panic futher up before exit_mm() is called. As was the case previously, we only panic when global init and all its threads in the thread-group have exited. Signed-off-by: chenqiwu Acked-by: Christian Brauner Acked-by: Oleg Nesterov [christian.brauner@ubuntu.com: fix typo, rewrite commit message] Link: https://lore.kernel.org/r/1576736993-10121-1-git-send-email-qiwuchen55@gmail.com Signed-off-by: Christian Brauner --- kernel/exit.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index a46a50d67002..fc364272759d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father, } write_unlock_irq(&tasklist_lock); - if (unlikely(pid_ns == &init_pid_ns)) { - panic("Attempted to kill init! exitcode=0x%08x\n", - father->signal->group_exit_code ?: father->exit_code); - } list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); @@ -786,6 +782,14 @@ void __noreturn do_exit(long code) acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { + /* + * If the last thread of global init has exited, panic + * immediately to get a useable coredump. + */ + if (unlikely(is_global_init(tsk))) + panic("Attempted to kill init! exitcode=0x%08x\n", + tsk->signal->group_exit_code ?: (int)code); + #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk->signal); -- cgit v1.3-14-g43fede From 2882d53c9c6f3b8311d225062522f03772cf0179 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Sat, 28 Dec 2019 22:24:50 -0800 Subject: seccomp: Check that seccomp_notif is zeroed out by the user This patch is a small change in enforcement of the uapi for SECCOMP_IOCTL_NOTIF_RECV ioctl. Specifically, the datastructure which is passed (seccomp_notif) must be zeroed out. Previously any of its members could be set to nonsense values, and we would ignore it. This ensures all fields are set to their zero value. Signed-off-by: Sargun Dhillon Reviewed-by: Christian Brauner Reviewed-by: Aleksa Sarai Acked-by: Tycho Andersen Link: https://lore.kernel.org/r/20191229062451.9467-2-sargun@sargun.me Fixes: 6a21cc50f0c7 ("seccomp: add a return code to trap to userspace") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook --- kernel/seccomp.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 12d2227e5786..b6ea3dcb57bf 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter, struct seccomp_notif unotif; ssize_t ret; + /* Verify that we're not given garbage to keep struct extensible. */ + ret = check_zeroed_user(buf, sizeof(unotif)); + if (ret < 0) + return ret; + if (!ret) + return -EINVAL; + memset(&unotif, 0, sizeof(unotif)); ret = down_interruptible(&filter->notif->request); -- cgit v1.3-14-g43fede From 02f4e01ce710fe20d2e5548d52bfdea52efd09d1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Jan 2020 19:04:57 -0500 Subject: tracing: Initialize val to zero in parse_entry of inject code gcc produces a variable may be uninitialized warning for "val" in parse_entry(). This is really a false positive, but the code is subtle enough to just initialize val to zero and it's not a fast path to worry about it. Marked for stable to remove the warning in the stable trees as well. Cc: stable@vger.kernel.org Fixes: 6c3edaf9fd6a3 ("tracing: Introduce trace event injection") Reported-by: kbuild test robot Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_inject.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index d45079ee62f8..22bcf7c51d1e 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -195,7 +195,7 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) unsigned long irq_flags; void *entry = NULL; int entry_size; - u64 val; + u64 val = 0; int len; entry = trace_alloc_entry(call, &entry_size); -- cgit v1.3-14-g43fede From d2ccbccb5444e9141b33cf5399927737e9ff1c3d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Jan 2020 21:56:44 -0500 Subject: tracing: Define MCOUNT_INSN_SIZE when not defined without direct calls In order to handle direct calls along side of function graph tracer, a check is made to see if the address being traced by the function graph tracer is a direct call or not. To get the address used by direct callers, the return address is subtracted by MCOUNT_INSN_SIZE. For some archs with certain configurations, MCOUNT_INSN_SIZE is undefined here. But these should not be using direct calls anyway. Just define MCOUNT_INSN_SIZE to zero in this case. Link: https://lore.kernel.org/r/202001020219.zvE3vsty%lkp@intel.com Reported-by: kbuild test robot Fixes: ff205766dbbee ("ftrace: Fix function_graph tracer interaction with BPF trampoline") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/fgraph.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index a2659735db73..1af321dec0f1 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -96,6 +96,20 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, return 0; } +/* + * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct + * functions. But those archs currently don't support direct functions + * anyway, and ftrace_find_rec_direct() is just a stub for them. + * Define MCOUNT_INSN_SIZE to keep those archs compiling. + */ +#ifndef MCOUNT_INSN_SIZE +/* Make sure this only works without direct calls */ +# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +# error MCOUNT_INSN_SIZE not defined with direct calls enabled +# endif +# define MCOUNT_INSN_SIZE 0 +#endif + int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { -- cgit v1.3-14-g43fede From b8299d362d0837ae39e87e9019ebe6b736e0f035 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 2 Jan 2020 22:02:41 -0500 Subject: tracing: Have stack tracer compile when MCOUNT_INSN_SIZE is not defined On some archs with some configurations, MCOUNT_INSN_SIZE is not defined, and this makes the stack tracer fail to compile. Just define it to zero in this case. Link: https://lore.kernel.org/r/202001020219.zvE3vsty%lkp@intel.com Cc: stable@vger.kernel.org Fixes: 4df297129f622 ("tracing: Remove most or all of stack tracer stack size from stack_max_size") Reported-by: kbuild test robot Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_stack.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4df9a209f7ca..c557f42a9397 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -283,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack) local_irq_restore(flags); } +/* Some archs may not define MCOUNT_INSN_SIZE */ +#ifndef MCOUNT_INSN_SIZE +# define MCOUNT_INSN_SIZE 0 +#endif + static void stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) -- cgit v1.3-14-g43fede From e31f7939c1c27faa5d0e3f14519eaf7c89e8a69d Mon Sep 17 00:00:00 2001 From: Wen Yang Date: Fri, 3 Jan 2020 11:02:48 +0800 Subject: ftrace: Avoid potential division by zero in function profiler The ftrace_profile->counter is unsigned long and do_div truncates it to 32 bits, which means it can test non-zero and be truncated to zero for division. Fix this issue by using div64_ul() instead. Link: http://lkml.kernel.org/r/20200103030248.14516-1-wenyang@linux.alibaba.com Cc: stable@vger.kernel.org Fixes: e330b3bcd8319 ("tracing: Show sample std dev in function profiling") Fixes: 34886c8bc590f ("tracing: add average time in function to function profiler") Signed-off-by: Wen Yang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ac99a3500076..9bf1f2cd515e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -526,8 +526,7 @@ static int function_stat_show(struct seq_file *m, void *v) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - avg = rec->time; - do_div(avg, rec->counter); + avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) goto out; #endif @@ -553,7 +552,8 @@ static int function_stat_show(struct seq_file *m, void *v) * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ - do_div(stddev, rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, + rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); -- cgit v1.3-14-g43fede From 50f9ad607ea891a9308e67b81f774c71736d1098 Mon Sep 17 00:00:00 2001 From: Kaitao Cheng Date: Tue, 31 Dec 2019 05:35:30 -0800 Subject: kernel/trace: Fix do not unregister tracepoints when register sched_migrate_task fail In the function, if register_trace_sched_migrate_task() returns error, sched_switch/sched_wakeup_new/sched_wakeup won't unregister. That is why fail_deprobe_sched_switch was added. Link: http://lkml.kernel.org/r/20191231133530.2794-1-pilgrimtao@gmail.com Cc: stable@vger.kernel.org Fixes: 478142c39c8c2 ("tracing: do not grab lock in wakeup latency function tracing") Signed-off-by: Kaitao Cheng Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_sched_wakeup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 5e43b9664eca..617e297f46dc 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -630,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr) if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_migrate_task\n"); - return; + goto fail_deprobe_sched_switch; } wakeup_reset(tr); @@ -648,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr) printk(KERN_ERR "failed to start wakeup tracer\n"); return; +fail_deprobe_sched_switch: + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); fail_deprobe_wake_new: unregister_trace_sched_wakeup_new(probe_wakeup, NULL); fail_deprobe: -- cgit v1.3-14-g43fede From 72879ee0c53e2fc17f443f7b1adcc0d5130cd934 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sat, 21 Dec 2019 15:48:25 +0000 Subject: tracing: Fix indentation issue There is a declaration that is indented one level too deeply, remove the extraneous tab. Link: http://lkml.kernel.org/r/20191221154825.33073-1-colin.king@canonical.com Signed-off-by: Colin Ian King Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_seq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 344e4c1aa09c..87de6edafd14 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -381,7 +381,7 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { - unsigned int save_len = s->seq.len; + unsigned int save_len = s->seq.len; if (s->full) return 0; -- cgit v1.3-14-g43fede From 84029fd04c201a4c7e0b07ba262664900f47c6f5 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Sat, 4 Jan 2020 12:59:43 -0800 Subject: memcg: account security cred as well to kmemcg The cred_jar kmem_cache is already memcg accounted in the current kernel but cred->security is not. Account cred->security to kmemcg. Recently we saw high root slab usage on our production and on further inspection, we found a buggy application leaking processes. Though that buggy application was contained within its memcg but we observe much more system memory overhead, couple of GiBs, during that period. This overhead can adversely impact the isolation on the system. One source of high overhead we found was cred->security objects, which have a lifetime of at least the life of the process which allocated them. Link: http://lkml.kernel.org/r/20191205223721.40034-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Chris Down Reviewed-by: Roman Gushchin Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cred.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/cred.c b/kernel/cred.c index c0a4c12d38b2..9ed51b70ed80 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void) new->magic = CRED_MAGIC; #endif - if (security_cred_alloc_blank(new, GFP_KERNEL) < 0) + if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; return new; @@ -282,7 +282,7 @@ struct cred *prepare_creds(void) new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; validate_creds(new); return new; @@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) #ifdef CONFIG_SECURITY new->security = NULL; #endif - if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; put_cred(old); -- cgit v1.3-14-g43fede From e10360f815ca6367357b2c2cfef17fc663e50f7b Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 27 Dec 2019 13:50:34 -0800 Subject: bpf: cgroup: prevent out-of-order release of cgroup bpf Before commit 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself") cgroup bpf structures were released with corresponding cgroup structures. It guaranteed the hierarchical order of destruction: children were always first. It preserved attached programs from being released before their propagated copies. But with cgroup auto-detachment there are no such guarantees anymore: cgroup bpf is released as soon as the cgroup is offline and there are no live associated sockets. It means that an attached program can be detached and released, while its propagated copy is still living in the cgroup subtree. This will obviously lead to an use-after-free bug. To reproduce the issue the following script can be used: #!/bin/bash CGROOT=/sys/fs/cgroup mkdir -p ${CGROOT}/A ${CGROOT}/B ${CGROOT}/A/C sleep 1 ./test_cgrp2_attach ${CGROOT}/A egress & A_PID=$! ./test_cgrp2_attach ${CGROOT}/B egress & B_PID=$! echo $$ > ${CGROOT}/A/C/cgroup.procs iperf -s & S_PID=$! iperf -c localhost -t 100 & C_PID=$! sleep 1 echo $$ > ${CGROOT}/B/cgroup.procs echo ${S_PID} > ${CGROOT}/B/cgroup.procs echo ${C_PID} > ${CGROOT}/B/cgroup.procs sleep 1 rmdir ${CGROOT}/A/C rmdir ${CGROOT}/A sleep 1 kill -9 ${S_PID} ${C_PID} ${A_PID} ${B_PID} On the unpatched kernel the following stacktrace can be obtained: [ 33.619799] BUG: unable to handle page fault for address: ffffbdb4801ab002 [ 33.620677] #PF: supervisor read access in kernel mode [ 33.621293] #PF: error_code(0x0000) - not-present page [ 33.622754] Oops: 0000 [#1] SMP NOPTI [ 33.623202] CPU: 0 PID: 601 Comm: iperf Not tainted 5.5.0-rc2+ #23 [ 33.625545] RIP: 0010:__cgroup_bpf_run_filter_skb+0x29f/0x3d0 [ 33.635809] Call Trace: [ 33.636118] ? __cgroup_bpf_run_filter_skb+0x2bf/0x3d0 [ 33.636728] ? __switch_to_asm+0x40/0x70 [ 33.637196] ip_finish_output+0x68/0xa0 [ 33.637654] ip_output+0x76/0xf0 [ 33.638046] ? __ip_finish_output+0x1c0/0x1c0 [ 33.638576] __ip_queue_xmit+0x157/0x410 [ 33.639049] __tcp_transmit_skb+0x535/0xaf0 [ 33.639557] tcp_write_xmit+0x378/0x1190 [ 33.640049] ? _copy_from_iter_full+0x8d/0x260 [ 33.640592] tcp_sendmsg_locked+0x2a2/0xdc0 [ 33.641098] ? sock_has_perm+0x10/0xa0 [ 33.641574] tcp_sendmsg+0x28/0x40 [ 33.641985] sock_sendmsg+0x57/0x60 [ 33.642411] sock_write_iter+0x97/0x100 [ 33.642876] new_sync_write+0x1b6/0x1d0 [ 33.643339] vfs_write+0xb6/0x1a0 [ 33.643752] ksys_write+0xa7/0xe0 [ 33.644156] do_syscall_64+0x5b/0x1b0 [ 33.644605] entry_SYSCALL_64_after_hwframe+0x44/0xa9 Fix this by grabbing a reference to the bpf structure of each ancestor on the initialization of the cgroup bpf structure, and dropping the reference at the end of releasing the cgroup bpf structure. This will restore the hierarchical order of cgroup bpf releasing, without adding any operations on hot paths. Thanks to Josef Bacik for the debugging and the initial analysis of the problem. Fixes: 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself") Reported-by: Josef Bacik Signed-off-by: Roman Gushchin Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/cgroup.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4fb20ab179fe..9e43b72eb619 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -35,8 +35,8 @@ void cgroup_bpf_offline(struct cgroup *cgrp) */ static void cgroup_bpf_release(struct work_struct *work) { - struct cgroup *cgrp = container_of(work, struct cgroup, - bpf.release_work); + struct cgroup *p, *cgrp = container_of(work, struct cgroup, + bpf.release_work); enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -65,6 +65,9 @@ static void cgroup_bpf_release(struct work_struct *work) mutex_unlock(&cgroup_mutex); + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_put(p); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -199,6 +202,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; + struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, @@ -206,6 +210,9 @@ int cgroup_bpf_inherit(struct cgroup *cgrp) if (ret) return ret; + for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) + cgroup_bpf_get(p); + for (i = 0; i < NR; i++) INIT_LIST_HEAD(&cgrp->bpf.progs[i]); -- cgit v1.3-14-g43fede From 6d4f151acf9a4f6fab09b615f246c717ddedcf0c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 6 Jan 2020 22:51:57 +0100 Subject: bpf: Fix passing modified ctx to ld/abs/ind instruction Anatoly has been fuzzing with kBdysch harness and reported a KASAN slab oob in one of the outcomes: [...] [ 77.359642] BUG: KASAN: slab-out-of-bounds in bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.360463] Read of size 4 at addr ffff8880679bac68 by task bpf/406 [ 77.361119] [ 77.361289] CPU: 2 PID: 406 Comm: bpf Not tainted 5.5.0-rc2-xfstests-00157-g2187f215eba #1 [ 77.362134] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014 [ 77.362984] Call Trace: [ 77.363249] dump_stack+0x97/0xe0 [ 77.363603] print_address_description.constprop.0+0x1d/0x220 [ 77.364251] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.365030] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.365860] __kasan_report.cold+0x37/0x7b [ 77.366365] ? bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.366940] kasan_report+0xe/0x20 [ 77.367295] bpf_skb_load_helper_8_no_cache+0x71/0x130 [ 77.367821] ? bpf_skb_load_helper_8+0xf0/0xf0 [ 77.368278] ? mark_lock+0xa3/0x9b0 [ 77.368641] ? kvm_sched_clock_read+0x14/0x30 [ 77.369096] ? sched_clock+0x5/0x10 [ 77.369460] ? sched_clock_cpu+0x18/0x110 [ 77.369876] ? bpf_skb_load_helper_8+0xf0/0xf0 [ 77.370330] ___bpf_prog_run+0x16c0/0x28f0 [ 77.370755] __bpf_prog_run32+0x83/0xc0 [ 77.371153] ? __bpf_prog_run64+0xc0/0xc0 [ 77.371568] ? match_held_lock+0x1b/0x230 [ 77.371984] ? rcu_read_lock_held+0xa1/0xb0 [ 77.372416] ? rcu_is_watching+0x34/0x50 [ 77.372826] sk_filter_trim_cap+0x17c/0x4d0 [ 77.373259] ? sock_kzfree_s+0x40/0x40 [ 77.373648] ? __get_filter+0x150/0x150 [ 77.374059] ? skb_copy_datagram_from_iter+0x80/0x280 [ 77.374581] ? do_raw_spin_unlock+0xa5/0x140 [ 77.375025] unix_dgram_sendmsg+0x33a/0xa70 [ 77.375459] ? do_raw_spin_lock+0x1d0/0x1d0 [ 77.375893] ? unix_peer_get+0xa0/0xa0 [ 77.376287] ? __fget_light+0xa4/0xf0 [ 77.376670] __sys_sendto+0x265/0x280 [ 77.377056] ? __ia32_sys_getpeername+0x50/0x50 [ 77.377523] ? lock_downgrade+0x350/0x350 [ 77.377940] ? __sys_setsockopt+0x2a6/0x2c0 [ 77.378374] ? sock_read_iter+0x240/0x240 [ 77.378789] ? __sys_socketpair+0x22a/0x300 [ 77.379221] ? __ia32_sys_socket+0x50/0x50 [ 77.379649] ? mark_held_locks+0x1d/0x90 [ 77.380059] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 77.380536] __x64_sys_sendto+0x74/0x90 [ 77.380938] do_syscall_64+0x68/0x2a0 [ 77.381324] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 77.381878] RIP: 0033:0x44c070 [...] After further debugging, turns out while in case of other helper functions we disallow passing modified ctx, the special case of ld/abs/ind instruction which has similar semantics (except r6 being the ctx argument) is missing such check. Modified ctx is impossible here as bpf_skb_load_helper_8_no_cache() and others are expecting skb fields in original position, hence, add check_ctx_reg() to reject any modified ctx. Issue was first introduced back in f1174f77b50c ("bpf/verifier: rework value tracking"). Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200106215157.3553-1-daniel@iogearbox.net --- kernel/bpf/verifier.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6f63ae7a370c..ce85e7041f0c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6264,6 +6264,7 @@ static bool may_access_skb(enum bpf_prog_type type) static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); + static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; @@ -6297,7 +6298,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) } /* check whether implicit source operand (register R6) is readable */ - err = check_reg_arg(env, BPF_REG_6, SRC_OP); + err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; @@ -6316,7 +6317,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (regs[BPF_REG_6].type != PTR_TO_CTX) { + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; @@ -6329,6 +6330,10 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + if (err < 0) + return err; + /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); -- cgit v1.3-14-g43fede