From e2d5b2bb769fa5f500760caba76436ba3a10a895 Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Tue, 11 May 2021 10:10:54 +0200 Subject: bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers The bpf_seq_printf, bpf_trace_printk and bpf_snprintf helpers share one per-cpu buffer that they use to store temporary data (arguments to bprintf). They "get" that buffer with try_get_fmt_tmp_buf and "put" it by the end of their scope with bpf_bprintf_cleanup. If one of these helpers gets called within the scope of one of these helpers, for example: a first bpf program gets called, uses bpf_trace_printk which calls raw_spin_lock_irqsave which is traced by another bpf program that calls bpf_snprintf, then the second "get" fails. Essentially, these helpers are not re-entrant. They would return -EBUSY and print a warning message once. This patch triples the number of bprintf buffers to allow three levels of nesting. This is very similar to what was done for tracepoints in "9594dc3c7e7 bpf: fix nested bpf tracepoints with per-cpu data" Fixes: d9c9e4db186a ("bpf: Factorize bpf_trace_printk and bpf_seq_printf") Reported-by: syzbot+63122d0bc347f18c1884@syzkaller.appspotmail.com Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210511081054.2125874-1-revest@chromium.org --- kernel/bpf/helpers.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'kernel/bpf/helpers.c') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 544773970dbc..ef658a9ea5c9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -696,34 +696,35 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, */ #define MAX_PRINTF_BUF_LEN 512 -struct bpf_printf_buf { - char tmp_buf[MAX_PRINTF_BUF_LEN]; +/* Support executing three nested bprintf helper calls on a given CPU */ +struct bpf_bprintf_buffers { + char tmp_bufs[3][MAX_PRINTF_BUF_LEN]; }; -static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf); -static DEFINE_PER_CPU(int, bpf_printf_buf_used); +static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); +static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); static int try_get_fmt_tmp_buf(char **tmp_buf) { - struct bpf_printf_buf *bufs; - int used; + struct bpf_bprintf_buffers *bufs; + int nest_level; preempt_disable(); - used = this_cpu_inc_return(bpf_printf_buf_used); - if (WARN_ON_ONCE(used > 1)) { - this_cpu_dec(bpf_printf_buf_used); + nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bufs->tmp_bufs))) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_printf_buf); - *tmp_buf = bufs->tmp_buf; + bufs = this_cpu_ptr(&bpf_bprintf_bufs); + *tmp_buf = bufs->tmp_bufs[nest_level - 1]; return 0; } void bpf_bprintf_cleanup(void) { - if (this_cpu_read(bpf_printf_buf_used)) { - this_cpu_dec(bpf_printf_buf_used); + if (this_cpu_read(bpf_bprintf_nest_level)) { + this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); } } -- cgit v1.2.3-70-g09d2 From 8afcc19fbf083a8459284d9a29b4b5ac1cb2396c Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 17 May 2021 11:28:29 +0200 Subject: bpf: Clarify a bpf_bprintf_prepare macro The per-cpu buffers contain bprintf data rather than printf arguments. The macro name and comment were a bit confusing, this rewords them in a clearer way. Signed-off-by: Florent Revest Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210517092830.1026418-1-revest@chromium.org --- kernel/bpf/helpers.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel/bpf/helpers.c') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ef658a9ea5c9..3a5ab614cbb0 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -692,13 +692,14 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, return -EINVAL; } -/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p +/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary + * arguments representation. */ -#define MAX_PRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BUF_LEN 512 /* Support executing three nested bprintf helper calls on a given CPU */ struct bpf_bprintf_buffers { - char tmp_bufs[3][MAX_PRINTF_BUF_LEN]; + char tmp_bufs[3][MAX_BPRINTF_BUF_LEN]; }; static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); @@ -761,7 +762,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) return -EBUSY; - tmp_buf_end = tmp_buf + MAX_PRINTF_BUF_LEN; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; *bin_args = (u32 *)tmp_buf; } -- cgit v1.2.3-70-g09d2 From 0af02eb2a7d76ca85a1ecaf4b3775e2c86408fab Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Mon, 17 May 2021 11:28:30 +0200 Subject: bpf: Avoid using ARRAY_SIZE on an uninitialized pointer The cppcheck static code analysis reported the following error: if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bufs->tmp_bufs))) { ^ ARRAY_SIZE is a macro that expands to sizeofs, so bufs is not actually dereferenced at runtime, and the code is actually safe. But to keep things tidy, this patch removes the need for a call to ARRAY_SIZE by extracting the size of the array into a macro. Cppcheck should no longer be confused and the code ends up being a bit cleaner. Fixes: e2d5b2bb769f ("bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers") Reported-by: kernel test robot Signed-off-by: Florent Revest Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210517092830.1026418-2-revest@chromium.org --- kernel/bpf/helpers.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/helpers.c') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3a5ab614cbb0..73443498d88f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -698,8 +698,9 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, #define MAX_BPRINTF_BUF_LEN 512 /* Support executing three nested bprintf helper calls on a given CPU */ +#define MAX_BPRINTF_NEST_LEVEL 3 struct bpf_bprintf_buffers { - char tmp_bufs[3][MAX_BPRINTF_BUF_LEN]; + char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; }; static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); @@ -711,7 +712,7 @@ static int try_get_fmt_tmp_buf(char **tmp_buf) preempt_disable(); nest_level = this_cpu_inc_return(bpf_bprintf_nest_level); - if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bufs->tmp_bufs))) { + if (WARN_ON_ONCE(nest_level > MAX_BPRINTF_NEST_LEVEL)) { this_cpu_dec(bpf_bprintf_nest_level); preempt_enable(); return -EBUSY; -- cgit v1.2.3-70-g09d2 From ff40e51043af63715ab413995ff46996ecf9583f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 28 May 2021 09:16:31 +0000 Subject: bpf, lockdown, audit: Fix buggy SELinux lockdown permission checks Commit 59438b46471a ("security,lockdown,selinux: implement SELinux lockdown") added an implementation of the locked_down LSM hook to SELinux, with the aim to restrict which domains are allowed to perform operations that would breach lockdown. This is indirectly also getting audit subsystem involved to report events. The latter is problematic, as reported by Ondrej and Serhei, since it can bring down the whole system via audit: 1) The audit events that are triggered due to calls to security_locked_down() can OOM kill a machine, see below details [0]. 2) It also seems to be causing a deadlock via avc_has_perm()/slow_avc_audit() when trying to wake up kauditd, for example, when using trace_sched_switch() tracepoint, see details in [1]. Triggering this was not via some hypothetical corner case, but with existing tools like runqlat & runqslower from bcc, for example, which make use of this tracepoint. Rough call sequence goes like: rq_lock(rq) -> -------------------------+ trace_sched_switch() -> | bpf_prog_xyz() -> +-> deadlock selinux_lockdown() -> | audit_log_end() -> | wake_up_interruptible() -> | try_to_wake_up() -> | rq_lock(rq) --------------+ What's worse is that the intention of 59438b46471a to further restrict lockdown settings for specific applications in respect to the global lockdown policy is completely broken for BPF. The SELinux policy rule for the current lockdown check looks something like this: allow : lockdown { }; However, this doesn't match with the 'current' task where the security_locked_down() is executed, example: httpd does a syscall. There is a tracing program attached to the syscall which triggers a BPF program to run, which ends up doing a bpf_probe_read_kernel{,_str}() helper call. The selinux_lockdown() hook does the permission check against 'current', that is, httpd in this example. httpd has literally zero relation to this tracing program, and it would be nonsensical having to write an SELinux policy rule against httpd to let the tracing helper pass. The policy in this case needs to be against the entity that is installing the BPF program. For example, if bpftrace would generate a histogram of syscall counts by user space application: bpftrace -e 'tracepoint:raw_syscalls:sys_enter { @[comm] = count(); }' bpftrace would then go and generate a BPF program from this internally. One way of doing it [for the sake of the example] could be to call bpf_get_current_task() helper and then access current->comm via one of bpf_probe_read_kernel{,_str}() helpers. So the program itself has nothing to do with httpd or any other random app doing a syscall here. The BPF program _explicitly initiated_ the lockdown check. The allow/deny policy belongs in the context of bpftrace: meaning, you want to grant bpftrace access to use these helpers, but other tracers on the system like my_random_tracer _not_. Therefore fix all three issues at the same time by taking a completely different approach for the security_locked_down() hook, that is, move the check into the program verification phase where we actually retrieve the BPF func proto. This also reliably gets the task (current) that is trying to install the BPF tracing program, e.g. bpftrace/bcc/perf/systemtap/etc, and it also fixes the OOM since we're moving this out of the BPF helper's fast-path which can be called several millions of times per second. The check is then also in line with other security_locked_down() hooks in the system where the enforcement is performed at open/load time, for example, open_kcore() for /proc/kcore access or module_sig_check() for module signatures just to pick few random ones. What's out of scope in the fix as well as in other security_locked_down() hook locations /outside/ of BPF subsystem is that if the lockdown policy changes on the fly there is no retrospective action. This requires a different discussion, potentially complex infrastructure, and it's also not clear whether this can be solved generically. Either way, it is out of scope for a suitable stable fix which this one is targeting. Note that the breakage is specifically on 59438b46471a where it started to rely on 'current' as UAPI behavior, and _not_ earlier infrastructure such as 9d1f8be5cf42 ("bpf: Restrict bpf when kernel lockdown is in confidentiality mode"). [0] https://bugzilla.redhat.com/show_bug.cgi?id=1955585, Jakub Hrozek says: I starting seeing this with F-34. When I run a container that is traced with BPF to record the syscalls it is doing, auditd is flooded with messages like: type=AVC msg=audit(1619784520.593:282387): avc: denied { confidentiality } for pid=476 comm="auditd" lockdown_reason="use of bpf to read kernel RAM" scontext=system_u:system_r:auditd_t:s0 tcontext=system_u:system_r:auditd_t:s0 tclass=lockdown permissive=0 This seems to be leading to auditd running out of space in the backlog buffer and eventually OOMs the machine. [...] auditd running at 99% CPU presumably processing all the messages, eventually I get: Apr 30 12:20:42 fedora kernel: audit: backlog limit exceeded Apr 30 12:20:42 fedora kernel: audit: backlog limit exceeded Apr 30 12:20:42 fedora kernel: audit: audit_backlog=2152579 > audit_backlog_limit=64 Apr 30 12:20:42 fedora kernel: audit: audit_backlog=2152626 > audit_backlog_limit=64 Apr 30 12:20:42 fedora kernel: audit: audit_backlog=2152694 > audit_backlog_limit=64 Apr 30 12:20:42 fedora kernel: audit: audit_lost=6878426 audit_rate_limit=0 audit_backlog_limit=64 Apr 30 12:20:45 fedora kernel: oci-seccomp-bpf invoked oom-killer: gfp_mask=0x100cca(GFP_HIGHUSER_MOVABLE), order=0, oom_score_adj=-1000 Apr 30 12:20:45 fedora kernel: CPU: 0 PID: 13284 Comm: oci-seccomp-bpf Not tainted 5.11.12-300.fc34.x86_64 #1 Apr 30 12:20:45 fedora kernel: Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014 [...] [1] https://lore.kernel.org/linux-audit/CANYvDQN7H5tVp47fbYcRasv4XF07eUbsDwT_eDCHXJUj43J7jQ@mail.gmail.com/, Serhei Makarov says: Upstream kernel 5.11.0-rc7 and later was found to deadlock during a bpf_probe_read_compat() call within a sched_switch tracepoint. The problem is reproducible with the reg_alloc3 testcase from SystemTap's BPF backend testsuite on x86_64 as well as the runqlat, runqslower tools from bcc on ppc64le. Example stack trace: [...] [ 730.868702] stack backtrace: [ 730.869590] CPU: 1 PID: 701 Comm: in:imjournal Not tainted, 5.12.0-0.rc2.20210309git144c79ef3353.166.fc35.x86_64 #1 [ 730.871605] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 [ 730.873278] Call Trace: [ 730.873770] dump_stack+0x7f/0xa1 [ 730.874433] check_noncircular+0xdf/0x100 [ 730.875232] __lock_acquire+0x1202/0x1e10 [ 730.876031] ? __lock_acquire+0xfc0/0x1e10 [ 730.876844] lock_acquire+0xc2/0x3a0 [ 730.877551] ? __wake_up_common_lock+0x52/0x90 [ 730.878434] ? lock_acquire+0xc2/0x3a0 [ 730.879186] ? lock_is_held_type+0xa7/0x120 [ 730.880044] ? skb_queue_tail+0x1b/0x50 [ 730.880800] _raw_spin_lock_irqsave+0x4d/0x90 [ 730.881656] ? __wake_up_common_lock+0x52/0x90 [ 730.882532] __wake_up_common_lock+0x52/0x90 [ 730.883375] audit_log_end+0x5b/0x100 [ 730.884104] slow_avc_audit+0x69/0x90 [ 730.884836] avc_has_perm+0x8b/0xb0 [ 730.885532] selinux_lockdown+0xa5/0xd0 [ 730.886297] security_locked_down+0x20/0x40 [ 730.887133] bpf_probe_read_compat+0x66/0xd0 [ 730.887983] bpf_prog_250599c5469ac7b5+0x10f/0x820 [ 730.888917] trace_call_bpf+0xe9/0x240 [ 730.889672] perf_trace_run_bpf_submit+0x4d/0xc0 [ 730.890579] perf_trace_sched_switch+0x142/0x180 [ 730.891485] ? __schedule+0x6d8/0xb20 [ 730.892209] __schedule+0x6d8/0xb20 [ 730.892899] schedule+0x5b/0xc0 [ 730.893522] exit_to_user_mode_prepare+0x11d/0x240 [ 730.894457] syscall_exit_to_user_mode+0x27/0x70 [ 730.895361] entry_SYSCALL_64_after_hwframe+0x44/0xae [...] Fixes: 59438b46471a ("security,lockdown,selinux: implement SELinux lockdown") Reported-by: Ondrej Mosnacek Reported-by: Jakub Hrozek Reported-by: Serhei Makarov Reported-by: Jiri Olsa Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Tested-by: Jiri Olsa Cc: Paul Moore Cc: James Morris Cc: Jerome Marchand Cc: Frank Eigler Cc: Linus Torvalds Link: https://lore.kernel.org/bpf/01135120-8bf7-df2e-cff0-1d73f1f841c3@iogearbox.net --- kernel/bpf/helpers.c | 7 +++++-- kernel/trace/bpf_trace.c | 32 ++++++++++++-------------------- 2 files changed, 17 insertions(+), 22 deletions(-) (limited to 'kernel/bpf/helpers.c') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 73443498d88f..a2f1f15ce432 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "../../lib/kstrtox.h" @@ -1069,11 +1070,13 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_snprintf: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d2d7cf6cfe83..7a52bc172841 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -215,16 +215,11 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = { static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { - int ret = security_locked_down(LOCKDOWN_BPF_READ); + int ret; - if (unlikely(ret < 0)) - goto fail; ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) - goto fail; - return ret; -fail: - memset(dst, 0, size); + memset(dst, 0, size); return ret; } @@ -246,10 +241,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_proto = { static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) { - int ret = security_locked_down(LOCKDOWN_BPF_READ); - - if (unlikely(ret < 0)) - goto fail; + int ret; /* * The strncpy_from_kernel_nofault() call will likely not fill the @@ -262,11 +254,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) - goto fail; - - return ret; -fail: - memset(dst, 0, size); + memset(dst, 0, size); return ret; } @@ -1011,16 +999,20 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: - return &bpf_probe_read_kernel_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: - return &bpf_probe_read_kernel_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: - return &bpf_probe_read_compat_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: - return &bpf_probe_read_compat_str_proto; + return security_locked_down(LOCKDOWN_BPF_READ) < 0 ? + NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: -- cgit v1.2.3-70-g09d2