From 57db7e4a2d92c2d3dfbca4ef8057849b2682436b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 13 Jun 2017 04:31:16 -0500 Subject: signal: Only reschedule timers on signals timers have sent Thomas Gleixner wrote: > The CRIU support added a 'feature' which allows a user space task to send > arbitrary (kernel) signals to itself. The changelog says: > > The kernel prevents sending of siginfo with positive si_code, because > these codes are reserved for kernel. I think we can allow a task to > send such a siginfo to itself. This operation should not be dangerous. > > Quite contrary to that claim, it turns out that it is outright dangerous > for signals with info->si_code == SI_TIMER. The following code sequence in > a user space task allows to crash the kernel: > > id = timer_create(CLOCK_XXX, ..... signo = SIGX); > timer_set(id, ....); > info->si_signo = SIGX; > info->si_code = SI_TIMER: > info->_sifields._timer._tid = id; > info->_sifields._timer._sys_private = 2; > rt_[tg]sigqueueinfo(..., SIGX, info); > sigemptyset(&sigset); > sigaddset(&sigset, SIGX); > rt_sigtimedwait(sigset, info); > > For timers based on CLOCK_PROCESS_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID this > results in a kernel crash because sigwait() dequeues the signal and the > dequeue code observes: > > info->si_code == SI_TIMER && info->_sifields._timer._sys_private != 0 > > which triggers the following callchain: > > do_schedule_next_timer() -> posix_cpu_timer_schedule() -> arm_timer() > > arm_timer() executes a list_add() on the timer, which is already armed via > the timer_set() syscall. That's a double list add which corrupts the posix > cpu timer list. As a consequence the kernel crashes on the next operation > touching the posix cpu timer list. > > Posix clocks which are internally implemented based on hrtimers are not > affected by this because hrtimer_start() can handle already armed timers > nicely, but it's a reliable way to trigger the WARN_ON() in > hrtimer_forward(), which complains about calling that function on an > already armed timer. This problem has existed since the posix timer code was merged into 2.5.63. A few releases earlier in 2.5.60 ptrace gained the ability to inject not just a signal (which linux has supported since 1.0) but the full siginfo of a signal. The core problem is that the code will reschedule in response to signals getting dequeued not just for signals the timers sent but for other signals that happen to a si_code of SI_TIMER. Avoid this confusion by testing to see if the queued signal was preallocated as all timer signals are preallocated, and so far only the timer code preallocates signals. Move the check for if a timer needs to be rescheduled up into collect_signal where the preallocation check must be performed, and pass the result back to dequeue_signal where the code reschedules timers. This makes it clear why the code cares about preallocated timers. Cc: stable@vger.kernel.org Reported-by: Thomas Gleixner History Tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Reference: 66dd34ad31e5 ("signal: allow to send any siginfo to itself") Reference: 1669ce53e2ff ("Add PTRACE_GETSIGINFO and PTRACE_SETSIGINFO") Fixes: db8b50ba75f2 ("[PATCH] POSIX clocks & timers") Signed-off-by: "Eric W. Biederman" --- kernel/signal.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/signal.c b/kernel/signal.c index ca92bcfeb322..45b4c1ffe14e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -510,7 +510,8 @@ int unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) +static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, + bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -532,6 +533,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); + + *resched_timer = + (first->flags & SIGQUEUE_PREALLOC) && + (info->si_code == SI_TIMER) && + (info->si_sys_private); + __sigqueue_free(first); } else { /* @@ -548,12 +555,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info) + siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info); + collect_signal(sig, pending, info, resched_timer); return sig; } @@ -565,15 +572,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, */ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) { + bool resched_timer = false; int signr; /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ - signr = __dequeue_signal(&tsk->pending, mask, info); + signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info); + mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS /* * itimer signal ? @@ -621,7 +629,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) current->jobctl |= JOBCTL_STOP_DEQUEUED; } #ifdef CONFIG_POSIX_TIMERS - if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { + if (resched_timer) { /* * Release the siglock to ensure proper locking order * of timer locks outside of siglocks. Note, we leave -- cgit v1.2.3 From ceea5e3771ed2378668455fa21861bead7504df5 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 8 Jun 2017 16:44:20 -0700 Subject: time: Fix clock->read(clock) race around clocksource changes In tests, which excercise switching of clocksources, a NULL pointer dereference can be observed on AMR64 platforms in the clocksource read() function: u64 clocksource_mmio_readl_down(struct clocksource *c) { return ~(u64)readl_relaxed(to_mmio_clksrc(c)->reg) & c->mask; } This is called from the core timekeeping code via: cycle_now = tkr->read(tkr->clock); tkr->read is the cached tkr->clock->read() function pointer. When the clocksource is changed then tkr->clock and tkr->read are updated sequentially. The code above results in a sequential load operation of tkr->read and tkr->clock as well. If the store to tkr->clock hits between the loads of tkr->read and tkr->clock, then the old read() function is called with the new clock pointer. As a consequence the read() function dereferences a different data structure and the resulting 'reg' pointer can point anywhere including NULL. This problem was introduced when the timekeeping code was switched over to use struct tk_read_base. Before that, it was theoretically possible as well when the compiler decided to reload clock in the code sequence: now = tk->clock->read(tk->clock); Add a helper function which avoids the issue by reading tk_read_base->clock once into a local variable clk and then issue the read function via clk->read(clk). This guarantees that the read() function always gets the proper clocksource pointer handed in. Since there is now no use for the tkr.read pointer, this patch also removes it, and to address stopping the fast timekeeper during suspend/resume, it introduces a dummy clocksource to use rather then just a dummy read function. Signed-off-by: John Stultz Acked-by: Ingo Molnar Cc: Prarit Bhargava Cc: Richard Cochran Cc: Stephen Boyd Cc: stable Cc: Miroslav Lichvar Cc: Daniel Mentz Link: http://lkml.kernel.org/r/1496965462-20003-2-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/timekeeper_internal.h | 1 - kernel/time/timekeeping.c | 52 +++++++++++++++++++++++++------------ 2 files changed, 36 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 110f4532188c..e9834ada4d0c 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -29,7 +29,6 @@ */ struct tk_read_base { struct clocksource *clock; - u64 (*read)(struct clocksource *cs); u64 mask; u64 cycle_last; u32 mult; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 9652bc57fd09..eff94cb8e89e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -118,6 +118,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +/* + * tk_clock_read - atomic clocksource read() helper + * + * This helper is necessary to use in the read paths because, while the + * seqlock ensures we don't return a bad value while structures are updated, + * it doesn't protect from potential crashes. There is the possibility that + * the tkr's clocksource may change between the read reference, and the + * clock reference passed to the read function. This can cause crashes if + * the wrong clocksource is passed to the wrong read function. + * This isn't necessary to use when holding the timekeeper_lock or doing + * a read of the fast-timekeeper tkrs (which is protected by its own locking + * and update logic). + */ +static inline u64 tk_clock_read(struct tk_read_base *tkr) +{ + struct clocksource *clock = READ_ONCE(tkr->clock); + + return clock->read(clock); +} + #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ @@ -175,7 +195,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) */ do { seq = read_seqcount_begin(&tk_core.seq); - now = tkr->read(tkr->clock); + now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; @@ -209,7 +229,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) u64 cycle_now, delta; /* read clocksource */ - cycle_now = tkr->read(tkr->clock); + cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); @@ -238,12 +258,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; - tk->tkr_mono.read = clock->read; tk->tkr_mono.mask = clock->mask; - tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; - tk->tkr_raw.read = clock->read; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; @@ -404,7 +422,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) now += timekeeping_delta_to_ns(tkr, clocksource_delta( - tkr->read(tkr->clock), + tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_retry(&tkf->seq, seq)); @@ -461,6 +479,10 @@ static u64 dummy_clock_read(struct clocksource *cs) return cycles_at_suspend; } +static struct clocksource dummy_clock = { + .read = dummy_clock_read, +}; + /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. @@ -477,13 +499,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk) struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - cycles_at_suspend = tkr->read(tkr->clock); - tkr_dummy.read = dummy_clock_read; + cycles_at_suspend = tk_clock_read(tkr); + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - tkr_dummy.read = dummy_clock_read; + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } @@ -649,11 +671,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr_mono.clock; u64 cycle_now, delta; u64 nsec; - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -929,8 +950,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) do { seq = read_seqcount_begin(&tk_core.seq); - - now = tk->tkr_mono.read(tk->tkr_mono.clock); + now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, @@ -1108,7 +1128,7 @@ int get_device_system_crosststamp(int (*get_time_fn) * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ - now = tk->tkr_mono.read(tk->tkr_mono.clock); + now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!cycle_between(interval_start, cycles, now)) { clock_was_set_seq = tk->clock_was_set_seq; @@ -1629,7 +1649,7 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && cycle_now > tk->tkr_mono.cycle_last) { u64 nsec, cyc_delta; @@ -2030,7 +2050,7 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif -- cgit v1.2.3 From 3d88d56c5873f6eebe23e05c3da701960146b801 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 8 Jun 2017 16:44:21 -0700 Subject: time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting Due to how the MONOTONIC_RAW accumulation logic was handled, there is the potential for a 1ns discontinuity when we do accumulations. This small discontinuity has for the most part gone un-noticed, but since ARM64 enabled CLOCK_MONOTONIC_RAW in their vDSO clock_gettime implementation, we've seen failures with the inconsistency-check test in kselftest. This patch addresses the issue by using the same sub-ns accumulation handling that CLOCK_MONOTONIC uses, which avoids the issue for in-kernel users. Since the ARM64 vDSO implementation has its own clock_gettime calculation logic, this patch reduces the frequency of errors, but failures are still seen. The ARM64 vDSO will need to be updated to include the sub-nanosecond xtime_nsec values in its calculation for this issue to be completely fixed. Signed-off-by: John Stultz Tested-by: Daniel Mentz Cc: Prarit Bhargava Cc: Kevin Brodsky Cc: Richard Cochran Cc: Stephen Boyd Cc: Will Deacon Cc: "stable #4 . 8+" Cc: Miroslav Lichvar Link: http://lkml.kernel.org/r/1496965462-20003-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/timekeeper_internal.h | 4 ++-- kernel/time/timekeeping.c | 19 ++++++++++--------- 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e9834ada4d0c..f7043ccca81c 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -57,7 +57,7 @@ struct tk_read_base { * interval. * @xtime_remainder: Shifted nano seconds left over when rounding * @cycle_interval - * @raw_interval: Raw nano seconds accumulated per NTP interval. + * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. * @ntp_error: Difference between accumulated time and NTP time in ntp * shifted nano seconds. * @ntp_error_shift: Shift conversion between clock shifted nano seconds and @@ -99,7 +99,7 @@ struct timekeeper { u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; - u32 raw_interval; + u64 raw_interval; /* The ntp_tick_length() value currently being used. * This cached copy ensures we consistently apply the tick * length for an entire tick, as ntp_tick_length may change diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index eff94cb8e89e..b602c48cb841 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -280,7 +280,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; - tk->raw_interval = (interval * clock->mult) >> clock->shift; + tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { @@ -1996,7 +1996,7 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; - u64 raw_nsecs; + u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) @@ -2011,14 +2011,15 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ - raw_nsecs = (u64)tk->raw_interval << shift; - raw_nsecs += tk->raw_time.tv_nsec; - if (raw_nsecs >= NSEC_PER_SEC) { - u64 raw_secs = raw_nsecs; - raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); - tk->raw_time.tv_sec += raw_secs; + tk->tkr_raw.xtime_nsec += (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift; + tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; + snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; + while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { + tk->tkr_raw.xtime_nsec -= snsec_per_sec; + tk->raw_time.tv_sec++; } - tk->raw_time.tv_nsec = raw_nsecs; + tk->raw_time.tv_nsec = tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift; + tk->tkr_raw.xtime_nsec -= (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift; /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; -- cgit v1.2.3 From 8a1898db51a3390241cd5fae267dc8aaa9db0f8b Mon Sep 17 00:00:00 2001 From: Hendrik Brueckner Date: Tue, 20 Jun 2017 12:26:39 +0200 Subject: perf/aux: Correct return code of rb_alloc_aux() if !has_aux(ev) If the event for which an AUX area is about to be allocated, does not support setting up an AUX area, rb_alloc_aux() return -ENOTSUPP. This error condition is being returned unfiltered to the user space, and, for example, the perf tools fails with: failed to mmap with 524 (INTERNAL ERROR: strerror_r(524, 0x3fff497a1c8, 512)=22) This error can be easily seen with "perf record -m 128,256 -e cpu-clock". The 524 error code maps to -ENOTSUPP (in rb_alloc_aux()). The -ENOTSUPP error code shall be only used within the kernel. So the correct error code would then be -EOPNOTSUPP. With this commit, the perf tool then reports: failed to mmap with 95 (Operation not supported) which is more clear. Signed-off-by: Hendrik Brueckner Acked-by: Alexander Shishkin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Pu Hou Cc: Thomas Gleixner Cc: Thomas-Mich Richter Cc: acme@kernel.org Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/1497954399-6355-1-git-send-email-brueckner@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- kernel/events/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 2831480c63a2..ee97196bb151 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -580,7 +580,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, int ret = -ENOMEM, max_order = 0; if (!has_aux(event)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) { /* -- cgit v1.2.3 From 6bdf6abc56b53103324dfd270a86580306e1a232 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 Jun 2017 03:04:59 +0200 Subject: bpf: prevent leaking pointer via xadd on unpriviledged Leaking kernel addresses on unpriviledged is generally disallowed, for example, verifier rejects the following: 0: (b7) r0 = 0 1: (18) r2 = 0xffff897e82304400 3: (7b) *(u64 *)(r1 +48) = r2 R2 leaks addr into ctx Doing pointer arithmetic on them is also forbidden, so that they don't turn into unknown value and then get leaked out. However, there's xadd as a special case, where we don't check the src reg for being a pointer register, e.g. the following will pass: 0: (b7) r0 = 0 1: (7b) *(u64 *)(r1 +48) = r0 2: (18) r2 = 0xffff897e82304400 ; map 4: (db) lock *(u64 *)(r1 +48) += r2 5: (95) exit We could store the pointer into skb->cb, loose the type context, and then read it out from there again to leak it eventually out of a map value. Or more easily in a different variant, too: 0: (bf) r6 = r1 1: (7a) *(u64 *)(r10 -8) = 0 2: (bf) r2 = r10 3: (07) r2 += -8 4: (18) r1 = 0x0 6: (85) call bpf_map_lookup_elem#1 7: (15) if r0 == 0x0 goto pc+3 R0=map_value(ks=8,vs=8,id=0),min_value=0,max_value=0 R6=ctx R10=fp 8: (b7) r3 = 0 9: (7b) *(u64 *)(r0 +0) = r3 10: (db) lock *(u64 *)(r0 +0) += r6 11: (b7) r0 = 0 12: (95) exit from 7 to 11: R0=inv,min_value=0,max_value=0 R6=ctx R10=fp 11: (b7) r0 = 0 12: (95) exit Prevent this by checking xadd src reg for pointer types. Also add a couple of test cases related to this. Fixes: 1be7f75d1668 ("bpf: enable non-root eBPF programs") Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Acked-by: Edward Cree Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 5 +++ tools/testing/selftests/bpf/test_verifier.c | 66 +++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 339c8a1371de..a8a725697bed 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -989,6 +989,11 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + if (is_pointer_value(env, insn->src_reg)) { + verbose("R%d leaks addr into mem\n", insn->src_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index cabb19b1e371..0ff8c55c0464 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -3748,6 +3748,72 @@ static struct bpf_test tests[] = { .result = REJECT, .errstr = "invalid bpf_context access", }, + { + "leak pointer into ctx 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_2, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 2 }, + .errstr_unpriv = "R2 leaks addr into mem", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "leak pointer into ctx 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_XADD(BPF_DW, BPF_REG_1, BPF_REG_10, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R10 leaks addr into mem", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "leak pointer into ctx 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 1 }, + .errstr_unpriv = "R2 leaks addr into ctx", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "leak pointer into map val", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr_unpriv = "R6 leaks addr into mem", + .result_unpriv = REJECT, + .result = ACCEPT, + }, { "helper access to map: full range", .insns = { -- cgit v1.2.3