summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c18
-rw-r--r--kernel/bpf/cgroup.c59
-rw-r--r--kernel/bpf/hashtab.c22
-rw-r--r--kernel/bpf/stackmap.c20
-rw-r--r--kernel/bpf/syscall.c46
-rw-r--r--kernel/cgroup.c22
-rw-r--r--kernel/events/core.c94
-rw-r--r--kernel/irq/irqdomain.c44
-rw-r--r--kernel/module.c53
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/power/suspend.c4
-rw-r--r--kernel/stacktrace.c12
-rw-r--r--kernel/sysctl.c1
-rw-r--r--kernel/time/tick-sched.c9
-rw-r--r--kernel/time/tick-sched.h2
-rw-r--r--kernel/trace/trace_hwlat.c8
-rw-r--r--kernel/trace/trace_kprobe.c2
-rw-r--r--kernel/ucount.c17
-rw-r--r--kernel/watchdog.c9
-rw-r--r--kernel/watchdog_hld.c3
20 files changed, 274 insertions, 173 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 229a5d5df977..3d55d95dcf49 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,7 +11,6 @@
*/
#include <linux/bpf.h>
#include <linux/err.h>
-#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
@@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
if (array_size >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
-
/* allocate all map elements and zero-initialize them */
- array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
- if (!array) {
- array = vzalloc(array_size);
- if (!array)
- return ERR_PTR(-ENOMEM);
- }
+ array = bpf_map_area_alloc(array_size);
+ if (!array)
+ return ERR_PTR(-ENOMEM);
/* copy mandatory map attributes */
array->map.map_type = attr->map_type;
@@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
if (array_size >= U32_MAX - PAGE_SIZE ||
elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
- kvfree(array);
+ bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
out:
@@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map)
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
bpf_array_free_percpu(array);
- kvfree(array);
+ bpf_map_area_free(array);
}
static const struct bpf_map_ops array_ops = {
@@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map)
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
BUG_ON(array->ptrs[i] != NULL);
- kvfree(array);
+
+ bpf_map_area_free(array);
}
static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a515f7b007c6..da0f53690295 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
e = rcu_dereference_protected(parent->bpf.effective[type],
lockdep_is_held(&cgroup_mutex));
rcu_assign_pointer(cgrp->bpf.effective[type], e);
+ cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
}
}
@@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
*
* Must be called with cgroup_mutex held.
*/
-void __cgroup_bpf_update(struct cgroup *cgrp,
- struct cgroup *parent,
- struct bpf_prog *prog,
- enum bpf_attach_type type)
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+ struct bpf_prog *prog, enum bpf_attach_type type,
+ bool new_overridable)
{
- struct bpf_prog *old_prog, *effective;
+ struct bpf_prog *old_prog, *effective = NULL;
struct cgroup_subsys_state *pos;
+ bool overridable = true;
- old_prog = xchg(cgrp->bpf.prog + type, prog);
+ if (parent) {
+ overridable = !parent->bpf.disallow_override[type];
+ effective = rcu_dereference_protected(parent->bpf.effective[type],
+ lockdep_is_held(&cgroup_mutex));
+ }
+
+ if (prog && effective && !overridable)
+ /* if parent has non-overridable prog attached, disallow
+ * attaching new programs to descendent cgroup
+ */
+ return -EPERM;
+
+ if (prog && effective && overridable != new_overridable)
+ /* if parent has overridable prog attached, only
+ * allow overridable programs in descendent cgroup
+ */
+ return -EPERM;
- effective = (!prog && parent) ?
- rcu_dereference_protected(parent->bpf.effective[type],
- lockdep_is_held(&cgroup_mutex)) :
- prog;
+ old_prog = cgrp->bpf.prog[type];
+
+ if (prog) {
+ overridable = new_overridable;
+ effective = prog;
+ if (old_prog &&
+ cgrp->bpf.disallow_override[type] == new_overridable)
+ /* disallow attaching non-overridable on top
+ * of existing overridable in this cgroup
+ * and vice versa
+ */
+ return -EPERM;
+ }
+
+ if (!prog && !old_prog)
+ /* report error when trying to detach and nothing is attached */
+ return -ENOENT;
+
+ cgrp->bpf.prog[type] = prog;
css_for_each_descendant_pre(pos, &cgrp->self) {
struct cgroup *desc = container_of(pos, struct cgroup, self);
/* skip the subtree if the descendant has its own program */
- if (desc->bpf.prog[type] && desc != cgrp)
+ if (desc->bpf.prog[type] && desc != cgrp) {
pos = css_rightmost_descendant(pos);
- else
+ } else {
rcu_assign_pointer(desc->bpf.effective[type],
effective);
+ desc->bpf.disallow_override[type] = !overridable;
+ }
}
if (prog)
@@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
+ return 0;
}
/**
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3f2bb58952d8..a753bbe7df0a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,7 +13,6 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
-#include <linux/vmalloc.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
@@ -103,7 +102,7 @@ static void htab_free_elems(struct bpf_htab *htab)
free_percpu(pptr);
}
free_elems:
- vfree(htab->elems);
+ bpf_map_area_free(htab->elems);
}
static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
@@ -125,7 +124,8 @@ static int prealloc_init(struct bpf_htab *htab)
{
int err = -ENOMEM, i;
- htab->elems = vzalloc(htab->elem_size * htab->map.max_entries);
+ htab->elems = bpf_map_area_alloc(htab->elem_size *
+ htab->map.max_entries);
if (!htab->elems)
return -ENOMEM;
@@ -320,14 +320,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
goto free_htab;
err = -ENOMEM;
- htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
- GFP_USER | __GFP_NOWARN);
-
- if (!htab->buckets) {
- htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket));
- if (!htab->buckets)
- goto free_htab;
- }
+ htab->buckets = bpf_map_area_alloc(htab->n_buckets *
+ sizeof(struct bucket));
+ if (!htab->buckets)
+ goto free_htab;
for (i = 0; i < htab->n_buckets; i++) {
INIT_HLIST_HEAD(&htab->buckets[i].head);
@@ -354,7 +350,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
free_extra_elems:
free_percpu(htab->extra_elems);
free_buckets:
- kvfree(htab->buckets);
+ bpf_map_area_free(htab->buckets);
free_htab:
kfree(htab);
return ERR_PTR(err);
@@ -1014,7 +1010,7 @@ static void htab_map_free(struct bpf_map *map)
prealloc_destroy(htab);
free_percpu(htab->extra_elems);
- kvfree(htab->buckets);
+ bpf_map_area_free(htab->buckets);
kfree(htab);
}
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 732ae16d12b7..be8519148c25 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,7 +7,6 @@
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
-#include <linux/vmalloc.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include "percpu_freelist.h"
@@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
int err;
- smap->elems = vzalloc(elem_size * smap->map.max_entries);
+ smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries);
if (!smap->elems)
return -ENOMEM;
@@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
return 0;
free_elems:
- vfree(smap->elems);
+ bpf_map_area_free(smap->elems);
return err;
}
@@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
if (cost >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-E2BIG);
- smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
- if (!smap) {
- smap = vzalloc(cost);
- if (!smap)
- return ERR_PTR(-ENOMEM);
- }
+ smap = bpf_map_area_alloc(cost);
+ if (!smap)
+ return ERR_PTR(-ENOMEM);
err = -E2BIG;
cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
@@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
put_buffers:
put_callchain_buffers();
free_smap:
- kvfree(smap);
+ bpf_map_area_free(smap);
return ERR_PTR(err);
}
@@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map)
/* wait for bpf programs to complete before freeing stack map */
synchronize_rcu();
- vfree(smap->elems);
+ bpf_map_area_free(smap->elems);
pcpu_freelist_destroy(&smap->freelist);
- kvfree(smap);
+ bpf_map_area_free(smap);
put_callchain_buffers();
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1d6b29e4e2c3..bbb016adbaeb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -12,6 +12,8 @@
#include <linux/bpf.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
@@ -49,6 +51,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl)
list_add(&tl->list_node, &bpf_map_types);
}
+void *bpf_map_area_alloc(size_t size)
+{
+ /* We definitely need __GFP_NORETRY, so OOM killer doesn't
+ * trigger under memory pressure as we really just want to
+ * fail instead.
+ */
+ const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+ void *area;
+
+ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+ area = kmalloc(size, GFP_USER | flags);
+ if (area != NULL)
+ return area;
+ }
+
+ return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
+ PAGE_KERNEL);
+}
+
+void bpf_map_area_free(void *area)
+{
+ kvfree(area);
+}
+
int bpf_map_precharge_memlock(u32 pages)
{
struct user_struct *user = get_current_user();
@@ -894,13 +920,14 @@ static int bpf_obj_get(const union bpf_attr *attr)
#ifdef CONFIG_CGROUP_BPF
-#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
static int bpf_prog_attach(const union bpf_attr *attr)
{
+ enum bpf_prog_type ptype;
struct bpf_prog *prog;
struct cgroup *cgrp;
- enum bpf_prog_type ptype;
+ int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -908,6 +935,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
+ if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+ return -EINVAL;
+
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
@@ -930,10 +960,13 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return PTR_ERR(cgrp);
}
- cgroup_bpf_update(cgrp, prog, attr->attach_type);
+ ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
+ attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+ if (ret)
+ bpf_prog_put(prog);
cgroup_put(cgrp);
- return 0;
+ return ret;
}
#define BPF_PROG_DETACH_LAST_FIELD attach_type
@@ -941,6 +974,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
static int bpf_prog_detach(const union bpf_attr *attr)
{
struct cgroup *cgrp;
+ int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -956,7 +990,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
if (IS_ERR(cgrp))
return PTR_ERR(cgrp);
- cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+ ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
cgroup_put(cgrp);
break;
@@ -964,7 +998,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
return -EINVAL;
}
- return 0;
+ return ret;
}
#endif /* CONFIG_CGROUP_BPF */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2ee9ec3051b2..53bbca7c4859 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5221,6 +5221,11 @@ err_free_css:
return ERR_PTR(err);
}
+/*
+ * The returned cgroup is fully initialized including its control mask, but
+ * it isn't associated with its kernfs_node and doesn't have the control
+ * mask applied.
+ */
static struct cgroup *cgroup_create(struct cgroup *parent)
{
struct cgroup_root *root = parent->root;
@@ -5288,11 +5293,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
cgroup_propagate_control(cgrp);
- /* @cgrp doesn't have dir yet so the following will only create csses */
- ret = cgroup_apply_control_enable(cgrp);
- if (ret)
- goto out_destroy;
-
return cgrp;
out_cancel_ref:
@@ -5300,9 +5300,6 @@ out_cancel_ref:
out_free_cgrp:
kfree(cgrp);
return ERR_PTR(ret);
-out_destroy:
- cgroup_destroy_locked(cgrp);
- return ERR_PTR(ret);
}
static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
@@ -6501,15 +6498,16 @@ static __init int cgroup_namespaces_init(void)
subsys_initcall(cgroup_namespaces_init);
#ifdef CONFIG_CGROUP_BPF
-void cgroup_bpf_update(struct cgroup *cgrp,
- struct bpf_prog *prog,
- enum bpf_attach_type type)
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+ enum bpf_attach_type type, bool overridable)
{
struct cgroup *parent = cgroup_parent(cgrp);
+ int ret;
mutex_lock(&cgroup_mutex);
- __cgroup_bpf_update(cgrp, parent, prog, type);
+ ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
mutex_unlock(&cgroup_mutex);
+ return ret;
}
#endif /* CONFIG_CGROUP_BPF */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 110b38a58493..e235bb991bdd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1469,7 +1469,6 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
-
lockdep_assert_held(&ctx->lock);
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1624,6 +1623,8 @@ static void perf_group_attach(struct perf_event *event)
{
struct perf_event *group_leader = event->group_leader, *pos;
+ lockdep_assert_held(&event->ctx->lock);
+
/*
* We can have double attach due to group movement in perf_event_open.
*/
@@ -1697,6 +1698,8 @@ static void perf_group_detach(struct perf_event *event)
struct perf_event *sibling, *tmp;
struct list_head *list = NULL;
+ lockdep_assert_held(&event->ctx->lock);
+
/*
* We can have double detach due to exit/hot-unplug + close.
*/
@@ -1895,9 +1898,29 @@ __perf_remove_from_context(struct perf_event *event,
*/
static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
{
- lockdep_assert_held(&event->ctx->mutex);
+ struct perf_event_context *ctx = event->ctx;
+
+ lockdep_assert_held(&ctx->mutex);
event_function_call(event, __perf_remove_from_context, (void *)flags);
+
+ /*
+ * The above event_function_call() can NO-OP when it hits
+ * TASK_TOMBSTONE. In that case we must already have been detached
+ * from the context (by perf_event_exit_event()) but the grouping
+ * might still be in-tact.
+ */
+ WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+ if ((flags & DETACH_GROUP) &&
+ (event->attach_state & PERF_ATTACH_GROUP)) {
+ /*
+ * Since in that case we cannot possibly be scheduled, simply
+ * detach now.
+ */
+ raw_spin_lock_irq(&ctx->lock);
+ perf_group_detach(event);
+ raw_spin_unlock_irq(&ctx->lock);
+ }
}
/*
@@ -3464,14 +3487,15 @@ struct perf_read_data {
int ret;
};
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
{
- int event_cpu = event->oncpu;
u16 local_pkg, event_pkg;
if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
- event_pkg = topology_physical_package_id(event_cpu);
- local_pkg = topology_physical_package_id(local_cpu);
+ int local_cpu = smp_processor_id();
+
+ event_pkg = topology_physical_package_id(event_cpu);
+ local_pkg = topology_physical_package_id(local_cpu);
if (event_pkg == local_pkg)
return local_cpu;
@@ -3601,7 +3625,7 @@ u64 perf_event_read_local(struct perf_event *event)
static int perf_event_read(struct perf_event *event, bool group)
{
- int ret = 0, cpu_to_read, local_cpu;
+ int event_cpu, ret = 0;
/*
* If event is enabled and currently active on a CPU, update the
@@ -3614,21 +3638,25 @@ static int perf_event_read(struct perf_event *event, bool group)
.ret = 0,
};
- local_cpu = get_cpu();
- cpu_to_read = find_cpu_to_read(event, local_cpu);
- put_cpu();
+ event_cpu = READ_ONCE(event->oncpu);
+ if ((unsigned)event_cpu >= nr_cpu_ids)
+ return 0;
+
+ preempt_disable();
+ event_cpu = __perf_event_read_cpu(event, event_cpu);
/*
* Purposely ignore the smp_call_function_single() return
* value.
*
- * If event->oncpu isn't a valid CPU it means the event got
+ * If event_cpu isn't a valid CPU it means the event got
* scheduled out and that will have updated the event count.
*
* Therefore, either way, we'll have an up-to-date event count
* after this.
*/
- (void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+ (void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+ preempt_enable();
ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
@@ -6609,6 +6637,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
char *buf = NULL;
char *name;
+ if (vma->vm_flags & VM_READ)
+ prot |= PROT_READ;
+ if (vma->vm_flags & VM_WRITE)
+ prot |= PROT_WRITE;
+ if (vma->vm_flags & VM_EXEC)
+ prot |= PROT_EXEC;
+
+ if (vma->vm_flags & VM_MAYSHARE)
+ flags = MAP_SHARED;
+ else
+ flags = MAP_PRIVATE;
+
+ if (vma->vm_flags & VM_DENYWRITE)
+ flags |= MAP_DENYWRITE;
+ if (vma->vm_flags & VM_MAYEXEC)
+ flags |= MAP_EXECUTABLE;
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
+ if (vma->vm_flags & VM_HUGETLB)
+ flags |= MAP_HUGETLB;
+
if (file) {
struct inode *inode;
dev_t dev;
@@ -6635,27 +6684,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
maj = MAJOR(dev);
min = MINOR(dev);
- if (vma->vm_flags & VM_READ)
- prot |= PROT_READ;
- if (vma->vm_flags & VM_WRITE)
- prot |= PROT_WRITE;
- if (vma->vm_flags & VM_EXEC)
- prot |= PROT_EXEC;
-
- if (vma->vm_flags & VM_MAYSHARE)
- flags = MAP_SHARED;
- else
- flags = MAP_PRIVATE;
-
- if (vma->vm_flags & VM_DENYWRITE)
- flags |= MAP_DENYWRITE;
- if (vma->vm_flags & VM_MAYEXEC)
- flags |= MAP_EXECUTABLE;
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
- if (vma->vm_flags & VM_HUGETLB)
- flags |= MAP_HUGETLB;
-
goto got_name;
} else {
if (vma->vm_ops && vma->vm_ops->name) {
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8c0a0ae43521..b59e6768c5e9 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1346,6 +1346,30 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain,
}
EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
+static void __irq_domain_activate_irq(struct irq_data *irq_data)
+{
+ if (irq_data && irq_data->domain) {
+ struct irq_domain *domain = irq_data->domain;
+
+ if (irq_data->parent_data)
+ __irq_domain_activate_irq(irq_data->parent_data);
+ if (domain->ops->activate)
+ domain->ops->activate(domain, irq_data);
+ }
+}
+
+static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
+{
+ if (irq_data && irq_data->domain) {
+ struct irq_domain *domain = irq_data->domain;
+
+ if (domain->ops->deactivate)
+ domain->ops->deactivate(domain, irq_data);
+ if (irq_data->parent_data)
+ __irq_domain_deactivate_irq(irq_data->parent_data);
+ }
+}
+
/**
* irq_domain_activate_irq - Call domain_ops->activate recursively to activate
* interrupt
@@ -1356,13 +1380,9 @@ EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
*/
void irq_domain_activate_irq(struct irq_data *irq_data)
{
- if (irq_data && irq_data->domain) {
- struct irq_domain *domain = irq_data->domain;
-
- if (irq_data->parent_data)
- irq_domain_activate_irq(irq_data->parent_data);
- if (domain->ops->activate)
- domain->ops->activate(domain, irq_data);
+ if (!irqd_is_activated(irq_data)) {
+ __irq_domain_activate_irq(irq_data);
+ irqd_set_activated(irq_data);
}
}
@@ -1376,13 +1396,9 @@ void irq_domain_activate_irq(struct irq_data *irq_data)
*/
void irq_domain_deactivate_irq(struct irq_data *irq_data)
{
- if (irq_data && irq_data->domain) {
- struct irq_domain *domain = irq_data->domain;
-
- if (domain->ops->deactivate)
- domain->ops->deactivate(domain, irq_data);
- if (irq_data->parent_data)
- irq_domain_deactivate_irq(irq_data->parent_data);
+ if (irqd_is_activated(irq_data)) {
+ __irq_domain_deactivate_irq(irq_data);
+ irqd_clr_activated(irq_data);
}
}
diff --git a/kernel/module.c b/kernel/module.c
index 38d4270925d4..3d8f126208e3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -389,16 +389,16 @@ extern const struct kernel_symbol __start___ksymtab_gpl[];
extern const struct kernel_symbol __stop___ksymtab_gpl[];
extern const struct kernel_symbol __start___ksymtab_gpl_future[];
extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
-extern const unsigned long __start___kcrctab[];
-extern const unsigned long __start___kcrctab_gpl[];
-extern const unsigned long __start___kcrctab_gpl_future[];
+extern const s32 __start___kcrctab[];
+extern const s32 __start___kcrctab_gpl[];
+extern const s32 __start___kcrctab_gpl_future[];
#ifdef CONFIG_UNUSED_SYMBOLS
extern const struct kernel_symbol __start___ksymtab_unused[];
extern const struct kernel_symbol __stop___ksymtab_unused[];
extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
-extern const unsigned long __start___kcrctab_unused[];
-extern const unsigned long __start___kcrctab_unused_gpl[];
+extern const s32 __start___kcrctab_unused[];
+extern const s32 __start___kcrctab_unused_gpl[];
#endif
#ifndef CONFIG_MODVERSIONS
@@ -497,7 +497,7 @@ struct find_symbol_arg {
/* Output */
struct module *owner;
- const unsigned long *crc;
+ const s32 *crc;
const struct kernel_symbol *sym;
};
@@ -563,7 +563,7 @@ static bool find_symbol_in_section(const struct symsearch *syms,
* (optional) module which owns it. Needs preempt disabled or module_mutex. */
const struct kernel_symbol *find_symbol(const char *name,
struct module **owner,
- const unsigned long **crc,
+ const s32 **crc,
bool gplok,
bool warn)
{
@@ -1249,23 +1249,17 @@ static int try_to_force_load(struct module *mod, const char *reason)
}
#ifdef CONFIG_MODVERSIONS
-/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */
-static unsigned long maybe_relocated(unsigned long crc,
- const struct module *crc_owner)
+
+static u32 resolve_rel_crc(const s32 *crc)
{
-#ifdef ARCH_RELOCATES_KCRCTAB
- if (crc_owner == NULL)
- return crc - (unsigned long)reloc_start;
-#endif
- return crc;
+ return *(u32 *)((void *)crc + *crc);
}
static int check_version(Elf_Shdr *sechdrs,
unsigned int versindex,
const char *symname,
struct module *mod,
- const unsigned long *crc,
- const struct module *crc_owner)
+ const s32 *crc)
{
unsigned int i, num_versions;
struct modversion_info *versions;
@@ -1283,13 +1277,19 @@ static int check_version(Elf_Shdr *sechdrs,
/ sizeof(struct modversion_info);
for (i = 0; i < num_versions; i++) {
+ u32 crcval;
+
if (strcmp(versions[i].name, symname) != 0)
continue;
- if (versions[i].crc == maybe_relocated(*crc, crc_owner))
+ if (IS_ENABLED(CONFIG_MODULE_REL_CRCS))
+ crcval = resolve_rel_crc(crc);
+ else
+ crcval = *crc;
+ if (versions[i].crc == crcval)
return 1;
- pr_debug("Found checksum %lX vs module %lX\n",
- maybe_relocated(*crc, crc_owner), versions[i].crc);
+ pr_debug("Found checksum %X vs module %lX\n",
+ crcval, versions[i].crc);
goto bad_version;
}
@@ -1307,7 +1307,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
unsigned int versindex,
struct module *mod)
{
- const unsigned long *crc;
+ const s32 *crc;
/*
* Since this should be found in kernel (which can't be removed), no
@@ -1321,8 +1321,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
}
preempt_enable();
return check_version(sechdrs, versindex,
- VMLINUX_SYMBOL_STR(module_layout), mod, crc,
- NULL);
+ VMLINUX_SYMBOL_STR(module_layout), mod, crc);
}
/* First part is kernel version, which we ignore if module has crcs. */
@@ -1340,8 +1339,7 @@ static inline int check_version(Elf_Shdr *sechdrs,
unsigned int versindex,
const char *symname,
struct module *mod,
- const unsigned long *crc,
- const struct module *crc_owner)
+ const s32 *crc)
{
return 1;
}
@@ -1368,7 +1366,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
{
struct module *owner;
const struct kernel_symbol *sym;
- const unsigned long *crc;
+ const s32 *crc;
int err;
/*
@@ -1383,8 +1381,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
if (!sym)
goto unlock;
- if (!check_version(info->sechdrs, info->index.vers, name, mod, crc,
- owner)) {
+ if (!check_version(info->sechdrs, info->index.vers, name, mod, crc)) {
sym = ERR_PTR(-EINVAL);
goto getname;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index 901c4fb46002..08aa88dde7de 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -249,7 +249,7 @@ void panic(const char *fmt, ...)
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
- pr_emerg("Rebooting in %d seconds..", panic_timeout);
+ pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f67ceb7768b8..15e6baef5c73 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -46,7 +46,7 @@ static const char * const mem_sleep_labels[] = {
const char *mem_sleep_states[PM_SUSPEND_MAX];
suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE;
-suspend_state_t mem_sleep_default = PM_SUSPEND_MAX;
+static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM;
unsigned int pm_suspend_global_flags;
EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
@@ -168,7 +168,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops)
}
if (valid_state(PM_SUSPEND_MEM)) {
mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
- if (mem_sleep_default >= PM_SUSPEND_MEM)
+ if (mem_sleep_default == PM_SUSPEND_MEM)
mem_sleep_current = PM_SUSPEND_MEM;
}
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index b6e4c16377c7..9c15a9124e83 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -18,10 +18,8 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
if (WARN_ON(!trace->entries))
return;
- for (i = 0; i < trace->nr_entries; i++) {
- printk("%*c", 1 + spaces, ' ');
- print_ip_sym(trace->entries[i]);
- }
+ for (i = 0; i < trace->nr_entries; i++)
+ printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
}
EXPORT_SYMBOL_GPL(print_stack_trace);
@@ -29,7 +27,6 @@ int snprint_stack_trace(char *buf, size_t size,
struct stack_trace *trace, int spaces)
{
int i;
- unsigned long ip;
int generated;
int total = 0;
@@ -37,9 +34,8 @@ int snprint_stack_trace(char *buf, size_t size,
return 0;
for (i = 0; i < trace->nr_entries; i++) {
- ip = trace->entries[i];
- generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
- 1 + spaces, ' ', (void *) ip, (void *) ip);
+ generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
+ (void *)trace->entries[i]);
total += generated;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8dbaec0e4f7f..1aea594a54db 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2475,6 +2475,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
break;
if (neg)
continue;
+ val = convmul * val / convdiv;
if ((min && val < *min) || (max && val > *max))
continue;
*i = val;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 74e0388cc88d..2c115fdab397 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -767,7 +767,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
tick = expires;
/* Skip reprogram of event if its not changed */
- if (ts->tick_stopped && (expires == ts->next_tick))
+ if (ts->tick_stopped && (expires == dev->next_event))
goto out;
/*
@@ -787,8 +787,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
trace_tick_stop(1, TICK_DEP_MASK_NONE);
}
- ts->next_tick = tick;
-
/*
* If the expiration time == KTIME_MAX, then we simply stop
* the tick timer.
@@ -804,10 +802,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
else
tick_program_event(tick, 1);
out:
- /*
- * Update the estimated sleep length until the next timer
- * (not only the tick).
- */
+ /* Update the estimated sleep length */
ts->sleep_length = ktime_sub(dev->next_event, now);
return tick;
}
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 075444e3d48e..bf38226e5c17 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -27,7 +27,6 @@ enum tick_nohz_mode {
* timer is modified for nohz sleeps. This is necessary
* to resume the tick timer operation in the timeline
* when the CPU returns from nohz sleep.
- * @next_tick: Next tick to be fired when in dynticks mode.
* @tick_stopped: Indicator that the idle tick has been stopped
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
* @idle_calls: Total number of idle calls
@@ -45,7 +44,6 @@ struct tick_sched {
unsigned long check_clocks;
enum tick_nohz_mode nohz_mode;
ktime_t last_tick;
- ktime_t next_tick;
int inidle;
int tick_stopped;
unsigned long idle_jiffies;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 775569ec50d0..af344a1bf0d0 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -266,7 +266,7 @@ out:
static struct cpumask save_cpumask;
static bool disable_migrate;
-static void move_to_next_cpu(void)
+static void move_to_next_cpu(bool initmask)
{
static struct cpumask *current_mask;
int next_cpu;
@@ -275,7 +275,7 @@ static void move_to_next_cpu(void)
return;
/* Just pick the first CPU on first iteration */
- if (!current_mask) {
+ if (initmask) {
current_mask = &save_cpumask;
get_online_cpus();
cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
@@ -330,10 +330,12 @@ static void move_to_next_cpu(void)
static int kthread_fn(void *data)
{
u64 interval;
+ bool initmask = true;
while (!kthread_should_stop()) {
- move_to_next_cpu();
+ move_to_next_cpu(initmask);
+ initmask = false;
local_irq_disable();
get_sample();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a133ecd741e4..7ad9e53ad174 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1372,7 +1372,7 @@ kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6)
return a1 + a2 + a3 + a4 + a5 + a6;
}
-static struct __init trace_event_file *
+static __init struct trace_event_file *
find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
{
struct trace_event_file *file;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 9d20d5dd298a..95c6336fc2b3 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -128,10 +128,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
struct hlist_head *hashent = ucounts_hashentry(ns, uid);
struct ucounts *ucounts, *new;
- spin_lock(&ucounts_lock);
+ spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (!ucounts) {
- spin_unlock(&ucounts_lock);
+ spin_unlock_irq(&ucounts_lock);
new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
@@ -141,7 +141,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
new->uid = uid;
atomic_set(&new->count, 0);
- spin_lock(&ucounts_lock);
+ spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (ucounts) {
kfree(new);
@@ -152,16 +152,18 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
}
if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
ucounts = NULL;
- spin_unlock(&ucounts_lock);
+ spin_unlock_irq(&ucounts_lock);
return ucounts;
}
static void put_ucounts(struct ucounts *ucounts)
{
+ unsigned long flags;
+
if (atomic_dec_and_test(&ucounts->count)) {
- spin_lock(&ucounts_lock);
+ spin_lock_irqsave(&ucounts_lock, flags);
hlist_del_init(&ucounts->node);
- spin_unlock(&ucounts_lock);
+ spin_unlock_irqrestore(&ucounts_lock, flags);
kfree(ucounts);
}
@@ -225,11 +227,10 @@ static __init int user_namespace_sysctl_init(void)
* properly.
*/
user_header = register_sysctl("user", empty);
+ kmemleak_ignore(user_header);
BUG_ON(!user_header);
BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
return 0;
}
subsys_initcall(user_namespace_sysctl_init);
-
-
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d4b0fa01cae3..63177be0159e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
#define for_each_watchdog_cpu(cpu) \
for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
+
/*
* The 'watchdog_running' variable is set to 1 when the watchdog threads
* are registered/started and is set to 0 when the watchdog threads are
@@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
int duration;
int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
+ if (atomic_read(&watchdog_park_in_progress) != 0)
+ return HRTIMER_NORESTART;
+
/* kick the hardlockup detector */
watchdog_interrupt_count();
@@ -467,12 +472,16 @@ static int watchdog_park_threads(void)
{
int cpu, ret = 0;
+ atomic_set(&watchdog_park_in_progress, 1);
+
for_each_watchdog_cpu(cpu) {
ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
if (ret)
break;
}
+ atomic_set(&watchdog_park_in_progress, 0);
+
return ret;
}
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 84016c8aee6b..12b8dd640786 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event,
/* Ensure the watchdog never gets throttled */
event->hw.interrupts = 0;
+ if (atomic_read(&watchdog_park_in_progress) != 0)
+ return;
+
if (__this_cpu_read(watchdog_nmi_touch) == true) {
__this_cpu_write(watchdog_nmi_touch, false);
return;