summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile7
-rw-r--r--kernel/capability.c21
-rw-r--r--kernel/cgroup.c45
-rw-r--r--kernel/compat.c10
-rw-r--r--kernel/cpu.c44
-rw-r--r--kernel/cpu_pm.c16
-rw-r--r--kernel/cred.c53
-rw-r--r--kernel/events/Makefile3
-rw-r--r--kernel/events/core.c25
-rw-r--r--kernel/events/uprobes.c1667
-rw-r--r--kernel/exit.c36
-rw-r--r--kernel/extable.c8
-rw-r--r--kernel/fork.c50
-rw-r--r--kernel/groups.c50
-rw-r--r--kernel/hrtimer.c53
-rw-r--r--kernel/irq/chip.c8
-rw-r--r--kernel/irq/internals.h3
-rw-r--r--kernel/irq/irqdomain.c106
-rw-r--r--kernel/irq/manage.c125
-rw-r--r--kernel/irq/migration.c13
-rw-r--r--kernel/kallsyms.c32
-rw-r--r--kernel/kcmp.c196
-rw-r--r--kernel/kfifo.c1
-rw-r--r--kernel/kmod.c30
-rw-r--r--kernel/lglock.c89
-rw-r--r--kernel/module.c3
-rw-r--r--kernel/panic.c6
-rw-r--r--kernel/pid.c3
-rw-r--r--kernel/pid_namespace.c33
-rw-r--r--kernel/power/Kconfig27
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/autosleep.c127
-rw-r--r--kernel/power/hibernate.c21
-rw-r--r--kernel/power/main.c160
-rw-r--r--kernel/power/power.h27
-rw-r--r--kernel/power/swap.c62
-rw-r--r--kernel/power/user.c2
-rw-r--r--kernel/power/wakelock.c259
-rw-r--r--kernel/printk.c670
-rw-r--r--kernel/ptrace.c15
-rw-r--r--kernel/rcutree.c17
-rw-r--r--kernel/rcutree.h15
-rw-r--r--kernel/rcutree_plugin.h179
-rw-r--r--kernel/relay.c5
-rw-r--r--kernel/res_counter.c10
-rw-r--r--kernel/resource.c4
-rw-r--r--kernel/sched/core.c541
-rw-r--r--kernel/sched/fair.c71
-rw-r--r--kernel/sched/idle_task.c1
-rw-r--r--kernel/sched/rt.c53
-rw-r--r--kernel/sched/sched.h4
-rw-r--r--kernel/semaphore.c2
-rw-r--r--kernel/signal.c131
-rw-r--r--kernel/smpboot.c17
-rw-r--r--kernel/sys.c491
-rw-r--r--kernel/sys_ni.c3
-rw-r--r--kernel/task_work.c84
-rw-r--r--kernel/time/Kconfig58
-rw-r--r--kernel/time/clockevents.c3
-rw-r--r--kernel/time/ntp.c16
-rw-r--r--kernel/time/tick-sched.c28
-rw-r--r--kernel/time/timekeeping.c70
-rw-r--r--kernel/timer.c8
-rw-r--r--kernel/trace/Kconfig22
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/ring_buffer.c11
-rw-r--r--kernel/trace/trace.c8
-rw-r--r--kernel/trace/trace.h5
-rw-r--r--kernel/trace/trace_kprobe.c899
-rw-r--r--kernel/trace/trace_probe.c839
-rw-r--r--kernel/trace/trace_probe.h161
-rw-r--r--kernel/trace/trace_uprobe.c788
-rw-r--r--kernel/uid16.c48
-rw-r--r--kernel/user.c51
-rw-r--r--kernel/user_namespace.c595
-rw-r--r--kernel/utsname.c2
-rw-r--r--kernel/watchdog.c31
77 files changed, 7389 insertions, 1992 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 6c07f30fa9b7..c0cc67ad764c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -5,12 +5,12 @@
obj-y = fork.o exec_domain.o panic.o printk.o \
cpu.o exit.o itimer.o time.o softirq.o resource.o \
sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
- signal.o sys.o kmod.o workqueue.o pid.o \
+ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \
rcupdate.o extable.o params.o posix-timers.o \
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o cred.o \
- async.o range.o groups.o
+ async.o range.o groups.o lglock.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
@@ -25,6 +25,9 @@ endif
obj-y += sched/
obj-y += power/
+ifeq ($(CONFIG_CHECKPOINT_RESTORE),y)
+obj-$(CONFIG_X86) += kcmp.o
+endif
obj-$(CONFIG_FREEZER) += freezer.o
obj-$(CONFIG_PROFILING) += profile.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
diff --git a/kernel/capability.c b/kernel/capability.c
index 3f1adb6c6470..493d97259484 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -419,3 +419,24 @@ bool nsown_capable(int cap)
{
return ns_capable(current_user_ns(), cap);
}
+
+/**
+ * inode_capable - Check superior capability over inode
+ * @inode: The inode in question
+ * @cap: The capability in question
+ *
+ * Return true if the current task has the given superior capability
+ * targeted at it's own user namespace and that the given inode is owned
+ * by the current user namespace or a child namespace.
+ *
+ * Currently we check to see if an inode is owned by the current
+ * user namespace by seeing if the inode's owner maps into the
+ * current user namespace.
+ *
+ */
+bool inode_capable(const struct inode *inode, int cap)
+{
+ struct user_namespace *ns = current_user_ns();
+
+ return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ad8eae5bb801..b303dfc7dce0 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -255,12 +255,17 @@ int cgroup_lock_is_held(void)
EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
+static int css_unbias_refcnt(int refcnt)
+{
+ return refcnt >= 0 ? refcnt : refcnt - CSS_DEACT_BIAS;
+}
+
/* the current nr of refs, always >= 0 whether @css is deactivated or not */
static int css_refcnt(struct cgroup_subsys_state *css)
{
int v = atomic_read(&css->refcnt);
- return v >= 0 ? v : v - CSS_DEACT_BIAS;
+ return css_unbias_refcnt(v);
}
/* convenient tests for these bits */
@@ -2214,9 +2219,9 @@ retry_find_task:
* only need to check permissions on one of them.
*/
tcred = __task_cred(tsk);
- if (cred->euid &&
- cred->euid != tcred->uid &&
- cred->euid != tcred->suid) {
+ if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
+ !uid_eq(cred->euid, tcred->uid) &&
+ !uid_eq(cred->euid, tcred->suid)) {
rcu_read_unlock();
ret = -EACCES;
goto out_unlock_cgroup;
@@ -3878,8 +3883,12 @@ static void css_dput_fn(struct work_struct *work)
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, dput_work);
+ struct dentry *dentry = css->cgroup->dentry;
+ struct super_block *sb = dentry->d_sb;
- dput(css->cgroup->dentry);
+ atomic_inc(&sb->s_active);
+ dput(dentry);
+ deactivate_super(sb);
}
static void init_cgroup_css(struct cgroup_subsys_state *css,
@@ -4971,10 +4980,12 @@ EXPORT_SYMBOL_GPL(__css_tryget);
void __css_put(struct cgroup_subsys_state *css)
{
struct cgroup *cgrp = css->cgroup;
+ int v;
rcu_read_lock();
- atomic_dec(&css->refcnt);
- switch (css_refcnt(css)) {
+ v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
+
+ switch (v) {
case 1:
if (notify_on_release(cgrp)) {
set_bit(CGRP_RELEASABLE, &cgrp->flags);
@@ -5132,7 +5143,7 @@ EXPORT_SYMBOL_GPL(css_depth);
* @root: the css supporsed to be an ancestor of the child.
*
* Returns true if "root" is an ancestor of "child" in its hierarchy. Because
- * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
+ * this function reads css->id, the caller must hold rcu_read_lock().
* But, considering usual usage, the csses should be valid objects after test.
* Assuming that the caller will do some action to the child if this returns
* returns true, the caller must take "child";s reference count.
@@ -5144,18 +5155,18 @@ bool css_is_ancestor(struct cgroup_subsys_state *child,
{
struct css_id *child_id;
struct css_id *root_id;
- bool ret = true;
- rcu_read_lock();
child_id = rcu_dereference(child->id);
+ if (!child_id)
+ return false;
root_id = rcu_dereference(root->id);
- if (!child_id
- || !root_id
- || (child_id->depth < root_id->depth)
- || (child_id->stack[root_id->depth] != root_id->id))
- ret = false;
- rcu_read_unlock();
- return ret;
+ if (!root_id)
+ return false;
+ if (child_id->depth < root_id->depth)
+ return false;
+ if (child_id->stack[root_id->depth] != root_id->id)
+ return false;
+ return true;
}
void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
diff --git a/kernel/compat.c b/kernel/compat.c
index d2c67aa49ae6..c28a306ae05c 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -1073,15 +1073,7 @@ asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat
if (copy_from_user(&newset32, unewset, sizeof(compat_sigset_t)))
return -EFAULT;
sigset_from_compat(&newset, &newset32);
- sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP));
-
- current->saved_sigmask = current->blocked;
- set_current_blocked(&newset);
-
- current->state = TASK_INTERRUPTIBLE;
- schedule();
- set_restore_sigmask();
- return -ERESTARTNOHAND;
+ return sigsuspend(&newset);
}
#endif /* __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0e6353cf147a..a4eb5227a19e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -10,7 +10,10 @@
#include <linux/sched.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
+#include <linux/oom.h>
+#include <linux/rcupdate.h>
#include <linux/export.h>
+#include <linux/bug.h>
#include <linux/kthread.h>
#include <linux/stop_machine.h>
#include <linux/mutex.h>
@@ -173,6 +176,47 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(unregister_cpu_notifier);
+/**
+ * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
+ * @cpu: a CPU id
+ *
+ * This function walks all processes, finds a valid mm struct for each one and
+ * then clears a corresponding bit in mm's cpumask. While this all sounds
+ * trivial, there are various non-obvious corner cases, which this function
+ * tries to solve in a safe manner.
+ *
+ * Also note that the function uses a somewhat relaxed locking scheme, so it may
+ * be called only for an already offlined CPU.
+ */
+void clear_tasks_mm_cpumask(int cpu)
+{
+ struct task_struct *p;
+
+ /*
+ * This function is called after the cpu is taken down and marked
+ * offline, so its not like new tasks will ever get this cpu set in
+ * their mm mask. -- Peter Zijlstra
+ * Thus, we may use rcu_read_lock() here, instead of grabbing
+ * full-fledged tasklist_lock.
+ */
+ WARN_ON(cpu_online(cpu));
+ rcu_read_lock();
+ for_each_process(p) {
+ struct task_struct *t;
+
+ /*
+ * Main thread might exit, but other threads may still have
+ * a valid mm. Find one.
+ */
+ t = find_lock_task_mm(p);
+ if (!t)
+ continue;
+ cpumask_clear_cpu(cpu, mm_cpumask(t->mm));
+ task_unlock(t);
+ }
+ rcu_read_unlock();
+}
+
static inline void check_for_tasks(int cpu)
{
struct task_struct *p;
diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index 249152e15308..9656a3c36503 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -81,7 +81,7 @@ int cpu_pm_unregister_notifier(struct notifier_block *nb)
EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
/**
- * cpm_pm_enter - CPU low power entry notifier
+ * cpu_pm_enter - CPU low power entry notifier
*
* Notifies listeners that a single CPU is entering a low power state that may
* cause some blocks in the same power domain as the cpu to reset.
@@ -89,7 +89,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
* Must be called on the affected CPU with interrupts disabled. Platform is
* responsible for ensuring that cpu_pm_enter is not called twice on the same
* CPU before cpu_pm_exit is called. Notified drivers can include VFP
- * co-processor, interrupt controller and it's PM extensions, local CPU
+ * co-processor, interrupt controller and its PM extensions, local CPU
* timers context save/restore which shouldn't be interrupted. Hence it
* must be called with interrupts disabled.
*
@@ -115,13 +115,13 @@ int cpu_pm_enter(void)
EXPORT_SYMBOL_GPL(cpu_pm_enter);
/**
- * cpm_pm_exit - CPU low power exit notifier
+ * cpu_pm_exit - CPU low power exit notifier
*
* Notifies listeners that a single CPU is exiting a low power state that may
* have caused some blocks in the same power domain as the cpu to reset.
*
* Notified drivers can include VFP co-processor, interrupt controller
- * and it's PM extensions, local CPU timers context save/restore which
+ * and its PM extensions, local CPU timers context save/restore which
* shouldn't be interrupted. Hence it must be called with interrupts disabled.
*
* Return conditions are same as __raw_notifier_call_chain.
@@ -139,7 +139,7 @@ int cpu_pm_exit(void)
EXPORT_SYMBOL_GPL(cpu_pm_exit);
/**
- * cpm_cluster_pm_enter - CPU cluster low power entry notifier
+ * cpu_cluster_pm_enter - CPU cluster low power entry notifier
*
* Notifies listeners that all cpus in a power domain are entering a low power
* state that may cause some blocks in the same power domain to reset.
@@ -147,7 +147,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
* Must be called after cpu_pm_enter has been called on all cpus in the power
* domain, and before cpu_pm_exit has been called on any cpu in the power
* domain. Notified drivers can include VFP co-processor, interrupt controller
- * and it's PM extensions, local CPU timers context save/restore which
+ * and its PM extensions, local CPU timers context save/restore which
* shouldn't be interrupted. Hence it must be called with interrupts disabled.
*
* Must be called with interrupts disabled.
@@ -174,7 +174,7 @@ int cpu_cluster_pm_enter(void)
EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
/**
- * cpm_cluster_pm_exit - CPU cluster low power exit notifier
+ * cpu_cluster_pm_exit - CPU cluster low power exit notifier
*
* Notifies listeners that all cpus in a power domain are exiting form a
* low power state that may have caused some blocks in the same power domain
@@ -183,7 +183,7 @@ EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
* Must be called after cpu_pm_exit has been called on all cpus in the power
* domain, and before cpu_pm_exit has been called on any cpu in the power
* domain. Notified drivers can include VFP co-processor, interrupt controller
- * and it's PM extensions, local CPU timers context save/restore which
+ * and its PM extensions, local CPU timers context save/restore which
* shouldn't be interrupted. Hence it must be called with interrupts disabled.
*
* Return conditions are same as __raw_notifier_call_chain.
diff --git a/kernel/cred.c b/kernel/cred.c
index e70683d9ec32..de728ac50d82 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -49,6 +49,14 @@ struct cred init_cred = {
.subscribers = ATOMIC_INIT(2),
.magic = CRED_MAGIC,
#endif
+ .uid = GLOBAL_ROOT_UID,
+ .gid = GLOBAL_ROOT_GID,
+ .suid = GLOBAL_ROOT_UID,
+ .sgid = GLOBAL_ROOT_GID,
+ .euid = GLOBAL_ROOT_UID,
+ .egid = GLOBAL_ROOT_GID,
+ .fsuid = GLOBAL_ROOT_UID,
+ .fsgid = GLOBAL_ROOT_GID,
.securebits = SECUREBITS_DEFAULT,
.cap_inheritable = CAP_EMPTY_SET,
.cap_permitted = CAP_FULL_SET,
@@ -148,6 +156,7 @@ static void put_cred_rcu(struct rcu_head *rcu)
if (cred->group_info)
put_group_info(cred->group_info);
free_uid(cred->user);
+ put_user_ns(cred->user_ns);
kmem_cache_free(cred_jar, cred);
}
@@ -198,13 +207,6 @@ void exit_creds(struct task_struct *tsk)
validate_creds(cred);
alter_cred_subscribers(cred, -1);
put_cred(cred);
-
- cred = (struct cred *) tsk->replacement_session_keyring;
- if (cred) {
- tsk->replacement_session_keyring = NULL;
- validate_creds(cred);
- put_cred(cred);
- }
}
/**
@@ -303,6 +305,7 @@ struct cred *prepare_creds(void)
set_cred_subscribers(new, 0);
get_group_info(new->group_info);
get_uid(new->user);
+ get_user_ns(new->user_ns);
#ifdef CONFIG_KEYS
key_get(new->thread_keyring);
@@ -386,8 +389,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
struct cred *new;
int ret;
- p->replacement_session_keyring = NULL;
-
if (
#ifdef CONFIG_KEYS
!p->cred->thread_keyring &&
@@ -414,11 +415,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
goto error_put;
}
- /* cache user_ns in cred. Doesn't need a refcount because it will
- * stay pinned by cred->user
- */
- new->user_ns = new->user->user_ns;
-
#ifdef CONFIG_KEYS
/* new threads get their own thread keyrings if their parent already
* had one */
@@ -493,10 +489,10 @@ int commit_creds(struct cred *new)
get_cred(new); /* we will require a ref for the subj creds too */
/* dumpability changes */
- if (old->euid != new->euid ||
- old->egid != new->egid ||
- old->fsuid != new->fsuid ||
- old->fsgid != new->fsgid ||
+ if (!uid_eq(old->euid, new->euid) ||
+ !gid_eq(old->egid, new->egid) ||
+ !uid_eq(old->fsuid, new->fsuid) ||
+ !gid_eq(old->fsgid, new->fsgid) ||
!cap_issubset(new->cap_permitted, old->cap_permitted)) {
if (task->mm)
set_dumpable(task->mm, suid_dumpable);
@@ -505,9 +501,9 @@ int commit_creds(struct cred *new)
}
/* alter the thread keyring */
- if (new->fsuid != old->fsuid)
+ if (!uid_eq(new->fsuid, old->fsuid))
key_fsuid_changed(task);
- if (new->fsgid != old->fsgid)
+ if (!gid_eq(new->fsgid, old->fsgid))
key_fsgid_changed(task);
/* do it
@@ -524,16 +520,16 @@ int commit_creds(struct cred *new)
alter_cred_subscribers(old, -2);
/* send notifications */
- if (new->uid != old->uid ||
- new->euid != old->euid ||
- new->suid != old->suid ||
- new->fsuid != old->fsuid)
+ if (!uid_eq(new->uid, old->uid) ||
+ !uid_eq(new->euid, old->euid) ||
+ !uid_eq(new->suid, old->suid) ||
+ !uid_eq(new->fsuid, old->fsuid))
proc_id_connector(task, PROC_EVENT_UID);
- if (new->gid != old->gid ||
- new->egid != old->egid ||
- new->sgid != old->sgid ||
- new->fsgid != old->fsgid)
+ if (!gid_eq(new->gid, old->gid) ||
+ !gid_eq(new->egid, old->egid) ||
+ !gid_eq(new->sgid, old->sgid) ||
+ !gid_eq(new->fsgid, old->fsgid))
proc_id_connector(task, PROC_EVENT_GID);
/* release the old obj and subj refs both */
@@ -678,6 +674,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
atomic_set(&new->usage, 1);
set_cred_subscribers(new, 0);
get_uid(new->user);
+ get_user_ns(new->user_ns);
get_group_info(new->group_info);
#ifdef CONFIG_KEYS
diff --git a/kernel/events/Makefile b/kernel/events/Makefile
index 22d901f9caf4..103f5d147b2f 100644
--- a/kernel/events/Makefile
+++ b/kernel/events/Makefile
@@ -3,4 +3,7 @@ CFLAGS_REMOVE_core.o = -pg
endif
obj-y := core.o ring_buffer.o callchain.o
+
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_UPROBES) += uprobes.o
+
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 91a445925855..d7d71d6ec972 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -253,9 +253,9 @@ perf_cgroup_match(struct perf_event *event)
return !event->cgrp || event->cgrp == cpuctx->cgrp;
}
-static inline void perf_get_cgroup(struct perf_event *event)
+static inline bool perf_tryget_cgroup(struct perf_event *event)
{
- css_get(&event->cgrp->css);
+ return css_tryget(&event->cgrp->css);
}
static inline void perf_put_cgroup(struct perf_event *event)
@@ -484,7 +484,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
event->cgrp = cgrp;
/* must be done before we fput() the file */
- perf_get_cgroup(event);
+ if (!perf_tryget_cgroup(event)) {
+ event->cgrp = NULL;
+ ret = -ENOENT;
+ goto out;
+ }
/*
* all events in a group must monitor
@@ -2039,8 +2043,8 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
* accessing the event control register. If a NMI hits, then it will
* not restart the event.
*/
-static void __perf_event_task_sched_out(struct task_struct *task,
- struct task_struct *next)
+void __perf_event_task_sched_out(struct task_struct *task,
+ struct task_struct *next)
{
int ctxn;
@@ -2279,8 +2283,8 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
* accessing the event control register. If a NMI hits, then it will
* keep the event running.
*/
-static void __perf_event_task_sched_in(struct task_struct *prev,
- struct task_struct *task)
+void __perf_event_task_sched_in(struct task_struct *prev,
+ struct task_struct *task)
{
struct perf_event_context *ctx;
int ctxn;
@@ -2305,12 +2309,6 @@ static void __perf_event_task_sched_in(struct task_struct *prev,
perf_branch_stack_sched_in(prev, task);
}
-void __perf_event_task_sched(struct task_struct *prev, struct task_struct *next)
-{
- __perf_event_task_sched_out(prev, next);
- __perf_event_task_sched_in(prev, next);
-}
-
static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
{
u64 frequency = event->attr.sample_freq;
@@ -3187,7 +3185,6 @@ static void perf_event_for_each(struct perf_event *event,
event = event->group_leader;
perf_event_for_each_child(event, func);
- func(event);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
perf_event_for_each_child(sibling, func);
mutex_unlock(&ctx->mutex);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
new file mode 100644
index 000000000000..985be4d80fe8
--- /dev/null
+++ b/kernel/events/uprobes.c
@@ -0,0 +1,1667 @@
+/*
+ * User-space Probes (UProbes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2008-2012
+ * Authors:
+ * Srikar Dronamraju
+ * Jim Keniston
+ * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h> /* read_mapping_page */
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/rmap.h> /* anon_vma_prepare */
+#include <linux/mmu_notifier.h> /* set_pte_at_notify */
+#include <linux/swap.h> /* try_to_free_swap */
+#include <linux/ptrace.h> /* user_enable_single_step */
+#include <linux/kdebug.h> /* notifier mechanism */
+
+#include <linux/uprobes.h>
+
+#define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES)
+#define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE
+
+static struct srcu_struct uprobes_srcu;
+static struct rb_root uprobes_tree = RB_ROOT;
+
+static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */
+
+#define UPROBES_HASH_SZ 13
+
+/* serialize (un)register */
+static struct mutex uprobes_mutex[UPROBES_HASH_SZ];
+
+#define uprobes_hash(v) (&uprobes_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
+
+/* serialize uprobe->pending_list */
+static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
+#define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ])
+
+/*
+ * uprobe_events allows us to skip the uprobe_mmap if there are no uprobe
+ * events active at this time. Probably a fine grained per inode count is
+ * better?
+ */
+static atomic_t uprobe_events = ATOMIC_INIT(0);
+
+/*
+ * Maintain a temporary per vma info that can be used to search if a vma
+ * has already been handled. This structure is introduced since extending
+ * vm_area_struct wasnt recommended.
+ */
+struct vma_info {
+ struct list_head probe_list;
+ struct mm_struct *mm;
+ loff_t vaddr;
+};
+
+struct uprobe {
+ struct rb_node rb_node; /* node in the rb tree */
+ atomic_t ref;
+ struct rw_semaphore consumer_rwsem;
+ struct list_head pending_list;
+ struct uprobe_consumer *consumers;
+ struct inode *inode; /* Also hold a ref to inode */
+ loff_t offset;
+ int flags;
+ struct arch_uprobe arch;
+};
+
+/*
+ * valid_vma: Verify if the specified vma is an executable vma
+ * Relax restrictions while unregistering: vm_flags might have
+ * changed after breakpoint was inserted.
+ * - is_register: indicates if we are in register context.
+ * - Return 1 if the specified virtual address is in an
+ * executable vma.
+ */
+static bool valid_vma(struct vm_area_struct *vma, bool is_register)
+{
+ if (!vma->vm_file)
+ return false;
+
+ if (!is_register)
+ return true;
+
+ if ((vma->vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) == (VM_READ|VM_EXEC))
+ return true;
+
+ return false;
+}
+
+static loff_t vma_address(struct vm_area_struct *vma, loff_t offset)
+{
+ loff_t vaddr;
+
+ vaddr = vma->vm_start + offset;
+ vaddr -= vma->vm_pgoff << PAGE_SHIFT;
+
+ return vaddr;
+}
+
+/**
+ * __replace_page - replace page in vma by new page.
+ * based on replace_page in mm/ksm.c
+ *
+ * @vma: vma that holds the pte pointing to page
+ * @page: the cowed page we are replacing by kpage
+ * @kpage: the modified page we replace page by
+ *
+ * Returns 0 on success, -EFAULT on failure.
+ */
+static int __replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *ptep;
+ spinlock_t *ptl;
+ unsigned long addr;
+ int err = -EFAULT;
+
+ addr = page_address_in_vma(page, vma);
+ if (addr == -EFAULT)
+ goto out;
+
+ pgd = pgd_offset(mm, addr);
+ if (!pgd_present(*pgd))
+ goto out;
+
+ pud = pud_offset(pgd, addr);
+ if (!pud_present(*pud))
+ goto out;
+
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd))
+ goto out;
+
+ ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ if (!ptep)
+ goto out;
+
+ get_page(kpage);
+ page_add_new_anon_rmap(kpage, vma, addr);
+
+ if (!PageAnon(page)) {
+ dec_mm_counter(mm, MM_FILEPAGES);
+ inc_mm_counter(mm, MM_ANONPAGES);
+ }
+
+ flush_cache_page(vma, addr, pte_pfn(*ptep));
+ ptep_clear_flush(vma, addr, ptep);
+ set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
+
+ page_remove_rmap(page);
+ if (!page_mapped(page))
+ try_to_free_swap(page);
+ put_page(page);
+ pte_unmap_unlock(ptep, ptl);
+ err = 0;
+
+out:
+ return err;
+}
+
+/**
+ * is_swbp_insn - check if instruction is breakpoint instruction.
+ * @insn: instruction to be checked.
+ * Default implementation of is_swbp_insn
+ * Returns true if @insn is a breakpoint instruction.
+ */
+bool __weak is_swbp_insn(uprobe_opcode_t *insn)
+{
+ return *insn == UPROBE_SWBP_INSN;
+}
+
+/*
+ * NOTE:
+ * Expect the breakpoint instruction to be the smallest size instruction for
+ * the architecture. If an arch has variable length instruction and the
+ * breakpoint instruction is not of the smallest length instruction
+ * supported by that architecture then we need to modify read_opcode /
+ * write_opcode accordingly. This would never be a problem for archs that
+ * have fixed length instructions.
+ */
+
+/*
+ * write_opcode - write the opcode at a given virtual address.
+ * @auprobe: arch breakpointing information.
+ * @mm: the probed process address space.
+ * @vaddr: the virtual address to store the opcode.
+ * @opcode: opcode to be written at @vaddr.
+ *
+ * Called with mm->mmap_sem held (for read and with a reference to
+ * mm).
+ *
+ * For mm @mm, write the opcode at @vaddr.
+ * Return 0 (success) or a negative errno.
+ */
+static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
+ unsigned long vaddr, uprobe_opcode_t opcode)
+{
+ struct page *old_page, *new_page;
+ struct address_space *mapping;
+ void *vaddr_old, *vaddr_new;
+ struct vm_area_struct *vma;
+ struct uprobe *uprobe;
+ loff_t addr;
+ int ret;
+
+ /* Read the page with vaddr into memory */
+ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
+ if (ret <= 0)
+ return ret;
+
+ ret = -EINVAL;
+
+ /*
+ * We are interested in text pages only. Our pages of interest
+ * should be mapped for read and execute only. We desist from
+ * adding probes in write mapped pages since the breakpoints
+ * might end up in the file copy.
+ */
+ if (!valid_vma(vma, is_swbp_insn(&opcode)))
+ goto put_out;
+
+ uprobe = container_of(auprobe, struct uprobe, arch);
+ mapping = uprobe->inode->i_mapping;
+ if (mapping != vma->vm_file->f_mapping)
+ goto put_out;
+
+ addr = vma_address(vma, uprobe->offset);
+ if (vaddr != (unsigned long)addr)
+ goto put_out;
+
+ ret = -ENOMEM;
+ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
+ if (!new_page)
+ goto put_out;
+
+ __SetPageUptodate(new_page);
+
+ /*
+ * lock page will serialize against do_wp_page()'s
+ * PageAnon() handling
+ */
+ lock_page(old_page);
+ /* copy the page now that we've got it stable */
+ vaddr_old = kmap_atomic(old_page);
+ vaddr_new = kmap_atomic(new_page);
+
+ memcpy(vaddr_new, vaddr_old, PAGE_SIZE);
+
+ /* poke the new insn in, ASSUMES we don't cross page boundary */
+ vaddr &= ~PAGE_MASK;
+ BUG_ON(vaddr + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
+ memcpy(vaddr_new + vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
+
+ kunmap_atomic(vaddr_new);
+ kunmap_atomic(vaddr_old);
+
+ ret = anon_vma_prepare(vma);
+ if (ret)
+ goto unlock_out;
+
+ lock_page(new_page);
+ ret = __replace_page(vma, old_page, new_page);
+ unlock_page(new_page);
+
+unlock_out:
+ unlock_page(old_page);
+ page_cache_release(new_page);
+
+put_out:
+ put_page(old_page);
+
+ return ret;
+}
+
+/**
+ * read_opcode - read the opcode at a given virtual address.
+ * @mm: the probed process address space.
+ * @vaddr: the virtual address to read the opcode.
+ * @opcode: location to store the read opcode.
+ *
+ * Called with mm->mmap_sem held (for read and with a reference to
+ * mm.
+ *
+ * For mm @mm, read the opcode at @vaddr and store it in @opcode.
+ * Return 0 (success) or a negative errno.
+ */
+static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode)
+{
+ struct page *page;
+ void *vaddr_new;
+ int ret;
+
+ ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &page, NULL);
+ if (ret <= 0)
+ return ret;
+
+ lock_page(page);
+ vaddr_new = kmap_atomic(page);
+ vaddr &= ~PAGE_MASK;
+ memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE);
+ kunmap_atomic(vaddr_new);
+ unlock_page(page);
+
+ put_page(page);
+
+ return 0;
+}
+
+static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
+{
+ uprobe_opcode_t opcode;
+ int result;
+
+ result = read_opcode(mm, vaddr, &opcode);
+ if (result)
+ return result;
+
+ if (is_swbp_insn(&opcode))
+ return 1;
+
+ return 0;
+}
+
+/**
+ * set_swbp - store breakpoint at a given address.
+ * @auprobe: arch specific probepoint information.
+ * @mm: the probed process address space.
+ * @vaddr: the virtual address to insert the opcode.
+ *
+ * For mm @mm, store the breakpoint instruction at @vaddr.
+ * Return 0 (success) or a negative errno.
+ */
+int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
+{
+ int result;
+
+ result = is_swbp_at_addr(mm, vaddr);
+ if (result == 1)
+ return -EEXIST;
+
+ if (result)
+ return result;
+
+ return write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN);
+}
+
+/**
+ * set_orig_insn - Restore the original instruction.
+ * @mm: the probed process address space.
+ * @auprobe: arch specific probepoint information.
+ * @vaddr: the virtual address to insert the opcode.
+ * @verify: if true, verify existance of breakpoint instruction.
+ *
+ * For mm @mm, restore the original opcode (opcode) at @vaddr.
+ * Return 0 (success) or a negative errno.
+ */
+int __weak
+set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, bool verify)
+{
+ if (verify) {
+ int result;
+
+ result = is_swbp_at_addr(mm, vaddr);
+ if (!result)
+ return -EINVAL;
+
+ if (result != 1)
+ return result;
+ }
+ return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+}
+
+static int match_uprobe(struct uprobe *l, struct uprobe *r)
+{
+ if (l->inode < r->inode)
+ return -1;
+
+ if (l->inode > r->inode)
+ return 1;
+
+ if (l->offset < r->offset)
+ return -1;
+
+ if (l->offset > r->offset)
+ return 1;
+
+ return 0;
+}
+
+static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset)
+{
+ struct uprobe u = { .inode = inode, .offset = offset };
+ struct rb_node *n = uprobes_tree.rb_node;
+ struct uprobe *uprobe;
+ int match;
+
+ while (n) {
+ uprobe = rb_entry(n, struct uprobe, rb_node);
+ match = match_uprobe(&u, uprobe);
+ if (!match) {
+ atomic_inc(&uprobe->ref);
+ return uprobe;
+ }
+
+ if (match < 0)
+ n = n->rb_left;
+ else
+ n = n->rb_right;
+ }
+ return NULL;
+}
+
+/*
+ * Find a uprobe corresponding to a given inode:offset
+ * Acquires uprobes_treelock
+ */
+static struct uprobe *find_uprobe(struct inode *inode, loff_t offset)
+{
+ struct uprobe *uprobe;
+ unsigned long flags;
+
+ spin_lock_irqsave(&uprobes_treelock, flags);
+ uprobe = __find_uprobe(inode, offset);
+ spin_unlock_irqrestore(&uprobes_treelock, flags);
+
+ return uprobe;
+}
+
+static struct uprobe *__insert_uprobe(struct uprobe *uprobe)
+{
+ struct rb_node **p = &uprobes_tree.rb_node;
+ struct rb_node *parent = NULL;
+ struct uprobe *u;
+ int match;
+
+ while (*p) {
+ parent = *p;
+ u = rb_entry(parent, struct uprobe, rb_node);
+ match = match_uprobe(uprobe, u);
+ if (!match) {
+ atomic_inc(&u->ref);
+ return u;
+ }
+
+ if (match < 0)
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+
+ }
+
+ u = NULL;
+ rb_link_node(&uprobe->rb_node, parent, p);
+ rb_insert_color(&uprobe->rb_node, &uprobes_tree);
+ /* get access + creation ref */
+ atomic_set(&uprobe->ref, 2);
+
+ return u;
+}
+
+/*
+ * Acquire uprobes_treelock.
+ * Matching uprobe already exists in rbtree;
+ * increment (access refcount) and return the matching uprobe.
+ *
+ * No matching uprobe; insert the uprobe in rb_tree;
+ * get a double refcount (access + creation) and return NULL.
+ */
+static struct uprobe *insert_uprobe(struct uprobe *uprobe)
+{
+ unsigned long flags;
+ struct uprobe *u;
+
+ spin_lock_irqsave(&uprobes_treelock, flags);
+ u = __insert_uprobe(uprobe);
+ spin_unlock_irqrestore(&uprobes_treelock, flags);
+
+ /* For now assume that the instruction need not be single-stepped */
+ uprobe->flags |= UPROBE_SKIP_SSTEP;
+
+ return u;
+}
+
+static void put_uprobe(struct uprobe *uprobe)
+{
+ if (atomic_dec_and_test(&uprobe->ref))
+ kfree(uprobe);
+}
+
+static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
+{
+ struct uprobe *uprobe, *cur_uprobe;
+
+ uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL);
+ if (!uprobe)
+ return NULL;
+
+ uprobe->inode = igrab(inode);
+ uprobe->offset = offset;
+ init_rwsem(&uprobe->consumer_rwsem);
+ INIT_LIST_HEAD(&uprobe->pending_list);
+
+ /* add to uprobes_tree, sorted on inode:offset */
+ cur_uprobe = insert_uprobe(uprobe);
+
+ /* a uprobe exists for this inode:offset combination */
+ if (cur_uprobe) {
+ kfree(uprobe);
+ uprobe = cur_uprobe;
+ iput(inode);
+ } else {
+ atomic_inc(&uprobe_events);
+ }
+
+ return uprobe;
+}
+
+static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
+{
+ struct uprobe_consumer *uc;
+
+ if (!(uprobe->flags & UPROBE_RUN_HANDLER))
+ return;
+
+ down_read(&uprobe->consumer_rwsem);
+ for (uc = uprobe->consumers; uc; uc = uc->next) {
+ if (!uc->filter || uc->filter(uc, current))
+ uc->handler(uc, regs);
+ }
+ up_read(&uprobe->consumer_rwsem);
+}
+
+/* Returns the previous consumer */
+static struct uprobe_consumer *
+consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
+{
+ down_write(&uprobe->consumer_rwsem);
+ uc->next = uprobe->consumers;
+ uprobe->consumers = uc;
+ up_write(&uprobe->consumer_rwsem);
+
+ return uc->next;
+}
+
+/*
+ * For uprobe @uprobe, delete the consumer @uc.
+ * Return true if the @uc is deleted successfully
+ * or return false.
+ */
+static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
+{
+ struct uprobe_consumer **con;
+ bool ret = false;
+
+ down_write(&uprobe->consumer_rwsem);
+ for (con = &uprobe->consumers; *con; con = &(*con)->next) {
+ if (*con == uc) {
+ *con = uc->next;
+ ret = true;
+ break;
+ }
+ }
+ up_write(&uprobe->consumer_rwsem);
+
+ return ret;
+}
+
+static int
+__copy_insn(struct address_space *mapping, struct vm_area_struct *vma, char *insn,
+ unsigned long nbytes, unsigned long offset)
+{
+ struct file *filp = vma->vm_file;
+ struct page *page;
+ void *vaddr;
+ unsigned long off1;
+ unsigned long idx;
+
+ if (!filp)
+ return -EINVAL;
+
+ idx = (unsigned long)(offset >> PAGE_CACHE_SHIFT);
+ off1 = offset &= ~PAGE_MASK;
+
+ /*
+ * Ensure that the page that has the original instruction is
+ * populated and in page-cache.
+ */
+ page = read_mapping_page(mapping, idx, filp);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
+ vaddr = kmap_atomic(page);
+ memcpy(insn, vaddr + off1, nbytes);
+ kunmap_atomic(vaddr);
+ page_cache_release(page);
+
+ return 0;
+}
+
+static int
+copy_insn(struct uprobe *uprobe, struct vm_area_struct *vma, unsigned long addr)
+{
+ struct address_space *mapping;
+ unsigned long nbytes;
+ int bytes;
+
+ addr &= ~PAGE_MASK;
+ nbytes = PAGE_SIZE - addr;
+ mapping = uprobe->inode->i_mapping;
+
+ /* Instruction at end of binary; copy only available bytes */
+ if (uprobe->offset + MAX_UINSN_BYTES > uprobe->inode->i_size)
+ bytes = uprobe->inode->i_size - uprobe->offset;
+ else
+ bytes = MAX_UINSN_BYTES;
+
+ /* Instruction at the page-boundary; copy bytes in second page */
+ if (nbytes < bytes) {
+ if (__copy_insn(mapping, vma, uprobe->arch.insn + nbytes,
+ bytes - nbytes, uprobe->offset + nbytes))
+ return -ENOMEM;
+
+ bytes = nbytes;
+ }
+ return __copy_insn(mapping, vma, uprobe->arch.insn, bytes, uprobe->offset);
+}
+
+/*
+ * How mm->uprobes_state.count gets updated
+ * uprobe_mmap() increments the count if
+ * - it successfully adds a breakpoint.
+ * - it cannot add a breakpoint, but sees that there is a underlying
+ * breakpoint (via a is_swbp_at_addr()).
+ *
+ * uprobe_munmap() decrements the count if
+ * - it sees a underlying breakpoint, (via is_swbp_at_addr)
+ * (Subsequent uprobe_unregister wouldnt find the breakpoint
+ * unless a uprobe_mmap kicks in, since the old vma would be
+ * dropped just after uprobe_munmap.)
+ *
+ * uprobe_register increments the count if:
+ * - it successfully adds a breakpoint.
+ *
+ * uprobe_unregister decrements the count if:
+ * - it sees a underlying breakpoint and removes successfully.
+ * (via is_swbp_at_addr)
+ * (Subsequent uprobe_munmap wouldnt find the breakpoint
+ * since there is no underlying breakpoint after the
+ * breakpoint removal.)
+ */
+static int
+install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
+ struct vm_area_struct *vma, loff_t vaddr)
+{
+ unsigned long addr;
+ int ret;
+
+ /*
+ * If probe is being deleted, unregister thread could be done with
+ * the vma-rmap-walk through. Adding a probe now can be fatal since
+ * nobody will be able to cleanup. Also we could be from fork or
+ * mremap path, where the probe might have already been inserted.
+ * Hence behave as if probe already existed.
+ */
+ if (!uprobe->consumers)
+ return -EEXIST;
+
+ addr = (unsigned long)vaddr;
+
+ if (!(uprobe->flags & UPROBE_COPY_INSN)) {
+ ret = copy_insn(uprobe, vma, addr);
+ if (ret)
+ return ret;
+
+ if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn))
+ return -EEXIST;
+
+ ret = arch_uprobe_analyze_insn(&uprobe->arch, mm);
+ if (ret)
+ return ret;
+
+ uprobe->flags |= UPROBE_COPY_INSN;
+ }
+
+ /*
+ * Ideally, should be updating the probe count after the breakpoint
+ * has been successfully inserted. However a thread could hit the
+ * breakpoint we just inserted even before the probe count is
+ * incremented. If this is the first breakpoint placed, breakpoint
+ * notifier might ignore uprobes and pass the trap to the thread.
+ * Hence increment before and decrement on failure.
+ */
+ atomic_inc(&mm->uprobes_state.count);
+ ret = set_swbp(&uprobe->arch, mm, addr);
+ if (ret)
+ atomic_dec(&mm->uprobes_state.count);
+
+ return ret;
+}
+
+static void
+remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, loff_t vaddr)
+{
+ if (!set_orig_insn(&uprobe->arch, mm, (unsigned long)vaddr, true))
+ atomic_dec(&mm->uprobes_state.count);
+}
+
+/*
+ * There could be threads that have hit the breakpoint and are entering the
+ * notifier code and trying to acquire the uprobes_treelock. The thread
+ * calling delete_uprobe() that is removing the uprobe from the rb_tree can
+ * race with these threads and might acquire the uprobes_treelock compared
+ * to some of the breakpoint hit threads. In such a case, the breakpoint
+ * hit threads will not find the uprobe. The current unregistering thread
+ * waits till all other threads have hit a breakpoint, to acquire the
+ * uprobes_treelock before the uprobe is removed from the rbtree.
+ */
+static void delete_uprobe(struct uprobe *uprobe)
+{
+ unsigned long flags;
+
+ synchronize_srcu(&uprobes_srcu);
+ spin_lock_irqsave(&uprobes_treelock, flags);
+ rb_erase(&uprobe->rb_node, &uprobes_tree);
+ spin_unlock_irqrestore(&uprobes_treelock, flags);
+ iput(uprobe->inode);
+ put_uprobe(uprobe);
+ atomic_dec(&uprobe_events);
+}
+
+static struct vma_info *
+__find_next_vma_info(struct address_space *mapping, struct list_head *head,
+ struct vma_info *vi, loff_t offset, bool is_register)
+{
+ struct prio_tree_iter iter;
+ struct vm_area_struct *vma;
+ struct vma_info *tmpvi;
+ unsigned long pgoff;
+ int existing_vma;
+ loff_t vaddr;
+
+ pgoff = offset >> PAGE_SHIFT;
+
+ vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+ if (!valid_vma(vma, is_register))
+ continue;
+
+ existing_vma = 0;
+ vaddr = vma_address(vma, offset);
+
+ list_for_each_entry(tmpvi, head, probe_list) {
+ if (tmpvi->mm == vma->vm_mm && tmpvi->vaddr == vaddr) {
+ existing_vma = 1;
+ break;
+ }
+ }
+
+ /*
+ * Another vma needs a probe to be installed. However skip
+ * installing the probe if the vma is about to be unlinked.
+ */
+ if (!existing_vma && atomic_inc_not_zero(&vma->vm_mm->mm_users)) {
+ vi->mm = vma->vm_mm;
+ vi->vaddr = vaddr;
+ list_add(&vi->probe_list, head);
+
+ return vi;
+ }
+ }
+
+ return NULL;
+}
+
+/*
+ * Iterate in the rmap prio tree and find a vma where a probe has not
+ * yet been inserted.
+ */
+static struct vma_info *
+find_next_vma_info(struct address_space *mapping, struct list_head *head,
+ loff_t offset, bool is_register)
+{
+ struct vma_info *vi, *retvi;
+
+ vi = kzalloc(sizeof(struct vma_info), GFP_KERNEL);
+ if (!vi)
+ return ERR_PTR(-ENOMEM);
+
+ mutex_lock(&mapping->i_mmap_mutex);
+ retvi = __find_next_vma_info(mapping, head, vi, offset, is_register);
+ mutex_unlock(&mapping->i_mmap_mutex);
+
+ if (!retvi)
+ kfree(vi);
+
+ return retvi;
+}
+
+static int register_for_each_vma(struct uprobe *uprobe, bool is_register)
+{
+ struct list_head try_list;
+ struct vm_area_struct *vma;
+ struct address_space *mapping;
+ struct vma_info *vi, *tmpvi;
+ struct mm_struct *mm;
+ loff_t vaddr;
+ int ret;
+
+ mapping = uprobe->inode->i_mapping;
+ INIT_LIST_HEAD(&try_list);
+
+ ret = 0;
+
+ for (;;) {
+ vi = find_next_vma_info(mapping, &try_list, uprobe->offset, is_register);
+ if (!vi)
+ break;
+
+ if (IS_ERR(vi)) {
+ ret = PTR_ERR(vi);
+ break;
+ }
+
+ mm = vi->mm;
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, (unsigned long)vi->vaddr);
+ if (!vma || !valid_vma(vma, is_register)) {
+ list_del(&vi->probe_list);
+ kfree(vi);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ continue;
+ }
+ vaddr = vma_address(vma, uprobe->offset);
+ if (vma->vm_file->f_mapping->host != uprobe->inode ||
+ vaddr != vi->vaddr) {
+ list_del(&vi->probe_list);
+ kfree(vi);
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ continue;
+ }
+
+ if (is_register)
+ ret = install_breakpoint(uprobe, mm, vma, vi->vaddr);
+ else
+ remove_breakpoint(uprobe, mm, vi->vaddr);
+
+ up_read(&mm->mmap_sem);
+ mmput(mm);
+ if (is_register) {
+ if (ret && ret == -EEXIST)
+ ret = 0;
+ if (ret)
+ break;
+ }
+ }
+
+ list_for_each_entry_safe(vi, tmpvi, &try_list, probe_list) {
+ list_del(&vi->probe_list);
+ kfree(vi);
+ }
+
+ return ret;
+}
+
+static int __uprobe_register(struct uprobe *uprobe)
+{
+ return register_for_each_vma(uprobe, true);
+}
+
+static void __uprobe_unregister(struct uprobe *uprobe)
+{
+ if (!register_for_each_vma(uprobe, false))
+ delete_uprobe(uprobe);
+
+ /* TODO : cant unregister? schedule a worker thread */
+}
+
+/*
+ * uprobe_register - register a probe
+ * @inode: the file in which the probe has to be placed.
+ * @offset: offset from the start of the file.
+ * @uc: information on howto handle the probe..
+ *
+ * Apart from the access refcount, uprobe_register() takes a creation
+ * refcount (thro alloc_uprobe) if and only if this @uprobe is getting
+ * inserted into the rbtree (i.e first consumer for a @inode:@offset
+ * tuple). Creation refcount stops uprobe_unregister from freeing the
+ * @uprobe even before the register operation is complete. Creation
+ * refcount is released when the last @uc for the @uprobe
+ * unregisters.
+ *
+ * Return errno if it cannot successully install probes
+ * else return 0 (success)
+ */
+int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
+{
+ struct uprobe *uprobe;
+ int ret;
+
+ if (!inode || !uc || uc->next)
+ return -EINVAL;
+
+ if (offset > i_size_read(inode))
+ return -EINVAL;
+
+ ret = 0;
+ mutex_lock(uprobes_hash(inode));
+ uprobe = alloc_uprobe(inode, offset);
+
+ if (uprobe && !consumer_add(uprobe, uc)) {
+ ret = __uprobe_register(uprobe);
+ if (ret) {
+ uprobe->consumers = NULL;
+ __uprobe_unregister(uprobe);
+ } else {
+ uprobe->flags |= UPROBE_RUN_HANDLER;
+ }
+ }
+
+ mutex_unlock(uprobes_hash(inode));
+ put_uprobe(uprobe);
+
+ return ret;
+}
+
+/*
+ * uprobe_unregister - unregister a already registered probe.
+ * @inode: the file in which the probe has to be removed.
+ * @offset: offset from the start of the file.
+ * @uc: identify which probe if multiple probes are colocated.
+ */
+void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
+{
+ struct uprobe *uprobe;
+
+ if (!inode || !uc)
+ return;
+
+ uprobe = find_uprobe(inode, offset);
+ if (!uprobe)
+ return;
+
+ mutex_lock(uprobes_hash(inode));
+
+ if (consumer_del(uprobe, uc)) {
+ if (!uprobe->consumers) {
+ __uprobe_unregister(uprobe);
+ uprobe->flags &= ~UPROBE_RUN_HANDLER;
+ }
+ }
+
+ mutex_unlock(uprobes_hash(inode));
+ if (uprobe)
+ put_uprobe(uprobe);
+}
+
+/*
+ * Of all the nodes that correspond to the given inode, return the node
+ * with the least offset.
+ */
+static struct rb_node *find_least_offset_node(struct inode *inode)
+{
+ struct uprobe u = { .inode = inode, .offset = 0};
+ struct rb_node *n = uprobes_tree.rb_node;
+ struct rb_node *close_node = NULL;
+ struct uprobe *uprobe;
+ int match;
+
+ while (n) {
+ uprobe = rb_entry(n, struct uprobe, rb_node);
+ match = match_uprobe(&u, uprobe);
+
+ if (uprobe->inode == inode)
+ close_node = n;
+
+ if (!match)
+ return close_node;
+
+ if (match < 0)
+ n = n->rb_left;
+ else
+ n = n->rb_right;
+ }
+
+ return close_node;
+}
+
+/*
+ * For a given inode, build a list of probes that need to be inserted.
+ */
+static void build_probe_list(struct inode *inode, struct list_head *head)
+{
+ struct uprobe *uprobe;
+ unsigned long flags;
+ struct rb_node *n;
+
+ spin_lock_irqsave(&uprobes_treelock, flags);
+
+ n = find_least_offset_node(inode);
+
+ for (; n; n = rb_next(n)) {
+ uprobe = rb_entry(n, struct uprobe, rb_node);
+ if (uprobe->inode != inode)
+ break;
+
+ list_add(&uprobe->pending_list, head);
+ atomic_inc(&uprobe->ref);
+ }
+
+ spin_unlock_irqrestore(&uprobes_treelock, flags);
+}
+
+/*
+ * Called from mmap_region.
+ * called with mm->mmap_sem acquired.
+ *
+ * Return -ve no if we fail to insert probes and we cannot
+ * bail-out.
+ * Return 0 otherwise. i.e:
+ *
+ * - successful insertion of probes
+ * - (or) no possible probes to be inserted.
+ * - (or) insertion of probes failed but we can bail-out.
+ */
+int uprobe_mmap(struct vm_area_struct *vma)
+{
+ struct list_head tmp_list;
+ struct uprobe *uprobe, *u;
+ struct inode *inode;
+ int ret, count;
+
+ if (!atomic_read(&uprobe_events) || !valid_vma(vma, true))
+ return 0;
+
+ inode = vma->vm_file->f_mapping->host;
+ if (!inode)
+ return 0;
+
+ INIT_LIST_HEAD(&tmp_list);
+ mutex_lock(uprobes_mmap_hash(inode));
+ build_probe_list(inode, &tmp_list);
+
+ ret = 0;
+ count = 0;
+
+ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
+ loff_t vaddr;
+
+ list_del(&uprobe->pending_list);
+ if (!ret) {
+ vaddr = vma_address(vma, uprobe->offset);
+
+ if (vaddr < vma->vm_start || vaddr >= vma->vm_end) {
+ put_uprobe(uprobe);
+ continue;
+ }
+
+ ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
+
+ /* Ignore double add: */
+ if (ret == -EEXIST) {
+ ret = 0;
+
+ if (!is_swbp_at_addr(vma->vm_mm, vaddr))
+ continue;
+
+ /*
+ * Unable to insert a breakpoint, but
+ * breakpoint lies underneath. Increment the
+ * probe count.
+ */
+ atomic_inc(&vma->vm_mm->uprobes_state.count);
+ }
+
+ if (!ret)
+ count++;
+ }
+ put_uprobe(uprobe);
+ }
+
+ mutex_unlock(uprobes_mmap_hash(inode));
+
+ if (ret)
+ atomic_sub(count, &vma->vm_mm->uprobes_state.count);
+
+ return ret;
+}
+
+/*
+ * Called in context of a munmap of a vma.
+ */
+void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+ struct list_head tmp_list;
+ struct uprobe *uprobe, *u;
+ struct inode *inode;
+
+ if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
+ return;
+
+ if (!atomic_read(&vma->vm_mm->uprobes_state.count))
+ return;
+
+ inode = vma->vm_file->f_mapping->host;
+ if (!inode)
+ return;
+
+ INIT_LIST_HEAD(&tmp_list);
+ mutex_lock(uprobes_mmap_hash(inode));
+ build_probe_list(inode, &tmp_list);
+
+ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
+ loff_t vaddr;
+
+ list_del(&uprobe->pending_list);
+ vaddr = vma_address(vma, uprobe->offset);
+
+ if (vaddr >= start && vaddr < end) {
+ /*
+ * An unregister could have removed the probe before
+ * unmap. So check before we decrement the count.
+ */
+ if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
+ atomic_dec(&vma->vm_mm->uprobes_state.count);
+ }
+ put_uprobe(uprobe);
+ }
+ mutex_unlock(uprobes_mmap_hash(inode));
+}
+
+/* Slot allocation for XOL */
+static int xol_add_vma(struct xol_area *area)
+{
+ struct mm_struct *mm;
+ int ret;
+
+ area->page = alloc_page(GFP_HIGHUSER);
+ if (!area->page)
+ return -ENOMEM;
+
+ ret = -EALREADY;
+ mm = current->mm;
+
+ down_write(&mm->mmap_sem);
+ if (mm->uprobes_state.xol_area)
+ goto fail;
+
+ ret = -ENOMEM;
+
+ /* Try to map as high as possible, this is only a hint. */
+ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0);
+ if (area->vaddr & ~PAGE_MASK) {
+ ret = area->vaddr;
+ goto fail;
+ }
+
+ ret = install_special_mapping(mm, area->vaddr, PAGE_SIZE,
+ VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO, &area->page);
+ if (ret)
+ goto fail;
+
+ smp_wmb(); /* pairs with get_xol_area() */
+ mm->uprobes_state.xol_area = area;
+ ret = 0;
+
+fail:
+ up_write(&mm->mmap_sem);
+ if (ret)
+ __free_page(area->page);
+
+ return ret;
+}
+
+static struct xol_area *get_xol_area(struct mm_struct *mm)
+{
+ struct xol_area *area;
+
+ area = mm->uprobes_state.xol_area;
+ smp_read_barrier_depends(); /* pairs with wmb in xol_add_vma() */
+
+ return area;
+}
+
+/*
+ * xol_alloc_area - Allocate process's xol_area.
+ * This area will be used for storing instructions for execution out of
+ * line.
+ *
+ * Returns the allocated area or NULL.
+ */
+static struct xol_area *xol_alloc_area(void)
+{
+ struct xol_area *area;
+
+ area = kzalloc(sizeof(*area), GFP_KERNEL);
+ if (unlikely(!area))
+ return NULL;
+
+ area->bitmap = kzalloc(BITS_TO_LONGS(UINSNS_PER_PAGE) * sizeof(long), GFP_KERNEL);
+
+ if (!area->bitmap)
+ goto fail;
+
+ init_waitqueue_head(&area->wq);
+ if (!xol_add_vma(area))
+ return area;
+
+fail:
+ kfree(area->bitmap);
+ kfree(area);
+
+ return get_xol_area(current->mm);
+}
+
+/*
+ * uprobe_clear_state - Free the area allocated for slots.
+ */
+void uprobe_clear_state(struct mm_struct *mm)
+{
+ struct xol_area *area = mm->uprobes_state.xol_area;
+
+ if (!area)
+ return;
+
+ put_page(area->page);
+ kfree(area->bitmap);
+ kfree(area);
+}
+
+/*
+ * uprobe_reset_state - Free the area allocated for slots.
+ */
+void uprobe_reset_state(struct mm_struct *mm)
+{
+ mm->uprobes_state.xol_area = NULL;
+ atomic_set(&mm->uprobes_state.count, 0);
+}
+
+/*
+ * - search for a free slot.
+ */
+static unsigned long xol_take_insn_slot(struct xol_area *area)
+{
+ unsigned long slot_addr;
+ int slot_nr;
+
+ do {
+ slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE);
+ if (slot_nr < UINSNS_PER_PAGE) {
+ if (!test_and_set_bit(slot_nr, area->bitmap))
+ break;
+
+ slot_nr = UINSNS_PER_PAGE;
+ continue;
+ }
+ wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE));
+ } while (slot_nr >= UINSNS_PER_PAGE);
+
+ slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES);
+ atomic_inc(&area->slot_count);
+
+ return slot_addr;
+}
+
+/*
+ * xol_get_insn_slot - If was not allocated a slot, then
+ * allocate a slot.
+ * Returns the allocated slot address or 0.
+ */
+static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot_addr)
+{
+ struct xol_area *area;
+ unsigned long offset;
+ void *vaddr;
+
+ area = get_xol_area(current->mm);
+ if (!area) {
+ area = xol_alloc_area();
+ if (!area)
+ return 0;
+ }
+ current->utask->xol_vaddr = xol_take_insn_slot(area);
+
+ /*
+ * Initialize the slot if xol_vaddr points to valid
+ * instruction slot.
+ */
+ if (unlikely(!current->utask->xol_vaddr))
+ return 0;
+
+ current->utask->vaddr = slot_addr;
+ offset = current->utask->xol_vaddr & ~PAGE_MASK;
+ vaddr = kmap_atomic(area->page);
+ memcpy(vaddr + offset, uprobe->arch.insn, MAX_UINSN_BYTES);
+ kunmap_atomic(vaddr);
+
+ return current->utask->xol_vaddr;
+}
+
+/*
+ * xol_free_insn_slot - If slot was earlier allocated by
+ * @xol_get_insn_slot(), make the slot available for
+ * subsequent requests.
+ */
+static void xol_free_insn_slot(struct task_struct *tsk)
+{
+ struct xol_area *area;
+ unsigned long vma_end;
+ unsigned long slot_addr;
+
+ if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask)
+ return;
+
+ slot_addr = tsk->utask->xol_vaddr;
+
+ if (unlikely(!slot_addr || IS_ERR_VALUE(slot_addr)))
+ return;
+
+ area = tsk->mm->uprobes_state.xol_area;
+ vma_end = area->vaddr + PAGE_SIZE;
+ if (area->vaddr <= slot_addr && slot_addr < vma_end) {
+ unsigned long offset;
+ int slot_nr;
+
+ offset = slot_addr - area->vaddr;
+ slot_nr = offset / UPROBE_XOL_SLOT_BYTES;
+ if (slot_nr >= UINSNS_PER_PAGE)
+ return;
+
+ clear_bit(slot_nr, area->bitmap);
+ atomic_dec(&area->slot_count);
+ if (waitqueue_active(&area->wq))
+ wake_up(&area->wq);
+
+ tsk->utask->xol_vaddr = 0;
+ }
+}
+
+/**
+ * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
+ * @regs: Reflects the saved state of the task after it has hit a breakpoint
+ * instruction.
+ * Return the address of the breakpoint instruction.
+ */
+unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+ return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE;
+}
+
+/*
+ * Called with no locks held.
+ * Called in context of a exiting or a exec-ing thread.
+ */
+void uprobe_free_utask(struct task_struct *t)
+{
+ struct uprobe_task *utask = t->utask;
+
+ if (t->uprobe_srcu_id != -1)
+ srcu_read_unlock_raw(&uprobes_srcu, t->uprobe_srcu_id);
+
+ if (!utask)
+ return;
+
+ if (utask->active_uprobe)
+ put_uprobe(utask->active_uprobe);
+
+ xol_free_insn_slot(t);
+ kfree(utask);
+ t->utask = NULL;
+}
+
+/*
+ * Called in context of a new clone/fork from copy_process.
+ */
+void uprobe_copy_process(struct task_struct *t)
+{
+ t->utask = NULL;
+ t->uprobe_srcu_id = -1;
+}
+
+/*
+ * Allocate a uprobe_task object for the task.
+ * Called when the thread hits a breakpoint for the first time.
+ *
+ * Returns:
+ * - pointer to new uprobe_task on success
+ * - NULL otherwise
+ */
+static struct uprobe_task *add_utask(void)
+{
+ struct uprobe_task *utask;
+
+ utask = kzalloc(sizeof *utask, GFP_KERNEL);
+ if (unlikely(!utask))
+ return NULL;
+
+ utask->active_uprobe = NULL;
+ current->utask = utask;
+ return utask;
+}
+
+/* Prepare to single-step probed instruction out of line. */
+static int
+pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long vaddr)
+{
+ if (xol_get_insn_slot(uprobe, vaddr) && !arch_uprobe_pre_xol(&uprobe->arch, regs))
+ return 0;
+
+ return -EFAULT;
+}
+
+/*
+ * If we are singlestepping, then ensure this thread is not connected to
+ * non-fatal signals until completion of singlestep. When xol insn itself
+ * triggers the signal, restart the original insn even if the task is
+ * already SIGKILL'ed (since coredump should report the correct ip). This
+ * is even more important if the task has a handler for SIGSEGV/etc, The
+ * _same_ instruction should be repeated again after return from the signal
+ * handler, and SSTEP can never finish in this case.
+ */
+bool uprobe_deny_signal(void)
+{
+ struct task_struct *t = current;
+ struct uprobe_task *utask = t->utask;
+
+ if (likely(!utask || !utask->active_uprobe))
+ return false;
+
+ WARN_ON_ONCE(utask->state != UTASK_SSTEP);
+
+ if (signal_pending(t)) {
+ spin_lock_irq(&t->sighand->siglock);
+ clear_tsk_thread_flag(t, TIF_SIGPENDING);
+ spin_unlock_irq(&t->sighand->siglock);
+
+ if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
+ utask->state = UTASK_SSTEP_TRAPPED;
+ set_tsk_thread_flag(t, TIF_UPROBE);
+ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+ }
+ }
+
+ return true;
+}
+
+/*
+ * Avoid singlestepping the original instruction if the original instruction
+ * is a NOP or can be emulated.
+ */
+static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
+{
+ if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
+ return true;
+
+ uprobe->flags &= ~UPROBE_SKIP_SSTEP;
+ return false;
+}
+
+/*
+ * Run handler and ask thread to singlestep.
+ * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
+ */
+static void handle_swbp(struct pt_regs *regs)
+{
+ struct vm_area_struct *vma;
+ struct uprobe_task *utask;
+ struct uprobe *uprobe;
+ struct mm_struct *mm;
+ unsigned long bp_vaddr;
+
+ uprobe = NULL;
+ bp_vaddr = uprobe_get_swbp_addr(regs);
+ mm = current->mm;
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, bp_vaddr);
+
+ if (vma && vma->vm_start <= bp_vaddr && valid_vma(vma, false)) {
+ struct inode *inode;
+ loff_t offset;
+
+ inode = vma->vm_file->f_mapping->host;
+ offset = bp_vaddr - vma->vm_start;
+ offset += (vma->vm_pgoff << PAGE_SHIFT);
+ uprobe = find_uprobe(inode, offset);
+ }
+
+ srcu_read_unlock_raw(&uprobes_srcu, current->uprobe_srcu_id);
+ current->uprobe_srcu_id = -1;
+ up_read(&mm->mmap_sem);
+
+ if (!uprobe) {
+ /* No matching uprobe; signal SIGTRAP. */
+ send_sig(SIGTRAP, current, 0);
+ return;
+ }
+
+ utask = current->utask;
+ if (!utask) {
+ utask = add_utask();
+ /* Cannot allocate; re-execute the instruction. */
+ if (!utask)
+ goto cleanup_ret;
+ }
+ utask->active_uprobe = uprobe;
+ handler_chain(uprobe, regs);
+ if (uprobe->flags & UPROBE_SKIP_SSTEP && can_skip_sstep(uprobe, regs))
+ goto cleanup_ret;
+
+ utask->state = UTASK_SSTEP;
+ if (!pre_ssout(uprobe, regs, bp_vaddr)) {
+ user_enable_single_step(current);
+ return;
+ }
+
+cleanup_ret:
+ if (utask) {
+ utask->active_uprobe = NULL;
+ utask->state = UTASK_RUNNING;
+ }
+ if (uprobe) {
+ if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
+
+ /*
+ * cannot singlestep; cannot skip instruction;
+ * re-execute the instruction.
+ */
+ instruction_pointer_set(regs, bp_vaddr);
+
+ put_uprobe(uprobe);
+ }
+}
+
+/*
+ * Perform required fix-ups and disable singlestep.
+ * Allow pending signals to take effect.
+ */
+static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
+{
+ struct uprobe *uprobe;
+
+ uprobe = utask->active_uprobe;
+ if (utask->state == UTASK_SSTEP_ACK)
+ arch_uprobe_post_xol(&uprobe->arch, regs);
+ else if (utask->state == UTASK_SSTEP_TRAPPED)
+ arch_uprobe_abort_xol(&uprobe->arch, regs);
+ else
+ WARN_ON_ONCE(1);
+
+ put_uprobe(uprobe);
+ utask->active_uprobe = NULL;
+ utask->state = UTASK_RUNNING;
+ user_disable_single_step(current);
+ xol_free_insn_slot(current);
+
+ spin_lock_irq(&current->sighand->siglock);
+ recalc_sigpending(); /* see uprobe_deny_signal() */
+ spin_unlock_irq(&current->sighand->siglock);
+}
+
+/*
+ * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag. (and on
+ * subsequent probe hits on the thread sets the state to UTASK_BP_HIT) and
+ * allows the thread to return from interrupt.
+ *
+ * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag and
+ * also sets the state to UTASK_SSTEP_ACK and allows the thread to return from
+ * interrupt.
+ *
+ * While returning to userspace, thread notices the TIF_UPROBE flag and calls
+ * uprobe_notify_resume().
+ */
+void uprobe_notify_resume(struct pt_regs *regs)
+{
+ struct uprobe_task *utask;
+
+ utask = current->utask;
+ if (!utask || utask->state == UTASK_BP_HIT)
+ handle_swbp(regs);
+ else
+ handle_singlestep(utask, regs);
+}
+
+/*
+ * uprobe_pre_sstep_notifier gets called from interrupt context as part of
+ * notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit.
+ */
+int uprobe_pre_sstep_notifier(struct pt_regs *regs)
+{
+ struct uprobe_task *utask;
+
+ if (!current->mm || !atomic_read(&current->mm->uprobes_state.count))
+ /* task is currently not uprobed */
+ return 0;
+
+ utask = current->utask;
+ if (utask)
+ utask->state = UTASK_BP_HIT;
+
+ set_thread_flag(TIF_UPROBE);
+ current->uprobe_srcu_id = srcu_read_lock_raw(&uprobes_srcu);
+
+ return 1;
+}
+
+/*
+ * uprobe_post_sstep_notifier gets called in interrupt context as part of notifier
+ * mechanism. Set TIF_UPROBE flag and indicate completion of singlestep.
+ */
+int uprobe_post_sstep_notifier(struct pt_regs *regs)
+{
+ struct uprobe_task *utask = current->utask;
+
+ if (!current->mm || !utask || !utask->active_uprobe)
+ /* task is currently not uprobed */
+ return 0;
+
+ utask->state = UTASK_SSTEP_ACK;
+ set_thread_flag(TIF_UPROBE);
+ return 1;
+}
+
+static struct notifier_block uprobe_exception_nb = {
+ .notifier_call = arch_uprobe_exception_notify,
+ .priority = INT_MAX-1, /* notified after kprobes, kgdb */
+};
+
+static int __init init_uprobes(void)
+{
+ int i;
+
+ for (i = 0; i < UPROBES_HASH_SZ; i++) {
+ mutex_init(&uprobes_mutex[i]);
+ mutex_init(&uprobes_mmap_mutex[i]);
+ }
+ init_srcu_struct(&uprobes_srcu);
+
+ return register_die_notifier(&uprobe_exception_nb);
+}
+module_init(init_uprobes);
+
+static void __exit exit_uprobes(void)
+{
+}
+module_exit(exit_uprobes);
diff --git a/kernel/exit.c b/kernel/exit.c
index d8bd3b425fa7..2f59cc334516 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,6 +72,18 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
list_del_rcu(&p->tasks);
list_del_init(&p->sibling);
__this_cpu_dec(process_counts);
+ /*
+ * If we are the last child process in a pid namespace to be
+ * reaped, notify the reaper sleeping zap_pid_ns_processes().
+ */
+ if (IS_ENABLED(CONFIG_PID_NS)) {
+ struct task_struct *parent = p->real_parent;
+
+ if ((task_active_pid_ns(parent)->child_reaper == parent) &&
+ list_empty(&parent->children) &&
+ (parent->flags & PF_EXITING))
+ wake_up_process(parent);
+ }
}
list_del_rcu(&p->thread_group);
}
@@ -643,6 +655,7 @@ static void exit_mm(struct task_struct * tsk)
mm_release(tsk, mm);
if (!mm)
return;
+ sync_mm_rss(mm);
/*
* Serialize with any possible pending coredump.
* We must hold mmap_sem around checking core_state
@@ -719,12 +732,6 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
- /*
- * We can not clear ->child_reaper or leave it alone.
- * There may by stealth EXIT_DEAD tasks on ->children,
- * forget_original_parent() must move them somewhere.
- */
- pid_ns->child_reaper = init_pid_ns.child_reaper;
} else if (father->signal->has_child_subreaper) {
struct task_struct *reaper;
@@ -884,9 +891,9 @@ static void check_stack_usage(void)
spin_lock(&low_water_lock);
if (free < lowest_to_date) {
- printk(KERN_WARNING "%s used greatest stack depth: %lu bytes "
- "left\n",
- current->comm, free);
+ printk(KERN_WARNING "%s (%d) used greatest stack depth: "
+ "%lu bytes left\n",
+ current->comm, task_pid_nr(current), free);
lowest_to_date = free;
}
spin_unlock(&low_water_lock);
@@ -946,12 +953,13 @@ void do_exit(long code)
exit_signals(tsk); /* sets PF_EXITING */
/*
* tsk->flags are checked in the futex code to protect against
- * an exiting task cleaning up the robust pi futexes.
+ * an exiting task cleaning up the robust pi futexes, and in
+ * task_work_add() to avoid the race with exit_task_work().
*/
smp_mb();
raw_spin_unlock_wait(&tsk->pi_lock);
- exit_irq_thread();
+ exit_task_work(tsk);
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
@@ -1214,7 +1222,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
unsigned long state;
int retval, status, traced;
pid_t pid = task_pid_vnr(p);
- uid_t uid = __task_cred(p)->uid;
+ uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p));
struct siginfo __user *infop;
if (!likely(wo->wo_flags & WEXITED))
@@ -1427,7 +1435,7 @@ static int wait_task_stopped(struct wait_opts *wo,
if (!unlikely(wo->wo_flags & WNOWAIT))
*p_code = 0;
- uid = task_uid(p);
+ uid = from_kuid_munged(current_user_ns(), task_uid(p));
unlock_sig:
spin_unlock_irq(&p->sighand->siglock);
if (!exit_code)
@@ -1500,7 +1508,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
}
if (!unlikely(wo->wo_flags & WNOWAIT))
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
- uid = task_uid(p);
+ uid = from_kuid_munged(current_user_ns(), task_uid(p));
spin_unlock_irq(&p->sighand->siglock);
pid = task_pid_vnr(p);
diff --git a/kernel/extable.c b/kernel/extable.c
index 5339705b8241..fe35a634bf76 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -35,10 +35,16 @@ DEFINE_MUTEX(text_mutex);
extern struct exception_table_entry __start___ex_table[];
extern struct exception_table_entry __stop___ex_table[];
+/* Cleared by build time tools if the table is already sorted. */
+u32 __initdata main_extable_sort_needed = 1;
+
/* Sort the kernel's built-in exception table */
void __init sort_main_extable(void)
{
- sort_extable(__start___ex_table, __stop___ex_table);
+ if (main_extable_sort_needed)
+ sort_extable(__start___ex_table, __stop___ex_table);
+ else
+ pr_notice("__ex_table already sorted, skipping sort\n");
}
/* Given an address, look for it in the exception tables. */
diff --git a/kernel/fork.c b/kernel/fork.c
index ad54c833116a..f00e319d8376 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -69,6 +69,7 @@
#include <linux/oom.h>
#include <linux/khugepaged.h>
#include <linux/signalfd.h>
+#include <linux/uprobes.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -292,8 +293,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
int node = tsk_fork_get_node(orig);
int err;
- prepare_to_copy(orig);
-
tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
@@ -305,12 +304,17 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
}
err = arch_dup_task_struct(tsk, orig);
- if (err)
- goto out;
+ /*
+ * We defer looking at err, because we will need this setup
+ * for the clean up path to work correctly.
+ */
tsk->stack = ti;
-
setup_thread_stack(tsk, orig);
+
+ if (err)
+ goto out;
+
clear_user_return_notifier(tsk);
clear_tsk_need_resched(tsk);
stackend = end_of_stack(tsk);
@@ -387,7 +391,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
}
charge = 0;
if (mpnt->vm_flags & VM_ACCOUNT) {
- unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
+ unsigned long len;
+ len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
goto fail_nomem;
charge = len;
@@ -453,6 +458,9 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
if (retval)
goto out;
+
+ if (file && uprobe_mmap(tmp))
+ goto out;
}
/* a new mm has just been created */
arch_dup_mmap(oldmm, mm);
@@ -601,6 +609,7 @@ void mmput(struct mm_struct *mm)
might_sleep();
if (atomic_dec_and_test(&mm->mm_users)) {
+ uprobe_clear_state(mm);
exit_aio(mm);
ksm_exit(mm);
khugepaged_exit(mm); /* must run before exit_mmap */
@@ -611,7 +620,6 @@ void mmput(struct mm_struct *mm)
list_del(&mm->mmlist);
spin_unlock(&mmlist_lock);
}
- put_swap_token(mm);
if (mm->binfmt)
module_put(mm->binfmt->module);
mmdrop(mm);
@@ -779,12 +787,11 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
exit_pi_state_list(tsk);
#endif
+ uprobe_free_utask(tsk);
+
/* Get rid of any cached register state */
deactivate_mm(tsk, mm);
- if (tsk->vfork_done)
- complete_vfork_done(tsk);
-
/*
* If we're exiting normally, clear a user-space tid field if
* requested. We leave this alone when dying by signal, to leave
@@ -805,6 +812,13 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
}
tsk->clear_child_tid = NULL;
}
+
+ /*
+ * All done, finally we can wake up parent and return this mm to him.
+ * Also kthread_stop() uses this completion for synchronization.
+ */
+ if (tsk->vfork_done)
+ complete_vfork_done(tsk);
}
/*
@@ -826,13 +840,10 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
memcpy(mm, oldmm, sizeof(*mm));
mm_init_cpumask(mm);
- /* Initializing for Swap token stuff */
- mm->token_priority = 0;
- mm->last_interval = 0;
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
+ uprobe_reset_state(mm);
if (!mm_init(mm, tsk))
goto fail_nomem;
@@ -907,10 +918,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
goto fail_nomem;
good_mm:
- /* Initializing for Swap token stuff */
- mm->token_priority = 0;
- mm->last_interval = 0;
-
tsk->mm = mm;
tsk->active_mm = mm;
return 0;
@@ -978,9 +985,8 @@ static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
* Share io context with parent, if CLONE_IO is set
*/
if (clone_flags & CLONE_IO) {
- tsk->io_context = ioc_task_link(ioc);
- if (unlikely(!tsk->io_context))
- return -ENOMEM;
+ ioc_task_link(ioc);
+ tsk->io_context = ioc;
} else if (ioprio_valid(ioc->ioprio)) {
new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
if (unlikely(!new_ioc))
@@ -1375,6 +1381,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
INIT_LIST_HEAD(&p->pi_state_list);
p->pi_state_cache = NULL;
#endif
+ uprobe_copy_process(p);
/*
* sigaltstack should be cleared when sharing the same VM
*/
@@ -1413,6 +1420,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
*/
p->group_leader = p;
INIT_LIST_HEAD(&p->thread_group);
+ INIT_HLIST_HEAD(&p->task_works);
/* Now that the task is set up, run cgroup callbacks if
* necessary. We need to run them before the task is visible
diff --git a/kernel/groups.c b/kernel/groups.c
index 99b53d1eb7ea..6b2588dd04ff 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -31,7 +31,7 @@ struct group_info *groups_alloc(int gidsetsize)
group_info->blocks[0] = group_info->small_block;
else {
for (i = 0; i < nblocks; i++) {
- gid_t *b;
+ kgid_t *b;
b = (void *)__get_free_page(GFP_USER);
if (!b)
goto out_undo_partial_alloc;
@@ -66,18 +66,15 @@ EXPORT_SYMBOL(groups_free);
static int groups_to_user(gid_t __user *grouplist,
const struct group_info *group_info)
{
+ struct user_namespace *user_ns = current_user_ns();
int i;
unsigned int count = group_info->ngroups;
- for (i = 0; i < group_info->nblocks; i++) {
- unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
- unsigned int len = cp_count * sizeof(*grouplist);
-
- if (copy_to_user(grouplist, group_info->blocks[i], len))
+ for (i = 0; i < count; i++) {
+ gid_t gid;
+ gid = from_kgid_munged(user_ns, GROUP_AT(group_info, i));
+ if (put_user(gid, grouplist+i))
return -EFAULT;
-
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
}
return 0;
}
@@ -86,18 +83,21 @@ static int groups_to_user(gid_t __user *grouplist,
static int groups_from_user(struct group_info *group_info,
gid_t __user *grouplist)
{
+ struct user_namespace *user_ns = current_user_ns();
int i;
unsigned int count = group_info->ngroups;
- for (i = 0; i < group_info->nblocks; i++) {
- unsigned int cp_count = min(NGROUPS_PER_BLOCK, count);
- unsigned int len = cp_count * sizeof(*grouplist);
-
- if (copy_from_user(group_info->blocks[i], grouplist, len))
+ for (i = 0; i < count; i++) {
+ gid_t gid;
+ kgid_t kgid;
+ if (get_user(gid, grouplist+i))
return -EFAULT;
- grouplist += NGROUPS_PER_BLOCK;
- count -= cp_count;
+ kgid = make_kgid(user_ns, gid);
+ if (!gid_valid(kgid))
+ return -EINVAL;
+
+ GROUP_AT(group_info, i) = kgid;
}
return 0;
}
@@ -117,9 +117,9 @@ static void groups_sort(struct group_info *group_info)
for (base = 0; base < max; base++) {
int left = base;
int right = left + stride;
- gid_t tmp = GROUP_AT(group_info, right);
+ kgid_t tmp = GROUP_AT(group_info, right);
- while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
+ while (left >= 0 && gid_gt(GROUP_AT(group_info, left), tmp)) {
GROUP_AT(group_info, right) =
GROUP_AT(group_info, left);
right = left;
@@ -132,7 +132,7 @@ static void groups_sort(struct group_info *group_info)
}
/* a simple bsearch */
-int groups_search(const struct group_info *group_info, gid_t grp)
+int groups_search(const struct group_info *group_info, kgid_t grp)
{
unsigned int left, right;
@@ -143,9 +143,9 @@ int groups_search(const struct group_info *group_info, gid_t grp)
right = group_info->ngroups;
while (left < right) {
unsigned int mid = (left+right)/2;
- if (grp > GROUP_AT(group_info, mid))
+ if (gid_gt(grp, GROUP_AT(group_info, mid)))
left = mid + 1;
- else if (grp < GROUP_AT(group_info, mid))
+ else if (gid_lt(grp, GROUP_AT(group_info, mid)))
right = mid;
else
return 1;
@@ -256,24 +256,24 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
/*
* Check whether we're fsgid/egid or in the supplemental group..
*/
-int in_group_p(gid_t grp)
+int in_group_p(kgid_t grp)
{
const struct cred *cred = current_cred();
int retval = 1;
- if (grp != cred->fsgid)
+ if (!gid_eq(grp, cred->fsgid))
retval = groups_search(cred->group_info, grp);
return retval;
}
EXPORT_SYMBOL(in_group_p);
-int in_egroup_p(gid_t grp)
+int in_egroup_p(kgid_t grp)
{
const struct cred *cred = current_cred();
int retval = 1;
- if (grp != cred->egid)
+ if (!gid_eq(grp, cred->egid))
retval = groups_search(cred->group_info, grp);
return retval;
}
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ae34bf51682b..6db7a5ed52b5 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -657,6 +657,14 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
return 0;
}
+static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
+{
+ ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
+ ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset;
+
+ return ktime_get_update_offsets(offs_real, offs_boot);
+}
+
/*
* Retrigger next event is called after clock was set
*
@@ -665,22 +673,12 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
static void retrigger_next_event(void *arg)
{
struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
- struct timespec realtime_offset, xtim, wtm, sleep;
if (!hrtimer_hres_active())
return;
- /* Optimized out for !HIGH_RES */
- get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep);
- set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
-
- /* Adjust CLOCK_REALTIME offset */
raw_spin_lock(&base->lock);
- base->clock_base[HRTIMER_BASE_REALTIME].offset =
- timespec_to_ktime(realtime_offset);
- base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
- timespec_to_ktime(sleep);
-
+ hrtimer_update_base(base);
hrtimer_force_reprogram(base, 0);
raw_spin_unlock(&base->lock);
}
@@ -710,13 +708,25 @@ static int hrtimer_switch_to_hres(void)
base->clock_base[i].resolution = KTIME_HIGH_RES;
tick_setup_sched_timer();
-
/* "Retrigger" the interrupt to get things going */
retrigger_next_event(NULL);
local_irq_restore(flags);
return 1;
}
+/*
+ * Called from timekeeping code to reprogramm the hrtimer interrupt
+ * device. If called from the timer interrupt context we defer it to
+ * softirq context.
+ */
+void clock_was_set_delayed(void)
+{
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+ cpu_base->clock_was_set = 1;
+ __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+}
+
#else
static inline int hrtimer_hres_active(void) { return 0; }
@@ -1250,11 +1260,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
- entry_time = now = ktime_get();
+ raw_spin_lock(&cpu_base->lock);
+ entry_time = now = hrtimer_update_base(cpu_base);
retry:
expires_next.tv64 = KTIME_MAX;
-
- raw_spin_lock(&cpu_base->lock);
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
@@ -1330,8 +1339,12 @@ retry:
* We need to prevent that we loop forever in the hrtimer
* interrupt routine. We give it 3 attempts to avoid
* overreacting on some spurious event.
+ *
+ * Acquire base lock for updating the offsets and retrieving
+ * the current time.
*/
- now = ktime_get();
+ raw_spin_lock(&cpu_base->lock);
+ now = hrtimer_update_base(cpu_base);
cpu_base->nr_retries++;
if (++retries < 3)
goto retry;
@@ -1343,6 +1356,7 @@ retry:
*/
cpu_base->nr_hangs++;
cpu_base->hang_detected = 1;
+ raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
if (delta.tv64 > cpu_base->max_hang_time.tv64)
cpu_base->max_hang_time = delta;
@@ -1395,6 +1409,13 @@ void hrtimer_peek_ahead_timers(void)
static void run_hrtimer_softirq(struct softirq_action *h)
{
+ struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
+
+ if (cpu_base->clock_was_set) {
+ cpu_base->clock_was_set = 0;
+ clock_was_set();
+ }
+
hrtimer_peek_ahead_timers();
}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index fc275e4f629b..eebd6d5cfb44 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -275,8 +275,10 @@ void handle_nested_irq(unsigned int irq)
kstat_incr_irqs_this_cpu(irq, desc);
action = desc->action;
- if (unlikely(!action || irqd_irq_disabled(&desc->irq_data)))
+ if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
+ desc->istate |= IRQS_PENDING;
goto out_unlock;
+ }
irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
raw_spin_unlock_irq(&desc->lock);
@@ -324,8 +326,10 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
- if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data)))
+ if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+ desc->istate |= IRQS_PENDING;
goto out_unlock;
+ }
handle_irq_event(desc);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 8e5c56b3b7d9..001fa5bab490 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -101,6 +101,9 @@ extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
extern void irq_set_thread_affinity(struct irq_desc *desc);
+extern int irq_do_set_affinity(struct irq_data *data,
+ const struct cpumask *dest, bool force);
+
/* Inline functions for support of irq chips on slow busses */
static inline void chip_bus_lock(struct irq_desc *desc)
{
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 0e0ba5f840b2..41c1564103f1 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1,3 +1,5 @@
+#define pr_fmt(fmt) "irq: " fmt
+
#include <linux/debugfs.h>
#include <linux/hardirq.h>
#include <linux/interrupt.h>
@@ -56,14 +58,73 @@ static struct irq_domain *irq_domain_alloc(struct device_node *of_node,
return domain;
}
+static void irq_domain_free(struct irq_domain *domain)
+{
+ of_node_put(domain->of_node);
+ kfree(domain);
+}
+
static void irq_domain_add(struct irq_domain *domain)
{
mutex_lock(&irq_domain_mutex);
list_add(&domain->link, &irq_domain_list);
mutex_unlock(&irq_domain_mutex);
- pr_debug("irq: Allocated domain of type %d @0x%p\n",
+ pr_debug("Allocated domain of type %d @0x%p\n",
+ domain->revmap_type, domain);
+}
+
+/**
+ * irq_domain_remove() - Remove an irq domain.
+ * @domain: domain to remove
+ *
+ * This routine is used to remove an irq domain. The caller must ensure
+ * that all mappings within the domain have been disposed of prior to
+ * use, depending on the revmap type.
+ */
+void irq_domain_remove(struct irq_domain *domain)
+{
+ mutex_lock(&irq_domain_mutex);
+
+ switch (domain->revmap_type) {
+ case IRQ_DOMAIN_MAP_LEGACY:
+ /*
+ * Legacy domains don't manage their own irq_desc
+ * allocations, we expect the caller to handle irq_desc
+ * freeing on their own.
+ */
+ break;
+ case IRQ_DOMAIN_MAP_TREE:
+ /*
+ * radix_tree_delete() takes care of destroying the root
+ * node when all entries are removed. Shout if there are
+ * any mappings left.
+ */
+ WARN_ON(domain->revmap_data.tree.height);
+ break;
+ case IRQ_DOMAIN_MAP_LINEAR:
+ kfree(domain->revmap_data.linear.revmap);
+ domain->revmap_data.linear.size = 0;
+ break;
+ case IRQ_DOMAIN_MAP_NOMAP:
+ break;
+ }
+
+ list_del(&domain->link);
+
+ /*
+ * If the going away domain is the default one, reset it.
+ */
+ if (unlikely(irq_default_domain == domain))
+ irq_set_default_host(NULL);
+
+ mutex_unlock(&irq_domain_mutex);
+
+ pr_debug("Removed domain of type %d @0x%p\n",
domain->revmap_type, domain);
+
+ irq_domain_free(domain);
}
+EXPORT_SYMBOL_GPL(irq_domain_remove);
static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain,
irq_hw_number_t hwirq)
@@ -117,8 +178,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
if (WARN_ON(!irq_data || irq_data->domain)) {
mutex_unlock(&irq_domain_mutex);
- of_node_put(domain->of_node);
- kfree(domain);
+ irq_domain_free(domain);
return NULL;
}
}
@@ -152,10 +212,12 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
irq_domain_add(domain);
return domain;
}
+EXPORT_SYMBOL_GPL(irq_domain_add_legacy);
/**
* irq_domain_add_linear() - Allocate and register a legacy revmap irq_domain.
* @of_node: pointer to interrupt controller's device tree node.
+ * @size: Number of interrupts in the domain.
* @ops: map/unmap domain callbacks
* @host_data: Controller private data pointer
*/
@@ -181,6 +243,7 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
irq_domain_add(domain);
return domain;
}
+EXPORT_SYMBOL_GPL(irq_domain_add_linear);
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
unsigned int max_irq,
@@ -195,6 +258,7 @@ struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
}
return domain;
}
+EXPORT_SYMBOL_GPL(irq_domain_add_nomap);
/**
* irq_domain_add_tree()
@@ -216,6 +280,7 @@ struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
}
return domain;
}
+EXPORT_SYMBOL_GPL(irq_domain_add_tree);
/**
* irq_find_host() - Locates a domain for a given device node
@@ -259,10 +324,11 @@ EXPORT_SYMBOL_GPL(irq_find_host);
*/
void irq_set_default_host(struct irq_domain *domain)
{
- pr_debug("irq: Default domain set to @0x%p\n", domain);
+ pr_debug("Default domain set to @0x%p\n", domain);
irq_default_domain = domain;
}
+EXPORT_SYMBOL_GPL(irq_set_default_host);
static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
irq_hw_number_t hwirq)
@@ -272,7 +338,7 @@ static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
irq_data->hwirq = hwirq;
irq_data->domain = domain;
if (domain->ops->map(domain, virq, hwirq)) {
- pr_debug("irq: -> mapping failed, freeing\n");
+ pr_debug("irq-%i==>hwirq-0x%lx mapping failed\n", virq, hwirq);
irq_data->domain = NULL;
irq_data->hwirq = 0;
return -1;
@@ -303,7 +369,7 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
virq = irq_alloc_desc_from(1, 0);
if (!virq) {
- pr_debug("irq: create_direct virq allocation failed\n");
+ pr_debug("create_direct virq allocation failed\n");
return 0;
}
if (virq >= domain->revmap_data.nomap.max_irq) {
@@ -312,7 +378,7 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
irq_free_desc(virq);
return 0;
}
- pr_debug("irq: create_direct obtained virq %d\n", virq);
+ pr_debug("create_direct obtained virq %d\n", virq);
if (irq_setup_virq(domain, virq, virq)) {
irq_free_desc(virq);
@@ -321,6 +387,7 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
return virq;
}
+EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
/**
* irq_create_mapping() - Map a hardware interrupt into linux irq space
@@ -338,23 +405,23 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
unsigned int hint;
int virq;
- pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
+ pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
/* Look for default domain if nececssary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL) {
- printk(KERN_WARNING "irq_create_mapping called for"
- " NULL domain, hwirq=%lx\n", hwirq);
+ pr_warning("irq_create_mapping called for"
+ " NULL domain, hwirq=%lx\n", hwirq);
WARN_ON(1);
return 0;
}
- pr_debug("irq: -> using domain @%p\n", domain);
+ pr_debug("-> using domain @%p\n", domain);
/* Check if mapping already exists */
virq = irq_find_mapping(domain, hwirq);
if (virq) {
- pr_debug("irq: -> existing mapping on virq %d\n", virq);
+ pr_debug("-> existing mapping on virq %d\n", virq);
return virq;
}
@@ -370,7 +437,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
if (virq <= 0)
virq = irq_alloc_desc_from(1, 0);
if (virq <= 0) {
- pr_debug("irq: -> virq allocation failed\n");
+ pr_debug("-> virq allocation failed\n");
return 0;
}
@@ -380,7 +447,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
return 0;
}
- pr_debug("irq: irq %lu on domain %s mapped to virtual irq %u\n",
+ pr_debug("irq %lu on domain %s mapped to virtual irq %u\n",
hwirq, domain->of_node ? domain->of_node->full_name : "null", virq);
return virq;
@@ -409,8 +476,8 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
if (intsize > 0)
return intspec[0];
#endif
- printk(KERN_WARNING "irq: no irq domain found for %s !\n",
- controller->full_name);
+ pr_warning("no irq domain found for %s !\n",
+ controller->full_name);
return 0;
}
@@ -560,6 +627,7 @@ unsigned int irq_radix_revmap_lookup(struct irq_domain *domain,
*/
return irq_data ? irq_data->irq : irq_find_mapping(domain, hwirq);
}
+EXPORT_SYMBOL_GPL(irq_radix_revmap_lookup);
/**
* irq_radix_revmap_insert() - Insert a hw irq to linux irq number mapping.
@@ -584,6 +652,7 @@ void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq,
mutex_unlock(&revmap_trees_mutex);
}
}
+EXPORT_SYMBOL_GPL(irq_radix_revmap_insert);
/**
* irq_linear_revmap() - Find a linux irq from a hw irq number.
@@ -617,6 +686,7 @@ unsigned int irq_linear_revmap(struct irq_domain *domain,
return revmap[hwirq];
}
+EXPORT_SYMBOL_GPL(irq_linear_revmap);
#ifdef CONFIG_IRQ_DOMAIN_DEBUG
static int virq_debug_show(struct seq_file *m, void *private)
@@ -691,8 +761,8 @@ static int __init irq_debugfs_init(void)
__initcall(irq_debugfs_init);
#endif /* CONFIG_IRQ_DOMAIN_DEBUG */
-int irq_domain_simple_map(struct irq_domain *d, unsigned int irq,
- irq_hw_number_t hwirq)
+static int irq_domain_simple_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hwirq)
{
return 0;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 585f6381f8e4..8c548232ba39 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -7,6 +7,8 @@
* This file contains driver APIs to the irq subsystem.
*/
+#define pr_fmt(fmt) "genirq: " fmt
+
#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/module.h>
@@ -14,6 +16,7 @@
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/sched.h>
+#include <linux/task_work.h>
#include "internals.h"
@@ -139,6 +142,25 @@ static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
#endif
+int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_desc *desc = irq_data_to_desc(data);
+ struct irq_chip *chip = irq_data_get_irq_chip(data);
+ int ret;
+
+ ret = chip->irq_set_affinity(data, mask, false);
+ switch (ret) {
+ case IRQ_SET_MASK_OK:
+ cpumask_copy(data->affinity, mask);
+ case IRQ_SET_MASK_OK_NOCOPY:
+ irq_set_thread_affinity(desc);
+ ret = 0;
+ }
+
+ return ret;
+}
+
int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
@@ -149,14 +171,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
return -EINVAL;
if (irq_can_move_pcntxt(data)) {
- ret = chip->irq_set_affinity(data, mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(data->affinity, mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- ret = 0;
- }
+ ret = irq_do_set_affinity(data, mask, false);
} else {
irqd_set_move_pending(data);
irq_copy_pending(desc, mask);
@@ -280,9 +295,8 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
static int
setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
{
- struct irq_chip *chip = irq_desc_get_chip(desc);
struct cpumask *set = irq_default_affinity;
- int ret, node = desc->irq_data.node;
+ int node = desc->irq_data.node;
/* Excludes PER_CPU and NO_BALANCE interrupts */
if (!irq_can_set_affinity(irq))
@@ -308,13 +322,7 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
if (cpumask_intersects(mask, nodemask))
cpumask_and(mask, mask, nodemask);
}
- ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(desc->irq_data.affinity, mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- }
+ irq_do_set_affinity(&desc->irq_data, mask, false);
return 0;
}
#else
@@ -565,7 +573,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
* IRQF_TRIGGER_* but the PIC does not support multiple
* flow-types?
*/
- pr_debug("genirq: No set_type function for IRQ %d (%s)\n", irq,
+ pr_debug("No set_type function for IRQ %d (%s)\n", irq,
chip ? (chip->name ? : "unknown") : "unknown");
return 0;
}
@@ -600,7 +608,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
ret = 0;
break;
default:
- pr_err("genirq: Setting trigger mode %lu for irq %u failed (%pF)\n",
+ pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n",
flags, irq, chip->irq_set_type);
}
if (unmask)
@@ -773,11 +781,39 @@ static void wake_threads_waitq(struct irq_desc *desc)
wake_up(&desc->wait_for_threads);
}
+static void irq_thread_dtor(struct task_work *unused)
+{
+ struct task_struct *tsk = current;
+ struct irq_desc *desc;
+ struct irqaction *action;
+
+ if (WARN_ON_ONCE(!(current->flags & PF_EXITING)))
+ return;
+
+ action = kthread_data(tsk);
+
+ pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
+ tsk->comm ? tsk->comm : "", tsk->pid, action->irq);
+
+
+ desc = irq_to_desc(action->irq);
+ /*
+ * If IRQTF_RUNTHREAD is set, we need to decrement
+ * desc->threads_active and wake possible waiters.
+ */
+ if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+ wake_threads_waitq(desc);
+
+ /* Prevent a stale desc->threads_oneshot */
+ irq_finalize_oneshot(desc, action);
+}
+
/*
* Interrupt handler thread
*/
static int irq_thread(void *data)
{
+ struct task_work on_exit_work;
static const struct sched_param param = {
.sched_priority = MAX_USER_RT_PRIO/2,
};
@@ -793,7 +829,9 @@ static int irq_thread(void *data)
handler_fn = irq_thread_fn;
sched_setscheduler(current, SCHED_FIFO, &param);
- current->irq_thread = 1;
+
+ init_task_work(&on_exit_work, irq_thread_dtor, NULL);
+ task_work_add(current, &on_exit_work, false);
while (!irq_wait_for_interrupt(action)) {
irqreturn_t action_ret;
@@ -815,44 +853,11 @@ static int irq_thread(void *data)
* cannot touch the oneshot mask at this point anymore as
* __setup_irq() might have given out currents thread_mask
* again.
- *
- * Clear irq_thread. Otherwise exit_irq_thread() would make
- * fuzz about an active irq thread going into nirvana.
*/
- current->irq_thread = 0;
+ task_work_cancel(current, irq_thread_dtor);
return 0;
}
-/*
- * Called from do_exit()
- */
-void exit_irq_thread(void)
-{
- struct task_struct *tsk = current;
- struct irq_desc *desc;
- struct irqaction *action;
-
- if (!tsk->irq_thread)
- return;
-
- action = kthread_data(tsk);
-
- pr_err("genirq: exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
- tsk->comm ? tsk->comm : "", tsk->pid, action->irq);
-
- desc = irq_to_desc(action->irq);
-
- /*
- * If IRQTF_RUNTHREAD is set, we need to decrement
- * desc->threads_active and wake possible waiters.
- */
- if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
- wake_threads_waitq(desc);
-
- /* Prevent a stale desc->threads_oneshot */
- irq_finalize_oneshot(desc, action);
-}
-
static void irq_setup_forced_threading(struct irqaction *new)
{
if (!force_irqthreads)
@@ -1044,7 +1049,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
* has. The type flags are unreliable as the
* underlying chip implementation can override them.
*/
- pr_err("genirq: Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
+ pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
irq);
ret = -EINVAL;
goto out_mask;
@@ -1095,7 +1100,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
if (nmsk != omsk)
/* hope the handler works with current trigger mode */
- pr_warning("genirq: irq %d uses trigger mode %u; requested %u\n",
+ pr_warning("irq %d uses trigger mode %u; requested %u\n",
irq, nmsk, omsk);
}
@@ -1133,7 +1138,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
mismatch:
if (!(new->flags & IRQF_PROBE_SHARED)) {
- pr_err("genirq: Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
+ pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
irq, new->flags, new->name, old->flags, old->name);
#ifdef CONFIG_DEBUG_SHIRQ
dump_stack();
@@ -1220,12 +1225,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
/* Found it - now remove it from the list of entries: */
*action_ptr = action->next;
- /* Currently used only by UML, might disappear one day: */
-#ifdef CONFIG_IRQ_RELEASE_METHOD
- if (desc->irq_data.chip->release)
- desc->irq_data.chip->release(irq, dev_id);
-#endif
-
/* If this was the last handler, shut down the IRQ line: */
if (!desc->action)
irq_shutdown(desc);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index c3c89751b327..ca3f4aaff707 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -42,17 +42,8 @@ void irq_move_masked_irq(struct irq_data *idata)
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
- < nr_cpu_ids)) {
- int ret = chip->irq_set_affinity(&desc->irq_data,
- desc->pending_mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- }
- }
+ if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
+ irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
cpumask_clear(desc->pending_mask);
}
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 079f1d39a8b8..2169feeba529 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -343,7 +343,7 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
/* Look up a kernel symbol and return it in a text buffer. */
static int __sprint_symbol(char *buffer, unsigned long address,
- int symbol_offset)
+ int symbol_offset, int add_offset)
{
char *modname;
const char *name;
@@ -358,13 +358,13 @@ static int __sprint_symbol(char *buffer, unsigned long address,
if (name != buffer)
strcpy(buffer, name);
len = strlen(buffer);
- buffer += len;
offset -= symbol_offset;
+ if (add_offset)
+ len += sprintf(buffer + len, "+%#lx/%#lx", offset, size);
+
if (modname)
- len += sprintf(buffer, "+%#lx/%#lx [%s]", offset, size, modname);
- else
- len += sprintf(buffer, "+%#lx/%#lx", offset, size);
+ len += sprintf(buffer + len, " [%s]", modname);
return len;
}
@@ -382,12 +382,28 @@ static int __sprint_symbol(char *buffer, unsigned long address,
*/
int sprint_symbol(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, 0);
+ return __sprint_symbol(buffer, address, 0, 1);
}
-
EXPORT_SYMBOL_GPL(sprint_symbol);
/**
+ * sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer
+ * @buffer: buffer to be stored
+ * @address: address to lookup
+ *
+ * This function looks up a kernel symbol with @address and stores its name
+ * and module name to @buffer if possible. If no symbol was found, just saves
+ * its @address as is.
+ *
+ * This function returns the number of bytes stored in @buffer.
+ */
+int sprint_symbol_no_offset(char *buffer, unsigned long address)
+{
+ return __sprint_symbol(buffer, address, 0, 0);
+}
+EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
+
+/**
* sprint_backtrace - Look up a backtrace symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
@@ -403,7 +419,7 @@ EXPORT_SYMBOL_GPL(sprint_symbol);
*/
int sprint_backtrace(char *buffer, unsigned long address)
{
- return __sprint_symbol(buffer, address, -1);
+ return __sprint_symbol(buffer, address, -1, 1);
}
/* Look up a kernel symbol and print it to the kernel messages. */
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
new file mode 100644
index 000000000000..30b7b225306c
--- /dev/null
+++ b/kernel/kcmp.c
@@ -0,0 +1,196 @@
+#include <linux/kernel.h>
+#include <linux/syscalls.h>
+#include <linux/fdtable.h>
+#include <linux/string.h>
+#include <linux/random.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/cache.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <linux/kcmp.h>
+
+#include <asm/unistd.h>
+
+/*
+ * We don't expose the real in-memory order of objects for security reasons.
+ * But still the comparison results should be suitable for sorting. So we
+ * obfuscate kernel pointers values and compare the production instead.
+ *
+ * The obfuscation is done in two steps. First we xor the kernel pointer with
+ * a random value, which puts pointer into a new position in a reordered space.
+ * Secondly we multiply the xor production with a large odd random number to
+ * permute its bits even more (the odd multiplier guarantees that the product
+ * is unique ever after the high bits are truncated, since any odd number is
+ * relative prime to 2^n).
+ *
+ * Note also that the obfuscation itself is invisible to userspace and if needed
+ * it can be changed to an alternate scheme.
+ */
+static unsigned long cookies[KCMP_TYPES][2] __read_mostly;
+
+static long kptr_obfuscate(long v, int type)
+{
+ return (v ^ cookies[type][0]) * cookies[type][1];
+}
+
+/*
+ * 0 - equal, i.e. v1 = v2
+ * 1 - less than, i.e. v1 < v2
+ * 2 - greater than, i.e. v1 > v2
+ * 3 - not equal but ordering unavailable (reserved for future)
+ */
+static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
+{
+ long ret;
+
+ ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+
+ return (ret < 0) | ((ret > 0) << 1);
+}
+
+/* The caller must have pinned the task */
+static struct file *
+get_file_raw_ptr(struct task_struct *task, unsigned int idx)
+{
+ struct file *file = NULL;
+
+ task_lock(task);
+ rcu_read_lock();
+
+ if (task->files)
+ file = fcheck_files(task->files, idx);
+
+ rcu_read_unlock();
+ task_unlock(task);
+
+ return file;
+}
+
+static void kcmp_unlock(struct mutex *m1, struct mutex *m2)
+{
+ if (likely(m2 != m1))
+ mutex_unlock(m2);
+ mutex_unlock(m1);
+}
+
+static int kcmp_lock(struct mutex *m1, struct mutex *m2)
+{
+ int err;
+
+ if (m2 > m1)
+ swap(m1, m2);
+
+ err = mutex_lock_killable(m1);
+ if (!err && likely(m1 != m2)) {
+ err = mutex_lock_killable_nested(m2, SINGLE_DEPTH_NESTING);
+ if (err)
+ mutex_unlock(m1);
+ }
+
+ return err;
+}
+
+SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
+ unsigned long, idx1, unsigned long, idx2)
+{
+ struct task_struct *task1, *task2;
+ int ret;
+
+ rcu_read_lock();
+
+ /*
+ * Tasks are looked up in caller's PID namespace only.
+ */
+ task1 = find_task_by_vpid(pid1);
+ task2 = find_task_by_vpid(pid2);
+ if (!task1 || !task2)
+ goto err_no_task;
+
+ get_task_struct(task1);
+ get_task_struct(task2);
+
+ rcu_read_unlock();
+
+ /*
+ * One should have enough rights to inspect task details.
+ */
+ ret = kcmp_lock(&task1->signal->cred_guard_mutex,
+ &task2->signal->cred_guard_mutex);
+ if (ret)
+ goto err;
+ if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
+ !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+ ret = -EPERM;
+ goto err_unlock;
+ }
+
+ switch (type) {
+ case KCMP_FILE: {
+ struct file *filp1, *filp2;
+
+ filp1 = get_file_raw_ptr(task1, idx1);
+ filp2 = get_file_raw_ptr(task2, idx2);
+
+ if (filp1 && filp2)
+ ret = kcmp_ptr(filp1, filp2, KCMP_FILE);
+ else
+ ret = -EBADF;
+ break;
+ }
+ case KCMP_VM:
+ ret = kcmp_ptr(task1->mm, task2->mm, KCMP_VM);
+ break;
+ case KCMP_FILES:
+ ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
+ break;
+ case KCMP_FS:
+ ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
+ break;
+ case KCMP_SIGHAND:
+ ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
+ break;
+ case KCMP_IO:
+ ret = kcmp_ptr(task1->io_context, task2->io_context, KCMP_IO);
+ break;
+ case KCMP_SYSVSEM:
+#ifdef CONFIG_SYSVIPC
+ ret = kcmp_ptr(task1->sysvsem.undo_list,
+ task2->sysvsem.undo_list,
+ KCMP_SYSVSEM);
+#else
+ ret = -EOPNOTSUPP;
+#endif
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+err_unlock:
+ kcmp_unlock(&task1->signal->cred_guard_mutex,
+ &task2->signal->cred_guard_mutex);
+err:
+ put_task_struct(task1);
+ put_task_struct(task2);
+
+ return ret;
+
+err_no_task:
+ rcu_read_unlock();
+ return -ESRCH;
+}
+
+static __init int kcmp_cookies_init(void)
+{
+ int i;
+
+ get_random_bytes(cookies, sizeof(cookies));
+
+ for (i = 0; i < KCMP_TYPES; i++)
+ cookies[i][1] |= (~(~0UL >> 1) | 1);
+
+ return 0;
+}
+arch_initcall(kcmp_cookies_init);
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index c744b88c44e2..59dcf5b81d24 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -402,6 +402,7 @@ unsigned int __kfifo_max_r(unsigned int len, size_t recsize)
return max;
return len;
}
+EXPORT_SYMBOL(__kfifo_max_r);
#define __KFIFO_PEEK(data, out, mask) \
((data)[(out) & (mask)])
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 05698a7415fe..ff2c7cb86d77 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -221,13 +221,12 @@ fail:
return 0;
}
-void call_usermodehelper_freeinfo(struct subprocess_info *info)
+static void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
if (info->cleanup)
(*info->cleanup)(info);
kfree(info);
}
-EXPORT_SYMBOL(call_usermodehelper_freeinfo);
static void umh_complete(struct subprocess_info *sub_info)
{
@@ -410,7 +409,7 @@ EXPORT_SYMBOL_GPL(usermodehelper_read_unlock);
/**
* __usermodehelper_set_disable_depth - Modify usermodehelper_disabled.
- * depth: New value to assign to usermodehelper_disabled.
+ * @depth: New value to assign to usermodehelper_disabled.
*
* Change the value of usermodehelper_disabled (under umhelper_sem locked for
* writing) and wakeup tasks waiting for it to change.
@@ -479,6 +478,7 @@ static void helper_unlock(void)
* structure. This should be passed to call_usermodehelper_exec to
* exec the process and free the structure.
*/
+static
struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
char **envp, gfp_t gfp_mask)
{
@@ -494,7 +494,6 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
out:
return sub_info;
}
-EXPORT_SYMBOL(call_usermodehelper_setup);
/**
* call_usermodehelper_setfns - set a cleanup/init function
@@ -512,6 +511,7 @@ EXPORT_SYMBOL(call_usermodehelper_setup);
* Function must be runnable in either a process context or the
* context in which call_usermodehelper_exec is called.
*/
+static
void call_usermodehelper_setfns(struct subprocess_info *info,
int (*init)(struct subprocess_info *info, struct cred *new),
void (*cleanup)(struct subprocess_info *info),
@@ -521,7 +521,6 @@ void call_usermodehelper_setfns(struct subprocess_info *info,
info->init = init;
info->data = data;
}
-EXPORT_SYMBOL(call_usermodehelper_setfns);
/**
* call_usermodehelper_exec - start a usermode application
@@ -535,6 +534,7 @@ EXPORT_SYMBOL(call_usermodehelper_setfns);
* asynchronously if wait is not set, and runs as a child of keventd.
* (ie. it runs with full root capabilities).
*/
+static
int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
{
DECLARE_COMPLETION_ONSTACK(done);
@@ -576,7 +576,25 @@ unlock:
helper_unlock();
return retval;
}
-EXPORT_SYMBOL(call_usermodehelper_exec);
+
+int call_usermodehelper_fns(
+ char *path, char **argv, char **envp, int wait,
+ int (*init)(struct subprocess_info *info, struct cred *new),
+ void (*cleanup)(struct subprocess_info *), void *data)
+{
+ struct subprocess_info *info;
+ gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL;
+
+ info = call_usermodehelper_setup(path, argv, envp, gfp_mask);
+
+ if (info == NULL)
+ return -ENOMEM;
+
+ call_usermodehelper_setfns(info, init, cleanup, data);
+
+ return call_usermodehelper_exec(info, wait);
+}
+EXPORT_SYMBOL(call_usermodehelper_fns);
static int proc_cap_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
diff --git a/kernel/lglock.c b/kernel/lglock.c
new file mode 100644
index 000000000000..6535a667a5a7
--- /dev/null
+++ b/kernel/lglock.c
@@ -0,0 +1,89 @@
+/* See include/linux/lglock.h for description */
+#include <linux/module.h>
+#include <linux/lglock.h>
+#include <linux/cpu.h>
+#include <linux/string.h>
+
+/*
+ * Note there is no uninit, so lglocks cannot be defined in
+ * modules (but it's fine to use them from there)
+ * Could be added though, just undo lg_lock_init
+ */
+
+void lg_lock_init(struct lglock *lg, char *name)
+{
+ LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0);
+}
+EXPORT_SYMBOL(lg_lock_init);
+
+void lg_local_lock(struct lglock *lg)
+{
+ arch_spinlock_t *lock;
+
+ preempt_disable();
+ rwlock_acquire_read(&lg->lock_dep_map, 0, 0, _RET_IP_);
+ lock = this_cpu_ptr(lg->lock);
+ arch_spin_lock(lock);
+}
+EXPORT_SYMBOL(lg_local_lock);
+
+void lg_local_unlock(struct lglock *lg)
+{
+ arch_spinlock_t *lock;
+
+ rwlock_release(&lg->lock_dep_map, 1, _RET_IP_);
+ lock = this_cpu_ptr(lg->lock);
+ arch_spin_unlock(lock);
+ preempt_enable();
+}
+EXPORT_SYMBOL(lg_local_unlock);
+
+void lg_local_lock_cpu(struct lglock *lg, int cpu)
+{
+ arch_spinlock_t *lock;
+
+ preempt_disable();
+ rwlock_acquire_read(&lg->lock_dep_map, 0, 0, _RET_IP_);
+ lock = per_cpu_ptr(lg->lock, cpu);
+ arch_spin_lock(lock);
+}
+EXPORT_SYMBOL(lg_local_lock_cpu);
+
+void lg_local_unlock_cpu(struct lglock *lg, int cpu)
+{
+ arch_spinlock_t *lock;
+
+ rwlock_release(&lg->lock_dep_map, 1, _RET_IP_);
+ lock = per_cpu_ptr(lg->lock, cpu);
+ arch_spin_unlock(lock);
+ preempt_enable();
+}
+EXPORT_SYMBOL(lg_local_unlock_cpu);
+
+void lg_global_lock(struct lglock *lg)
+{
+ int i;
+
+ preempt_disable();
+ rwlock_acquire(&lg->lock_dep_map, 0, 0, _RET_IP_);
+ for_each_possible_cpu(i) {
+ arch_spinlock_t *lock;
+ lock = per_cpu_ptr(lg->lock, i);
+ arch_spin_lock(lock);
+ }
+}
+EXPORT_SYMBOL(lg_global_lock);
+
+void lg_global_unlock(struct lglock *lg)
+{
+ int i;
+
+ rwlock_release(&lg->lock_dep_map, 1, _RET_IP_);
+ for_each_possible_cpu(i) {
+ arch_spinlock_t *lock;
+ lock = per_cpu_ptr(lg->lock, i);
+ arch_spin_unlock(lock);
+ }
+ preempt_enable();
+}
+EXPORT_SYMBOL(lg_global_unlock);
diff --git a/kernel/module.c b/kernel/module.c
index a4e60973ca73..4edbd9c11aca 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2429,7 +2429,8 @@ static int copy_and_check(struct load_info *info,
goto free_hdr;
}
- if (len < hdr->e_shoff + hdr->e_shnum * sizeof(Elf_Shdr)) {
+ if (hdr->e_shoff >= len ||
+ hdr->e_shnum * sizeof(Elf_Shdr) > len - hdr->e_shoff) {
err = -ENOEXEC;
goto free_hdr;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index 8ed89a175d79..d2a5f4ecc6dd 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -27,7 +27,7 @@
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
-int panic_on_oops;
+int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
static unsigned long tainted_mask;
static int pause_on_oops;
static int pause_on_oops_flag;
@@ -108,8 +108,6 @@ void panic(const char *fmt, ...)
*/
crash_kexec(NULL);
- kmsg_dump(KMSG_DUMP_PANIC);
-
/*
* Note smp_send_stop is the usual smp shutdown function, which
* unfortunately means it may not be hardened to work in a panic
@@ -117,6 +115,8 @@ void panic(const char *fmt, ...)
*/
smp_send_stop();
+ kmsg_dump(KMSG_DUMP_PANIC);
+
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
bust_spinlocks(0);
diff --git a/kernel/pid.c b/kernel/pid.c
index 9f08dfabaf13..e86b291ad834 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -547,7 +547,8 @@ void __init pidhash_init(void)
pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
HASH_EARLY | HASH_SMALL,
- &pidhash_shift, NULL, 4096);
+ &pidhash_shift, NULL,
+ 0, 4096);
pidhash_size = 1U << pidhash_shift;
for (i = 0; i < pidhash_size; i++)
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 57bc1fd35b3c..b3c7fd554250 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -149,7 +149,12 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
{
int nr;
int rc;
- struct task_struct *task;
+ struct task_struct *task, *me = current;
+
+ /* Ignore SIGCHLD causing any terminated children to autoreap */
+ spin_lock_irq(&me->sighand->siglock);
+ me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
+ spin_unlock_irq(&me->sighand->siglock);
/*
* The last thread in the cgroup-init thread group is terminating.
@@ -179,11 +184,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
}
read_unlock(&tasklist_lock);
+ /* Firstly reap the EXIT_ZOMBIE children we may have. */
do {
clear_thread_flag(TIF_SIGPENDING);
rc = sys_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
+ /*
+ * sys_wait4() above can't reap the TASK_DEAD children.
+ * Make sure they all go away, see __unhash_process().
+ */
+ for (;;) {
+ bool need_wait = false;
+
+ read_lock(&tasklist_lock);
+ if (!list_empty(&current->children)) {
+ __set_current_state(TASK_UNINTERRUPTIBLE);
+ need_wait = true;
+ }
+ read_unlock(&tasklist_lock);
+
+ if (!need_wait)
+ break;
+ schedule();
+ }
+
if (pid_ns->reboot)
current->signal->group_exit_code = pid_ns->reboot;
@@ -191,6 +216,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
return;
}
+#ifdef CONFIG_CHECKPOINT_RESTORE
static int pid_ns_ctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -218,8 +244,8 @@ static struct ctl_table pid_ns_ctl_table[] = {
},
{ }
};
-
static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
+#endif /* CONFIG_CHECKPOINT_RESTORE */
int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
{
@@ -253,7 +279,10 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
static __init int pid_namespaces_init(void)
{
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
+#endif
return 0;
}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index deb5461e3216..8f9b4eb974e0 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -103,6 +103,33 @@ config PM_SLEEP_SMP
select HOTPLUG
select HOTPLUG_CPU
+config PM_AUTOSLEEP
+ bool "Opportunistic sleep"
+ depends on PM_SLEEP
+ default n
+ ---help---
+ Allow the kernel to trigger a system transition into a global sleep
+ state automatically whenever there are no active wakeup sources.
+
+config PM_WAKELOCKS
+ bool "User space wakeup sources interface"
+ depends on PM_SLEEP
+ default n
+ ---help---
+ Allow user space to create, activate and deactivate wakeup source
+ objects with the help of a sysfs-based interface.
+
+config PM_WAKELOCKS_LIMIT
+ int "Maximum number of user space wakeup sources (0 = no limit)"
+ range 0 100000
+ default 100
+ depends on PM_WAKELOCKS
+
+config PM_WAKELOCKS_GC
+ bool "Garbage collector for user space wakeup sources"
+ depends on PM_WAKELOCKS
+ default y
+
config PM_RUNTIME
bool "Run-time PM core functionality"
depends on !IA64_HP_SIM
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 66d808ec5252..29472bff11ef 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -9,5 +9,7 @@ obj-$(CONFIG_SUSPEND) += suspend.o
obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o
obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o \
block_io.o
+obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o
+obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c
new file mode 100644
index 000000000000..ca304046d9e2
--- /dev/null
+++ b/kernel/power/autosleep.c
@@ -0,0 +1,127 @@
+/*
+ * kernel/power/autosleep.c
+ *
+ * Opportunistic sleep support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/pm_wakeup.h>
+
+#include "power.h"
+
+static suspend_state_t autosleep_state;
+static struct workqueue_struct *autosleep_wq;
+/*
+ * Note: it is only safe to mutex_lock(&autosleep_lock) if a wakeup_source
+ * is active, otherwise a deadlock with try_to_suspend() is possible.
+ * Alternatively mutex_lock_interruptible() can be used. This will then fail
+ * if an auto_sleep cycle tries to freeze processes.
+ */
+static DEFINE_MUTEX(autosleep_lock);
+static struct wakeup_source *autosleep_ws;
+
+static void try_to_suspend(struct work_struct *work)
+{
+ unsigned int initial_count, final_count;
+
+ if (!pm_get_wakeup_count(&initial_count, true))
+ goto out;
+
+ mutex_lock(&autosleep_lock);
+
+ if (!pm_save_wakeup_count(initial_count)) {
+ mutex_unlock(&autosleep_lock);
+ goto out;
+ }
+
+ if (autosleep_state == PM_SUSPEND_ON) {
+ mutex_unlock(&autosleep_lock);
+ return;
+ }
+ if (autosleep_state >= PM_SUSPEND_MAX)
+ hibernate();
+ else
+ pm_suspend(autosleep_state);
+
+ mutex_unlock(&autosleep_lock);
+
+ if (!pm_get_wakeup_count(&final_count, false))
+ goto out;
+
+ /*
+ * If the wakeup occured for an unknown reason, wait to prevent the
+ * system from trying to suspend and waking up in a tight loop.
+ */
+ if (final_count == initial_count)
+ schedule_timeout_uninterruptible(HZ / 2);
+
+ out:
+ queue_up_suspend_work();
+}
+
+static DECLARE_WORK(suspend_work, try_to_suspend);
+
+void queue_up_suspend_work(void)
+{
+ if (!work_pending(&suspend_work) && autosleep_state > PM_SUSPEND_ON)
+ queue_work(autosleep_wq, &suspend_work);
+}
+
+suspend_state_t pm_autosleep_state(void)
+{
+ return autosleep_state;
+}
+
+int pm_autosleep_lock(void)
+{
+ return mutex_lock_interruptible(&autosleep_lock);
+}
+
+void pm_autosleep_unlock(void)
+{
+ mutex_unlock(&autosleep_lock);
+}
+
+int pm_autosleep_set_state(suspend_state_t state)
+{
+
+#ifndef CONFIG_HIBERNATION
+ if (state >= PM_SUSPEND_MAX)
+ return -EINVAL;
+#endif
+
+ __pm_stay_awake(autosleep_ws);
+
+ mutex_lock(&autosleep_lock);
+
+ autosleep_state = state;
+
+ __pm_relax(autosleep_ws);
+
+ if (state > PM_SUSPEND_ON) {
+ pm_wakep_autosleep_enabled(true);
+ queue_up_suspend_work();
+ } else {
+ pm_wakep_autosleep_enabled(false);
+ }
+
+ mutex_unlock(&autosleep_lock);
+ return 0;
+}
+
+int __init pm_autosleep_init(void)
+{
+ autosleep_ws = wakeup_source_register("autosleep");
+ if (!autosleep_ws)
+ return -ENOMEM;
+
+ autosleep_wq = alloc_ordered_workqueue("autosleep", 0);
+ if (autosleep_wq)
+ return 0;
+
+ wakeup_source_unregister(autosleep_ws);
+ return -ENOMEM;
+}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index e09dfbfeecee..238025f5472e 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -25,7 +25,8 @@
#include <linux/freezer.h>
#include <linux/gfp.h>
#include <linux/syscore_ops.h>
-#include <scsi/scsi_scan.h>
+#include <linux/ctype.h>
+#include <linux/genhd.h>
#include "power.h"
@@ -722,6 +723,17 @@ static int software_resume(void)
/* Check if the device is there */
swsusp_resume_device = name_to_dev_t(resume_file);
+
+ /*
+ * name_to_dev_t is ineffective to verify parition if resume_file is in
+ * integer format. (e.g. major:minor)
+ */
+ if (isdigit(resume_file[0]) && resume_wait) {
+ int partno;
+ while (!get_gendisk(swsusp_resume_device, &partno))
+ msleep(10);
+ }
+
if (!swsusp_resume_device) {
/*
* Some device discovery might still be in progress; we need
@@ -735,13 +747,6 @@ static int software_resume(void)
async_synchronize_full();
}
- /*
- * We can't depend on SCSI devices being available after loading
- * one of their modules until scsi_complete_async_scans() is
- * called and the resume device usually is a SCSI one.
- */
- scsi_complete_async_scans();
-
swsusp_resume_device = name_to_dev_t(resume_file);
if (!swsusp_resume_device) {
error = -ENODEV;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 1c12581f1c62..428f8a034e96 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -269,8 +269,7 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
return (s - buf);
}
-static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
- const char *buf, size_t n)
+static suspend_state_t decode_state(const char *buf, size_t n)
{
#ifdef CONFIG_SUSPEND
suspend_state_t state = PM_SUSPEND_STANDBY;
@@ -278,27 +277,48 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
#endif
char *p;
int len;
- int error = -EINVAL;
p = memchr(buf, '\n', n);
len = p ? p - buf : n;
- /* First, check if we are requested to hibernate */
- if (len == 4 && !strncmp(buf, "disk", len)) {
- error = hibernate();
- goto Exit;
- }
+ /* Check hibernation first. */
+ if (len == 4 && !strncmp(buf, "disk", len))
+ return PM_SUSPEND_MAX;
#ifdef CONFIG_SUSPEND
- for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) {
- if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) {
- error = pm_suspend(state);
- break;
- }
- }
+ for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++)
+ if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
+ return state;
#endif
- Exit:
+ return PM_SUSPEND_ON;
+}
+
+static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ suspend_state_t state;
+ int error;
+
+ error = pm_autosleep_lock();
+ if (error)
+ return error;
+
+ if (pm_autosleep_state() > PM_SUSPEND_ON) {
+ error = -EBUSY;
+ goto out;
+ }
+
+ state = decode_state(buf, n);
+ if (state < PM_SUSPEND_MAX)
+ error = pm_suspend(state);
+ else if (state == PM_SUSPEND_MAX)
+ error = hibernate();
+ else
+ error = -EINVAL;
+
+ out:
+ pm_autosleep_unlock();
return error ? error : n;
}
@@ -339,7 +359,8 @@ static ssize_t wakeup_count_show(struct kobject *kobj,
{
unsigned int val;
- return pm_get_wakeup_count(&val) ? sprintf(buf, "%u\n", val) : -EINTR;
+ return pm_get_wakeup_count(&val, true) ?
+ sprintf(buf, "%u\n", val) : -EINTR;
}
static ssize_t wakeup_count_store(struct kobject *kobj,
@@ -347,15 +368,106 @@ static ssize_t wakeup_count_store(struct kobject *kobj,
const char *buf, size_t n)
{
unsigned int val;
+ int error;
+
+ error = pm_autosleep_lock();
+ if (error)
+ return error;
+
+ if (pm_autosleep_state() > PM_SUSPEND_ON) {
+ error = -EBUSY;
+ goto out;
+ }
+ error = -EINVAL;
if (sscanf(buf, "%u", &val) == 1) {
if (pm_save_wakeup_count(val))
- return n;
+ error = n;
}
- return -EINVAL;
+
+ out:
+ pm_autosleep_unlock();
+ return error;
}
power_attr(wakeup_count);
+
+#ifdef CONFIG_PM_AUTOSLEEP
+static ssize_t autosleep_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ suspend_state_t state = pm_autosleep_state();
+
+ if (state == PM_SUSPEND_ON)
+ return sprintf(buf, "off\n");
+
+#ifdef CONFIG_SUSPEND
+ if (state < PM_SUSPEND_MAX)
+ return sprintf(buf, "%s\n", valid_state(state) ?
+ pm_states[state] : "error");
+#endif
+#ifdef CONFIG_HIBERNATION
+ return sprintf(buf, "disk\n");
+#else
+ return sprintf(buf, "error");
+#endif
+}
+
+static ssize_t autosleep_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ suspend_state_t state = decode_state(buf, n);
+ int error;
+
+ if (state == PM_SUSPEND_ON
+ && strcmp(buf, "off") && strcmp(buf, "off\n"))
+ return -EINVAL;
+
+ error = pm_autosleep_set_state(state);
+ return error ? error : n;
+}
+
+power_attr(autosleep);
+#endif /* CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+static ssize_t wake_lock_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return pm_show_wakelocks(buf, true);
+}
+
+static ssize_t wake_lock_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ int error = pm_wake_lock(buf);
+ return error ? error : n;
+}
+
+power_attr(wake_lock);
+
+static ssize_t wake_unlock_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return pm_show_wakelocks(buf, false);
+}
+
+static ssize_t wake_unlock_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t n)
+{
+ int error = pm_wake_unlock(buf);
+ return error ? error : n;
+}
+
+power_attr(wake_unlock);
+
+#endif /* CONFIG_PM_WAKELOCKS */
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_PM_TRACE
@@ -409,6 +521,13 @@ static struct attribute * g[] = {
#ifdef CONFIG_PM_SLEEP
&pm_async_attr.attr,
&wakeup_count_attr.attr,
+#ifdef CONFIG_PM_AUTOSLEEP
+ &autosleep_attr.attr,
+#endif
+#ifdef CONFIG_PM_WAKELOCKS
+ &wake_lock_attr.attr,
+ &wake_unlock_attr.attr,
+#endif
#ifdef CONFIG_PM_DEBUG
&pm_test_attr.attr,
#endif
@@ -444,7 +563,10 @@ static int __init pm_init(void)
power_kobj = kobject_create_and_add("power", NULL);
if (!power_kobj)
return -ENOMEM;
- return sysfs_create_group(power_kobj, &attr_group);
+ error = sysfs_create_group(power_kobj, &attr_group);
+ if (error)
+ return error;
+ return pm_autosleep_init();
}
core_initcall(pm_init);
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 98f3622d7407..b0bd4beaebfe 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -264,3 +264,30 @@ static inline void suspend_thaw_processes(void)
{
}
#endif
+
+#ifdef CONFIG_PM_AUTOSLEEP
+
+/* kernel/power/autosleep.c */
+extern int pm_autosleep_init(void);
+extern int pm_autosleep_lock(void);
+extern void pm_autosleep_unlock(void);
+extern suspend_state_t pm_autosleep_state(void);
+extern int pm_autosleep_set_state(suspend_state_t state);
+
+#else /* !CONFIG_PM_AUTOSLEEP */
+
+static inline int pm_autosleep_init(void) { return 0; }
+static inline int pm_autosleep_lock(void) { return 0; }
+static inline void pm_autosleep_unlock(void) {}
+static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; }
+
+#endif /* !CONFIG_PM_AUTOSLEEP */
+
+#ifdef CONFIG_PM_WAKELOCKS
+
+/* kernel/power/wakelock.c */
+extern ssize_t pm_show_wakelocks(char *buf, bool show_active);
+extern int pm_wake_lock(const char *buf);
+extern int pm_wake_unlock(const char *buf);
+
+#endif /* !CONFIG_PM_WAKELOCKS */
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index eef311a58a64..11e22c068e8b 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -6,7 +6,7 @@
*
* Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
* Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
+ * Copyright (C) 2010-2012 Bojan Smojver <bojan@rexursive.com>
*
* This file is released under the GPLv2.
*
@@ -282,14 +282,17 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
return -ENOSPC;
if (bio_chain) {
- src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+ src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN |
+ __GFP_NORETRY);
if (src) {
copy_page(src, buf);
} else {
ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
if (ret)
return ret;
- src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+ src = (void *)__get_free_page(__GFP_WAIT |
+ __GFP_NOWARN |
+ __GFP_NORETRY);
if (src) {
copy_page(src, buf);
} else {
@@ -367,12 +370,17 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
clear_page(handle->cur);
handle->cur_swap = offset;
handle->k = 0;
- }
- if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
- error = hib_wait_on_bio_chain(bio_chain);
- if (error)
- goto out;
- handle->reqd_free_pages = reqd_free_pages();
+
+ if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
+ error = hib_wait_on_bio_chain(bio_chain);
+ if (error)
+ goto out;
+ /*
+ * Recalculate the number of required free pages, to
+ * make sure we never take more than half.
+ */
+ handle->reqd_free_pages = reqd_free_pages();
+ }
}
out:
return error;
@@ -419,8 +427,9 @@ static int swap_writer_finish(struct swap_map_handle *handle,
/* Maximum number of threads for compression/decompression. */
#define LZO_THREADS 3
-/* Maximum number of pages for read buffering. */
-#define LZO_READ_PAGES (MAP_PAGE_ENTRIES * 8)
+/* Minimum/maximum number of pages for read buffering. */
+#define LZO_MIN_RD_PAGES 1024
+#define LZO_MAX_RD_PAGES 8192
/**
@@ -631,12 +640,6 @@ static int save_image_lzo(struct swap_map_handle *handle,
}
/*
- * Adjust number of free pages after all allocations have been done.
- * We don't want to run out of pages when writing.
- */
- handle->reqd_free_pages = reqd_free_pages();
-
- /*
* Start the CRC32 thread.
*/
init_waitqueue_head(&crc->go);
@@ -657,6 +660,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
goto out_clean;
}
+ /*
+ * Adjust the number of required free pages after all allocations have
+ * been done. We don't want to run out of pages when writing.
+ */
+ handle->reqd_free_pages = reqd_free_pages();
+
printk(KERN_INFO
"PM: Using %u thread(s) for compression.\n"
"PM: Compressing and saving image data (%u pages) ... ",
@@ -1067,7 +1076,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
unsigned i, thr, run_threads, nr_threads;
unsigned ring = 0, pg = 0, ring_size = 0,
have = 0, want, need, asked = 0;
- unsigned long read_pages;
+ unsigned long read_pages = 0;
unsigned char **page = NULL;
struct dec_data *data = NULL;
struct crc_data *crc = NULL;
@@ -1079,7 +1088,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
nr_threads = num_online_cpus() - 1;
nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
- page = vmalloc(sizeof(*page) * LZO_READ_PAGES);
+ page = vmalloc(sizeof(*page) * LZO_MAX_RD_PAGES);
if (!page) {
printk(KERN_ERR "PM: Failed to allocate LZO page\n");
ret = -ENOMEM;
@@ -1144,15 +1153,22 @@ static int load_image_lzo(struct swap_map_handle *handle,
}
/*
- * Adjust number of pages for read buffering, in case we are short.
+ * Set the number of pages for read buffering.
+ * This is complete guesswork, because we'll only know the real
+ * picture once prepare_image() is called, which is much later on
+ * during the image load phase. We'll assume the worst case and
+ * say that none of the image pages are from high memory.
*/
- read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1;
- read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES);
+ if (low_free_pages() > snapshot_get_image_size())
+ read_pages = (low_free_pages() - snapshot_get_image_size()) / 2;
+ read_pages = clamp_val(read_pages, LZO_MIN_RD_PAGES, LZO_MAX_RD_PAGES);
for (i = 0; i < read_pages; i++) {
page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
__GFP_WAIT | __GFP_HIGH :
- __GFP_WAIT);
+ __GFP_WAIT | __GFP_NOWARN |
+ __GFP_NORETRY);
+
if (!page[i]) {
if (i < LZO_CMP_PAGES) {
ring_size = i;
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 91b0fd021a95..4ed81e74f86f 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -24,7 +24,6 @@
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
-#include <scsi/scsi_scan.h>
#include <asm/uaccess.h>
@@ -84,7 +83,6 @@ static int snapshot_open(struct inode *inode, struct file *filp)
* appear.
*/
wait_for_device_probe();
- scsi_complete_async_scans();
data->swap = -1;
data->mode = O_WRONLY;
diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c
new file mode 100644
index 000000000000..c8fba3380076
--- /dev/null
+++ b/kernel/power/wakelock.c
@@ -0,0 +1,259 @@
+/*
+ * kernel/power/wakelock.c
+ *
+ * User space wakeup sources support.
+ *
+ * Copyright (C) 2012 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * This code is based on the analogous interface allowing user space to
+ * manipulate wakelocks on Android.
+ */
+
+#include <linux/ctype.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+static DEFINE_MUTEX(wakelocks_lock);
+
+struct wakelock {
+ char *name;
+ struct rb_node node;
+ struct wakeup_source ws;
+#ifdef CONFIG_PM_WAKELOCKS_GC
+ struct list_head lru;
+#endif
+};
+
+static struct rb_root wakelocks_tree = RB_ROOT;
+
+ssize_t pm_show_wakelocks(char *buf, bool show_active)
+{
+ struct rb_node *node;
+ struct wakelock *wl;
+ char *str = buf;
+ char *end = buf + PAGE_SIZE;
+
+ mutex_lock(&wakelocks_lock);
+
+ for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) {
+ wl = rb_entry(node, struct wakelock, node);
+ if (wl->ws.active == show_active)
+ str += scnprintf(str, end - str, "%s ", wl->name);
+ }
+ if (str > buf)
+ str--;
+
+ str += scnprintf(str, end - str, "\n");
+
+ mutex_unlock(&wakelocks_lock);
+ return (str - buf);
+}
+
+#if CONFIG_PM_WAKELOCKS_LIMIT > 0
+static unsigned int number_of_wakelocks;
+
+static inline bool wakelocks_limit_exceeded(void)
+{
+ return number_of_wakelocks > CONFIG_PM_WAKELOCKS_LIMIT;
+}
+
+static inline void increment_wakelocks_number(void)
+{
+ number_of_wakelocks++;
+}
+
+static inline void decrement_wakelocks_number(void)
+{
+ number_of_wakelocks--;
+}
+#else /* CONFIG_PM_WAKELOCKS_LIMIT = 0 */
+static inline bool wakelocks_limit_exceeded(void) { return false; }
+static inline void increment_wakelocks_number(void) {}
+static inline void decrement_wakelocks_number(void) {}
+#endif /* CONFIG_PM_WAKELOCKS_LIMIT */
+
+#ifdef CONFIG_PM_WAKELOCKS_GC
+#define WL_GC_COUNT_MAX 100
+#define WL_GC_TIME_SEC 300
+
+static LIST_HEAD(wakelocks_lru_list);
+static unsigned int wakelocks_gc_count;
+
+static inline void wakelocks_lru_add(struct wakelock *wl)
+{
+ list_add(&wl->lru, &wakelocks_lru_list);
+}
+
+static inline void wakelocks_lru_most_recent(struct wakelock *wl)
+{
+ list_move(&wl->lru, &wakelocks_lru_list);
+}
+
+static void wakelocks_gc(void)
+{
+ struct wakelock *wl, *aux;
+ ktime_t now;
+
+ if (++wakelocks_gc_count <= WL_GC_COUNT_MAX)
+ return;
+
+ now = ktime_get();
+ list_for_each_entry_safe_reverse(wl, aux, &wakelocks_lru_list, lru) {
+ u64 idle_time_ns;
+ bool active;
+
+ spin_lock_irq(&wl->ws.lock);
+ idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws.last_time));
+ active = wl->ws.active;
+ spin_unlock_irq(&wl->ws.lock);
+
+ if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC))
+ break;
+
+ if (!active) {
+ wakeup_source_remove(&wl->ws);
+ rb_erase(&wl->node, &wakelocks_tree);
+ list_del(&wl->lru);
+ kfree(wl->name);
+ kfree(wl);
+ decrement_wakelocks_number();
+ }
+ }
+ wakelocks_gc_count = 0;
+}
+#else /* !CONFIG_PM_WAKELOCKS_GC */
+static inline void wakelocks_lru_add(struct wakelock *wl) {}
+static inline void wakelocks_lru_most_recent(struct wakelock *wl) {}
+static inline void wakelocks_gc(void) {}
+#endif /* !CONFIG_PM_WAKELOCKS_GC */
+
+static struct wakelock *wakelock_lookup_add(const char *name, size_t len,
+ bool add_if_not_found)
+{
+ struct rb_node **node = &wakelocks_tree.rb_node;
+ struct rb_node *parent = *node;
+ struct wakelock *wl;
+
+ while (*node) {
+ int diff;
+
+ parent = *node;
+ wl = rb_entry(*node, struct wakelock, node);
+ diff = strncmp(name, wl->name, len);
+ if (diff == 0) {
+ if (wl->name[len])
+ diff = -1;
+ else
+ return wl;
+ }
+ if (diff < 0)
+ node = &(*node)->rb_left;
+ else
+ node = &(*node)->rb_right;
+ }
+ if (!add_if_not_found)
+ return ERR_PTR(-EINVAL);
+
+ if (wakelocks_limit_exceeded())
+ return ERR_PTR(-ENOSPC);
+
+ /* Not found, we have to add a new one. */
+ wl = kzalloc(sizeof(*wl), GFP_KERNEL);
+ if (!wl)
+ return ERR_PTR(-ENOMEM);
+
+ wl->name = kstrndup(name, len, GFP_KERNEL);
+ if (!wl->name) {
+ kfree(wl);
+ return ERR_PTR(-ENOMEM);
+ }
+ wl->ws.name = wl->name;
+ wakeup_source_add(&wl->ws);
+ rb_link_node(&wl->node, parent, node);
+ rb_insert_color(&wl->node, &wakelocks_tree);
+ wakelocks_lru_add(wl);
+ increment_wakelocks_number();
+ return wl;
+}
+
+int pm_wake_lock(const char *buf)
+{
+ const char *str = buf;
+ struct wakelock *wl;
+ u64 timeout_ns = 0;
+ size_t len;
+ int ret = 0;
+
+ while (*str && !isspace(*str))
+ str++;
+
+ len = str - buf;
+ if (!len)
+ return -EINVAL;
+
+ if (*str && *str != '\n') {
+ /* Find out if there's a valid timeout string appended. */
+ ret = kstrtou64(skip_spaces(str), 10, &timeout_ns);
+ if (ret)
+ return -EINVAL;
+ }
+
+ mutex_lock(&wakelocks_lock);
+
+ wl = wakelock_lookup_add(buf, len, true);
+ if (IS_ERR(wl)) {
+ ret = PTR_ERR(wl);
+ goto out;
+ }
+ if (timeout_ns) {
+ u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1;
+
+ do_div(timeout_ms, NSEC_PER_MSEC);
+ __pm_wakeup_event(&wl->ws, timeout_ms);
+ } else {
+ __pm_stay_awake(&wl->ws);
+ }
+
+ wakelocks_lru_most_recent(wl);
+
+ out:
+ mutex_unlock(&wakelocks_lock);
+ return ret;
+}
+
+int pm_wake_unlock(const char *buf)
+{
+ struct wakelock *wl;
+ size_t len;
+ int ret = 0;
+
+ len = strlen(buf);
+ if (!len)
+ return -EINVAL;
+
+ if (buf[len-1] == '\n')
+ len--;
+
+ if (!len)
+ return -EINVAL;
+
+ mutex_lock(&wakelocks_lock);
+
+ wl = wakelock_lookup_add(buf, len, false);
+ if (IS_ERR(wl)) {
+ ret = PTR_ERR(wl);
+ goto out;
+ }
+ __pm_relax(&wl->ws);
+
+ wakelocks_lru_most_recent(wl);
+ wakelocks_gc();
+
+ out:
+ mutex_unlock(&wakelocks_lock);
+ return ret;
+}
diff --git a/kernel/printk.c b/kernel/printk.c
index 32462d2b364a..177fa49357a5 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -193,12 +193,21 @@ static int console_may_schedule;
* separated by ',', and find the message after the ';' character.
*/
+enum log_flags {
+ LOG_NOCONS = 1, /* already flushed, do not print to console */
+ LOG_NEWLINE = 2, /* text ended with a newline */
+ LOG_PREFIX = 4, /* text started with a prefix */
+ LOG_CONT = 8, /* text is a fragment of a continuation line */
+};
+
struct log {
u64 ts_nsec; /* timestamp in nanoseconds */
u16 len; /* length of entire record */
u16 text_len; /* length of text buffer */
u16 dict_len; /* length of dictionary buffer */
- u16 level; /* syslog level + facility */
+ u8 facility; /* syslog facility */
+ u8 flags:5; /* internal record flags */
+ u8 level:3; /* syslog level */
};
/*
@@ -210,6 +219,8 @@ static DEFINE_RAW_SPINLOCK(logbuf_lock);
/* the next printk record to read by syslog(READ) or /proc/kmsg */
static u64 syslog_seq;
static u32 syslog_idx;
+static enum log_flags syslog_prev;
+static size_t syslog_partial;
/* index and sequence number of the first record stored in the buffer */
static u64 log_first_seq;
@@ -227,10 +238,10 @@ static u32 clear_idx;
#define LOG_LINE_MAX 1024
/* record buffer */
-#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
#define LOG_ALIGN 4
#else
-#define LOG_ALIGN 8
+#define LOG_ALIGN __alignof__(struct log)
#endif
#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
@@ -286,6 +297,7 @@ static u32 log_next(u32 idx)
/* insert record into the buffer, discard old ones, update heads */
static void log_store(int facility, int level,
+ enum log_flags flags, u64 ts_nsec,
const char *dict, u16 dict_len,
const char *text, u16 text_len)
{
@@ -329,8 +341,13 @@ static void log_store(int facility, int level,
msg->text_len = text_len;
memcpy(log_dict(msg), dict, dict_len);
msg->dict_len = dict_len;
- msg->level = (facility << 3) | (level & 7);
- msg->ts_nsec = local_clock();
+ msg->facility = facility;
+ msg->level = level & 7;
+ msg->flags = flags & 0x1f;
+ if (ts_nsec > 0)
+ msg->ts_nsec = ts_nsec;
+ else
+ msg->ts_nsec = local_clock();
memset(log_dict(msg) + dict_len, 0, pad_len);
msg->len = sizeof(struct log) + text_len + dict_len + pad_len;
@@ -414,21 +431,23 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
if (!user)
return -EBADF;
- mutex_lock(&user->lock);
- raw_spin_lock(&logbuf_lock);
+ ret = mutex_lock_interruptible(&user->lock);
+ if (ret)
+ return ret;
+ raw_spin_lock_irq(&logbuf_lock);
while (user->seq == log_next_seq) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
goto out;
}
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
ret = wait_event_interruptible(log_wait,
user->seq != log_next_seq);
if (ret)
goto out;
- raw_spin_lock(&logbuf_lock);
+ raw_spin_lock_irq(&logbuf_lock);
}
if (user->seq < log_first_seq) {
@@ -436,7 +455,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
user->idx = log_first_idx;
user->seq = log_first_seq;
ret = -EPIPE;
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
goto out;
}
@@ -444,13 +463,13 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
ts_usec = msg->ts_nsec;
do_div(ts_usec, 1000);
len = sprintf(user->buf, "%u,%llu,%llu;",
- msg->level, user->seq, ts_usec);
+ (msg->facility << 3) | msg->level, user->seq, ts_usec);
/* escape non-printable characters */
for (i = 0; i < msg->text_len; i++) {
unsigned char c = log_text(msg)[i];
- if (c < ' ' || c >= 128)
+ if (c < ' ' || c >= 127 || c == '\\')
len += sprintf(user->buf + len, "\\x%02x", c);
else
user->buf[len++] = c;
@@ -474,7 +493,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
continue;
}
- if (c < ' ' || c >= 128) {
+ if (c < ' ' || c >= 127 || c == '\\') {
len += sprintf(user->buf + len, "\\x%02x", c);
continue;
}
@@ -486,7 +505,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
user->idx = log_next(user->idx);
user->seq++;
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
if (len > count) {
ret = -EINVAL;
@@ -513,7 +532,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
if (offset)
return -ESPIPE;
- raw_spin_lock(&logbuf_lock);
+ raw_spin_lock_irq(&logbuf_lock);
switch (whence) {
case SEEK_SET:
/* the first record */
@@ -537,7 +556,7 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
default:
ret = -EINVAL;
}
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
return ret;
}
@@ -551,14 +570,14 @@ static unsigned int devkmsg_poll(struct file *file, poll_table *wait)
poll_wait(file, &log_wait, wait);
- raw_spin_lock(&logbuf_lock);
+ raw_spin_lock_irq(&logbuf_lock);
if (user->seq < log_next_seq) {
/* return error when data has vanished underneath us */
if (user->seq < log_first_seq)
ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI;
ret = POLLIN|POLLRDNORM;
}
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
return ret;
}
@@ -582,10 +601,10 @@ static int devkmsg_open(struct inode *inode, struct file *file)
mutex_init(&user->lock);
- raw_spin_lock(&logbuf_lock);
+ raw_spin_lock_irq(&logbuf_lock);
user->idx = log_first_idx;
user->seq = log_first_seq;
- raw_spin_unlock(&logbuf_lock);
+ raw_spin_unlock_irq(&logbuf_lock);
file->private_data = user;
return 0;
@@ -785,44 +804,64 @@ static bool printk_time;
#endif
module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
+static size_t print_time(u64 ts, char *buf)
+{
+ unsigned long rem_nsec;
+
+ if (!printk_time)
+ return 0;
+
+ if (!buf)
+ return 15;
+
+ rem_nsec = do_div(ts, 1000000000);
+ return sprintf(buf, "[%5lu.%06lu] ",
+ (unsigned long)ts, rem_nsec / 1000);
+}
+
static size_t print_prefix(const struct log *msg, bool syslog, char *buf)
{
size_t len = 0;
+ unsigned int prefix = (msg->facility << 3) | msg->level;
if (syslog) {
if (buf) {
- len += sprintf(buf, "<%u>", msg->level);
+ len += sprintf(buf, "<%u>", prefix);
} else {
len += 3;
- if (msg->level > 9)
- len++;
- if (msg->level > 99)
+ if (prefix > 999)
+ len += 3;
+ else if (prefix > 99)
+ len += 2;
+ else if (prefix > 9)
len++;
}
}
- if (printk_time) {
- if (buf) {
- unsigned long long ts = msg->ts_nsec;
- unsigned long rem_nsec = do_div(ts, 1000000000);
-
- len += sprintf(buf + len, "[%5lu.%06lu] ",
- (unsigned long) ts, rem_nsec / 1000);
- } else {
- len += 15;
- }
- }
-
+ len += print_time(msg->ts_nsec, buf ? buf + len : NULL);
return len;
}
-static size_t msg_print_text(const struct log *msg, bool syslog,
- char *buf, size_t size)
+static size_t msg_print_text(const struct log *msg, enum log_flags prev,
+ bool syslog, char *buf, size_t size)
{
const char *text = log_text(msg);
size_t text_size = msg->text_len;
+ bool prefix = true;
+ bool newline = true;
size_t len = 0;
+ if ((prev & LOG_CONT) && !(msg->flags & LOG_PREFIX))
+ prefix = false;
+
+ if (msg->flags & LOG_CONT) {
+ if ((prev & LOG_CONT) && !(prev & LOG_NEWLINE))
+ prefix = false;
+
+ if (!(msg->flags & LOG_NEWLINE))
+ newline = false;
+ }
+
do {
const char *next = memchr(text, '\n', text_size);
size_t text_len;
@@ -840,16 +879,22 @@ static size_t msg_print_text(const struct log *msg, bool syslog,
text_len + 1>= size - len)
break;
- len += print_prefix(msg, syslog, buf + len);
+ if (prefix)
+ len += print_prefix(msg, syslog, buf + len);
memcpy(buf + len, text, text_len);
len += text_len;
- buf[len++] = '\n';
+ if (next || newline)
+ buf[len++] = '\n';
} else {
/* SYSLOG_ACTION_* buffer size only calculation */
- len += print_prefix(msg, syslog, NULL);
- len += text_len + 1;
+ if (prefix)
+ len += print_prefix(msg, syslog, NULL);
+ len += text_len;
+ if (next || newline)
+ len++;
}
+ prefix = true;
text = next;
} while (text);
@@ -860,26 +905,60 @@ static int syslog_print(char __user *buf, int size)
{
char *text;
struct log *msg;
- int len;
+ int len = 0;
text = kmalloc(LOG_LINE_MAX, GFP_KERNEL);
if (!text)
return -ENOMEM;
- raw_spin_lock_irq(&logbuf_lock);
- if (syslog_seq < log_first_seq) {
- /* messages are gone, move to first one */
- syslog_seq = log_first_seq;
- syslog_idx = log_first_idx;
- }
- msg = log_from_idx(syslog_idx);
- len = msg_print_text(msg, true, text, LOG_LINE_MAX);
- syslog_idx = log_next(syslog_idx);
- syslog_seq++;
- raw_spin_unlock_irq(&logbuf_lock);
+ while (size > 0) {
+ size_t n;
+ size_t skip;
+
+ raw_spin_lock_irq(&logbuf_lock);
+ if (syslog_seq < log_first_seq) {
+ /* messages are gone, move to first one */
+ syslog_seq = log_first_seq;
+ syslog_idx = log_first_idx;
+ syslog_prev = 0;
+ syslog_partial = 0;
+ }
+ if (syslog_seq == log_next_seq) {
+ raw_spin_unlock_irq(&logbuf_lock);
+ break;
+ }
+
+ skip = syslog_partial;
+ msg = log_from_idx(syslog_idx);
+ n = msg_print_text(msg, syslog_prev, true, text, LOG_LINE_MAX);
+ if (n - syslog_partial <= size) {
+ /* message fits into buffer, move forward */
+ syslog_idx = log_next(syslog_idx);
+ syslog_seq++;
+ syslog_prev = msg->flags;
+ n -= syslog_partial;
+ syslog_partial = 0;
+ } else if (!len){
+ /* partial read(), remember position */
+ n = size;
+ syslog_partial += n;
+ } else
+ n = 0;
+ raw_spin_unlock_irq(&logbuf_lock);
+
+ if (!n)
+ break;
+
+ if (copy_to_user(buf, text + skip, n)) {
+ if (!len)
+ len = -EFAULT;
+ break;
+ }
- if (len > 0 && copy_to_user(buf, text, len))
- len = -EFAULT;
+ len += n;
+ size -= n;
+ buf += n;
+ }
kfree(text);
return len;
@@ -899,6 +978,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
u64 next_seq;
u64 seq;
u32 idx;
+ enum log_flags prev;
if (clear_seq < log_first_seq) {
/* messages are gone, move to first available one */
@@ -909,41 +989,47 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
/*
* Find first record that fits, including all following records,
* into the user-provided buffer for this dump.
- */
+ */
seq = clear_seq;
idx = clear_idx;
+ prev = 0;
while (seq < log_next_seq) {
struct log *msg = log_from_idx(idx);
- len += msg_print_text(msg, true, NULL, 0);
+ len += msg_print_text(msg, prev, true, NULL, 0);
idx = log_next(idx);
seq++;
}
+
+ /* move first record forward until length fits into the buffer */
seq = clear_seq;
idx = clear_idx;
+ prev = 0;
while (len > size && seq < log_next_seq) {
struct log *msg = log_from_idx(idx);
- len -= msg_print_text(msg, true, NULL, 0);
+ len -= msg_print_text(msg, prev, true, NULL, 0);
idx = log_next(idx);
seq++;
}
- /* last message in this dump */
+ /* last message fitting into this dump */
next_seq = log_next_seq;
len = 0;
+ prev = 0;
while (len >= 0 && seq < next_seq) {
struct log *msg = log_from_idx(idx);
int textlen;
- textlen = msg_print_text(msg, true, text, LOG_LINE_MAX);
+ textlen = msg_print_text(msg, prev, true, text, LOG_LINE_MAX);
if (textlen < 0) {
len = textlen;
break;
}
idx = log_next(idx);
seq++;
+ prev = msg->flags;
raw_spin_unlock_irq(&logbuf_lock);
if (copy_to_user(buf + len, text, textlen))
@@ -956,6 +1042,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
/* messages are gone, move to next one */
seq = log_first_seq;
idx = log_first_idx;
+ prev = 0;
}
}
}
@@ -1027,6 +1114,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
/* Clear ring buffer */
case SYSLOG_ACTION_CLEAR:
syslog_print_all(NULL, 0, true);
+ break;
/* Disable logging to console */
case SYSLOG_ACTION_CONSOLE_OFF:
if (saved_console_loglevel == -1)
@@ -1059,6 +1147,8 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
/* messages are gone, move to first one */
syslog_seq = log_first_seq;
syslog_idx = log_first_idx;
+ syslog_prev = 0;
+ syslog_partial = 0;
}
if (from_file) {
/*
@@ -1068,19 +1158,20 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
*/
error = log_next_idx - syslog_idx;
} else {
- u64 seq;
- u32 idx;
+ u64 seq = syslog_seq;
+ u32 idx = syslog_idx;
+ enum log_flags prev = syslog_prev;
error = 0;
- seq = syslog_seq;
- idx = syslog_idx;
while (seq < log_next_seq) {
struct log *msg = log_from_idx(idx);
- error += msg_print_text(msg, true, NULL, 0);
+ error += msg_print_text(msg, prev, true, NULL, 0);
idx = log_next(idx);
seq++;
+ prev = msg->flags;
}
+ error -= syslog_partial;
}
raw_spin_unlock_irq(&logbuf_lock);
break;
@@ -1259,22 +1350,98 @@ static inline void printk_delay(void)
}
}
+/*
+ * Continuation lines are buffered, and not committed to the record buffer
+ * until the line is complete, or a race forces it. The line fragments
+ * though, are printed immediately to the consoles to ensure everything has
+ * reached the console in case of a kernel crash.
+ */
+static struct cont {
+ char buf[LOG_LINE_MAX];
+ size_t len; /* length == 0 means unused buffer */
+ size_t cons; /* bytes written to console */
+ struct task_struct *owner; /* task of first print*/
+ u64 ts_nsec; /* time of first print */
+ u8 level; /* log level of first message */
+ u8 facility; /* log level of first message */
+ bool flushed:1; /* buffer sealed and committed */
+} cont;
+
+static void cont_flush(void)
+{
+ if (cont.flushed)
+ return;
+ if (cont.len == 0)
+ return;
+
+ log_store(cont.facility, cont.level, LOG_NOCONS, cont.ts_nsec,
+ NULL, 0, cont.buf, cont.len);
+
+ cont.flushed = true;
+}
+
+static bool cont_add(int facility, int level, const char *text, size_t len)
+{
+ if (cont.len && cont.flushed)
+ return false;
+
+ if (cont.len + len > sizeof(cont.buf)) {
+ cont_flush();
+ return false;
+ }
+
+ if (!cont.len) {
+ cont.facility = facility;
+ cont.level = level;
+ cont.owner = current;
+ cont.ts_nsec = local_clock();
+ cont.cons = 0;
+ cont.flushed = false;
+ }
+
+ memcpy(cont.buf + cont.len, text, len);
+ cont.len += len;
+ return true;
+}
+
+static size_t cont_print_text(char *text, size_t size)
+{
+ size_t textlen = 0;
+ size_t len;
+
+ if (cont.cons == 0) {
+ textlen += print_time(cont.ts_nsec, text);
+ size -= textlen;
+ }
+
+ len = cont.len - cont.cons;
+ if (len > 0) {
+ if (len+1 > size)
+ len = size-1;
+ memcpy(text + textlen, cont.buf + cont.cons, len);
+ textlen += len;
+ cont.cons = cont.len;
+ }
+
+ if (cont.flushed) {
+ text[textlen++] = '\n';
+ /* got everything, release buffer */
+ cont.len = 0;
+ }
+ return textlen;
+}
+
asmlinkage int vprintk_emit(int facility, int level,
const char *dict, size_t dictlen,
const char *fmt, va_list args)
{
static int recursion_bug;
- static char cont_buf[LOG_LINE_MAX];
- static size_t cont_len;
- static int cont_level;
- static struct task_struct *cont_task;
static char textbuf[LOG_LINE_MAX];
char *text = textbuf;
size_t text_len;
+ enum log_flags lflags = 0;
unsigned long flags;
int this_cpu;
- bool newline = false;
- bool prefix = false;
int printed_len = 0;
boot_delay_msec();
@@ -1313,7 +1480,8 @@ asmlinkage int vprintk_emit(int facility, int level,
recursion_bug = 0;
printed_len += strlen(recursion_msg);
/* emit KERN_CRIT message */
- log_store(0, 2, NULL, 0, recursion_msg, printed_len);
+ log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0,
+ NULL, 0, recursion_msg, printed_len);
}
/*
@@ -1325,7 +1493,7 @@ asmlinkage int vprintk_emit(int facility, int level,
/* mark and strip a trailing newline */
if (text_len && text[text_len-1] == '\n') {
text_len--;
- newline = true;
+ lflags |= LOG_NEWLINE;
}
/* strip syslog prefix and extract log level or control flags */
@@ -1335,7 +1503,7 @@ asmlinkage int vprintk_emit(int facility, int level,
if (level == -1)
level = text[1] - '0';
case 'd': /* KERN_DEFAULT */
- prefix = true;
+ lflags |= LOG_PREFIX;
case 'c': /* KERN_CONT */
text += 3;
text_len -= 3;
@@ -1345,61 +1513,41 @@ asmlinkage int vprintk_emit(int facility, int level,
if (level == -1)
level = default_message_loglevel;
- if (dict) {
- prefix = true;
- newline = true;
- }
+ if (dict)
+ lflags |= LOG_PREFIX|LOG_NEWLINE;
- if (!newline) {
- if (cont_len && (prefix || cont_task != current)) {
- /*
- * Flush earlier buffer, which is either from a
- * different thread, or when we got a new prefix.
- */
- log_store(facility, cont_level, NULL, 0, cont_buf, cont_len);
- cont_len = 0;
- }
-
- if (!cont_len) {
- cont_level = level;
- cont_task = current;
- }
+ if (!(lflags & LOG_NEWLINE)) {
+ /*
+ * Flush the conflicting buffer. An earlier newline was missing,
+ * or another task also prints continuation lines.
+ */
+ if (cont.len && (lflags & LOG_PREFIX || cont.owner != current))
+ cont_flush();
- /* buffer or append to earlier buffer from the same thread */
- if (cont_len + text_len > sizeof(cont_buf))
- text_len = sizeof(cont_buf) - cont_len;
- memcpy(cont_buf + cont_len, text, text_len);
- cont_len += text_len;
+ /* buffer line if possible, otherwise store it right away */
+ if (!cont_add(facility, level, text, text_len))
+ log_store(facility, level, lflags | LOG_CONT, 0,
+ dict, dictlen, text, text_len);
} else {
- if (cont_len && cont_task == current) {
- if (prefix) {
- /*
- * New prefix from the same thread; flush. We
- * either got no earlier newline, or we race
- * with an interrupt.
- */
- log_store(facility, cont_level,
- NULL, 0, cont_buf, cont_len);
- cont_len = 0;
- }
+ bool stored = false;
- /* append to the earlier buffer and flush */
- if (cont_len + text_len > sizeof(cont_buf))
- text_len = sizeof(cont_buf) - cont_len;
- memcpy(cont_buf + cont_len, text, text_len);
- cont_len += text_len;
- log_store(facility, cont_level,
- NULL, 0, cont_buf, cont_len);
- cont_len = 0;
- cont_task = NULL;
- printed_len = cont_len;
- } else {
- /* ordinary single and terminated line */
- log_store(facility, level,
- dict, dictlen, text, text_len);
- printed_len = text_len;
+ /*
+ * If an earlier newline was missing and it was the same task,
+ * either merge it with the current buffer and flush, or if
+ * there was a race with interrupts (prefix == true) then just
+ * flush it out and store this line separately.
+ */
+ if (cont.len && cont.owner == current) {
+ if (!(lflags & LOG_PREFIX))
+ stored = cont_add(facility, level, text, text_len);
+ cont_flush();
}
+
+ if (!stored)
+ log_store(facility, level, lflags, 0,
+ dict, dictlen, text, text_len);
}
+ printed_len += text_len;
/*
* Try to acquire and then immediately release the console semaphore.
@@ -1486,11 +1634,18 @@ EXPORT_SYMBOL(printk);
#else
#define LOG_LINE_MAX 0
+static struct cont {
+ size_t len;
+ size_t cons;
+ u8 level;
+ bool flushed:1;
+} cont;
static struct log *log_from_idx(u32 idx) { return NULL; }
static u32 log_next(u32 idx) { return 0; }
static void call_console_drivers(int level, const char *text, size_t len) {}
-static size_t msg_print_text(const struct log *msg, bool syslog,
- char *buf, size_t size) { return 0; }
+static size_t msg_print_text(const struct log *msg, enum log_flags prev,
+ bool syslog, char *buf, size_t size) { return 0; }
+static size_t cont_print_text(char *text, size_t size) { return 0; }
#endif /* CONFIG_PRINTK */
@@ -1765,6 +1920,7 @@ void wake_up_klogd(void)
/* the next printk record to write to the console */
static u64 console_seq;
static u32 console_idx;
+static enum log_flags console_prev;
/**
* console_unlock - unlock the console system
@@ -1782,6 +1938,7 @@ static u32 console_idx;
*/
void console_unlock(void)
{
+ static char text[LOG_LINE_MAX];
static u64 seen_seq;
unsigned long flags;
bool wake_klogd = false;
@@ -1794,10 +1951,23 @@ void console_unlock(void)
console_may_schedule = 0;
+ /* flush buffered message fragment immediately to console */
+ raw_spin_lock_irqsave(&logbuf_lock, flags);
+ if (cont.len && (cont.cons < cont.len || cont.flushed)) {
+ size_t len;
+
+ len = cont_print_text(text, sizeof(text));
+ raw_spin_unlock(&logbuf_lock);
+ stop_critical_timings();
+ call_console_drivers(cont.level, text, len);
+ start_critical_timings();
+ local_irq_restore(flags);
+ } else
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
again:
for (;;) {
struct log *msg;
- static char text[LOG_LINE_MAX];
size_t len;
int level;
@@ -1811,18 +1981,35 @@ again:
/* messages are gone, move to first one */
console_seq = log_first_seq;
console_idx = log_first_idx;
+ console_prev = 0;
}
-
+skip:
if (console_seq == log_next_seq)
break;
msg = log_from_idx(console_idx);
- level = msg->level & 7;
-
- len = msg_print_text(msg, false, text, sizeof(text));
+ if (msg->flags & LOG_NOCONS) {
+ /*
+ * Skip record we have buffered and already printed
+ * directly to the console when we received it.
+ */
+ console_idx = log_next(console_idx);
+ console_seq++;
+ /*
+ * We will get here again when we register a new
+ * CON_PRINTBUFFER console. Clear the flag so we
+ * will properly dump everything later.
+ */
+ msg->flags &= ~LOG_NOCONS;
+ goto skip;
+ }
+ level = msg->level;
+ len = msg_print_text(msg, console_prev, false,
+ text, sizeof(text));
console_idx = log_next(console_idx);
console_seq++;
+ console_prev = msg->flags;
raw_spin_unlock(&logbuf_lock);
stop_critical_timings(); /* don't trace print latency */
@@ -2085,6 +2272,7 @@ void register_console(struct console *newcon)
raw_spin_lock_irqsave(&logbuf_lock, flags);
console_seq = syslog_seq;
console_idx = syslog_idx;
+ console_prev = syslog_prev;
raw_spin_unlock_irqrestore(&logbuf_lock, flags);
/*
* We're about to replay the log buffer. Only do this to the
@@ -2300,48 +2488,214 @@ module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);
* kmsg_dump - dump kernel log to kernel message dumpers.
* @reason: the reason (oops, panic etc) for dumping
*
- * Iterate through each of the dump devices and call the oops/panic
- * callbacks with the log buffer.
+ * Call each of the registered dumper's dump() callback, which can
+ * retrieve the kmsg records with kmsg_dump_get_line() or
+ * kmsg_dump_get_buffer().
*/
void kmsg_dump(enum kmsg_dump_reason reason)
{
- u64 idx;
struct kmsg_dumper *dumper;
- const char *s1, *s2;
- unsigned long l1, l2;
unsigned long flags;
if ((reason > KMSG_DUMP_OOPS) && !always_kmsg_dump)
return;
- /* Theoretically, the log could move on after we do this, but
- there's not a lot we can do about that. The new messages
- will overwrite the start of what we dump. */
+ rcu_read_lock();
+ list_for_each_entry_rcu(dumper, &dump_list, list) {
+ if (dumper->max_reason && reason > dumper->max_reason)
+ continue;
+
+ /* initialize iterator with data about the stored records */
+ dumper->active = true;
+
+ raw_spin_lock_irqsave(&logbuf_lock, flags);
+ dumper->cur_seq = clear_seq;
+ dumper->cur_idx = clear_idx;
+ dumper->next_seq = log_next_seq;
+ dumper->next_idx = log_next_idx;
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+
+ /* invoke dumper which will iterate over records */
+ dumper->dump(dumper, reason);
+
+ /* reset iterator */
+ dumper->active = false;
+ }
+ rcu_read_unlock();
+}
+
+/**
+ * kmsg_dump_get_line - retrieve one kmsg log line
+ * @dumper: registered kmsg dumper
+ * @syslog: include the "<4>" prefixes
+ * @line: buffer to copy the line to
+ * @size: maximum size of the buffer
+ * @len: length of line placed into buffer
+ *
+ * Start at the beginning of the kmsg buffer, with the oldest kmsg
+ * record, and copy one record into the provided buffer.
+ *
+ * Consecutive calls will return the next available record moving
+ * towards the end of the buffer with the youngest messages.
+ *
+ * A return value of FALSE indicates that there are no more records to
+ * read.
+ */
+bool kmsg_dump_get_line(struct kmsg_dumper *dumper, bool syslog,
+ char *line, size_t size, size_t *len)
+{
+ unsigned long flags;
+ struct log *msg;
+ size_t l = 0;
+ bool ret = false;
+
+ if (!dumper->active)
+ goto out;
raw_spin_lock_irqsave(&logbuf_lock, flags);
- if (syslog_seq < log_first_seq)
- idx = syslog_idx;
- else
- idx = log_first_idx;
+ if (dumper->cur_seq < log_first_seq) {
+ /* messages are gone, move to first available one */
+ dumper->cur_seq = log_first_seq;
+ dumper->cur_idx = log_first_idx;
+ }
- if (idx > log_next_idx) {
- s1 = log_buf;
- l1 = log_next_idx;
+ /* last entry */
+ if (dumper->cur_seq >= log_next_seq) {
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+ goto out;
+ }
- s2 = log_buf + idx;
- l2 = log_buf_len - idx;
- } else {
- s1 = "";
- l1 = 0;
+ msg = log_from_idx(dumper->cur_idx);
+ l = msg_print_text(msg, 0, syslog, line, size);
+
+ dumper->cur_idx = log_next(dumper->cur_idx);
+ dumper->cur_seq++;
+ ret = true;
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+out:
+ if (len)
+ *len = l;
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_get_line);
+
+/**
+ * kmsg_dump_get_buffer - copy kmsg log lines
+ * @dumper: registered kmsg dumper
+ * @syslog: include the "<4>" prefixes
+ * @buf: buffer to copy the line to
+ * @size: maximum size of the buffer
+ * @len: length of line placed into buffer
+ *
+ * Start at the end of the kmsg buffer and fill the provided buffer
+ * with as many of the the *youngest* kmsg records that fit into it.
+ * If the buffer is large enough, all available kmsg records will be
+ * copied with a single call.
+ *
+ * Consecutive calls will fill the buffer with the next block of
+ * available older records, not including the earlier retrieved ones.
+ *
+ * A return value of FALSE indicates that there are no more records to
+ * read.
+ */
+bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog,
+ char *buf, size_t size, size_t *len)
+{
+ unsigned long flags;
+ u64 seq;
+ u32 idx;
+ u64 next_seq;
+ u32 next_idx;
+ enum log_flags prev;
+ size_t l = 0;
+ bool ret = false;
+
+ if (!dumper->active)
+ goto out;
+
+ raw_spin_lock_irqsave(&logbuf_lock, flags);
+ if (dumper->cur_seq < log_first_seq) {
+ /* messages are gone, move to first available one */
+ dumper->cur_seq = log_first_seq;
+ dumper->cur_idx = log_first_idx;
+ }
+
+ /* last entry */
+ if (dumper->cur_seq >= dumper->next_seq) {
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+ goto out;
+ }
+
+ /* calculate length of entire buffer */
+ seq = dumper->cur_seq;
+ idx = dumper->cur_idx;
+ prev = 0;
+ while (seq < dumper->next_seq) {
+ struct log *msg = log_from_idx(idx);
+
+ l += msg_print_text(msg, prev, true, NULL, 0);
+ idx = log_next(idx);
+ seq++;
+ prev = msg->flags;
+ }
- s2 = log_buf + idx;
- l2 = log_next_idx - idx;
+ /* move first record forward until length fits into the buffer */
+ seq = dumper->cur_seq;
+ idx = dumper->cur_idx;
+ prev = 0;
+ while (l > size && seq < dumper->next_seq) {
+ struct log *msg = log_from_idx(idx);
+
+ l -= msg_print_text(msg, prev, true, NULL, 0);
+ idx = log_next(idx);
+ seq++;
+ prev = msg->flags;
}
+
+ /* last message in next interation */
+ next_seq = seq;
+ next_idx = idx;
+
+ l = 0;
+ prev = 0;
+ while (seq < dumper->next_seq) {
+ struct log *msg = log_from_idx(idx);
+
+ l += msg_print_text(msg, prev, syslog, buf + l, size - l);
+ idx = log_next(idx);
+ seq++;
+ prev = msg->flags;
+ }
+
+ dumper->next_seq = next_seq;
+ dumper->next_idx = next_idx;
+ ret = true;
raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+out:
+ if (len)
+ *len = l;
+ return ret;
+}
+EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);
- rcu_read_lock();
- list_for_each_entry_rcu(dumper, &dump_list, list)
- dumper->dump(dumper, reason, s1, l1, s2, l2);
- rcu_read_unlock();
+/**
+ * kmsg_dump_rewind - reset the interator
+ * @dumper: registered kmsg dumper
+ *
+ * Reset the dumper's iterator so that kmsg_dump_get_line() and
+ * kmsg_dump_get_buffer() can be called again and used multiple
+ * times within the same dumper.dump() callback.
+ */
+void kmsg_dump_rewind(struct kmsg_dumper *dumper)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&logbuf_lock, flags);
+ dumper->cur_seq = clear_seq;
+ dumper->cur_idx = clear_idx;
+ dumper->next_seq = log_next_seq;
+ dumper->next_idx = log_next_idx;
+ raw_spin_unlock_irqrestore(&logbuf_lock, flags);
}
+EXPORT_SYMBOL_GPL(kmsg_dump_rewind);
#endif
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index ee8d49b9c309..a232bb59d93f 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -198,15 +198,14 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
return 0;
rcu_read_lock();
tcred = __task_cred(task);
- if (cred->user->user_ns == tcred->user->user_ns &&
- (cred->uid == tcred->euid &&
- cred->uid == tcred->suid &&
- cred->uid == tcred->uid &&
- cred->gid == tcred->egid &&
- cred->gid == tcred->sgid &&
- cred->gid == tcred->gid))
+ if (uid_eq(cred->uid, tcred->euid) &&
+ uid_eq(cred->uid, tcred->suid) &&
+ uid_eq(cred->uid, tcred->uid) &&
+ gid_eq(cred->gid, tcred->egid) &&
+ gid_eq(cred->gid, tcred->sgid) &&
+ gid_eq(cred->gid, tcred->gid))
goto ok;
- if (ptrace_has_cap(tcred->user->user_ns, mode))
+ if (ptrace_has_cap(tcred->user_ns, mode))
goto ok;
rcu_read_unlock();
return -EPERM;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0da7b88d92d0..4b97bba7396e 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -201,6 +201,7 @@ void rcu_note_context_switch(int cpu)
{
trace_rcu_utilization("Start context switch");
rcu_sched_qs(cpu);
+ rcu_preempt_note_context_switch(cpu);
trace_rcu_utilization("End context switch");
}
EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -1397,6 +1398,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
rdp->qlen_lazy += rsp->qlen_lazy;
rdp->qlen += rsp->qlen;
rdp->n_cbs_adopted += rsp->qlen;
+ if (rsp->qlen_lazy != rsp->qlen)
+ rcu_idle_count_callbacks_posted();
rsp->qlen_lazy = 0;
rsp->qlen = 0;
@@ -1528,7 +1531,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
struct rcu_head *next, *list, **tail;
- int bl, count, count_lazy;
+ int bl, count, count_lazy, i;
/* If no callbacks are ready, just return.*/
if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
@@ -1551,9 +1554,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
*rdp->nxttail[RCU_DONE_TAIL] = NULL;
tail = rdp->nxttail[RCU_DONE_TAIL];
- for (count = RCU_NEXT_SIZE - 1; count >= 0; count--)
- if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL])
- rdp->nxttail[count] = &rdp->nxtlist;
+ for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
+ if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
+ rdp->nxttail[i] = &rdp->nxtlist;
local_irq_restore(flags);
/* Invoke callbacks. */
@@ -1581,9 +1584,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
if (list != NULL) {
*tail = rdp->nxtlist;
rdp->nxtlist = list;
- for (count = 0; count < RCU_NEXT_SIZE; count++)
- if (&rdp->nxtlist == rdp->nxttail[count])
- rdp->nxttail[count] = tail;
+ for (i = 0; i < RCU_NEXT_SIZE; i++)
+ if (&rdp->nxtlist == rdp->nxttail[i])
+ rdp->nxttail[i] = tail;
else
break;
}
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 7f5d138dedf5..19b61ac1079f 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,6 +84,20 @@ struct rcu_dynticks {
/* Process level is worth LLONG_MAX/2. */
int dynticks_nmi_nesting; /* Track NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
+#ifdef CONFIG_RCU_FAST_NO_HZ
+ int dyntick_drain; /* Prepare-for-idle state variable. */
+ unsigned long dyntick_holdoff;
+ /* No retries for the jiffy of failure. */
+ struct timer_list idle_gp_timer;
+ /* Wake up CPU sleeping with callbacks. */
+ unsigned long idle_gp_timer_expires;
+ /* When to wake up CPU (for repost). */
+ bool idle_first_pass; /* First pass of attempt to go idle? */
+ unsigned long nonlazy_posted;
+ /* # times non-lazy CBs posted to CPU. */
+ unsigned long nonlazy_posted_snap;
+ /* idle-period nonlazy_posted snapshot. */
+#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
};
/* RCU's kthread states for tracing. */
@@ -430,6 +444,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
/* Forward declarations for rcutree_plugin.h */
static void rcu_bootup_announce(void);
long rcu_batches_completed(void);
+static void rcu_preempt_note_context_switch(int cpu);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 2411000d9869..3e4899459f3d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu)
*
* Caller must disable preemption.
*/
-void rcu_preempt_note_context_switch(void)
+static void rcu_preempt_note_context_switch(int cpu)
{
struct task_struct *t = current;
unsigned long flags;
@@ -164,7 +164,7 @@ void rcu_preempt_note_context_switch(void)
(t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
/* Possibly blocking in an RCU read-side critical section. */
- rdp = __this_cpu_ptr(rcu_preempt_state.rda);
+ rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
rnp = rdp->mynode;
raw_spin_lock_irqsave(&rnp->lock, flags);
t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -228,7 +228,7 @@ void rcu_preempt_note_context_switch(void)
* means that we continue to block the current grace period.
*/
local_irq_save(flags);
- rcu_preempt_qs(smp_processor_id());
+ rcu_preempt_qs(cpu);
local_irq_restore(flags);
}
@@ -1002,6 +1002,14 @@ void rcu_force_quiescent_state(void)
EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * CPUs being in quiescent states.
+ */
+static void rcu_preempt_note_context_switch(int cpu)
+{
+}
+
+/*
* Because preemptible RCU does not exist, there are never any preempted
* RCU readers.
*/
@@ -1886,8 +1894,9 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
* Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
* any flavor of RCU.
*/
-int rcu_needs_cpu(int cpu)
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
{
+ *delta_jiffies = ULONG_MAX;
return rcu_cpu_has_callbacks(cpu);
}
@@ -1962,41 +1971,6 @@ static void rcu_idle_count_callbacks_posted(void)
#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */
#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */
-/* Loop counter for rcu_prepare_for_idle(). */
-static DEFINE_PER_CPU(int, rcu_dyntick_drain);
-/* If rcu_dyntick_holdoff==jiffies, don't try to enter dyntick-idle mode. */
-static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
-/* Timer to awaken the CPU if it enters dyntick-idle mode with callbacks. */
-static DEFINE_PER_CPU(struct timer_list, rcu_idle_gp_timer);
-/* Scheduled expiry time for rcu_idle_gp_timer to allow reposting. */
-static DEFINE_PER_CPU(unsigned long, rcu_idle_gp_timer_expires);
-/* Enable special processing on first attempt to enter dyntick-idle mode. */
-static DEFINE_PER_CPU(bool, rcu_idle_first_pass);
-/* Running count of non-lazy callbacks posted, never decremented. */
-static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted);
-/* Snapshot of rcu_nonlazy_posted to detect meaningful exits from idle. */
-static DEFINE_PER_CPU(unsigned long, rcu_nonlazy_posted_snap);
-
-/*
- * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
- * callbacks on this CPU, (2) this CPU has not yet attempted to enter
- * dyntick-idle mode, or (3) this CPU is in the process of attempting to
- * enter dyntick-idle mode. Otherwise, if we have recently tried and failed
- * to enter dyntick-idle mode, we refuse to try to enter it. After all,
- * it is better to incur scheduling-clock interrupts than to spin
- * continuously for the same time duration!
- */
-int rcu_needs_cpu(int cpu)
-{
- /* Flag a new idle sojourn to the idle-entry state machine. */
- per_cpu(rcu_idle_first_pass, cpu) = 1;
- /* If no callbacks, RCU doesn't need the CPU. */
- if (!rcu_cpu_has_callbacks(cpu))
- return 0;
- /* Otherwise, RCU needs the CPU only if it recently tried and failed. */
- return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies;
-}
-
/*
* Does the specified flavor of RCU have non-lazy callbacks pending on
* the specified CPU? Both RCU flavor and CPU are specified by the
@@ -2040,6 +2014,47 @@ static bool rcu_cpu_has_nonlazy_callbacks(int cpu)
}
/*
+ * Allow the CPU to enter dyntick-idle mode if either: (1) There are no
+ * callbacks on this CPU, (2) this CPU has not yet attempted to enter
+ * dyntick-idle mode, or (3) this CPU is in the process of attempting to
+ * enter dyntick-idle mode. Otherwise, if we have recently tried and failed
+ * to enter dyntick-idle mode, we refuse to try to enter it. After all,
+ * it is better to incur scheduling-clock interrupts than to spin
+ * continuously for the same time duration!
+ *
+ * The delta_jiffies argument is used to store the time when RCU is
+ * going to need the CPU again if it still has callbacks. The reason
+ * for this is that rcu_prepare_for_idle() might need to post a timer,
+ * but if so, it will do so after tick_nohz_stop_sched_tick() has set
+ * the wakeup time for this CPU. This means that RCU's timer can be
+ * delayed until the wakeup time, which defeats the purpose of posting
+ * a timer.
+ */
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies)
+{
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ /* Flag a new idle sojourn to the idle-entry state machine. */
+ rdtp->idle_first_pass = 1;
+ /* If no callbacks, RCU doesn't need the CPU. */
+ if (!rcu_cpu_has_callbacks(cpu)) {
+ *delta_jiffies = ULONG_MAX;
+ return 0;
+ }
+ if (rdtp->dyntick_holdoff == jiffies) {
+ /* RCU recently tried and failed, so don't try again. */
+ *delta_jiffies = 1;
+ return 1;
+ }
+ /* Set up for the possibility that RCU will post a timer. */
+ if (rcu_cpu_has_nonlazy_callbacks(cpu))
+ *delta_jiffies = RCU_IDLE_GP_DELAY;
+ else
+ *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY;
+ return 0;
+}
+
+/*
* Handler for smp_call_function_single(). The only point of this
* handler is to wake the CPU up, so the handler does only tracing.
*/
@@ -2075,21 +2090,24 @@ static void rcu_idle_gp_timer_func(unsigned long cpu_in)
*/
static void rcu_prepare_for_idle_init(int cpu)
{
- per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
- setup_timer(&per_cpu(rcu_idle_gp_timer, cpu),
- rcu_idle_gp_timer_func, cpu);
- per_cpu(rcu_idle_gp_timer_expires, cpu) = jiffies - 1;
- per_cpu(rcu_idle_first_pass, cpu) = 1;
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ rdtp->dyntick_holdoff = jiffies - 1;
+ setup_timer(&rdtp->idle_gp_timer, rcu_idle_gp_timer_func, cpu);
+ rdtp->idle_gp_timer_expires = jiffies - 1;
+ rdtp->idle_first_pass = 1;
}
/*
* Clean up for exit from idle. Because we are exiting from idle, there
- * is no longer any point to rcu_idle_gp_timer, so cancel it. This will
+ * is no longer any point to ->idle_gp_timer, so cancel it. This will
* do nothing if this timer is not active, so just cancel it unconditionally.
*/
static void rcu_cleanup_after_idle(int cpu)
{
- del_timer(&per_cpu(rcu_idle_gp_timer, cpu));
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ del_timer(&rdtp->idle_gp_timer);
trace_rcu_prep_idle("Cleanup after idle");
}
@@ -2108,42 +2126,41 @@ static void rcu_cleanup_after_idle(int cpu)
* Because it is not legal to invoke rcu_process_callbacks() with irqs
* disabled, we do one pass of force_quiescent_state(), then do a
* invoke_rcu_core() to cause rcu_process_callbacks() to be invoked
- * later. The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ * later. The ->dyntick_drain field controls the sequencing.
*
* The caller must have disabled interrupts.
*/
static void rcu_prepare_for_idle(int cpu)
{
struct timer_list *tp;
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
/*
* If this is an idle re-entry, for example, due to use of
* RCU_NONIDLE() or the new idle-loop tracing API within the idle
* loop, then don't take any state-machine actions, unless the
* momentary exit from idle queued additional non-lazy callbacks.
- * Instead, repost the rcu_idle_gp_timer if this CPU has callbacks
+ * Instead, repost the ->idle_gp_timer if this CPU has callbacks
* pending.
*/
- if (!per_cpu(rcu_idle_first_pass, cpu) &&
- (per_cpu(rcu_nonlazy_posted, cpu) ==
- per_cpu(rcu_nonlazy_posted_snap, cpu))) {
+ if (!rdtp->idle_first_pass &&
+ (rdtp->nonlazy_posted == rdtp->nonlazy_posted_snap)) {
if (rcu_cpu_has_callbacks(cpu)) {
- tp = &per_cpu(rcu_idle_gp_timer, cpu);
- mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
+ tp = &rdtp->idle_gp_timer;
+ mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
}
return;
}
- per_cpu(rcu_idle_first_pass, cpu) = 0;
- per_cpu(rcu_nonlazy_posted_snap, cpu) =
- per_cpu(rcu_nonlazy_posted, cpu) - 1;
+ rdtp->idle_first_pass = 0;
+ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted - 1;
/*
* If there are no callbacks on this CPU, enter dyntick-idle mode.
* Also reset state to avoid prejudicing later attempts.
*/
if (!rcu_cpu_has_callbacks(cpu)) {
- per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
- per_cpu(rcu_dyntick_drain, cpu) = 0;
+ rdtp->dyntick_holdoff = jiffies - 1;
+ rdtp->dyntick_drain = 0;
trace_rcu_prep_idle("No callbacks");
return;
}
@@ -2152,36 +2169,37 @@ static void rcu_prepare_for_idle(int cpu)
* If in holdoff mode, just return. We will presumably have
* refrained from disabling the scheduling-clock tick.
*/
- if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) {
+ if (rdtp->dyntick_holdoff == jiffies) {
trace_rcu_prep_idle("In holdoff");
return;
}
- /* Check and update the rcu_dyntick_drain sequencing. */
- if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+ /* Check and update the ->dyntick_drain sequencing. */
+ if (rdtp->dyntick_drain <= 0) {
/* First time through, initialize the counter. */
- per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES;
- } else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES &&
+ rdtp->dyntick_drain = RCU_IDLE_FLUSHES;
+ } else if (rdtp->dyntick_drain <= RCU_IDLE_OPT_FLUSHES &&
!rcu_pending(cpu) &&
!local_softirq_pending()) {
/* Can we go dyntick-idle despite still having callbacks? */
- trace_rcu_prep_idle("Dyntick with callbacks");
- per_cpu(rcu_dyntick_drain, cpu) = 0;
- per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
- if (rcu_cpu_has_nonlazy_callbacks(cpu))
- per_cpu(rcu_idle_gp_timer_expires, cpu) =
+ rdtp->dyntick_drain = 0;
+ rdtp->dyntick_holdoff = jiffies;
+ if (rcu_cpu_has_nonlazy_callbacks(cpu)) {
+ trace_rcu_prep_idle("Dyntick with callbacks");
+ rdtp->idle_gp_timer_expires =
jiffies + RCU_IDLE_GP_DELAY;
- else
- per_cpu(rcu_idle_gp_timer_expires, cpu) =
+ } else {
+ rdtp->idle_gp_timer_expires =
jiffies + RCU_IDLE_LAZY_GP_DELAY;
- tp = &per_cpu(rcu_idle_gp_timer, cpu);
- mod_timer_pinned(tp, per_cpu(rcu_idle_gp_timer_expires, cpu));
- per_cpu(rcu_nonlazy_posted_snap, cpu) =
- per_cpu(rcu_nonlazy_posted, cpu);
+ trace_rcu_prep_idle("Dyntick with lazy callbacks");
+ }
+ tp = &rdtp->idle_gp_timer;
+ mod_timer_pinned(tp, rdtp->idle_gp_timer_expires);
+ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
return; /* Nothing more to do immediately. */
- } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+ } else if (--(rdtp->dyntick_drain) <= 0) {
/* We have hit the limit, so time to give up. */
- per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
+ rdtp->dyntick_holdoff = jiffies;
trace_rcu_prep_idle("Begin holdoff");
invoke_rcu_core(); /* Force the CPU out of dyntick-idle. */
return;
@@ -2227,7 +2245,7 @@ static void rcu_prepare_for_idle(int cpu)
*/
static void rcu_idle_count_callbacks_posted(void)
{
- __this_cpu_add(rcu_nonlazy_posted, 1);
+ __this_cpu_add(rcu_dynticks.nonlazy_posted, 1);
}
#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
@@ -2238,11 +2256,12 @@ static void rcu_idle_count_callbacks_posted(void)
static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
{
- struct timer_list *tltp = &per_cpu(rcu_idle_gp_timer, cpu);
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+ struct timer_list *tltp = &rdtp->idle_gp_timer;
sprintf(cp, "drain=%d %c timer=%lu",
- per_cpu(rcu_dyntick_drain, cpu),
- per_cpu(rcu_dyntick_holdoff, cpu) == jiffies ? 'H' : '.',
+ rdtp->dyntick_drain,
+ rdtp->dyntick_holdoff == jiffies ? 'H' : '.',
timer_pending(tltp) ? tltp->expires - jiffies : -1);
}
diff --git a/kernel/relay.c b/kernel/relay.c
index ab56a1764d4d..e8cd2027abbd 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in,
struct splice_pipe_desc spd = {
.pages = pages,
.nr_pages = 0,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.partial = partial,
.flags = flags,
.ops = &relay_pipe_buf_ops,
@@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in,
ret += padding;
out:
- splice_shrink_spd(pipe, &spd);
- return ret;
+ splice_shrink_spd(&spd);
+ return ret;
}
static ssize_t relay_file_splice_read(struct file *in,
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index bebe2b170d49..ad581aa2369a 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -94,13 +94,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
counter->usage -= val;
}
-void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+void res_counter_uncharge_until(struct res_counter *counter,
+ struct res_counter *top,
+ unsigned long val)
{
unsigned long flags;
struct res_counter *c;
local_irq_save(flags);
- for (c = counter; c != NULL; c = c->parent) {
+ for (c = counter; c != top; c = c->parent) {
spin_lock(&c->lock);
res_counter_uncharge_locked(c, val);
spin_unlock(&c->lock);
@@ -108,6 +110,10 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
local_irq_restore(flags);
}
+void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+{
+ res_counter_uncharge_until(counter, NULL, val);
+}
static inline unsigned long long *
res_counter_member(struct res_counter *counter, int member)
diff --git a/kernel/resource.c b/kernel/resource.c
index 7e8ea66a8c01..e1d2b8ee76d5 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -515,8 +515,8 @@ out:
* @root: root resource descriptor
* @new: resource descriptor desired by caller
* @size: requested resource region size
- * @min: minimum size to allocate
- * @max: maximum size to allocate
+ * @min: minimum boundary to allocate
+ * @max: maximum boundary to allocate
* @align: alignment requested, in bytes
* @alignf: alignment function, optional, called if not NULL
* @alignf_data: arbitrary data to pass to the @alignf function
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d833cc94eedc..468bdd44c1ba 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -142,9 +142,8 @@ const_debug unsigned int sysctl_sched_features =
#define SCHED_FEAT(name, enabled) \
#name ,
-static __read_mostly char *sched_feat_names[] = {
+static const char * const sched_feat_names[] = {
#include "features.h"
- NULL
};
#undef SCHED_FEAT
@@ -1912,7 +1911,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
sched_info_switch(prev, next);
- perf_event_task_sched(prev, next);
+ perf_event_task_sched_out(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
@@ -1955,6 +1954,13 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
*/
prev_state = prev->state;
finish_arch_switch(prev);
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ local_irq_disable();
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+ perf_event_task_sched_in(prev, current);
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+ local_irq_enable();
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
@@ -2075,7 +2081,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
#endif
/* Here we just switch the register state and the stack. */
- rcu_switch_from(prev);
switch_to(prev, next, prev);
barrier();
@@ -2155,11 +2160,73 @@ unsigned long this_cpu_load(void)
}
+/*
+ * Global load-average calculations
+ *
+ * We take a distributed and async approach to calculating the global load-avg
+ * in order to minimize overhead.
+ *
+ * The global load average is an exponentially decaying average of nr_running +
+ * nr_uninterruptible.
+ *
+ * Once every LOAD_FREQ:
+ *
+ * nr_active = 0;
+ * for_each_possible_cpu(cpu)
+ * nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
+ *
+ * avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
+ *
+ * Due to a number of reasons the above turns in the mess below:
+ *
+ * - for_each_possible_cpu() is prohibitively expensive on machines with
+ * serious number of cpus, therefore we need to take a distributed approach
+ * to calculating nr_active.
+ *
+ * \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
+ * = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
+ *
+ * So assuming nr_active := 0 when we start out -- true per definition, we
+ * can simply take per-cpu deltas and fold those into a global accumulate
+ * to obtain the same result. See calc_load_fold_active().
+ *
+ * Furthermore, in order to avoid synchronizing all per-cpu delta folding
+ * across the machine, we assume 10 ticks is sufficient time for every
+ * cpu to have completed this task.
+ *
+ * This places an upper-bound on the IRQ-off latency of the machine. Then
+ * again, being late doesn't loose the delta, just wrecks the sample.
+ *
+ * - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
+ * this would add another cross-cpu cacheline miss and atomic operation
+ * to the wakeup path. Instead we increment on whatever cpu the task ran
+ * when it went into uninterruptible state and decrement on whatever cpu
+ * did the wakeup. This means that only the sum of nr_uninterruptible over
+ * all cpus yields the correct result.
+ *
+ * This covers the NO_HZ=n code, for extra head-aches, see the comment below.
+ */
+
/* Variables and functions for calc_load */
static atomic_long_t calc_load_tasks;
static unsigned long calc_load_update;
unsigned long avenrun[3];
-EXPORT_SYMBOL(avenrun);
+EXPORT_SYMBOL(avenrun); /* should be removed */
+
+/**
+ * get_avenrun - get the load average array
+ * @loads: pointer to dest load array
+ * @offset: offset to add
+ * @shift: shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+ loads[0] = (avenrun[0] + offset) << shift;
+ loads[1] = (avenrun[1] + offset) << shift;
+ loads[2] = (avenrun[2] + offset) << shift;
+}
static long calc_load_fold_active(struct rq *this_rq)
{
@@ -2176,6 +2243,9 @@ static long calc_load_fold_active(struct rq *this_rq)
return delta;
}
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
static unsigned long
calc_load(unsigned long load, unsigned long exp, unsigned long active)
{
@@ -2187,30 +2257,118 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active)
#ifdef CONFIG_NO_HZ
/*
- * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
+ * Handle NO_HZ for the global load-average.
+ *
+ * Since the above described distributed algorithm to compute the global
+ * load-average relies on per-cpu sampling from the tick, it is affected by
+ * NO_HZ.
+ *
+ * The basic idea is to fold the nr_active delta into a global idle-delta upon
+ * entering NO_HZ state such that we can include this as an 'extra' cpu delta
+ * when we read the global state.
+ *
+ * Obviously reality has to ruin such a delightfully simple scheme:
+ *
+ * - When we go NO_HZ idle during the window, we can negate our sample
+ * contribution, causing under-accounting.
+ *
+ * We avoid this by keeping two idle-delta counters and flipping them
+ * when the window starts, thus separating old and new NO_HZ load.
+ *
+ * The only trick is the slight shift in index flip for read vs write.
+ *
+ * 0s 5s 10s 15s
+ * +10 +10 +10 +10
+ * |-|-----------|-|-----------|-|-----------|-|
+ * r:0 0 1 1 0 0 1 1 0
+ * w:0 1 1 0 0 1 1 0 0
+ *
+ * This ensures we'll fold the old idle contribution in this window while
+ * accumlating the new one.
+ *
+ * - When we wake up from NO_HZ idle during the window, we push up our
+ * contribution, since we effectively move our sample point to a known
+ * busy state.
+ *
+ * This is solved by pushing the window forward, and thus skipping the
+ * sample, for this cpu (effectively using the idle-delta for this cpu which
+ * was in effect at the time the window opened). This also solves the issue
+ * of having to deal with a cpu having been in NOHZ idle for multiple
+ * LOAD_FREQ intervals.
*
* When making the ILB scale, we should try to pull this in as well.
*/
-static atomic_long_t calc_load_tasks_idle;
+static atomic_long_t calc_load_idle[2];
+static int calc_load_idx;
-void calc_load_account_idle(struct rq *this_rq)
+static inline int calc_load_write_idx(void)
{
+ int idx = calc_load_idx;
+
+ /*
+ * See calc_global_nohz(), if we observe the new index, we also
+ * need to observe the new update time.
+ */
+ smp_rmb();
+
+ /*
+ * If the folding window started, make sure we start writing in the
+ * next idle-delta.
+ */
+ if (!time_before(jiffies, calc_load_update))
+ idx++;
+
+ return idx & 1;
+}
+
+static inline int calc_load_read_idx(void)
+{
+ return calc_load_idx & 1;
+}
+
+void calc_load_enter_idle(void)
+{
+ struct rq *this_rq = this_rq();
long delta;
+ /*
+ * We're going into NOHZ mode, if there's any pending delta, fold it
+ * into the pending idle delta.
+ */
delta = calc_load_fold_active(this_rq);
- if (delta)
- atomic_long_add(delta, &calc_load_tasks_idle);
+ if (delta) {
+ int idx = calc_load_write_idx();
+ atomic_long_add(delta, &calc_load_idle[idx]);
+ }
}
-static long calc_load_fold_idle(void)
+void calc_load_exit_idle(void)
{
- long delta = 0;
+ struct rq *this_rq = this_rq();
/*
- * Its got a race, we don't care...
+ * If we're still before the sample window, we're done.
*/
- if (atomic_long_read(&calc_load_tasks_idle))
- delta = atomic_long_xchg(&calc_load_tasks_idle, 0);
+ if (time_before(jiffies, this_rq->calc_load_update))
+ return;
+
+ /*
+ * We woke inside or after the sample window, this means we're already
+ * accounted through the nohz accounting, so skip the entire deal and
+ * sync up for the next window.
+ */
+ this_rq->calc_load_update = calc_load_update;
+ if (time_before(jiffies, this_rq->calc_load_update + 10))
+ this_rq->calc_load_update += LOAD_FREQ;
+}
+
+static long calc_load_fold_idle(void)
+{
+ int idx = calc_load_read_idx();
+ long delta = 0;
+
+ if (atomic_long_read(&calc_load_idle[idx]))
+ delta = atomic_long_xchg(&calc_load_idle[idx], 0);
return delta;
}
@@ -2296,66 +2454,39 @@ static void calc_global_nohz(void)
{
long delta, active, n;
- /*
- * If we crossed a calc_load_update boundary, make sure to fold
- * any pending idle changes, the respective CPUs might have
- * missed the tick driven calc_load_account_active() update
- * due to NO_HZ.
- */
- delta = calc_load_fold_idle();
- if (delta)
- atomic_long_add(delta, &calc_load_tasks);
-
- /*
- * It could be the one fold was all it took, we done!
- */
- if (time_before(jiffies, calc_load_update + 10))
- return;
-
- /*
- * Catch-up, fold however many we are behind still
- */
- delta = jiffies - calc_load_update - 10;
- n = 1 + (delta / LOAD_FREQ);
+ if (!time_before(jiffies, calc_load_update + 10)) {
+ /*
+ * Catch-up, fold however many we are behind still
+ */
+ delta = jiffies - calc_load_update - 10;
+ n = 1 + (delta / LOAD_FREQ);
- active = atomic_long_read(&calc_load_tasks);
- active = active > 0 ? active * FIXED_1 : 0;
+ active = atomic_long_read(&calc_load_tasks);
+ active = active > 0 ? active * FIXED_1 : 0;
- avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
- avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
- avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+ avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+ avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+ avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
- calc_load_update += n * LOAD_FREQ;
-}
-#else
-void calc_load_account_idle(struct rq *this_rq)
-{
-}
+ calc_load_update += n * LOAD_FREQ;
+ }
-static inline long calc_load_fold_idle(void)
-{
- return 0;
+ /*
+ * Flip the idle index...
+ *
+ * Make sure we first write the new time then flip the index, so that
+ * calc_load_write_idx() will see the new time when it reads the new
+ * index, this avoids a double flip messing things up.
+ */
+ smp_wmb();
+ calc_load_idx++;
}
+#else /* !CONFIG_NO_HZ */
-static void calc_global_nohz(void)
-{
-}
-#endif
+static inline long calc_load_fold_idle(void) { return 0; }
+static inline void calc_global_nohz(void) { }
-/**
- * get_avenrun - get the load average array
- * @loads: pointer to dest load array
- * @offset: offset to add
- * @shift: shift count to shift the result left
- *
- * These values are estimates at best, so no need for locking.
- */
-void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
-{
- loads[0] = (avenrun[0] + offset) << shift;
- loads[1] = (avenrun[1] + offset) << shift;
- loads[2] = (avenrun[2] + offset) << shift;
-}
+#endif /* CONFIG_NO_HZ */
/*
* calc_load - update the avenrun load estimates 10 ticks after the
@@ -2363,11 +2494,18 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
*/
void calc_global_load(unsigned long ticks)
{
- long active;
+ long active, delta;
if (time_before(jiffies, calc_load_update + 10))
return;
+ /*
+ * Fold the 'old' idle-delta to include all NO_HZ cpus.
+ */
+ delta = calc_load_fold_idle();
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
+
active = atomic_long_read(&calc_load_tasks);
active = active > 0 ? active * FIXED_1 : 0;
@@ -2378,12 +2516,7 @@ void calc_global_load(unsigned long ticks)
calc_load_update += LOAD_FREQ;
/*
- * Account one period with whatever state we found before
- * folding in the nohz state and ageing the entire idle period.
- *
- * This avoids loosing a sample when we go idle between
- * calc_load_account_active() (10 ticks ago) and now and thus
- * under-accounting.
+ * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
*/
calc_global_nohz();
}
@@ -2400,7 +2533,6 @@ static void calc_load_account_active(struct rq *this_rq)
return;
delta = calc_load_fold_active(this_rq);
- delta += calc_load_fold_idle();
if (delta)
atomic_long_add(delta, &calc_load_tasks);
@@ -2408,6 +2540,10 @@ static void calc_load_account_active(struct rq *this_rq)
}
/*
+ * End of global load-average stuff
+ */
+
+/*
* The exact cpuload at various idx values, calculated at every tick would be
* load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
*
@@ -2510,25 +2646,32 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
sched_avg_update(this_rq);
}
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
/*
* Called from nohz_idle_balance() to update the load ratings before doing the
* idle balance.
*/
void update_idle_cpu_load(struct rq *this_rq)
{
- unsigned long curr_jiffies = jiffies;
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
unsigned long load = this_rq->load.weight;
unsigned long pending_updates;
/*
- * Bloody broken means of dealing with nohz, but better than nothing..
- * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
- * update and see 0 difference the one time and 2 the next, even though
- * we ticked at roughtly the same rate.
- *
- * Hence we only use this from nohz_idle_balance() and skip this
- * nonsense when called from the scheduler_tick() since that's
- * guaranteed a stable rate.
+ * bail if there's load or we're actually up-to-date.
*/
if (load || curr_jiffies == this_rq->last_load_update_tick)
return;
@@ -2540,12 +2683,38 @@ void update_idle_cpu_load(struct rq *this_rq)
}
/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
* Called from scheduler_tick()
*/
static void update_cpu_load_active(struct rq *this_rq)
{
/*
- * See the mess in update_idle_cpu_load().
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
*/
this_rq->last_load_update_tick = jiffies;
__update_cpu_load(this_rq, this_rq->load.weight, 1);
@@ -4063,11 +4232,8 @@ static bool check_same_owner(struct task_struct *p)
rcu_read_lock();
pcred = __task_cred(p);
- if (cred->user->user_ns == pcred->user->user_ns)
- match = (cred->euid == pcred->euid ||
- cred->euid == pcred->uid);
- else
- match = false;
+ match = (uid_eq(cred->euid, pcred->euid) ||
+ uid_eq(cred->euid, pcred->uid));
rcu_read_unlock();
return match;
}
@@ -4978,7 +5144,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
p->sched_class->set_cpus_allowed(p, new_mask);
cpumask_copy(&p->cpus_allowed, new_mask);
- p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+ p->nr_cpus_allowed = cpumask_weight(new_mask);
}
/*
@@ -5520,15 +5686,20 @@ static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
#ifdef CONFIG_SCHED_DEBUG
-static __read_mostly int sched_domain_debug_enabled;
+static __read_mostly int sched_debug_enabled;
-static int __init sched_domain_debug_setup(char *str)
+static int __init sched_debug_setup(char *str)
{
- sched_domain_debug_enabled = 1;
+ sched_debug_enabled = 1;
return 0;
}
-early_param("sched_debug", sched_domain_debug_setup);
+early_param("sched_debug", sched_debug_setup);
+
+static inline bool sched_debug(void)
+{
+ return sched_debug_enabled;
+}
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
@@ -5568,7 +5739,12 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
break;
}
- if (!group->sgp->power) {
+ /*
+ * Even though we initialize ->power to something semi-sane,
+ * we leave power_orig unset. This allows us to detect if
+ * domain iteration is still funny without causing /0 traps.
+ */
+ if (!group->sgp->power_orig) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
@@ -5616,7 +5792,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
int level = 0;
- if (!sched_domain_debug_enabled)
+ if (!sched_debug_enabled)
return;
if (!sd) {
@@ -5637,6 +5813,10 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
+static inline bool sched_debug(void)
+{
+ return false;
+}
#endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd)
@@ -5958,6 +6138,44 @@ struct sched_domain_topology_level {
struct sd_data data;
};
+/*
+ * Build an iteration mask that can exclude certain CPUs from the upwards
+ * domain traversal.
+ *
+ * Asymmetric node setups can result in situations where the domain tree is of
+ * unequal depth, make sure to skip domains that already cover the entire
+ * range.
+ *
+ * In that case build_sched_domains() will have terminated the iteration early
+ * and our sibling sd spans will be empty. Domains should always include the
+ * cpu they're built on, so check that.
+ *
+ */
+static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+{
+ const struct cpumask *span = sched_domain_span(sd);
+ struct sd_data *sdd = sd->private;
+ struct sched_domain *sibling;
+ int i;
+
+ for_each_cpu(i, span) {
+ sibling = *per_cpu_ptr(sdd->sd, i);
+ if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+ continue;
+
+ cpumask_set_cpu(i, sched_group_mask(sg));
+ }
+}
+
+/*
+ * Return the canonical balance cpu for this group, this is the first cpu
+ * of this group that's also in the iteration mask.
+ */
+int group_balance_cpu(struct sched_group *sg)
+{
+ return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+}
+
static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
@@ -5976,6 +6194,12 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
if (cpumask_test_cpu(i, covered))
continue;
+ child = *per_cpu_ptr(sdd->sd, i);
+
+ /* See the comment near build_group_mask(). */
+ if (!cpumask_test_cpu(i, sched_domain_span(child)))
+ continue;
+
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, cpu_to_node(cpu));
@@ -5983,8 +6207,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
goto fail;
sg_span = sched_group_cpus(sg);
-
- child = *per_cpu_ptr(sdd->sd, i);
if (child->child) {
child = child->child;
cpumask_copy(sg_span, sched_domain_span(child));
@@ -5993,10 +6215,24 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
cpumask_or(covered, covered, sg_span);
- sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
- atomic_inc(&sg->sgp->ref);
+ sg->sgp = *per_cpu_ptr(sdd->sgp, i);
+ if (atomic_inc_return(&sg->sgp->ref) == 1)
+ build_group_mask(sd, sg);
+
+ /*
+ * Initialize sgp->power such that even if we mess up the
+ * domains and no possible iteration will get us here, we won't
+ * die on a /0 trap.
+ */
+ sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
- if (cpumask_test_cpu(cpu, sg_span))
+ /*
+ * Make sure the first group of this domain contains the
+ * canonical balance cpu. Otherwise the sched_domain iteration
+ * breaks. See update_sg_lb_stats().
+ */
+ if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+ group_balance_cpu(sg) == cpu)
groups = sg;
if (!first)
@@ -6070,6 +6306,7 @@ build_sched_groups(struct sched_domain *sd, int cpu)
cpumask_clear(sched_group_cpus(sg));
sg->sgp->power = 0;
+ cpumask_setall(sched_group_mask(sg));
for_each_cpu(j, span) {
if (get_group(j, sdd, NULL) != group)
@@ -6111,7 +6348,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
sg = sg->next;
} while (sg != sd->groups);
- if (cpu != group_first_cpu(sg))
+ if (cpu != group_balance_cpu(sg))
return;
update_group_power(sd, cpu);
@@ -6161,11 +6398,8 @@ int sched_domain_level_max;
static int __init setup_relax_domain_level(char *str)
{
- unsigned long val;
-
- val = simple_strtoul(str, NULL, 0);
- if (val < sched_domain_level_max)
- default_relax_domain_level = val;
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+ pr_warn("Unable to set relax_domain_level\n");
return 1;
}
@@ -6275,14 +6509,13 @@ static struct sched_domain_topology_level *sched_domain_topology = default_topol
#ifdef CONFIG_NUMA
static int sched_domains_numa_levels;
-static int sched_domains_numa_scale;
static int *sched_domains_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
static int sched_domains_curr_level;
static inline int sd_local_flags(int level)
{
- if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+ if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
return 0;
return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
@@ -6340,6 +6573,42 @@ static const struct cpumask *sd_numa_mask(int cpu)
return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
}
+static void sched_numa_warn(const char *str)
+{
+ static int done = false;
+ int i,j;
+
+ if (done)
+ return;
+
+ done = true;
+
+ printk(KERN_WARNING "ERROR: %s\n\n", str);
+
+ for (i = 0; i < nr_node_ids; i++) {
+ printk(KERN_WARNING " ");
+ for (j = 0; j < nr_node_ids; j++)
+ printk(KERN_CONT "%02d ", node_distance(i,j));
+ printk(KERN_CONT "\n");
+ }
+ printk(KERN_WARNING "\n");
+}
+
+static bool find_numa_distance(int distance)
+{
+ int i;
+
+ if (distance == node_distance(0, 0))
+ return true;
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ if (sched_domains_numa_distance[i] == distance)
+ return true;
+ }
+
+ return false;
+}
+
static void sched_init_numa(void)
{
int next_distance, curr_distance = node_distance(0, 0);
@@ -6347,7 +6616,6 @@ static void sched_init_numa(void)
int level = 0;
int i, j, k;
- sched_domains_numa_scale = curr_distance;
sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
if (!sched_domains_numa_distance)
return;
@@ -6358,23 +6626,41 @@ static void sched_init_numa(void)
*
* Assumes node_distance(0,j) includes all distances in
* node_distance(i,j) in order to avoid cubic time.
- *
- * XXX: could be optimized to O(n log n) by using sort()
*/
next_distance = curr_distance;
for (i = 0; i < nr_node_ids; i++) {
for (j = 0; j < nr_node_ids; j++) {
- int distance = node_distance(0, j);
- if (distance > curr_distance &&
- (distance < next_distance ||
- next_distance == curr_distance))
- next_distance = distance;
+ for (k = 0; k < nr_node_ids; k++) {
+ int distance = node_distance(i, k);
+
+ if (distance > curr_distance &&
+ (distance < next_distance ||
+ next_distance == curr_distance))
+ next_distance = distance;
+
+ /*
+ * While not a strong assumption it would be nice to know
+ * about cases where if node A is connected to B, B is not
+ * equally connected to A.
+ */
+ if (sched_debug() && node_distance(k, i) != distance)
+ sched_numa_warn("Node-distance not symmetric");
+
+ if (sched_debug() && i && !find_numa_distance(distance))
+ sched_numa_warn("Node-0 not representative");
+ }
+ if (next_distance != curr_distance) {
+ sched_domains_numa_distance[level++] = next_distance;
+ sched_domains_numa_levels = level;
+ curr_distance = next_distance;
+ } else break;
}
- if (next_distance != curr_distance) {
- sched_domains_numa_distance[level++] = next_distance;
- sched_domains_numa_levels = level;
- curr_distance = next_distance;
- } else break;
+
+ /*
+ * In case of sched_debug() we verify the above assumption.
+ */
+ if (!sched_debug())
+ break;
}
/*
* 'level' contains the number of unique distances, excluding the
@@ -6399,7 +6685,7 @@ static void sched_init_numa(void)
return;
for (j = 0; j < nr_node_ids; j++) {
- struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+ struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
if (!mask)
return;
@@ -6486,7 +6772,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
*per_cpu_ptr(sdd->sg, j) = sg;
- sgp = kzalloc_node(sizeof(struct sched_group_power),
+ sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sgp)
return -ENOMEM;
@@ -6539,7 +6825,6 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
if (!sd)
return child;
- set_domain_attribute(sd, attr);
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
@@ -6547,6 +6832,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
child->parent = sd;
}
sd->child = child;
+ set_domain_attribute(sd, attr);
return sd;
}
@@ -6687,7 +6973,6 @@ static int init_sched_domains(const struct cpumask *cpu_map)
if (!doms_cur)
doms_cur = &fallback_doms;
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
- dattr_cur = NULL;
err = build_sched_domains(doms_cur[0], NULL);
register_sched_domain_sysctl();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d17cf96..c099cc6eebe3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2703,7 +2703,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
int want_sd = 1;
int sync = wake_flags & WF_SYNC;
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
return prev_cpu;
if (sd_flag & SD_BALANCE_WAKE) {
@@ -3503,15 +3503,22 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
unsigned long scale_rt_power(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, available;
+ u64 total, available, age_stamp, avg;
- total = sched_avg_period() + (rq->clock - rq->age_stamp);
+ /*
+ * Since we're reading these variables without serialization make sure
+ * we read them once before doing sanity checks on them.
+ */
+ age_stamp = ACCESS_ONCE(rq->age_stamp);
+ avg = ACCESS_ONCE(rq->rt_avg);
+
+ total = sched_avg_period() + (rq->clock - age_stamp);
- if (unlikely(total < rq->rt_avg)) {
+ if (unlikely(total < avg)) {
/* Ensures that power won't end up being negative */
available = 0;
} else {
- available = total - rq->rt_avg;
+ available = total - avg;
}
if (unlikely((s64)total < SCHED_POWER_SCALE))
@@ -3574,13 +3581,28 @@ void update_group_power(struct sched_domain *sd, int cpu)
power = 0;
- group = child->groups;
- do {
- power += group->sgp->power;
- group = group->next;
- } while (group != child->groups);
+ if (child->flags & SD_OVERLAP) {
+ /*
+ * SD_OVERLAP domains cannot assume that child groups
+ * span the current group.
+ */
- sdg->sgp->power = power;
+ for_each_cpu(cpu, sched_group_cpus(sdg))
+ power += power_of(cpu);
+ } else {
+ /*
+ * !SD_OVERLAP domains can assume that child groups
+ * span the current group.
+ */
+
+ group = child->groups;
+ do {
+ power += group->sgp->power;
+ group = group->next;
+ } while (group != child->groups);
+ }
+
+ sdg->sgp->power_orig = sdg->sgp->power = power;
}
/*
@@ -3610,7 +3632,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
+ * @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
* @load_idx: Load index of sched_domain of this_cpu for load calc.
* @local_group: Does group contain this_cpu.
@@ -3630,7 +3652,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
int i;
if (local_group)
- balance_cpu = group_first_cpu(group);
+ balance_cpu = group_balance_cpu(group);
/* Tally up the load of all CPUs in the group */
max_cpu_load = 0;
@@ -3645,7 +3667,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
/* Bias balancing toward cpus of our domain */
if (local_group) {
- if (idle_cpu(i) && !first_idle_cpu) {
+ if (idle_cpu(i) && !first_idle_cpu &&
+ cpumask_test_cpu(i, sched_group_mask(group))) {
first_idle_cpu = 1;
balance_cpu = i;
}
@@ -3719,11 +3742,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
/**
* update_sd_pick_busiest - return 1 on busiest group
- * @sd: sched_domain whose statistics are to be checked
+ * @env: The load balancing environment.
* @sds: sched_domain statistics
* @sg: sched_group candidate to be checked for being the busiest
* @sgs: sched_group statistics
- * @this_cpu: the current cpu
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
@@ -3761,9 +3783,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
+ * @env: The load balancing environment.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
@@ -3852,10 +3872,8 @@ static inline void update_sd_lb_stats(struct lb_env *env,
* Returns 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
- * @sd: The sched_domain whose packing is to be checked.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain which is to be packed
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: returns amount of imbalanced due to packing.
*/
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
{
@@ -3881,9 +3899,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
* fix_small_imbalance - Calculate the minor imbalance that exists
* amongst the groups of a sched_domain, during
* load balancing.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: Variable to store the imbalance.
*/
static inline
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
@@ -4026,11 +4043,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
* Also calculates the amount of weighted load which should be moved
* to restore balance.
*
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- * be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
+ * @env: The load balancing environment.
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index b44d604b35d1..b6baf370cae9 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -25,7 +25,6 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
static struct task_struct *pick_next_task_idle(struct rq *rq)
{
schedstat_inc(rq, sched_goidle);
- calc_load_account_idle(rq);
return rq->idle;
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c5565c3c515f..573e1ca01102 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -274,13 +274,16 @@ static void update_rt_migration(struct rt_rq *rt_rq)
static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total++;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory++;
update_rt_migration(rt_rq);
@@ -288,13 +291,16 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total--;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory--;
update_rt_migration(rt_rq);
@@ -1161,7 +1167,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
- if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
inc_nr_running(rq);
@@ -1225,7 +1231,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
cpu = task_cpu(p);
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
goto out;
/* For anything but wake ups, just return the task_cpu */
@@ -1260,9 +1266,9 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
* will have to sort it out.
*/
if (curr && unlikely(rt_task(curr)) &&
- (curr->rt.nr_cpus_allowed < 2 ||
+ (curr->nr_cpus_allowed < 2 ||
curr->prio <= p->prio) &&
- (p->rt.nr_cpus_allowed > 1)) {
+ (p->nr_cpus_allowed > 1)) {
int target = find_lowest_rq(p);
if (target != -1)
@@ -1276,10 +1282,10 @@ out:
static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
- if (rq->curr->rt.nr_cpus_allowed == 1)
+ if (rq->curr->nr_cpus_allowed == 1)
return;
- if (p->rt.nr_cpus_allowed != 1
+ if (p->nr_cpus_allowed != 1
&& cpupri_find(&rq->rd->cpupri, p, NULL))
return;
@@ -1395,7 +1401,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
* The previous task needs to be made eligible for pushing
* if it is still active
*/
- if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
+ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
}
@@ -1408,7 +1414,7 @@ static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
if (!task_running(rq, p) &&
(cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
- (p->rt.nr_cpus_allowed > 1))
+ (p->nr_cpus_allowed > 1))
return 1;
return 0;
}
@@ -1464,7 +1470,7 @@ static int find_lowest_rq(struct task_struct *task)
if (unlikely(!lowest_mask))
return -1;
- if (task->rt.nr_cpus_allowed == 1)
+ if (task->nr_cpus_allowed == 1)
return -1; /* No other targets possible */
if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
@@ -1556,7 +1562,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
task_running(rq, task) ||
!task->on_rq)) {
- raw_spin_unlock(&lowest_rq->lock);
+ double_unlock_balance(rq, lowest_rq);
lowest_rq = NULL;
break;
}
@@ -1586,7 +1592,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
BUG_ON(rq->cpu != task_cpu(p));
BUG_ON(task_current(rq, p));
- BUG_ON(p->rt.nr_cpus_allowed <= 1);
+ BUG_ON(p->nr_cpus_allowed <= 1);
BUG_ON(!p->on_rq);
BUG_ON(!rt_task(p));
@@ -1793,9 +1799,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
if (!task_running(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
- p->rt.nr_cpus_allowed > 1 &&
+ p->nr_cpus_allowed > 1 &&
rt_task(rq->curr) &&
- (rq->curr->rt.nr_cpus_allowed < 2 ||
+ (rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
}
@@ -1817,7 +1823,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
* Only update if the process changes its state from whether it
* can migrate or not.
*/
- if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
return;
rq = task_rq(p);
@@ -1979,6 +1985,8 @@ static void watchdog(struct rq *rq, struct task_struct *p)
static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
+ struct sched_rt_entity *rt_se = &p->rt;
+
update_curr_rt(rq);
watchdog(rq, p);
@@ -1996,12 +2004,15 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
p->rt.time_slice = RR_TIMESLICE;
/*
- * Requeue to the end of queue if we are not the only element
- * on the queue:
+ * Requeue to the end of queue if we (and all of our ancestors) are the
+ * only element on the queue
*/
- if (p->rt.run_list.prev != p->rt.run_list.next) {
- requeue_task_rt(rq, p, 0);
- set_tsk_need_resched(p);
+ for_each_sched_rt_entity(rt_se) {
+ if (rt_se->run_list.prev != rt_se->run_list.next) {
+ requeue_task_rt(rq, p, 0);
+ set_tsk_need_resched(p);
+ return;
+ }
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ba9dccfd24ce..55844f24435a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -526,6 +526,8 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_id);
+extern int group_balance_cpu(struct sched_group *sg);
+
#endif /* CONFIG_SMP */
#include "stats.h"
@@ -940,8 +942,6 @@ static inline u64 sched_avg_period(void)
return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
}
-void calc_load_account_idle(struct rq *this_rq);
-
#ifdef CONFIG_SCHED_HRTICK
/*
diff --git a/kernel/semaphore.c b/kernel/semaphore.c
index 60636a4e25c3..4567fc020fe3 100644
--- a/kernel/semaphore.c
+++ b/kernel/semaphore.c
@@ -118,7 +118,7 @@ EXPORT_SYMBOL(down_killable);
* down_trylock - try to acquire the semaphore, without waiting
* @sem: the semaphore to be acquired
*
- * Try to acquire the semaphore atomically. Returns 0 if the mutex has
+ * Try to acquire the semaphore atomically. Returns 0 if the semaphore has
* been acquired successfully or 1 if it it cannot be acquired.
*
* NOTE: This return value is inverted from both spin_trylock and
diff --git a/kernel/signal.c b/kernel/signal.c
index 1a006b5d9d9d..677102789cf2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -29,6 +29,7 @@
#include <linux/pid_namespace.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
+#include <linux/uprobes.h>
#define CREATE_TRACE_POINTS
#include <trace/events/signal.h>
@@ -767,14 +768,13 @@ static int kill_ok_by_cred(struct task_struct *t)
const struct cred *cred = current_cred();
const struct cred *tcred = __task_cred(t);
- if (cred->user->user_ns == tcred->user->user_ns &&
- (cred->euid == tcred->suid ||
- cred->euid == tcred->uid ||
- cred->uid == tcred->suid ||
- cred->uid == tcred->uid))
+ if (uid_eq(cred->euid, tcred->suid) ||
+ uid_eq(cred->euid, tcred->uid) ||
+ uid_eq(cred->uid, tcred->suid) ||
+ uid_eq(cred->uid, tcred->uid))
return 1;
- if (ns_capable(tcred->user->user_ns, CAP_KILL))
+ if (ns_capable(tcred->user_ns, CAP_KILL))
return 1;
return 0;
@@ -1020,15 +1020,6 @@ static inline int legacy_queue(struct sigpending *signals, int sig)
return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
}
-/*
- * map the uid in struct cred into user namespace *ns
- */
-static inline uid_t map_cred_ns(const struct cred *cred,
- struct user_namespace *ns)
-{
- return user_ns_map_uid(ns, cred, cred->uid);
-}
-
#ifdef CONFIG_USER_NS
static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t)
{
@@ -1038,8 +1029,10 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str
if (SI_FROMKERNEL(info))
return;
- info->si_uid = user_ns_map_uid(task_cred_xxx(t, user_ns),
- current_cred(), info->si_uid);
+ rcu_read_lock();
+ info->si_uid = from_kuid_munged(task_cred_xxx(t, user_ns),
+ make_kuid(current_user_ns(), info->si_uid));
+ rcu_read_unlock();
}
#else
static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t)
@@ -1106,7 +1099,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
q->info.si_code = SI_USER;
q->info.si_pid = task_tgid_nr_ns(current,
task_active_pid_ns(t));
- q->info.si_uid = current_uid();
+ q->info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
break;
case (unsigned long) SEND_SIG_PRIV:
q->info.si_signo = sig;
@@ -1387,10 +1380,8 @@ static int kill_as_cred_perm(const struct cred *cred,
struct task_struct *target)
{
const struct cred *pcred = __task_cred(target);
- if (cred->user_ns != pcred->user_ns)
- return 0;
- if (cred->euid != pcred->suid && cred->euid != pcred->uid &&
- cred->uid != pcred->suid && cred->uid != pcred->uid)
+ if (!uid_eq(cred->euid, pcred->suid) && !uid_eq(cred->euid, pcred->uid) &&
+ !uid_eq(cred->uid, pcred->suid) && !uid_eq(cred->uid, pcred->uid))
return 0;
return 1;
}
@@ -1665,21 +1656,20 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
info.si_signo = sig;
info.si_errno = 0;
/*
- * we are under tasklist_lock here so our parent is tied to
- * us and cannot exit and release its namespace.
+ * We are under tasklist_lock here so our parent is tied to
+ * us and cannot change.
*
- * the only it can is to switch its nsproxy with sys_unshare,
- * bu uncharing pid namespaces is not allowed, so we'll always
- * see relevant namespace
+ * task_active_pid_ns will always return the same pid namespace
+ * until a task passes through release_task.
*
* write_lock() currently calls preempt_disable() which is the
* same as rcu_read_lock(), but according to Oleg, this is not
* correct to rely on this
*/
rcu_read_lock();
- info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
- info.si_uid = map_cred_ns(__task_cred(tsk),
- task_cred_xxx(tsk->parent, user_ns));
+ info.si_pid = task_pid_nr_ns(tsk, task_active_pid_ns(tsk->parent));
+ info.si_uid = from_kuid_munged(task_cred_xxx(tsk->parent, user_ns),
+ task_uid(tsk));
rcu_read_unlock();
info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime);
@@ -1762,8 +1752,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
*/
rcu_read_lock();
info.si_pid = task_pid_nr_ns(tsk, parent->nsproxy->pid_ns);
- info.si_uid = map_cred_ns(__task_cred(tsk),
- task_cred_xxx(parent, user_ns));
+ info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk));
rcu_read_unlock();
info.si_utime = cputime_to_clock_t(tsk->utime);
@@ -1973,7 +1962,7 @@ static void ptrace_do_notify(int signr, int exit_code, int why)
info.si_signo = signr;
info.si_code = exit_code;
info.si_pid = task_pid_vnr(current);
- info.si_uid = current_uid();
+ info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
/* Let the debugger run. */
ptrace_stop(exit_code, why, 1, &info);
@@ -2181,8 +2170,8 @@ static int ptrace_signal(int signr, siginfo_t *info,
info->si_code = SI_USER;
rcu_read_lock();
info->si_pid = task_pid_vnr(current->parent);
- info->si_uid = map_cred_ns(__task_cred(current->parent),
- current_user_ns());
+ info->si_uid = from_kuid_munged(current_user_ns(),
+ task_uid(current->parent));
rcu_read_unlock();
}
@@ -2202,6 +2191,9 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
struct signal_struct *signal = current->signal;
int signr;
+ if (unlikely(uprobe_deny_signal()))
+ return 0;
+
relock:
/*
* We'll jump back here after any time we were stopped in TASK_STOPPED.
@@ -2376,24 +2368,34 @@ relock:
}
/**
- * block_sigmask - add @ka's signal mask to current->blocked
- * @ka: action for @signr
- * @signr: signal that has been successfully delivered
+ * signal_delivered -
+ * @sig: number of signal being delivered
+ * @info: siginfo_t of signal being delivered
+ * @ka: sigaction setting that chose the handler
+ * @regs: user register state
+ * @stepping: nonzero if debugger single-step or block-step in use
*
* This function should be called when a signal has succesfully been
- * delivered. It adds the mask of signals for @ka to current->blocked
- * so that they are blocked during the execution of the signal
- * handler. In addition, @signr will be blocked unless %SA_NODEFER is
- * set in @ka->sa.sa_flags.
+ * delivered. It updates the blocked signals accordingly (@ka->sa.sa_mask
+ * is always blocked, and the signal itself is blocked unless %SA_NODEFER
+ * is set in @ka->sa.sa_flags. Tracing is notified.
*/
-void block_sigmask(struct k_sigaction *ka, int signr)
+void signal_delivered(int sig, siginfo_t *info, struct k_sigaction *ka,
+ struct pt_regs *regs, int stepping)
{
sigset_t blocked;
+ /* A signal was successfully delivered, and the
+ saved sigmask was stored on the signal frame,
+ and will be restored by sigreturn. So we can
+ simply clear the restore sigmask flag. */
+ clear_restore_sigmask();
+
sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
if (!(ka->sa.sa_flags & SA_NODEFER))
- sigaddset(&blocked, signr);
+ sigaddset(&blocked, sig);
set_current_blocked(&blocked);
+ tracehook_signal_handler(sig, info, ka, regs, stepping);
}
/*
@@ -2526,7 +2528,16 @@ static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset)
* It is wrong to change ->blocked directly, this helper should be used
* to ensure the process can't miss a shared signal we are going to block.
*/
-void set_current_blocked(const sigset_t *newset)
+void set_current_blocked(sigset_t *newset)
+{
+ struct task_struct *tsk = current;
+ sigdelsetmask(newset, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ spin_lock_irq(&tsk->sighand->siglock);
+ __set_task_blocked(tsk, newset);
+ spin_unlock_irq(&tsk->sighand->siglock);
+}
+
+void __set_current_blocked(const sigset_t *newset)
{
struct task_struct *tsk = current;
@@ -2566,7 +2577,7 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset)
return -EINVAL;
}
- set_current_blocked(&newset);
+ __set_current_blocked(&newset);
return 0;
}
@@ -2835,7 +2846,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig)
info.si_errno = 0;
info.si_code = SI_USER;
info.si_pid = task_tgid_vnr(current);
- info.si_uid = current_uid();
+ info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
return kill_something_info(sig, &info, pid);
}
@@ -2878,7 +2889,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig)
info.si_errno = 0;
info.si_code = SI_TKILL;
info.si_pid = task_tgid_vnr(current);
- info.si_uid = current_uid();
+ info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
return do_send_specific(tgid, pid, sig, &info);
}
@@ -3140,7 +3151,7 @@ SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset,
return -EINVAL;
}
- set_current_blocked(&new_blocked);
+ __set_current_blocked(&new_blocked);
}
if (oset) {
@@ -3204,7 +3215,6 @@ SYSCALL_DEFINE1(ssetmask, int, newmask)
int old = current->blocked.sig[0];
sigset_t newset;
- siginitset(&newset, newmask & ~(sigmask(SIGKILL) | sigmask(SIGSTOP)));
set_current_blocked(&newset);
return old;
@@ -3243,6 +3253,17 @@ SYSCALL_DEFINE0(pause)
#endif
+int sigsuspend(sigset_t *set)
+{
+ current->saved_sigmask = current->blocked;
+ set_current_blocked(set);
+
+ current->state = TASK_INTERRUPTIBLE;
+ schedule();
+ set_restore_sigmask();
+ return -ERESTARTNOHAND;
+}
+
#ifdef __ARCH_WANT_SYS_RT_SIGSUSPEND
/**
* sys_rt_sigsuspend - replace the signal mask for a value with the
@@ -3260,15 +3281,7 @@ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize)
if (copy_from_user(&newset, unewset, sizeof(newset)))
return -EFAULT;
- sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP));
-
- current->saved_sigmask = current->blocked;
- set_current_blocked(&newset);
-
- current->state = TASK_INTERRUPTIBLE;
- schedule();
- set_restore_sigmask();
- return -ERESTARTNOHAND;
+ return sigsuspend(&newset);
}
#endif /* __ARCH_WANT_SYS_RT_SIGSUSPEND */
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index e1a797e028a3..98f60c5caa1b 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -31,6 +31,12 @@ void __init idle_thread_set_boot_cpu(void)
per_cpu(idle_threads, smp_processor_id()) = current;
}
+/**
+ * idle_init - Initialize the idle thread for a cpu
+ * @cpu: The cpu for which the idle thread should be initialized
+ *
+ * Creates the thread if it does not exist.
+ */
static inline void idle_init(unsigned int cpu)
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
@@ -45,17 +51,16 @@ static inline void idle_init(unsigned int cpu)
}
/**
- * idle_thread_init - Initialize the idle thread for a cpu
- * @cpu: The cpu for which the idle thread should be initialized
- *
- * Creates the thread if it does not exist.
+ * idle_threads_init - Initialize idle threads for all cpus
*/
void __init idle_threads_init(void)
{
- unsigned int cpu;
+ unsigned int cpu, boot_cpu;
+
+ boot_cpu = smp_processor_id();
for_each_possible_cpu(cpu) {
- if (cpu != smp_processor_id())
+ if (cpu != boot_cpu)
idle_init(cpu);
}
}
diff --git a/kernel/sys.c b/kernel/sys.c
index ba0ae8eea6fb..2d39a84cd857 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -36,6 +36,8 @@
#include <linux/personality.h>
#include <linux/ptrace.h>
#include <linux/fs_struct.h>
+#include <linux/file.h>
+#include <linux/mount.h>
#include <linux/gfp.h>
#include <linux/syscore_ops.h>
#include <linux/version.h>
@@ -93,10 +95,8 @@
int overflowuid = DEFAULT_OVERFLOWUID;
int overflowgid = DEFAULT_OVERFLOWGID;
-#ifdef CONFIG_UID16
EXPORT_SYMBOL(overflowuid);
EXPORT_SYMBOL(overflowgid);
-#endif
/*
* the same as above, but for filesystems which can only store a 16-bit
@@ -133,11 +133,10 @@ static bool set_one_prio_perm(struct task_struct *p)
{
const struct cred *cred = current_cred(), *pcred = __task_cred(p);
- if (pcred->user->user_ns == cred->user->user_ns &&
- (pcred->uid == cred->euid ||
- pcred->euid == cred->euid))
+ if (uid_eq(pcred->uid, cred->euid) ||
+ uid_eq(pcred->euid, cred->euid))
return true;
- if (ns_capable(pcred->user->user_ns, CAP_SYS_NICE))
+ if (ns_capable(pcred->user_ns, CAP_SYS_NICE))
return true;
return false;
}
@@ -177,6 +176,7 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
const struct cred *cred = current_cred();
int error = -EINVAL;
struct pid *pgrp;
+ kuid_t uid;
if (which > PRIO_USER || which < PRIO_PROCESS)
goto out;
@@ -209,18 +209,19 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = (struct user_struct *) cred->user;
+ uid = make_kuid(cred->user_ns, who);
+ user = cred->user;
if (!who)
- who = cred->uid;
- else if ((who != cred->uid) &&
- !(user = find_user(who)))
+ uid = cred->uid;
+ else if (!uid_eq(uid, cred->uid) &&
+ !(user = find_user(uid)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p) {
- if (__task_cred(p)->uid == who)
+ if (uid_eq(task_uid(p), uid))
error = set_one_prio(p, niceval, error);
} while_each_thread(g, p);
- if (who != cred->uid)
+ if (!uid_eq(uid, cred->uid))
free_uid(user); /* For find_user() */
break;
}
@@ -244,6 +245,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
const struct cred *cred = current_cred();
long niceval, retval = -ESRCH;
struct pid *pgrp;
+ kuid_t uid;
if (which > PRIO_USER || which < PRIO_PROCESS)
return -EINVAL;
@@ -274,21 +276,22 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = (struct user_struct *) cred->user;
+ uid = make_kuid(cred->user_ns, who);
+ user = cred->user;
if (!who)
- who = cred->uid;
- else if ((who != cred->uid) &&
- !(user = find_user(who)))
+ uid = cred->uid;
+ else if (!uid_eq(uid, cred->uid) &&
+ !(user = find_user(uid)))
goto out_unlock; /* No processes for this user */
do_each_thread(g, p) {
- if (__task_cred(p)->uid == who) {
+ if (uid_eq(task_uid(p), uid)) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
} while_each_thread(g, p);
- if (who != cred->uid)
+ if (!uid_eq(uid, cred->uid))
free_uid(user); /* for find_user() */
break;
}
@@ -553,9 +556,19 @@ void ctrl_alt_del(void)
*/
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kgid_t krgid, kegid;
+
+ krgid = make_kgid(ns, rgid);
+ kegid = make_kgid(ns, egid);
+
+ if ((rgid != (gid_t) -1) && !gid_valid(krgid))
+ return -EINVAL;
+ if ((egid != (gid_t) -1) && !gid_valid(kegid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -564,25 +577,25 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
retval = -EPERM;
if (rgid != (gid_t) -1) {
- if (old->gid == rgid ||
- old->egid == rgid ||
+ if (gid_eq(old->gid, krgid) ||
+ gid_eq(old->egid, krgid) ||
nsown_capable(CAP_SETGID))
- new->gid = rgid;
+ new->gid = krgid;
else
goto error;
}
if (egid != (gid_t) -1) {
- if (old->gid == egid ||
- old->egid == egid ||
- old->sgid == egid ||
+ if (gid_eq(old->gid, kegid) ||
+ gid_eq(old->egid, kegid) ||
+ gid_eq(old->sgid, kegid) ||
nsown_capable(CAP_SETGID))
- new->egid = egid;
+ new->egid = kegid;
else
goto error;
}
if (rgid != (gid_t) -1 ||
- (egid != (gid_t) -1 && egid != old->gid))
+ (egid != (gid_t) -1 && !gid_eq(kegid, old->gid)))
new->sgid = new->egid;
new->fsgid = new->egid;
@@ -600,9 +613,15 @@ error:
*/
SYSCALL_DEFINE1(setgid, gid_t, gid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kgid_t kgid;
+
+ kgid = make_kgid(ns, gid);
+ if (!gid_valid(kgid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -611,9 +630,9 @@ SYSCALL_DEFINE1(setgid, gid_t, gid)
retval = -EPERM;
if (nsown_capable(CAP_SETGID))
- new->gid = new->egid = new->sgid = new->fsgid = gid;
- else if (gid == old->gid || gid == old->sgid)
- new->egid = new->fsgid = gid;
+ new->gid = new->egid = new->sgid = new->fsgid = kgid;
+ else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid))
+ new->egid = new->fsgid = kgid;
else
goto error;
@@ -631,7 +650,7 @@ static int set_user(struct cred *new)
{
struct user_struct *new_user;
- new_user = alloc_uid(current_user_ns(), new->uid);
+ new_user = alloc_uid(new->uid);
if (!new_user)
return -EAGAIN;
@@ -670,9 +689,19 @@ static int set_user(struct cred *new)
*/
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kuid_t kruid, keuid;
+
+ kruid = make_kuid(ns, ruid);
+ keuid = make_kuid(ns, euid);
+
+ if ((ruid != (uid_t) -1) && !uid_valid(kruid))
+ return -EINVAL;
+ if ((euid != (uid_t) -1) && !uid_valid(keuid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -681,29 +710,29 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
retval = -EPERM;
if (ruid != (uid_t) -1) {
- new->uid = ruid;
- if (old->uid != ruid &&
- old->euid != ruid &&
+ new->uid = kruid;
+ if (!uid_eq(old->uid, kruid) &&
+ !uid_eq(old->euid, kruid) &&
!nsown_capable(CAP_SETUID))
goto error;
}
if (euid != (uid_t) -1) {
- new->euid = euid;
- if (old->uid != euid &&
- old->euid != euid &&
- old->suid != euid &&
+ new->euid = keuid;
+ if (!uid_eq(old->uid, keuid) &&
+ !uid_eq(old->euid, keuid) &&
+ !uid_eq(old->suid, keuid) &&
!nsown_capable(CAP_SETUID))
goto error;
}
- if (new->uid != old->uid) {
+ if (!uid_eq(new->uid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
if (ruid != (uid_t) -1 ||
- (euid != (uid_t) -1 && euid != old->uid))
+ (euid != (uid_t) -1 && !uid_eq(keuid, old->uid)))
new->suid = new->euid;
new->fsuid = new->euid;
@@ -731,9 +760,15 @@ error:
*/
SYSCALL_DEFINE1(setuid, uid_t, uid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kuid_t kuid;
+
+ kuid = make_kuid(ns, uid);
+ if (!uid_valid(kuid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -742,17 +777,17 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
retval = -EPERM;
if (nsown_capable(CAP_SETUID)) {
- new->suid = new->uid = uid;
- if (uid != old->uid) {
+ new->suid = new->uid = kuid;
+ if (!uid_eq(kuid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
- } else if (uid != old->uid && uid != new->suid) {
+ } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) {
goto error;
}
- new->fsuid = new->euid = uid;
+ new->fsuid = new->euid = kuid;
retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
if (retval < 0)
@@ -772,9 +807,24 @@ error:
*/
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kuid_t kruid, keuid, ksuid;
+
+ kruid = make_kuid(ns, ruid);
+ keuid = make_kuid(ns, euid);
+ ksuid = make_kuid(ns, suid);
+
+ if ((ruid != (uid_t) -1) && !uid_valid(kruid))
+ return -EINVAL;
+
+ if ((euid != (uid_t) -1) && !uid_valid(keuid))
+ return -EINVAL;
+
+ if ((suid != (uid_t) -1) && !uid_valid(ksuid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -784,29 +834,29 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
retval = -EPERM;
if (!nsown_capable(CAP_SETUID)) {
- if (ruid != (uid_t) -1 && ruid != old->uid &&
- ruid != old->euid && ruid != old->suid)
+ if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) &&
+ !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
goto error;
- if (euid != (uid_t) -1 && euid != old->uid &&
- euid != old->euid && euid != old->suid)
+ if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) &&
+ !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid))
goto error;
- if (suid != (uid_t) -1 && suid != old->uid &&
- suid != old->euid && suid != old->suid)
+ if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) &&
+ !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid))
goto error;
}
if (ruid != (uid_t) -1) {
- new->uid = ruid;
- if (ruid != old->uid) {
+ new->uid = kruid;
+ if (!uid_eq(kruid, old->uid)) {
retval = set_user(new);
if (retval < 0)
goto error;
}
}
if (euid != (uid_t) -1)
- new->euid = euid;
+ new->euid = keuid;
if (suid != (uid_t) -1)
- new->suid = suid;
+ new->suid = ksuid;
new->fsuid = new->euid;
retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
@@ -820,14 +870,19 @@ error:
return retval;
}
-SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid)
+SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp)
{
const struct cred *cred = current_cred();
int retval;
+ uid_t ruid, euid, suid;
- if (!(retval = put_user(cred->uid, ruid)) &&
- !(retval = put_user(cred->euid, euid)))
- retval = put_user(cred->suid, suid);
+ ruid = from_kuid_munged(cred->user_ns, cred->uid);
+ euid = from_kuid_munged(cred->user_ns, cred->euid);
+ suid = from_kuid_munged(cred->user_ns, cred->suid);
+
+ if (!(retval = put_user(ruid, ruidp)) &&
+ !(retval = put_user(euid, euidp)))
+ retval = put_user(suid, suidp);
return retval;
}
@@ -837,9 +892,22 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __u
*/
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
{
+ struct user_namespace *ns = current_user_ns();
const struct cred *old;
struct cred *new;
int retval;
+ kgid_t krgid, kegid, ksgid;
+
+ krgid = make_kgid(ns, rgid);
+ kegid = make_kgid(ns, egid);
+ ksgid = make_kgid(ns, sgid);
+
+ if ((rgid != (gid_t) -1) && !gid_valid(krgid))
+ return -EINVAL;
+ if ((egid != (gid_t) -1) && !gid_valid(kegid))
+ return -EINVAL;
+ if ((sgid != (gid_t) -1) && !gid_valid(ksgid))
+ return -EINVAL;
new = prepare_creds();
if (!new)
@@ -848,23 +916,23 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid)
retval = -EPERM;
if (!nsown_capable(CAP_SETGID)) {
- if (rgid != (gid_t) -1 && rgid != old->gid &&
- rgid != old->egid && rgid != old->sgid)
+ if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) &&
+ !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
goto error;
- if (egid != (gid_t) -1 && egid != old->gid &&
- egid != old->egid && egid != old->sgid)
+ if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) &&
+ !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
goto error;
- if (sgid != (gid_t) -1 && sgid != old->gid &&
- sgid != old->egid && sgid != old->sgid)
+ if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) &&
+ !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
goto error;
}
if (rgid != (gid_t) -1)
- new->gid = rgid;
+ new->gid = krgid;
if (egid != (gid_t) -1)
- new->egid = egid;
+ new->egid = kegid;
if (sgid != (gid_t) -1)
- new->sgid = sgid;
+ new->sgid = ksgid;
new->fsgid = new->egid;
return commit_creds(new);
@@ -874,14 +942,19 @@ error:
return retval;
}
-SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid)
+SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp)
{
const struct cred *cred = current_cred();
int retval;
+ gid_t rgid, egid, sgid;
- if (!(retval = put_user(cred->gid, rgid)) &&
- !(retval = put_user(cred->egid, egid)))
- retval = put_user(cred->sgid, sgid);
+ rgid = from_kgid_munged(cred->user_ns, cred->gid);
+ egid = from_kgid_munged(cred->user_ns, cred->egid);
+ sgid = from_kgid_munged(cred->user_ns, cred->sgid);
+
+ if (!(retval = put_user(rgid, rgidp)) &&
+ !(retval = put_user(egid, egidp)))
+ retval = put_user(sgid, sgidp);
return retval;
}
@@ -898,18 +971,24 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid)
const struct cred *old;
struct cred *new;
uid_t old_fsuid;
+ kuid_t kuid;
+
+ old = current_cred();
+ old_fsuid = from_kuid_munged(old->user_ns, old->fsuid);
+
+ kuid = make_kuid(old->user_ns, uid);
+ if (!uid_valid(kuid))
+ return old_fsuid;
new = prepare_creds();
if (!new)
- return current_fsuid();
- old = current_cred();
- old_fsuid = old->fsuid;
+ return old_fsuid;
- if (uid == old->uid || uid == old->euid ||
- uid == old->suid || uid == old->fsuid ||
+ if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) ||
+ uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) ||
nsown_capable(CAP_SETUID)) {
- if (uid != old_fsuid) {
- new->fsuid = uid;
+ if (!uid_eq(kuid, old->fsuid)) {
+ new->fsuid = kuid;
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
goto change_okay;
}
@@ -931,18 +1010,24 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid)
const struct cred *old;
struct cred *new;
gid_t old_fsgid;
+ kgid_t kgid;
+
+ old = current_cred();
+ old_fsgid = from_kgid_munged(old->user_ns, old->fsgid);
+
+ kgid = make_kgid(old->user_ns, gid);
+ if (!gid_valid(kgid))
+ return old_fsgid;
new = prepare_creds();
if (!new)
- return current_fsgid();
- old = current_cred();
- old_fsgid = old->fsgid;
+ return old_fsgid;
- if (gid == old->gid || gid == old->egid ||
- gid == old->sgid || gid == old->fsgid ||
+ if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) ||
+ gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) ||
nsown_capable(CAP_SETGID)) {
- if (gid != old_fsgid) {
- new->fsgid = gid;
+ if (!gid_eq(kgid, old->fsgid)) {
+ new->fsgid = kgid;
goto change_okay;
}
}
@@ -1295,8 +1380,8 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
memcpy(u->nodename, tmp, len);
memset(u->nodename + len, 0, sizeof(u->nodename) - len);
errno = 0;
+ uts_proc_notify(UTS_PROC_HOSTNAME);
}
- uts_proc_notify(UTS_PROC_HOSTNAME);
up_write(&uts_sem);
return errno;
}
@@ -1346,8 +1431,8 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
memcpy(u->domainname, tmp, len);
memset(u->domainname + len, 0, sizeof(u->domainname) - len);
errno = 0;
+ uts_proc_notify(UTS_PROC_DOMAINNAME);
}
- uts_proc_notify(UTS_PROC_DOMAINNAME);
up_write(&uts_sem);
return errno;
}
@@ -1498,15 +1583,14 @@ static int check_prlimit_permission(struct task_struct *task)
return 0;
tcred = __task_cred(task);
- if (cred->user->user_ns == tcred->user->user_ns &&
- (cred->uid == tcred->euid &&
- cred->uid == tcred->suid &&
- cred->uid == tcred->uid &&
- cred->gid == tcred->egid &&
- cred->gid == tcred->sgid &&
- cred->gid == tcred->gid))
+ if (uid_eq(cred->uid, tcred->euid) &&
+ uid_eq(cred->uid, tcred->suid) &&
+ uid_eq(cred->uid, tcred->uid) &&
+ gid_eq(cred->gid, tcred->egid) &&
+ gid_eq(cred->gid, tcred->sgid) &&
+ gid_eq(cred->gid, tcred->gid))
return 0;
- if (ns_capable(tcred->user->user_ns, CAP_SYS_RESOURCE))
+ if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE))
return 0;
return -EPERM;
@@ -1702,77 +1786,105 @@ SYSCALL_DEFINE1(umask, int, mask)
}
#ifdef CONFIG_CHECKPOINT_RESTORE
+static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
+{
+ struct file *exe_file;
+ struct dentry *dentry;
+ int err;
+
+ exe_file = fget(fd);
+ if (!exe_file)
+ return -EBADF;
+
+ dentry = exe_file->f_path.dentry;
+
+ /*
+ * Because the original mm->exe_file points to executable file, make
+ * sure that this one is executable as well, to avoid breaking an
+ * overall picture.
+ */
+ err = -EACCES;
+ if (!S_ISREG(dentry->d_inode->i_mode) ||
+ exe_file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+ goto exit;
+
+ err = inode_permission(dentry->d_inode, MAY_EXEC);
+ if (err)
+ goto exit;
+
+ down_write(&mm->mmap_sem);
+
+ /*
+ * Forbid mm->exe_file change if old file still mapped.
+ */
+ err = -EBUSY;
+ if (mm->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_unlock;
+ }
+
+ /*
+ * The symlink can be changed only once, just to disallow arbitrary
+ * transitions malicious software might bring in. This means one
+ * could make a snapshot over all processes running and monitor
+ * /proc/pid/exe changes to notice unusual activity if needed.
+ */
+ err = -EPERM;
+ if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
+ goto exit_unlock;
+
+ err = 0;
+ set_mm_exe_file(mm, exe_file);
+exit_unlock:
+ up_write(&mm->mmap_sem);
+
+exit:
+ fput(exe_file);
+ return err;
+}
+
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
unsigned long rlim = rlimit(RLIMIT_DATA);
- unsigned long vm_req_flags;
- unsigned long vm_bad_flags;
- struct vm_area_struct *vma;
- int error = 0;
struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int error;
- if (arg4 | arg5)
+ if (arg5 || (arg4 && opt != PR_SET_MM_AUXV))
return -EINVAL;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
- if (addr >= TASK_SIZE)
+ 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;
+ error = -EINVAL;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, addr);
- if (opt != PR_SET_MM_START_BRK && opt != PR_SET_MM_BRK) {
- /* It must be existing VMA */
- if (!vma || vma->vm_start > addr)
- goto out;
- }
-
- error = -EINVAL;
switch (opt) {
case PR_SET_MM_START_CODE:
+ mm->start_code = addr;
+ break;
case PR_SET_MM_END_CODE:
- vm_req_flags = VM_READ | VM_EXEC;
- vm_bad_flags = VM_WRITE | VM_MAYSHARE;
-
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
- (vma->vm_flags & vm_bad_flags))
- goto out;
-
- if (opt == PR_SET_MM_START_CODE)
- mm->start_code = addr;
- else
- mm->end_code = addr;
+ mm->end_code = addr;
break;
-
case PR_SET_MM_START_DATA:
- case PR_SET_MM_END_DATA:
- vm_req_flags = VM_READ | VM_WRITE;
- vm_bad_flags = VM_EXEC | VM_MAYSHARE;
-
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags ||
- (vma->vm_flags & vm_bad_flags))
- goto out;
-
- if (opt == PR_SET_MM_START_DATA)
- mm->start_data = addr;
- else
- mm->end_data = addr;
+ mm->start_data = addr;
break;
-
- case PR_SET_MM_START_STACK:
-
-#ifdef CONFIG_STACK_GROWSUP
- vm_req_flags = VM_READ | VM_WRITE | VM_GROWSUP;
-#else
- vm_req_flags = VM_READ | VM_WRITE | VM_GROWSDOWN;
-#endif
- if ((vma->vm_flags & vm_req_flags) != vm_req_flags)
- goto out;
-
- mm->start_stack = addr;
+ case PR_SET_MM_END_DATA:
+ mm->end_data = addr;
break;
case PR_SET_MM_START_BRK:
@@ -1799,24 +1911,89 @@ static int prctl_set_mm(int opt, unsigned long addr,
mm->brk = addr;
break;
+ /*
+ * If command line arguments and environment
+ * are placed somewhere else on stack, we can
+ * set them up here, ARG_START/END to setup
+ * command line argumets and ENV_START/END
+ * for environment.
+ */
+ case PR_SET_MM_START_STACK:
+ case PR_SET_MM_ARG_START:
+ case PR_SET_MM_ARG_END:
+ case PR_SET_MM_ENV_START:
+ case PR_SET_MM_ENV_END:
+ if (!vma) {
+ error = -EFAULT;
+ goto out;
+ }
+ if (opt == PR_SET_MM_START_STACK)
+ mm->start_stack = addr;
+ else if (opt == PR_SET_MM_ARG_START)
+ mm->arg_start = addr;
+ else if (opt == PR_SET_MM_ARG_END)
+ mm->arg_end = addr;
+ else if (opt == PR_SET_MM_ENV_START)
+ mm->env_start = addr;
+ else if (opt == PR_SET_MM_ENV_END)
+ mm->env_end = addr;
+ break;
+
+ /*
+ * This doesn't move auxiliary vector itself
+ * since it's pinned to mm_struct, but allow
+ * to fill vector with new values. It's up
+ * to a caller to provide sane values here
+ * otherwise user space tools which use this
+ * vector might be unhappy.
+ */
+ case PR_SET_MM_AUXV: {
+ unsigned long user_auxv[AT_VECTOR_SIZE];
+
+ if (arg4 > sizeof(user_auxv))
+ goto out;
+ up_read(&mm->mmap_sem);
+
+ if (copy_from_user(user_auxv, (const void __user *)addr, arg4))
+ return -EFAULT;
+
+ /* Make sure the last entry is always AT_NULL */
+ user_auxv[AT_VECTOR_SIZE - 2] = 0;
+ user_auxv[AT_VECTOR_SIZE - 1] = 0;
+
+ BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+
+ task_lock(current);
+ memcpy(mm->saved_auxv, user_auxv, arg4);
+ task_unlock(current);
+
+ return 0;
+ }
default:
- error = -EINVAL;
goto out;
}
error = 0;
-
out:
up_read(&mm->mmap_sem);
-
return error;
}
+
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return put_user(me->clear_child_tid, tid_addr);
+}
+
#else /* CONFIG_CHECKPOINT_RESTORE */
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
return -EINVAL;
}
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return -EINVAL;
+}
#endif
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
@@ -1971,6 +2148,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SET_MM:
error = prctl_set_mm(arg2, arg3, arg4, arg5);
break;
+ case PR_GET_TID_ADDRESS:
+ error = prctl_get_tid_address(me, (int __user **)arg2);
+ break;
case PR_SET_CHILD_SUBREAPER:
me->signal->is_child_subreaper = !!arg2;
error = 0;
@@ -2032,7 +2212,6 @@ int orderly_poweroff(bool force)
NULL
};
int ret = -ENOMEM;
- struct subprocess_info *info;
if (argv == NULL) {
printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
@@ -2040,18 +2219,16 @@ int orderly_poweroff(bool force)
goto out;
}
- info = call_usermodehelper_setup(argv[0], argv, envp, GFP_ATOMIC);
- if (info == NULL) {
- argv_free(argv);
- goto out;
- }
-
- call_usermodehelper_setfns(info, NULL, argv_cleanup, NULL);
+ ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_NO_WAIT,
+ NULL, argv_cleanup, NULL);
+out:
+ if (likely(!ret))
+ return 0;
- ret = call_usermodehelper_exec(info, UMH_NO_WAIT);
+ if (ret == -ENOMEM)
+ argv_free(argv);
- out:
- if (ret && force) {
+ if (force) {
printk(KERN_WARNING "Failed to start orderly shutdown: "
"forcing the issue\n");
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 47bfa16430d7..dbff751e4086 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -203,3 +203,6 @@ cond_syscall(sys_fanotify_mark);
cond_syscall(sys_name_to_handle_at);
cond_syscall(sys_open_by_handle_at);
cond_syscall(compat_sys_open_by_handle_at);
+
+/* compare kernel pointers */
+cond_syscall(sys_kcmp);
diff --git a/kernel/task_work.c b/kernel/task_work.c
new file mode 100644
index 000000000000..82d1c794066d
--- /dev/null
+++ b/kernel/task_work.c
@@ -0,0 +1,84 @@
+#include <linux/spinlock.h>
+#include <linux/task_work.h>
+#include <linux/tracehook.h>
+
+int
+task_work_add(struct task_struct *task, struct task_work *twork, bool notify)
+{
+ unsigned long flags;
+ int err = -ESRCH;
+
+#ifndef TIF_NOTIFY_RESUME
+ if (notify)
+ return -ENOTSUPP;
+#endif
+ /*
+ * We must not insert the new work if the task has already passed
+ * exit_task_work(). We rely on do_exit()->raw_spin_unlock_wait()
+ * and check PF_EXITING under pi_lock.
+ */
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+ if (likely(!(task->flags & PF_EXITING))) {
+ hlist_add_head(&twork->hlist, &task->task_works);
+ err = 0;
+ }
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+ /* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */
+ if (likely(!err) && notify)
+ set_notify_resume(task);
+ return err;
+}
+
+struct task_work *
+task_work_cancel(struct task_struct *task, task_work_func_t func)
+{
+ unsigned long flags;
+ struct task_work *twork;
+ struct hlist_node *pos;
+
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+ hlist_for_each_entry(twork, pos, &task->task_works, hlist) {
+ if (twork->func == func) {
+ hlist_del(&twork->hlist);
+ goto found;
+ }
+ }
+ twork = NULL;
+ found:
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+ return twork;
+}
+
+void task_work_run(void)
+{
+ struct task_struct *task = current;
+ struct hlist_head task_works;
+ struct hlist_node *pos;
+
+ raw_spin_lock_irq(&task->pi_lock);
+ hlist_move_list(&task->task_works, &task_works);
+ raw_spin_unlock_irq(&task->pi_lock);
+
+ if (unlikely(hlist_empty(&task_works)))
+ return;
+ /*
+ * We use hlist to save the space in task_struct, but we want fifo.
+ * Find the last entry, the list should be short, then process them
+ * in reverse order.
+ */
+ for (pos = task_works.first; pos->next; pos = pos->next)
+ ;
+
+ for (;;) {
+ struct hlist_node **pprev = pos->pprev;
+ struct task_work *twork = container_of(pos, struct task_work,
+ hlist);
+ twork->func(twork);
+
+ if (pprev == &task_works.first)
+ break;
+ pos = container_of(pprev, struct hlist_node, next);
+ }
+}
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index a20dc8a3c949..fd42bd452b75 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -2,6 +2,55 @@
# Timer subsystem related configuration options
#
+# Options selectable by arch Kconfig
+
+# Watchdog function for clocksources to detect instabilities
+config CLOCKSOURCE_WATCHDOG
+ bool
+
+# Architecture has extra clocksource data
+config ARCH_CLOCKSOURCE_DATA
+ bool
+
+# Timekeeping vsyscall support
+config GENERIC_TIME_VSYSCALL
+ bool
+
+# ktime_t scalar 64bit nsec representation
+config KTIME_SCALAR
+ bool
+
+# Old style timekeeping
+config ARCH_USES_GETTIMEOFFSET
+ bool
+
+# The generic clock events infrastructure
+config GENERIC_CLOCKEVENTS
+ bool
+
+# Migration helper. Builds, but does not invoke
+config GENERIC_CLOCKEVENTS_BUILD
+ bool
+ default y
+ depends on GENERIC_CLOCKEVENTS
+
+# Clockevents broadcasting infrastructure
+config GENERIC_CLOCKEVENTS_BROADCAST
+ bool
+ depends on GENERIC_CLOCKEVENTS
+
+# Automatically adjust the min. reprogramming time for
+# clock event device
+config GENERIC_CLOCKEVENTS_MIN_ADJUST
+ bool
+
+# Generic update of CMOS clock
+config GENERIC_CMOS_UPDATE
+ bool
+
+if GENERIC_CLOCKEVENTS
+menu "Timers subsystem"
+
# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is
# only related to the tick functionality. Oneshot clockevent devices
# are supported independ of this.
@@ -26,10 +75,5 @@ config HIGH_RES_TIMERS
hardware is not capable then this option only increases
the size of the kernel image.
-config GENERIC_CLOCKEVENTS_BUILD
- bool
- default y
- depends on GENERIC_CLOCKEVENTS
-
-config GENERIC_CLOCKEVENTS_MIN_ADJUST
- bool
+endmenu
+endif
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 9cd928f7a7c6..7e1ce012a851 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -297,8 +297,7 @@ void clockevents_register_device(struct clock_event_device *dev)
}
EXPORT_SYMBOL_GPL(clockevents_register_device);
-static void clockevents_config(struct clock_event_device *dev,
- u32 freq)
+void clockevents_config(struct clock_event_device *dev, u32 freq)
{
u64 sec;
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index f03fd83b170b..b7fbadc5c973 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -409,15 +409,20 @@ int second_overflow(unsigned long secs)
time_state = TIME_DEL;
break;
case TIME_INS:
- if (secs % 86400 == 0) {
+ if (!(time_status & STA_INS))
+ time_state = TIME_OK;
+ else if (secs % 86400 == 0) {
leap = -1;
time_state = TIME_OOP;
+ time_tai++;
printk(KERN_NOTICE
"Clock: inserting leap second 23:59:60 UTC\n");
}
break;
case TIME_DEL:
- if ((secs + 1) % 86400 == 0) {
+ if (!(time_status & STA_DEL))
+ time_state = TIME_OK;
+ else if ((secs + 1) % 86400 == 0) {
leap = 1;
time_tai--;
time_state = TIME_WAIT;
@@ -426,7 +431,6 @@ int second_overflow(unsigned long secs)
}
break;
case TIME_OOP:
- time_tai++;
time_state = TIME_WAIT;
break;
@@ -473,8 +477,6 @@ int second_overflow(unsigned long secs)
<< NTP_SCALE_SHIFT;
time_adjust = 0;
-
-
out:
spin_unlock_irqrestore(&ntp_lock, flags);
@@ -559,10 +561,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
/* only set allowed bits */
time_status &= STA_RONLY;
time_status |= txc->status & ~STA_RONLY;
-
}
+
/*
- * Called with the xtime lock held, so we can access and modify
+ * Called with ntp_lock held, so we can access and modify
* all the global NTP state:
*/
static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6a3a5b9ff561..4a08472c3ca7 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -274,6 +274,7 @@ EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
+ unsigned long rcu_delta_jiffies;
ktime_t last_update, expires, now;
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
@@ -322,7 +323,7 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
time_delta = timekeeping_max_deferment();
} while (read_seqretry(&xtime_lock, seq));
- if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
+ if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
arch_needs_cpu(cpu)) {
next_jiffies = last_jiffies + 1;
delta_jiffies = 1;
@@ -330,6 +331,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
/* Get the next timer wheel timer */
next_jiffies = get_next_timer_interrupt(last_jiffies);
delta_jiffies = next_jiffies - last_jiffies;
+ if (rcu_delta_jiffies < delta_jiffies) {
+ next_jiffies = last_jiffies + rcu_delta_jiffies;
+ delta_jiffies = rcu_delta_jiffies;
+ }
}
/*
* Do not stop the tick, if we are only one off
@@ -401,6 +406,7 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
*/
if (!ts->tick_stopped) {
select_nohz_load_balancer(1);
+ calc_load_enter_idle();
ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
@@ -576,6 +582,7 @@ void tick_nohz_idle_exit(void)
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
+ update_cpu_load_nohz();
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
@@ -591,6 +598,7 @@ void tick_nohz_idle_exit(void)
account_idle_ticks(ticks);
#endif
+ calc_load_exit_idle();
touch_softlockup_watchdog();
/*
* Cancel the scheduled timer and restore the tick
@@ -814,6 +822,16 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
return HRTIMER_RESTART;
}
+static int sched_skew_tick;
+
+static int __init skew_tick(char *str)
+{
+ get_option(&str, &sched_skew_tick);
+
+ return 0;
+}
+early_param("skew_tick", skew_tick);
+
/**
* tick_setup_sched_timer - setup the tick emulation timer
*/
@@ -831,6 +849,14 @@ void tick_setup_sched_timer(void)
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
+ /* Offset the tick to avert xtime_lock contention. */
+ if (sched_skew_tick) {
+ u64 offset = ktime_to_ns(tick_period) >> 1;
+ do_div(offset, num_possible_cpus());
+ offset *= smp_processor_id();
+ hrtimer_add_expires_ns(&ts->sched_timer, offset);
+ }
+
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);
hrtimer_start_expires(&ts->sched_timer,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d66b21308f7c..3447cfaf11e7 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -70,6 +70,12 @@ struct timekeeper {
/* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */
struct timespec raw_time;
+ /* Offset clock monotonic -> clock realtime */
+ ktime_t offs_real;
+
+ /* Offset clock monotonic -> clock boottime */
+ ktime_t offs_boot;
+
/* Seqlock for all timekeeper values */
seqlock_t lock;
};
@@ -172,6 +178,14 @@ static inline s64 timekeeping_get_ns_raw(void)
return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
}
+static void update_rt_offset(void)
+{
+ struct timespec tmp, *wtm = &timekeeper.wall_to_monotonic;
+
+ set_normalized_timespec(&tmp, -wtm->tv_sec, -wtm->tv_nsec);
+ timekeeper.offs_real = timespec_to_ktime(tmp);
+}
+
/* must hold write on timekeeper.lock */
static void timekeeping_update(bool clearntp)
{
@@ -179,6 +193,7 @@ static void timekeeping_update(bool clearntp)
timekeeper.ntp_error = 0;
ntp_clear();
}
+ update_rt_offset();
update_vsyscall(&timekeeper.xtime, &timekeeper.wall_to_monotonic,
timekeeper.clock, timekeeper.mult);
}
@@ -240,7 +255,6 @@ void getnstimeofday(struct timespec *ts)
timespec_add_ns(ts, nsecs);
}
-
EXPORT_SYMBOL(getnstimeofday);
ktime_t ktime_get(void)
@@ -357,8 +371,8 @@ void do_gettimeofday(struct timeval *tv)
tv->tv_sec = now.tv_sec;
tv->tv_usec = now.tv_nsec/1000;
}
-
EXPORT_SYMBOL(do_gettimeofday);
+
/**
* do_settimeofday - Sets the time of day
* @tv: pointer to the timespec variable containing the new time
@@ -392,7 +406,6 @@ int do_settimeofday(const struct timespec *tv)
return 0;
}
-
EXPORT_SYMBOL(do_settimeofday);
@@ -606,6 +619,7 @@ void __init timekeeping_init(void)
}
set_normalized_timespec(&timekeeper.wall_to_monotonic,
-boot.tv_sec, -boot.tv_nsec);
+ update_rt_offset();
timekeeper.total_sleep_time.tv_sec = 0;
timekeeper.total_sleep_time.tv_nsec = 0;
write_sequnlock_irqrestore(&timekeeper.lock, flags);
@@ -614,6 +628,12 @@ void __init timekeeping_init(void)
/* time in seconds when suspend began */
static struct timespec timekeeping_suspend_time;
+static void update_sleep_time(struct timespec t)
+{
+ timekeeper.total_sleep_time = t;
+ timekeeper.offs_boot = timespec_to_ktime(t);
+}
+
/**
* __timekeeping_inject_sleeptime - Internal function to add sleep interval
* @delta: pointer to a timespec delta value
@@ -632,8 +652,7 @@ static void __timekeeping_inject_sleeptime(struct timespec *delta)
timekeeper.xtime = timespec_add(timekeeper.xtime, *delta);
timekeeper.wall_to_monotonic =
timespec_sub(timekeeper.wall_to_monotonic, *delta);
- timekeeper.total_sleep_time = timespec_add(
- timekeeper.total_sleep_time, *delta);
+ update_sleep_time(timespec_add(timekeeper.total_sleep_time, *delta));
}
@@ -698,6 +717,7 @@ static void timekeeping_resume(void)
timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
timekeeper.ntp_error = 0;
timekeeping_suspended = 0;
+ timekeeping_update(false);
write_sequnlock_irqrestore(&timekeeper.lock, flags);
touch_softlockup_watchdog();
@@ -964,6 +984,9 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
timekeeper.xtime.tv_sec++;
leap = second_overflow(timekeeper.xtime.tv_sec);
timekeeper.xtime.tv_sec += leap;
+ timekeeper.wall_to_monotonic.tv_sec -= leap;
+ if (leap)
+ clock_was_set_delayed();
}
/* Accumulate raw time */
@@ -1079,6 +1102,9 @@ static void update_wall_time(void)
timekeeper.xtime.tv_sec++;
leap = second_overflow(timekeeper.xtime.tv_sec);
timekeeper.xtime.tv_sec += leap;
+ timekeeper.wall_to_monotonic.tv_sec -= leap;
+ if (leap)
+ clock_was_set_delayed();
}
timekeeping_update(false);
@@ -1246,6 +1272,40 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
} while (read_seqretry(&timekeeper.lock, seq));
}
+#ifdef CONFIG_HIGH_RES_TIMERS
+/**
+ * ktime_get_update_offsets - hrtimer helper
+ * @offs_real: pointer to storage for monotonic -> realtime offset
+ * @offs_boot: pointer to storage for monotonic -> boottime offset
+ *
+ * Returns current monotonic time and updates the offsets
+ * Called from hrtimer_interupt() or retrigger_next_event()
+ */
+ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
+{
+ ktime_t now;
+ unsigned int seq;
+ u64 secs, nsecs;
+
+ do {
+ seq = read_seqbegin(&timekeeper.lock);
+
+ secs = timekeeper.xtime.tv_sec;
+ nsecs = timekeeper.xtime.tv_nsec;
+ nsecs += timekeeping_get_ns();
+ /* If arch requires, add in gettimeoffset() */
+ nsecs += arch_gettimeoffset();
+
+ *offs_real = timekeeper.offs_real;
+ *offs_boot = timekeeper.offs_boot;
+ } while (read_seqretry(&timekeeper.lock, seq));
+
+ now = ktime_add_ns(ktime_set(secs, 0), nsecs);
+ now = ktime_sub(now, *offs_real);
+ return now;
+}
+#endif
+
/**
* ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
*/
diff --git a/kernel/timer.c b/kernel/timer.c
index 09de9a941cd7..6ec7e7e0db43 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1435,25 +1435,25 @@ SYSCALL_DEFINE0(getppid)
SYSCALL_DEFINE0(getuid)
{
/* Only we change this so SMP safe */
- return current_uid();
+ return from_kuid_munged(current_user_ns(), current_uid());
}
SYSCALL_DEFINE0(geteuid)
{
/* Only we change this so SMP safe */
- return current_euid();
+ return from_kuid_munged(current_user_ns(), current_euid());
}
SYSCALL_DEFINE0(getgid)
{
/* Only we change this so SMP safe */
- return current_gid();
+ return from_kgid_munged(current_user_ns(), current_gid());
}
SYSCALL_DEFINE0(getegid)
{
/* Only we change this so SMP safe */
- return current_egid();
+ return from_kgid_munged(current_user_ns(), current_egid());
}
#endif
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d81a1a532994..8c4c07071cc5 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -271,7 +271,7 @@ config PROFILE_ANNOTATED_BRANCHES
bool "Trace likely/unlikely profiler"
select TRACE_BRANCH_PROFILING
help
- This tracer profiles all the the likely and unlikely macros
+ This tracer profiles all likely and unlikely macros
in the kernel. It will display the results in:
/sys/kernel/debug/tracing/trace_stat/branch_annotated
@@ -372,6 +372,7 @@ config KPROBE_EVENT
depends on HAVE_REGS_AND_STACK_ACCESS_API
bool "Enable kprobes-based dynamic events"
select TRACING
+ select PROBE_EVENTS
default y
help
This allows the user to add tracing events (similar to tracepoints)
@@ -384,6 +385,25 @@ config KPROBE_EVENT
This option is also required by perf-probe subcommand of perf tools.
If you want to use perf tools, this option is strongly recommended.
+config UPROBE_EVENT
+ bool "Enable uprobes-based dynamic events"
+ depends on ARCH_SUPPORTS_UPROBES
+ depends on MMU
+ select UPROBES
+ select PROBE_EVENTS
+ select TRACING
+ default n
+ help
+ This allows the user to add tracing events on top of userspace
+ dynamic events (similar to tracepoints) on the fly via the trace
+ events interface. Those events can be inserted wherever uprobes
+ can probe, and record various registers.
+ This option is required if you plan to use perf-probe subcommand
+ of perf tools on user space applications.
+
+config PROBE_EVENTS
+ def_bool n
+
config DYNAMIC_FTRACE
bool "enable/disable ftrace tracepoints dynamically"
depends on FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index b3afe0e76f79..b831087c8200 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -60,5 +60,7 @@ endif
ifeq ($(CONFIG_TRACING),y)
obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
endif
+obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
+obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6420cda62336..f765465bffe4 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1075,6 +1075,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
rb_init_page(bpage->page);
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+ INIT_LIST_HEAD(&cpu_buffer->new_pages);
ret = rb_allocate_pages(cpu_buffer, nr_pages);
if (ret < 0)
@@ -1346,10 +1347,9 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
* If something was added to this page, it was full
* since it is not the tail page. So we deduct the
* bytes consumed in ring buffer from here.
- * No need to update overruns, since this page is
- * deleted from ring buffer and its entries are
- * already accounted for.
+ * Increment overrun to account for the lost events.
*/
+ local_add(page_entries, &cpu_buffer->overrun);
local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
}
@@ -1486,6 +1486,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
if (!buffer)
return size;
+ /* Make sure the requested buffer exists */
+ if (cpu_id != RING_BUFFER_ALL_CPUS &&
+ !cpumask_test_cpu(cpu_id, buffer->cpumask))
+ return size;
+
size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
size *= BUF_PAGE_SIZE;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 68032c6177db..a7fa0702be1c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
void tracing_off(void)
{
if (global_trace.buffer)
- ring_buffer_record_on(global_trace.buffer);
+ ring_buffer_record_off(global_trace.buffer);
/*
* This flag is only looked at when buffers haven't been
* allocated yet. We don't really care about the race
@@ -3609,6 +3609,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
.pages = pages_def,
.partial = partial_def,
.nr_pages = 0, /* This gets updated below. */
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &tracing_pipe_buf_ops,
.spd_release = tracing_spd_release_pipe,
@@ -3680,7 +3681,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
ret = splice_to_pipe(pipe, &spd);
out:
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
return ret;
out_err:
@@ -4231,6 +4232,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
struct splice_pipe_desc spd = {
.pages = pages_def,
.partial = partial_def,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &buffer_pipe_buf_ops,
.spd_release = buffer_spd_release,
@@ -4318,7 +4320,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
}
ret = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
out:
return ret;
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6c6f7933eede..5aec220d2de0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -103,6 +103,11 @@ struct kretprobe_trace_entry_head {
unsigned long ret_ip;
};
+struct uprobe_trace_entry_head {
+ struct trace_entry ent;
+ unsigned long ip;
+};
+
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 580a05ec926b..b31d3d5699fe 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -19,547 +19,15 @@
#include <linux/module.h>
#include <linux/uaccess.h>
-#include <linux/kprobes.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/debugfs.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/ctype.h>
-#include <linux/ptrace.h>
-#include <linux/perf_event.h>
-#include <linux/stringify.h>
-#include <linux/limits.h>
-#include <asm/bitsperlong.h>
-
-#include "trace.h"
-#include "trace_output.h"
-
-#define MAX_TRACE_ARGS 128
-#define MAX_ARGSTR_LEN 63
-#define MAX_EVENT_NAME_LEN 64
-#define MAX_STRING_SIZE PATH_MAX
-#define KPROBE_EVENT_SYSTEM "kprobes"
-
-/* Reserved field names */
-#define FIELD_STRING_IP "__probe_ip"
-#define FIELD_STRING_RETIP "__probe_ret_ip"
-#define FIELD_STRING_FUNC "__probe_func"
-
-const char *reserved_field_names[] = {
- "common_type",
- "common_flags",
- "common_preempt_count",
- "common_pid",
- "common_tgid",
- FIELD_STRING_IP,
- FIELD_STRING_RETIP,
- FIELD_STRING_FUNC,
-};
-
-/* Printing function type */
-typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *,
- void *);
-#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
-#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
-
-/* Printing in basic type function template */
-#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \
-static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
- const char *name, \
- void *data, void *ent)\
-{ \
- return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
-} \
-static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
-
-DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
-DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
-
-/* data_rloc: data relative location, compatible with u32 */
-#define make_data_rloc(len, roffs) \
- (((u32)(len) << 16) | ((u32)(roffs) & 0xffff))
-#define get_rloc_len(dl) ((u32)(dl) >> 16)
-#define get_rloc_offs(dl) ((u32)(dl) & 0xffff)
-
-static inline void *get_rloc_data(u32 *dl)
-{
- return (u8 *)dl + get_rloc_offs(*dl);
-}
-
-/* For data_loc conversion */
-static inline void *get_loc_data(u32 *dl, void *ent)
-{
- return (u8 *)ent + get_rloc_offs(*dl);
-}
-
-/*
- * Convert data_rloc to data_loc:
- * data_rloc stores the offset from data_rloc itself, but data_loc
- * stores the offset from event entry.
- */
-#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs))
-
-/* For defining macros, define string/string_size types */
-typedef u32 string;
-typedef u32 string_size;
-
-/* Print type function for string type */
-static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
- const char *name,
- void *data, void *ent)
-{
- int len = *(u32 *)data >> 16;
-
- if (!len)
- return trace_seq_printf(s, " %s=(fault)", name);
- else
- return trace_seq_printf(s, " %s=\"%s\"", name,
- (const char *)get_loc_data(data, ent));
-}
-static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
-
-/* Data fetch function type */
-typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
-
-struct fetch_param {
- fetch_func_t fn;
- void *data;
-};
-
-static __kprobes void call_fetch(struct fetch_param *fprm,
- struct pt_regs *regs, void *dest)
-{
- return fprm->fn(regs, fprm->data, dest);
-}
-
-#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
-/*
- * Define macro for basic types - we don't need to define s* types, because
- * we have to care only about bitwidth at recording time.
- */
-#define DEFINE_BASIC_FETCH_FUNCS(method) \
-DEFINE_FETCH_##method(u8) \
-DEFINE_FETCH_##method(u16) \
-DEFINE_FETCH_##method(u32) \
-DEFINE_FETCH_##method(u64)
-
-#define CHECK_FETCH_FUNCS(method, fn) \
- (((FETCH_FUNC_NAME(method, u8) == fn) || \
- (FETCH_FUNC_NAME(method, u16) == fn) || \
- (FETCH_FUNC_NAME(method, u32) == fn) || \
- (FETCH_FUNC_NAME(method, u64) == fn) || \
- (FETCH_FUNC_NAME(method, string) == fn) || \
- (FETCH_FUNC_NAME(method, string_size) == fn)) \
- && (fn != NULL))
-
-/* Data fetch function templates */
-#define DEFINE_FETCH_reg(type) \
-static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
- void *offset, void *dest) \
-{ \
- *(type *)dest = (type)regs_get_register(regs, \
- (unsigned int)((unsigned long)offset)); \
-}
-DEFINE_BASIC_FETCH_FUNCS(reg)
-/* No string on the register */
-#define fetch_reg_string NULL
-#define fetch_reg_string_size NULL
-
-#define DEFINE_FETCH_stack(type) \
-static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
- void *offset, void *dest) \
-{ \
- *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
- (unsigned int)((unsigned long)offset)); \
-}
-DEFINE_BASIC_FETCH_FUNCS(stack)
-/* No string on the stack entry */
-#define fetch_stack_string NULL
-#define fetch_stack_string_size NULL
-
-#define DEFINE_FETCH_retval(type) \
-static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
- void *dummy, void *dest) \
-{ \
- *(type *)dest = (type)regs_return_value(regs); \
-}
-DEFINE_BASIC_FETCH_FUNCS(retval)
-/* No string on the retval */
-#define fetch_retval_string NULL
-#define fetch_retval_string_size NULL
-
-#define DEFINE_FETCH_memory(type) \
-static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
- void *addr, void *dest) \
-{ \
- type retval; \
- if (probe_kernel_address(addr, retval)) \
- *(type *)dest = 0; \
- else \
- *(type *)dest = retval; \
-}
-DEFINE_BASIC_FETCH_FUNCS(memory)
-/*
- * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
- * length and relative data location.
- */
-static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- long ret;
- int maxlen = get_rloc_len(*(u32 *)dest);
- u8 *dst = get_rloc_data(dest);
- u8 *src = addr;
- mm_segment_t old_fs = get_fs();
- if (!maxlen)
- return;
- /*
- * Try to get string again, since the string can be changed while
- * probing.
- */
- set_fs(KERNEL_DS);
- pagefault_disable();
- do
- ret = __copy_from_user_inatomic(dst++, src++, 1);
- while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
- dst[-1] = '\0';
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) { /* Failed to fetch string */
- ((u8 *)get_rloc_data(dest))[0] = '\0';
- *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
- } else
- *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
- get_rloc_offs(*(u32 *)dest));
-}
-/* Return the length of string -- including null terminal byte */
-static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
- void *addr, void *dest)
-{
- int ret, len = 0;
- u8 c;
- mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
- pagefault_disable();
- do {
- ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
- len++;
- } while (c && ret == 0 && len < MAX_STRING_SIZE);
- pagefault_enable();
- set_fs(old_fs);
-
- if (ret < 0) /* Failed to check the length */
- *(u32 *)dest = 0;
- else
- *(u32 *)dest = len;
-}
-
-/* Memory fetching by symbol */
-struct symbol_cache {
- char *symbol;
- long offset;
- unsigned long addr;
-};
-
-static unsigned long update_symbol_cache(struct symbol_cache *sc)
-{
- sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
- if (sc->addr)
- sc->addr += sc->offset;
- return sc->addr;
-}
-
-static void free_symbol_cache(struct symbol_cache *sc)
-{
- kfree(sc->symbol);
- kfree(sc);
-}
-
-static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
-{
- struct symbol_cache *sc;
-
- if (!sym || strlen(sym) == 0)
- return NULL;
- sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
- if (!sc)
- return NULL;
-
- sc->symbol = kstrdup(sym, GFP_KERNEL);
- if (!sc->symbol) {
- kfree(sc);
- return NULL;
- }
- sc->offset = offset;
- update_symbol_cache(sc);
- return sc;
-}
-
-#define DEFINE_FETCH_symbol(type) \
-static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
- void *data, void *dest) \
-{ \
- struct symbol_cache *sc = data; \
- if (sc->addr) \
- fetch_memory_##type(regs, (void *)sc->addr, dest); \
- else \
- *(type *)dest = 0; \
-}
-DEFINE_BASIC_FETCH_FUNCS(symbol)
-DEFINE_FETCH_symbol(string)
-DEFINE_FETCH_symbol(string_size)
-
-/* Dereference memory access function */
-struct deref_fetch_param {
- struct fetch_param orig;
- long offset;
-};
-
-#define DEFINE_FETCH_deref(type) \
-static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
- void *data, void *dest) \
-{ \
- struct deref_fetch_param *dprm = data; \
- unsigned long addr; \
- call_fetch(&dprm->orig, regs, &addr); \
- if (addr) { \
- addr += dprm->offset; \
- fetch_memory_##type(regs, (void *)addr, dest); \
- } else \
- *(type *)dest = 0; \
-}
-DEFINE_BASIC_FETCH_FUNCS(deref)
-DEFINE_FETCH_deref(string)
-DEFINE_FETCH_deref(string_size)
-
-static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
-{
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- update_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- update_symbol_cache(data->orig.data);
-}
-
-static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
-{
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- free_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- free_symbol_cache(data->orig.data);
- kfree(data);
-}
-
-/* Bitfield fetch function */
-struct bitfield_fetch_param {
- struct fetch_param orig;
- unsigned char hi_shift;
- unsigned char low_shift;
-};
+#include "trace_probe.h"
-#define DEFINE_FETCH_bitfield(type) \
-static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
- void *data, void *dest) \
-{ \
- struct bitfield_fetch_param *bprm = data; \
- type buf = 0; \
- call_fetch(&bprm->orig, regs, &buf); \
- if (buf) { \
- buf <<= bprm->hi_shift; \
- buf >>= bprm->low_shift; \
- } \
- *(type *)dest = buf; \
-}
-DEFINE_BASIC_FETCH_FUNCS(bitfield)
-#define fetch_bitfield_string NULL
-#define fetch_bitfield_string_size NULL
-
-static __kprobes void
-update_bitfield_fetch_param(struct bitfield_fetch_param *data)
-{
- /*
- * Don't check the bitfield itself, because this must be the
- * last fetch function.
- */
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- update_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- update_symbol_cache(data->orig.data);
-}
-
-static __kprobes void
-free_bitfield_fetch_param(struct bitfield_fetch_param *data)
-{
- /*
- * Don't check the bitfield itself, because this must be the
- * last fetch function.
- */
- if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
- free_deref_fetch_param(data->orig.data);
- else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
- free_symbol_cache(data->orig.data);
- kfree(data);
-}
-
-/* Default (unsigned long) fetch type */
-#define __DEFAULT_FETCH_TYPE(t) u##t
-#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
-#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
-#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
-
-/* Fetch types */
-enum {
- FETCH_MTD_reg = 0,
- FETCH_MTD_stack,
- FETCH_MTD_retval,
- FETCH_MTD_memory,
- FETCH_MTD_symbol,
- FETCH_MTD_deref,
- FETCH_MTD_bitfield,
- FETCH_MTD_END,
-};
-
-#define ASSIGN_FETCH_FUNC(method, type) \
- [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
-
-#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
- {.name = _name, \
- .size = _size, \
- .is_signed = sign, \
- .print = PRINT_TYPE_FUNC_NAME(ptype), \
- .fmt = PRINT_TYPE_FMT_NAME(ptype), \
- .fmttype = _fmttype, \
- .fetch = { \
-ASSIGN_FETCH_FUNC(reg, ftype), \
-ASSIGN_FETCH_FUNC(stack, ftype), \
-ASSIGN_FETCH_FUNC(retval, ftype), \
-ASSIGN_FETCH_FUNC(memory, ftype), \
-ASSIGN_FETCH_FUNC(symbol, ftype), \
-ASSIGN_FETCH_FUNC(deref, ftype), \
-ASSIGN_FETCH_FUNC(bitfield, ftype), \
- } \
- }
-
-#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
- __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
-
-#define FETCH_TYPE_STRING 0
-#define FETCH_TYPE_STRSIZE 1
-
-/* Fetch type information table */
-static const struct fetch_type {
- const char *name; /* Name of type */
- size_t size; /* Byte size of type */
- int is_signed; /* Signed flag */
- print_type_func_t print; /* Print functions */
- const char *fmt; /* Fromat string */
- const char *fmttype; /* Name in format file */
- /* Fetch functions */
- fetch_func_t fetch[FETCH_MTD_END];
-} fetch_type_table[] = {
- /* Special types */
- [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
- sizeof(u32), 1, "__data_loc char[]"),
- [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
- string_size, sizeof(u32), 0, "u32"),
- /* Basic types */
- ASSIGN_FETCH_TYPE(u8, u8, 0),
- ASSIGN_FETCH_TYPE(u16, u16, 0),
- ASSIGN_FETCH_TYPE(u32, u32, 0),
- ASSIGN_FETCH_TYPE(u64, u64, 0),
- ASSIGN_FETCH_TYPE(s8, u8, 1),
- ASSIGN_FETCH_TYPE(s16, u16, 1),
- ASSIGN_FETCH_TYPE(s32, u32, 1),
- ASSIGN_FETCH_TYPE(s64, u64, 1),
-};
-
-static const struct fetch_type *find_fetch_type(const char *type)
-{
- int i;
-
- if (!type)
- type = DEFAULT_FETCH_TYPE_STR;
-
- /* Special case: bitfield */
- if (*type == 'b') {
- unsigned long bs;
- type = strchr(type, '/');
- if (!type)
- goto fail;
- type++;
- if (strict_strtoul(type, 0, &bs))
- goto fail;
- switch (bs) {
- case 8:
- return find_fetch_type("u8");
- case 16:
- return find_fetch_type("u16");
- case 32:
- return find_fetch_type("u32");
- case 64:
- return find_fetch_type("u64");
- default:
- goto fail;
- }
- }
-
- for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
- if (strcmp(type, fetch_type_table[i].name) == 0)
- return &fetch_type_table[i];
-fail:
- return NULL;
-}
-
-/* Special function : only accept unsigned long */
-static __kprobes void fetch_stack_address(struct pt_regs *regs,
- void *dummy, void *dest)
-{
- *(unsigned long *)dest = kernel_stack_pointer(regs);
-}
-
-static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
- fetch_func_t orig_fn)
-{
- int i;
-
- if (type != &fetch_type_table[FETCH_TYPE_STRING])
- return NULL; /* Only string type needs size function */
- for (i = 0; i < FETCH_MTD_END; i++)
- if (type->fetch[i] == orig_fn)
- return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
-
- WARN_ON(1); /* This should not happen */
- return NULL;
-}
+#define KPROBE_EVENT_SYSTEM "kprobes"
/**
* Kprobe event core functions
*/
-struct probe_arg {
- struct fetch_param fetch;
- struct fetch_param fetch_size;
- unsigned int offset; /* Offset from argument entry */
- const char *name; /* Name of this argument */
- const char *comm; /* Command of this argument */
- const struct fetch_type *type; /* Type of this argument */
-};
-
-/* Flags for trace_probe */
-#define TP_FLAG_TRACE 1
-#define TP_FLAG_PROFILE 2
-#define TP_FLAG_REGISTERED 4
-
struct trace_probe {
struct list_head list;
struct kretprobe rp; /* Use rp.kp for kprobe use */
@@ -631,18 +99,6 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
static int kretprobe_dispatcher(struct kretprobe_instance *ri,
struct pt_regs *regs);
-/* Check the name is good for event/group/fields */
-static int is_good_name(const char *name)
-{
- if (!isalpha(*name) && *name != '_')
- return 0;
- while (*++name != '\0') {
- if (!isalpha(*name) && !isdigit(*name) && *name != '_')
- return 0;
- }
- return 1;
-}
-
/*
* Allocate new trace_probe and initialize it (including kprobes).
*/
@@ -651,7 +107,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
void *addr,
const char *symbol,
unsigned long offs,
- int nargs, int is_return)
+ int nargs, bool is_return)
{
struct trace_probe *tp;
int ret = -ENOMEM;
@@ -702,34 +158,12 @@ error:
return ERR_PTR(ret);
}
-static void update_probe_arg(struct probe_arg *arg)
-{
- if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
- update_bitfield_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
- update_deref_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
- update_symbol_cache(arg->fetch.data);
-}
-
-static void free_probe_arg(struct probe_arg *arg)
-{
- if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
- free_bitfield_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
- free_deref_fetch_param(arg->fetch.data);
- else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
- free_symbol_cache(arg->fetch.data);
- kfree(arg->name);
- kfree(arg->comm);
-}
-
static void free_trace_probe(struct trace_probe *tp)
{
int i;
for (i = 0; i < tp->nr_args; i++)
- free_probe_arg(&tp->args[i]);
+ traceprobe_free_probe_arg(&tp->args[i]);
kfree(tp->call.class->system);
kfree(tp->call.name);
@@ -787,7 +221,7 @@ static int __register_trace_probe(struct trace_probe *tp)
return -EINVAL;
for (i = 0; i < tp->nr_args; i++)
- update_probe_arg(&tp->args[i]);
+ traceprobe_update_arg(&tp->args[i]);
/* Set/clear disabled flag according to tp->flag */
if (trace_probe_is_enabled(tp))
@@ -919,227 +353,6 @@ static struct notifier_block trace_probe_module_nb = {
.priority = 1 /* Invoked after kprobe module callback */
};
-/* Split symbol and offset. */
-static int split_symbol_offset(char *symbol, unsigned long *offset)
-{
- char *tmp;
- int ret;
-
- if (!offset)
- return -EINVAL;
-
- tmp = strchr(symbol, '+');
- if (tmp) {
- /* skip sign because strict_strtol doesn't accept '+' */
- ret = strict_strtoul(tmp + 1, 0, offset);
- if (ret)
- return ret;
- *tmp = '\0';
- } else
- *offset = 0;
- return 0;
-}
-
-#define PARAM_MAX_ARGS 16
-#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
-
-static int parse_probe_vars(char *arg, const struct fetch_type *t,
- struct fetch_param *f, int is_return)
-{
- int ret = 0;
- unsigned long param;
-
- if (strcmp(arg, "retval") == 0) {
- if (is_return)
- f->fn = t->fetch[FETCH_MTD_retval];
- else
- ret = -EINVAL;
- } else if (strncmp(arg, "stack", 5) == 0) {
- if (arg[5] == '\0') {
- if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
- f->fn = fetch_stack_address;
- else
- ret = -EINVAL;
- } else if (isdigit(arg[5])) {
- ret = strict_strtoul(arg + 5, 10, &param);
- if (ret || param > PARAM_MAX_STACK)
- ret = -EINVAL;
- else {
- f->fn = t->fetch[FETCH_MTD_stack];
- f->data = (void *)param;
- }
- } else
- ret = -EINVAL;
- } else
- ret = -EINVAL;
- return ret;
-}
-
-/* Recursive argument parser */
-static int __parse_probe_arg(char *arg, const struct fetch_type *t,
- struct fetch_param *f, int is_return)
-{
- int ret = 0;
- unsigned long param;
- long offset;
- char *tmp;
-
- switch (arg[0]) {
- case '$':
- ret = parse_probe_vars(arg + 1, t, f, is_return);
- break;
- case '%': /* named register */
- ret = regs_query_register_offset(arg + 1);
- if (ret >= 0) {
- f->fn = t->fetch[FETCH_MTD_reg];
- f->data = (void *)(unsigned long)ret;
- ret = 0;
- }
- break;
- case '@': /* memory or symbol */
- if (isdigit(arg[1])) {
- ret = strict_strtoul(arg + 1, 0, &param);
- if (ret)
- break;
- f->fn = t->fetch[FETCH_MTD_memory];
- f->data = (void *)param;
- } else {
- ret = split_symbol_offset(arg + 1, &offset);
- if (ret)
- break;
- f->data = alloc_symbol_cache(arg + 1, offset);
- if (f->data)
- f->fn = t->fetch[FETCH_MTD_symbol];
- }
- break;
- case '+': /* deref memory */
- arg++; /* Skip '+', because strict_strtol() rejects it. */
- case '-':
- tmp = strchr(arg, '(');
- if (!tmp)
- break;
- *tmp = '\0';
- ret = strict_strtol(arg, 0, &offset);
- if (ret)
- break;
- arg = tmp + 1;
- tmp = strrchr(arg, ')');
- if (tmp) {
- struct deref_fetch_param *dprm;
- const struct fetch_type *t2 = find_fetch_type(NULL);
- *tmp = '\0';
- dprm = kzalloc(sizeof(struct deref_fetch_param),
- GFP_KERNEL);
- if (!dprm)
- return -ENOMEM;
- dprm->offset = offset;
- ret = __parse_probe_arg(arg, t2, &dprm->orig,
- is_return);
- if (ret)
- kfree(dprm);
- else {
- f->fn = t->fetch[FETCH_MTD_deref];
- f->data = (void *)dprm;
- }
- }
- break;
- }
- if (!ret && !f->fn) { /* Parsed, but do not find fetch method */
- pr_info("%s type has no corresponding fetch method.\n",
- t->name);
- ret = -EINVAL;
- }
- return ret;
-}
-
-#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long))
-
-/* Bitfield type needs to be parsed into a fetch function */
-static int __parse_bitfield_probe_arg(const char *bf,
- const struct fetch_type *t,
- struct fetch_param *f)
-{
- struct bitfield_fetch_param *bprm;
- unsigned long bw, bo;
- char *tail;
-
- if (*bf != 'b')
- return 0;
-
- bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
- if (!bprm)
- return -ENOMEM;
- bprm->orig = *f;
- f->fn = t->fetch[FETCH_MTD_bitfield];
- f->data = (void *)bprm;
-
- bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */
- if (bw == 0 || *tail != '@')
- return -EINVAL;
-
- bf = tail + 1;
- bo = simple_strtoul(bf, &tail, 0);
- if (tail == bf || *tail != '/')
- return -EINVAL;
-
- bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
- bprm->low_shift = bprm->hi_shift + bo;
- return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
-}
-
-/* String length checking wrapper */
-static int parse_probe_arg(char *arg, struct trace_probe *tp,
- struct probe_arg *parg, int is_return)
-{
- const char *t;
- int ret;
-
- if (strlen(arg) > MAX_ARGSTR_LEN) {
- pr_info("Argument is too long.: %s\n", arg);
- return -ENOSPC;
- }
- parg->comm = kstrdup(arg, GFP_KERNEL);
- if (!parg->comm) {
- pr_info("Failed to allocate memory for command '%s'.\n", arg);
- return -ENOMEM;
- }
- t = strchr(parg->comm, ':');
- if (t) {
- arg[t - parg->comm] = '\0';
- t++;
- }
- parg->type = find_fetch_type(t);
- if (!parg->type) {
- pr_info("Unsupported type: %s\n", t);
- return -EINVAL;
- }
- parg->offset = tp->size;
- tp->size += parg->type->size;
- ret = __parse_probe_arg(arg, parg->type, &parg->fetch, is_return);
- if (ret >= 0 && t != NULL)
- ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
- if (ret >= 0) {
- parg->fetch_size.fn = get_fetch_size_function(parg->type,
- parg->fetch.fn);
- parg->fetch_size.data = parg->fetch.data;
- }
- return ret;
-}
-
-/* Return 1 if name is reserved or already used by another argument */
-static int conflict_field_name(const char *name,
- struct probe_arg *args, int narg)
-{
- int i;
- for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
- if (strcmp(reserved_field_names[i], name) == 0)
- return 1;
- for (i = 0; i < narg; i++)
- if (strcmp(args[i].name, name) == 0)
- return 1;
- return 0;
-}
-
static int create_trace_probe(int argc, char **argv)
{
/*
@@ -1162,7 +375,7 @@ static int create_trace_probe(int argc, char **argv)
*/
struct trace_probe *tp;
int i, ret = 0;
- int is_return = 0, is_delete = 0;
+ bool is_return = false, is_delete = false;
char *symbol = NULL, *event = NULL, *group = NULL;
char *arg;
unsigned long offset = 0;
@@ -1171,11 +384,11 @@ static int create_trace_probe(int argc, char **argv)
/* argc must be >= 1 */
if (argv[0][0] == 'p')
- is_return = 0;
+ is_return = false;
else if (argv[0][0] == 'r')
- is_return = 1;
+ is_return = true;
else if (argv[0][0] == '-')
- is_delete = 1;
+ is_delete = true;
else {
pr_info("Probe definition must be started with 'p', 'r' or"
" '-'.\n");
@@ -1240,7 +453,7 @@ static int create_trace_probe(int argc, char **argv)
/* a symbol specified */
symbol = argv[1];
/* TODO: support .init module functions */
- ret = split_symbol_offset(symbol, &offset);
+ ret = traceprobe_split_symbol_offset(symbol, &offset);
if (ret) {
pr_info("Failed to parse symbol.\n");
return ret;
@@ -1302,7 +515,8 @@ static int create_trace_probe(int argc, char **argv)
goto error;
}
- if (conflict_field_name(tp->args[i].name, tp->args, i)) {
+ if (traceprobe_conflict_field_name(tp->args[i].name,
+ tp->args, i)) {
pr_info("Argument[%d] name '%s' conflicts with "
"another field.\n", i, argv[i]);
ret = -EINVAL;
@@ -1310,7 +524,8 @@ static int create_trace_probe(int argc, char **argv)
}
/* Parse fetch argument */
- ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
+ ret = traceprobe_parse_probe_arg(arg, &tp->size, &tp->args[i],
+ is_return, true);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -1412,70 +627,11 @@ static int probes_open(struct inode *inode, struct file *file)
return seq_open(file, &probes_seq_op);
}
-static int command_trace_probe(const char *buf)
-{
- char **argv;
- int argc = 0, ret = 0;
-
- argv = argv_split(GFP_KERNEL, buf, &argc);
- if (!argv)
- return -ENOMEM;
-
- if (argc)
- ret = create_trace_probe(argc, argv);
-
- argv_free(argv);
- return ret;
-}
-
-#define WRITE_BUFSIZE 4096
-
static ssize_t probes_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
- char *kbuf, *tmp;
- int ret;
- size_t done;
- size_t size;
-
- kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
- if (!kbuf)
- return -ENOMEM;
-
- ret = done = 0;
- while (done < count) {
- size = count - done;
- if (size >= WRITE_BUFSIZE)
- size = WRITE_BUFSIZE - 1;
- if (copy_from_user(kbuf, buffer + done, size)) {
- ret = -EFAULT;
- goto out;
- }
- kbuf[size] = '\0';
- tmp = strchr(kbuf, '\n');
- if (tmp) {
- *tmp = '\0';
- size = tmp - kbuf + 1;
- } else if (done + size < count) {
- pr_warning("Line length is too long: "
- "Should be less than %d.", WRITE_BUFSIZE);
- ret = -EINVAL;
- goto out;
- }
- done += size;
- /* Remove comments */
- tmp = strchr(kbuf, '#');
- if (tmp)
- *tmp = '\0';
-
- ret = command_trace_probe(kbuf);
- if (ret)
- goto out;
- }
- ret = done;
-out:
- kfree(kbuf);
- return ret;
+ return traceprobe_probes_write(file, buffer, count, ppos,
+ create_trace_probe);
}
static const struct file_operations kprobe_events_ops = {
@@ -1711,16 +867,6 @@ partial:
return TRACE_TYPE_PARTIAL_LINE;
}
-#undef DEFINE_FIELD
-#define DEFINE_FIELD(type, item, name, is_signed) \
- do { \
- ret = trace_define_field(event_call, #type, name, \
- offsetof(typeof(field), item), \
- sizeof(field.item), is_signed, \
- FILTER_OTHER); \
- if (ret) \
- return ret; \
- } while (0)
static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
{
@@ -2051,8 +1197,9 @@ static __init int kprobe_trace_self_tests_init(void)
pr_info("Testing kprobe tracing: ");
- ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
- "$stack $stack0 +0($stack)");
+ ret = traceprobe_command("p:testprobe kprobe_trace_selftest_target "
+ "$stack $stack0 +0($stack)",
+ create_trace_probe);
if (WARN_ON_ONCE(ret)) {
pr_warning("error on probing function entry.\n");
warn++;
@@ -2066,8 +1213,8 @@ static __init int kprobe_trace_self_tests_init(void)
enable_trace_probe(tp, TP_FLAG_TRACE);
}
- ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
- "$retval");
+ ret = traceprobe_command("r:testprobe2 kprobe_trace_selftest_target "
+ "$retval", create_trace_probe);
if (WARN_ON_ONCE(ret)) {
pr_warning("error on probing function return.\n");
warn++;
@@ -2101,13 +1248,13 @@ static __init int kprobe_trace_self_tests_init(void)
} else
disable_trace_probe(tp, TP_FLAG_TRACE);
- ret = command_trace_probe("-:testprobe");
+ ret = traceprobe_command("-:testprobe", create_trace_probe);
if (WARN_ON_ONCE(ret)) {
pr_warning("error on deleting a probe.\n");
warn++;
}
- ret = command_trace_probe("-:testprobe2");
+ ret = traceprobe_command("-:testprobe2", create_trace_probe);
if (WARN_ON_ONCE(ret)) {
pr_warning("error on deleting a probe.\n");
warn++;
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
new file mode 100644
index 000000000000..daa9980153af
--- /dev/null
+++ b/kernel/trace/trace_probe.c
@@ -0,0 +1,839 @@
+/*
+ * Common code for probe-based Dynamic events.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * This code was copied from kernel/trace/trace_kprobe.c written by
+ * Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Updates to make this generic:
+ * Copyright (C) IBM Corporation, 2010-2011
+ * Author: Srikar Dronamraju
+ */
+
+#include "trace_probe.h"
+
+const char *reserved_field_names[] = {
+ "common_type",
+ "common_flags",
+ "common_preempt_count",
+ "common_pid",
+ "common_tgid",
+ FIELD_STRING_IP,
+ FIELD_STRING_RETIP,
+ FIELD_STRING_FUNC,
+};
+
+/* Printing function type */
+#define PRINT_TYPE_FUNC_NAME(type) print_type_##type
+#define PRINT_TYPE_FMT_NAME(type) print_type_format_##type
+
+/* Printing in basic type function template */
+#define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt, cast) \
+static __kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, \
+ const char *name, \
+ void *data, void *ent)\
+{ \
+ return trace_seq_printf(s, " %s=" fmt, name, (cast)*(type *)data);\
+} \
+static const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
+
+DEFINE_BASIC_PRINT_TYPE_FUNC(u8, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "%x", unsigned int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u32, "%lx", unsigned long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(u64, "%llx", unsigned long long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s8, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s16, "%d", int)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%ld", long)
+DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%lld", long long)
+
+static inline void *get_rloc_data(u32 *dl)
+{
+ return (u8 *)dl + get_rloc_offs(*dl);
+}
+
+/* For data_loc conversion */
+static inline void *get_loc_data(u32 *dl, void *ent)
+{
+ return (u8 *)ent + get_rloc_offs(*dl);
+}
+
+/* For defining macros, define string/string_size types */
+typedef u32 string;
+typedef u32 string_size;
+
+/* Print type function for string type */
+static __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
+ const char *name,
+ void *data, void *ent)
+{
+ int len = *(u32 *)data >> 16;
+
+ if (!len)
+ return trace_seq_printf(s, " %s=(fault)", name);
+ else
+ return trace_seq_printf(s, " %s=\"%s\"", name,
+ (const char *)get_loc_data(data, ent));
+}
+
+static const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
+
+#define FETCH_FUNC_NAME(method, type) fetch_##method##_##type
+/*
+ * Define macro for basic types - we don't need to define s* types, because
+ * we have to care only about bitwidth at recording time.
+ */
+#define DEFINE_BASIC_FETCH_FUNCS(method) \
+DEFINE_FETCH_##method(u8) \
+DEFINE_FETCH_##method(u16) \
+DEFINE_FETCH_##method(u32) \
+DEFINE_FETCH_##method(u64)
+
+#define CHECK_FETCH_FUNCS(method, fn) \
+ (((FETCH_FUNC_NAME(method, u8) == fn) || \
+ (FETCH_FUNC_NAME(method, u16) == fn) || \
+ (FETCH_FUNC_NAME(method, u32) == fn) || \
+ (FETCH_FUNC_NAME(method, u64) == fn) || \
+ (FETCH_FUNC_NAME(method, string) == fn) || \
+ (FETCH_FUNC_NAME(method, string_size) == fn)) \
+ && (fn != NULL))
+
+/* Data fetch function templates */
+#define DEFINE_FETCH_reg(type) \
+static __kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, \
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)regs_get_register(regs, \
+ (unsigned int)((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(reg)
+/* No string on the register */
+#define fetch_reg_string NULL
+#define fetch_reg_string_size NULL
+
+#define DEFINE_FETCH_stack(type) \
+static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+ void *offset, void *dest) \
+{ \
+ *(type *)dest = (type)regs_get_kernel_stack_nth(regs, \
+ (unsigned int)((unsigned long)offset)); \
+}
+DEFINE_BASIC_FETCH_FUNCS(stack)
+/* No string on the stack entry */
+#define fetch_stack_string NULL
+#define fetch_stack_string_size NULL
+
+#define DEFINE_FETCH_retval(type) \
+static __kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,\
+ void *dummy, void *dest) \
+{ \
+ *(type *)dest = (type)regs_return_value(regs); \
+}
+DEFINE_BASIC_FETCH_FUNCS(retval)
+/* No string on the retval */
+#define fetch_retval_string NULL
+#define fetch_retval_string_size NULL
+
+#define DEFINE_FETCH_memory(type) \
+static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+ void *addr, void *dest) \
+{ \
+ type retval; \
+ if (probe_kernel_address(addr, retval)) \
+ *(type *)dest = 0; \
+ else \
+ *(type *)dest = retval; \
+}
+DEFINE_BASIC_FETCH_FUNCS(memory)
+/*
+ * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
+ * length and relative data location.
+ */
+static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ long ret;
+ int maxlen = get_rloc_len(*(u32 *)dest);
+ u8 *dst = get_rloc_data(dest);
+ u8 *src = addr;
+ mm_segment_t old_fs = get_fs();
+
+ if (!maxlen)
+ return;
+
+ /*
+ * Try to get string again, since the string can be changed while
+ * probing.
+ */
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do
+ ret = __copy_from_user_inatomic(dst++, src++, 1);
+ while (dst[-1] && ret == 0 && src - (u8 *)addr < maxlen);
+
+ dst[-1] = '\0';
+ pagefault_enable();
+ set_fs(old_fs);
+
+ if (ret < 0) { /* Failed to fetch string */
+ ((u8 *)get_rloc_data(dest))[0] = '\0';
+ *(u32 *)dest = make_data_rloc(0, get_rloc_offs(*(u32 *)dest));
+ } else {
+ *(u32 *)dest = make_data_rloc(src - (u8 *)addr,
+ get_rloc_offs(*(u32 *)dest));
+ }
+}
+
+/* Return the length of string -- including null terminal byte */
+static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+ void *addr, void *dest)
+{
+ mm_segment_t old_fs;
+ int ret, len = 0;
+ u8 c;
+
+ old_fs = get_fs();
+ set_fs(KERNEL_DS);
+ pagefault_disable();
+
+ do {
+ ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+ len++;
+ } while (c && ret == 0 && len < MAX_STRING_SIZE);
+
+ pagefault_enable();
+ set_fs(old_fs);
+
+ if (ret < 0) /* Failed to check the length */
+ *(u32 *)dest = 0;
+ else
+ *(u32 *)dest = len;
+}
+
+/* Memory fetching by symbol */
+struct symbol_cache {
+ char *symbol;
+ long offset;
+ unsigned long addr;
+};
+
+static unsigned long update_symbol_cache(struct symbol_cache *sc)
+{
+ sc->addr = (unsigned long)kallsyms_lookup_name(sc->symbol);
+
+ if (sc->addr)
+ sc->addr += sc->offset;
+
+ return sc->addr;
+}
+
+static void free_symbol_cache(struct symbol_cache *sc)
+{
+ kfree(sc->symbol);
+ kfree(sc);
+}
+
+static struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
+{
+ struct symbol_cache *sc;
+
+ if (!sym || strlen(sym) == 0)
+ return NULL;
+
+ sc = kzalloc(sizeof(struct symbol_cache), GFP_KERNEL);
+ if (!sc)
+ return NULL;
+
+ sc->symbol = kstrdup(sym, GFP_KERNEL);
+ if (!sc->symbol) {
+ kfree(sc);
+ return NULL;
+ }
+ sc->offset = offset;
+ update_symbol_cache(sc);
+
+ return sc;
+}
+
+#define DEFINE_FETCH_symbol(type) \
+static __kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct symbol_cache *sc = data; \
+ if (sc->addr) \
+ fetch_memory_##type(regs, (void *)sc->addr, dest); \
+ else \
+ *(type *)dest = 0; \
+}
+DEFINE_BASIC_FETCH_FUNCS(symbol)
+DEFINE_FETCH_symbol(string)
+DEFINE_FETCH_symbol(string_size)
+
+/* Dereference memory access function */
+struct deref_fetch_param {
+ struct fetch_param orig;
+ long offset;
+};
+
+#define DEFINE_FETCH_deref(type) \
+static __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct deref_fetch_param *dprm = data; \
+ unsigned long addr; \
+ call_fetch(&dprm->orig, regs, &addr); \
+ if (addr) { \
+ addr += dprm->offset; \
+ fetch_memory_##type(regs, (void *)addr, dest); \
+ } else \
+ *(type *)dest = 0; \
+}
+DEFINE_BASIC_FETCH_FUNCS(deref)
+DEFINE_FETCH_deref(string)
+DEFINE_FETCH_deref(string_size)
+
+static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
+{
+ if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+ update_deref_fetch_param(data->orig.data);
+ else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+ update_symbol_cache(data->orig.data);
+}
+
+static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
+{
+ if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+ free_deref_fetch_param(data->orig.data);
+ else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+ free_symbol_cache(data->orig.data);
+ kfree(data);
+}
+
+/* Bitfield fetch function */
+struct bitfield_fetch_param {
+ struct fetch_param orig;
+ unsigned char hi_shift;
+ unsigned char low_shift;
+};
+
+#define DEFINE_FETCH_bitfield(type) \
+static __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,\
+ void *data, void *dest) \
+{ \
+ struct bitfield_fetch_param *bprm = data; \
+ type buf = 0; \
+ call_fetch(&bprm->orig, regs, &buf); \
+ if (buf) { \
+ buf <<= bprm->hi_shift; \
+ buf >>= bprm->low_shift; \
+ } \
+ *(type *)dest = buf; \
+}
+
+DEFINE_BASIC_FETCH_FUNCS(bitfield)
+#define fetch_bitfield_string NULL
+#define fetch_bitfield_string_size NULL
+
+static __kprobes void
+update_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+ /*
+ * Don't check the bitfield itself, because this must be the
+ * last fetch function.
+ */
+ if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+ update_deref_fetch_param(data->orig.data);
+ else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+ update_symbol_cache(data->orig.data);
+}
+
+static __kprobes void
+free_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+ /*
+ * Don't check the bitfield itself, because this must be the
+ * last fetch function.
+ */
+ if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+ free_deref_fetch_param(data->orig.data);
+ else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+ free_symbol_cache(data->orig.data);
+
+ kfree(data);
+}
+
+/* Default (unsigned long) fetch type */
+#define __DEFAULT_FETCH_TYPE(t) u##t
+#define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
+#define DEFAULT_FETCH_TYPE _DEFAULT_FETCH_TYPE(BITS_PER_LONG)
+#define DEFAULT_FETCH_TYPE_STR __stringify(DEFAULT_FETCH_TYPE)
+
+#define ASSIGN_FETCH_FUNC(method, type) \
+ [FETCH_MTD_##method] = FETCH_FUNC_NAME(method, type)
+
+#define __ASSIGN_FETCH_TYPE(_name, ptype, ftype, _size, sign, _fmttype) \
+ {.name = _name, \
+ .size = _size, \
+ .is_signed = sign, \
+ .print = PRINT_TYPE_FUNC_NAME(ptype), \
+ .fmt = PRINT_TYPE_FMT_NAME(ptype), \
+ .fmttype = _fmttype, \
+ .fetch = { \
+ASSIGN_FETCH_FUNC(reg, ftype), \
+ASSIGN_FETCH_FUNC(stack, ftype), \
+ASSIGN_FETCH_FUNC(retval, ftype), \
+ASSIGN_FETCH_FUNC(memory, ftype), \
+ASSIGN_FETCH_FUNC(symbol, ftype), \
+ASSIGN_FETCH_FUNC(deref, ftype), \
+ASSIGN_FETCH_FUNC(bitfield, ftype), \
+ } \
+ }
+
+#define ASSIGN_FETCH_TYPE(ptype, ftype, sign) \
+ __ASSIGN_FETCH_TYPE(#ptype, ptype, ftype, sizeof(ftype), sign, #ptype)
+
+#define FETCH_TYPE_STRING 0
+#define FETCH_TYPE_STRSIZE 1
+
+/* Fetch type information table */
+static const struct fetch_type fetch_type_table[] = {
+ /* Special types */
+ [FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
+ sizeof(u32), 1, "__data_loc char[]"),
+ [FETCH_TYPE_STRSIZE] = __ASSIGN_FETCH_TYPE("string_size", u32,
+ string_size, sizeof(u32), 0, "u32"),
+ /* Basic types */
+ ASSIGN_FETCH_TYPE(u8, u8, 0),
+ ASSIGN_FETCH_TYPE(u16, u16, 0),
+ ASSIGN_FETCH_TYPE(u32, u32, 0),
+ ASSIGN_FETCH_TYPE(u64, u64, 0),
+ ASSIGN_FETCH_TYPE(s8, u8, 1),
+ ASSIGN_FETCH_TYPE(s16, u16, 1),
+ ASSIGN_FETCH_TYPE(s32, u32, 1),
+ ASSIGN_FETCH_TYPE(s64, u64, 1),
+};
+
+static const struct fetch_type *find_fetch_type(const char *type)
+{
+ int i;
+
+ if (!type)
+ type = DEFAULT_FETCH_TYPE_STR;
+
+ /* Special case: bitfield */
+ if (*type == 'b') {
+ unsigned long bs;
+
+ type = strchr(type, '/');
+ if (!type)
+ goto fail;
+
+ type++;
+ if (strict_strtoul(type, 0, &bs))
+ goto fail;
+
+ switch (bs) {
+ case 8:
+ return find_fetch_type("u8");
+ case 16:
+ return find_fetch_type("u16");
+ case 32:
+ return find_fetch_type("u32");
+ case 64:
+ return find_fetch_type("u64");
+ default:
+ goto fail;
+ }
+ }
+
+ for (i = 0; i < ARRAY_SIZE(fetch_type_table); i++)
+ if (strcmp(type, fetch_type_table[i].name) == 0)
+ return &fetch_type_table[i];
+
+fail:
+ return NULL;
+}
+
+/* Special function : only accept unsigned long */
+static __kprobes void fetch_stack_address(struct pt_regs *regs,
+ void *dummy, void *dest)
+{
+ *(unsigned long *)dest = kernel_stack_pointer(regs);
+}
+
+static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
+ fetch_func_t orig_fn)
+{
+ int i;
+
+ if (type != &fetch_type_table[FETCH_TYPE_STRING])
+ return NULL; /* Only string type needs size function */
+
+ for (i = 0; i < FETCH_MTD_END; i++)
+ if (type->fetch[i] == orig_fn)
+ return fetch_type_table[FETCH_TYPE_STRSIZE].fetch[i];
+
+ WARN_ON(1); /* This should not happen */
+
+ return NULL;
+}
+
+/* Split symbol and offset. */
+int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
+{
+ char *tmp;
+ int ret;
+
+ if (!offset)
+ return -EINVAL;
+
+ tmp = strchr(symbol, '+');
+ if (tmp) {
+ /* skip sign because strict_strtol doesn't accept '+' */
+ ret = strict_strtoul(tmp + 1, 0, offset);
+ if (ret)
+ return ret;
+
+ *tmp = '\0';
+ } else
+ *offset = 0;
+
+ return 0;
+}
+
+#define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long))
+
+static int parse_probe_vars(char *arg, const struct fetch_type *t,
+ struct fetch_param *f, bool is_return)
+{
+ int ret = 0;
+ unsigned long param;
+
+ if (strcmp(arg, "retval") == 0) {
+ if (is_return)
+ f->fn = t->fetch[FETCH_MTD_retval];
+ else
+ ret = -EINVAL;
+ } else if (strncmp(arg, "stack", 5) == 0) {
+ if (arg[5] == '\0') {
+ if (strcmp(t->name, DEFAULT_FETCH_TYPE_STR) == 0)
+ f->fn = fetch_stack_address;
+ else
+ ret = -EINVAL;
+ } else if (isdigit(arg[5])) {
+ ret = strict_strtoul(arg + 5, 10, &param);
+ if (ret || param > PARAM_MAX_STACK)
+ ret = -EINVAL;
+ else {
+ f->fn = t->fetch[FETCH_MTD_stack];
+ f->data = (void *)param;
+ }
+ } else
+ ret = -EINVAL;
+ } else
+ ret = -EINVAL;
+
+ return ret;
+}
+
+/* Recursive argument parser */
+static int parse_probe_arg(char *arg, const struct fetch_type *t,
+ struct fetch_param *f, bool is_return, bool is_kprobe)
+{
+ unsigned long param;
+ long offset;
+ char *tmp;
+ int ret;
+
+ ret = 0;
+
+ /* Until uprobe_events supports only reg arguments */
+ if (!is_kprobe && arg[0] != '%')
+ return -EINVAL;
+
+ switch (arg[0]) {
+ case '$':
+ ret = parse_probe_vars(arg + 1, t, f, is_return);
+ break;
+
+ case '%': /* named register */
+ ret = regs_query_register_offset(arg + 1);
+ if (ret >= 0) {
+ f->fn = t->fetch[FETCH_MTD_reg];
+ f->data = (void *)(unsigned long)ret;
+ ret = 0;
+ }
+ break;
+
+ case '@': /* memory or symbol */
+ if (isdigit(arg[1])) {
+ ret = strict_strtoul(arg + 1, 0, &param);
+ if (ret)
+ break;
+
+ f->fn = t->fetch[FETCH_MTD_memory];
+ f->data = (void *)param;
+ } else {
+ ret = traceprobe_split_symbol_offset(arg + 1, &offset);
+ if (ret)
+ break;
+
+ f->data = alloc_symbol_cache(arg + 1, offset);
+ if (f->data)
+ f->fn = t->fetch[FETCH_MTD_symbol];
+ }
+ break;
+
+ case '+': /* deref memory */
+ arg++; /* Skip '+', because strict_strtol() rejects it. */
+ case '-':
+ tmp = strchr(arg, '(');
+ if (!tmp)
+ break;
+
+ *tmp = '\0';
+ ret = strict_strtol(arg, 0, &offset);
+
+ if (ret)
+ break;
+
+ arg = tmp + 1;
+ tmp = strrchr(arg, ')');
+
+ if (tmp) {
+ struct deref_fetch_param *dprm;
+ const struct fetch_type *t2;
+
+ t2 = find_fetch_type(NULL);
+ *tmp = '\0';
+ dprm = kzalloc(sizeof(struct deref_fetch_param), GFP_KERNEL);
+
+ if (!dprm)
+ return -ENOMEM;
+
+ dprm->offset = offset;
+ ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
+ is_kprobe);
+ if (ret)
+ kfree(dprm);
+ else {
+ f->fn = t->fetch[FETCH_MTD_deref];
+ f->data = (void *)dprm;
+ }
+ }
+ break;
+ }
+ if (!ret && !f->fn) { /* Parsed, but do not find fetch method */
+ pr_info("%s type has no corresponding fetch method.\n", t->name);
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
+#define BYTES_TO_BITS(nb) ((BITS_PER_LONG * (nb)) / sizeof(long))
+
+/* Bitfield type needs to be parsed into a fetch function */
+static int __parse_bitfield_probe_arg(const char *bf,
+ const struct fetch_type *t,
+ struct fetch_param *f)
+{
+ struct bitfield_fetch_param *bprm;
+ unsigned long bw, bo;
+ char *tail;
+
+ if (*bf != 'b')
+ return 0;
+
+ bprm = kzalloc(sizeof(*bprm), GFP_KERNEL);
+ if (!bprm)
+ return -ENOMEM;
+
+ bprm->orig = *f;
+ f->fn = t->fetch[FETCH_MTD_bitfield];
+ f->data = (void *)bprm;
+ bw = simple_strtoul(bf + 1, &tail, 0); /* Use simple one */
+
+ if (bw == 0 || *tail != '@')
+ return -EINVAL;
+
+ bf = tail + 1;
+ bo = simple_strtoul(bf, &tail, 0);
+
+ if (tail == bf || *tail != '/')
+ return -EINVAL;
+
+ bprm->hi_shift = BYTES_TO_BITS(t->size) - (bw + bo);
+ bprm->low_shift = bprm->hi_shift + bo;
+
+ return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0;
+}
+
+/* String length checking wrapper */
+int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
+ struct probe_arg *parg, bool is_return, bool is_kprobe)
+{
+ const char *t;
+ int ret;
+
+ if (strlen(arg) > MAX_ARGSTR_LEN) {
+ pr_info("Argument is too long.: %s\n", arg);
+ return -ENOSPC;
+ }
+ parg->comm = kstrdup(arg, GFP_KERNEL);
+ if (!parg->comm) {
+ pr_info("Failed to allocate memory for command '%s'.\n", arg);
+ return -ENOMEM;
+ }
+ t = strchr(parg->comm, ':');
+ if (t) {
+ arg[t - parg->comm] = '\0';
+ t++;
+ }
+ parg->type = find_fetch_type(t);
+ if (!parg->type) {
+ pr_info("Unsupported type: %s\n", t);
+ return -EINVAL;
+ }
+ parg->offset = *size;
+ *size += parg->type->size;
+ ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, is_kprobe);
+
+ if (ret >= 0 && t != NULL)
+ ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
+
+ if (ret >= 0) {
+ parg->fetch_size.fn = get_fetch_size_function(parg->type,
+ parg->fetch.fn);
+ parg->fetch_size.data = parg->fetch.data;
+ }
+
+ return ret;
+}
+
+/* Return 1 if name is reserved or already used by another argument */
+int traceprobe_conflict_field_name(const char *name,
+ struct probe_arg *args, int narg)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+ if (strcmp(reserved_field_names[i], name) == 0)
+ return 1;
+
+ for (i = 0; i < narg; i++)
+ if (strcmp(args[i].name, name) == 0)
+ return 1;
+
+ return 0;
+}
+
+void traceprobe_update_arg(struct probe_arg *arg)
+{
+ if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+ update_bitfield_fetch_param(arg->fetch.data);
+ else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+ update_deref_fetch_param(arg->fetch.data);
+ else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+ update_symbol_cache(arg->fetch.data);
+}
+
+void traceprobe_free_probe_arg(struct probe_arg *arg)
+{
+ if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+ free_bitfield_fetch_param(arg->fetch.data);
+ else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+ free_deref_fetch_param(arg->fetch.data);
+ else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+ free_symbol_cache(arg->fetch.data);
+
+ kfree(arg->name);
+ kfree(arg->comm);
+}
+
+int traceprobe_command(const char *buf, int (*createfn)(int, char **))
+{
+ char **argv;
+ int argc, ret;
+
+ argc = 0;
+ ret = 0;
+ argv = argv_split(GFP_KERNEL, buf, &argc);
+ if (!argv)
+ return -ENOMEM;
+
+ if (argc)
+ ret = createfn(argc, argv);
+
+ argv_free(argv);
+
+ return ret;
+}
+
+#define WRITE_BUFSIZE 4096
+
+ssize_t traceprobe_probes_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos,
+ int (*createfn)(int, char **))
+{
+ char *kbuf, *tmp;
+ int ret = 0;
+ size_t done = 0;
+ size_t size;
+
+ kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ while (done < count) {
+ size = count - done;
+
+ if (size >= WRITE_BUFSIZE)
+ size = WRITE_BUFSIZE - 1;
+
+ if (copy_from_user(kbuf, buffer + done, size)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ kbuf[size] = '\0';
+ tmp = strchr(kbuf, '\n');
+
+ if (tmp) {
+ *tmp = '\0';
+ size = tmp - kbuf + 1;
+ } else if (done + size < count) {
+ pr_warning("Line length is too long: "
+ "Should be less than %d.", WRITE_BUFSIZE);
+ ret = -EINVAL;
+ goto out;
+ }
+ done += size;
+ /* Remove comments */
+ tmp = strchr(kbuf, '#');
+
+ if (tmp)
+ *tmp = '\0';
+
+ ret = traceprobe_command(kbuf, createfn);
+ if (ret)
+ goto out;
+ }
+ ret = done;
+
+out:
+ kfree(kbuf);
+
+ return ret;
+}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
new file mode 100644
index 000000000000..933708677814
--- /dev/null
+++ b/kernel/trace/trace_probe.h
@@ -0,0 +1,161 @@
+/*
+ * Common header file for probe-based Dynamic events.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * This code was copied from kernel/trace/trace_kprobe.h written by
+ * Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
+ *
+ * Updates to make this generic:
+ * Copyright (C) IBM Corporation, 2010-2011
+ * Author: Srikar Dronamraju
+ */
+
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/debugfs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/ptrace.h>
+#include <linux/perf_event.h>
+#include <linux/kprobes.h>
+#include <linux/stringify.h>
+#include <linux/limits.h>
+#include <linux/uaccess.h>
+#include <asm/bitsperlong.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+#define MAX_TRACE_ARGS 128
+#define MAX_ARGSTR_LEN 63
+#define MAX_EVENT_NAME_LEN 64
+#define MAX_STRING_SIZE PATH_MAX
+
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+#undef DEFINE_FIELD
+#define DEFINE_FIELD(type, item, name, is_signed) \
+ do { \
+ ret = trace_define_field(event_call, #type, name, \
+ offsetof(typeof(field), item), \
+ sizeof(field.item), is_signed, \
+ FILTER_OTHER); \
+ if (ret) \
+ return ret; \
+ } while (0)
+
+
+/* Flags for trace_probe */
+#define TP_FLAG_TRACE 1
+#define TP_FLAG_PROFILE 2
+#define TP_FLAG_REGISTERED 4
+#define TP_FLAG_UPROBE 8
+
+
+/* data_rloc: data relative location, compatible with u32 */
+#define make_data_rloc(len, roffs) \
+ (((u32)(len) << 16) | ((u32)(roffs) & 0xffff))
+#define get_rloc_len(dl) ((u32)(dl) >> 16)
+#define get_rloc_offs(dl) ((u32)(dl) & 0xffff)
+
+/*
+ * Convert data_rloc to data_loc:
+ * data_rloc stores the offset from data_rloc itself, but data_loc
+ * stores the offset from event entry.
+ */
+#define convert_rloc_to_loc(dl, offs) ((u32)(dl) + (offs))
+
+/* Data fetch function type */
+typedef void (*fetch_func_t)(struct pt_regs *, void *, void *);
+/* Printing function type */
+typedef int (*print_type_func_t)(struct trace_seq *, const char *, void *, void *);
+
+/* Fetch types */
+enum {
+ FETCH_MTD_reg = 0,
+ FETCH_MTD_stack,
+ FETCH_MTD_retval,
+ FETCH_MTD_memory,
+ FETCH_MTD_symbol,
+ FETCH_MTD_deref,
+ FETCH_MTD_bitfield,
+ FETCH_MTD_END,
+};
+
+/* Fetch type information table */
+struct fetch_type {
+ const char *name; /* Name of type */
+ size_t size; /* Byte size of type */
+ int is_signed; /* Signed flag */
+ print_type_func_t print; /* Print functions */
+ const char *fmt; /* Fromat string */
+ const char *fmttype; /* Name in format file */
+ /* Fetch functions */
+ fetch_func_t fetch[FETCH_MTD_END];
+};
+
+struct fetch_param {
+ fetch_func_t fn;
+ void *data;
+};
+
+struct probe_arg {
+ struct fetch_param fetch;
+ struct fetch_param fetch_size;
+ unsigned int offset; /* Offset from argument entry */
+ const char *name; /* Name of this argument */
+ const char *comm; /* Command of this argument */
+ const struct fetch_type *type; /* Type of this argument */
+};
+
+static inline __kprobes void call_fetch(struct fetch_param *fprm,
+ struct pt_regs *regs, void *dest)
+{
+ return fprm->fn(regs, fprm->data, dest);
+}
+
+/* Check the name is good for event/group/fields */
+static inline int is_good_name(const char *name)
+{
+ if (!isalpha(*name) && *name != '_')
+ return 0;
+ while (*++name != '\0') {
+ if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+ return 0;
+ }
+ return 1;
+}
+
+extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
+ struct probe_arg *parg, bool is_return, bool is_kprobe);
+
+extern int traceprobe_conflict_field_name(const char *name,
+ struct probe_arg *args, int narg);
+
+extern void traceprobe_update_arg(struct probe_arg *arg);
+extern void traceprobe_free_probe_arg(struct probe_arg *arg);
+
+extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset);
+
+extern ssize_t traceprobe_probes_write(struct file *file,
+ const char __user *buffer, size_t count, loff_t *ppos,
+ int (*createfn)(int, char**));
+
+extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
new file mode 100644
index 000000000000..2b36ac68549e
--- /dev/null
+++ b/kernel/trace/trace_uprobe.c
@@ -0,0 +1,788 @@
+/*
+ * uprobes-based tracing events
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * Copyright (C) IBM Corporation, 2010-2012
+ * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/uprobes.h>
+#include <linux/namei.h>
+
+#include "trace_probe.h"
+
+#define UPROBE_EVENT_SYSTEM "uprobes"
+
+/*
+ * uprobe event core functions
+ */
+struct trace_uprobe;
+struct uprobe_trace_consumer {
+ struct uprobe_consumer cons;
+ struct trace_uprobe *tu;
+};
+
+struct trace_uprobe {
+ struct list_head list;
+ struct ftrace_event_class class;
+ struct ftrace_event_call call;
+ struct uprobe_trace_consumer *consumer;
+ struct inode *inode;
+ char *filename;
+ unsigned long offset;
+ unsigned long nhit;
+ unsigned int flags; /* For TP_FLAG_* */
+ ssize_t size; /* trace entry size */
+ unsigned int nr_args;
+ struct probe_arg args[];
+};
+
+#define SIZEOF_TRACE_UPROBE(n) \
+ (offsetof(struct trace_uprobe, args) + \
+ (sizeof(struct probe_arg) * (n)))
+
+static int register_uprobe_event(struct trace_uprobe *tu);
+static void unregister_uprobe_event(struct trace_uprobe *tu);
+
+static DEFINE_MUTEX(uprobe_lock);
+static LIST_HEAD(uprobe_list);
+
+static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs);
+
+/*
+ * Allocate new trace_uprobe and initialize it (including uprobes).
+ */
+static struct trace_uprobe *
+alloc_trace_uprobe(const char *group, const char *event, int nargs)
+{
+ struct trace_uprobe *tu;
+
+ if (!event || !is_good_name(event))
+ return ERR_PTR(-EINVAL);
+
+ if (!group || !is_good_name(group))
+ return ERR_PTR(-EINVAL);
+
+ tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL);
+ if (!tu)
+ return ERR_PTR(-ENOMEM);
+
+ tu->call.class = &tu->class;
+ tu->call.name = kstrdup(event, GFP_KERNEL);
+ if (!tu->call.name)
+ goto error;
+
+ tu->class.system = kstrdup(group, GFP_KERNEL);
+ if (!tu->class.system)
+ goto error;
+
+ INIT_LIST_HEAD(&tu->list);
+ return tu;
+
+error:
+ kfree(tu->call.name);
+ kfree(tu);
+
+ return ERR_PTR(-ENOMEM);
+}
+
+static void free_trace_uprobe(struct trace_uprobe *tu)
+{
+ int i;
+
+ for (i = 0; i < tu->nr_args; i++)
+ traceprobe_free_probe_arg(&tu->args[i]);
+
+ iput(tu->inode);
+ kfree(tu->call.class->system);
+ kfree(tu->call.name);
+ kfree(tu->filename);
+ kfree(tu);
+}
+
+static struct trace_uprobe *find_probe_event(const char *event, const char *group)
+{
+ struct trace_uprobe *tu;
+
+ list_for_each_entry(tu, &uprobe_list, list)
+ if (strcmp(tu->call.name, event) == 0 &&
+ strcmp(tu->call.class->system, group) == 0)
+ return tu;
+
+ return NULL;
+}
+
+/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */
+static void unregister_trace_uprobe(struct trace_uprobe *tu)
+{
+ list_del(&tu->list);
+ unregister_uprobe_event(tu);
+ free_trace_uprobe(tu);
+}
+
+/* Register a trace_uprobe and probe_event */
+static int register_trace_uprobe(struct trace_uprobe *tu)
+{
+ struct trace_uprobe *old_tp;
+ int ret;
+
+ mutex_lock(&uprobe_lock);
+
+ /* register as an event */
+ old_tp = find_probe_event(tu->call.name, tu->call.class->system);
+ if (old_tp)
+ /* delete old event */
+ unregister_trace_uprobe(old_tp);
+
+ ret = register_uprobe_event(tu);
+ if (ret) {
+ pr_warning("Failed to register probe event(%d)\n", ret);
+ goto end;
+ }
+
+ list_add_tail(&tu->list, &uprobe_list);
+
+end:
+ mutex_unlock(&uprobe_lock);
+
+ return ret;
+}
+
+/*
+ * Argument syntax:
+ * - Add uprobe: p[:[GRP/]EVENT] PATH:SYMBOL[+offs] [FETCHARGS]
+ *
+ * - Remove uprobe: -:[GRP/]EVENT
+ */
+static int create_trace_uprobe(int argc, char **argv)
+{
+ struct trace_uprobe *tu;
+ struct inode *inode;
+ char *arg, *event, *group, *filename;
+ char buf[MAX_EVENT_NAME_LEN];
+ struct path path;
+ unsigned long offset;
+ bool is_delete;
+ int i, ret;
+
+ inode = NULL;
+ ret = 0;
+ is_delete = false;
+ event = NULL;
+ group = NULL;
+
+ /* argc must be >= 1 */
+ if (argv[0][0] == '-')
+ is_delete = true;
+ else if (argv[0][0] != 'p') {
+ pr_info("Probe definition must be started with 'p', 'r' or" " '-'.\n");
+ return -EINVAL;
+ }
+
+ if (argv[0][1] == ':') {
+ event = &argv[0][2];
+ arg = strchr(event, '/');
+
+ if (arg) {
+ group = event;
+ event = arg + 1;
+ event[-1] = '\0';
+
+ if (strlen(group) == 0) {
+ pr_info("Group name is not specified\n");
+ return -EINVAL;
+ }
+ }
+ if (strlen(event) == 0) {
+ pr_info("Event name is not specified\n");
+ return -EINVAL;
+ }
+ }
+ if (!group)
+ group = UPROBE_EVENT_SYSTEM;
+
+ if (is_delete) {
+ if (!event) {
+ pr_info("Delete command needs an event name.\n");
+ return -EINVAL;
+ }
+ mutex_lock(&uprobe_lock);
+ tu = find_probe_event(event, group);
+
+ if (!tu) {
+ mutex_unlock(&uprobe_lock);
+ pr_info("Event %s/%s doesn't exist.\n", group, event);
+ return -ENOENT;
+ }
+ /* delete an event */
+ unregister_trace_uprobe(tu);
+ mutex_unlock(&uprobe_lock);
+ return 0;
+ }
+
+ if (argc < 2) {
+ pr_info("Probe point is not specified.\n");
+ return -EINVAL;
+ }
+ if (isdigit(argv[1][0])) {
+ pr_info("probe point must be have a filename.\n");
+ return -EINVAL;
+ }
+ arg = strchr(argv[1], ':');
+ if (!arg)
+ goto fail_address_parse;
+
+ *arg++ = '\0';
+ filename = argv[1];
+ ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+ if (ret)
+ goto fail_address_parse;
+
+ ret = strict_strtoul(arg, 0, &offset);
+ if (ret)
+ goto fail_address_parse;
+
+ inode = igrab(path.dentry->d_inode);
+
+ argc -= 2;
+ argv += 2;
+
+ /* setup a probe */
+ if (!event) {
+ char *tail = strrchr(filename, '/');
+ char *ptr;
+
+ ptr = kstrdup((tail ? tail + 1 : filename), GFP_KERNEL);
+ if (!ptr) {
+ ret = -ENOMEM;
+ goto fail_address_parse;
+ }
+
+ tail = ptr;
+ ptr = strpbrk(tail, ".-_");
+ if (ptr)
+ *ptr = '\0';
+
+ snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset);
+ event = buf;
+ kfree(tail);
+ }
+
+ tu = alloc_trace_uprobe(group, event, argc);
+ if (IS_ERR(tu)) {
+ pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu));
+ ret = PTR_ERR(tu);
+ goto fail_address_parse;
+ }
+ tu->offset = offset;
+ tu->inode = inode;
+ tu->filename = kstrdup(filename, GFP_KERNEL);
+
+ if (!tu->filename) {
+ pr_info("Failed to allocate filename.\n");
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ /* parse arguments */
+ ret = 0;
+ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+ /* Increment count for freeing args in error case */
+ tu->nr_args++;
+
+ /* Parse argument name */
+ arg = strchr(argv[i], '=');
+ if (arg) {
+ *arg++ = '\0';
+ tu->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+ } else {
+ arg = argv[i];
+ /* If argument name is omitted, set "argN" */
+ snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
+ tu->args[i].name = kstrdup(buf, GFP_KERNEL);
+ }
+
+ if (!tu->args[i].name) {
+ pr_info("Failed to allocate argument[%d] name.\n", i);
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ if (!is_good_name(tu->args[i].name)) {
+ pr_info("Invalid argument[%d] name: %s\n", i, tu->args[i].name);
+ ret = -EINVAL;
+ goto error;
+ }
+
+ if (traceprobe_conflict_field_name(tu->args[i].name, tu->args, i)) {
+ pr_info("Argument[%d] name '%s' conflicts with "
+ "another field.\n", i, argv[i]);
+ ret = -EINVAL;
+ goto error;
+ }
+
+ /* Parse fetch argument */
+ ret = traceprobe_parse_probe_arg(arg, &tu->size, &tu->args[i], false, false);
+ if (ret) {
+ pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
+ goto error;
+ }
+ }
+
+ ret = register_trace_uprobe(tu);
+ if (ret)
+ goto error;
+ return 0;
+
+error:
+ free_trace_uprobe(tu);
+ return ret;
+
+fail_address_parse:
+ if (inode)
+ iput(inode);
+
+ pr_info("Failed to parse address.\n");
+
+ return ret;
+}
+
+static void cleanup_all_probes(void)
+{
+ struct trace_uprobe *tu;
+
+ mutex_lock(&uprobe_lock);
+ while (!list_empty(&uprobe_list)) {
+ tu = list_entry(uprobe_list.next, struct trace_uprobe, list);
+ unregister_trace_uprobe(tu);
+ }
+ mutex_unlock(&uprobe_lock);
+}
+
+/* Probes listing interfaces */
+static void *probes_seq_start(struct seq_file *m, loff_t *pos)
+{
+ mutex_lock(&uprobe_lock);
+ return seq_list_start(&uprobe_list, *pos);
+}
+
+static void *probes_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ return seq_list_next(v, &uprobe_list, pos);
+}
+
+static void probes_seq_stop(struct seq_file *m, void *v)
+{
+ mutex_unlock(&uprobe_lock);
+}
+
+static int probes_seq_show(struct seq_file *m, void *v)
+{
+ struct trace_uprobe *tu = v;
+ int i;
+
+ seq_printf(m, "p:%s/%s", tu->call.class->system, tu->call.name);
+ seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
+
+ for (i = 0; i < tu->nr_args; i++)
+ seq_printf(m, " %s=%s", tu->args[i].name, tu->args[i].comm);
+
+ seq_printf(m, "\n");
+ return 0;
+}
+
+static const struct seq_operations probes_seq_op = {
+ .start = probes_seq_start,
+ .next = probes_seq_next,
+ .stop = probes_seq_stop,
+ .show = probes_seq_show
+};
+
+static int probes_open(struct inode *inode, struct file *file)
+{
+ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
+ cleanup_all_probes();
+
+ return seq_open(file, &probes_seq_op);
+}
+
+static ssize_t probes_write(struct file *file, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ return traceprobe_probes_write(file, buffer, count, ppos, create_trace_uprobe);
+}
+
+static const struct file_operations uprobe_events_ops = {
+ .owner = THIS_MODULE,
+ .open = probes_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+ .write = probes_write,
+};
+
+/* Probes profiling interfaces */
+static int probes_profile_seq_show(struct seq_file *m, void *v)
+{
+ struct trace_uprobe *tu = v;
+
+ seq_printf(m, " %s %-44s %15lu\n", tu->filename, tu->call.name, tu->nhit);
+ return 0;
+}
+
+static const struct seq_operations profile_seq_op = {
+ .start = probes_seq_start,
+ .next = probes_seq_next,
+ .stop = probes_seq_stop,
+ .show = probes_profile_seq_show
+};
+
+static int profile_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &profile_seq_op);
+}
+
+static const struct file_operations uprobe_profile_ops = {
+ .owner = THIS_MODULE,
+ .open = profile_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+/* uprobe handler */
+static void uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs)
+{
+ struct uprobe_trace_entry_head *entry;
+ struct ring_buffer_event *event;
+ struct ring_buffer *buffer;
+ u8 *data;
+ int size, i, pc;
+ unsigned long irq_flags;
+ struct ftrace_event_call *call = &tu->call;
+
+ tu->nhit++;
+
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
+ size = sizeof(*entry) + tu->size;
+
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
+ if (!event)
+ return;
+
+ entry = ring_buffer_event_data(event);
+ entry->ip = uprobe_get_swbp_addr(task_pt_regs(current));
+ data = (u8 *)&entry[1];
+ for (i = 0; i < tu->nr_args; i++)
+ call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+
+ if (!filter_current_check_discard(buffer, call, entry, event))
+ trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
+}
+
+/* Event entry printers */
+static enum print_line_t
+print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event)
+{
+ struct uprobe_trace_entry_head *field;
+ struct trace_seq *s = &iter->seq;
+ struct trace_uprobe *tu;
+ u8 *data;
+ int i;
+
+ field = (struct uprobe_trace_entry_head *)iter->ent;
+ tu = container_of(event, struct trace_uprobe, call.event);
+
+ if (!trace_seq_printf(s, "%s: (", tu->call.name))
+ goto partial;
+
+ if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
+ goto partial;
+
+ if (!trace_seq_puts(s, ")"))
+ goto partial;
+
+ data = (u8 *)&field[1];
+ for (i = 0; i < tu->nr_args; i++) {
+ if (!tu->args[i].type->print(s, tu->args[i].name,
+ data + tu->args[i].offset, field))
+ goto partial;
+ }
+
+ if (trace_seq_puts(s, "\n"))
+ return TRACE_TYPE_HANDLED;
+
+partial:
+ return TRACE_TYPE_PARTIAL_LINE;
+}
+
+static int probe_event_enable(struct trace_uprobe *tu, int flag)
+{
+ struct uprobe_trace_consumer *utc;
+ int ret = 0;
+
+ if (!tu->inode || tu->consumer)
+ return -EINTR;
+
+ utc = kzalloc(sizeof(struct uprobe_trace_consumer), GFP_KERNEL);
+ if (!utc)
+ return -EINTR;
+
+ utc->cons.handler = uprobe_dispatcher;
+ utc->cons.filter = NULL;
+ ret = uprobe_register(tu->inode, tu->offset, &utc->cons);
+ if (ret) {
+ kfree(utc);
+ return ret;
+ }
+
+ tu->flags |= flag;
+ utc->tu = tu;
+ tu->consumer = utc;
+
+ return 0;
+}
+
+static void probe_event_disable(struct trace_uprobe *tu, int flag)
+{
+ if (!tu->inode || !tu->consumer)
+ return;
+
+ uprobe_unregister(tu->inode, tu->offset, &tu->consumer->cons);
+ tu->flags &= ~flag;
+ kfree(tu->consumer);
+ tu->consumer = NULL;
+}
+
+static int uprobe_event_define_fields(struct ftrace_event_call *event_call)
+{
+ int ret, i;
+ struct uprobe_trace_entry_head field;
+ struct trace_uprobe *tu = (struct trace_uprobe *)event_call->data;
+
+ DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+ /* Set argument names as fields */
+ for (i = 0; i < tu->nr_args; i++) {
+ ret = trace_define_field(event_call, tu->args[i].type->fmttype,
+ tu->args[i].name,
+ sizeof(field) + tu->args[i].offset,
+ tu->args[i].type->size,
+ tu->args[i].type->is_signed,
+ FILTER_OTHER);
+
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+#define LEN_OR_ZERO (len ? len - pos : 0)
+static int __set_print_fmt(struct trace_uprobe *tu, char *buf, int len)
+{
+ const char *fmt, *arg;
+ int i;
+ int pos = 0;
+
+ fmt = "(%lx)";
+ arg = "REC->" FIELD_STRING_IP;
+
+ /* When len=0, we just calculate the needed length */
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
+
+ for (i = 0; i < tu->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%s",
+ tu->args[i].name, tu->args[i].type->fmt);
+ }
+
+ pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
+
+ for (i = 0; i < tu->nr_args; i++) {
+ pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+ tu->args[i].name);
+ }
+
+ return pos; /* return the length of print_fmt */
+}
+#undef LEN_OR_ZERO
+
+static int set_print_fmt(struct trace_uprobe *tu)
+{
+ char *print_fmt;
+ int len;
+
+ /* First: called with 0 length to calculate the needed length */
+ len = __set_print_fmt(tu, NULL, 0);
+ print_fmt = kmalloc(len + 1, GFP_KERNEL);
+ if (!print_fmt)
+ return -ENOMEM;
+
+ /* Second: actually write the @print_fmt */
+ __set_print_fmt(tu, print_fmt, len + 1);
+ tu->call.print_fmt = print_fmt;
+
+ return 0;
+}
+
+#ifdef CONFIG_PERF_EVENTS
+/* uprobe profile handler */
+static void uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs)
+{
+ struct ftrace_event_call *call = &tu->call;
+ struct uprobe_trace_entry_head *entry;
+ struct hlist_head *head;
+ u8 *data;
+ int size, __size, i;
+ int rctx;
+
+ __size = sizeof(*entry) + tu->size;
+ size = ALIGN(__size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+ if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough"))
+ return;
+
+ preempt_disable();
+
+ entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+ if (!entry)
+ goto out;
+
+ entry->ip = uprobe_get_swbp_addr(task_pt_regs(current));
+ data = (u8 *)&entry[1];
+ for (i = 0; i < tu->nr_args; i++)
+ call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset);
+
+ head = this_cpu_ptr(call->perf_events);
+ perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
+
+ out:
+ preempt_enable();
+}
+#endif /* CONFIG_PERF_EVENTS */
+
+static
+int trace_uprobe_register(struct ftrace_event_call *event, enum trace_reg type, void *data)
+{
+ struct trace_uprobe *tu = (struct trace_uprobe *)event->data;
+
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return probe_event_enable(tu, TP_FLAG_TRACE);
+
+ case TRACE_REG_UNREGISTER:
+ probe_event_disable(tu, TP_FLAG_TRACE);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return probe_event_enable(tu, TP_FLAG_PROFILE);
+
+ case TRACE_REG_PERF_UNREGISTER:
+ probe_event_disable(tu, TP_FLAG_PROFILE);
+ return 0;
+#endif
+ default:
+ return 0;
+ }
+ return 0;
+}
+
+static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
+{
+ struct uprobe_trace_consumer *utc;
+ struct trace_uprobe *tu;
+
+ utc = container_of(con, struct uprobe_trace_consumer, cons);
+ tu = utc->tu;
+ if (!tu || tu->consumer != utc)
+ return 0;
+
+ if (tu->flags & TP_FLAG_TRACE)
+ uprobe_trace_func(tu, regs);
+
+#ifdef CONFIG_PERF_EVENTS
+ if (tu->flags & TP_FLAG_PROFILE)
+ uprobe_perf_func(tu, regs);
+#endif
+ return 0;
+}
+
+static struct trace_event_functions uprobe_funcs = {
+ .trace = print_uprobe_event
+};
+
+static int register_uprobe_event(struct trace_uprobe *tu)
+{
+ struct ftrace_event_call *call = &tu->call;
+ int ret;
+
+ /* Initialize ftrace_event_call */
+ INIT_LIST_HEAD(&call->class->fields);
+ call->event.funcs = &uprobe_funcs;
+ call->class->define_fields = uprobe_event_define_fields;
+
+ if (set_print_fmt(tu) < 0)
+ return -ENOMEM;
+
+ ret = register_ftrace_event(&call->event);
+ if (!ret) {
+ kfree(call->print_fmt);
+ return -ENODEV;
+ }
+ call->flags = 0;
+ call->class->reg = trace_uprobe_register;
+ call->data = tu;
+ ret = trace_add_event_call(call);
+
+ if (ret) {
+ pr_info("Failed to register uprobe event: %s\n", call->name);
+ kfree(call->print_fmt);
+ unregister_ftrace_event(&call->event);
+ }
+
+ return ret;
+}
+
+static void unregister_uprobe_event(struct trace_uprobe *tu)
+{
+ /* tu->event is unregistered in trace_remove_event_call() */
+ trace_remove_event_call(&tu->call);
+ kfree(tu->call.print_fmt);
+ tu->call.print_fmt = NULL;
+}
+
+/* Make a trace interface for controling probe points */
+static __init int init_uprobe_trace(void)
+{
+ struct dentry *d_tracer;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ trace_create_file("uprobe_events", 0644, d_tracer,
+ NULL, &uprobe_events_ops);
+ /* Profile interface */
+ trace_create_file("uprobe_profile", 0444, d_tracer,
+ NULL, &uprobe_profile_ops);
+ return 0;
+}
+
+fs_initcall(init_uprobe_trace);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 51c6e89e8619..d7948eb10225 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -81,14 +81,19 @@ SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid)
return ret;
}
-SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruid, old_uid_t __user *, euid, old_uid_t __user *, suid)
+SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruidp, old_uid_t __user *, euidp, old_uid_t __user *, suidp)
{
const struct cred *cred = current_cred();
int retval;
+ old_uid_t ruid, euid, suid;
- if (!(retval = put_user(high2lowuid(cred->uid), ruid)) &&
- !(retval = put_user(high2lowuid(cred->euid), euid)))
- retval = put_user(high2lowuid(cred->suid), suid);
+ ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid));
+ euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid));
+ suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid));
+
+ if (!(retval = put_user(ruid, ruidp)) &&
+ !(retval = put_user(euid, euidp)))
+ retval = put_user(suid, suidp);
return retval;
}
@@ -103,14 +108,19 @@ SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid)
}
-SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgid, old_gid_t __user *, egid, old_gid_t __user *, sgid)
+SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgidp, old_gid_t __user *, egidp, old_gid_t __user *, sgidp)
{
const struct cred *cred = current_cred();
int retval;
+ old_gid_t rgid, egid, sgid;
+
+ rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid));
+ egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid));
+ sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid));
- if (!(retval = put_user(high2lowgid(cred->gid), rgid)) &&
- !(retval = put_user(high2lowgid(cred->egid), egid)))
- retval = put_user(high2lowgid(cred->sgid), sgid);
+ if (!(retval = put_user(rgid, rgidp)) &&
+ !(retval = put_user(egid, egidp)))
+ retval = put_user(sgid, sgidp);
return retval;
}
@@ -134,11 +144,14 @@ SYSCALL_DEFINE1(setfsgid16, old_gid_t, gid)
static int groups16_to_user(old_gid_t __user *grouplist,
struct group_info *group_info)
{
+ struct user_namespace *user_ns = current_user_ns();
int i;
old_gid_t group;
+ kgid_t kgid;
for (i = 0; i < group_info->ngroups; i++) {
- group = high2lowgid(GROUP_AT(group_info, i));
+ kgid = GROUP_AT(group_info, i);
+ group = high2lowgid(from_kgid_munged(user_ns, kgid));
if (put_user(group, grouplist+i))
return -EFAULT;
}
@@ -149,13 +162,20 @@ static int groups16_to_user(old_gid_t __user *grouplist,
static int groups16_from_user(struct group_info *group_info,
old_gid_t __user *grouplist)
{
+ struct user_namespace *user_ns = current_user_ns();
int i;
old_gid_t group;
+ kgid_t kgid;
for (i = 0; i < group_info->ngroups; i++) {
if (get_user(group, grouplist+i))
return -EFAULT;
- GROUP_AT(group_info, i) = low2highgid(group);
+
+ kgid = make_kgid(user_ns, low2highgid(group));
+ if (!gid_valid(kgid))
+ return -EINVAL;
+
+ GROUP_AT(group_info, i) = kgid;
}
return 0;
@@ -211,20 +231,20 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
SYSCALL_DEFINE0(getuid16)
{
- return high2lowuid(current_uid());
+ return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
}
SYSCALL_DEFINE0(geteuid16)
{
- return high2lowuid(current_euid());
+ return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
}
SYSCALL_DEFINE0(getgid16)
{
- return high2lowgid(current_gid());
+ return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
}
SYSCALL_DEFINE0(getegid16)
{
- return high2lowgid(current_egid());
+ return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
}
diff --git a/kernel/user.c b/kernel/user.c
index 71dd2363ab0f..b815fefbe76f 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -22,10 +22,27 @@
* and 1 for... ?
*/
struct user_namespace init_user_ns = {
+ .uid_map = {
+ .nr_extents = 1,
+ .extent[0] = {
+ .first = 0,
+ .lower_first = 0,
+ .count = 4294967295U,
+ },
+ },
+ .gid_map = {
+ .nr_extents = 1,
+ .extent[0] = {
+ .first = 0,
+ .lower_first = 0,
+ .count = 4294967295U,
+ },
+ },
.kref = {
.refcount = ATOMIC_INIT(3),
},
- .creator = &root_user,
+ .owner = GLOBAL_ROOT_UID,
+ .group = GLOBAL_ROOT_GID,
};
EXPORT_SYMBOL_GPL(init_user_ns);
@@ -34,11 +51,14 @@ EXPORT_SYMBOL_GPL(init_user_ns);
* when changing user ID's (ie setuid() and friends).
*/
+#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7)
+#define UIDHASH_SZ (1 << UIDHASH_BITS)
#define UIDHASH_MASK (UIDHASH_SZ - 1)
#define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
-#define uidhashentry(ns, uid) ((ns)->uidhash_table + __uidhashfn((uid)))
+#define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid))))
static struct kmem_cache *uid_cachep;
+struct hlist_head uidhash_table[UIDHASH_SZ];
/*
* The uidhash_lock is mostly taken from process context, but it is
@@ -51,14 +71,14 @@ static struct kmem_cache *uid_cachep;
*/
static DEFINE_SPINLOCK(uidhash_lock);
-/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->user_ns */
+/* root_user.__count is 1, for init task cred */
struct user_struct root_user = {
- .__count = ATOMIC_INIT(2),
+ .__count = ATOMIC_INIT(1),
.processes = ATOMIC_INIT(1),
.files = ATOMIC_INIT(0),
.sigpending = ATOMIC_INIT(0),
.locked_shm = 0,
- .user_ns = &init_user_ns,
+ .uid = GLOBAL_ROOT_UID,
};
/*
@@ -72,16 +92,15 @@ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
static void uid_hash_remove(struct user_struct *up)
{
hlist_del_init(&up->uidhash_node);
- put_user_ns(up->user_ns);
}
-static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
+static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
{
struct user_struct *user;
struct hlist_node *h;
hlist_for_each_entry(user, h, hashent, uidhash_node) {
- if (user->uid == uid) {
+ if (uid_eq(user->uid, uid)) {
atomic_inc(&user->__count);
return user;
}
@@ -110,14 +129,13 @@ static void free_user(struct user_struct *up, unsigned long flags)
*
* If the user_struct could not be found, return NULL.
*/
-struct user_struct *find_user(uid_t uid)
+struct user_struct *find_user(kuid_t uid)
{
struct user_struct *ret;
unsigned long flags;
- struct user_namespace *ns = current_user_ns();
spin_lock_irqsave(&uidhash_lock, flags);
- ret = uid_hash_find(uid, uidhashentry(ns, uid));
+ ret = uid_hash_find(uid, uidhashentry(uid));
spin_unlock_irqrestore(&uidhash_lock, flags);
return ret;
}
@@ -136,9 +154,9 @@ void free_uid(struct user_struct *up)
local_irq_restore(flags);
}
-struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
+struct user_struct *alloc_uid(kuid_t uid)
{
- struct hlist_head *hashent = uidhashentry(ns, uid);
+ struct hlist_head *hashent = uidhashentry(uid);
struct user_struct *up, *new;
spin_lock_irq(&uidhash_lock);
@@ -153,8 +171,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
new->uid = uid;
atomic_set(&new->__count, 1);
- new->user_ns = get_user_ns(ns);
-
/*
* Before adding this, check whether we raced
* on adding the same user already..
@@ -162,7 +178,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
if (up) {
- put_user_ns(ns);
key_put(new->uid_keyring);
key_put(new->session_keyring);
kmem_cache_free(uid_cachep, new);
@@ -187,11 +202,11 @@ static int __init uid_cache_init(void)
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
for(n = 0; n < UIDHASH_SZ; ++n)
- INIT_HLIST_HEAD(init_user_ns.uidhash_table + n);
+ INIT_HLIST_HEAD(uidhash_table + n);
/* Insert the root user immediately (init already runs as root) */
spin_lock_irq(&uidhash_lock);
- uid_hash_insert(&root_user, uidhashentry(&init_user_ns, 0));
+ uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
spin_unlock_irq(&uidhash_lock);
return 0;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 3b906e98b1db..86602316422d 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -11,9 +11,20 @@
#include <linux/user_namespace.h>
#include <linux/highuid.h>
#include <linux/cred.h>
+#include <linux/securebits.h>
+#include <linux/keyctl.h>
+#include <linux/key-type.h>
+#include <keys/user-type.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/ctype.h>
static struct kmem_cache *user_ns_cachep __read_mostly;
+static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+ struct uid_gid_map *map);
+
/*
* Create a new user namespace, deriving the creator from the user in the
* passed credentials, and replacing that user with the new root user for the
@@ -24,109 +35,565 @@ static struct kmem_cache *user_ns_cachep __read_mostly;
*/
int create_user_ns(struct cred *new)
{
- struct user_namespace *ns;
- struct user_struct *root_user;
- int n;
+ struct user_namespace *ns, *parent_ns = new->user_ns;
+ kuid_t owner = new->euid;
+ kgid_t group = new->egid;
+
+ /* The creator needs a mapping in the parent user namespace
+ * or else we won't be able to reasonably tell userspace who
+ * created a user_namespace.
+ */
+ if (!kuid_has_mapping(parent_ns, owner) ||
+ !kgid_has_mapping(parent_ns, group))
+ return -EPERM;
- ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL);
+ ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL);
if (!ns)
return -ENOMEM;
kref_init(&ns->kref);
+ ns->parent = parent_ns;
+ ns->owner = owner;
+ ns->group = group;
- for (n = 0; n < UIDHASH_SZ; ++n)
- INIT_HLIST_HEAD(ns->uidhash_table + n);
-
- /* Alloc new root user. */
- root_user = alloc_uid(ns, 0);
- if (!root_user) {
- kmem_cache_free(user_ns_cachep, ns);
- return -ENOMEM;
- }
-
- /* set the new root user in the credentials under preparation */
- ns->creator = new->user;
- new->user = root_user;
- new->uid = new->euid = new->suid = new->fsuid = 0;
- new->gid = new->egid = new->sgid = new->fsgid = 0;
- put_group_info(new->group_info);
- new->group_info = get_group_info(&init_groups);
+ /* Start with the same capabilities as init but useless for doing
+ * anything as the capabilities are bound to the new user namespace.
+ */
+ new->securebits = SECUREBITS_DEFAULT;
+ new->cap_inheritable = CAP_EMPTY_SET;
+ new->cap_permitted = CAP_FULL_SET;
+ new->cap_effective = CAP_FULL_SET;
+ new->cap_bset = CAP_FULL_SET;
#ifdef CONFIG_KEYS
key_put(new->request_key_auth);
new->request_key_auth = NULL;
#endif
/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
- /* root_user holds a reference to ns, our reference can be dropped */
- put_user_ns(ns);
+ /* Leave the new->user_ns reference with the new user namespace. */
+ /* Leave the reference to our user_ns with the new cred. */
+ new->user_ns = ns;
return 0;
}
-/*
- * Deferred destructor for a user namespace. This is required because
- * free_user_ns() may be called with uidhash_lock held, but we need to call
- * back to free_uid() which will want to take the lock again.
- */
-static void free_user_ns_work(struct work_struct *work)
+void free_user_ns(struct kref *kref)
{
- struct user_namespace *ns =
- container_of(work, struct user_namespace, destroyer);
- free_uid(ns->creator);
+ struct user_namespace *parent, *ns =
+ container_of(kref, struct user_namespace, kref);
+
+ parent = ns->parent;
kmem_cache_free(user_ns_cachep, ns);
+ put_user_ns(parent);
}
+EXPORT_SYMBOL(free_user_ns);
-void free_user_ns(struct kref *kref)
+static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
{
- struct user_namespace *ns =
- container_of(kref, struct user_namespace, kref);
+ unsigned idx, extents;
+ u32 first, last, id2;
+
+ id2 = id + count - 1;
+
+ /* Find the matching extent */
+ extents = map->nr_extents;
+ smp_read_barrier_depends();
+ for (idx = 0; idx < extents; idx++) {
+ first = map->extent[idx].first;
+ last = first + map->extent[idx].count - 1;
+ if (id >= first && id <= last &&
+ (id2 >= first && id2 <= last))
+ break;
+ }
+ /* Map the id or note failure */
+ if (idx < extents)
+ id = (id - first) + map->extent[idx].lower_first;
+ else
+ id = (u32) -1;
- INIT_WORK(&ns->destroyer, free_user_ns_work);
- schedule_work(&ns->destroyer);
+ return id;
}
-EXPORT_SYMBOL(free_user_ns);
-uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid)
+static u32 map_id_down(struct uid_gid_map *map, u32 id)
{
- struct user_namespace *tmp;
+ unsigned idx, extents;
+ u32 first, last;
- if (likely(to == cred->user->user_ns))
- return uid;
+ /* Find the matching extent */
+ extents = map->nr_extents;
+ smp_read_barrier_depends();
+ for (idx = 0; idx < extents; idx++) {
+ first = map->extent[idx].first;
+ last = first + map->extent[idx].count - 1;
+ if (id >= first && id <= last)
+ break;
+ }
+ /* Map the id or note failure */
+ if (idx < extents)
+ id = (id - first) + map->extent[idx].lower_first;
+ else
+ id = (u32) -1;
+ return id;
+}
- /* Is cred->user the creator of the target user_ns
- * or the creator of one of it's parents?
- */
- for ( tmp = to; tmp != &init_user_ns;
- tmp = tmp->creator->user_ns ) {
- if (cred->user == tmp->creator) {
- return (uid_t)0;
- }
+static u32 map_id_up(struct uid_gid_map *map, u32 id)
+{
+ unsigned idx, extents;
+ u32 first, last;
+
+ /* Find the matching extent */
+ extents = map->nr_extents;
+ smp_read_barrier_depends();
+ for (idx = 0; idx < extents; idx++) {
+ first = map->extent[idx].lower_first;
+ last = first + map->extent[idx].count - 1;
+ if (id >= first && id <= last)
+ break;
}
+ /* Map the id or note failure */
+ if (idx < extents)
+ id = (id - first) + map->extent[idx].first;
+ else
+ id = (u32) -1;
+
+ return id;
+}
+
+/**
+ * make_kuid - Map a user-namespace uid pair into a kuid.
+ * @ns: User namespace that the uid is in
+ * @uid: User identifier
+ *
+ * Maps a user-namespace uid pair into a kernel internal kuid,
+ * and returns that kuid.
+ *
+ * When there is no mapping defined for the user-namespace uid
+ * pair INVALID_UID is returned. Callers are expected to test
+ * for and handle handle INVALID_UID being returned. INVALID_UID
+ * may be tested for using uid_valid().
+ */
+kuid_t make_kuid(struct user_namespace *ns, uid_t uid)
+{
+ /* Map the uid to a global kernel uid */
+ return KUIDT_INIT(map_id_down(&ns->uid_map, uid));
+}
+EXPORT_SYMBOL(make_kuid);
+
+/**
+ * from_kuid - Create a uid from a kuid user-namespace pair.
+ * @targ: The user namespace we want a uid in.
+ * @kuid: The kernel internal uid to start with.
+ *
+ * Map @kuid into the user-namespace specified by @targ and
+ * return the resulting uid.
+ *
+ * There is always a mapping into the initial user_namespace.
+ *
+ * If @kuid has no mapping in @targ (uid_t)-1 is returned.
+ */
+uid_t from_kuid(struct user_namespace *targ, kuid_t kuid)
+{
+ /* Map the uid from a global kernel uid */
+ return map_id_up(&targ->uid_map, __kuid_val(kuid));
+}
+EXPORT_SYMBOL(from_kuid);
- /* No useful relationship so no mapping */
- return overflowuid;
+/**
+ * from_kuid_munged - Create a uid from a kuid user-namespace pair.
+ * @targ: The user namespace we want a uid in.
+ * @kuid: The kernel internal uid to start with.
+ *
+ * Map @kuid into the user-namespace specified by @targ and
+ * return the resulting uid.
+ *
+ * There is always a mapping into the initial user_namespace.
+ *
+ * Unlike from_kuid from_kuid_munged never fails and always
+ * returns a valid uid. This makes from_kuid_munged appropriate
+ * for use in syscalls like stat and getuid where failing the
+ * system call and failing to provide a valid uid are not an
+ * options.
+ *
+ * If @kuid has no mapping in @targ overflowuid is returned.
+ */
+uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid)
+{
+ uid_t uid;
+ uid = from_kuid(targ, kuid);
+
+ if (uid == (uid_t) -1)
+ uid = overflowuid;
+ return uid;
}
+EXPORT_SYMBOL(from_kuid_munged);
-gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid)
+/**
+ * make_kgid - Map a user-namespace gid pair into a kgid.
+ * @ns: User namespace that the gid is in
+ * @uid: group identifier
+ *
+ * Maps a user-namespace gid pair into a kernel internal kgid,
+ * and returns that kgid.
+ *
+ * When there is no mapping defined for the user-namespace gid
+ * pair INVALID_GID is returned. Callers are expected to test
+ * for and handle INVALID_GID being returned. INVALID_GID may be
+ * tested for using gid_valid().
+ */
+kgid_t make_kgid(struct user_namespace *ns, gid_t gid)
{
- struct user_namespace *tmp;
+ /* Map the gid to a global kernel gid */
+ return KGIDT_INIT(map_id_down(&ns->gid_map, gid));
+}
+EXPORT_SYMBOL(make_kgid);
- if (likely(to == cred->user->user_ns))
- return gid;
+/**
+ * from_kgid - Create a gid from a kgid user-namespace pair.
+ * @targ: The user namespace we want a gid in.
+ * @kgid: The kernel internal gid to start with.
+ *
+ * Map @kgid into the user-namespace specified by @targ and
+ * return the resulting gid.
+ *
+ * There is always a mapping into the initial user_namespace.
+ *
+ * If @kgid has no mapping in @targ (gid_t)-1 is returned.
+ */
+gid_t from_kgid(struct user_namespace *targ, kgid_t kgid)
+{
+ /* Map the gid from a global kernel gid */
+ return map_id_up(&targ->gid_map, __kgid_val(kgid));
+}
+EXPORT_SYMBOL(from_kgid);
+
+/**
+ * from_kgid_munged - Create a gid from a kgid user-namespace pair.
+ * @targ: The user namespace we want a gid in.
+ * @kgid: The kernel internal gid to start with.
+ *
+ * Map @kgid into the user-namespace specified by @targ and
+ * return the resulting gid.
+ *
+ * There is always a mapping into the initial user_namespace.
+ *
+ * Unlike from_kgid from_kgid_munged never fails and always
+ * returns a valid gid. This makes from_kgid_munged appropriate
+ * for use in syscalls like stat and getgid where failing the
+ * system call and failing to provide a valid gid are not options.
+ *
+ * If @kgid has no mapping in @targ overflowgid is returned.
+ */
+gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid)
+{
+ gid_t gid;
+ gid = from_kgid(targ, kgid);
- /* Is cred->user the creator of the target user_ns
- * or the creator of one of it's parents?
+ if (gid == (gid_t) -1)
+ gid = overflowgid;
+ return gid;
+}
+EXPORT_SYMBOL(from_kgid_munged);
+
+static int uid_m_show(struct seq_file *seq, void *v)
+{
+ struct user_namespace *ns = seq->private;
+ struct uid_gid_extent *extent = v;
+ struct user_namespace *lower_ns;
+ uid_t lower;
+
+ lower_ns = current_user_ns();
+ if ((lower_ns == ns) && lower_ns->parent)
+ lower_ns = lower_ns->parent;
+
+ lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first));
+
+ seq_printf(seq, "%10u %10u %10u\n",
+ extent->first,
+ lower,
+ extent->count);
+
+ return 0;
+}
+
+static int gid_m_show(struct seq_file *seq, void *v)
+{
+ struct user_namespace *ns = seq->private;
+ struct uid_gid_extent *extent = v;
+ struct user_namespace *lower_ns;
+ gid_t lower;
+
+ lower_ns = current_user_ns();
+ if ((lower_ns == ns) && lower_ns->parent)
+ lower_ns = lower_ns->parent;
+
+ lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first));
+
+ seq_printf(seq, "%10u %10u %10u\n",
+ extent->first,
+ lower,
+ extent->count);
+
+ return 0;
+}
+
+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;
+
+ if (pos < map->nr_extents)
+ extent = &map->extent[pos];
+
+ return extent;
+}
+
+static void *uid_m_start(struct seq_file *seq, loff_t *ppos)
+{
+ struct user_namespace *ns = seq->private;
+
+ return m_start(seq, ppos, &ns->uid_map);
+}
+
+static void *gid_m_start(struct seq_file *seq, loff_t *ppos)
+{
+ struct user_namespace *ns = seq->private;
+
+ return m_start(seq, ppos, &ns->gid_map);
+}
+
+static void *m_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return seq->op->start(seq, pos);
+}
+
+static void m_stop(struct seq_file *seq, void *v)
+{
+ return;
+}
+
+struct seq_operations proc_uid_seq_operations = {
+ .start = uid_m_start,
+ .stop = m_stop,
+ .next = m_next,
+ .show = uid_m_show,
+};
+
+struct seq_operations proc_gid_seq_operations = {
+ .start = gid_m_start,
+ .stop = m_stop,
+ .next = m_next,
+ .show = gid_m_show,
+};
+
+static DEFINE_MUTEX(id_map_mutex);
+
+static ssize_t map_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos,
+ int cap_setid,
+ struct uid_gid_map *map,
+ struct uid_gid_map *parent_map)
+{
+ struct seq_file *seq = file->private_data;
+ struct user_namespace *ns = seq->private;
+ struct uid_gid_map new_map;
+ unsigned idx;
+ struct uid_gid_extent *extent, *last = NULL;
+ unsigned long page = 0;
+ char *kbuf, *pos, *next_line;
+ ssize_t ret = -EINVAL;
+
+ /*
+ * The id_map_mutex serializes all writes to any given map.
+ *
+ * Any map is only ever written once.
+ *
+ * An id map fits within 1 cache line on most architectures.
+ *
+ * On read nothing needs to be done unless you are on an
+ * architecture with a crazy cache coherency model like alpha.
+ *
+ * There is a one time data dependency between reading the
+ * count of the extents and the values of the extents. The
+ * desired behavior is to see the values of the extents that
+ * were written before the count of the extents.
+ *
+ * To achieve this smp_wmb() is used on guarantee the write
+ * order and smp_read_barrier_depends() is guaranteed that we
+ * don't have crazy architectures returning stale data.
+ *
*/
- for ( tmp = to; tmp != &init_user_ns;
- tmp = tmp->creator->user_ns ) {
- if (cred->user == tmp->creator) {
- return (gid_t)0;
+ mutex_lock(&id_map_mutex);
+
+ ret = -EPERM;
+ /* Only allow one successful write to the map */
+ if (map->nr_extents != 0)
+ goto out;
+
+ /* Require the appropriate privilege CAP_SETUID or CAP_SETGID
+ * over the user namespace in order to set the id mapping.
+ */
+ if (!ns_capable(ns, cap_setid))
+ goto out;
+
+ /* Get a buffer */
+ ret = -ENOMEM;
+ page = __get_free_page(GFP_TEMPORARY);
+ kbuf = (char *) page;
+ if (!page)
+ goto out;
+
+ /* Only allow <= page size writes at the beginning of the file */
+ ret = -EINVAL;
+ if ((*ppos != 0) || (count >= PAGE_SIZE))
+ goto out;
+
+ /* Slurp in the user data */
+ ret = -EFAULT;
+ if (copy_from_user(kbuf, buf, count))
+ goto out;
+ kbuf[count] = '\0';
+
+ /* Parse the user data */
+ ret = -EINVAL;
+ pos = kbuf;
+ new_map.nr_extents = 0;
+ 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 */
+ next_line = strchr(pos, '\n');
+ if (next_line) {
+ *next_line = '\0';
+ next_line++;
+ if (*next_line == '\0')
+ next_line = NULL;
}
+
+ pos = skip_spaces(pos);
+ extent->first = simple_strtoul(pos, &pos, 10);
+ if (!isspace(*pos))
+ goto out;
+
+ pos = skip_spaces(pos);
+ extent->lower_first = simple_strtoul(pos, &pos, 10);
+ if (!isspace(*pos))
+ goto out;
+
+ pos = skip_spaces(pos);
+ extent->count = simple_strtoul(pos, &pos, 10);
+ if (*pos && !isspace(*pos))
+ goto out;
+
+ /* Verify there is not trailing junk on the line */
+ pos = skip_spaces(pos);
+ if (*pos != '\0')
+ goto out;
+
+ /* Verify we have been given valid starting values */
+ if ((extent->first == (u32) -1) ||
+ (extent->lower_first == (u32) -1 ))
+ goto out;
+
+ /* 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)
+ goto out;
+
+ /* For now only accept extents that are strictly in order */
+ if (last &&
+ (((last->first + last->count) > extent->first) ||
+ ((last->lower_first + last->count) > extent->lower_first)))
+ goto out;
+
+ new_map.nr_extents++;
+ last = extent;
+
+ /* Fail if the file contains too many extents */
+ if ((new_map.nr_extents == UID_GID_MAP_MAX_EXTENTS) &&
+ (next_line != NULL))
+ goto out;
+ }
+ /* Be very certaint the new map actually exists */
+ if (new_map.nr_extents == 0)
+ goto out;
+
+ ret = -EPERM;
+ /* Validate the user is allowed to use user id's mapped to. */
+ if (!new_idmap_permitted(ns, cap_setid, &new_map))
+ goto out;
+
+ /* Map the lower ids from the parent user namespace to the
+ * kernel global id space.
+ */
+ for (idx = 0; idx < new_map.nr_extents; idx++) {
+ u32 lower_first;
+ extent = &new_map.extent[idx];
+
+ lower_first = map_id_range_down(parent_map,
+ extent->lower_first,
+ extent->count);
+
+ /* Fail if we can not map the specified extent to
+ * the kernel global id space.
+ */
+ if (lower_first == (u32) -1)
+ goto out;
+
+ extent->lower_first = lower_first;
}
- /* No useful relationship so no mapping */
- return overflowgid;
+ /* Install the map */
+ memcpy(map->extent, new_map.extent,
+ new_map.nr_extents*sizeof(new_map.extent[0]));
+ smp_wmb();
+ map->nr_extents = new_map.nr_extents;
+
+ *ppos = count;
+ ret = count;
+out:
+ mutex_unlock(&id_map_mutex);
+ if (page)
+ free_page(page);
+ return ret;
+}
+
+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;
+
+ if (!ns->parent)
+ return -EPERM;
+
+ return map_write(file, buf, size, ppos, CAP_SETUID,
+ &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)
+{
+ struct seq_file *seq = file->private_data;
+ struct user_namespace *ns = seq->private;
+
+ if (!ns->parent)
+ return -EPERM;
+
+ return map_write(file, buf, size, ppos, CAP_SETGID,
+ &ns->gid_map, &ns->parent->gid_map);
+}
+
+static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid,
+ struct uid_gid_map *new_map)
+{
+ /* Allow the specified ids if we have the appropriate capability
+ * (CAP_SETUID or CAP_SETGID) over the parent user namespace.
+ */
+ if (ns_capable(ns->parent, cap_setid))
+ return true;
+
+ return false;
}
static __init int user_namespaces_init(void)
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 405caf91aad5..679d97a5d3fd 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -43,7 +43,7 @@ static struct uts_namespace *clone_uts_ns(struct task_struct *tsk,
down_read(&uts_sem);
memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
- ns->user_ns = get_user_ns(task_cred_xxx(tsk, user)->user_ns);
+ ns->user_ns = get_user_ns(task_cred_xxx(tsk, user_ns));
up_read(&uts_sem);
return ns;
}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index df30ee08bdd4..4b1dfba70f7c 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -24,6 +24,7 @@
#include <linux/sysctl.h>
#include <asm/irq_regs.h>
+#include <linux/kvm_para.h>
#include <linux/perf_event.h>
int watchdog_enabled = 1;
@@ -280,6 +281,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
__this_cpu_write(softlockup_touch_sync, false);
sched_clock_tick();
}
+
+ /* Clear the guest paused flag on watchdog reset */
+ kvm_check_and_clear_guest_paused();
__touch_watchdog();
return HRTIMER_RESTART;
}
@@ -292,6 +296,14 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
*/
duration = is_softlockup(touch_ts);
if (unlikely(duration)) {
+ /*
+ * If a virtual machine is stopped by the host it can look to
+ * the watchdog like a soft lockup, check to see if the host
+ * stopped the vm before we issue the warning
+ */
+ if (kvm_check_and_clear_guest_paused())
+ return HRTIMER_RESTART;
+
/* only warn once */
if (__this_cpu_read(soft_watchdog_warn) == true)
return HRTIMER_RESTART;
@@ -360,6 +372,13 @@ static int watchdog(void *unused)
#ifdef CONFIG_HARDLOCKUP_DETECTOR
+/*
+ * People like the simple clean cpu node info on boot.
+ * Reduce the watchdog noise by only printing messages
+ * that are different from what cpu0 displayed.
+ */
+static unsigned long cpu0_err;
+
static int watchdog_nmi_enable(int cpu)
{
struct perf_event_attr *wd_attr;
@@ -378,11 +397,21 @@ static int watchdog_nmi_enable(int cpu)
/* Try to register using hardware perf events */
event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
+
+ /* save cpu0 error for future comparision */
+ if (cpu == 0 && IS_ERR(event))
+ cpu0_err = PTR_ERR(event);
+
if (!IS_ERR(event)) {
- pr_info("enabled, takes one hw-pmu counter.\n");
+ /* only print for cpu0 or different than cpu0 */
+ if (cpu == 0 || cpu0_err)
+ pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
goto out_save;
}
+ /* skip displaying the same error again */
+ if (cpu > 0 && (PTR_ERR(event) == cpu0_err))
+ return PTR_ERR(event);
/* vary the KERN level based on the returned errno */
if (PTR_ERR(event) == -EOPNOTSUPP)