summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/acct.c6
-rw-r--r--kernel/audit.c2
-rw-r--r--kernel/exit.c39
-rw-r--r--kernel/fork.c10
-rw-r--r--kernel/kexec.c69
-rw-r--r--kernel/kmod.c5
-rw-r--r--kernel/panic.c23
-rw-r--r--kernel/profile.c20
-rw-r--r--kernel/seccomp.c4
-rw-r--r--kernel/signal.c91
-rw-r--r--kernel/smp.c18
-rw-r--r--kernel/sysctl.c94
-rw-r--r--kernel/user_namespace.c33
-rw-r--r--kernel/utsname_sysctl.c6
14 files changed, 234 insertions, 186 deletions
diff --git a/kernel/acct.c b/kernel/acct.c
index 8d6e145138bb..808a86ff229d 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -55,7 +55,7 @@
#include <linux/times.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <asm/div64.h>
#include <linux/blkdev.h> /* sector_div */
#include <linux/pid_namespace.h>
@@ -134,7 +134,7 @@ static int check_free_space(struct bsd_acct_struct *acct, struct file *file)
spin_lock(&acct_lock);
if (file != acct->file) {
if (act)
- res = act>0;
+ res = act > 0;
goto out;
}
@@ -262,7 +262,7 @@ SYSCALL_DEFINE1(acct, const char __user *, name)
if (name) {
struct filename *tmp = getname(name);
if (IS_ERR(tmp))
- return (PTR_ERR(tmp));
+ return PTR_ERR(tmp);
error = acct_on(tmp);
putname(tmp);
} else {
diff --git a/kernel/audit.c b/kernel/audit.c
index 47845c57eb19..f30106459a32 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -44,7 +44,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/init.h>
-#include <asm/types.h>
+#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/mm.h>
#include <linux/export.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 750c2e594617..e5c4668f1799 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -313,45 +313,6 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
}
}
-/*
- * Let kernel threads use this to say that they allow a certain signal.
- * Must not be used if kthread was cloned with CLONE_SIGHAND.
- */
-int allow_signal(int sig)
-{
- if (!valid_signal(sig) || sig < 1)
- return -EINVAL;
-
- spin_lock_irq(&current->sighand->siglock);
- /* This is only needed for daemonize()'ed kthreads */
- sigdelset(&current->blocked, sig);
- /*
- * Kernel threads handle their own signals. Let the signal code
- * know it'll be handled, so that they don't get converted to
- * SIGKILL or just silently dropped.
- */
- current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
- return 0;
-}
-
-EXPORT_SYMBOL(allow_signal);
-
-int disallow_signal(int sig)
-{
- if (!valid_signal(sig) || sig < 1)
- return -EINVAL;
-
- spin_lock_irq(&current->sighand->siglock);
- current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
- recalc_sigpending();
- spin_unlock_irq(&current->sighand->siglock);
- return 0;
-}
-
-EXPORT_SYMBOL(disallow_signal);
-
#ifdef CONFIG_MEMCG
/*
* A task is exiting. If it owned this mm, find a new owner for the mm.
diff --git a/kernel/fork.c b/kernel/fork.c
index 0d53eb0dfb6f..d2799d1fc952 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1606,10 +1606,12 @@ long do_fork(unsigned long clone_flags,
*/
if (!IS_ERR(p)) {
struct completion vfork;
+ struct pid *pid;
trace_sched_process_fork(current, p);
- nr = task_pid_vnr(p);
+ pid = get_task_pid(p, PIDTYPE_PID);
+ nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
@@ -1624,12 +1626,14 @@ long do_fork(unsigned long clone_flags,
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
- ptrace_event(trace, nr);
+ ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
- ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+ ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
+
+ put_pid(pid);
} else {
nr = PTR_ERR(p);
}
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 28c57069ef68..6748688813d0 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -125,8 +125,8 @@ static struct page *kimage_alloc_page(struct kimage *image,
unsigned long dest);
static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
- unsigned long nr_segments,
- struct kexec_segment __user *segments)
+ unsigned long nr_segments,
+ struct kexec_segment __user *segments)
{
size_t segment_bytes;
struct kimage *image;
@@ -257,13 +257,13 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
image->control_code_page = kimage_alloc_control_pages(image,
get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
- printk(KERN_ERR "Could not allocate control_code_buffer\n");
+ pr_err("Could not allocate control_code_buffer\n");
goto out_free;
}
image->swap_page = kimage_alloc_control_pages(image, 0);
if (!image->swap_page) {
- printk(KERN_ERR "Could not allocate swap buffer\n");
+ pr_err("Could not allocate swap buffer\n");
goto out_free;
}
@@ -332,7 +332,7 @@ static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
image->control_code_page = kimage_alloc_control_pages(image,
get_order(KEXEC_CONTROL_PAGE_SIZE));
if (!image->control_code_page) {
- printk(KERN_ERR "Could not allocate control_code_buffer\n");
+ pr_err("Could not allocate control_code_buffer\n");
goto out_free;
}
@@ -621,8 +621,8 @@ static void kimage_terminate(struct kimage *image)
#define for_each_kimage_entry(image, ptr, entry) \
for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
- ptr = (entry & IND_INDIRECTION)? \
- phys_to_virt((entry & PAGE_MASK)): ptr +1)
+ ptr = (entry & IND_INDIRECTION) ? \
+ phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
static void kimage_free_entry(kimage_entry_t entry)
{
@@ -650,8 +650,7 @@ static void kimage_free(struct kimage *image)
* done with it.
*/
ind = entry;
- }
- else if (entry & IND_SOURCE)
+ } else if (entry & IND_SOURCE)
kimage_free_entry(entry);
}
/* Free the final indirection page */
@@ -774,8 +773,7 @@ static struct page *kimage_alloc_page(struct kimage *image,
addr = old_addr;
page = old_page;
break;
- }
- else {
+ } else {
/* Place the page on the destination list I
* will use it later.
*/
@@ -1059,7 +1057,7 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
return -EINVAL;
ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
- for (i=0; i < nr_segments; i++) {
+ for (i = 0; i < nr_segments; i++) {
result = copy_from_user(&in, &segments[i], sizeof(in));
if (result)
return -EFAULT;
@@ -1214,14 +1212,14 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
* squirrelled away. ELF notes happen to provide
* all of that, so there is no need to invent something new.
*/
- buf = (u32*)per_cpu_ptr(crash_notes, cpu);
+ buf = (u32 *)per_cpu_ptr(crash_notes, cpu);
if (!buf)
return;
memset(&prstatus, 0, sizeof(prstatus));
prstatus.pr_pid = current->pid;
elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
- &prstatus, sizeof(prstatus));
+ &prstatus, sizeof(prstatus));
final_note(buf);
}
@@ -1230,8 +1228,7 @@ static int __init crash_notes_memory_init(void)
/* Allocate memory for saving cpu registers. */
crash_notes = alloc_percpu(note_buf_t);
if (!crash_notes) {
- printk("Kexec: Memory allocation for saving cpu register"
- " states failed\n");
+ pr_warn("Kexec: Memory allocation for saving cpu register states failed\n");
return -ENOMEM;
}
return 0;
@@ -1253,10 +1250,10 @@ subsys_initcall(crash_notes_memory_init);
*
* The function returns 0 on success and -EINVAL on failure.
*/
-static int __init parse_crashkernel_mem(char *cmdline,
- unsigned long long system_ram,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
+static int __init parse_crashkernel_mem(char *cmdline,
+ unsigned long long system_ram,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
{
char *cur = cmdline, *tmp;
@@ -1267,12 +1264,12 @@ static int __init parse_crashkernel_mem(char *cmdline,
/* get the start of the range */
start = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("crashkernel: Memory value expected\n");
+ pr_warn("crashkernel: Memory value expected\n");
return -EINVAL;
}
cur = tmp;
if (*cur != '-') {
- pr_warning("crashkernel: '-' expected\n");
+ pr_warn("crashkernel: '-' expected\n");
return -EINVAL;
}
cur++;
@@ -1281,31 +1278,30 @@ static int __init parse_crashkernel_mem(char *cmdline,
if (*cur != ':') {
end = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("crashkernel: Memory "
- "value expected\n");
+ pr_warn("crashkernel: Memory value expected\n");
return -EINVAL;
}
cur = tmp;
if (end <= start) {
- pr_warning("crashkernel: end <= start\n");
+ pr_warn("crashkernel: end <= start\n");
return -EINVAL;
}
}
if (*cur != ':') {
- pr_warning("crashkernel: ':' expected\n");
+ pr_warn("crashkernel: ':' expected\n");
return -EINVAL;
}
cur++;
size = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("Memory value expected\n");
+ pr_warn("Memory value expected\n");
return -EINVAL;
}
cur = tmp;
if (size >= system_ram) {
- pr_warning("crashkernel: invalid size\n");
+ pr_warn("crashkernel: invalid size\n");
return -EINVAL;
}
@@ -1323,8 +1319,7 @@ static int __init parse_crashkernel_mem(char *cmdline,
cur++;
*crash_base = memparse(cur, &tmp);
if (cur == tmp) {
- pr_warning("Memory value expected "
- "after '@'\n");
+ pr_warn("Memory value expected after '@'\n");
return -EINVAL;
}
}
@@ -1336,26 +1331,26 @@ static int __init parse_crashkernel_mem(char *cmdline,
/*
* That function parses "simple" (old) crashkernel command lines like
*
- * crashkernel=size[@offset]
+ * crashkernel=size[@offset]
*
* It returns 0 on success and -EINVAL on failure.
*/
-static int __init parse_crashkernel_simple(char *cmdline,
- unsigned long long *crash_size,
- unsigned long long *crash_base)
+static int __init parse_crashkernel_simple(char *cmdline,
+ unsigned long long *crash_size,
+ unsigned long long *crash_base)
{
char *cur = cmdline;
*crash_size = memparse(cmdline, &cur);
if (cmdline == cur) {
- pr_warning("crashkernel: memory value expected\n");
+ pr_warn("crashkernel: memory value expected\n");
return -EINVAL;
}
if (*cur == '@')
*crash_base = memparse(cur+1, &cur);
else if (*cur != ' ' && *cur != '\0') {
- pr_warning("crashkernel: unrecognized char\n");
+ pr_warn("crashkernel: unrecognized char\n");
return -EINVAL;
}
@@ -1691,7 +1686,7 @@ int kernel_kexec(void)
* CPU hotplug again; so re-enable it here.
*/
cpu_hotplug_enable();
- printk(KERN_EMERG "Starting new kernel\n");
+ pr_emerg("Starting new kernel\n");
machine_shutdown();
}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 0ac67a5861c5..8637e041a247 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -285,10 +285,7 @@ static int wait_for_helper(void *data)
pid_t pid;
/* If SIGCLD is ignored sys_wait4 won't populate the status. */
- spin_lock_irq(&current->sighand->siglock);
- current->sighand->action[SIGCHLD-1].sa.sa_handler = SIG_DFL;
- spin_unlock_irq(&current->sighand->siglock);
-
+ kernel_sigaction(SIGCHLD, SIG_DFL);
pid = kernel_thread(____call_usermodehelper, sub_info, SIGCHLD);
if (pid < 0) {
sub_info->retval = pid;
diff --git a/kernel/panic.c b/kernel/panic.c
index d02fa9fef46a..62e16cef9cc2 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -32,6 +32,7 @@ static unsigned long tainted_mask;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
+static bool crash_kexec_post_notifiers;
int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
@@ -112,9 +113,11 @@ void panic(const char *fmt, ...)
/*
* If we have crashed and we have a crash kernel loaded let it handle
* everything else.
- * Do we want to call this before we try to display a message?
+ * If we want to run this after calling panic_notifiers, pass
+ * the "crash_kexec_post_notifiers" option to the kernel.
*/
- crash_kexec(NULL);
+ if (!crash_kexec_post_notifiers)
+ crash_kexec(NULL);
/*
* Note smp_send_stop is the usual smp shutdown function, which
@@ -131,6 +134,15 @@ void panic(const char *fmt, ...)
kmsg_dump(KMSG_DUMP_PANIC);
+ /*
+ * If you doubt kdump always works fine in any situation,
+ * "crash_kexec_post_notifiers" offers you a chance to run
+ * panic_notifiers and dumping kmsg before kdump.
+ * Note: since some panic_notifiers can make crashed kernel
+ * more unstable, it can increase risks of the kdump failure too.
+ */
+ crash_kexec(NULL);
+
bust_spinlocks(0);
if (!panic_blink)
@@ -472,6 +484,13 @@ EXPORT_SYMBOL(__stack_chk_fail);
core_param(panic, panic_timeout, int, 0644);
core_param(pause_on_oops, pause_on_oops, int, 0644);
+static int __init setup_crash_kexec_post_notifiers(char *s)
+{
+ crash_kexec_post_notifiers = true;
+ return 0;
+}
+early_param("crash_kexec_post_notifiers", setup_crash_kexec_post_notifiers);
+
static int __init oops_setup(char *s)
{
if (!s)
diff --git a/kernel/profile.c b/kernel/profile.c
index cb980f0c731b..54bf5ba26420 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -52,9 +52,9 @@ static DEFINE_MUTEX(profile_flip_mutex);
int profile_setup(char *str)
{
- static char schedstr[] = "schedule";
- static char sleepstr[] = "sleep";
- static char kvmstr[] = "kvm";
+ static const char schedstr[] = "schedule";
+ static const char sleepstr[] = "sleep";
+ static const char kvmstr[] = "kvm";
int par;
if (!strncmp(str, sleepstr, strlen(sleepstr))) {
@@ -64,12 +64,10 @@ int profile_setup(char *str)
str += strlen(sleepstr) + 1;
if (get_option(&str, &par))
prof_shift = par;
- printk(KERN_INFO
- "kernel sleep profiling enabled (shift: %ld)\n",
+ pr_info("kernel sleep profiling enabled (shift: %ld)\n",
prof_shift);
#else
- printk(KERN_WARNING
- "kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
+ pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
#endif /* CONFIG_SCHEDSTATS */
} else if (!strncmp(str, schedstr, strlen(schedstr))) {
prof_on = SCHED_PROFILING;
@@ -77,8 +75,7 @@ int profile_setup(char *str)
str += strlen(schedstr) + 1;
if (get_option(&str, &par))
prof_shift = par;
- printk(KERN_INFO
- "kernel schedule profiling enabled (shift: %ld)\n",
+ pr_info("kernel schedule profiling enabled (shift: %ld)\n",
prof_shift);
} else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
prof_on = KVM_PROFILING;
@@ -86,13 +83,12 @@ int profile_setup(char *str)
str += strlen(kvmstr) + 1;
if (get_option(&str, &par))
prof_shift = par;
- printk(KERN_INFO
- "kernel KVM profiling enabled (shift: %ld)\n",
+ pr_info("kernel KVM profiling enabled (shift: %ld)\n",
prof_shift);
} else if (get_option(&str, &par)) {
prof_shift = par;
prof_on = CPU_PROFILING;
- printk(KERN_INFO "kernel profiling enabled (shift: %ld)\n",
+ pr_info("kernel profiling enabled (shift: %ld)\n",
prof_shift);
}
return 1;
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b35c21503a36..f6d76bebe69f 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -39,7 +39,7 @@
* is only needed for handling filters shared across tasks.
* @prev: points to a previously installed, or inherited, filter
* @len: the number of instructions in the program
- * @insns: the BPF program instructions to evaluate
+ * @insnsi: the BPF program instructions to evaluate
*
* seccomp_filter objects are organized in a tree linked via the @prev
* pointer. For any task, it appears to be a singly-linked list starting
@@ -220,7 +220,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
return -ENOMEM;
/*
- * Installing a seccomp filter requires that the task have
+ * Installing a seccomp filter requires that the task has
* CAP_SYS_ADMIN in its namespace or be running with no_new_privs.
* This avoids scenarios where unprivileged tasks can affect the
* behavior of privileged children.
diff --git a/kernel/signal.c b/kernel/signal.c
index 6e600aaa2af4..a4077e90f19f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -277,6 +277,7 @@ void task_clear_jobctl_trapping(struct task_struct *task)
{
if (unlikely(task->jobctl & JOBCTL_TRAPPING)) {
task->jobctl &= ~JOBCTL_TRAPPING;
+ smp_mb(); /* advised by wake_up_bit() */
wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT);
}
}
@@ -705,11 +706,8 @@ void signal_wake_up_state(struct task_struct *t, unsigned int state)
* Returns 1 if any signals were found.
*
* All callers must be holding the siglock.
- *
- * This version takes a sigset mask and looks at all signals,
- * not just those in the first mask word.
*/
-static int rm_from_queue_full(sigset_t *mask, struct sigpending *s)
+static int flush_sigqueue_mask(sigset_t *mask, struct sigpending *s)
{
struct sigqueue *q, *n;
sigset_t m;
@@ -727,29 +725,6 @@ static int rm_from_queue_full(sigset_t *mask, struct sigpending *s)
}
return 1;
}
-/*
- * Remove signals in mask from the pending set and queue.
- * Returns 1 if any signals were found.
- *
- * All callers must be holding the siglock.
- */
-static int rm_from_queue(unsigned long mask, struct sigpending *s)
-{
- struct sigqueue *q, *n;
-
- if (!sigtestsetmask(&s->signal, mask))
- return 0;
-
- sigdelsetmask(&s->signal, mask);
- list_for_each_entry_safe(q, n, &s->list, list) {
- if (q->info.si_signo < SIGRTMIN &&
- (mask & sigmask(q->info.si_signo))) {
- list_del_init(&q->list);
- __sigqueue_free(q);
- }
- }
- return 1;
-}
static inline int is_si_special(const struct siginfo *info)
{
@@ -861,6 +836,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
{
struct signal_struct *signal = p->signal;
struct task_struct *t;
+ sigset_t flush;
if (signal->flags & (SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP)) {
if (signal->flags & SIGNAL_GROUP_COREDUMP)
@@ -872,26 +848,25 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
/*
* This is a stop signal. Remove SIGCONT from all queues.
*/
- rm_from_queue(sigmask(SIGCONT), &signal->shared_pending);
- t = p;
- do {
- rm_from_queue(sigmask(SIGCONT), &t->pending);
- } while_each_thread(p, t);
+ siginitset(&flush, sigmask(SIGCONT));
+ flush_sigqueue_mask(&flush, &signal->shared_pending);
+ for_each_thread(p, t)
+ flush_sigqueue_mask(&flush, &t->pending);
} else if (sig == SIGCONT) {
unsigned int why;
/*
* Remove all stop signals from all queues, wake all threads.
*/
- rm_from_queue(SIG_KERNEL_STOP_MASK, &signal->shared_pending);
- t = p;
- do {
+ siginitset(&flush, SIG_KERNEL_STOP_MASK);
+ flush_sigqueue_mask(&flush, &signal->shared_pending);
+ for_each_thread(p, t) {
+ flush_sigqueue_mask(&flush, &t->pending);
task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING);
- rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending);
if (likely(!(t->ptrace & PT_SEIZED)))
wake_up_state(t, __TASK_STOPPED);
else
ptrace_trap_notify(t);
- } while_each_thread(p, t);
+ }
/*
* Notify the parent with CLD_CONTINUED if we were stopped.
@@ -2854,7 +2829,7 @@ int do_sigtimedwait(const sigset_t *which, siginfo_t *info,
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, &tsk->real_blocked);
- siginitset(&tsk->real_blocked, 0);
+ sigemptyset(&tsk->real_blocked);
sig = dequeue_signal(tsk, &mask, info);
}
spin_unlock_irq(&tsk->sighand->siglock);
@@ -3091,18 +3066,39 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo,
}
#endif
+/*
+ * For kthreads only, must not be used if cloned with CLONE_SIGHAND
+ */
+void kernel_sigaction(int sig, __sighandler_t action)
+{
+ spin_lock_irq(&current->sighand->siglock);
+ current->sighand->action[sig - 1].sa.sa_handler = action;
+ if (action == SIG_IGN) {
+ sigset_t mask;
+
+ sigemptyset(&mask);
+ sigaddset(&mask, sig);
+
+ flush_sigqueue_mask(&mask, &current->signal->shared_pending);
+ flush_sigqueue_mask(&mask, &current->pending);
+ recalc_sigpending();
+ }
+ spin_unlock_irq(&current->sighand->siglock);
+}
+EXPORT_SYMBOL(kernel_sigaction);
+
int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
{
- struct task_struct *t = current;
+ struct task_struct *p = current, *t;
struct k_sigaction *k;
sigset_t mask;
if (!valid_signal(sig) || sig < 1 || (act && sig_kernel_only(sig)))
return -EINVAL;
- k = &t->sighand->action[sig-1];
+ k = &p->sighand->action[sig-1];
- spin_lock_irq(&current->sighand->siglock);
+ spin_lock_irq(&p->sighand->siglock);
if (oact)
*oact = *k;
@@ -3121,21 +3117,20 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
* (for example, SIGCHLD), shall cause the pending signal to
* be discarded, whether or not it is blocked"
*/
- if (sig_handler_ignored(sig_handler(t, sig), sig)) {
+ if (sig_handler_ignored(sig_handler(p, sig), sig)) {
sigemptyset(&mask);
sigaddset(&mask, sig);
- rm_from_queue_full(&mask, &t->signal->shared_pending);
- do {
- rm_from_queue_full(&mask, &t->pending);
- } while_each_thread(current, t);
+ flush_sigqueue_mask(&mask, &p->signal->shared_pending);
+ for_each_thread(p, t)
+ flush_sigqueue_mask(&mask, &t->pending);
}
}
- spin_unlock_irq(&current->sighand->siglock);
+ spin_unlock_irq(&p->sighand->siglock);
return 0;
}
-static int
+static int
do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long sp)
{
stack_t oss;
diff --git a/kernel/smp.c b/kernel/smp.c
index 06d574e42c72..306f8180b0d5 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -185,14 +185,26 @@ void generic_smp_call_function_single_interrupt(void)
{
struct llist_node *entry;
struct call_single_data *csd, *csd_next;
+ static bool warned;
+
+ entry = llist_del_all(&__get_cpu_var(call_single_queue));
+ entry = llist_reverse_order(entry);
/*
* Shouldn't receive this interrupt on a cpu that is not yet online.
*/
- WARN_ON_ONCE(!cpu_online(smp_processor_id()));
+ if (unlikely(!cpu_online(smp_processor_id()) && !warned)) {
+ warned = true;
+ WARN(1, "IPI on offline CPU %d\n", smp_processor_id());
- entry = llist_del_all(&__get_cpu_var(call_single_queue));
- entry = llist_reverse_order(entry);
+ /*
+ * We don't have to use the _safe() variant here
+ * because we are not invoking the IPI handlers yet.
+ */
+ llist_for_each_entry(csd, entry, llist)
+ pr_warn("IPI callback %pS sent to offline CPU\n",
+ csd->func);
+ }
llist_for_each_entry_safe(csd, csd_next, entry, llist) {
csd->func(csd->info);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 40ce2d983b12..db19e3e2aa4b 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -173,6 +173,13 @@ extern int no_unaligned_warning;
#endif
#ifdef CONFIG_PROC_SYSCTL
+
+#define SYSCTL_WRITES_LEGACY -1
+#define SYSCTL_WRITES_WARN 0
+#define SYSCTL_WRITES_STRICT 1
+
+static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
static int proc_taint(struct ctl_table *table, int write,
@@ -195,7 +202,7 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
/* Note: sysrq code uses it's own private copy */
static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE;
-static int sysrq_sysctl_handler(ctl_table *table, int write,
+static int sysrq_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
@@ -495,6 +502,15 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_taint,
},
+ {
+ .procname = "sysctl_writes_strict",
+ .data = &sysctl_writes_strict,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &neg_one,
+ .extra2 = &one,
+ },
#endif
#ifdef CONFIG_LATENCYTOP
{
@@ -1703,8 +1719,8 @@ int __init sysctl_init(void)
#ifdef CONFIG_PROC_SYSCTL
-static int _proc_do_string(void* data, int maxlen, int write,
- void __user *buffer,
+static int _proc_do_string(char *data, int maxlen, int write,
+ char __user *buffer,
size_t *lenp, loff_t *ppos)
{
size_t len;
@@ -1717,21 +1733,30 @@ static int _proc_do_string(void* data, int maxlen, int write,
}
if (write) {
- len = 0;
+ if (sysctl_writes_strict == SYSCTL_WRITES_STRICT) {
+ /* Only continue writes not past the end of buffer. */
+ len = strlen(data);
+ if (len > maxlen - 1)
+ len = maxlen - 1;
+
+ if (*ppos > len)
+ return 0;
+ len = *ppos;
+ } else {
+ /* Start writing from beginning of buffer. */
+ len = 0;
+ }
+
+ *ppos += *lenp;
p = buffer;
- while (len < *lenp) {
+ while ((p - buffer) < *lenp && len < maxlen - 1) {
if (get_user(c, p++))
return -EFAULT;
if (c == 0 || c == '\n')
break;
- len++;
+ data[len++] = c;
}
- if (len >= maxlen)
- len = maxlen-1;
- if(copy_from_user(data, buffer, len))
- return -EFAULT;
- ((char *) data)[len] = 0;
- *ppos += *lenp;
+ data[len] = 0;
} else {
len = strlen(data);
if (len > maxlen)
@@ -1748,10 +1773,10 @@ static int _proc_do_string(void* data, int maxlen, int write,
if (len > *lenp)
len = *lenp;
if (len)
- if(copy_to_user(buffer, data, len))
+ if (copy_to_user(buffer, data, len))
return -EFAULT;
if (len < *lenp) {
- if(put_user('\n', ((char __user *) buffer) + len))
+ if (put_user('\n', buffer + len))
return -EFAULT;
len++;
}
@@ -1761,6 +1786,14 @@ static int _proc_do_string(void* data, int maxlen, int write,
return 0;
}
+static void warn_sysctl_write(struct ctl_table *table)
+{
+ pr_warn_once("%s wrote to %s when file position was not 0!\n"
+ "This will not be supported in the future. To silence this\n"
+ "warning, set kernel.sysctl_writes_strict = -1\n",
+ current->comm, table->procname);
+}
+
/**
* proc_dostring - read a string sysctl
* @table: the sysctl table
@@ -1781,8 +1814,11 @@ static int _proc_do_string(void* data, int maxlen, int write,
int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return _proc_do_string(table->data, table->maxlen, write,
- buffer, lenp, ppos);
+ if (write && *ppos && sysctl_writes_strict == SYSCTL_WRITES_WARN)
+ warn_sysctl_write(table);
+
+ return _proc_do_string((char *)(table->data), table->maxlen, write,
+ (char __user *)buffer, lenp, ppos);
}
static size_t proc_skip_spaces(char **buf)
@@ -1956,6 +1992,18 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
conv = do_proc_dointvec_conv;
if (write) {
+ if (*ppos) {
+ switch (sysctl_writes_strict) {
+ case SYSCTL_WRITES_STRICT:
+ goto out;
+ case SYSCTL_WRITES_WARN:
+ warn_sysctl_write(table);
+ break;
+ default:
+ break;
+ }
+ }
+
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
page = __get_free_page(GFP_TEMPORARY);
@@ -2013,6 +2061,7 @@ free:
return err ? : -EINVAL;
}
*lenp -= left;
+out:
*ppos += *lenp;
return err;
}
@@ -2205,6 +2254,18 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
left = *lenp;
if (write) {
+ if (*ppos) {
+ switch (sysctl_writes_strict) {
+ case SYSCTL_WRITES_STRICT:
+ goto out;
+ case SYSCTL_WRITES_WARN:
+ warn_sysctl_write(table);
+ break;
+ default:
+ break;
+ }
+ }
+
if (left > PAGE_SIZE - 1)
left = PAGE_SIZE - 1;
page = __get_free_page(GFP_TEMPORARY);
@@ -2260,6 +2321,7 @@ free:
return err ? : -EINVAL;
}
*lenp -= left;
+out:
*ppos += *lenp;
return err;
}
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index bf71b4b2d632..fcc02560fd6b 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -286,7 +286,7 @@ EXPORT_SYMBOL(from_kuid_munged);
/**
* make_kgid - Map a user-namespace gid pair into a kgid.
* @ns: User namespace that the gid is in
- * @uid: group identifier
+ * @gid: group identifier
*
* Maps a user-namespace gid pair into a kernel internal kgid,
* and returns that kgid.
@@ -482,7 +482,8 @@ static int projid_m_show(struct seq_file *seq, void *v)
return 0;
}
-static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map)
+static void *m_start(struct seq_file *seq, loff_t *ppos,
+ struct uid_gid_map *map)
{
struct uid_gid_extent *extent = NULL;
loff_t pos = *ppos;
@@ -546,7 +547,8 @@ struct seq_operations proc_projid_seq_operations = {
.show = projid_m_show,
};
-static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent)
+static bool mappings_overlap(struct uid_gid_map *new_map,
+ struct uid_gid_extent *extent)
{
u32 upper_first, lower_first, upper_last, lower_last;
unsigned idx;
@@ -653,7 +655,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
ret = -EINVAL;
pos = kbuf;
new_map.nr_extents = 0;
- for (;pos; pos = next_line) {
+ for (; pos; pos = next_line) {
extent = &new_map.extent[new_map.nr_extents];
/* Find the end of line and ensure I don't look past it */
@@ -687,13 +689,16 @@ static ssize_t map_write(struct file *file, const char __user *buf,
/* Verify we have been given valid starting values */
if ((extent->first == (u32) -1) ||
- (extent->lower_first == (u32) -1 ))
+ (extent->lower_first == (u32) -1))
goto out;
- /* Verify count is not zero and does not cause the extent to wrap */
+ /* Verify count is not zero and does not cause the
+ * extent to wrap
+ */
if ((extent->first + extent->count) <= extent->first)
goto out;
- if ((extent->lower_first + extent->count) <= extent->lower_first)
+ if ((extent->lower_first + extent->count) <=
+ extent->lower_first)
goto out;
/* Do the ranges in extent overlap any previous extents? */
@@ -751,7 +756,8 @@ out:
return ret;
}
-ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
+ssize_t proc_uid_map_write(struct file *file, const char __user *buf,
+ size_t size, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
@@ -767,7 +773,8 @@ ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t siz
&ns->uid_map, &ns->parent->uid_map);
}
-ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
+ssize_t proc_gid_map_write(struct file *file, const char __user *buf,
+ size_t size, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
@@ -783,7 +790,8 @@ ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t siz
&ns->gid_map, &ns->parent->gid_map);
}
-ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos)
+ssize_t proc_projid_map_write(struct file *file, const char __user *buf,
+ size_t size, loff_t *ppos)
{
struct seq_file *seq = file->private_data;
struct user_namespace *ns = seq->private;
@@ -800,7 +808,7 @@ ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t
&ns->projid_map, &ns->parent->projid_map);
}
-static bool new_idmap_permitted(const struct file *file,
+static bool new_idmap_permitted(const struct file *file,
struct user_namespace *ns, int cap_setid,
struct uid_gid_map *new_map)
{
@@ -811,8 +819,7 @@ static bool new_idmap_permitted(const struct file *file,
kuid_t uid = make_kuid(ns->parent, id);
if (uid_eq(uid, file->f_cred->fsuid))
return true;
- }
- else if (cap_setid == CAP_SETGID) {
+ } else if (cap_setid == CAP_SETGID) {
kgid_t gid = make_kgid(ns->parent, id);
if (gid_eq(gid, file->f_cred->fsgid))
return true;
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 6fbe811c7ad1..c8eac43267e9 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -17,7 +17,7 @@
#ifdef CONFIG_PROC_SYSCTL
-static void *get_uts(ctl_table *table, int write)
+static void *get_uts(struct ctl_table *table, int write)
{
char *which = table->data;
struct uts_namespace *uts_ns;
@@ -32,7 +32,7 @@ static void *get_uts(ctl_table *table, int write)
return which;
}
-static void put_uts(ctl_table *table, int write, void *which)
+static void put_uts(struct ctl_table *table, int write, void *which)
{
if (!write)
up_read(&uts_sem);
@@ -44,7 +44,7 @@ static void put_uts(ctl_table *table, int write, void *which)
* Special case of dostring for the UTS structure. This has locks
* to observe. Should this be in kernel/sys.c ????
*/
-static int proc_do_uts_string(ctl_table *table, int write,
+static int proc_do_uts_string(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table uts_table;
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-10 08:00:08 +0000