aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/cgroup/cgroup.c37
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/module/internal.h13
-rw-r--r--kernel/module/kallsyms.c35
-rw-r--r--kernel/module/main.c9
-rw-r--r--kernel/time/posix-timers.c19
-rw-r--r--kernel/trace/Kconfig3
-rw-r--r--kernel/trace/trace.c11
-rw-r--r--kernel/trace/trace_events_hist.c2
9 files changed, 83 insertions, 48 deletions
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1779ccddb734..13c8e91d7862 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -765,7 +765,8 @@ struct css_set init_css_set = {
.task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
.threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets),
.cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links),
- .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node),
+ .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node),
+ .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node),
.mg_node = LIST_HEAD_INIT(init_css_set.mg_node),
/*
@@ -1240,7 +1241,8 @@ static struct css_set *find_css_set(struct css_set *old_cset,
INIT_LIST_HEAD(&cset->threaded_csets);
INIT_HLIST_NODE(&cset->hlist);
INIT_LIST_HEAD(&cset->cgrp_links);
- INIT_LIST_HEAD(&cset->mg_preload_node);
+ INIT_LIST_HEAD(&cset->mg_src_preload_node);
+ INIT_LIST_HEAD(&cset->mg_dst_preload_node);
INIT_LIST_HEAD(&cset->mg_node);
/* Copy the set of subsystem state objects generated in
@@ -2597,21 +2599,27 @@ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp)
*/
void cgroup_migrate_finish(struct cgroup_mgctx *mgctx)
{
- LIST_HEAD(preloaded);
struct css_set *cset, *tmp_cset;
lockdep_assert_held(&cgroup_mutex);
spin_lock_irq(&css_set_lock);
- list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded);
- list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded);
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets,
+ mg_src_preload_node) {
+ cset->mg_src_cgrp = NULL;
+ cset->mg_dst_cgrp = NULL;
+ cset->mg_dst_cset = NULL;
+ list_del_init(&cset->mg_src_preload_node);
+ put_css_set_locked(cset);
+ }
- list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) {
+ list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets,
+ mg_dst_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cgrp = NULL;
cset->mg_dst_cset = NULL;
- list_del_init(&cset->mg_preload_node);
+ list_del_init(&cset->mg_dst_preload_node);
put_css_set_locked(cset);
}
@@ -2651,7 +2659,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
if (src_cset->dead)
return;
- if (!list_empty(&src_cset->mg_preload_node))
+ if (!list_empty(&src_cset->mg_src_preload_node))
return;
src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
@@ -2664,7 +2672,7 @@ void cgroup_migrate_add_src(struct css_set *src_cset,
src_cset->mg_src_cgrp = src_cgrp;
src_cset->mg_dst_cgrp = dst_cgrp;
get_css_set(src_cset);
- list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets);
+ list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets);
}
/**
@@ -2689,7 +2697,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
/* look up the dst cset for each src cset and link it to src */
list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets,
- mg_preload_node) {
+ mg_src_preload_node) {
struct css_set *dst_cset;
struct cgroup_subsys *ss;
int ssid;
@@ -2708,7 +2716,7 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
if (src_cset == dst_cset) {
src_cset->mg_src_cgrp = NULL;
src_cset->mg_dst_cgrp = NULL;
- list_del_init(&src_cset->mg_preload_node);
+ list_del_init(&src_cset->mg_src_preload_node);
put_css_set(src_cset);
put_css_set(dst_cset);
continue;
@@ -2716,8 +2724,8 @@ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx)
src_cset->mg_dst_cset = dst_cset;
- if (list_empty(&dst_cset->mg_preload_node))
- list_add_tail(&dst_cset->mg_preload_node,
+ if (list_empty(&dst_cset->mg_dst_preload_node))
+ list_add_tail(&dst_cset->mg_dst_preload_node,
&mgctx->preloaded_dst_csets);
else
put_css_set(dst_cset);
@@ -2963,7 +2971,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
goto out_finish;
spin_lock_irq(&css_set_lock);
- list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) {
+ list_for_each_entry(src_cset, &mgctx.preloaded_src_csets,
+ mg_src_preload_node) {
struct task_struct *task, *ntask;
/* all tasks in src_csets need to be migrated */
diff --git a/kernel/exit.c b/kernel/exit.c
index f072959fcab7..64c938ce36fe 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -766,7 +766,7 @@ void __noreturn do_exit(long code)
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
- exit_itimers(tsk->signal);
+ exit_itimers(tsk);
#endif
if (tsk->mm)
setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index bc5507ab8450..ec104c2950c3 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -11,6 +11,7 @@
#include <linux/mutex.h>
#include <linux/rculist.h>
#include <linux/rcupdate.h>
+#include <linux/mm.h>
#ifndef ARCH_SHF_SMALL
#define ARCH_SHF_SMALL 0
@@ -30,11 +31,13 @@
* to ensure complete separation of code and data, but
* only when CONFIG_STRICT_MODULE_RWX=y
*/
-#ifdef CONFIG_STRICT_MODULE_RWX
-# define strict_align(X) PAGE_ALIGN(X)
-#else
-# define strict_align(X) (X)
-#endif
+static inline unsigned int strict_align(unsigned int size)
+{
+ if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ return PAGE_ALIGN(size);
+ else
+ return size;
+}
extern struct mutex module_mutex;
extern struct list_head modules;
diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c
index 3e11523bc6f6..77e75bead569 100644
--- a/kernel/module/kallsyms.c
+++ b/kernel/module/kallsyms.c
@@ -137,6 +137,7 @@ void layout_symtab(struct module *mod, struct load_info *info)
info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1);
info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym);
mod->data_layout.size += strtab_size;
+ /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */
info->core_typeoffs = mod->data_layout.size;
mod->data_layout.size += ndst * sizeof(char);
mod->data_layout.size = strict_align(mod->data_layout.size);
@@ -169,19 +170,20 @@ void add_kallsyms(struct module *mod, const struct load_info *info)
Elf_Sym *dst;
char *s;
Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
+ unsigned long strtab_size;
/* Set up to point into init section. */
mod->kallsyms = (void __rcu *)mod->init_layout.base +
info->mod_kallsyms_init_off;
- preempt_disable();
+ rcu_read_lock();
/* The following is safe since this pointer cannot change */
- rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr;
- rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+ rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr;
+ rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
/* Make sure we get permanent strtab: don't use info->strtab. */
- rcu_dereference_sched(mod->kallsyms)->strtab =
+ rcu_dereference(mod->kallsyms)->strtab =
(void *)info->sechdrs[info->index.str].sh_addr;
- rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs;
+ rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs;
/*
* Now populate the cut down core kallsyms for after init
@@ -190,22 +192,29 @@ void add_kallsyms(struct module *mod, const struct load_info *info)
mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs;
mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs;
mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs;
- src = rcu_dereference_sched(mod->kallsyms)->symtab;
- for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) {
- rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info);
+ strtab_size = info->core_typeoffs - info->stroffs;
+ src = rcu_dereference(mod->kallsyms)->symtab;
+ for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) {
+ rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info);
if (i == 0 || is_livepatch_module(mod) ||
is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum,
info->index.pcpu)) {
+ ssize_t ret;
+
mod->core_kallsyms.typetab[ndst] =
- rcu_dereference_sched(mod->kallsyms)->typetab[i];
+ rcu_dereference(mod->kallsyms)->typetab[i];
dst[ndst] = src[i];
dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
- s += strscpy(s,
- &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name],
- KSYM_NAME_LEN) + 1;
+ ret = strscpy(s,
+ &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name],
+ strtab_size);
+ if (ret < 0)
+ break;
+ s += ret + 1;
+ strtab_size -= ret + 1;
}
}
- preempt_enable();
+ rcu_read_unlock();
mod->core_kallsyms.num_symtab = ndst;
}
diff --git a/kernel/module/main.c b/kernel/module/main.c
index fed58d30725d..0548151dd933 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2939,24 +2939,25 @@ static void cfi_init(struct module *mod)
{
#ifdef CONFIG_CFI_CLANG
initcall_t *init;
+#ifdef CONFIG_MODULE_UNLOAD
exitcall_t *exit;
+#endif
rcu_read_lock_sched();
mod->cfi_check = (cfi_check_fn)
find_kallsyms_symbol_value(mod, "__cfi_check");
init = (initcall_t *)
find_kallsyms_symbol_value(mod, "__cfi_jt_init_module");
- exit = (exitcall_t *)
- find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module");
- rcu_read_unlock_sched();
-
/* Fix init/exit functions to point to the CFI jump table */
if (init)
mod->init = *init;
#ifdef CONFIG_MODULE_UNLOAD
+ exit = (exitcall_t *)
+ find_kallsyms_symbol_value(mod, "__cfi_jt_cleanup_module");
if (exit)
mod->exit = *exit;
#endif
+ rcu_read_unlock_sched();
cfi_module_add(mod, mod_tree.addr_min);
#endif
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ retry_delete:
}
/*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
*/
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
{
+ struct list_head timers;
struct k_itimer *tmr;
- while (!list_empty(&sig->posix_timers)) {
- tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+ if (list_empty(&tsk->signal->posix_timers))
+ return;
+
+ spin_lock_irq(&tsk->sighand->siglock);
+ list_replace_init(&tsk->signal->posix_timers, &timers);
+ spin_unlock_irq(&tsk->sighand->siglock);
+
+ while (!list_empty(&timers)) {
+ tmr = list_first_entry(&timers, struct k_itimer, list);
itimer_delete(tmr);
}
}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index debbbb083286..ccd6a5ade3e9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -194,7 +194,8 @@ config FUNCTION_TRACER
sequence is then dynamically patched into a tracer call when
tracing is enabled by the administrator. If it's runtime disabled
(the bootup default), then the overhead of the instructions is very
- small and not measurable even in micro-benchmarks.
+ small and not measurable even in micro-benchmarks (at least on
+ x86, but may have impact on other architectures).
config FUNCTION_GRAPH_TRACER
bool "Kernel Function Graph Tracer"
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a8cfac0611bc..b8dd54627075 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -9864,6 +9864,12 @@ void trace_init_global_iter(struct trace_iterator *iter)
/* Output in nanoseconds only if we are using a clock in nanoseconds. */
if (trace_clocks[iter->tr->clock_id].in_ns)
iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
+
+ /* Can not use kmalloc for iter.temp and iter.fmt */
+ iter->temp = static_temp_buf;
+ iter->temp_size = STATIC_TEMP_BUF_SIZE;
+ iter->fmt = static_fmt_buf;
+ iter->fmt_size = STATIC_FMT_BUF_SIZE;
}
void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
@@ -9896,11 +9902,6 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
/* Simulate the iterator */
trace_init_global_iter(&iter);
- /* Can not use kmalloc for iter.temp and iter.fmt */
- iter.temp = static_temp_buf;
- iter.temp_size = STATIC_TEMP_BUF_SIZE;
- iter.fmt = static_fmt_buf;
- iter.fmt_size = STATIC_FMT_BUF_SIZE;
for_each_tracing_cpu(cpu) {
atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 48e82e141d54..e87a46794079 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -4430,6 +4430,8 @@ static int parse_var_defs(struct hist_trigger_data *hist_data)
s = kstrdup(field_str, GFP_KERNEL);
if (!s) {
+ kfree(hist_data->attrs->var_defs.name[n_vars]);
+ hist_data->attrs->var_defs.name[n_vars] = NULL;
ret = -ENOMEM;
goto free;
}
Powered by cgit, Gruvboxed by Blaster4385.