diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/bounds.c | 4 | ||||
| -rw-r--r-- | kernel/debug/kdb/kdb_io.c | 15 | ||||
| -rw-r--r-- | kernel/debug/kdb/kdb_private.h | 2 | ||||
| -rw-r--r-- | kernel/debug/kdb/kdb_support.c | 10 | ||||
| -rw-r--r-- | kernel/irq/manage.c | 8 | ||||
| -rw-r--r-- | kernel/kprobes.c | 27 | ||||
| -rw-r--r-- | kernel/locking/lockdep.c | 4 | ||||
| -rw-r--r-- | kernel/printk/printk.c | 7 | ||||
| -rw-r--r-- | kernel/sched/core.c | 4 | ||||
| -rw-r--r-- | kernel/seccomp.c | 148 | ||||
| -rw-r--r-- | kernel/signal.c | 2 | ||||
| -rw-r--r-- | kernel/sysctl.c | 18 |
12 files changed, 133 insertions, 116 deletions
diff --git a/kernel/bounds.c b/kernel/bounds.c index e1d1d1952bfa..c37f68d758db 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -12,7 +12,7 @@ #include <linux/log2.h> #include <linux/spinlock_types.h> -void foo(void) +int main(void) { /* The enum constants to put into include/generated/bounds.h */ DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); @@ -22,4 +22,6 @@ void foo(void) #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); /* End of constants */ + + return 0; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 3990c1f73e45..d3c5b15c86c1 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -215,7 +215,7 @@ static char *kdb_read(char *buffer, size_t bufsize) int count; int i; int diag, dtab_count; - int key; + int key, buf_size, ret; static int last_crlf; diag = kdbgetintenv("DTABCOUNT", &dtab_count); @@ -343,9 +343,8 @@ poll_again: else p_tmp = tmpbuffer; len = strlen(p_tmp); - count = kallsyms_symbol_complete(p_tmp, - sizeof(tmpbuffer) - - (p_tmp - tmpbuffer)); + buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer); + count = kallsyms_symbol_complete(p_tmp, buf_size); if (tab == 2 && count > 0) { kdb_printf("\n%d symbols are found.", count); if (count > dtab_count) { @@ -357,9 +356,13 @@ poll_again: } kdb_printf("\n"); for (i = 0; i < count; i++) { - if (WARN_ON(!kallsyms_symbol_next(p_tmp, i))) + ret = kallsyms_symbol_next(p_tmp, i, buf_size); + if (WARN_ON(!ret)) break; - kdb_printf("%s ", p_tmp); + if (ret != -E2BIG) + kdb_printf("%s ", p_tmp); + else + kdb_printf("%s... ", p_tmp); *(p_tmp + len) = '\0'; } if (i >= dtab_count) diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 75014d7f4568..533e04e75a9c 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -83,7 +83,7 @@ typedef struct __ksymtab { unsigned long sym_start; unsigned long sym_end; } kdb_symtab_t; -extern int kallsyms_symbol_next(char *prefix_name, int flag); +extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size); extern int kallsyms_symbol_complete(char *prefix_name, int max_len); /* Exported Symbols for kernel loadable modules to use. */ diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index d35cc2d3a4cc..2aed4a33521b 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len) * Parameters: * prefix_name prefix of a symbol name to lookup * flag 0 means search from the head, 1 means continue search. + * buf_size maximum length that can be written to prefix_name + * buffer * Returns: * 1 if a symbol matches the given prefix. * 0 if no string found */ -int kallsyms_symbol_next(char *prefix_name, int flag) +int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size) { int prefix_len = strlen(prefix_name); static loff_t pos; @@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag) pos = 0; while ((name = kdb_walk_kallsyms(&pos))) { - if (strncmp(name, prefix_name, prefix_len) == 0) { - strncpy(prefix_name, name, strlen(name)+1); - return 1; - } + if (!strncmp(name, prefix_name, prefix_len)) + return strscpy(prefix_name, name, buf_size); } return 0; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ec72aeb6defe..36a13b75b48f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -882,6 +882,9 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) local_bh_disable(); ret = action->thread_fn(action->irq, action->dev_id); + if (ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + irq_finalize_oneshot(desc, action); local_bh_enable(); return ret; @@ -898,6 +901,9 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc, irqreturn_t ret; ret = action->thread_fn(action->irq, action->dev_id); + if (ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + irq_finalize_oneshot(desc, action); return ret; } @@ -975,8 +981,6 @@ static int irq_thread(void *data) irq_thread_check_affinity(desc, action); action_ret = handler_fn(desc, action); - if (action_ret == IRQ_HANDLED) - atomic_inc(&desc->threads_handled); if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 388bcace62f8..d8daf6c55d2b 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -665,9 +665,10 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) } /* Cancel unoptimizing for reusing */ -static void reuse_unused_kprobe(struct kprobe *ap) +static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; + int ret; BUG_ON(!kprobe_unused(ap)); /* @@ -681,8 +682,12 @@ static void reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - BUG_ON(!kprobe_optready(ap)); + ret = kprobe_optready(ap); + if (ret) + return ret; + optimize_kprobe(ap); + return 0; } /* Remove optimized instructions */ @@ -894,11 +899,16 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) #define kprobe_disarmed(p) kprobe_disabled(p) #define wait_for_kprobe_optimizer() do {} while (0) -/* There should be no unused kprobes can be reused without optimization */ -static void reuse_unused_kprobe(struct kprobe *ap) +static int reuse_unused_kprobe(struct kprobe *ap) { + /* + * If the optimized kprobe is NOT supported, the aggr kprobe is + * released at the same time that the last aggregated kprobe is + * unregistered. + * Thus there should be no chance to reuse unused kprobe. + */ printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); - BUG_ON(kprobe_unused(ap)); + return -EINVAL; } static void free_aggr_kprobe(struct kprobe *p) @@ -1276,9 +1286,12 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) goto out; } init_aggr_kprobe(ap, orig_p); - } else if (kprobe_unused(ap)) + } else if (kprobe_unused(ap)) { /* This probe is going to die. Rescue it */ - reuse_unused_kprobe(ap); + ret = reuse_unused_kprobe(ap); + if (ret) + goto out; + } if (kprobe_gone(ap)) { /* diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 6e171b547a80..774ab79d3ec7 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3826,7 +3826,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - if (unlikely(!lock_stat)) + if (unlikely(!lock_stat || !debug_locks)) return; if (unlikely(current->lockdep_recursion)) @@ -3846,7 +3846,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - if (unlikely(!lock_stat)) + if (unlikely(!lock_stat || !debug_locks)) return; if (unlikely(current->lockdep_recursion)) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index da573aeaeb12..eb6a190c7a3a 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -885,7 +885,12 @@ static void __init log_buf_len_update(unsigned size) /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { - unsigned size = memparse(str, &str); + unsigned int size; + + if (!str) + return -EINVAL; + + size = memparse(str, &str); log_buf_len_update(size); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6a5671bdb792..6b9021b9bc26 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4205,8 +4205,8 @@ static int __sched_setscheduler(struct task_struct *p, int reset_on_fork; int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; - /* may grab non-irq protected spin_locks */ - BUG_ON(in_interrupt()); + /* The pi code expects interrupts enabled */ + BUG_ON(pi && in_interrupt()); recheck: /* double check policy once rq lock held */ if (policy < 0) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 9a9203b15cde..a39f81c7e87a 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -175,7 +175,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) * * Returns valid seccomp BPF response codes. */ -static u32 seccomp_run_filters(struct seccomp_data *sd) +static u32 seccomp_run_filters(const struct seccomp_data *sd) { struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; @@ -579,20 +579,10 @@ void secure_computing_strict(int this_syscall) BUG(); } #else -int __secure_computing(void) -{ - u32 phase1_result = seccomp_phase1(NULL); - - if (likely(phase1_result == SECCOMP_PHASE1_OK)) - return 0; - else if (likely(phase1_result == SECCOMP_PHASE1_SKIP)) - return -1; - else - return seccomp_phase2(phase1_result); -} #ifdef CONFIG_SECCOMP_FILTER -static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) +static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, + const bool recheck_after_trace) { u32 filter_ret, action; int data; @@ -624,10 +614,50 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) goto skip; case SECCOMP_RET_TRACE: - return filter_ret; /* Save the rest for phase 2. */ + /* We've been put in this state by the ptracer already. */ + if (recheck_after_trace) + return 0; + + /* ENOSYS these calls if there is no tracer attached. */ + if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { + syscall_set_return_value(current, + task_pt_regs(current), + -ENOSYS, 0); + goto skip; + } + + /* Allow the BPF to provide the event message */ + ptrace_event(PTRACE_EVENT_SECCOMP, data); + /* + * The delivery of a fatal signal during event + * notification may silently skip tracer notification, + * which could leave us with a potentially unmodified + * syscall that the tracer would have liked to have + * changed. Since the process is about to die, we just + * force the syscall to be skipped and let the signal + * kill the process and correctly handle any tracer exit + * notifications. + */ + if (fatal_signal_pending(current)) + goto skip; + /* Check if the tracer forced the syscall to be skipped. */ + this_syscall = syscall_get_nr(current, task_pt_regs(current)); + if (this_syscall < 0) + goto skip; + + /* + * Recheck the syscall, since it may have changed. This + * intentionally uses a NULL struct seccomp_data to force + * a reload of all registers. This does not goto skip since + * a skip would have already been reported. + */ + if (__seccomp_filter(this_syscall, NULL, true)) + return -1; + + return 0; case SECCOMP_RET_ALLOW: - return SECCOMP_PHASE1_OK; + return 0; case SECCOMP_RET_KILL: default: @@ -639,96 +669,38 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd) skip: audit_seccomp(this_syscall, 0, action); - return SECCOMP_PHASE1_SKIP; + return -1; +} +#else +static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, + const bool recheck_after_trace) +{ + BUG(); } #endif -/** - * seccomp_phase1() - run fast path seccomp checks on the current syscall - * @arg sd: The seccomp_data or NULL - * - * This only reads pt_regs via the syscall_xyz helpers. The only change - * it will make to pt_regs is via syscall_set_return_value, and it will - * only do that if it returns SECCOMP_PHASE1_SKIP. - * - * If sd is provided, it will not read pt_regs at all. - * - * It may also call do_exit or force a signal; these actions must be - * safe. - * - * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should - * be processed normally. - * - * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be - * invoked. In this case, seccomp_phase1 will have set the return value - * using syscall_set_return_value. - * - * If it returns anything else, then the return value should be passed - * to seccomp_phase2 from a context in which ptrace hooks are safe. - */ -u32 seccomp_phase1(struct seccomp_data *sd) +int __secure_computing(const struct seccomp_data *sd) { int mode = current->seccomp.mode; - int this_syscall = sd ? sd->nr : - syscall_get_nr(current, task_pt_regs(current)); + int this_syscall; if (config_enabled(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) - return SECCOMP_PHASE1_OK; + return 0; + + this_syscall = sd ? sd->nr : + syscall_get_nr(current, task_pt_regs(current)); switch (mode) { case SECCOMP_MODE_STRICT: __secure_computing_strict(this_syscall); /* may call do_exit */ - return SECCOMP_PHASE1_OK; -#ifdef CONFIG_SECCOMP_FILTER + return 0; case SECCOMP_MODE_FILTER: - return __seccomp_phase1_filter(this_syscall, sd); -#endif + return __seccomp_filter(this_syscall, sd, false); default: BUG(); } } - -/** - * seccomp_phase2() - finish slow path seccomp work for the current syscall - * @phase1_result: The return value from seccomp_phase1() - * - * This must be called from a context in which ptrace hooks can be used. - * - * Returns 0 if the syscall should be processed or -1 to skip the syscall. - */ -int seccomp_phase2(u32 phase1_result) -{ - struct pt_regs *regs = task_pt_regs(current); - u32 action = phase1_result & SECCOMP_RET_ACTION; - int data = phase1_result & SECCOMP_RET_DATA; - - BUG_ON(action != SECCOMP_RET_TRACE); - - audit_seccomp(syscall_get_nr(current, regs), 0, action); - - /* Skip these calls if there is no tracer. */ - if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { - syscall_set_return_value(current, regs, - -ENOSYS, 0); - return -1; - } - - /* Allow the BPF to provide the event message */ - ptrace_event(PTRACE_EVENT_SECCOMP, data); - /* - * The delivery of a fatal signal during event - * notification may silently skip tracer notification. - * Terminating the task now avoids executing a system - * call that may not be intended. - */ - if (fatal_signal_pending(current)) - do_exit(SIGSYS); - if (syscall_get_nr(current, regs) < 0) - return -1; /* Explicit request to skip. */ - - return 0; -} #endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */ long prctl_get_seccomp(void) diff --git a/kernel/signal.c b/kernel/signal.c index 8bfbc47f0a23..5b1313309356 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -991,7 +991,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, - from_ancestor_ns || (info == SEND_SIG_FORCED))) + from_ancestor_ns || (info == SEND_SIG_PRIV) || (info == SEND_SIG_FORCED))) goto ret; pending = group ? &t->signal->shared_pending : &t->pending; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 14f19af9d79a..ae30e357f554 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2045,6 +2045,24 @@ static struct ctl_table fs_table[] = { .extra2 = &one, }, { + .procname = "protected_fifos", + .data = &sysctl_protected_fifos, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, + { + .procname = "protected_regular", + .data = &sysctl_protected_regular, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, + { .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), |