diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit.c | 2 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_main.c | 27 | ||||
-rw-r--r-- | kernel/events/core.c | 24 | ||||
-rw-r--r-- | kernel/locking/qspinlock.c | 8 | ||||
-rw-r--r-- | kernel/power/power.h | 3 | ||||
-rw-r--r-- | kernel/rcu/tree_plugin.h | 14 | ||||
-rw-r--r-- | kernel/relay.c | 2 | ||||
-rw-r--r-- | kernel/sched/rt.c | 2 | ||||
-rw-r--r-- | kernel/seccomp.c | 21 | ||||
-rw-r--r-- | kernel/signal.c | 11 | ||||
-rw-r--r-- | kernel/sys.c | 24 | ||||
-rw-r--r-- | kernel/time/tick-broadcast.c | 8 | ||||
-rw-r--r-- | kernel/workqueue.c | 2 |
13 files changed, 124 insertions, 24 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index da4e7c0e36f7..3461a3d874fe 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -742,6 +742,8 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); + if (!ab) + return; audit_log_task_info(ab, current); audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 2a20c0dfdafc..5a58421d7e2d 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1564,6 +1564,7 @@ static int kdb_md(int argc, const char **argv) int symbolic = 0; int valid = 0; int phys = 0; + int raw = 0; kdbgetintenv("MDCOUNT", &mdcount); kdbgetintenv("RADIX", &radix); @@ -1573,9 +1574,10 @@ static int kdb_md(int argc, const char **argv) repeat = mdcount * 16 / bytesperword; if (strcmp(argv[0], "mdr") == 0) { - if (argc != 2) + if (argc == 2 || (argc == 0 && last_addr != 0)) + valid = raw = 1; + else return KDB_ARGCOUNT; - valid = 1; } else if (isdigit(argv[0][2])) { bytesperword = (int)(argv[0][2] - '0'); if (bytesperword == 0) { @@ -1611,7 +1613,10 @@ static int kdb_md(int argc, const char **argv) radix = last_radix; bytesperword = last_bytesperword; repeat = last_repeat; - mdcount = ((repeat * bytesperword) + 15) / 16; + if (raw) + mdcount = repeat; + else + mdcount = ((repeat * bytesperword) + 15) / 16; } if (argc) { @@ -1628,7 +1633,10 @@ static int kdb_md(int argc, const char **argv) diag = kdbgetularg(argv[nextarg], &val); if (!diag) { mdcount = (int) val; - repeat = mdcount * 16 / bytesperword; + if (raw) + repeat = mdcount; + else + repeat = mdcount * 16 / bytesperword; } } if (argc >= nextarg+1) { @@ -1638,8 +1646,15 @@ static int kdb_md(int argc, const char **argv) } } - if (strcmp(argv[0], "mdr") == 0) - return kdb_mdr(addr, mdcount); + if (strcmp(argv[0], "mdr") == 0) { + int ret; + last_addr = addr; + ret = kdb_mdr(addr, mdcount); + last_addr += mdcount; + last_repeat = mdcount; + last_bytesperword = bytesperword; // to make REPEAT happy + return ret; + } switch (radix) { case 10: diff --git a/kernel/events/core.c b/kernel/events/core.c index 9a2fb850232e..f196c2990c98 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -634,9 +634,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp) static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp_out = cpuctx->cgrp; - if (cgrp_out) - __update_cgrp_time(cgrp_out); + struct perf_cgroup *cgrp = cpuctx->cgrp; + struct cgroup_subsys_state *css; + + if (cgrp) { + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + __update_cgrp_time(cgrp); + } + } } static inline void update_cgrp_time_from_event(struct perf_event *event) @@ -664,6 +670,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, { struct perf_cgroup *cgrp; struct perf_cgroup_info *info; + struct cgroup_subsys_state *css; /* * ctx->lock held by caller @@ -674,8 +681,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, return; cgrp = perf_cgroup_from_task(task, ctx); - info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + info = this_cpu_ptr(cgrp->info); + info->timestamp = ctx->timestamp; + } } #define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ @@ -5690,7 +5701,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) values[n++] = running; - if (leader != event) + if ((leader != event) && + (leader->state == PERF_EVENT_STATE_ACTIVE)) leader->pmu->read(leader); values[n++] = perf_event_count(leader); diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index b2caec7315af..a72f5df643f8 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -495,6 +495,14 @@ queue: tail = encode_tail(smp_processor_id(), idx); node += idx; + + /* + * Ensure that we increment the head node->count before initialising + * the actual node. If the compiler is kind enough to reorder these + * stores, then an IRQ could overwrite our assignments. + */ + barrier(); + node->locked = 0; node->next = NULL; pv_init_node(node); diff --git a/kernel/power/power.h b/kernel/power/power.h index 56d1d0dedf76..ccba4d820078 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -103,9 +103,6 @@ extern int in_suspend; extern dev_t swsusp_resume_device; extern sector_t swsusp_resume_block; -extern asmlinkage int swsusp_arch_suspend(void); -extern asmlinkage int swsusp_arch_resume(void); - extern int create_basic_memory_bitmaps(void); extern void free_basic_memory_bitmaps(void); extern int hibernate_preallocate_memory(void); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index be12d1aac840..a1a7bafcce15 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -514,8 +514,14 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) } t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); - list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + /* + * We could be printing a lot while holding a spinlock. + * Avoid triggering hard lockup. + */ + touch_nmi_watchdog(); sched_show_task(t); + } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -1524,6 +1530,12 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) char *ticks_title; unsigned long ticks_value; + /* + * We could be printing a lot while holding a spinlock. Avoid + * triggering hard lockup. + */ + touch_nmi_watchdog(); + if (rsp->gpnum == rdp->gpnum) { ticks_title = "ticks this GP"; ticks_value = rdp->ticks_this_gp; diff --git a/kernel/relay.c b/kernel/relay.c index 2603e04f55f9..91e8fbf8aff3 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -163,7 +163,7 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > UINT_MAX / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 12e8970f1146..a941b0739d11 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -831,6 +831,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) struct rq *rq = rq_of_rt_rq(rt_rq); raw_spin_lock(&rq->lock); + update_rq_clock(rq); + if (rt_rq->rt_time) { u64 runtime; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index af182a6df25b..3975856d476c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -16,6 +16,8 @@ #include <linux/atomic.h> #include <linux/audit.h> #include <linux/compat.h> +#include <linux/nospec.h> +#include <linux/prctl.h> #include <linux/sched.h> #include <linux/seccomp.h> #include <linux/slab.h> @@ -214,8 +216,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) return true; } +void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } + static inline void seccomp_assign_mode(struct task_struct *task, - unsigned long seccomp_mode) + unsigned long seccomp_mode, + unsigned long flags) { assert_spin_locked(&task->sighand->siglock); @@ -225,6 +230,9 @@ static inline void seccomp_assign_mode(struct task_struct *task, * filter) is set. */ smp_mb__before_atomic(); + /* Assume default seccomp processes want spec flaw mitigation. */ + if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) + arch_seccomp_spec_mitigate(task); set_tsk_thread_flag(task, TIF_SECCOMP); } @@ -292,7 +300,7 @@ static inline pid_t seccomp_can_sync_threads(void) * without dropping the locks. * */ -static inline void seccomp_sync_threads(void) +static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller; @@ -333,7 +341,8 @@ static inline void seccomp_sync_threads(void) * allow one thread to transition the other. */ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) - seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); + seccomp_assign_mode(thread, SECCOMP_MODE_FILTER, + flags); } } @@ -452,7 +461,7 @@ static long seccomp_attach_filter(unsigned int flags, /* Now that the new filter is in place, synchronize to all threads. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) - seccomp_sync_threads(); + seccomp_sync_threads(flags); return 0; } @@ -712,7 +721,7 @@ static long seccomp_set_mode_strict(void) #ifdef TIF_NOTSC disable_TSC(); #endif - seccomp_assign_mode(current, seccomp_mode); + seccomp_assign_mode(current, seccomp_mode, 0); ret = 0; out: @@ -770,7 +779,7 @@ static long seccomp_set_mode_filter(unsigned int flags, /* Do not free the successfully attached filter. */ prepared = NULL; - seccomp_assign_mode(current, seccomp_mode); + seccomp_assign_mode(current, seccomp_mode, flags); out: spin_unlock_irq(¤t->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) diff --git a/kernel/signal.c b/kernel/signal.c index 4d094ae3a625..e47ffc5db975 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1485,6 +1485,10 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) return ret; } + /* -INT_MIN is undefined. Exclude this case to avoid a UBSAN warning */ + if (pid == INT_MIN) + return -ESRCH; + read_lock(&tasklist_lock); if (pid != -1) { ret = __kill_pgrp_info(sig, info, @@ -2581,6 +2585,13 @@ void __set_current_blocked(const sigset_t *newset) { struct task_struct *tsk = current; + /* + * In case the signal mask hasn't changed, there is nothing we need + * to do. The current->blocked shouldn't be modified by other task. + */ + if (sigequalsets(&tsk->blocked, newset)) + return; + spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, newset); spin_unlock_irq(&tsk->sighand->siglock); diff --git a/kernel/sys.c b/kernel/sys.c index 89d5be418157..b13b530b5e0f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -53,6 +53,8 @@ #include <linux/uidgid.h> #include <linux/cred.h> +#include <linux/nospec.h> + #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> @@ -1311,6 +1313,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); @@ -2072,6 +2075,17 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) } #endif +int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) +{ + return -EINVAL; +} + +int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, + unsigned long ctrl) +{ + return -EINVAL; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2270,6 +2284,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; + case PR_GET_SPECULATION_CTRL: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_get(me, arg2); + break; + case PR_SET_SPECULATION_CTRL: + if (arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_set(me, arg2, arg3); + break; default: error = -EINVAL; break; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index d2a20e83ebae..22d7454b387b 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -610,6 +610,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) now = ktime_get(); /* Find all expired events */ for_each_cpu(cpu, tick_broadcast_oneshot_mask) { + /* + * Required for !SMP because for_each_cpu() reports + * unconditionally CPU0 as set on UP kernels. + */ + if (!IS_ENABLED(CONFIG_SMP) && + cpumask_empty(tick_broadcast_oneshot_mask)) + break; + td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event.tv64 <= now.tv64) { cpumask_set_cpu(cpu, tmpmask); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 73203f649ad4..67eb84723dc5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5315,7 +5315,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) ret = device_register(&wq_dev->dev); if (ret) { - kfree(wq_dev); + put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } |