diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 1 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 2 | ||||
| -rw-r--r-- | kernel/cred.c | 9 | ||||
| -rw-r--r-- | kernel/events/ring_buffer.c | 39 | ||||
| -rw-r--r-- | kernel/ptrace.c | 20 | ||||
| -rw-r--r-- | kernel/sys.c | 2 | ||||
| -rw-r--r-- | kernel/sysctl.c | 6 | ||||
| -rw-r--r-- | kernel/time/ntp.c | 2 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 5 | ||||
| -rw-r--r-- | kernel/trace/trace_events_hist.c | 3 |
10 files changed, 73 insertions, 16 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index a767c0378a15..9e59dd5f1cdf 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -30,6 +30,7 @@ KCOV_INSTRUMENT_extable.o := n # Don't self-instrument. KCOV_INSTRUMENT_kcov.o := n KASAN_SANITIZE_kcov.o := n +CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) # cond_syscall is currently not LTO compatible CFLAGS_sys_ni.o = $(DISABLE_LTO) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5680b82e6ea0..4d633ff5f546 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5542,7 +5542,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, - (1 << size * 8) - 1); + (1ULL << size * 8) - 1); } } diff --git a/kernel/cred.c b/kernel/cred.c index ecf03657e71c..efd04b2ec84c 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -448,6 +448,15 @@ int commit_creds(struct cred *new) if (task->mm) set_dumpable(task->mm, suid_dumpable); task->pdeath_signal = 0; + /* + * If a task drops privileges and becomes nondumpable, + * the dumpability change must become visible before + * the credential change; otherwise, a __ptrace_may_access() + * racing with this change may be able to attach to a task it + * shouldn't be able to attach to (as if the task had dropped + * privileges without becoming nondumpable). + * Pairs with a read barrier in __ptrace_may_access(). + */ smp_wmb(); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 99c7f199f2d4..12f351b253bb 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -49,14 +49,30 @@ static void perf_output_put_handle(struct perf_output_handle *handle) unsigned long head; again: + /* + * In order to avoid publishing a head value that goes backwards, + * we must ensure the load of @rb->head happens after we've + * incremented @rb->nest. + * + * Otherwise we can observe a @rb->head value before one published + * by an IRQ/NMI happening between the load and the increment. + */ + barrier(); head = local_read(&rb->head); /* - * IRQ/NMI can happen here, which means we can miss a head update. + * IRQ/NMI can happen here and advance @rb->head, causing our + * load above to be stale. */ - if (!local_dec_and_test(&rb->nest)) + /* + * If this isn't the outermost nesting, we don't have to update + * @rb->user_page->data_head. + */ + if (local_read(&rb->nest) > 1) { + local_dec(&rb->nest); goto out; + } /* * Since the mmap() consumer (userspace) can run on a different CPU: @@ -85,12 +101,21 @@ again: * See perf_output_begin(). */ smp_wmb(); /* B, matches C */ - rb->user_page->data_head = head; + WRITE_ONCE(rb->user_page->data_head, head); + + /* + * We must publish the head before decrementing the nest count, + * otherwise an IRQ/NMI can publish a more recent head value and our + * write will (temporarily) publish a stale value. + */ + barrier(); + local_set(&rb->nest, 0); /* - * Now check if we missed an update -- rely on previous implied - * compiler barriers to force a re-read. + * Ensure we decrement @rb->nest before we validate the @rb->head. + * Otherwise we cannot be sure we caught the 'last' nested update. */ + barrier(); if (unlikely(head != local_read(&rb->head))) { local_inc(&rb->nest); goto again; @@ -465,7 +490,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) handle->aux_flags); } - rb->user_page->aux_head = rb->aux_head; + WRITE_ONCE(rb->user_page->aux_head, rb->aux_head); if (rb_need_aux_wakeup(rb)) wakeup = true; @@ -497,7 +522,7 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; - rb->user_page->aux_head = rb->aux_head; + WRITE_ONCE(rb->user_page->aux_head, rb->aux_head); if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index fc0d667f5792..5d0838c2349e 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -323,6 +323,16 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) return -EPERM; ok: rcu_read_unlock(); + /* + * If a task drops privileges and becomes nondumpable (through a syscall + * like setresuid()) while we are trying to access it, we must ensure + * that the dumpability is read after the credentials; otherwise, + * we may be able to attach to a task that we shouldn't be able to + * attach to (as if the task had dropped privileges without becoming + * nondumpable). + * Pairs with a write barrier in commit_creds(). + */ + smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && @@ -704,6 +714,10 @@ static int ptrace_peek_siginfo(struct task_struct *child, if (arg.nr < 0) return -EINVAL; + /* Ensure arg.off fits in an unsigned long */ + if (arg.off > ULONG_MAX) + return 0; + if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else @@ -711,18 +725,20 @@ static int ptrace_peek_siginfo(struct task_struct *child, for (i = 0; i < arg.nr; ) { siginfo_t info; - s32 off = arg.off + i; + unsigned long off = arg.off + i; + bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { + found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); - if (off >= 0) /* beyond the end of the list */ + if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT diff --git a/kernel/sys.c b/kernel/sys.c index 69b9a37ecf0d..4e3082fe7dcb 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1922,7 +1922,7 @@ static int validate_prctl_map(struct prctl_mm_map *prctl_map) ((unsigned long)prctl_map->__m1 __op \ (unsigned long)prctl_map->__m2) ? 0 : -EINVAL error = __prctl_check_order(start_code, <, end_code); - error |= __prctl_check_order(start_data, <, end_data); + error |= __prctl_check_order(start_data,<=, end_data); error |= __prctl_check_order(start_brk, <=, brk); error |= __prctl_check_order(arg_start, <=, arg_end); error |= __prctl_check_order(env_start, <=, env_end); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b04776bfefc1..6483f2feef43 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2770,8 +2770,10 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int if (neg) continue; val = convmul * val / convdiv; - if ((min && val < *min) || (max && val > *max)) - continue; + if ((min && val < *min) || (max && val > *max)) { + err = -EINVAL; + break; + } *i = val; } else { val = convdiv * (*i) / convmul; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index a09ded765f6c..33b3ec9ff28d 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -700,7 +700,7 @@ static inline void process_adjtimex_modes(struct timex *txc, time_constant = max(time_constant, 0l); } - if (txc->modes & ADJ_TAI && txc->constant > 0) + if (txc->modes & ADJ_TAI && txc->constant >= 0) *time_tai = txc->constant; if (txc->modes & ADJ_OFFSET) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 601758d532c6..58936ed15f9f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -802,17 +802,18 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; + u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); + nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); - return base; - + return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8d96ae7d23c2..746d37b5599c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1641,6 +1641,9 @@ static u64 hist_field_var_ref(struct hist_field *hist_field, struct hist_elt_data *elt_data; u64 var_val = 0; + if (WARN_ON_ONCE(!elt)) + return var_val; + elt_data = elt->private_data; var_val = elt_data->var_ref_vals[hist_field->var_ref_idx]; |