summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/audit.c47
-rw-r--r--kernel/audit.h3
-rw-r--r--kernel/audit_tree.c88
-rw-r--r--kernel/auditsc.c9
-rw-r--r--kernel/bpf/verifier.c12
-rw-r--r--kernel/fork.c141
-rw-r--r--kernel/gcov/base.c5
-rw-r--r--kernel/locking/lockdep.c16
-rw-r--r--kernel/module.c9
-rw-r--r--kernel/params.c4
-rw-r--r--kernel/pid.c15
-rw-r--r--kernel/printk/printk.c53
-rw-r--r--kernel/ptrace.c39
-rw-r--r--kernel/signal.c14
-rw-r--r--kernel/smp.c80
-rw-r--r--kernel/sys.c47
-rw-r--r--kernel/sysctl.c16
-rw-r--r--kernel/time/clockevents.c2
-rw-r--r--kernel/trace/trace_events.c15
-rw-r--r--kernel/trace/trace_functions_graph.c8
20 files changed, 405 insertions, 218 deletions
diff --git a/kernel/audit.c b/kernel/audit.c
index 72ab759a0b43..ab5745ddf962 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -43,6 +43,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/file.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/atomic.h>
@@ -107,6 +108,7 @@ static u32 audit_rate_limit;
* When set to zero, this means unlimited. */
static u32 audit_backlog_limit = 64;
#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static u32 audit_backlog_wait_time_master = AUDIT_BACKLOG_WAIT_TIME;
static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
static u32 audit_backlog_wait_overflow = 0;
@@ -338,13 +340,13 @@ static int audit_set_backlog_limit(u32 limit)
static int audit_set_backlog_wait_time(u32 timeout)
{
return audit_do_config_change("audit_backlog_wait_time",
- &audit_backlog_wait_time, timeout);
+ &audit_backlog_wait_time_master, timeout);
}
static int audit_set_enabled(u32 state)
{
int rc;
- if (state < AUDIT_OFF || state > AUDIT_LOCKED)
+ if (state > AUDIT_LOCKED)
return -EINVAL;
rc = audit_do_config_change("audit_enabled", &audit_enabled, state);
@@ -663,7 +665,7 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type)
case AUDIT_MAKE_EQUIV:
/* Only support auditd and auditctl in initial pid namespace
* for now. */
- if ((task_active_pid_ns(current) != &init_pid_ns))
+ if (task_active_pid_ns(current) != &init_pid_ns)
return -EPERM;
if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
@@ -834,7 +836,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.lost = atomic_read(&audit_lost);
s.backlog = skb_queue_len(&audit_skb_queue);
s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL;
- s.backlog_wait_time = audit_backlog_wait_time;
+ s.backlog_wait_time = audit_backlog_wait_time_master;
audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
@@ -877,8 +879,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) {
if (sizeof(s) > (size_t)nlh->nlmsg_len)
return -EINVAL;
- if (s.backlog_wait_time < 0 ||
- s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME)
+ if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME)
return -EINVAL;
err = audit_set_backlog_wait_time(s.backlog_wait_time);
if (err < 0)
@@ -1385,7 +1386,8 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
return NULL;
}
- audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+ if (!reserve)
+ audit_backlog_wait_time = audit_backlog_wait_time_master;
ab = audit_buffer_alloc(ctx, gfp_mask, type);
if (!ab) {
@@ -1759,7 +1761,7 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
} else
audit_log_format(ab, " name=(null)");
- if (n->ino != (unsigned long)-1) {
+ if (n->ino != (unsigned long)-1)
audit_log_format(ab, " inode=%lu"
" dev=%02x:%02x mode=%#ho"
" ouid=%u ogid=%u rdev=%02x:%02x",
@@ -1771,7 +1773,6 @@ void audit_log_name(struct audit_context *context, struct audit_names *n,
from_kgid(&init_user_ns, n->gid),
MAJOR(n->rdev),
MINOR(n->rdev));
- }
if (n->osid != 0) {
char *ctx = NULL;
u32 len;
@@ -1838,11 +1839,29 @@ error_path:
}
EXPORT_SYMBOL(audit_log_task_context);
+void audit_log_d_path_exe(struct audit_buffer *ab,
+ struct mm_struct *mm)
+{
+ struct file *exe_file;
+
+ if (!mm)
+ goto out_null;
+
+ exe_file = get_mm_exe_file(mm);
+ if (!exe_file)
+ goto out_null;
+
+ audit_log_d_path(ab, " exe=", &exe_file->f_path);
+ fput(exe_file);
+ return;
+out_null:
+ audit_log_format(ab, " exe=(null)");
+}
+
void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
const struct cred *cred;
char comm[sizeof(tsk->comm)];
- struct mm_struct *mm = tsk->mm;
char *tty;
if (!ab)
@@ -1878,13 +1897,7 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
audit_log_format(ab, " comm=");
audit_log_untrustedstring(ab, get_task_comm(comm, tsk));
- if (mm) {
- down_read(&mm->mmap_sem);
- if (mm->exe_file)
- audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
- up_read(&mm->mmap_sem);
- } else
- audit_log_format(ab, " exe=(null)");
+ audit_log_d_path_exe(ab, tsk->mm);
audit_log_task_context(ab);
}
EXPORT_SYMBOL(audit_log_task_info);
diff --git a/kernel/audit.h b/kernel/audit.h
index 1caa0d345d90..d641f9bb3ed0 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -257,6 +257,9 @@ extern struct list_head audit_filter_list[];
extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);
+extern void audit_log_d_path_exe(struct audit_buffer *ab,
+ struct mm_struct *mm);
+
/* audit watch functions */
#ifdef CONFIG_AUDIT_WATCH
extern void audit_put_watch(struct audit_watch *watch);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 2e0c97427b33..71fd1f289885 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -37,6 +37,7 @@ struct audit_chunk {
static LIST_HEAD(tree_list);
static LIST_HEAD(prune_list);
+static struct task_struct *prune_thread;
/*
* One struct chunk is attached to each inode of interest.
@@ -651,6 +652,57 @@ static int tag_mount(struct vfsmount *mnt, void *arg)
return tag_chunk(mnt->mnt_root->d_inode, arg);
}
+/*
+ * That gets run when evict_chunk() ends up needing to kill audit_tree.
+ * Runs from a separate thread.
+ */
+static int prune_tree_thread(void *unused)
+{
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (list_empty(&prune_list))
+ schedule();
+ __set_current_state(TASK_RUNNING);
+
+ mutex_lock(&audit_cmd_mutex);
+ mutex_lock(&audit_filter_mutex);
+
+ while (!list_empty(&prune_list)) {
+ struct audit_tree *victim;
+
+ victim = list_entry(prune_list.next,
+ struct audit_tree, list);
+ list_del_init(&victim->list);
+
+ mutex_unlock(&audit_filter_mutex);
+
+ prune_one(victim);
+
+ mutex_lock(&audit_filter_mutex);
+ }
+
+ mutex_unlock(&audit_filter_mutex);
+ mutex_unlock(&audit_cmd_mutex);
+ }
+ return 0;
+}
+
+static int audit_launch_prune(void)
+{
+ if (prune_thread)
+ return 0;
+ prune_thread = kthread_create(prune_tree_thread, NULL,
+ "audit_prune_tree");
+ if (IS_ERR(prune_thread)) {
+ pr_err("cannot start thread audit_prune_tree");
+ prune_thread = NULL;
+ return -ENOMEM;
+ } else {
+ wake_up_process(prune_thread);
+ return 0;
+ }
+}
+
/* called with audit_filter_mutex */
int audit_add_tree_rule(struct audit_krule *rule)
{
@@ -674,6 +726,12 @@ int audit_add_tree_rule(struct audit_krule *rule)
/* do not set rule->tree yet */
mutex_unlock(&audit_filter_mutex);
+ if (unlikely(!prune_thread)) {
+ err = audit_launch_prune();
+ if (err)
+ goto Err;
+ }
+
err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
@@ -811,36 +869,10 @@ int audit_tag_tree(char *old, char *new)
return failed;
}
-/*
- * That gets run when evict_chunk() ends up needing to kill audit_tree.
- * Runs from a separate thread.
- */
-static int prune_tree_thread(void *unused)
-{
- mutex_lock(&audit_cmd_mutex);
- mutex_lock(&audit_filter_mutex);
-
- while (!list_empty(&prune_list)) {
- struct audit_tree *victim;
-
- victim = list_entry(prune_list.next, struct audit_tree, list);
- list_del_init(&victim->list);
-
- mutex_unlock(&audit_filter_mutex);
-
- prune_one(victim);
-
- mutex_lock(&audit_filter_mutex);
- }
-
- mutex_unlock(&audit_filter_mutex);
- mutex_unlock(&audit_cmd_mutex);
- return 0;
-}
static void audit_schedule_prune(void)
{
- kthread_run(prune_tree_thread, NULL, "audit_prune_tree");
+ wake_up_process(prune_thread);
}
/*
@@ -907,9 +939,9 @@ static void evict_chunk(struct audit_chunk *chunk)
for (n = 0; n < chunk->count; n++)
list_del_init(&chunk->owners[n].list);
spin_unlock(&hash_lock);
+ mutex_unlock(&audit_filter_mutex);
if (need_prune)
audit_schedule_prune();
- mutex_unlock(&audit_filter_mutex);
}
static int audit_tree_handle_event(struct fsnotify_group *group,
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index dc4ae70a7413..84c74d08c62b 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2361,7 +2361,6 @@ static void audit_log_task(struct audit_buffer *ab)
kuid_t auid, uid;
kgid_t gid;
unsigned int sessionid;
- struct mm_struct *mm = current->mm;
char comm[sizeof(current->comm)];
auid = audit_get_loginuid(current);
@@ -2376,13 +2375,7 @@ static void audit_log_task(struct audit_buffer *ab)
audit_log_task_context(ab);
audit_log_format(ab, " pid=%d comm=", task_pid_nr(current));
audit_log_untrustedstring(ab, get_task_comm(comm, current));
- if (mm) {
- down_read(&mm->mmap_sem);
- if (mm->exe_file)
- audit_log_d_path(ab, " exe=", &mm->exe_file->f_path);
- up_read(&mm->mmap_sem);
- } else
- audit_log_format(ab, " exe=(null)");
+ audit_log_d_path_exe(ab, current->mm);
}
/**
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 630a7bac1e51..47dcd3aa6e23 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1397,7 +1397,8 @@ peek_stack:
/* tell verifier to check for equivalent states
* after every call and jump
*/
- env->explored_states[t + 1] = STATE_LIST_MARK;
+ if (t + 1 < insn_cnt)
+ env->explored_states[t + 1] = STATE_LIST_MARK;
} else {
/* conditional jump with two edges */
ret = push_insn(t, t + 1, FALLTHROUGH, env);
@@ -1636,6 +1637,8 @@ static int do_check(struct verifier_env *env)
if (err)
return err;
+ src_reg_type = regs[insn->src_reg].type;
+
/* check that memory (src_reg + off) is readable,
* the state of dst_reg will be updated by this func
*/
@@ -1645,9 +1648,12 @@ static int do_check(struct verifier_env *env)
if (err)
return err;
- src_reg_type = regs[insn->src_reg].type;
+ if (BPF_SIZE(insn->code) != BPF_W) {
+ insn_idx++;
+ continue;
+ }
- if (insn->imm == 0 && BPF_SIZE(insn->code) == BPF_W) {
+ if (insn->imm == 0) {
/* saw a valid insn
* dst_reg = *(u32 *)(src_reg + off)
* use reserved 'imm' field to mark this insn
diff --git a/kernel/fork.c b/kernel/fork.c
index f2c1e7352298..03c1eaaa6ef5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -74,6 +74,7 @@
#include <linux/uprobes.h>
#include <linux/aio.h>
#include <linux/compiler.h>
+#include <linux/sysctl.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -88,6 +89,16 @@
#include <trace/events/task.h>
/*
+ * Minimum number of threads to boot the kernel
+ */
+#define MIN_THREADS 20
+
+/*
+ * Maximum number of threads
+ */
+#define MAX_THREADS FUTEX_TID_MASK
+
+/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
unsigned long total_forks; /* Handle normal Linux uptimes. */
@@ -253,7 +264,30 @@ EXPORT_SYMBOL_GPL(__put_task_struct);
void __init __weak arch_task_cache_init(void) { }
-void __init fork_init(unsigned long mempages)
+/*
+ * set_max_threads
+ */
+static void set_max_threads(unsigned int max_threads_suggested)
+{
+ u64 threads;
+
+ /*
+ * The number of threads shall be limited such that the thread
+ * structures may only consume a small part of the available memory.
+ */
+ if (fls64(totalram_pages) + fls64(PAGE_SIZE) > 64)
+ threads = MAX_THREADS;
+ else
+ threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
+ (u64) THREAD_SIZE * 8UL);
+
+ if (threads > max_threads_suggested)
+ threads = max_threads_suggested;
+
+ max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
+}
+
+void __init fork_init(void)
{
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
@@ -268,18 +302,7 @@ void __init fork_init(unsigned long mempages)
/* do the arch specific task caches init */
arch_task_cache_init();
- /*
- * The default maximum number of threads is set to a safe
- * value: the thread structures can take up at most half
- * of memory.
- */
- max_threads = mempages / (8 * THREAD_SIZE / PAGE_SIZE);
-
- /*
- * we need to allow at least 20 threads to boot a system
- */
- if (max_threads < 20)
- max_threads = 20;
+ set_max_threads(MAX_THREADS);
init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
@@ -380,6 +403,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
*/
down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
+ /* No ordering required: file already has been exposed. */
+ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+
mm->total_vm = oldmm->total_vm;
mm->shared_vm = oldmm->shared_vm;
mm->exec_vm = oldmm->exec_vm;
@@ -505,7 +531,13 @@ static inline void mm_free_pgd(struct mm_struct *mm)
pgd_free(mm, mm->pgd);
}
#else
-#define dup_mmap(mm, oldmm) (0)
+static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+ down_write(&oldmm->mmap_sem);
+ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ up_write(&oldmm->mmap_sem);
+ return 0;
+}
#define mm_alloc_pgd(mm) (0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */
@@ -674,34 +706,53 @@ void mmput(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mmput);
+/**
+ * set_mm_exe_file - change a reference to the mm's executable file
+ *
+ * This changes mm's executable file (shown as symlink /proc/[pid]/exe).
+ *
+ * Main users are mmput() and sys_execve(). Callers prevent concurrent
+ * invocations: in mmput() nobody alive left, in execve task is single
+ * threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
+ * mm->exe_file, but does so without using set_mm_exe_file() in order
+ * to do avoid the need for any locks.
+ */
void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
+ struct file *old_exe_file;
+
+ /*
+ * It is safe to dereference the exe_file without RCU as
+ * this function is only called if nobody else can access
+ * this mm -- see comment above for justification.
+ */
+ old_exe_file = rcu_dereference_raw(mm->exe_file);
+
if (new_exe_file)
get_file(new_exe_file);
- if (mm->exe_file)
- fput(mm->exe_file);
- mm->exe_file = new_exe_file;
+ rcu_assign_pointer(mm->exe_file, new_exe_file);
+ if (old_exe_file)
+ fput(old_exe_file);
}
+/**
+ * get_mm_exe_file - acquire a reference to the mm's executable file
+ *
+ * Returns %NULL if mm has no associated executable file.
+ * User must release file via fput().
+ */
struct file *get_mm_exe_file(struct mm_struct *mm)
{
struct file *exe_file;
- /* We need mmap_sem to protect against races with removal of exe_file */
- down_read(&mm->mmap_sem);
- exe_file = mm->exe_file;
- if (exe_file)
- get_file(exe_file);
- up_read(&mm->mmap_sem);
+ rcu_read_lock();
+ exe_file = rcu_dereference(mm->exe_file);
+ if (exe_file && !get_file_rcu(exe_file))
+ exe_file = NULL;
+ rcu_read_unlock();
return exe_file;
}
-
-static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
-{
- /* It's safe to write the exe_file pointer without exe_file_lock because
- * this is called during fork when the task is not yet in /proc */
- newmm->exe_file = get_mm_exe_file(oldmm);
-}
+EXPORT_SYMBOL(get_mm_exe_file);
/**
* get_task_mm - acquire a reference to the task's mm
@@ -864,8 +915,6 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
if (!mm_init(mm, tsk))
goto fail_nomem;
- dup_mm_exe_file(oldmm, mm);
-
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
@@ -1403,10 +1452,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_cleanup_io;
if (pid != &init_struct_pid) {
- retval = -ENOMEM;
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
- if (!pid)
+ if (IS_ERR(pid)) {
+ retval = PTR_ERR(pid);
goto bad_fork_cleanup_io;
+ }
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -2000,3 +2050,26 @@ int unshare_files(struct files_struct **displaced)
task_unlock(task);
return 0;
}
+
+int sysctl_max_threads(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table t;
+ int ret;
+ int threads = max_threads;
+ int min = MIN_THREADS;
+ int max = MAX_THREADS;
+
+ t = *table;
+ t.data = &threads;
+ t.extra1 = &min;
+ t.extra2 = &max;
+
+ ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+ if (ret || !write)
+ return ret;
+
+ set_max_threads(threads);
+
+ return 0;
+}
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index b358a802fd18..a744098e4eb7 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -18,6 +18,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/sched.h>
#include "gcov.h"
static int gcov_events_enabled;
@@ -107,8 +108,10 @@ void gcov_enable_events(void)
gcov_events_enabled = 1;
/* Perform event callback for previously registered entries. */
- while ((info = gcov_info_next(info)))
+ while ((info = gcov_info_next(info))) {
gcov_event(GCOV_ADD, info);
+ cond_resched();
+ }
mutex_unlock(&gcov_lock);
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index ba77ab5f64dd..a0831e1b99f4 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -551,7 +551,21 @@ static void print_lockdep_cache(struct lockdep_map *lock)
static void print_lock(struct held_lock *hlock)
{
- print_lock_name(hlock_class(hlock));
+ /*
+ * We can be called locklessly through debug_show_all_locks() so be
+ * extra careful, the hlock might have been released and cleared.
+ */
+ unsigned int class_idx = hlock->class_idx;
+
+ /* Don't re-read hlock->class_idx, can't use READ_ONCE() on bitfields: */
+ barrier();
+
+ if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) {
+ printk("<RELEASED>\n");
+ return;
+ }
+
+ print_lock_name(lock_classes + class_idx - 1);
printk(", at: ");
print_ip_sym(hlock->acquire_ip);
}
diff --git a/kernel/module.c b/kernel/module.c
index 650b038ae520..42a1d2afb217 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -387,9 +387,9 @@ static bool check_symbol(const struct symsearch *syms,
pr_warn("Symbol %s is marked as UNUSED, however this module is "
"using it.\n", fsa->name);
pr_warn("This symbol will go away in the future.\n");
- pr_warn("Please evalute if this is the right api to use and if "
- "it really is, submit a report the linux kernel "
- "mailinglist together with submitting your code for "
+ pr_warn("Please evaluate if this is the right api to use and "
+ "if it really is, submit a report to the linux kernel "
+ "mailing list together with submitting your code for "
"inclusion.\n");
}
#endif
@@ -2511,7 +2511,8 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
return err;
/* Suck in entire file: we'll want most of it. */
- info->hdr = vmalloc(info->len);
+ info->hdr = __vmalloc(info->len,
+ GFP_KERNEL | __GFP_HIGHMEM | __GFP_NOWARN, PAGE_KERNEL);
if (!info->hdr)
return -ENOMEM;
diff --git a/kernel/params.c b/kernel/params.c
index 728e05b167de..a22d6a759b1a 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -173,9 +173,9 @@ static char *next_arg(char *args, char **param, char **val)
if (args[i-1] == '"')
args[i-1] = '\0';
}
- if (quoted && args[i-1] == '"')
- args[i-1] = '\0';
}
+ if (quoted && args[i-1] == '"')
+ args[i-1] = '\0';
if (args[i]) {
args[i] = '\0';
diff --git a/kernel/pid.c b/kernel/pid.c
index cd36a5e0d173..4fd07d5b7baf 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -182,7 +182,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
spin_unlock_irq(&pidmap_lock);
kfree(page);
if (unlikely(!map->page))
- break;
+ return -ENOMEM;
}
if (likely(atomic_read(&map->nr_free))) {
for ( ; ; ) {
@@ -210,7 +210,7 @@ static int alloc_pidmap(struct pid_namespace *pid_ns)
}
pid = mk_pid(pid_ns, map, offset);
}
- return -1;
+ return -EAGAIN;
}
int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
@@ -301,17 +301,20 @@ struct pid *alloc_pid(struct pid_namespace *ns)
int i, nr;
struct pid_namespace *tmp;
struct upid *upid;
+ int retval = -ENOMEM;
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid)
- goto out;
+ return ERR_PTR(retval);
tmp = ns;
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
nr = alloc_pidmap(tmp);
- if (nr < 0)
+ if (IS_ERR_VALUE(nr)) {
+ retval = nr;
goto out_free;
+ }
pid->numbers[i].nr = nr;
pid->numbers[i].ns = tmp;
@@ -339,7 +342,6 @@ struct pid *alloc_pid(struct pid_namespace *ns)
}
spin_unlock_irq(&pidmap_lock);
-out:
return pid;
out_unlock:
@@ -351,8 +353,7 @@ out_free:
free_pidmap(pid->numbers + i);
kmem_cache_free(ns->pid_cachep, pid);
- pid = NULL;
- goto out;
+ return ERR_PTR(retval);
}
void disable_pid_allocation(struct pid_namespace *ns)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 879edfc5ee52..c099b082cd02 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2017,24 +2017,6 @@ int add_preferred_console(char *name, int idx, char *options)
return __add_preferred_console(name, idx, options, NULL);
}
-int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options)
-{
- struct console_cmdline *c;
- int i;
-
- for (i = 0, c = console_cmdline;
- i < MAX_CMDLINECONSOLES && c->name[0];
- i++, c++)
- if (strcmp(c->name, name) == 0 && c->index == idx) {
- strlcpy(c->name, name_new, sizeof(c->name));
- c->options = options;
- c->index = idx_new;
- return i;
- }
- /* not found */
- return -1;
-}
-
bool console_suspend_enabled = true;
EXPORT_SYMBOL(console_suspend_enabled);
@@ -2436,9 +2418,6 @@ void register_console(struct console *newcon)
if (preferred_console < 0 || bcon || !console_drivers)
preferred_console = selected_console;
- if (newcon->early_setup)
- newcon->early_setup();
-
/*
* See if we want to use this console driver. If we
* didn't select a console we take the first one
@@ -2464,23 +2443,27 @@ void register_console(struct console *newcon)
for (i = 0, c = console_cmdline;
i < MAX_CMDLINECONSOLES && c->name[0];
i++, c++) {
- BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
- if (strcmp(c->name, newcon->name) != 0)
- continue;
- if (newcon->index >= 0 &&
- newcon->index != c->index)
- continue;
- if (newcon->index < 0)
- newcon->index = c->index;
+ if (!newcon->match ||
+ newcon->match(newcon, c->name, c->index, c->options) != 0) {
+ /* default matching */
+ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
+ if (strcmp(c->name, newcon->name) != 0)
+ continue;
+ if (newcon->index >= 0 &&
+ newcon->index != c->index)
+ continue;
+ if (newcon->index < 0)
+ newcon->index = c->index;
- if (_braille_register_console(newcon, c))
- return;
+ if (_braille_register_console(newcon, c))
+ return;
+
+ if (newcon->setup &&
+ newcon->setup(newcon, c->options) != 0)
+ break;
+ }
- if (newcon->setup &&
- newcon->setup(newcon, console_cmdline[i].options) != 0)
- break;
newcon->flags |= CON_ENABLED;
- newcon->index = c->index;
if (i == selected_console) {
newcon->flags |= CON_CONSDEV;
preferred_console = selected_console;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 227fec36b12a..c8e0e050a36a 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -456,8 +456,6 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
static int ptrace_detach(struct task_struct *child, unsigned int data)
{
- bool dead = false;
-
if (!valid_signal(data))
return -EIO;
@@ -467,18 +465,19 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
write_lock_irq(&tasklist_lock);
/*
- * This child can be already killed. Make sure de_thread() or
- * our sub-thread doing do_wait() didn't do release_task() yet.
+ * We rely on ptrace_freeze_traced(). It can't be killed and
+ * untraced by another thread, it can't be a zombie.
*/
- if (child->ptrace) {
- child->exit_code = data;
- dead = __ptrace_detach(current, child);
- }
+ WARN_ON(!child->ptrace || child->exit_state);
+ /*
+ * tasklist_lock avoids the race with wait_task_stopped(), see
+ * the comment in ptrace_resume().
+ */
+ child->exit_code = data;
+ __ptrace_detach(current, child);
write_unlock_irq(&tasklist_lock);
proc_ptrace_connector(child, PTRACE_DETACH);
- if (unlikely(dead))
- release_task(child);
return 0;
}
@@ -697,6 +696,8 @@ static int ptrace_peek_siginfo(struct task_struct *child,
static int ptrace_resume(struct task_struct *child, long request,
unsigned long data)
{
+ bool need_siglock;
+
if (!valid_signal(data))
return -EIO;
@@ -724,8 +725,26 @@ static int ptrace_resume(struct task_struct *child, long request,
user_disable_single_step(child);
}
+ /*
+ * Change ->exit_code and ->state under siglock to avoid the race
+ * with wait_task_stopped() in between; a non-zero ->exit_code will
+ * wrongly look like another report from tracee.
+ *
+ * Note that we need siglock even if ->exit_code == data and/or this
+ * status was not reported yet, the new status must not be cleared by
+ * wait_task_stopped() after resume.
+ *
+ * If data == 0 we do not care if wait_task_stopped() reports the old
+ * status and clears the code too; this can't race with the tracee, it
+ * takes siglock after resume.
+ */
+ need_siglock = data && !thread_group_empty(current);
+ if (need_siglock)
+ spin_lock_irq(&child->sighand->siglock);
child->exit_code = data;
wake_up_state(child, __TASK_TRACED);
+ if (need_siglock)
+ spin_unlock_irq(&child->sighand->siglock);
return 0;
}
diff --git a/kernel/signal.c b/kernel/signal.c
index a390499943e4..d51c5ddd855c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2992,11 +2992,9 @@ static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info)
* Nor can they impersonate a kill()/tgkill(), which adds source info.
*/
if ((info->si_code >= 0 || info->si_code == SI_TKILL) &&
- (task_pid_vnr(current) != pid)) {
- /* We used to allow any < 0 si_code */
- WARN_ON_ONCE(info->si_code < 0);
+ (task_pid_vnr(current) != pid))
return -EPERM;
- }
+
info->si_signo = sig;
/* POSIX.1b doesn't mention process groups. */
@@ -3041,12 +3039,10 @@ static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info)
/* Not even root can pretend to send signals from the kernel.
* Nor can they impersonate a kill()/tgkill(), which adds source info.
*/
- if (((info->si_code >= 0 || info->si_code == SI_TKILL)) &&
- (task_pid_vnr(current) != pid)) {
- /* We used to allow any < 0 si_code */
- WARN_ON_ONCE(info->si_code < 0);
+ if ((info->si_code >= 0 || info->si_code == SI_TKILL) &&
+ (task_pid_vnr(current) != pid))
return -EPERM;
- }
+
info->si_signo = sig;
return do_send_specific(tgid, pid, sig, info);
diff --git a/kernel/smp.c b/kernel/smp.c
index f38a1e692259..07854477c164 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -19,7 +19,7 @@
enum {
CSD_FLAG_LOCK = 0x01,
- CSD_FLAG_WAIT = 0x02,
+ CSD_FLAG_SYNCHRONOUS = 0x02,
};
struct call_function_data {
@@ -107,7 +107,7 @@ void __init call_function_init(void)
*/
static void csd_lock_wait(struct call_single_data *csd)
{
- while (csd->flags & CSD_FLAG_LOCK)
+ while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK)
cpu_relax();
}
@@ -121,19 +121,17 @@ static void csd_lock(struct call_single_data *csd)
* to ->flags with any subsequent assignments to other
* fields of the specified call_single_data structure:
*/
- smp_mb();
+ smp_wmb();
}
static void csd_unlock(struct call_single_data *csd)
{
- WARN_ON((csd->flags & CSD_FLAG_WAIT) && !(csd->flags & CSD_FLAG_LOCK));
+ WARN_ON(!(csd->flags & CSD_FLAG_LOCK));
/*
* ensure we're all done before releasing data:
*/
- smp_mb();
-
- csd->flags &= ~CSD_FLAG_LOCK;
+ smp_store_release(&csd->flags, 0);
}
static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
@@ -144,13 +142,16 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
* ->func, ->info, and ->flags set.
*/
static int generic_exec_single(int cpu, struct call_single_data *csd,
- smp_call_func_t func, void *info, int wait)
+ smp_call_func_t func, void *info)
{
- struct call_single_data csd_stack = { .flags = 0 };
- unsigned long flags;
-
-
if (cpu == smp_processor_id()) {
+ unsigned long flags;
+
+ /*
+ * We can unlock early even for the synchronous on-stack case,
+ * since we're doing this from the same CPU..
+ */
+ csd_unlock(csd);
local_irq_save(flags);
func(info);
local_irq_restore(flags);
@@ -158,24 +159,14 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
}
- if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
+ if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+ csd_unlock(csd);
return -ENXIO;
-
-
- if (!csd) {
- csd = &csd_stack;
- if (!wait)
- csd = this_cpu_ptr(&csd_data);
}
- csd_lock(csd);
-
csd->func = func;
csd->info = info;
- if (wait)
- csd->flags |= CSD_FLAG_WAIT;
-
/*
* The list addition should be visible before sending the IPI
* handler locks the list to pull the entry off it because of
@@ -190,9 +181,6 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
arch_send_call_function_single_ipi(cpu);
- if (wait)
- csd_lock_wait(csd);
-
return 0;
}
@@ -250,8 +238,17 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
}
llist_for_each_entry_safe(csd, csd_next, entry, llist) {
- csd->func(csd->info);
- csd_unlock(csd);
+ smp_call_func_t func = csd->func;
+ void *info = csd->info;
+
+ /* Do we wait until *after* callback? */
+ if (csd->flags & CSD_FLAG_SYNCHRONOUS) {
+ func(info);
+ csd_unlock(csd);
+ } else {
+ csd_unlock(csd);
+ func(info);
+ }
}
/*
@@ -274,6 +271,8 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
int wait)
{
+ struct call_single_data *csd;
+ struct call_single_data csd_stack = { .flags = CSD_FLAG_LOCK | CSD_FLAG_SYNCHRONOUS };
int this_cpu;
int err;
@@ -292,7 +291,16 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled()
&& !oops_in_progress);
- err = generic_exec_single(cpu, NULL, func, info, wait);
+ csd = &csd_stack;
+ if (!wait) {
+ csd = this_cpu_ptr(&csd_data);
+ csd_lock(csd);
+ }
+
+ err = generic_exec_single(cpu, csd, func, info);
+
+ if (wait)
+ csd_lock_wait(csd);
put_cpu();
@@ -321,7 +329,15 @@ int smp_call_function_single_async(int cpu, struct call_single_data *csd)
int err = 0;
preempt_disable();
- err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
+
+ /* We could deadlock if we have to wait here with interrupts disabled! */
+ if (WARN_ON_ONCE(csd->flags & CSD_FLAG_LOCK))
+ csd_lock_wait(csd);
+
+ csd->flags = CSD_FLAG_LOCK;
+ smp_wmb();
+
+ err = generic_exec_single(cpu, csd, csd->func, csd->info);
preempt_enable();
return err;
@@ -433,6 +449,8 @@ void smp_call_function_many(const struct cpumask *mask,
struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
csd_lock(csd);
+ if (wait)
+ csd->flags |= CSD_FLAG_SYNCHRONOUS;
csd->func = func;
csd->info = info;
llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
diff --git a/kernel/sys.c b/kernel/sys.c
index 3be344902316..a4e372b798a5 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1649,14 +1649,13 @@ SYSCALL_DEFINE1(umask, int, mask)
return mask;
}
-static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
+static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
{
struct fd exe;
+ struct file *old_exe, *exe_file;
struct inode *inode;
int err;
- VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
-
exe = fdget(fd);
if (!exe.file)
return -EBADF;
@@ -1680,15 +1679,22 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
/*
* Forbid mm->exe_file change if old file still mapped.
*/
+ exe_file = get_mm_exe_file(mm);
err = -EBUSY;
- if (mm->exe_file) {
+ if (exe_file) {
struct vm_area_struct *vma;
- for (vma = mm->mmap; vma; vma = vma->vm_next)
- if (vma->vm_file &&
- path_equal(&vma->vm_file->f_path,
- &mm->exe_file->f_path))
- goto exit;
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (!vma->vm_file)
+ continue;
+ if (path_equal(&vma->vm_file->f_path,
+ &exe_file->f_path))
+ goto exit_err;
+ }
+
+ up_read(&mm->mmap_sem);
+ fput(exe_file);
}
/*
@@ -1702,10 +1708,18 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
goto exit;
err = 0;
- set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */
+ /* set the new file, lockless */
+ get_file(exe.file);
+ old_exe = xchg(&mm->exe_file, exe.file);
+ if (old_exe)
+ fput(old_exe);
exit:
fdput(exe);
return err;
+exit_err:
+ up_read(&mm->mmap_sem);
+ fput(exe_file);
+ goto exit;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
@@ -1840,10 +1854,9 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
}
- down_write(&mm->mmap_sem);
if (prctl_map.exe_fd != (u32)-1)
- error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
- downgrade_write(&mm->mmap_sem);
+ error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
+ down_read(&mm->mmap_sem);
if (error)
goto out;
@@ -1909,12 +1922,8 @@ static int prctl_set_mm(int opt, unsigned long addr,
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
- if (opt == PR_SET_MM_EXE_FILE) {
- down_write(&mm->mmap_sem);
- error = prctl_set_mm_exe_file_locked(mm, (unsigned int)addr);
- up_write(&mm->mmap_sem);
- return error;
- }
+ if (opt == PR_SET_MM_EXE_FILE)
+ return prctl_set_mm_exe_file(mm, (unsigned int)addr);
if (addr >= TASK_SIZE || addr < mmap_min_addr)
return -EINVAL;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 42b7fc2860c1..2082b1a88fb9 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -93,11 +93,9 @@
#include <linux/nmi.h>
#endif
-
#if defined(CONFIG_SYSCTL)
/* External variables not in a header file. */
-extern int max_threads;
extern int suid_dumpable;
#ifdef CONFIG_COREDUMP
extern int core_uses_pid;
@@ -710,10 +708,10 @@ static struct ctl_table kern_table[] = {
#endif
{
.procname = "threads-max",
- .data = &max_threads,
+ .data = NULL,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = sysctl_max_threads,
},
{
.procname = "random",
@@ -1983,7 +1981,15 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp,
int write, void *data)
{
if (write) {
- *valp = *negp ? -*lvalp : *lvalp;
+ if (*negp) {
+ if (*lvalp > (unsigned long) INT_MAX + 1)
+ return -EINVAL;
+ *valp = -*lvalp;
+ } else {
+ if (*lvalp > (unsigned long) INT_MAX)
+ return -EINVAL;
+ *valp = *lvalp;
+ }
} else {
int val = *valp;
if (val < 0) {
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 25d942d1da27..11dc22a6983b 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -440,7 +440,7 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
mutex_unlock(&clockevents_mutex);
return ret;
}
-EXPORT_SYMBOL_GPL(clockevents_unbind);
+EXPORT_SYMBOL_GPL(clockevents_unbind_device);
/* Sanity check of state transition callbacks */
static int clockevents_sanity_check(struct clock_event_device *dev)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7da1dfeb322e..3ab69fb72b85 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -565,6 +565,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
+ int ret;
/*
* The buf format can be <subsystem>:<event-name>
@@ -590,7 +591,13 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
event = NULL;
}
- return __ftrace_set_clr_event(tr, match, sub, event, set);
+ ret = __ftrace_set_clr_event(tr, match, sub, event, set);
+
+ /* Put back the colon to allow this to be called again */
+ if (buf)
+ *(buf - 1) = ':';
+
+ return ret;
}
/**
@@ -1753,6 +1760,8 @@ static void update_event_printk(struct ftrace_event_call *call,
ptr++;
/* Check for alpha chars like ULL */
} while (isalnum(*ptr));
+ if (!*ptr)
+ break;
/*
* A number must have some kind of delimiter after
* it, and we can ignore that too.
@@ -1779,12 +1788,16 @@ static void update_event_printk(struct ftrace_event_call *call,
do {
ptr++;
} while (isalnum(*ptr) || *ptr == '_');
+ if (!*ptr)
+ break;
/*
* If what comes after this variable is a '.' or
* '->' then we can continue to ignore that string.
*/
if (*ptr == '.' || (ptr[0] == '-' && ptr[1] == '>')) {
ptr += *ptr == '.' ? 1 : 2;
+ if (!*ptr)
+ break;
goto skip_more;
}
/*
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9cfea4c6d314..a51e79688455 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1308,15 +1308,19 @@ void graph_trace_open(struct trace_iterator *iter)
{
/* pid and depth on the last trace processed */
struct fgraph_data *data;
+ gfp_t gfpflags;
int cpu;
iter->private = NULL;
- data = kzalloc(sizeof(*data), GFP_KERNEL);
+ /* We can be called in atomic context via ftrace_dump() */
+ gfpflags = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL;
+
+ data = kzalloc(sizeof(*data), gfpflags);
if (!data)
goto out_err;
- data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+ data->cpu_data = alloc_percpu_gfp(struct fgraph_cpu_data, gfpflags);
if (!data->cpu_data)
goto out_err_free;
generated by cgit v1.2.3 (git 2.0.4) at 2025-05-25 14:47:24 +0000