summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile3
-rw-r--r--kernel/audit_tree.c100
-rw-r--r--kernel/auditsc.c7
-rw-r--r--kernel/cpu.c2
-rw-r--r--kernel/elfcore.c28
-rw-r--r--kernel/exit.c5
-rw-r--r--kernel/fork.c19
-rw-r--r--kernel/kprobes.c647
-rw-r--r--kernel/padata.c8
-rw-r--r--kernel/panic.c46
-rw-r--r--kernel/params.c1
-rw-r--r--kernel/perf_event.c2
-rw-r--r--kernel/pid.c2
-rw-r--r--kernel/posix-cpu-timers.c36
-rw-r--r--kernel/power/hibernate.c9
-rw-r--r--kernel/power/suspend.c3
-rw-r--r--kernel/printk.c3
-rw-r--r--kernel/relay.c5
-rw-r--r--kernel/sched.c4
-rw-r--r--kernel/sched_cpupri.c2
-rw-r--r--kernel/sched_rt.c5
-rw-r--r--kernel/signal.c45
-rw-r--r--kernel/sys.c3
-rw-r--r--kernel/sysctl.c12
-rw-r--r--kernel/sysctl_binary.c7
-rw-r--r--kernel/tsacct.c1
26 files changed, 762 insertions, 243 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 7b974699f8c2..a987aa1676b5 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -91,6 +91,9 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_X86_DS) += trace/
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 4b05bd9479db..028e85663f27 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -548,6 +548,11 @@ int audit_remove_tree_rule(struct audit_krule *rule)
return 0;
}
+static int compare_root(struct vfsmount *mnt, void *arg)
+{
+ return mnt->mnt_root->d_inode == arg;
+}
+
void audit_trim_trees(void)
{
struct list_head cursor;
@@ -559,7 +564,6 @@ void audit_trim_trees(void)
struct path path;
struct vfsmount *root_mnt;
struct node *node;
- struct list_head list;
int err;
tree = container_of(cursor.next, struct audit_tree, list);
@@ -577,24 +581,16 @@ void audit_trim_trees(void)
if (!root_mnt)
goto skip_it;
- list_add_tail(&list, &root_mnt->mnt_list);
spin_lock(&hash_lock);
list_for_each_entry(node, &tree->chunks, list) {
- struct audit_chunk *chunk = find_chunk(node);
- struct inode *inode = chunk->watch.inode;
- struct vfsmount *mnt;
+ struct inode *inode = find_chunk(node)->watch.inode;
node->index |= 1U<<31;
- list_for_each_entry(mnt, &list, mnt_list) {
- if (mnt->mnt_root->d_inode == inode) {
- node->index &= ~(1U<<31);
- break;
- }
- }
+ if (iterate_mounts(compare_root, inode, root_mnt))
+ node->index &= ~(1U<<31);
}
spin_unlock(&hash_lock);
trim_marked(tree);
put_tree(tree);
- list_del_init(&list);
drop_collected_mounts(root_mnt);
skip_it:
mutex_lock(&audit_filter_mutex);
@@ -603,22 +599,6 @@ skip_it:
mutex_unlock(&audit_filter_mutex);
}
-static int is_under(struct vfsmount *mnt, struct dentry *dentry,
- struct path *path)
-{
- if (mnt != path->mnt) {
- for (;;) {
- if (mnt->mnt_parent == mnt)
- return 0;
- if (mnt->mnt_parent == path->mnt)
- break;
- mnt = mnt->mnt_parent;
- }
- dentry = mnt->mnt_mountpoint;
- }
- return is_subdir(dentry, path->dentry);
-}
-
int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
{
@@ -638,13 +618,17 @@ void audit_put_tree(struct audit_tree *tree)
put_tree(tree);
}
+static int tag_mount(struct vfsmount *mnt, void *arg)
+{
+ return tag_chunk(mnt->mnt_root->d_inode, arg);
+}
+
/* called with audit_filter_mutex */
int audit_add_tree_rule(struct audit_krule *rule)
{
struct audit_tree *seed = rule->tree, *tree;
struct path path;
- struct vfsmount *mnt, *p;
- struct list_head list;
+ struct vfsmount *mnt;
int err;
list_for_each_entry(tree, &tree_list, list) {
@@ -670,16 +654,9 @@ int audit_add_tree_rule(struct audit_krule *rule)
err = -ENOMEM;
goto Err;
}
- list_add_tail(&list, &mnt->mnt_list);
get_tree(tree);
- list_for_each_entry(p, &list, mnt_list) {
- err = tag_chunk(p->mnt_root->d_inode, tree);
- if (err)
- break;
- }
-
- list_del(&list);
+ err = iterate_mounts(tag_mount, tree, mnt);
drop_collected_mounts(mnt);
if (!err) {
@@ -714,31 +691,23 @@ int audit_tag_tree(char *old, char *new)
{
struct list_head cursor, barrier;
int failed = 0;
- struct path path;
+ struct path path1, path2;
struct vfsmount *tagged;
- struct list_head list;
- struct vfsmount *mnt;
- struct dentry *dentry;
int err;
- err = kern_path(new, 0, &path);
+ err = kern_path(new, 0, &path2);
if (err)
return err;
- tagged = collect_mounts(&path);
- path_put(&path);
+ tagged = collect_mounts(&path2);
+ path_put(&path2);
if (!tagged)
return -ENOMEM;
- err = kern_path(old, 0, &path);
+ err = kern_path(old, 0, &path1);
if (err) {
drop_collected_mounts(tagged);
return err;
}
- mnt = mntget(path.mnt);
- dentry = dget(path.dentry);
- path_put(&path);
-
- list_add_tail(&list, &tagged->mnt_list);
mutex_lock(&audit_filter_mutex);
list_add(&barrier, &tree_list);
@@ -746,7 +715,7 @@ int audit_tag_tree(char *old, char *new)
while (cursor.next != &tree_list) {
struct audit_tree *tree;
- struct vfsmount *p;
+ int good_one = 0;
tree = container_of(cursor.next, struct audit_tree, list);
get_tree(tree);
@@ -754,30 +723,19 @@ int audit_tag_tree(char *old, char *new)
list_add(&cursor, &tree->list);
mutex_unlock(&audit_filter_mutex);
- err = kern_path(tree->pathname, 0, &path);
- if (err) {
- put_tree(tree);
- mutex_lock(&audit_filter_mutex);
- continue;
+ err = kern_path(tree->pathname, 0, &path2);
+ if (!err) {
+ good_one = path_is_under(&path1, &path2);
+ path_put(&path2);
}
- spin_lock(&vfsmount_lock);
- if (!is_under(mnt, dentry, &path)) {
- spin_unlock(&vfsmount_lock);
- path_put(&path);
+ if (!good_one) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
continue;
}
- spin_unlock(&vfsmount_lock);
- path_put(&path);
-
- list_for_each_entry(p, &list, mnt_list) {
- failed = tag_chunk(p->mnt_root->d_inode, tree);
- if (failed)
- break;
- }
+ failed = iterate_mounts(tag_mount, tree, tagged);
if (failed) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
@@ -818,10 +776,8 @@ int audit_tag_tree(char *old, char *new)
}
list_del(&barrier);
list_del(&cursor);
- list_del(&list);
mutex_unlock(&audit_filter_mutex);
- dput(dentry);
- mntput(mnt);
+ path_put(&path1);
drop_collected_mounts(tagged);
return failed;
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fc0f928167e7..f3a461c0970a 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1988,7 +1988,6 @@ void __audit_inode(const char *name, const struct dentry *dentry)
/**
* audit_inode_child - collect inode info for created/removed objects
- * @dname: inode's dentry name
* @dentry: dentry being audited
* @parent: inode of dentry parent
*
@@ -2000,13 +1999,14 @@ void __audit_inode(const char *name, const struct dentry *dentry)
* must be hooked prior, in order to capture the target inode during
* unsuccessful attempts.
*/
-void __audit_inode_child(const char *dname, const struct dentry *dentry,
+void __audit_inode_child(const struct dentry *dentry,
const struct inode *parent)
{
int idx;
struct audit_context *context = current->audit_context;
const char *found_parent = NULL, *found_child = NULL;
const struct inode *inode = dentry->d_inode;
+ const char *dname = dentry->d_name.name;
int dirlen = 0;
if (!context->in_syscall)
@@ -2014,9 +2014,6 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry,
if (inode)
handle_one(inode);
- /* determine matching parent */
- if (!dname)
- goto add_names;
/* parent is more likely, look for it first */
for (idx = 0; idx < context->name_count; idx++) {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 677f25376a38..f8cced2692b3 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -338,7 +338,7 @@ int __cpuinit cpu_up(unsigned int cpu)
if (!cpu_possible(cpu)) {
printk(KERN_ERR "can't online cpu %d because it is not "
"configured as may-hotadd at boot time\n", cpu);
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
+#if defined(CONFIG_IA64)
printk(KERN_ERR "please check additional_cpus= boot "
"parameter\n");
#endif
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
new file mode 100644
index 000000000000..ff915efef66d
--- /dev/null
+++ b/kernel/elfcore.c
@@ -0,0 +1,28 @@
+#include <linux/elf.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+#include <asm/elf.h>
+
+
+Elf_Half __weak elf_core_extra_phdrs(void)
+{
+ return 0;
+}
+
+int __weak elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
+ unsigned long limit)
+{
+ return 1;
+}
+
+int __weak elf_core_write_extra_data(struct file *file, size_t *size,
+ unsigned long limit)
+{
+ return 1;
+}
+
+size_t __weak elf_core_extra_data_size(void)
+{
+ return 0;
+}
diff --git a/kernel/exit.c b/kernel/exit.c
index 45ed043b8bf5..ce1e48c2d93d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -952,7 +952,8 @@ NORET_TYPE void do_exit(long code)
preempt_count());
acct_update_integrals(tsk);
-
+ /* sync mm's RSS info before statistics gathering */
+ sync_mm_rss(tsk, tsk->mm);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
@@ -1188,7 +1189,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
if (unlikely(wo->wo_flags & WNOWAIT)) {
int exit_code = p->exit_code;
- int why, status;
+ int why;
get_task_struct(p);
read_unlock(&tasklist_lock);
diff --git a/kernel/fork.c b/kernel/fork.c
index 17bbf093356d..b0ec34abc0bb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -329,15 +329,17 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
if (!tmp)
goto fail_nomem;
*tmp = *mpnt;
+ INIT_LIST_HEAD(&tmp->anon_vma_chain);
pol = mpol_dup(vma_policy(mpnt));
retval = PTR_ERR(pol);
if (IS_ERR(pol))
goto fail_nomem_policy;
vma_set_policy(tmp, pol);
+ if (anon_vma_fork(tmp, mpnt))
+ goto fail_nomem_anon_vma_fork;
tmp->vm_flags &= ~VM_LOCKED;
tmp->vm_mm = mm;
tmp->vm_next = NULL;
- anon_vma_link(tmp);
file = tmp->vm_file;
if (file) {
struct inode *inode = file->f_path.dentry->d_inode;
@@ -392,6 +394,8 @@ out:
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
return retval;
+fail_nomem_anon_vma_fork:
+ mpol_put(pol);
fail_nomem_policy:
kmem_cache_free(vm_area_cachep, tmp);
fail_nomem:
@@ -455,8 +459,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
mm->core_state = NULL;
mm->nr_ptes = 0;
- set_mm_counter(mm, file_rss, 0);
- set_mm_counter(mm, anon_rss, 0);
+ memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
mm->free_area_cache = TASK_UNMAPPED_BASE;
mm->cached_hole_size = ~0UL;
@@ -825,6 +828,8 @@ void __cleanup_sighand(struct sighand_struct *sighand)
*/
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
+ unsigned long cpu_limit;
+
/* Thread group counters. */
thread_group_cputime_init(sig);
@@ -839,9 +844,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
sig->cputime_expires.virt_exp = cputime_zero;
sig->cputime_expires.sched_exp = 0;
- if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
- sig->cputime_expires.prof_exp =
- secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+ cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ if (cpu_limit != RLIM_INFINITY) {
+ sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
sig->cputimer.running = 1;
}
@@ -1034,7 +1039,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
- p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
+ task_rlimit(p, RLIMIT_NPROC)) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
p->real_cred->user != INIT_USER)
goto bad_fork_free;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ccec774c716d..fa034d29cf73 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -42,9 +42,11 @@
#include <linux/freezer.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
+#include <linux/sysctl.h>
#include <linux/kdebug.h>
#include <linux/memory.h>
#include <linux/ftrace.h>
+#include <linux/cpu.h>
#include <asm-generic/sections.h>
#include <asm/cacheflush.h>
@@ -105,57 +107,74 @@ static struct kprobe_blackpoint kprobe_blacklist[] = {
* stepping on the instruction on a vmalloced/kmalloced/data page
* is a recipe for disaster
*/
-#define INSNS_PER_PAGE (PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
-
struct kprobe_insn_page {
struct list_head list;
kprobe_opcode_t *insns; /* Page of instruction slots */
- char slot_used[INSNS_PER_PAGE];
int nused;
int ngarbage;
+ char slot_used[];
+};
+
+#define KPROBE_INSN_PAGE_SIZE(slots) \
+ (offsetof(struct kprobe_insn_page, slot_used) + \
+ (sizeof(char) * (slots)))
+
+struct kprobe_insn_cache {
+ struct list_head pages; /* list of kprobe_insn_page */
+ size_t insn_size; /* size of instruction slot */
+ int nr_garbage;
};
+static int slots_per_page(struct kprobe_insn_cache *c)
+{
+ return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t));
+}
+
enum kprobe_slot_state {
SLOT_CLEAN = 0,
SLOT_DIRTY = 1,
SLOT_USED = 2,
};
-static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_pages */
-static LIST_HEAD(kprobe_insn_pages);
-static int kprobe_garbage_slots;
-static int collect_garbage_slots(void);
+static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_slots */
+static struct kprobe_insn_cache kprobe_insn_slots = {
+ .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
+ .insn_size = MAX_INSN_SIZE,
+ .nr_garbage = 0,
+};
+static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c);
/**
* __get_insn_slot() - Find a slot on an executable page for an instruction.
* We allocate an executable page if there's no room on existing ones.
*/
-static kprobe_opcode_t __kprobes *__get_insn_slot(void)
+static kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip;
retry:
- list_for_each_entry(kip, &kprobe_insn_pages, list) {
- if (kip->nused < INSNS_PER_PAGE) {
+ list_for_each_entry(kip, &c->pages, list) {
+ if (kip->nused < slots_per_page(c)) {
int i;
- for (i = 0; i < INSNS_PER_PAGE; i++) {
+ for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_CLEAN) {
kip->slot_used[i] = SLOT_USED;
kip->nused++;
- return kip->insns + (i * MAX_INSN_SIZE);
+ return kip->insns + (i * c->insn_size);
}
}
- /* Surprise! No unused slots. Fix kip->nused. */
- kip->nused = INSNS_PER_PAGE;
+ /* kip->nused is broken. Fix it. */
+ kip->nused = slots_per_page(c);
+ WARN_ON(1);
}
}
/* If there are any garbage slots, collect it and try again. */
- if (kprobe_garbage_slots && collect_garbage_slots() == 0) {
+ if (c->nr_garbage && collect_garbage_slots(c) == 0)
goto retry;
- }
- /* All out of space. Need to allocate a new page. Use slot 0. */
- kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
+
+ /* All out of space. Need to allocate a new page. */
+ kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL);
if (!kip)
return NULL;
@@ -170,20 +189,23 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void)
return NULL;
}
INIT_LIST_HEAD(&kip->list);
- list_add(&kip->list, &kprobe_insn_pages);
- memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
+ memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c));
kip->slot_used[0] = SLOT_USED;
kip->nused = 1;
kip->ngarbage = 0;
+ list_add(&kip->list, &c->pages);
return kip->insns;
}
+
kprobe_opcode_t __kprobes *get_insn_slot(void)
{
- kprobe_opcode_t *ret;
+ kprobe_opcode_t *ret = NULL;
+
mutex_lock(&kprobe_insn_mutex);
- ret = __get_insn_slot();
+ ret = __get_insn_slot(&kprobe_insn_slots);
mutex_unlock(&kprobe_insn_mutex);
+
return ret;
}
@@ -199,7 +221,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
* so as not to have to set it up again the
* next time somebody inserts a probe.
*/
- if (!list_is_singular(&kprobe_insn_pages)) {
+ if (!list_is_singular(&kip->list)) {
list_del(&kip->list);
module_free(NULL, kip->insns);
kfree(kip);
@@ -209,51 +231,84 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
return 0;
}
-static int __kprobes collect_garbage_slots(void)
+static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c)
{
struct kprobe_insn_page *kip, *next;
/* Ensure no-one is interrupted on the garbages */
synchronize_sched();
- list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
+ list_for_each_entry_safe(kip, next, &c->pages, list) {
int i;
if (kip->ngarbage == 0)
continue;
kip->ngarbage = 0; /* we will collect all garbages */
- for (i = 0; i < INSNS_PER_PAGE; i++) {
+ for (i = 0; i < slots_per_page(c); i++) {
if (kip->slot_used[i] == SLOT_DIRTY &&
collect_one_slot(kip, i))
break;
}
}
- kprobe_garbage_slots = 0;
+ c->nr_garbage = 0;
return 0;
}
-void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
+ kprobe_opcode_t *slot, int dirty)
{
struct kprobe_insn_page *kip;
- mutex_lock(&kprobe_insn_mutex);
- list_for_each_entry(kip, &kprobe_insn_pages, list) {
- if (kip->insns <= slot &&
- slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
- int i = (slot - kip->insns) / MAX_INSN_SIZE;
+ list_for_each_entry(kip, &c->pages, list) {
+ long idx = ((long)slot - (long)kip->insns) / c->insn_size;
+ if (idx >= 0 && idx < slots_per_page(c)) {
+ WARN_ON(kip->slot_used[idx] != SLOT_USED);
if (dirty) {
- kip->slot_used[i] = SLOT_DIRTY;
+ kip->slot_used[idx] = SLOT_DIRTY;
kip->ngarbage++;
+ if (++c->nr_garbage > slots_per_page(c))
+ collect_garbage_slots(c);
} else
- collect_one_slot(kip, i);
- break;
+ collect_one_slot(kip, idx);
+ return;
}
}
+ /* Could not free this slot. */
+ WARN_ON(1);
+}
- if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
- collect_garbage_slots();
-
+void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+{
+ mutex_lock(&kprobe_insn_mutex);
+ __free_insn_slot(&kprobe_insn_slots, slot, dirty);
mutex_unlock(&kprobe_insn_mutex);
}
+#ifdef CONFIG_OPTPROBES
+/* For optimized_kprobe buffer */
+static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */
+static struct kprobe_insn_cache kprobe_optinsn_slots = {
+ .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
+ /* .insn_size is initialized later */
+ .nr_garbage = 0,
+};
+/* Get a slot for optimized_kprobe buffer */
+kprobe_opcode_t __kprobes *get_optinsn_slot(void)
+{
+ kprobe_opcode_t *ret = NULL;
+
+ mutex_lock(&kprobe_optinsn_mutex);
+ ret = __get_insn_slot(&kprobe_optinsn_slots);
+ mutex_unlock(&kprobe_optinsn_mutex);
+
+ return ret;
+}
+
+void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty)
+{
+ mutex_lock(&kprobe_optinsn_mutex);
+ __free_insn_slot(&kprobe_optinsn_slots, slot, dirty);
+ mutex_unlock(&kprobe_optinsn_mutex);
+}
+#endif
#endif
/* We have preemption disabled.. so it is safe to use __ versions */
@@ -284,23 +339,401 @@ struct kprobe __kprobes *get_kprobe(void *addr)
if (p->addr == addr)
return p;
}
+
+ return NULL;
+}
+
+static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs);
+
+/* Return true if the kprobe is an aggregator */
+static inline int kprobe_aggrprobe(struct kprobe *p)
+{
+ return p->pre_handler == aggr_pre_handler;
+}
+
+/*
+ * Keep all fields in the kprobe consistent
+ */
+static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+{
+ memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
+ memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+}
+
+#ifdef CONFIG_OPTPROBES
+/* NOTE: change this value only with kprobe_mutex held */
+static bool kprobes_allow_optimization;
+
+/*
+ * Call all pre_handler on the list, but ignores its return value.
+ * This must be called from arch-dep optimized caller.
+ */
+void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kprobe *kp;
+
+ list_for_each_entry_rcu(kp, &p->list, list) {
+ if (kp->pre_handler && likely(!kprobe_disabled(kp))) {
+ set_kprobe_instance(kp);
+ kp->pre_handler(kp, regs);
+ }
+ reset_kprobe_instance();
+ }
+}
+
+/* Return true(!0) if the kprobe is ready for optimization. */
+static inline int kprobe_optready(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ if (kprobe_aggrprobe(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ return arch_prepared_optinsn(&op->optinsn);
+ }
+
+ return 0;
+}
+
+/*
+ * Return an optimized kprobe whose optimizing code replaces
+ * instructions including addr (exclude breakpoint).
+ */
+struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
+{
+ int i;
+ struct kprobe *p = NULL;
+ struct optimized_kprobe *op;
+
+ /* Don't check i == 0, since that is a breakpoint case. */
+ for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++)
+ p = get_kprobe((void *)(addr - i));
+
+ if (p && kprobe_optready(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (arch_within_optimized_kprobe(op, addr))
+ return p;
+ }
+
return NULL;
}
+/* Optimization staging list, protected by kprobe_mutex */
+static LIST_HEAD(optimizing_list);
+
+static void kprobe_optimizer(struct work_struct *work);
+static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
+#define OPTIMIZE_DELAY 5
+
+/* Kprobe jump optimizer */
+static __kprobes void kprobe_optimizer(struct work_struct *work)
+{
+ struct optimized_kprobe *op, *tmp;
+
+ /* Lock modules while optimizing kprobes */
+ mutex_lock(&module_mutex);
+ mutex_lock(&kprobe_mutex);
+ if (kprobes_all_disarmed || !kprobes_allow_optimization)
+ goto end;
+
+ /*
+ * Wait for quiesence period to ensure all running interrupts
+ * are done. Because optprobe may modify multiple instructions
+ * there is a chance that Nth instruction is interrupted. In that
+ * case, running interrupt can return to 2nd-Nth byte of jump
+ * instruction. This wait is for avoiding it.
+ */
+ synchronize_sched();
+
+ /*
+ * The optimization/unoptimization refers online_cpus via
+ * stop_machine() and cpu-hotplug modifies online_cpus.
+ * And same time, text_mutex will be held in cpu-hotplug and here.
+ * This combination can cause a deadlock (cpu-hotplug try to lock
+ * text_mutex but stop_machine can not be done because online_cpus
+ * has been changed)
+ * To avoid this deadlock, we need to call get_online_cpus()
+ * for preventing cpu-hotplug outside of text_mutex locking.
+ */
+ get_online_cpus();
+ mutex_lock(&text_mutex);
+ list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
+ WARN_ON(kprobe_disabled(&op->kp));
+ if (arch_optimize_kprobe(op) < 0)
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ list_del_init(&op->list);
+ }
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+end:
+ mutex_unlock(&kprobe_mutex);
+ mutex_unlock(&module_mutex);
+}
+
+/* Optimize kprobe if p is ready to be optimized */
+static __kprobes void optimize_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ /* Check if the kprobe is disabled or not ready for optimization. */
+ if (!kprobe_optready(p) || !kprobes_allow_optimization ||
+ (kprobe_disabled(p) || kprobes_all_disarmed))
+ return;
+
+ /* Both of break_handler and post_handler are not supported. */
+ if (p->break_handler || p->post_handler)
+ return;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+
+ /* Check there is no other kprobes at the optimized instructions */
+ if (arch_check_optimized_kprobe(op) < 0)
+ return;
+
+ /* Check if it is already optimized. */
+ if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
+ return;
+
+ op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
+ list_add(&op->list, &optimizing_list);
+ if (!delayed_work_pending(&optimizing_work))
+ schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+}
+
+/* Unoptimize a kprobe if p is optimized */
+static __kprobes void unoptimize_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!list_empty(&op->list))
+ /* Dequeue from the optimization queue */
+ list_del_init(&op->list);
+ else
+ /* Replace jump with break */
+ arch_unoptimize_kprobe(op);
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ }
+}
+
+/* Remove optimized instructions */
+static void __kprobes kill_optimized_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ if (!list_empty(&op->list)) {
+ /* Dequeue from the optimization queue */
+ list_del_init(&op->list);
+ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+ }
+ /* Don't unoptimize, because the target code will be freed. */
+ arch_remove_optimized_kprobe(op);
+}
+
+/* Try to prepare optimized instructions */
+static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ arch_prepare_optimized_kprobe(op);
+}
+
+/* Free optimized instructions and optimized_kprobe */
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = container_of(p, struct optimized_kprobe, kp);
+ arch_remove_optimized_kprobe(op);
+ kfree(op);
+}
+
+/* Allocate new optimized_kprobe and try to prepare optimized instructions */
+static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+{
+ struct optimized_kprobe *op;
+
+ op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL);
+ if (!op)
+ return NULL;
+
+ INIT_LIST_HEAD(&op->list);
+ op->kp.addr = p->addr;
+ arch_prepare_optimized_kprobe(op);
+
+ return &op->kp;
+}
+
+static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p);
+
+/*
+ * Prepare an optimized_kprobe and optimize it
+ * NOTE: p must be a normal registered kprobe
+ */
+static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
+{
+ struct kprobe *ap;
+ struct optimized_kprobe *op;
+
+ ap = alloc_aggr_kprobe(p);
+ if (!ap)
+ return;
+
+ op = container_of(ap, struct optimized_kprobe, kp);
+ if (!arch_prepared_optinsn(&op->optinsn)) {
+ /* If failed to setup optimizing, fallback to kprobe */
+ free_aggr_kprobe(ap);
+ return;
+ }
+
+ init_aggr_kprobe(ap, p);
+ optimize_kprobe(ap);
+}
+
+#ifdef CONFIG_SYSCTL
+static void __kprobes optimize_all_kprobes(void)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct kprobe *p;
+ unsigned int i;
+
+ /* If optimization is already allowed, just return */
+ if (kprobes_allow_optimization)
+ return;
+
+ kprobes_allow_optimization = true;
+ mutex_lock(&text_mutex);
+ for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+ head = &kprobe_table[i];
+ hlist_for_each_entry_rcu(p, node, head, hlist)
+ if (!kprobe_disabled(p))
+ optimize_kprobe(p);
+ }
+ mutex_unlock(&text_mutex);
+ printk(KERN_INFO "Kprobes globally optimized\n");
+}
+
+static void __kprobes unoptimize_all_kprobes(void)
+{
+ struct hlist_head *head;
+ struct hlist_node *node;
+ struct kprobe *p;
+ unsigned int i;
+
+ /* If optimization is already prohibited, just return */
+ if (!kprobes_allow_optimization)
+ return;
+
+ kprobes_allow_optimization = false;
+ printk(KERN_INFO "Kprobes globally unoptimized\n");
+ get_online_cpus(); /* For avoiding text_mutex deadlock */
+ mutex_lock(&text_mutex);
+ for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+ head = &kprobe_table[i];
+ hlist_for_each_entry_rcu(p, node, head, hlist) {
+ if (!kprobe_disabled(p))
+ unoptimize_kprobe(p);
+ }
+ }
+
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+ /* Allow all currently running kprobes to complete */
+ synchronize_sched();
+}
+
+int sysctl_kprobes_optimization;
+int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *length,
+ loff_t *ppos)
+{
+ int ret;
+
+ mutex_lock(&kprobe_mutex);
+ sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
+ ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+ if (sysctl_kprobes_optimization)
+ optimize_all_kprobes();
+ else
+ unoptimize_all_kprobes();
+ mutex_unlock(&kprobe_mutex);
+
+ return ret;
+}
+#endif /* CONFIG_SYSCTL */
+
+static void __kprobes __arm_kprobe(struct kprobe *p)
+{
+ struct kprobe *old_p;
+
+ /* Check collision with other optimized kprobes */
+ old_p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(old_p))
+ unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
+
+ arch_arm_kprobe(p);
+ optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */
+}
+
+static void __kprobes __disarm_kprobe(struct kprobe *p)
+{
+ struct kprobe *old_p;
+
+ unoptimize_kprobe(p); /* Try to unoptimize */
+ arch_disarm_kprobe(p);
+
+ /* If another kprobe was blocked, optimize it. */
+ old_p = get_optimized_kprobe((unsigned long)p->addr);
+ if (unlikely(old_p))
+ optimize_kprobe(old_p);
+}
+
+#else /* !CONFIG_OPTPROBES */
+
+#define optimize_kprobe(p) do {} while (0)
+#define unoptimize_kprobe(p) do {} while (0)
+#define kill_optimized_kprobe(p) do {} while (0)
+#define prepare_optimized_kprobe(p) do {} while (0)
+#define try_to_optimize_kprobe(p) do {} while (0)
+#define __arm_kprobe(p) arch_arm_kprobe(p)
+#define __disarm_kprobe(p) arch_disarm_kprobe(p)
+
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+ kfree(p);
+}
+
+static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+{
+ return kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+}
+#endif /* CONFIG_OPTPROBES */
+
/* Arm a kprobe with text_mutex */
static void __kprobes arm_kprobe(struct kprobe *kp)
{
+ /*
+ * Here, since __arm_kprobe() doesn't use stop_machine(),
+ * this doesn't cause deadlock on text_mutex. So, we don't
+ * need get_online_cpus().
+ */
mutex_lock(&text_mutex);
- arch_arm_kprobe(kp);
+ __arm_kprobe(kp);
mutex_unlock(&text_mutex);
}
/* Disarm a kprobe with text_mutex */
static void __kprobes disarm_kprobe(struct kprobe *kp)
{
+ get_online_cpus(); /* For avoiding text_mutex deadlock */
mutex_lock(&text_mutex);
- arch_disarm_kprobe(kp);
+ __disarm_kprobe(kp);
mutex_unlock(&text_mutex);
+ put_online_cpus();
}
/*
@@ -369,7 +802,7 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
{
struct kprobe *kp;
- if (p->pre_handler != aggr_pre_handler) {
+ if (!kprobe_aggrprobe(p)) {
p->nmissed++;
} else {
list_for_each_entry_rcu(kp, &p->list, list)
@@ -493,21 +926,16 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
}
/*
- * Keep all fields in the kprobe consistent
- */
-static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
-{
- memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
- memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
-}
-
-/*
* Add the new probe to ap->list. Fail if this is the
* second jprobe at the address - two jprobes can't coexist
*/
static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
{
BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
+
+ if (p->break_handler || p->post_handler)
+ unoptimize_kprobe(ap); /* Fall back to normal kprobe */
+
if (p->break_handler) {
if (ap->break_handler)
return -EEXIST;
@@ -522,7 +950,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
ap->flags &= ~KPROBE_FLAG_DISABLED;
if (!kprobes_all_disarmed)
/* Arm the breakpoint again. */
- arm_kprobe(ap);
+ __arm_kprobe(ap);
}
return 0;
}
@@ -531,12 +959,13 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
* Fill in the required fields of the "manager kprobe". Replace the
* earlier kprobe in the hlist with the manager kprobe
*/
-static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
+static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
{
+ /* Copy p's insn slot to ap */
copy_kprobe(p, ap);
flush_insn_slot(ap);
ap->addr = p->addr;
- ap->flags = p->flags;
+ ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED;
ap->pre_handler = aggr_pre_handler;
ap->fault_handler = aggr_fault_handler;
/* We don't care the kprobe which has gone. */
@@ -546,8 +975,9 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
ap->break_handler = aggr_break_handler;
INIT_LIST_HEAD(&ap->list);
- list_add_rcu(&p->list, &ap->list);
+ INIT_HLIST_NODE(&ap->hlist);
+ list_add_rcu(&p->list, &ap->list);
hlist_replace_rcu(&p->hlist, &ap->hlist);
}
@@ -561,12 +991,12 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
int ret = 0;
struct kprobe *ap = old_p;
- if (old_p->pre_handler != aggr_pre_handler) {
- /* If old_p is not an aggr_probe, create new aggr_kprobe. */
- ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+ if (!kprobe_aggrprobe(old_p)) {
+ /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */
+ ap = alloc_aggr_kprobe(old_p);
if (!ap)
return -ENOMEM;
- add_aggr_kprobe(ap, old_p);
+ init_aggr_kprobe(ap, old_p);
}
if (kprobe_gone(ap)) {
@@ -585,6 +1015,9 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
*/
return ret;
+ /* Prepare optimized instructions if possible. */
+ prepare_optimized_kprobe(ap);
+
/*
* Clear gone flag to prevent allocating new slot again, and
* set disabled flag because it is not armed yet.
@@ -593,6 +1026,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
| KPROBE_FLAG_DISABLED;
}
+ /* Copy ap's insn slot to p */
copy_kprobe(ap, p);
return add_new_kprobe(ap, p);
}
@@ -743,27 +1177,34 @@ int __kprobes register_kprobe(struct kprobe *p)
p->nmissed = 0;
INIT_LIST_HEAD(&p->list);
mutex_lock(&kprobe_mutex);
+
+ get_online_cpus(); /* For avoiding text_mutex deadlock. */
+ mutex_lock(&text_mutex);
+
old_p = get_kprobe(p->addr);
if (old_p) {
+ /* Since this may unoptimize old_p, locking text_mutex. */
ret = register_aggr_kprobe(old_p, p);
goto out;
}
- mutex_lock(&text_mutex);
ret = arch_prepare_kprobe(p);
if (ret)
- goto out_unlock_text;
+ goto out;
INIT_HLIST_NODE(&p->hlist);
hlist_add_head_rcu(&p->hlist,
&kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
if (!kprobes_all_disarmed && !kprobe_disabled(p))
- arch_arm_kprobe(p);
+ __arm_kprobe(p);
+
+ /* Try to optimize kprobe */
+ try_to_optimize_kprobe(p);
-out_unlock_text:
- mutex_unlock(&text_mutex);
out:
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
mutex_unlock(&kprobe_mutex);
if (probed_mod)
@@ -785,7 +1226,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
return -EINVAL;
if (old_p == p ||
- (old_p->pre_handler == aggr_pre_handler &&
+ (kprobe_aggrprobe(old_p) &&
list_is_singular(&old_p->list))) {
/*
* Only probe on the hash list. Disarm only if kprobes are
@@ -793,7 +1234,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
* already have been removed. We save on flushing icache.
*/
if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
- disarm_kprobe(p);
+ disarm_kprobe(old_p);
hlist_del_rcu(&old_p->hlist);
} else {
if (p->break_handler && !kprobe_gone(p))
@@ -809,8 +1250,13 @@ noclean:
list_del_rcu(&p->list);
if (!kprobe_disabled(old_p)) {
try_to_disable_aggr_kprobe(old_p);
- if (!kprobes_all_disarmed && kprobe_disabled(old_p))
- disarm_kprobe(old_p);
+ if (!kprobes_all_disarmed) {
+ if (kprobe_disabled(old_p))
+ disarm_kprobe(old_p);
+ else
+ /* Try to optimize this probe again */
+ optimize_kprobe(old_p);
+ }
}
}
return 0;
@@ -827,7 +1273,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
old_p = list_entry(p->list.next, struct kprobe, list);
list_del(&p->list);
arch_remove_kprobe(old_p);
- kfree(old_p);
+ free_aggr_kprobe(old_p);
}
}
@@ -1123,7 +1569,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
struct kprobe *kp;
p->flags |= KPROBE_FLAG_GONE;
- if (p->pre_handler == aggr_pre_handler) {
+ if (kprobe_aggrprobe(p)) {
/*
* If this is an aggr_kprobe, we have to list all the
* chained probes and mark them GONE.
@@ -1132,6 +1578,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
kp->flags |= KPROBE_FLAG_GONE;
p->post_handler = NULL;
p->break_handler = NULL;
+ kill_optimized_kprobe(p);
}
/*
* Here, we can remove insn_slot safely, because no thread calls
@@ -1241,6 +1688,15 @@ static int __init init_kprobes(void)
}
}
+#if defined(CONFIG_OPTPROBES)
+#if defined(__ARCH_WANT_KPROBES_INSN_SLOT)
+ /* Init kprobe_optinsn_slots */
+ kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE;
+#endif
+ /* By default, kprobes can be optimized */
+ kprobes_allow_optimization = true;
+#endif
+
/* By default, kprobes are armed */
kprobes_all_disarmed = false;
@@ -1259,7 +1715,7 @@ static int __init init_kprobes(void)
#ifdef CONFIG_DEBUG_FS
static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
- const char *sym, int offset,char *modname)
+ const char *sym, int offset, char *modname, struct kprobe *pp)
{
char *kprobe_type;
@@ -1269,19 +1725,21 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
kprobe_type = "j";
else
kprobe_type = "k";
+
if (sym)
- seq_printf(pi, "%p %s %s+0x%x %s %s%s\n",
+ seq_printf(pi, "%p %s %s+0x%x %s ",
p->addr, kprobe_type, sym, offset,
- (modname ? modname : " "),
- (kprobe_gone(p) ? "[GONE]" : ""),
- ((kprobe_disabled(p) && !kprobe_gone(p)) ?
- "[DISABLED]" : ""));
+ (modname ? modname : " "));
else
- seq_printf(pi, "%p %s %p %s%s\n",
- p->addr, kprobe_type, p->addr,
- (kprobe_gone(p) ? "[GONE]" : ""),
- ((kprobe_disabled(p) && !kprobe_gone(p)) ?
- "[DISABLED]" : ""));
+ seq_printf(pi, "%p %s %p ",
+ p->addr, kprobe_type, p->addr);
+
+ if (!pp)
+ pp = p;
+ seq_printf(pi, "%s%s%s\n",
+ (kprobe_gone(p) ? "[GONE]" : ""),
+ ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""),
+ (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""));
}
static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
@@ -1317,11 +1775,11 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
hlist_for_each_entry_rcu(p, node, head, hlist) {
sym = kallsyms_lookup((unsigned long)p->addr, NULL,
&offset, &modname, namebuf);
- if (p->pre_handler == aggr_pre_handler) {
+ if (kprobe_aggrprobe(p)) {
list_for_each_entry_rcu(kp, &p->list, list)
- report_probe(pi, kp, sym, offset, modname);
+ report_probe(pi, kp, sym, offset, modname, p);
} else
- report_probe(pi, p, sym, offset, modname);
+ report_probe(pi, p, sym, offset, modname, NULL);
}
preempt_enable();
return 0;
@@ -1399,12 +1857,13 @@ int __kprobes enable_kprobe(struct kprobe *kp)
goto out;
}
- if (!kprobes_all_disarmed && kprobe_disabled(p))
- arm_kprobe(p);
-
- p->flags &= ~KPROBE_FLAG_DISABLED;
if (p != kp)
kp->flags &= ~KPROBE_FLAG_DISABLED;
+
+ if (!kprobes_all_disarmed && kprobe_disabled(p)) {
+ p->flags &= ~KPROBE_FLAG_DISABLED;
+ arm_kprobe(p);
+ }
out:
mutex_unlock(&kprobe_mutex);
return ret;
@@ -1424,12 +1883,13 @@ static void __kprobes arm_all_kprobes(void)
if (!kprobes_all_disarmed)
goto already_enabled;
+ /* Arming kprobes doesn't optimize kprobe itself */
mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist)
if (!kprobe_disabled(p))
- arch_arm_kprobe(p);
+ __arm_kprobe(p);
}
mutex_unlock(&text_mutex);
@@ -1456,16 +1916,23 @@ static void __kprobes disarm_all_kprobes(void)
kprobes_all_disarmed = true;
printk(KERN_INFO "Kprobes globally disabled\n");
+
+ /*
+ * Here we call get_online_cpus() for avoiding text_mutex deadlock,
+ * because disarming may also unoptimize kprobes.
+ */
+ get_online_cpus();
mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
- arch_disarm_kprobe(p);
+ __disarm_kprobe(p);
}
}
mutex_unlock(&text_mutex);
+ put_online_cpus();
mutex_unlock(&kprobe_mutex);
/* Allow all currently running kprobes to complete */
synchronize_sched();
diff --git a/kernel/padata.c b/kernel/padata.c
index 6f9bcb8313d6..93caf65ff57c 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -642,6 +642,9 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask,
if (!pd)
goto err_free_inst;
+ if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL))
+ goto err_free_pd;
+
rcu_assign_pointer(pinst->pd, pd);
pinst->wq = wq;
@@ -654,12 +657,14 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask,
pinst->cpu_notifier.priority = 0;
err = register_hotcpu_notifier(&pinst->cpu_notifier);
if (err)
- goto err_free_pd;
+ goto err_free_cpumask;
mutex_init(&pinst->lock);
return pinst;
+err_free_cpumask:
+ free_cpumask_var(pinst->cpumask);
err_free_pd:
padata_free_pd(pd);
err_free_inst:
@@ -685,6 +690,7 @@ void padata_free(struct padata_instance *pinst)
unregister_hotcpu_notifier(&pinst->cpu_notifier);
padata_free_pd(pinst->pd);
+ free_cpumask_var(pinst->cpumask);
kfree(pinst);
}
EXPORT_SYMBOL(padata_free);
diff --git a/kernel/panic.c b/kernel/panic.c
index c787333282b8..13d966b4c14a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -36,15 +36,36 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
EXPORT_SYMBOL(panic_notifier_list);
-static long no_blink(long time)
-{
- return 0;
-}
-
/* Returns how long it waited in ms */
long (*panic_blink)(long time);
EXPORT_SYMBOL(panic_blink);
+static void panic_blink_one_second(void)
+{
+ static long i = 0, end;
+
+ if (panic_blink) {
+ end = i + MSEC_PER_SEC;
+
+ while (i < end) {
+ i += panic_blink(i);
+ mdelay(1);
+ i++;
+ }
+ } else {
+ /*
+ * When running under a hypervisor a small mdelay may get
+ * rounded up to the hypervisor timeslice. For example, with
+ * a 1ms in 10ms hypervisor timeslice we might inflate a
+ * mdelay(1) loop by 10x.
+ *
+ * If we have nothing to blink, spin on 1 second calls to
+ * mdelay to avoid this.
+ */
+ mdelay(MSEC_PER_SEC);
+ }
+}
+
/**
* panic - halt the system
* @fmt: The text string to print
@@ -95,9 +116,6 @@ NORET_TYPE void panic(const char * fmt, ...)
bust_spinlocks(0);
- if (!panic_blink)
- panic_blink = no_blink;
-
if (panic_timeout > 0) {
/*
* Delay timeout seconds before rebooting the machine.
@@ -105,11 +123,9 @@ NORET_TYPE void panic(const char * fmt, ...)
*/
printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
- for (i = 0; i < panic_timeout*1000; ) {
+ for (i = 0; i < panic_timeout; i++) {
touch_nmi_watchdog();
- i += panic_blink(i);
- mdelay(1);
- i++;
+ panic_blink_one_second();
}
/*
* This will not be a clean reboot, with everything
@@ -135,11 +151,9 @@ NORET_TYPE void panic(const char * fmt, ...)
}
#endif
local_irq_enable();
- for (i = 0; ; ) {
+ while (1) {
touch_softlockup_watchdog();
- i += panic_blink(i);
- mdelay(1);
- i++;
+ panic_blink_one_second();
}
}
diff --git a/kernel/params.c b/kernel/params.c
index cf1b69183127..8d95f5451b22 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -24,7 +24,6 @@
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/ctype.h>
-#include <linux/string.h>
#if 0
#define DEBUGP printk
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index a661e7991865..8e352c756ba7 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2610,7 +2610,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
if (user_locked > user_lock_limit)
extra = user_locked - user_lock_limit;
- lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+ lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
locked = vma->vm_mm->locked_vm + extra;
diff --git a/kernel/pid.c b/kernel/pid.c
index b08e697cd83f..86b296943e5f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -376,7 +376,7 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
EXPORT_SYMBOL(pid_task);
/*
- * Must be called under rcu_read_lock() or with tasklist_lock read-held.
+ * Must be called under rcu_read_lock().
*/
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 438ff4523513..1a22dfd42df9 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -982,6 +982,7 @@ static void check_thread_timers(struct task_struct *tsk,
int maxfire;
struct list_head *timers = tsk->cpu_timers;
struct signal_struct *const sig = tsk->signal;
+ unsigned long soft;
maxfire = 20;
tsk->cputime_expires.prof_exp = cputime_zero;
@@ -1030,9 +1031,10 @@ static void check_thread_timers(struct task_struct *tsk,
/*
* Check for the special case thread timers.
*/
- if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) {
- unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max;
- unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur;
+ soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+ if (soft != RLIM_INFINITY) {
+ unsigned long hard =
+ ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
if (hard != RLIM_INFINITY &&
tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
@@ -1043,14 +1045,13 @@ static void check_thread_timers(struct task_struct *tsk,
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
- if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) {
+ if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
/*
* At the soft limit, send a SIGXCPU every second.
*/
- if (sig->rlim[RLIMIT_RTTIME].rlim_cur
- < sig->rlim[RLIMIT_RTTIME].rlim_max) {
- sig->rlim[RLIMIT_RTTIME].rlim_cur +=
- USEC_PER_SEC;
+ if (soft < hard) {
+ soft += USEC_PER_SEC;
+ sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
}
printk(KERN_INFO
"RT Watchdog Timeout: %s[%d]\n",
@@ -1121,6 +1122,7 @@ static void check_process_timers(struct task_struct *tsk,
unsigned long long sum_sched_runtime, sched_expires;
struct list_head *timers = sig->cpu_timers;
struct task_cputime cputime;
+ unsigned long soft;
/*
* Don't sample the current process CPU clocks if there are no timers.
@@ -1193,11 +1195,13 @@ static void check_process_timers(struct task_struct *tsk,
SIGPROF);
check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
SIGVTALRM);
-
- if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+ soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+ if (soft != RLIM_INFINITY) {
unsigned long psecs = cputime_to_secs(ptime);
+ unsigned long hard =
+ ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
cputime_t x;
- if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) {
+ if (psecs >= hard) {
/*
* At the hard limit, we just die.
* No need to calculate anything else now.
@@ -1205,17 +1209,17 @@ static void check_process_timers(struct task_struct *tsk,
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
- if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) {
+ if (psecs >= soft) {
/*
* At the soft limit, send a SIGXCPU every second.
*/
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
- if (sig->rlim[RLIMIT_CPU].rlim_cur
- < sig->rlim[RLIMIT_CPU].rlim_max) {
- sig->rlim[RLIMIT_CPU].rlim_cur++;
+ if (soft < hard) {
+ soft++;
+ sig->rlim[RLIMIT_CPU].rlim_cur = soft;
}
}
- x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+ x = secs_to_cputime(soft);
if (cputime_eq(prof_expires, cputime_zero) ||
cputime_lt(x, prof_expires)) {
prof_expires = x;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index bbfe472d7524..da5288ec2392 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -323,6 +323,7 @@ static int create_image(int platform_mode)
int hibernation_snapshot(int platform_mode)
{
int error;
+ gfp_t saved_mask;
error = platform_begin(platform_mode);
if (error)
@@ -334,6 +335,7 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Recover_platform;
@@ -351,6 +353,7 @@ int hibernation_snapshot(int platform_mode)
dpm_resume_end(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+ set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
platform_end(platform_mode);
@@ -445,14 +448,17 @@ static int resume_target_kernel(bool platform_mode)
int hibernation_restore(int platform_mode)
{
int error;
+ gfp_t saved_mask;
pm_prepare_console();
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
dpm_resume_end(PMSG_RECOVER);
}
+ set_gfp_allowed_mask(saved_mask);
resume_console();
pm_restore_console();
return error;
@@ -466,6 +472,7 @@ int hibernation_restore(int platform_mode)
int hibernation_platform_enter(void)
{
int error;
+ gfp_t saved_mask;
if (!hibernation_ops)
return -ENOSYS;
@@ -481,6 +488,7 @@ int hibernation_platform_enter(void)
entering_platform_hibernation = true;
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
@@ -518,6 +526,7 @@ int hibernation_platform_enter(void)
Resume_devices:
entering_platform_hibernation = false;
dpm_resume_end(PMSG_RESTORE);
+ set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6f10dfc2d3e9..44cce10b582d 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -189,6 +189,7 @@ static int suspend_enter(suspend_state_t state)
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
+ gfp_t saved_mask;
if (!suspend_ops)
return -ENOSYS;
@@ -199,6 +200,7 @@ int suspend_devices_and_enter(suspend_state_t state)
goto Close;
}
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
@@ -215,6 +217,7 @@ int suspend_devices_and_enter(suspend_state_t state)
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
+ set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
if (suspend_ops->end)
diff --git a/kernel/printk.c b/kernel/printk.c
index 40674122ecf2..75077ad0b537 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -70,8 +70,6 @@ int console_printk[4] = {
DEFAULT_CONSOLE_LOGLEVEL, /* default_console_loglevel */
};
-static int saved_console_loglevel = -1;
-
/*
* Low level drivers may need that to know if they can schedule in
* their unblank() callback or not. So let's export it.
@@ -146,6 +144,7 @@ static char __log_buf[__LOG_BUF_LEN];
static char *log_buf = __log_buf;
static int log_buf_len = __LOG_BUF_LEN;
static unsigned logged_chars; /* Number of chars produced since last read+clear operation */
+static int saved_console_loglevel = -1;
#ifdef CONFIG_KEXEC
/*
diff --git a/kernel/relay.c b/kernel/relay.c
index c705a41b4ba3..3d97f2821611 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1215,14 +1215,14 @@ static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
/*
* subbuf_splice_actor - splice up to one subbuf's worth of data
*/
-static int subbuf_splice_actor(struct file *in,
+static ssize_t subbuf_splice_actor(struct file *in,
loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len,
unsigned int flags,
int *nonpad_ret)
{
- unsigned int pidx, poff, total_len, subbuf_pages, nr_pages, ret;
+ unsigned int pidx, poff, total_len, subbuf_pages, nr_pages;
struct rchan_buf *rbuf = in->private_data;
unsigned int subbuf_size = rbuf->chan->subbuf_size;
uint64_t pos = (uint64_t) *ppos;
@@ -1241,6 +1241,7 @@ static int subbuf_splice_actor(struct file *in,
.ops = &relay_pipe_buf_ops,
.spd_release = relay_page_release,
};
+ ssize_t ret;
if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
return 0;
diff --git a/kernel/sched.c b/kernel/sched.c
index abb36b16b93b..b47ceeec1a91 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4353,7 +4353,7 @@ int can_nice(const struct task_struct *p, const int nice)
/* convert nice value [19,-20] to rlimit style value [1,40] */
int nice_rlim = 20 - nice;
- return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
capable(CAP_SYS_NICE));
}
@@ -4530,7 +4530,7 @@ recheck:
if (!lock_task_sighand(p, &flags))
return -ESRCH;
- rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+ rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
unlock_task_sighand(p, &flags);
/* can't set/change the rt policy */
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index eeb3506c4834..82095bf2099f 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -47,7 +47,7 @@ static int convert_prio(int prio)
}
#define for_each_cpupri_active(array, idx) \
- for_each_bit(idx, array, CPUPRI_NR_PRIORITIES)
+ for_each_set_bit(idx, array, CPUPRI_NR_PRIORITIES)
/**
* cpupri_find - find the best (lowest-pri) CPU in the system
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index bf3e38fdbe6d..5a6ed1f0990a 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1662,8 +1662,9 @@ static void watchdog(struct rq *rq, struct task_struct *p)
if (!p->signal)
return;
- soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur;
- hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max;
+ /* max may change after cur was read, this will be fixed next tick */
+ soft = task_rlimit(p, RLIMIT_RTTIME);
+ hard = task_rlimit_max(p, RLIMIT_RTTIME);
if (soft != RLIM_INFINITY) {
unsigned long next;
diff --git a/kernel/signal.c b/kernel/signal.c
index 934ae5e687b9..dbd7fe073c55 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -159,6 +159,10 @@ void recalc_sigpending(void)
/* Given the mask, find the first available signal that should be serviced. */
+#define SYNCHRONOUS_MASK \
+ (sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \
+ sigmask(SIGTRAP) | sigmask(SIGFPE))
+
int next_signal(struct sigpending *pending, sigset_t *mask)
{
unsigned long i, *s, *m, x;
@@ -166,26 +170,39 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
s = pending->signal.sig;
m = mask->sig;
+
+ /*
+ * Handle the first word specially: it contains the
+ * synchronous signals that need to be dequeued first.
+ */
+ x = *s &~ *m;
+ if (x) {
+ if (x & SYNCHRONOUS_MASK)
+ x &= SYNCHRONOUS_MASK;
+ sig = ffz(~x) + 1;
+ return sig;
+ }
+
switch (_NSIG_WORDS) {
default:
- for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m)
- if ((x = *s &~ *m) != 0) {
- sig = ffz(~x) + i*_NSIG_BPW + 1;
- break;
- }
+ for (i = 1; i < _NSIG_WORDS; ++i) {
+ x = *++s &~ *++m;
+ if (!x)
+ continue;
+ sig = ffz(~x) + i*_NSIG_BPW + 1;
+ break;
+ }
break;
- case 2: if ((x = s[0] &~ m[0]) != 0)
- sig = 1;
- else if ((x = s[1] &~ m[1]) != 0)
- sig = _NSIG_BPW + 1;
- else
+ case 2:
+ x = s[1] &~ m[1];
+ if (!x)
break;
- sig += ffz(~x);
+ sig = ffz(~x) + _NSIG_BPW + 1;
break;
- case 1: if ((x = *s &~ *m) != 0)
- sig = ffz(~x) + 1;
+ case 1:
+ /* Nothing to do */
break;
}
@@ -228,7 +245,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
if (override_rlimit ||
atomic_read(&user->sigpending) <=
- t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
+ task_rlimit(t, RLIMIT_SIGPENDING)) {
q = kmem_cache_alloc(sigqueue_cachep, flags);
} else {
print_dropped_signal(sig);
diff --git a/kernel/sys.c b/kernel/sys.c
index 877fe4f8e05e..9814e43fb23b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -571,8 +571,7 @@ static int set_user(struct cred *new)
if (!new_user)
return -EAGAIN;
- if (atomic_read(&new_user->processes) >=
- current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
+ if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
new_user != INIT_USER) {
free_uid(new_user);
return -EAGAIN;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 33e7a38b6eb9..0ef19c614f6d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -50,6 +50,7 @@
#include <linux/ftrace.h>
#include <linux/slow-work.h>
#include <linux/perf_event.h>
+#include <linux/kprobes.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -1450,6 +1451,17 @@ static struct ctl_table debug_table[] = {
.proc_handler = proc_dointvec
},
#endif
+#if defined(CONFIG_OPTPROBES)
+ {
+ .procname = "kprobes-optimization",
+ .data = &sysctl_kprobes_optimization,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_kprobes_optimization_handler,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
{ }
};
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 8f5d16e0707a..8cd50d8f9bde 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -1331,7 +1331,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
ssize_t result;
char *pathname;
int flags;
- int acc_mode, fmode;
+ int acc_mode;
pathname = sysctl_getname(name, nlen, &table);
result = PTR_ERR(pathname);
@@ -1342,15 +1342,12 @@ static ssize_t binary_sysctl(const int *name, int nlen,
if (oldval && oldlen && newval && newlen) {
flags = O_RDWR;
acc_mode = MAY_READ | MAY_WRITE;
- fmode = FMODE_READ | FMODE_WRITE;
} else if (newval && newlen) {
flags = O_WRONLY;
acc_mode = MAY_WRITE;
- fmode = FMODE_WRITE;
} else if (oldval && oldlen) {
flags = O_RDONLY;
acc_mode = MAY_READ;
- fmode = FMODE_READ;
} else {
result = 0;
goto out_putname;
@@ -1361,7 +1358,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
if (result)
goto out_putname;
- result = may_open(&nd.path, acc_mode, fmode);
+ result = may_open(&nd.path, acc_mode, flags);
if (result)
goto out_putpath;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 00d59d048edf..0a67e041edf8 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -21,6 +21,7 @@
#include <linux/tsacct_kern.h>
#include <linux/acct.h>
#include <linux/jiffies.h>
+#include <linux/mm.h>
/*
* fill in basic accounting fields
OpenPOWER on IntegriCloud