summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit_watch.c8
-rw-r--r--kernel/bpf/hashtab.c84
-rw-r--r--kernel/bpf/verifier.c7
-rw-r--r--kernel/configs/tiny.config8
-rw-r--r--kernel/cpuset.c15
-rw-r--r--kernel/events/core.c97
-rw-r--r--kernel/events/uprobes.c5
-rw-r--r--kernel/exit.c7
-rw-r--r--kernel/fork.c37
-rw-r--r--kernel/irq/affinity.c2
-rw-r--r--kernel/irq/chip.c11
-rw-r--r--kernel/irq/manage.c8
-rw-r--r--kernel/kexec_file.c3
-rw-r--r--kernel/power/snapshot.c10
-rw-r--r--kernel/printk/braille.c4
-rw-r--r--kernel/printk/nmi.c38
-rw-r--r--kernel/sched/cputime.c33
-rw-r--r--kernel/seccomp.c12
-rw-r--r--kernel/sysctl.c45
-rw-r--r--kernel/time/tick-sched.c3
-rw-r--r--kernel/time/timekeeping.c5
-rw-r--r--kernel/time/timekeeping_debug.c9
-rw-r--r--kernel/trace/blktrace.c2
23 files changed, 349 insertions, 104 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index d6709eb70970..0d302a87f21b 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -19,6 +19,7 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#include <linux/file.h>
#include <linux/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
@@ -544,10 +545,11 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark)
unsigned long ino;
dev_t dev;
- rcu_read_lock();
- exe_file = rcu_dereference(tsk->mm->exe_file);
+ exe_file = get_task_exe_file(tsk);
+ if (!exe_file)
+ return 0;
ino = exe_file->f_inode->i_ino;
dev = exe_file->f_inode->i_sb->s_dev;
- rcu_read_unlock();
+ fput(exe_file);
return audit_mark_compare(mark, ino, dev);
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fff3650d52fc..570eeca7bdfa 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -26,11 +26,18 @@ struct bpf_htab {
struct bucket *buckets;
void *elems;
struct pcpu_freelist freelist;
+ void __percpu *extra_elems;
atomic_t count; /* number of elements in this hashtable */
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
};
+enum extra_elem_state {
+ HTAB_NOT_AN_EXTRA_ELEM = 0,
+ HTAB_EXTRA_ELEM_FREE,
+ HTAB_EXTRA_ELEM_USED
+};
+
/* each htab element is struct htab_elem + key + value */
struct htab_elem {
union {
@@ -38,7 +45,10 @@ struct htab_elem {
struct bpf_htab *htab;
struct pcpu_freelist_node fnode;
};
- struct rcu_head rcu;
+ union {
+ struct rcu_head rcu;
+ enum extra_elem_state state;
+ };
u32 hash;
char key[0] __aligned(8);
};
@@ -113,6 +123,23 @@ free_elems:
return err;
}
+static int alloc_extra_elems(struct bpf_htab *htab)
+{
+ void __percpu *pptr;
+ int cpu;
+
+ pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN);
+ if (!pptr)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state =
+ HTAB_EXTRA_ELEM_FREE;
+ }
+ htab->extra_elems = pptr;
+ return 0;
+}
+
/* Called from syscall */
static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
{
@@ -185,6 +212,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
if (percpu)
cost += (u64) round_up(htab->map.value_size, 8) *
num_possible_cpus() * htab->map.max_entries;
+ else
+ cost += (u64) htab->elem_size * num_possible_cpus();
if (cost >= U32_MAX - PAGE_SIZE)
/* make sure page count doesn't overflow */
@@ -212,14 +241,22 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
raw_spin_lock_init(&htab->buckets[i].lock);
}
+ if (!percpu) {
+ err = alloc_extra_elems(htab);
+ if (err)
+ goto free_buckets;
+ }
+
if (!(attr->map_flags & BPF_F_NO_PREALLOC)) {
err = prealloc_elems_and_freelist(htab);
if (err)
- goto free_buckets;
+ goto free_extra_elems;
}
return &htab->map;
+free_extra_elems:
+ free_percpu(htab->extra_elems);
free_buckets:
kvfree(htab->buckets);
free_htab:
@@ -349,7 +386,6 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
kfree(l);
-
}
static void htab_elem_free_rcu(struct rcu_head *head)
@@ -370,6 +406,11 @@ static void htab_elem_free_rcu(struct rcu_head *head)
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
+ if (l->state == HTAB_EXTRA_ELEM_USED) {
+ l->state = HTAB_EXTRA_ELEM_FREE;
+ return;
+ }
+
if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) {
pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
@@ -381,25 +422,44 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
- bool percpu, bool onallcpus)
+ bool percpu, bool onallcpus,
+ bool old_elem_exists)
{
u32 size = htab->map.value_size;
bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC);
struct htab_elem *l_new;
void __percpu *pptr;
+ int err = 0;
if (prealloc) {
l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
if (!l_new)
- return ERR_PTR(-E2BIG);
+ err = -E2BIG;
} else {
if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ err = -E2BIG;
+ } else {
+ l_new = kmalloc(htab->elem_size,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (!l_new)
+ return ERR_PTR(-ENOMEM);
}
- l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ }
+
+ if (err) {
+ if (!old_elem_exists)
+ return ERR_PTR(err);
+
+ /* if we're updating the existing element and the hash table
+ * is full, use per-cpu extra elems
+ */
+ l_new = this_cpu_ptr(htab->extra_elems);
+ if (l_new->state != HTAB_EXTRA_ELEM_FREE)
+ return ERR_PTR(-E2BIG);
+ l_new->state = HTAB_EXTRA_ELEM_USED;
+ } else {
+ l_new->state = HTAB_NOT_AN_EXTRA_ELEM;
}
memcpy(l_new->key, key, key_size);
@@ -489,7 +549,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
if (ret)
goto err;
- l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false);
+ l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
+ !!l_old);
if (IS_ERR(l_new)) {
/* all pre-allocated elements are in use or memory exhausted */
ret = PTR_ERR(l_new);
@@ -563,7 +624,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
}
} else {
l_new = alloc_htab_elem(htab, key, value, key_size,
- hash, true, onallcpus);
+ hash, true, onallcpus, false);
if (IS_ERR(l_new)) {
ret = PTR_ERR(l_new);
goto err;
@@ -652,6 +713,7 @@ static void htab_map_free(struct bpf_map *map)
htab_free_elems(htab);
pcpu_freelist_destroy(&htab->freelist);
}
+ free_percpu(htab->extra_elems);
kvfree(htab->buckets);
kfree(htab);
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f72f23b8fdab..daea765d72e6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -194,6 +194,7 @@ struct verifier_env {
struct verifier_state_list **explored_states; /* search pruning optimization */
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
u32 used_map_cnt; /* number of used maps */
+ u32 id_gen; /* used to generate unique reg IDs */
bool allow_ptr_leaks;
};
@@ -1052,7 +1053,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
goto error;
break;
case BPF_MAP_TYPE_CGROUP_ARRAY:
- if (func_id != BPF_FUNC_skb_in_cgroup)
+ if (func_id != BPF_FUNC_skb_under_cgroup)
goto error;
break;
default:
@@ -1074,7 +1075,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
goto error;
break;
- case BPF_FUNC_skb_in_cgroup:
+ case BPF_FUNC_skb_under_cgroup:
if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
goto error;
break;
@@ -1301,7 +1302,7 @@ add_imm:
/* dst_reg stays as pkt_ptr type and since some positive
* integer value was added to the pointer, increment its 'id'
*/
- dst_reg->id++;
+ dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range and off to zero */
dst_reg->off = 0;
diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config
index c2de56ab0fce..7fa0c4ae6394 100644
--- a/kernel/configs/tiny.config
+++ b/kernel/configs/tiny.config
@@ -1,4 +1,12 @@
+# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_KERNEL_GZIP is not set
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
CONFIG_KERNEL_XZ=y
+# CONFIG_KERNEL_LZO is not set
+# CONFIG_KERNEL_LZ4 is not set
CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
CONFIG_SLOB=y
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c7fd2778ed50..c27e53326bef 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2069,6 +2069,20 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
mutex_unlock(&cpuset_mutex);
}
+/*
+ * Make sure the new task conform to the current state of its parent,
+ * which could have been changed by cpuset just after it inherits the
+ * state from the parent and before it sits on the cgroup's task list.
+ */
+void cpuset_fork(struct task_struct *task)
+{
+ if (task_css_is_root(task, cpuset_cgrp_id))
+ return;
+
+ set_cpus_allowed_ptr(task, &current->cpus_allowed);
+ task->mems_allowed = current->mems_allowed;
+}
+
struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
@@ -2079,6 +2093,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
.attach = cpuset_attach,
.post_attach = cpuset_post_attach,
.bind = cpuset_bind,
+ .fork = cpuset_fork,
.legacy_cftypes = files,
.early_init = true,
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1903b8f3a705..3cfabdf7b942 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -242,18 +242,6 @@ unlock:
return ret;
}
-static void event_function_local(struct perf_event *event, event_f func, void *data)
-{
- struct event_function_struct efs = {
- .event = event,
- .func = func,
- .data = data,
- };
-
- int ret = event_function(&efs);
- WARN_ON_ONCE(ret);
-}
-
static void event_function_call(struct perf_event *event, event_f func, void *data)
{
struct perf_event_context *ctx = event->ctx;
@@ -303,6 +291,54 @@ again:
raw_spin_unlock_irq(&ctx->lock);
}
+/*
+ * Similar to event_function_call() + event_function(), but hard assumes IRQs
+ * are already disabled and we're on the right CPU.
+ */
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct task_struct *task = READ_ONCE(ctx->task);
+ struct perf_event_context *task_ctx = NULL;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ if (task) {
+ if (task == TASK_TOMBSTONE)
+ return;
+
+ task_ctx = ctx;
+ }
+
+ perf_ctx_lock(cpuctx, task_ctx);
+
+ task = ctx->task;
+ if (task == TASK_TOMBSTONE)
+ goto unlock;
+
+ if (task) {
+ /*
+ * We must be either inactive or active and the right task,
+ * otherwise we're screwed, since we cannot IPI to somewhere
+ * else.
+ */
+ if (ctx->is_active) {
+ if (WARN_ON_ONCE(task != current))
+ goto unlock;
+
+ if (WARN_ON_ONCE(cpuctx->task_ctx != ctx))
+ goto unlock;
+ }
+ } else {
+ WARN_ON_ONCE(&cpuctx->ctx != ctx);
+ }
+
+ func(event, cpuctx, ctx, data);
+unlock:
+ perf_ctx_unlock(cpuctx, task_ctx);
+}
+
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
PERF_FLAG_PID_CGROUP |\
@@ -3513,9 +3549,10 @@ static int perf_event_read(struct perf_event *event, bool group)
.group = group,
.ret = 0,
};
- smp_call_function_single(event->oncpu,
- __perf_event_read, &data, 1);
- ret = data.ret;
+ ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
+ /* The event must have been read from an online CPU: */
+ WARN_ON_ONCE(ret);
+ ret = ret ? : data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
unsigned long flags;
@@ -6129,7 +6166,7 @@ static int __perf_pmu_output_stop(void *info)
{
struct perf_event *event = info;
struct pmu *pmu = event->pmu;
- struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
struct remote_output ro = {
.rb = event->rb,
};
@@ -6584,15 +6621,6 @@ got_name:
}
/*
- * Whether this @filter depends on a dynamic object which is not loaded
- * yet or its load addresses are not known.
- */
-static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
-{
- return filter->filter && filter->inode;
-}
-
-/*
* Check whether inode and address range match filter criteria.
*/
static bool perf_addr_filter_match(struct perf_addr_filter *filter,
@@ -6653,6 +6681,13 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma)
struct perf_event_context *ctx;
int ctxn;
+ /*
+ * Data tracing isn't supported yet and as such there is no need
+ * to keep track of anything that isn't related to executable code:
+ */
+ if (!(vma->vm_flags & VM_EXEC))
+ return;
+
rcu_read_lock();
for_each_task_context_nr(ctxn) {
ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
@@ -7805,7 +7840,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
list_for_each_entry(filter, &ifh->list, entry) {
event->addr_filters_offs[count] = 0;
- if (perf_addr_filter_needs_mmap(filter))
+ /*
+ * Adjust base offset if the filter is associated to a binary
+ * that needs to be mapped:
+ */
+ if (filter->inode)
event->addr_filters_offs[count] =
perf_addr_filter_apply(filter, mm);
@@ -7936,8 +7975,10 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
goto fail;
}
- if (token == IF_SRC_FILE) {
- filename = match_strdup(&args[2]);
+ if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
+ int fpos = filter->range ? 2 : 1;
+
+ filename = match_strdup(&args[fpos]);
if (!filename) {
ret = -ENOMEM;
goto fail;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index b7a525ab2083..8c50276b60d1 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
err = -EAGAIN;
ptep = page_check_address(page, mm, addr, &ptl, 0);
- if (!ptep)
+ if (!ptep) {
+ mem_cgroup_cancel_charge(kpage, memcg, false);
goto unlock;
+ }
get_page(kpage);
page_add_new_anon_rmap(kpage, vma, addr, false);
@@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
err = 0;
unlock:
- mem_cgroup_cancel_charge(kpage, memcg, false);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(page);
return err;
diff --git a/kernel/exit.c b/kernel/exit.c
index 2f974ae042a6..091a78be3b09 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -848,12 +848,7 @@ void do_exit(long code)
TASKS_RCU(preempt_enable());
exit_notify(tsk, group_dead);
proc_exit_connector(tsk);
-#ifdef CONFIG_NUMA
- task_lock(tsk);
- mpol_put(tsk->mempolicy);
- tsk->mempolicy = NULL;
- task_unlock(tsk);
-#endif
+ mpol_put_task_policy(tsk);
#ifdef CONFIG_FUTEX
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
diff --git a/kernel/fork.c b/kernel/fork.c
index 52e725d4a866..beb31725f7e2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -799,6 +799,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm)
EXPORT_SYMBOL(get_mm_exe_file);
/**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+ struct file *exe_file = NULL;
+ struct mm_struct *mm;
+
+ task_lock(task);
+ mm = task->mm;
+ if (mm) {
+ if (!(task->flags & PF_KTHREAD))
+ exe_file = get_mm_exe_file(mm);
+ }
+ task_unlock(task);
+ return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
+/**
* get_task_mm - acquire a reference to the task's mm
*
* Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning
@@ -913,14 +936,12 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
deactivate_mm(tsk, mm);
/*
- * If we're exiting normally, clear a user-space tid field if
- * requested. We leave this alone when dying by signal, to leave
- * the value intact in a core dump, and to save the unnecessary
- * trouble, say, a killed vfork parent shouldn't touch this mm.
- * Userland only wants this done for a sys_exit.
+ * Signal userspace if we're not exiting with a core dump
+ * because we want to leave the value intact for debugging
+ * purposes.
*/
if (tsk->clear_child_tid) {
- if (!(tsk->flags & PF_SIGNALED) &&
+ if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
atomic_read(&mm->mm_users) > 1) {
/*
* We don't check the error code - if userspace has
@@ -1404,7 +1425,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
@@ -1556,6 +1576,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
@@ -1656,6 +1677,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
@@ -1688,7 +1710,6 @@ bad_fork_cleanup_policy:
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f68959341c0f..32f6cfcff212 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -39,6 +39,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
return NULL;
}
+ get_online_cpus();
if (max_vecs >= num_online_cpus()) {
cpumask_copy(affinity_mask, cpu_online_mask);
*nr_vecs = num_online_cpus();
@@ -56,6 +57,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
}
*nr_vecs = vecs;
}
+ put_online_cpus();
return affinity_mask;
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b4c1bc7c9ca2..637389088b3f 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -820,6 +820,17 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
desc->name = name;
if (handle != handle_bad_irq && is_chained) {
+ /*
+ * We're about to start this interrupt immediately,
+ * hence the need to set the trigger configuration.
+ * But the .set_type callback may have overridden the
+ * flow handler, ignoring that we're dealing with a
+ * chained interrupt. Reset it immediately because we
+ * do know better.
+ */
+ __irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data));
+ desc->handle_irq = handle;
+
irq_settings_set_noprobe(desc);
irq_settings_set_norequest(desc);
irq_settings_set_nothread(desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 73a2b786b5e9..9530fcd27704 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1681,8 +1681,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
action->dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
- if (retval < 0)
+ if (retval < 0) {
+ kfree(action);
return retval;
+ }
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
@@ -1985,8 +1987,10 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler,
action->percpu_dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
- if (retval < 0)
+ if (retval < 0) {
+ kfree(action);
return retval;
+ }
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 503bc2d348e5..037c321c5618 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -887,7 +887,10 @@ int kexec_load_purgatory(struct kimage *image, unsigned long min,
return 0;
out:
vfree(pi->sechdrs);
+ pi->sechdrs = NULL;
+
vfree(pi->purgatory_buf);
+ pi->purgatory_buf = NULL;
return ret;
}
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 9a0178c2ac1d..b02228411d57 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -835,9 +835,9 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
*/
static bool rtree_next_node(struct memory_bitmap *bm)
{
- bm->cur.node = list_entry(bm->cur.node->list.next,
- struct rtree_node, list);
- if (&bm->cur.node->list != &bm->cur.zone->leaves) {
+ if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) {
+ bm->cur.node = list_entry(bm->cur.node->list.next,
+ struct rtree_node, list);
bm->cur.node_pfn += BM_BITS_PER_BLOCK;
bm->cur.node_bit = 0;
touch_softlockup_watchdog();
@@ -845,9 +845,9 @@ static bool rtree_next_node(struct memory_bitmap *bm)
}
/* No more nodes, goto next zone */
- bm->cur.zone = list_entry(bm->cur.zone->list.next,
+ if (!list_is_last(&bm->cur.zone->list, &bm->zones)) {
+ bm->cur.zone = list_entry(bm->cur.zone->list.next,
struct mem_zone_bm_rtree, list);
- if (&bm->cur.zone->list != &bm->zones) {
bm->cur.node = list_entry(bm->cur.zone->leaves.next,
struct rtree_node, list);
bm->cur.node_pfn = 0;
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index 276762f3a460..d5760c42f042 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -9,10 +9,10 @@
char *_braille_console_setup(char **str, char **brl_options)
{
- if (!memcmp(*str, "brl,", 4)) {
+ if (!strncmp(*str, "brl,", 4)) {
*brl_options = "";
*str += 4;
- } else if (!memcmp(str, "brl=", 4)) {
+ } else if (!strncmp(*str, "brl=", 4)) {
*brl_options = *str + 4;
*str = strchr(*brl_options, ',');
if (!*str)
diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c
index b69eb8a2876f..16bab471c7e2 100644
--- a/kernel/printk/nmi.c
+++ b/kernel/printk/nmi.c
@@ -99,27 +99,33 @@ again:
return add;
}
-/*
- * printk one line from the temporary buffer from @start index until
- * and including the @end index.
- */
-static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void printk_nmi_flush_line(const char *text, int len)
{
- const char *buf = s->buffer + start;
-
/*
* The buffers are flushed in NMI only on panic. The messages must
* go only into the ring buffer at this stage. Consoles will get
* explicitly called later when a crashdump is not generated.
*/
if (in_nmi())
- printk_deferred("%.*s", (end - start) + 1, buf);
+ printk_deferred("%.*s", len, text);
else
- printk("%.*s", (end - start) + 1, buf);
+ printk("%.*s", len, text);
}
/*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
+ int start, int end)
+{
+ const char *buf = s->buffer + start;
+
+ printk_nmi_flush_line(buf, (end - start) + 1);
+}
+
+/*
* Flush data from the associated per_CPU buffer. The function
* can be called either via IRQ work or independently.
*/
@@ -150,9 +156,11 @@ more:
* the buffer an unexpected way. If we printed something then
* @len must only increase.
*/
- if (i && i >= len)
- pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
- i, len);
+ if (i && i >= len) {
+ const char *msg = "printk_nmi_flush: internal error\n";
+
+ printk_nmi_flush_line(msg, strlen(msg));
+ }
if (!len)
goto out; /* Someone else has already flushed the buffer. */
@@ -166,14 +174,14 @@ more:
/* Print line by line. */
for (; i < size; i++) {
if (s->buffer[i] == '\n') {
- print_nmi_seq_line(s, last_i, i);
+ printk_nmi_flush_seq_line(s, last_i, i);
last_i = i + 1;
}
}
/* Check if there was a partial line. */
if (last_i < size) {
- print_nmi_seq_line(s, last_i, size - 1);
- pr_cont("\n");
+ printk_nmi_flush_seq_line(s, last_i, size - 1);
+ printk_nmi_flush_line("\n", strlen("\n"));
}
/*
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 9858266fb0b3..a846cf89eb96 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime)
cpustat[CPUTIME_IDLE] += (__force u64) cputime;
}
+/*
+ * When a guest is interrupted for a longer amount of time, missed clock
+ * ticks are not redelivered later. Due to that, this function may on
+ * occasion account more time than the calling functions think elapsed.
+ */
static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
{
#ifdef CONFIG_PARAVIRT
@@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
* idle, or potentially user or system time. Due to rounding,
* other time can exceed ticks occasionally.
*/
- other = account_other_time(cputime);
+ other = account_other_time(ULONG_MAX);
if (other >= cputime)
return;
cputime -= other;
@@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
}
cputime = cputime_one_jiffy;
- steal = steal_account_process_time(cputime);
+ steal = steal_account_process_time(ULONG_MAX);
if (steal >= cputime)
return;
@@ -516,7 +521,7 @@ void account_idle_ticks(unsigned long ticks)
}
cputime = jiffies_to_cputime(ticks);
- steal = steal_account_process_time(cputime);
+ steal = steal_account_process_time(ULONG_MAX);
if (steal >= cputime)
return;
@@ -614,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr,
stime = curr->stime;
utime = curr->utime;
- if (utime == 0) {
- stime = rtime;
+ /*
+ * If either stime or both stime and utime are 0, assume all runtime is
+ * userspace. Once a task gets some ticks, the monotonicy code at
+ * 'update' will ensure things converge to the observed ratio.
+ */
+ if (stime == 0) {
+ utime = rtime;
goto update;
}
- if (stime == 0) {
- utime = rtime;
+ if (utime == 0) {
+ stime = rtime;
goto update;
}
stime = scale_stime((__force u64)stime, (__force u64)rtime,
(__force u64)(stime + utime));
+update:
/*
* Make sure stime doesn't go backwards; this preserves monotonicity
* for utime because rtime is monotonic.
@@ -649,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr,
stime = rtime - utime;
}
-update:
prev->stime = stime;
prev->utime = utime;
out:
@@ -694,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
unsigned long now = READ_ONCE(jiffies);
cputime_t delta, other;
+ /*
+ * Unlike tick based timing, vtime based timing never has lost
+ * ticks, and no need for steal time accounting to make up for
+ * lost ticks. Vtime accounts a rounded version of actual
+ * elapsed time. Limit account_other_time to prevent rounding
+ * errors from causing elapsed vtime to go negative.
+ */
delta = jiffies_to_cputime(now - tsk->vtime_snap);
other = account_other_time(delta);
WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ef6c6c3f9d8a..0db7c8a2afe2 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -605,12 +605,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
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.
+ * 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))
- do_exit(SIGSYS);
+ 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)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b43d0b27c1fe..a13bbdaab47d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
return 0;
}
+static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
+ int *valp,
+ int write, void *data)
+{
+ if (write) {
+ if (*negp)
+ return -EINVAL;
+ *valp = *lvalp;
+ } else {
+ unsigned int val = *valp;
+ *lvalp = (unsigned long)val;
+ }
+ return 0;
+}
+
static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
@@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,buffer,lenp,ppos,
- NULL,NULL);
+ return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
+ do_proc_douintvec_conv, NULL);
}
/*
@@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write,
return -ENOSYS;
}
+int proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
* exception granted :-)
*/
EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 204fdc86863d..2ec7c00228f3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -908,10 +908,11 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
ktime_t now, expires;
int cpu = smp_processor_id();
+ now = tick_nohz_start_idle(ts);
+
if (can_stop_idle_tick(cpu, ts)) {
int was_stopped = ts->tick_stopped;
- now = tick_nohz_start_idle(ts);
ts->idle_calls++;
expires = tick_nohz_stop_sched_tick(ts, now, cpu);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3b65746c7f15..e07fb093f819 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -401,7 +401,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
do {
seq = raw_read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
- now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+ now = ktime_to_ns(tkr->base);
+
+ now += clocksource_delta(tkr->read(tkr->clock),
+ tkr->cycle_last, tkr->mask);
} while (read_seqcount_retry(&tkf->seq, seq));
return now;
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index f6bd65236712..107310a6f36f 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -23,7 +23,9 @@
#include "timekeeping_internal.h"
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
{
@@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init);
void tk_debug_account_sleep_time(struct timespec64 *t)
{
- sleep_time_bin[fls(t->tv_sec)]++;
+ /* Cap bin index so we don't overflow the array */
+ int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+ sleep_time_bin[bin]++;
}
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7598e6ca817a..dbafc5df03f3 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
what |= MASK_TC_BIT(op_flags, META);
what |= MASK_TC_BIT(op_flags, PREFLUSH);
what |= MASK_TC_BIT(op_flags, FUA);
- if (op == REQ_OP_DISCARD)
+ if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
what |= BLK_TC_ACT(BLK_TC_DISCARD);
if (op == REQ_OP_FLUSH)
what |= BLK_TC_ACT(BLK_TC_FLUSH);