aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorRusty Russell <rusty@rustcorp.com.au>2008-12-30 08:02:35 +1030
committerRusty Russell <rusty@rustcorp.com.au>2008-12-30 08:02:35 +1030
commit33edcf133ba93ecba2e4b6472e97b689895d805c (patch)
tree327d7a20acef64005e7c5ccbfa1265be28aeb6ac /kernel
parentbe4d638c1597580ed2294d899d9f1a2cd10e462c (diff)
parent3c92ec8ae91ecf59d88c798301833d7cf83f2179 (diff)
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile5
-rw-r--r--kernel/acct.c7
-rw-r--r--kernel/auditsc.c255
-rw-r--r--kernel/capability.c288
-rw-r--r--kernel/cgroup.c27
-rw-r--r--kernel/cred-internals.h21
-rw-r--r--kernel/cred.c588
-rw-r--r--kernel/delayacct.c2
-rw-r--r--kernel/exit.c28
-rw-r--r--kernel/extable.c5
-rw-r--r--kernel/fork.c76
-rw-r--r--kernel/futex.c20
-rw-r--r--kernel/futex_compat.c7
-rw-r--r--kernel/kallsyms.c16
-rw-r--r--kernel/kmod.c30
-rw-r--r--kernel/kthread.c3
-rw-r--r--kernel/lockdep.c1
-rw-r--r--kernel/marker.c192
-rw-r--r--kernel/module.c13
-rw-r--r--kernel/nsproxy.c15
-rw-r--r--kernel/posix-timers.c6
-rw-r--r--kernel/power/disk.c13
-rw-r--r--kernel/power/main.c5
-rw-r--r--kernel/profile.c2
-rw-r--r--kernel/ptrace.c41
-rw-r--r--kernel/sched.c407
-rw-r--r--kernel/sched_clock.c6
-rw-r--r--kernel/sched_debug.c57
-rw-r--r--kernel/sched_fair.c9
-rw-r--r--kernel/sched_rt.c9
-rw-r--r--kernel/sched_stats.h5
-rw-r--r--kernel/signal.c62
-rw-r--r--kernel/sys.c586
-rw-r--r--kernel/sysctl.c22
-rw-r--r--kernel/timer.c8
-rw-r--r--kernel/trace/Kconfig115
-rw-r--r--kernel/trace/Makefile9
-rw-r--r--kernel/trace/ftrace.c929
-rw-r--r--kernel/trace/ring_buffer.c709
-rw-r--r--kernel/trace/trace.c978
-rw-r--r--kernel/trace/trace.h265
-rw-r--r--kernel/trace/trace_boot.c158
-rw-r--r--kernel/trace/trace_branch.c342
-rw-r--r--kernel/trace/trace_functions.c30
-rw-r--r--kernel/trace/trace_functions_graph.c669
-rw-r--r--kernel/trace/trace_hw_branches.c195
-rw-r--r--kernel/trace/trace_irqsoff.c61
-rw-r--r--kernel/trace/trace_mmiotrace.c33
-rw-r--r--kernel/trace/trace_nop.c65
-rw-r--r--kernel/trace/trace_power.c179
-rw-r--r--kernel/trace/trace_sched_switch.c121
-rw-r--r--kernel/trace/trace_sched_wakeup.c72
-rw-r--r--kernel/trace/trace_selftest.c173
-rw-r--r--kernel/trace/trace_stack.c70
-rw-r--r--kernel/trace/trace_sysprof.c31
-rw-r--r--kernel/tracepoint.c295
-rw-r--r--kernel/tsacct.c6
-rw-r--r--kernel/uid16.c31
-rw-r--r--kernel/user.c98
-rw-r--r--kernel/user_namespace.c65
-rw-r--r--kernel/workqueue.c8
61 files changed, 6549 insertions, 1995 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 19fad003b19..027edda6351 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.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 pm_qos_params.o sched_clock.o
+ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
@@ -19,7 +19,6 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
CFLAGS_REMOVE_rtmutex-debug.o = -pg
CFLAGS_REMOVE_cgroup-debug.o = -pg
CFLAGS_REMOVE_sched_clock.o = -pg
-CFLAGS_REMOVE_sched.o = -pg
endif
obj-$(CONFIG_FREEZER) += freezer.o
@@ -90,7 +89,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
-ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
+ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
# needed for x86 only. Why this used to be enabled for all architectures is beyond
# me. I suspect most platforms don't need this, but until we know that for sure
diff --git a/kernel/acct.c b/kernel/acct.c
index f6006a60df5..d57b7cbb98b 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -530,15 +530,14 @@ static void do_acct_process(struct bsd_acct_struct *acct,
do_div(elapsed, AHZ);
ac.ac_btime = get_seconds() - elapsed;
/* we really need to bite the bullet and change layout */
- ac.ac_uid = current->uid;
- ac.ac_gid = current->gid;
+ current_uid_gid(&ac.ac_uid, &ac.ac_gid);
#if ACCT_VERSION==2
ac.ac_ahz = AHZ;
#endif
#if ACCT_VERSION==1 || ACCT_VERSION==2
/* backward-compatible 16 bit fields */
- ac.ac_uid16 = current->uid;
- ac.ac_gid16 = current->gid;
+ ac.ac_uid16 = ac.ac_uid;
+ ac.ac_gid16 = ac.ac_gid;
#endif
#if ACCT_VERSION==3
ac.ac_pid = task_tgid_nr_ns(current, ns);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 2a3f0afc4d2..4819f371197 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -65,6 +65,7 @@
#include <linux/highmem.h>
#include <linux/syscalls.h>
#include <linux/inotify.h>
+#include <linux/capability.h>
#include "audit.h"
@@ -84,6 +85,15 @@ int audit_n_rules;
/* determines whether we collect data for signals sent */
int audit_signals;
+struct audit_cap_data {
+ kernel_cap_t permitted;
+ kernel_cap_t inheritable;
+ union {
+ unsigned int fE; /* effective bit of a file capability */
+ kernel_cap_t effective; /* effective set of a process */
+ };
+};
+
/* When fs/namei.c:getname() is called, we store the pointer in name and
* we don't let putname() free it (instead we free all of the saved
* pointers at syscall exit time).
@@ -100,6 +110,8 @@ struct audit_names {
gid_t gid;
dev_t rdev;
u32 osid;
+ struct audit_cap_data fcap;
+ unsigned int fcap_ver;
};
struct audit_aux_data {
@@ -184,6 +196,20 @@ struct audit_aux_data_pids {
int pid_count;
};
+struct audit_aux_data_bprm_fcaps {
+ struct audit_aux_data d;
+ struct audit_cap_data fcap;
+ unsigned int fcap_ver;
+ struct audit_cap_data old_pcap;
+ struct audit_cap_data new_pcap;
+};
+
+struct audit_aux_data_capset {
+ struct audit_aux_data d;
+ pid_t pid;
+ struct audit_cap_data cap;
+};
+
struct audit_tree_refs {
struct audit_tree_refs *next;
struct audit_chunk *c[31];
@@ -421,6 +447,7 @@ static int audit_filter_rules(struct task_struct *tsk,
struct audit_names *name,
enum audit_state *state)
{
+ const struct cred *cred = get_task_cred(tsk);
int i, j, need_sid = 1;
u32 sid;
@@ -440,28 +467,28 @@ static int audit_filter_rules(struct task_struct *tsk,
}
break;
case AUDIT_UID:
- result = audit_comparator(tsk->uid, f->op, f->val);
+ result = audit_comparator(cred->uid, f->op, f->val);
break;
case AUDIT_EUID:
- result = audit_comparator(tsk->euid, f->op, f->val);
+ result = audit_comparator(cred->euid, f->op, f->val);
break;
case AUDIT_SUID:
- result = audit_comparator(tsk->suid, f->op, f->val);
+ result = audit_comparator(cred->suid, f->op, f->val);
break;
case AUDIT_FSUID:
- result = audit_comparator(tsk->fsuid, f->op, f->val);
+ result = audit_comparator(cred->fsuid, f->op, f->val);
break;
case AUDIT_GID:
- result = audit_comparator(tsk->gid, f->op, f->val);
+ result = audit_comparator(cred->gid, f->op, f->val);
break;
case AUDIT_EGID:
- result = audit_comparator(tsk->egid, f->op, f->val);
+ result = audit_comparator(cred->egid, f->op, f->val);
break;
case AUDIT_SGID:
- result = audit_comparator(tsk->sgid, f->op, f->val);
+ result = audit_comparator(cred->sgid, f->op, f->val);
break;
case AUDIT_FSGID:
- result = audit_comparator(tsk->fsgid, f->op, f->val);
+ result = audit_comparator(cred->fsgid, f->op, f->val);
break;
case AUDIT_PERS:
result = audit_comparator(tsk->personality, f->op, f->val);
@@ -615,8 +642,10 @@ static int audit_filter_rules(struct task_struct *tsk,
break;
}
- if (!result)
+ if (!result) {
+ put_cred(cred);
return 0;
+ }
}
if (rule->filterkey && ctx)
ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
@@ -624,6 +653,7 @@ static int audit_filter_rules(struct task_struct *tsk,
case AUDIT_NEVER: *state = AUDIT_DISABLED; break;
case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break;
}
+ put_cred(cred);
return 1;
}
@@ -1171,8 +1201,38 @@ static void audit_log_execve_info(struct audit_context *context,
kfree(buf);
}
+static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap)
+{
+ int i;
+
+ audit_log_format(ab, " %s=", prefix);
+ CAP_FOR_EACH_U32(i) {
+ audit_log_format(ab, "%08x", cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+ }
+}
+
+static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
+{
+ kernel_cap_t *perm = &name->fcap.permitted;
+ kernel_cap_t *inh = &name->fcap.inheritable;
+ int log = 0;
+
+ if (!cap_isclear(*perm)) {
+ audit_log_cap(ab, "cap_fp", perm);
+ log = 1;
+ }
+ if (!cap_isclear(*inh)) {
+ audit_log_cap(ab, "cap_fi", inh);
+ log = 1;
+ }
+
+ if (log)
+ audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver);
+}
+
static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
{
+ const struct cred *cred;
int i, call_panic = 0;
struct audit_buffer *ab;
struct audit_aux_data *aux;
@@ -1182,14 +1242,15 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
context->pid = tsk->pid;
if (!context->ppid)
context->ppid = sys_getppid();
- context->uid = tsk->uid;
- context->gid = tsk->gid;
- context->euid = tsk->euid;
- context->suid = tsk->suid;
- context->fsuid = tsk->fsuid;
- context->egid = tsk->egid;
- context->sgid = tsk->sgid;
- context->fsgid = tsk->fsgid;
+ cred = current_cred();
+ context->uid = cred->uid;
+ context->gid = cred->gid;
+ context->euid = cred->euid;
+ context->suid = cred->suid;
+ context->fsuid = cred->fsuid;
+ context->egid = cred->egid;
+ context->sgid = cred->sgid;
+ context->fsgid = cred->fsgid;
context->personality = tsk->personality;
ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
@@ -1334,6 +1395,28 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]);
break; }
+ case AUDIT_BPRM_FCAPS: {
+ struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
+ audit_log_format(ab, "fver=%x", axs->fcap_ver);
+ audit_log_cap(ab, "fp", &axs->fcap.permitted);
+ audit_log_cap(ab, "fi", &axs->fcap.inheritable);
+ audit_log_format(ab, " fe=%d", axs->fcap.fE);
+ audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted);
+ audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable);
+ audit_log_cap(ab, "old_pe", &axs->old_pcap.effective);
+ audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted);
+ audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable);
+ audit_log_cap(ab, "new_pe", &axs->new_pcap.effective);
+ break; }
+
+ case AUDIT_CAPSET: {
+ struct audit_aux_data_capset *axs = (void *)aux;
+ audit_log_format(ab, "pid=%d", axs->pid);
+ audit_log_cap(ab, "cap_pi", &axs->cap.inheritable);
+ audit_log_cap(ab, "cap_pp", &axs->cap.permitted);
+ audit_log_cap(ab, "cap_pe", &axs->cap.effective);
+ break; }
+
}
audit_log_end(ab);
}
@@ -1421,6 +1504,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
}
}
+ audit_log_fcaps(ab, n);
+
audit_log_end(ab);
}
@@ -1802,8 +1887,36 @@ static int audit_inc_name_count(struct audit_context *context,
return 0;
}
+
+static inline int audit_copy_fcaps(struct audit_names *name, const struct dentry *dentry)
+{
+ struct cpu_vfs_cap_data caps;
+ int rc;
+
+ memset(&name->fcap.permitted, 0, sizeof(kernel_cap_t));
+ memset(&name->fcap.inheritable, 0, sizeof(kernel_cap_t));
+ name->fcap.fE = 0;
+ name->fcap_ver = 0;
+
+ if (!dentry)
+ return 0;
+
+ rc = get_vfs_caps_from_disk(dentry, &caps);
+ if (rc)
+ return rc;
+
+ name->fcap.permitted = caps.permitted;
+ name->fcap.inheritable = caps.inheritable;
+ name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
+ name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;
+
+ return 0;
+}
+
+
/* Copy inode data into an audit_names. */
-static void audit_copy_inode(struct audit_names *name, const struct inode *inode)
+static void audit_copy_inode(struct audit_names *name, const struct dentry *dentry,
+ const struct inode *inode)
{
name->ino = inode->i_ino;
name->dev = inode->i_sb->s_dev;
@@ -1812,6 +1925,7 @@ static void audit_copy_inode(struct audit_names *name, const struct inode *inode
name->gid = inode->i_gid;
name->rdev = inode->i_rdev;
security_inode_getsecid(inode, &name->osid);
+ audit_copy_fcaps(name, dentry);
}
/**
@@ -1846,7 +1960,7 @@ void __audit_inode(const char *name, const struct dentry *dentry)
context->names[idx].name = NULL;
}
handle_path(dentry);
- audit_copy_inode(&context->names[idx], inode);
+ audit_copy_inode(&context->names[idx], dentry, inode);
}
/**
@@ -1907,7 +2021,7 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry,
if (!strcmp(dname, n->name) ||
!audit_compare_dname_path(dname, n->name, &dirlen)) {
if (inode)
- audit_copy_inode(n, inode);
+ audit_copy_inode(n, NULL, inode);
else
n->ino = (unsigned long)-1;
found_child = n->name;
@@ -1921,7 +2035,7 @@ add_names:
return;
idx = context->name_count - 1;
context->names[idx].name = NULL;
- audit_copy_inode(&context->names[idx], parent);
+ audit_copy_inode(&context->names[idx], NULL, parent);
}
if (!found_child) {
@@ -1942,7 +2056,7 @@ add_names:
}
if (inode)
- audit_copy_inode(&context->names[idx], inode);
+ audit_copy_inode(&context->names[idx], NULL, inode);
else
context->names[idx].ino = (unsigned long)-1;
}
@@ -1996,7 +2110,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
audit_log_format(ab, "login pid=%d uid=%u "
"old auid=%u new auid=%u"
" old ses=%u new ses=%u",
- task->pid, task->uid,
+ task->pid, task_uid(task),
task->loginuid, loginuid,
task->sessionid, sessionid);
audit_log_end(ab);
@@ -2379,7 +2493,7 @@ void __audit_ptrace(struct task_struct *t)
context->target_pid = t->pid;
context->target_auid = audit_get_loginuid(t);
- context->target_uid = t->uid;
+ context->target_uid = task_uid(t);
context->target_sessionid = audit_get_sessionid(t);
security_task_getsecid(t, &context->target_sid);
memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
@@ -2398,6 +2512,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
struct audit_aux_data_pids *axp;
struct task_struct *tsk = current;
struct audit_context *ctx = tsk->audit_context;
+ uid_t uid = current_uid(), t_uid = task_uid(t);
if (audit_pid && t->tgid == audit_pid) {
if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
@@ -2405,7 +2520,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
if (tsk->loginuid != -1)
audit_sig_uid = tsk->loginuid;
else
- audit_sig_uid = tsk->uid;
+ audit_sig_uid = uid;
security_task_getsecid(tsk, &audit_sig_sid);
}
if (!audit_signals || audit_dummy_context())
@@ -2417,7 +2532,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
if (!ctx->target_pid) {
ctx->target_pid = t->tgid;
ctx->target_auid = audit_get_loginuid(t);
- ctx->target_uid = t->uid;
+ ctx->target_uid = t_uid;
ctx->target_sessionid = audit_get_sessionid(t);
security_task_getsecid(t, &ctx->target_sid);
memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
@@ -2438,7 +2553,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
axp->target_pid[axp->pid_count] = t->tgid;
axp->target_auid[axp->pid_count] = audit_get_loginuid(t);
- axp->target_uid[axp->pid_count] = t->uid;
+ axp->target_uid[axp->pid_count] = t_uid;
axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
security_task_getsecid(t, &axp->target_sid[axp->pid_count]);
memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
@@ -2448,6 +2563,86 @@ int __audit_signal_info(int sig, struct task_struct *t)
}
/**
+ * __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps
+ * @bprm: pointer to the bprm being processed
+ * @new: the proposed new credentials
+ * @old: the old credentials
+ *
+ * Simply check if the proc already has the caps given by the file and if not
+ * store the priv escalation info for later auditing at the end of the syscall
+ *
+ * -Eric
+ */
+int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
+ const struct cred *new, const struct cred *old)
+{
+ struct audit_aux_data_bprm_fcaps *ax;
+ struct audit_context *context = current->audit_context;
+ struct cpu_vfs_cap_data vcaps;
+ struct dentry *dentry;
+
+ ax = kmalloc(sizeof(*ax), GFP_KERNEL);
+ if (!ax)
+ return -ENOMEM;
+
+ ax->d.type = AUDIT_BPRM_FCAPS;
+ ax->d.next = context->aux;
+ context->aux = (void *)ax;
+
+ dentry = dget(bprm->file->f_dentry);
+ get_vfs_caps_from_disk(dentry, &vcaps);
+ dput(dentry);
+
+ ax->fcap.permitted = vcaps.permitted;
+ ax->fcap.inheritable = vcaps.inheritable;
+ ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE);
+ ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT;
+
+ ax->old_pcap.permitted = old->cap_permitted;
+ ax->old_pcap.inheritable = old->cap_inheritable;
+ ax->old_pcap.effective = old->cap_effective;
+
+ ax->new_pcap.permitted = new->cap_permitted;
+ ax->new_pcap.inheritable = new->cap_inheritable;
+ ax->new_pcap.effective = new->cap_effective;
+ return 0;
+}
+
+/**
+ * __audit_log_capset - store information about the arguments to the capset syscall
+ * @pid: target pid of the capset call
+ * @new: the new credentials
+ * @old: the old (current) credentials
+ *
+ * Record the aguments userspace sent to sys_capset for later printing by the
+ * audit system if applicable
+ */
+int __audit_log_capset(pid_t pid,
+ const struct cred *new, const struct cred *old)
+{
+ struct audit_aux_data_capset *ax;
+ struct audit_context *context = current->audit_context;
+
+ if (likely(!audit_enabled || !context || context->dummy))
+ return 0;
+
+ ax = kmalloc(sizeof(*ax), GFP_KERNEL);
+ if (!ax)
+ return -ENOMEM;
+
+ ax->d.type = AUDIT_CAPSET;
+ ax->d.next = context->aux;
+ context->aux = (void *)ax;
+
+ ax->pid = pid;
+ ax->cap.effective = new->cap_effective;
+ ax->cap.inheritable = new->cap_effective;
+ ax->cap.permitted = new->cap_permitted;
+
+ return 0;
+}
+
+/**
* audit_core_dumps - record information about processes that end abnormally
* @signr: signal value
*
@@ -2458,7 +2653,8 @@ void audit_core_dumps(long signr)
{
struct audit_buffer *ab;
u32 sid;
- uid_t auid = audit_get_loginuid(current);
+ uid_t auid = audit_get_loginuid(current), uid;
+ gid_t gid;
unsigned int sessionid = audit_get_sessionid(current);
if (!audit_enabled)
@@ -2468,8 +2664,9 @@ void audit_core_dumps(long signr)
return;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
+ current_uid_gid(&uid, &gid);
audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u",
- auid, current->uid, current->gid, sessionid);
+ auid, uid, gid, sessionid);
security_task_getsecid(current, &sid);
if (sid) {
char *ctx = NULL;
diff --git a/kernel/capability.c b/kernel/capability.c
index 33e51e78c2d..36b4b4daebe 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -7,6 +7,7 @@
* 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
*/
+#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/module.h>
@@ -14,12 +15,7 @@
#include <linux/syscalls.h>
#include <linux/pid_namespace.h>
#include <asm/uaccess.h>
-
-/*
- * This lock protects task->cap_* for all tasks including current.
- * Locking rule: acquire this prior to tasklist_lock.
- */
-static DEFINE_SPINLOCK(task_capability_lock);
+#include "cred-internals.h"
/*
* Leveraged for setting/resetting capabilities
@@ -33,6 +29,17 @@ EXPORT_SYMBOL(__cap_empty_set);
EXPORT_SYMBOL(__cap_full_set);
EXPORT_SYMBOL(__cap_init_eff_set);
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
+int file_caps_enabled = 1;
+
+static int __init file_caps_disable(char *str)
+{
+ file_caps_enabled = 0;
+ return 1;
+}
+__setup("no_file_caps", file_caps_disable);
+#endif
+
/*
* More recent versions of libcap are available from:
*
@@ -115,167 +122,12 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
return 0;
}
-#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
-
-/*
- * Without filesystem capability support, we nominally support one process
- * setting the capabilities of another
- */
-static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
- kernel_cap_t *pIp, kernel_cap_t *pPp)
-{
- struct task_struct *target;
- int ret;
-
- spin_lock(&task_capability_lock);
- read_lock(&tasklist_lock);
-
- if (pid && pid != task_pid_vnr(current)) {
- target = find_task_by_vpid(pid);
- if (!target) {
- ret = -ESRCH;
- goto out;
- }
- } else
- target = current;
-
- ret = security_capget(target, pEp, pIp, pPp);
-
-out:
- read_unlock(&tasklist_lock);
- spin_unlock(&task_capability_lock);
-
- return ret;
-}
-
-/*
- * cap_set_pg - set capabilities for all processes in a given process
- * group. We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective,
- kernel_cap_t *inheritable,
- kernel_cap_t *permitted)
-{
- struct task_struct *g, *target;
- int ret = -EPERM;
- int found = 0;
- struct pid *pgrp;
-
- spin_lock(&task_capability_lock);
- read_lock(&tasklist_lock);
-
- pgrp = find_vpid(pgrp_nr);
- do_each_pid_task(pgrp, PIDTYPE_PGID, g) {
- target = g;
- while_each_thread(g, target) {
- if (!security_capset_check(target, effective,
- inheritable, permitted)) {
- security_capset_set(target, effective,
- inheritable, permitted);
- ret = 0;
- }
- found = 1;
- }
- } while_each_pid_task(pgrp, PIDTYPE_PGID, g);
-
- read_unlock(&tasklist_lock);
- spin_unlock(&task_capability_lock);
-
- if (!found)
- ret = 0;
- return ret;
-}
-
-/*
- * cap_set_all - set capabilities for all processes other than init
- * and self. We call this holding task_capability_lock and tasklist_lock.
- */
-static inline int cap_set_all(kernel_cap_t *effective,
- kernel_cap_t *inheritable,
- kernel_cap_t *permitted)
-{
- struct task_struct *g, *target;
- int ret = -EPERM;
- int found = 0;
-
- spin_lock(&task_capability_lock);
- read_lock(&tasklist_lock);
-
- do_each_thread(g, target) {
- if (target == current
- || is_container_init(target->group_leader))
- continue;
- found = 1;
- if (security_capset_check(target, effective, inheritable,
- permitted))
- continue;
- ret = 0;
- security_capset_set(target, effective, inheritable, permitted);
- } while_each_thread(g, target);
-
- read_unlock(&tasklist_lock);
- spin_unlock(&task_capability_lock);
-
- if (!found)
- ret = 0;
-
- return ret;
-}
-
-/*
- * Given the target pid does not refer to the current process we
- * need more elaborate support... (This support is not present when
- * filesystem capabilities are configured.)
- */
-static inline int do_sys_capset_other_tasks(pid_t pid, kernel_cap_t *effective,
- kernel_cap_t *inheritable,
- kernel_cap_t *permitted)
-{
- struct task_struct *target;
- int ret;
-
- if (!capable(CAP_SETPCAP))
- return -EPERM;
-
- if (pid == -1) /* all procs other than current and init */
- return cap_set_all(effective, inheritable, permitted);
-
- else if (pid < 0) /* all procs in process group */
- return cap_set_pg(-pid, effective, inheritable, permitted);
-
- /* target != current */
- spin_lock(&task_capability_lock);
- read_lock(&tasklist_lock);
-
- target = find_task_by_vpid(pid);
- if (!target)
- ret = -ESRCH;
- else {
- ret = security_capset_check(target, effective, inheritable,
- permitted);
-
- /* having verified that the proposed changes are legal,
- we now put them into effect. */
- if (!ret)
- security_capset_set(target, effective, inheritable,
- permitted);
- }
-
- read_unlock(&tasklist_lock);
- spin_unlock(&task_capability_lock);
-
- return ret;
-}
-
-#else /* ie., def CONFIG_SECURITY_FILE_CAPABILITIES */
-
/*
- * If we have configured with filesystem capability support, then the
- * only thing that can change the capabilities of the current process
- * is the current process. As such, we can't be in this code at the
- * same time as we are in the process of setting capabilities in this
- * process. The net result is that we can limit our use of locks to
- * when we are reading the caps of another process.
+ * The only thing that can change the capabilities of the current
+ * process is the current process. As such, we can't be in this code
+ * at the same time as we are in the process of setting capabilities
+ * in this process. The net result is that we can limit our use of
+ * locks to when we are reading the caps of another process.
*/
static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
kernel_cap_t *pIp, kernel_cap_t *pPp)
@@ -285,7 +137,6 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
if (pid && (pid != task_pid_vnr(current))) {
struct task_struct *target;
- spin_lock(&task_capability_lock);
read_lock(&tasklist_lock);
target = find_task_by_vpid(pid);
@@ -295,50 +146,12 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
ret = security_capget(target, pEp, pIp, pPp);
read_unlock(&tasklist_lock);
- spin_unlock(&task_capability_lock);
} else
ret = security_capget(current, pEp, pIp, pPp);
return ret;
}
-/*
- * With filesystem capability support configured, the kernel does not
- * permit the changing of capabilities in one process by another
- * process. (CAP_SETPCAP has much less broad semantics when configured
- * this way.)
- */
-static inline int do_sys_capset_other_tasks(pid_t pid,
- kernel_cap_t *effective,
- kernel_cap_t *inheritable,
- kernel_cap_t *permitted)
-{
- return -EPERM;
-}
-
-#endif /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */
-
-/*
- * Atomically modify the effective capabilities returning the original
- * value. No permission check is performed here - it is assumed that the
- * caller is permitted to set the desired effective capabilities.
- */
-kernel_cap_t cap_set_effective(const kernel_cap_t pE_new)
-{
- kernel_cap_t pE_old;
-
- spin_lock(&task_capability_lock);
-
- pE_old = current->cap_effective;
- current->cap_effective = pE_new;
-
- spin_unlock(&task_capability_lock);
-
- return pE_old;
-}
-
-EXPORT_SYMBOL(cap_set_effective);
-
/**
* sys_capget - get the capabilities of a given process.
* @header: pointer to struct that contains capability version and
@@ -366,7 +179,6 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
return -EINVAL;
ret = cap_get_target_pid(pid, &pE, &pI, &pP);
-
if (!ret) {
struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
unsigned i;
@@ -412,16 +224,14 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr)
* @data: pointer to struct that contains the effective, permitted,
* and inheritable capabilities
*
- * Set capabilities for a given process, all processes, or all
- * processes in a given process group.
+ * Set capabilities for the current process only. The ability to any other
+ * process(es) has been deprecated and removed.
*
* The restrictions on setting capabilities are specified as:
*
- * [pid is for the 'target' task. 'current' is the calling task.]
- *
- * I: any raised capabilities must be a subset of the (old current) permitted
- * P: any raised capabilities must be a subset of the (old current) permitted
- * E: must be set to a subset of (new target) permitted
+ * I: any raised capabilities must be a subset of the old permitted
+ * P: any raised capabilities must be a subset of the old permitted
+ * E: must be set to a subset of new permitted
*
* Returns 0 on success and < 0 on error.
*/
@@ -430,6 +240,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
unsigned i, tocopy;
kernel_cap_t inheritable, permitted, effective;
+ struct cred *new;
int ret;
pid_t pid;
@@ -440,10 +251,13 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
if (get_user(pid, &header->pid))
return -EFAULT;
- if (copy_from_user(&kdata, data, tocopy
- * sizeof(struct __user_cap_data_struct))) {
+ /* may only affect current now */
+ if (pid != 0 && pid != task_pid_vnr(current))
+ return -EPERM;
+
+ if (copy_from_user(&kdata, data,
+ tocopy * sizeof(struct __user_cap_data_struct)))
return -EFAULT;
- }
for (i = 0; i < tocopy; i++) {
effective.cap[i] = kdata[i].effective;
@@ -457,32 +271,23 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
i++;
}
- if (pid && (pid != task_pid_vnr(current)))
- ret = do_sys_capset_other_tasks(pid, &effective, &inheritable,
- &permitted);
- else {
- /*
- * This lock is required even when filesystem
- * capability support is configured - it protects the
- * sys_capget() call from returning incorrect data in
- * the case that the targeted process is not the
- * current one.
- */
- spin_lock(&task_capability_lock);
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
- ret = security_capset_check(current, &effective, &inheritable,
- &permitted);
- /*
- * Having verified that the proposed changes are
- * legal, we now put them into effect.
- */
- if (!ret)
- security_capset_set(current, &effective, &inheritable,
- &permitted);
- spin_unlock(&task_capability_lock);
- }
+ ret = security_capset(new, current_cred(),
+ &effective, &inheritable, &permitted);
+ if (ret < 0)
+ goto error;
+
+ ret = audit_log_capset(pid, new, current_cred());
+ if (ret < 0)
+ return ret;
+ return commit_creds(new);
+error:
+ abort_creds(new);
return ret;
}
@@ -498,6 +303,11 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
*/
int capable(int cap)
{
+ if (unlikely(!cap_valid(cap))) {
+ printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap);
+ BUG();
+ }
+
if (has_capability(current, cap)) {
current->flags |= PF_SUPERPRIV;
return 1;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fe00b3b983a..48348dde6d8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -571,8 +571,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
if (inode) {
inode->i_mode = mode;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
+ inode->i_uid = current_fsuid();
+ inode->i_gid = current_fsgid();
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
@@ -702,7 +702,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
* any child cgroups exist. This is theoretically supportable
* but involves complex error handling, so it's being left until
* later */
- if (!list_empty(&cgrp->children))
+ if (root->number_of_cgroups > 1)
return -EBUSY;
/* Process each subsystem */
@@ -1024,7 +1024,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
if (ret == -EBUSY) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
- goto drop_new_super;
+ goto free_cg_links;
}
/* EBUSY should be the only error here */
@@ -1073,10 +1073,11 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
return simple_set_mnt(mnt, sb);
+ free_cg_links:
+ free_cg_links(&tmp_cg_links);
drop_new_super:
up_write(&sb->s_umount);
deactivate_super(sb);
- free_cg_links(&tmp_cg_links);
return ret;
}
@@ -1279,6 +1280,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
{
struct task_struct *tsk;
+ const struct cred *cred = current_cred(), *tcred;
int ret;
if (pid) {
@@ -1288,14 +1290,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
rcu_read_unlock();
return -ESRCH;
}
- get_task_struct(tsk);
- rcu_read_unlock();
- if ((current->euid) && (current->euid != tsk->uid)
- && (current->euid != tsk->suid)) {
- put_task_struct(tsk);
+ tcred = __task_cred(tsk);
+ if (cred->euid &&
+ cred->euid != tcred->uid &&
+ cred->euid != tcred->suid) {
+ rcu_read_unlock();
return -EACCES;
}
+ get_task_struct(tsk);
+ rcu_read_unlock();
} else {
tsk = current;
get_task_struct(tsk);
@@ -2934,9 +2938,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
again:
root = subsys->root;
if (root == &rootnode) {
- printk(KERN_INFO
- "Not cloning cgroup for unused subsystem %s\n",
- subsys->name);
mutex_unlock(&cgroup_mutex);
return 0;
}
diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h
new file mode 100644
index 00000000000..2dc4fc2d0bf
--- /dev/null
+++ b/kernel/cred-internals.h
@@ -0,0 +1,21 @@
+/* Internal credentials stuff
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+/*
+ * user.c
+ */
+static inline void sched_switch_user(struct task_struct *p)
+{
+#ifdef CONFIG_USER_SCHED
+ sched_move_task(p);
+#endif /* CONFIG_USER_SCHED */
+}
+
diff --git a/kernel/cred.c b/kernel/cred.c
new file mode 100644
index 00000000000..ff7bc071991
--- /dev/null
+++ b/kernel/cred.c
@@ -0,0 +1,588 @@
+/* Task credentials management - see Documentation/credentials.txt
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#include <linux/module.h>
+#include <linux/cred.h>
+#include <linux/sched.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/init_task.h>
+#include <linux/security.h>
+#include <linux/cn_proc.h>
+#include "cred-internals.h"
+
+static struct kmem_cache *cred_jar;
+
+/*
+ * The common credentials for the initial task's thread group
+ */
+#ifdef CONFIG_KEYS
+static struct thread_group_cred init_tgcred = {
+ .usage = ATOMIC_INIT(2),
+ .tgid = 0,
+ .lock = SPIN_LOCK_UNLOCKED,
+};
+#endif
+
+/*
+ * The initial credentials for the initial task
+ */
+struct cred init_cred = {
+ .usage = ATOMIC_INIT(4),
+ .securebits = SECUREBITS_DEFAULT,
+ .cap_inheritable = CAP_INIT_INH_SET,
+ .cap_permitted = CAP_FULL_SET,
+ .cap_effective = CAP_INIT_EFF_SET,
+ .cap_bset = CAP_INIT_BSET,
+ .user = INIT_USER,
+ .group_info = &init_groups,
+#ifdef CONFIG_KEYS
+ .tgcred = &init_tgcred,
+#endif
+};
+
+/*
+ * Dispose of the shared task group credentials
+ */
+#ifdef CONFIG_KEYS
+static void release_tgcred_rcu(struct rcu_head *rcu)
+{
+ struct thread_group_cred *tgcred =
+ container_of(rcu, struct thread_group_cred, rcu);
+
+ BUG_ON(atomic_read(&tgcred->usage) != 0);
+
+ key_put(tgcred->session_keyring);
+ key_put(tgcred->process_keyring);
+ kfree(tgcred);
+}
+#endif
+
+/*
+ * Release a set of thread group credentials.
+ */
+static void release_tgcred(struct cred *cred)
+{
+#ifdef CONFIG_KEYS
+ struct thread_group_cred *tgcred = cred->tgcred;
+
+ if (atomic_dec_and_test(&tgcred->usage))
+ call_rcu(&tgcred->rcu, release_tgcred_rcu);
+#endif
+}
+
+/*
+ * The RCU callback to actually dispose of a set of credentials
+ */
+static void put_cred_rcu(struct rcu_head *rcu)
+{
+ struct cred *cred = container_of(rcu, struct cred, rcu);
+
+ if (atomic_read(&cred->usage) != 0)
+ panic("CRED: put_cred_rcu() sees %p with usage %d\n",
+ cred, atomic_read(&cred->usage));
+
+ security_cred_free(cred);
+ key_put(cred->thread_keyring);
+ key_put(cred->request_key_auth);
+ release_tgcred(cred);
+ put_group_info(cred->group_info);
+ free_uid(cred->user);
+ kmem_cache_free(cred_jar, cred);
+}
+
+/**
+ * __put_cred - Destroy a set of credentials
+ * @cred: The record to release
+ *
+ * Destroy a set of credentials on which no references remain.
+ */
+void __put_cred(struct cred *cred)
+{
+ BUG_ON(atomic_read(&cred->usage) != 0);
+
+ call_rcu(&cred->rcu, put_cred_rcu);
+}
+EXPORT_SYMBOL(__put_cred);
+
+/**
+ * prepare_creds - Prepare a new set of credentials for modification
+ *
+ * Prepare a new set of task credentials for modification. A task's creds
+ * shouldn't generally be modified directly, therefore this function is used to
+ * prepare a new copy, which the caller then modifies and then commits by
+ * calling commit_creds().
+ *
+ * Preparation involves making a copy of the objective creds for modification.
+ *
+ * Returns a pointer to the new creds-to-be if successful, NULL otherwise.
+ *
+ * Call commit_creds() or abort_creds() to clean up.
+ */
+struct cred *prepare_creds(void)
+{
+ struct task_struct *task = current;
+ const struct cred *old;
+ struct cred *new;
+
+ BUG_ON(atomic_read(&task->real_cred->usage) < 1);
+
+ new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ old = task->cred;
+ memcpy(new, old, sizeof(struct cred));
+
+ atomic_set(&new->usage, 1);
+ get_group_info(new->group_info);
+ get_uid(new->user);
+
+#ifdef CONFIG_KEYS
+ key_get(new->thread_keyring);
+ key_get(new->request_key_auth);
+ atomic_inc(&new->tgcred->usage);
+#endif
+
+#ifdef CONFIG_SECURITY
+ new->security = NULL;
+#endif
+
+ if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ goto error;
+ return new;
+
+error:
+ abort_creds(new);
+ return NULL;
+}
+EXPORT_SYMBOL(prepare_creds);
+
+/*
+ * Prepare credentials for current to perform an execve()
+ * - The caller must hold current->cred_exec_mutex
+ */
+struct cred *prepare_exec_creds(void)
+{
+ struct thread_group_cred *tgcred = NULL;
+ struct cred *new;
+
+#ifdef CONFIG_KEYS
+ tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
+ if (!tgcred)
+ return NULL;
+#endif
+
+ new = prepare_creds();
+ if (!new) {
+ kfree(tgcred);
+ return new;
+ }
+
+#ifdef CONFIG_KEYS
+ /* newly exec'd tasks don't get a thread keyring */
+ key_put(new->thread_keyring);
+ new->thread_keyring = NULL;
+
+ /* create a new per-thread-group creds for all this set of threads to
+ * share */
+ memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred));
+
+ atomic_set(&tgcred->usage, 1);
+ spin_lock_init(&tgcred->lock);
+
+ /* inherit the session keyring; new process keyring */
+ key_get(tgcred->session_keyring);
+ tgcred->process_keyring = NULL;
+
+ release_tgcred(new);
+ new->tgcred = tgcred;
+#endif
+
+ return new;
+}
+
+/*
+ * prepare new credentials for the usermode helper dispatcher
+ */
+struct cred *prepare_usermodehelper_creds(void)
+{
+#ifdef CONFIG_KEYS
+ struct thread_group_cred *tgcred = NULL;
+#endif
+ struct cred *new;
+
+#ifdef CONFIG_KEYS
+ tgcred = kzalloc(sizeof(*new->tgcred), GFP_ATOMIC);
+ if (!tgcred)
+ return NULL;
+#endif
+
+ new = kmem_cache_alloc(cred_jar, GFP_ATOMIC);
+ if (!new)
+ return NULL;
+
+ memcpy(new, &init_cred, sizeof(struct cred));
+
+ atomic_set(&new->usage, 1);
+ get_group_info(new->group_info);
+ get_uid(new->user);
+
+#ifdef CONFIG_KEYS
+ new->thread_keyring = NULL;
+ new->request_key_auth = NULL;
+ new->jit_keyring = KEY_REQKEY_DEFL_DEFAULT;
+
+ atomic_set(&tgcred->usage, 1);
+ spin_lock_init(&tgcred->lock);
+ new->tgcred = tgcred;
+#endif
+
+#ifdef CONFIG_SECURITY
+ new->security = NULL;
+#endif
+ if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0)
+ goto error;
+
+ BUG_ON(atomic_read(&new->usage) != 1);
+ return new;
+
+error:
+ put_cred(new);
+ return NULL;
+}
+
+/*
+ * Copy credentials for the new process created by fork()
+ *
+ * We share if we can, but under some circumstances we have to generate a new
+ * set.
+ *
+ * The new process gets the current process's subjective credentials as its
+ * objective and subjective credentials
+ */
+int copy_creds(struct task_struct *p, unsigned long clone_flags)
+{
+#ifdef CONFIG_KEYS
+ struct thread_group_cred *tgcred;
+#endif
+ struct cred *new;
+ int ret;
+
+ mutex_init(&p->cred_exec_mutex);
+
+ if (
+#ifdef CONFIG_KEYS
+ !p->cred->thread_keyring &&
+#endif
+ clone_flags & CLONE_THREAD
+ ) {
+ p->real_cred = get_cred(p->cred);
+ get_cred(p->cred);
+ atomic_inc(&p->cred->user->processes);
+ return 0;
+ }
+
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+
+ if (clone_flags & CLONE_NEWUSER) {
+ ret = create_user_ns(new);
+ if (ret < 0)
+ goto error_put;
+ }
+
+#ifdef CONFIG_KEYS
+ /* new threads get their own thread keyrings if their parent already
+ * had one */
+ if (new->thread_keyring) {
+ key_put(new->thread_keyring);
+ new->thread_keyring = NULL;
+ if (clone_flags & CLONE_THREAD)
+ install_thread_keyring_to_cred(new);
+ }
+
+ /* we share the process and session keyrings between all the threads in
+ * a process - this is slightly icky as we violate COW credentials a
+ * bit */
+ if (!(clone_flags & CLONE_THREAD)) {
+ tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL);
+ if (!tgcred) {
+ ret = -ENOMEM;
+ goto error_put;
+ }
+ atomic_set(&tgcred->usage, 1);
+ spin_lock_init(&tgcred->lock);
+ tgcred->process_keyring = NULL;
+ tgcred->session_keyring = key_get(new->tgcred->session_keyring);
+
+ release_tgcred(new);
+ new->tgcred = tgcred;
+ }
+#endif
+
+ atomic_inc(&new->user->processes);
+ p->cred = p->real_cred = get_cred(new);
+ return 0;
+
+error_put:
+ put_cred(new);
+ return ret;
+}
+
+/**
+ * commit_creds - Install new credentials upon the current task
+ * @new: The credentials to be assigned
+ *
+ * Install a new set of credentials to the current task, using RCU to replace
+ * the old set. Both the objective and the subjective credentials pointers are
+ * updated. This function may not be called if the subjective credentials are
+ * in an overridden state.
+ *
+ * This function eats the caller's reference to the new credentials.
+ *
+ * Always returns 0 thus allowing this function to be tail-called at the end
+ * of, say, sys_setgid().
+ */
+int commit_creds(struct cred *new)
+{
+ struct task_struct *task = current;
+ const struct cred *old;
+
+ BUG_ON(task->cred != task->real_cred);
+ BUG_ON(atomic_read(&task->real_cred->usage) < 2);
+ BUG_ON(atomic_read(&new->usage) < 1);
+
+ old = task->real_cred;
+ security_commit_creds(new, old);
+
+ 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 ||
+ !cap_issubset(new->cap_permitted, old->cap_permitted)) {
+ set_dumpable(task->mm, suid_dumpable);
+ task->pdeath_signal = 0;
+ smp_wmb();
+ }
+
+ /* alter the thread keyring */
+ if (new->fsuid != old->fsuid)
+ key_fsuid_changed(task);
+ if (new->fsgid != old->fsgid)
+ key_fsgid_changed(task);
+
+ /* do it
+ * - What if a process setreuid()'s and this brings the
+ * new uid over his NPROC rlimit? We can check this now
+ * cheaply with the new uid cache, so if it matters
+ * we should be checking for it. -DaveM
+ */
+ if (new->user != old->user)
+ atomic_inc(&new->user->processes);
+ rcu_assign_pointer(task->real_cred, new);
+ rcu_assign_pointer(task->cred, new);
+ if (new->user != old->user)
+ atomic_dec(&old->user->processes);
+
+ sched_switch_user(task);
+
+ /* send notifications */
+ if (new->uid != old->uid ||
+ new->euid != old->euid ||
+ new->suid != old->suid ||
+ 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)
+ proc_id_connector(task, PROC_EVENT_GID);
+
+ /* release the old obj and subj refs both */
+ put_cred(old);
+ put_cred(old);
+ return 0;
+}
+EXPORT_SYMBOL(commit_creds);
+
+/**
+ * abort_creds - Discard a set of credentials and unlock the current task
+ * @new: The credentials that were going to be applied
+ *
+ * Discard a set of credentials that were under construction and unlock the
+ * current task.
+ */
+void abort_creds(struct cred *new)
+{
+ BUG_ON(atomic_read(&new->usage) < 1);
+ put_cred(new);
+}
+EXPORT_SYMBOL(abort_creds);
+
+/**
+ * override_creds - Override the current process's subjective credentials
+ * @new: The credentials to be assigned
+ *
+ * Install a set of temporary override subjective credentials on the current
+ * process, returning the old set for later reversion.
+ */
+const struct cred *override_creds(const struct cred *new)
+{
+ const struct cred *old = current->cred;
+
+ rcu_assign_pointer(current->cred, get_cred(new));
+ return old;
+}
+EXPORT_SYMBOL(override_creds);
+
+/**
+ * revert_creds - Revert a temporary subjective credentials override
+ * @old: The credentials to be restored
+ *
+ * Revert a temporary set of override subjective credentials to an old set,
+ * discarding the override set.
+ */
+void revert_creds(const struct cred *old)
+{
+ const struct cred *override = current->cred;
+
+ rcu_assign_pointer(current->cred, old);
+ put_cred(override);
+}
+EXPORT_SYMBOL(revert_creds);
+
+/*
+ * initialise the credentials stuff
+ */
+void __init cred_init(void)
+{
+ /* allocate a slab in which we can store credentials */
+ cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred),
+ 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+}
+
+/**
+ * prepare_kernel_cred - Prepare a set of credentials for a kernel service
+ * @daemon: A userspace daemon to be used as a reference
+ *
+ * Prepare a set of credentials for a kernel service. This can then be used to
+ * override a task's own credentials so that work can be done on behalf of that
+ * task that requires a different subjective context.
+ *
+ * @daemon is used to provide a base for the security record, but can be NULL.
+ * If @daemon is supplied, then the security data will be derived from that;
+ * otherwise they'll be set to 0 and no groups, full capabilities and no keys.
+ *
+ * The caller may change these controls afterwards if desired.
+ *
+ * Returns the new credentials or NULL if out of memory.
+ *
+ * Does not take, and does not return holding current->cred_replace_mutex.
+ */
+struct cred *prepare_kernel_cred(struct task_struct *daemon)
+{
+ const struct cred *old;
+ struct cred *new;
+
+ new = kmem_cache_alloc(cred_jar, GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ if (daemon)
+ old = get_task_cred(daemon);
+ else
+ old = get_cred(&init_cred);
+
+ get_uid(new->user);
+ get_group_info(new->group_info);
+
+#ifdef CONFIG_KEYS
+ atomic_inc(&init_tgcred.usage);
+ new->tgcred = &init_tgcred;
+ new->request_key_auth = NULL;
+ new->thread_keyring = NULL;
+ new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING;
+#endif
+
+#ifdef CONFIG_SECURITY
+ new->security = NULL;
+#endif
+ if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ goto error;
+
+ atomic_set(&new->usage, 1);
+ put_cred(old);
+ return new;
+
+error:
+ put_cred(new);
+ return NULL;
+}
+EXPORT_SYMBOL(prepare_kernel_cred);
+
+/**
+ * set_security_override - Set the security ID in a set of credentials
+ * @new: The credentials to alter
+ * @secid: The LSM security ID to set
+ *
+ * Set the LSM security ID in a set of credentials so that the subjective
+ * security is overridden when an alternative set of credentials is used.
+ */
+int set_security_override(struct cred *new, u32 secid)
+{
+ return security_kernel_act_as(new, secid);
+}
+EXPORT_SYMBOL(set_security_override);
+
+/**
+ * set_security_override_from_ctx - Set the security ID in a set of credentials
+ * @new: The credentials to alter
+ * @secctx: The LSM security context to generate the security ID from.
+ *
+ * Set the LSM security ID in a set of credentials so that the subjective
+ * security is overridden when an alternative set of credentials is used. The
+ * security ID is specified in string form as a security context to be
+ * interpreted by the LSM.
+ */
+int set_security_override_from_ctx(struct cred *new, const char *secctx)
+{
+ u32 secid;
+ int ret;
+
+ ret = security_secctx_to_secid(secctx, strlen(secctx), &secid);
+ if (ret < 0)
+ return ret;
+
+ return set_security_override(new, secid);
+}
+EXPORT_SYMBOL(set_security_override_from_ctx);
+
+/**
+ * set_create_files_as - Set the LSM file create context in a set of credentials
+ * @new: The credentials to alter
+ * @inode: The inode to take the context from
+ *
+ * Change the LSM file creation context in a set of credentials to be the same
+ * as the object context of the specified inode, so that the new inodes have
+ * the same MAC context as that inode.
+ */
+int set_create_files_as(struct cred *new, struct inode *inode)
+{
+ new->fsuid = inode->i_uid;
+ new->fsgid = inode->i_gid;
+ return security_kernel_create_files_as(new, inode);
+}
+EXPORT_SYMBOL(set_create_files_as);
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index b3179dad71b..abb6e17505e 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -127,7 +127,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
*/
t1 = tsk->sched_info.pcount;
t2 = tsk->sched_info.run_delay;
- t3 = tsk->sched_info.cpu_time;
+ t3 = tsk->se.sum_exec_runtime;
d->cpu_count += t1;
diff --git a/kernel/exit.c b/kernel/exit.c
index 2d8be7ebb0f..c7422ca9203 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,12 +46,18 @@
#include <linux/blkdev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/tracehook.h>
+#include <linux/init_task.h>
#include <trace/sched.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/pgtable.h>
#include <asm/mmu_context.h>
+#include "cred-internals.h"
+
+DEFINE_TRACE(sched_process_free);
+DEFINE_TRACE(sched_process_exit);
+DEFINE_TRACE(sched_process_wait);
static void exit_mm(struct task_struct * tsk);
@@ -164,7 +170,10 @@ void release_task(struct task_struct * p)
int zap_leader;
repeat:
tracehook_prepare_release_task(p);
- atomic_dec(&p->user->processes);
+ /* don't need to get the RCU readlock here - the process is dead and
+ * can't be modifying its own credentials */
+ atomic_dec(&__task_cred(p)->user->processes);
+
proc_flush_task(p);
write_lock_irq(&tasklist_lock);
tracehook_finish_release_task(p);
@@ -339,12 +348,12 @@ static void reparent_to_kthreadd(void)
/* cpus_allowed? */
/* rt_priority? */
/* signals? */
- security_task_reparent_to_init(current);
memcpy(current->signal->rlim, init_task.signal->rlim,
sizeof(current->signal->rlim));
- atomic_inc(&(INIT_USER->__count));
+
+ atomic_inc(&init_cred.usage);
+ commit_creds(&init_cred);
write_unlock_irq(&tasklist_lock);
- switch_uid(INIT_USER);
}
void __set_special_pids(struct pid *pid)
@@ -1078,7 +1087,6 @@ NORET_TYPE void do_exit(long code)
check_stack_usage();
exit_thread();
cgroup_exit(tsk, 1);
- exit_keys(tsk);
if (group_dead && tsk->signal->leader)
disassociate_ctty(1);
@@ -1123,7 +1131,6 @@ NORET_TYPE void do_exit(long code)
preempt_disable();
/* causes final put_task_struct in finish_task_switch(). */
tsk->state = TASK_DEAD;
-
schedule();
BUG();
/* Avoid "noreturn function does return". */
@@ -1263,12 +1270,12 @@ static int wait_task_zombie(struct task_struct *p, int options,
unsigned long state;
int retval, status, traced;
pid_t pid = task_pid_vnr(p);
+ uid_t uid = __task_cred(p)->uid;
if (!likely(options & WEXITED))
return 0;
if (unlikely(options & WNOWAIT)) {
- uid_t uid = p->uid;
int exit_code = p->exit_code;
int why, status;
@@ -1389,7 +1396,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
if (!retval && infop)
retval = put_user(pid, &infop->si_pid);
if (!retval && infop)
- retval = put_user(p->uid, &infop->si_uid);
+ retval = put_user(uid, &infop->si_uid);
if (!retval)
retval = pid;
@@ -1454,7 +1461,8 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
if (!unlikely(options & WNOWAIT))
p->exit_code = 0;
- uid = p->uid;
+ /* don't need the RCU readlock here as we're holding a spinlock */
+ uid = __task_cred(p)->uid;
unlock_sig:
spin_unlock_irq(&p->sighand->siglock);
if (!exit_code)
@@ -1528,10 +1536,10 @@ static int wait_task_continued(struct task_struct *p, int options,
}
if (!unlikely(options & WNOWAIT))
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
+ uid = __task_cred(p)->uid;
spin_unlock_irq(&p->sighand->siglock);
pid = task_pid_vnr(p);
- uid = p->uid;
get_task_struct(p);
read_unlock(&tasklist_lock);
diff --git a/kernel/extable.c b/kernel/extable.c
index a26cb2e1702..feb0317cf09 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -17,6 +17,7 @@
*/
#include <linux/module.h>
#include <linux/init.h>
+#include <linux/ftrace.h>
#include <asm/uaccess.h>
#include <asm/sections.h>
@@ -40,7 +41,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
return e;
}
-int core_kernel_text(unsigned long addr)
+__notrace_funcgraph int core_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext &&
addr <= (unsigned long)_etext)
@@ -53,7 +54,7 @@ int core_kernel_text(unsigned long addr)
return 0;
}
-int __kernel_text_address(unsigned long addr)
+__notrace_funcgraph int __kernel_text_address(unsigned long addr)
{
if (core_kernel_text(addr))
return 1;
diff --git a/kernel/fork.c b/kernel/fork.c
index 495da2e9a8b..6144b36cd89 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -47,6 +47,7 @@
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/memcontrol.h>
+#include <linux/ftrace.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/acct.h>
@@ -80,6 +81,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
+DEFINE_TRACE(sched_process_fork);
+
int nr_processes(void)
{
int cpu;
@@ -137,6 +140,7 @@ void free_task(struct task_struct *tsk)
prop_local_destroy_single(&tsk->dirties);
free_thread_info(tsk->stack);
rt_mutex_debug_task_free(tsk);
+ ftrace_graph_exit_task(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
@@ -147,9 +151,8 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(atomic_read(&tsk->usage));
WARN_ON(tsk == current);
- security_task_free(tsk);
- free_uid(tsk->user);
- put_group_info(tsk->group_info);
+ put_cred(tsk->real_cred);
+ put_cred(tsk->cred);
delayacct_tsk_free(tsk);
if (!profile_handoff_task(tsk))
@@ -818,12 +821,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
if (!sig)
return -ENOMEM;
- ret = copy_thread_group_keys(tsk);
- if (ret < 0) {
- kmem_cache_free(signal_cachep, sig);
- return ret;
- }
-
atomic_set(&sig->count, 1);
atomic_set(&sig->live, 1);
init_waitqueue_head(&sig->wait_chldexit);
@@ -868,7 +865,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
void __cleanup_signal(struct signal_struct *sig)
{
thread_group_cputime_free(sig);
- exit_thread_group_keys(sig);
tty_kref_put(sig->tty);
kmem_cache_free(signal_cachep, sig);
}
@@ -984,16 +980,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
- if (atomic_read(&p->user->processes) >=
+ if (atomic_read(&p->real_cred->user->processes) >=
p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
- p->user != current->nsproxy->user_ns->root_user)
+ p->real_cred->user != INIT_USER)
goto bad_fork_free;
}
- atomic_inc(&p->user->__count);
- atomic_inc(&p->user->processes);
- get_group_info(p->group_info);
+ retval = copy_creds(p, clone_flags);
+ if (retval < 0)
+ goto bad_fork_free;
/*
* If multiple threads are within copy_process(), then this check
@@ -1048,10 +1044,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
do_posix_clock_monotonic_gettime(&p->start_time);
p->real_start_time = p->start_time;
monotonic_to_bootbased(&p->real_start_time);
-#ifdef CONFIG_SECURITY
- p->security = NULL;
-#endif
- p->cap_bset = current->cap_bset;
p->io_context = NULL;
p->audit_context = NULL;
cgroup_fork(p);
@@ -1092,14 +1084,14 @@ static struct task_struct *copy_process(unsigned long clone_flags,
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
+ if (unlikely(ptrace_reparented(current)))
+ ptrace_fork(p, clone_flags);
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
- if ((retval = security_task_alloc(p)))
- goto bad_fork_cleanup_policy;
if ((retval = audit_alloc(p)))
- goto bad_fork_cleanup_security;
+ goto bad_fork_cleanup_policy;
/* copy all the process information */
if ((retval = copy_semundo(clone_flags, p)))
goto bad_fork_cleanup_audit;
@@ -1113,10 +1105,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_cleanup_sighand;
if ((retval = copy_mm(clone_flags, p)))
goto bad_fork_cleanup_signal;
- if ((retval = copy_keys(clone_flags, p)))
- goto bad_fork_cleanup_mm;
if ((retval = copy_namespaces(clone_flags, p)))
- goto bad_fork_cleanup_keys;
+ goto bad_fork_cleanup_mm;
if ((retval = copy_io(clone_flags, p)))
goto bad_fork_cleanup_namespaces;
retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
@@ -1136,6 +1126,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
}
}
+ ftrace_graph_init_task(p);
+
p->pid = pid_nr(pid);
p->tgid = p->pid;
if (clone_flags & CLONE_THREAD)
@@ -1144,7 +1136,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
if (current->nsproxy != p->nsproxy) {
retval = ns_cgroup_clone(p, pid);
if (retval)
- goto bad_fork_free_pid;
+ goto bad_fork_free_graph;
}
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1237,7 +1229,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
- goto bad_fork_free_pid;
+ goto bad_fork_free_graph;
}
if (clone_flags & CLONE_THREAD) {
@@ -1274,6 +1266,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
cgroup_post_fork(p);
return p;
+bad_fork_free_graph:
+ ftrace_graph_exit_task(p);
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
@@ -1281,8 +1275,6 @@ bad_fork_cleanup_io:
put_io_context(p->io_context);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
-bad_fork_cleanup_keys:
- exit_keys(p);
bad_fork_cleanup_mm:
if (p->mm)
mmput(p->mm);
@@ -1298,8 +1290,6 @@ bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
-bad_fork_cleanup_security:
- security_task_free(p);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
@@ -1312,9 +1302,9 @@ bad_fork_cleanup_cgroup:
bad_fork_cleanup_put_domain:
module_put(task_thread_info(p)->exec_domain->module);
bad_fork_cleanup_count:
- put_group_info(p->group_info);
- atomic_dec(&p->user->processes);
- free_uid(p->user);
+ atomic_dec(&p->cred->user->processes);
+ put_cred(p->real_cred);
+ put_cred(p->cred);
bad_fork_free:
free_task(p);
fork_out:
@@ -1358,6 +1348,21 @@ long do_fork(unsigned long clone_flags,
long nr;
/*
+ * Do some preliminary argument and permissions checking before we
+ * actually start allocating stuff
+ */
+ if (clone_flags & CLONE_NEWUSER) {
+ if (clone_flags & CLONE_THREAD)
+ return -EINVAL;
+ /* hopefully this check will go away when userns support is
+ * complete
+ */
+ if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
+ !capable(CAP_SETGID))
+ return -EPERM;
+ }
+
+ /*
* We hope to recycle these flags after 2.6.26
*/
if (unlikely(clone_flags & CLONE_STOPPED)) {
@@ -1605,8 +1610,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags)
err = -EINVAL;
if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
- CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWUSER|
- CLONE_NEWNET))
+ CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET))
goto bad_unshare_out;
/*
diff --git a/kernel/futex.c b/kernel/futex.c
index 8af10027514..4fe790e89d0 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -439,13 +439,20 @@ static void free_pi_state(struct futex_pi_state *pi_state)
static struct task_struct * futex_find_get_task(pid_t pid)
{
struct task_struct *p;
+ const struct cred *cred = current_cred(), *pcred;
rcu_read_lock();
p = find_task_by_vpid(pid);
- if (!p || ((current->euid != p->euid) && (current->euid != p->uid)))
+ if (!p) {
p = ERR_PTR(-ESRCH);
- else
- get_task_struct(p);
+ } else {
+ pcred = __task_cred(p);
+ if (cred->euid != pcred->euid &&
+ cred->euid != pcred->uid)
+ p = ERR_PTR(-ESRCH);
+ else
+ get_task_struct(p);
+ }
rcu_read_unlock();
@@ -1829,6 +1836,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
{
struct robust_list_head __user *head;
unsigned long ret;
+ const struct cred *cred = current_cred(), *pcred;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
@@ -1844,8 +1852,10 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr,
if (!p)
goto err_unlock;
ret = -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_PTRACE))
+ pcred = __task_cred(p);
+ if (cred->euid != pcred->euid &&
+ cred->euid != pcred->uid &&
+ !capable(CAP_SYS_PTRACE))
goto err_unlock;
head = p->robust_list;
rcu_read_unlock();
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 04ac3a9e42c..d607a5b9ee2 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -135,6 +135,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
{
struct compat_robust_list_head __user *head;
unsigned long ret;
+ const struct cred *cred = current_cred(), *pcred;
if (!futex_cmpxchg_enabled)
return -ENOSYS;
@@ -150,8 +151,10 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
if (!p)
goto err_unlock;
ret = -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_PTRACE))
+ pcred = __task_cred(p);
+ if (cred->euid != pcred->euid &&
+ cred->euid != pcred->uid &&
+ !capable(CAP_SYS_PTRACE))
goto err_unlock;
head = p->compat_robust_list;
read_unlock(&tasklist_lock);
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 7b8b0f21a5b..e694afa0eb8 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -30,20 +30,19 @@
#define all_var 0
#endif
-/* These will be re-linked against their real values during the second link stage */
-extern const unsigned long kallsyms_addresses[] __attribute__((weak));
-extern const u8 kallsyms_names[] __attribute__((weak));
+extern const unsigned long kallsyms_addresses[];
+extern const u8 kallsyms_names[];
/* tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV)
*/
extern const unsigned long kallsyms_num_syms
-__attribute__((weak, section(".rodata")));
+ __attribute__((__section__(".rodata")));
-extern const u8 kallsyms_token_table[] __attribute__((weak));
-extern const u16 kallsyms_token_index[] __attribute__((weak));
+extern const u8 kallsyms_token_table[];
+extern const u16 kallsyms_token_index[];
-extern const unsigned long kallsyms_markers[] __attribute__((weak));
+extern const unsigned long kallsyms_markers[];
static inline int is_kernel_inittext(unsigned long addr)
{
@@ -168,9 +167,6 @@ static unsigned long get_symbol_pos(unsigned long addr,
unsigned long symbol_start = 0, symbol_end = 0;
unsigned long i, low, high, mid;
- /* This kernel should never had been booted. */
- BUG_ON(!kallsyms_addresses);
-
/* do a binary search on the sorted kallsyms_addresses array */
low = 0;
high = kallsyms_num_syms;
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 3d3c3ea3a02..b46dbb90866 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -118,10 +118,10 @@ EXPORT_SYMBOL(request_module);
struct subprocess_info {
struct work_struct work;
struct completion *complete;
+ struct cred *cred;
char *path;
char **argv;
char **envp;
- struct key *ring;
enum umh_wait wait;
int retval;
struct file *stdin;
@@ -134,19 +134,20 @@ struct subprocess_info {
static int ____call_usermodehelper(void *data)
{
struct subprocess_info *sub_info = data;
- struct key *new_session, *old_session;
int retval;
- /* Unblock all signals and set the session keyring. */
- new_session = key_get(sub_info->ring);
+ BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+
+ /* Unblock all signals */
spin_lock_irq(&current->sighand->siglock);
- old_session = __install_session_keyring(current, new_session);
flush_signal_handlers(current, 1);
sigemptyset(&current->blocked);
recalc_sigpending();
spin_unlock_irq(&current->sighand->siglock);
- key_put(old_session);
+ /* Install the credentials */
+ commit_creds(sub_info->cred);
+ sub_info->cred = NULL;
/* Install input pipe when needed */
if (sub_info->stdin) {
@@ -185,6 +186,8 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info)
{
if (info->cleanup)
(*info->cleanup)(info->argv, info->envp);
+ if (info->cred)
+ put_cred(info->cred);
kfree(info);
}
EXPORT_SYMBOL(call_usermodehelper_freeinfo);
@@ -240,6 +243,8 @@ static void __call_usermodehelper(struct work_struct *work)
pid_t pid;
enum umh_wait wait = sub_info->wait;
+ BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+
/* CLONE_VFORK: wait until the usermode helper has execve'd
* successfully We need the data structures to stay around
* until that is done. */
@@ -362,6 +367,9 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv,
sub_info->path = path;
sub_info->argv = argv;
sub_info->envp = envp;
+ sub_info->cred = prepare_usermodehelper_creds();
+ if (!sub_info->cred)
+ return NULL;
out:
return sub_info;
@@ -376,7 +384,13 @@ EXPORT_SYMBOL(call_usermodehelper_setup);
void call_usermodehelper_setkeys(struct subprocess_info *info,
struct key *session_keyring)
{
- info->ring = session_keyring;
+#ifdef CONFIG_KEYS
+ struct thread_group_cred *tgcred = info->cred->tgcred;
+ key_put(tgcred->session_keyring);
+ tgcred->session_keyring = key_get(session_keyring);
+#else
+ BUG();
+#endif
}
EXPORT_SYMBOL(call_usermodehelper_setkeys);
@@ -444,6 +458,8 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info,
DECLARE_COMPLETION_ONSTACK(done);
int retval = 0;
+ BUG_ON(atomic_read(&sub_info->cred->usage) != 1);
+
helper_lock();
if (sub_info->path[0] == '\0')
goto out;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 8e7a7ce3ed0..4fbc456f393 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
+DEFINE_TRACE(sched_kthread_stop);
+DEFINE_TRACE(sched_kthread_stop_ret);
+
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 46a404173db..74b1878b8bb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -25,6 +25,7 @@
* Thanks to Arjan van de Ven for coming up with the initial idea of
* mapping lock dependencies runtime.
*/
+#define DISABLE_BRANCH_PROFILING
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/delay.h>
diff --git a/kernel/marker.c b/kernel/marker.c
index e9c6b2bc940..ea54f264786 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -43,6 +43,7 @@ static DEFINE_MUTEX(markers_mutex);
*/
#define MARKER_HASH_BITS 6
#define MARKER_TABLE_SIZE (1 << MARKER_HASH_BITS)
+static struct hlist_head marker_table[MARKER_TABLE_SIZE];
/*
* Note about RCU :
@@ -64,11 +65,10 @@ struct marker_entry {
void *oldptr;
int rcu_pending;
unsigned char ptype:1;
+ unsigned char format_allocated:1;
char name[0]; /* Contains name'\0'format'\0' */
};
-static struct hlist_head marker_table[MARKER_TABLE_SIZE];
-
/**
* __mark_empty_function - Empty probe callback
* @probe_private: probe private data
@@ -81,7 +81,7 @@ static struct hlist_head marker_table[MARKER_TABLE_SIZE];
* though the function pointer change and the marker enabling are two distinct
* operations that modifies the execution flow of preemptible code.
*/
-void __mark_empty_function(void *probe_private, void *call_private,
+notrace void __mark_empty_function(void *probe_private, void *call_private,
const char *fmt, va_list *args)
{
}
@@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function);
* need to put a full smp_rmb() in this branch. This is why we do not use
* rcu_dereference() for the pointer read.
*/
-void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
+notrace void marker_probe_cb(const struct marker *mdata,
+ void *call_private, ...)
{
va_list args;
char ptype;
@@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
* sure the teardown of the callbacks can be done correctly when they
* are in modules and they insure RCU read coherency.
*/
- rcu_read_lock_sched();
+ rcu_read_lock_sched_notrace();
ptype = mdata->ptype;
if (likely(!ptype)) {
marker_probe_func *func;
@@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
va_end(args);
}
}
- rcu_read_unlock_sched();
+ rcu_read_unlock_sched_notrace();
}
EXPORT_SYMBOL_GPL(marker_probe_cb);
@@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb);
*
* Should be connected to markers "MARK_NOARGS".
*/
-void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
+static notrace void marker_probe_cb_noarg(const struct marker *mdata,
+ void *call_private, ...)
{
va_list args; /* not initialized */
char ptype;
- rcu_read_lock_sched();
+ rcu_read_lock_sched_notrace();
ptype = mdata->ptype;
if (likely(!ptype)) {
marker_probe_func *func;
@@ -195,9 +197,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
multi[i].func(multi[i].probe_private, call_private,
mdata->format, &args);
}
- rcu_read_unlock_sched();
+ rcu_read_unlock_sched_notrace();
}
-EXPORT_SYMBOL_GPL(marker_probe_cb_noarg);
static void free_old_closure(struct rcu_head *head)
{
@@ -416,6 +417,7 @@ static struct marker_entry *add_marker(const char *name, const char *format)
e->single.probe_private = NULL;
e->multi = NULL;
e->ptype = 0;
+ e->format_allocated = 0;
e->refcount = 0;
e->rcu_pending = 0;
hlist_add_head(&e->hlist, head);
@@ -447,6 +449,8 @@ static int remove_marker(const char *name)
if (e->single.func != __mark_empty_function)
return -EBUSY;
hlist_del(&e->hlist);
+ if (e->format_allocated)
+ kfree(e->format);
/* Make sure the call_rcu has been executed */
if (e->rcu_pending)
rcu_barrier_sched();
@@ -457,57 +461,34 @@ static int remove_marker(const char *name)
/*
* Set the mark_entry format to the format found in the element.
*/
-static int marker_set_format(struct marker_entry **entry, const char *format)
+static int marker_set_format(struct marker_entry *entry, const char *format)
{
- struct marker_entry *e;
- size_t name_len = strlen((*entry)->name) + 1;
- size_t format_len = strlen(format) + 1;
-
-
- e = kmalloc(sizeof(struct marker_entry) + name_len + format_len,
- GFP_KERNEL);
- if (!e)
+ entry->format = kstrdup(format, GFP_KERNEL);
+ if (!entry->format)
return -ENOMEM;
- memcpy(&e->name[0], (*entry)->name, name_len);
- e->format = &e->name[name_len];
- memcpy(e->format, format, format_len);
- if (strcmp(e->format, MARK_NOARGS) == 0)
- e->call = marker_probe_cb_noarg;
- else
- e->call = marker_probe_cb;
- e->single = (*entry)->single;
- e->multi = (*entry)->multi;
- e->ptype = (*entry)->ptype;
- e->refcount = (*entry)->refcount;
- e->rcu_pending = 0;
- hlist_add_before(&e->hlist, &(*entry)->hlist);
- hlist_del(&(*entry)->hlist);
- /* Make sure the call_rcu has been executed */
- if ((*entry)->rcu_pending)
- rcu_barrier_sched();
- kfree(*entry);
- *entry = e;
+ entry->format_allocated = 1;
+
trace_mark(core_marker_format, "name %s format %s",
- e->name, e->format);
+ entry->name, entry->format);
return 0;
}
/*
* Sets the probe callback corresponding to one marker.
*/
-static int set_marker(struct marker_entry **entry, struct marker *elem,
+static int set_marker(struct marker_entry *entry, struct marker *elem,
int active)
{
- int ret;
- WARN_ON(strcmp((*entry)->name, elem->name) != 0);
+ int ret = 0;
+ WARN_ON(strcmp(entry->name, elem->name) != 0);
- if ((*entry)->format) {
- if (strcmp((*entry)->format, elem->format) != 0) {
+ if (entry->format) {
+ if (strcmp(entry->format, elem->format) != 0) {
printk(KERN_NOTICE
"Format mismatch for probe %s "
"(%s), marker (%s)\n",
- (*entry)->name,
- (*entry)->format,
+ entry->name,
+ entry->format,
elem->format);
return -EPERM;
}
@@ -523,37 +504,67 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
* pass from a "safe" callback (with argument) to an "unsafe"
* callback (does not set arguments).
*/
- elem->call = (*entry)->call;
+ elem->call = entry->call;
/*
* Sanity check :
* We only update the single probe private data when the ptr is
* set to a _non_ single probe! (0 -> 1 and N -> 1, N != 1)
*/
WARN_ON(elem->single.func != __mark_empty_function
- && elem->single.probe_private
- != (*entry)->single.probe_private &&
- !elem->ptype);
- elem->single.probe_private = (*entry)->single.probe_private;
+ && elem->single.probe_private != entry->single.probe_private
+ && !elem->ptype);
+ elem->single.probe_private = entry->single.probe_private;
/*
* Make sure the private data is valid when we update the
* single probe ptr.
*/
smp_wmb();
- elem->single.func = (*entry)->single.func;
+ elem->single.func = entry->single.func;
/*
* We also make sure that the new probe callbacks array is consistent
* before setting a pointer to it.
*/
- rcu_assign_pointer(elem->multi, (*entry)->multi);
+ rcu_assign_pointer(elem->multi, entry->multi);
/*
* Update the function or multi probe array pointer before setting the
* ptype.
*/
smp_wmb();
- elem->ptype = (*entry)->ptype;
+ elem->ptype = entry->ptype;
+
+ if (elem->tp_name && (active ^ elem->state)) {
+ WARN_ON(!elem->tp_cb);
+ /*
+ * It is ok to directly call the probe registration because type
+ * checking has been done in the __trace_mark_tp() macro.
+ */
+
+ if (active) {
+ /*
+ * try_module_get should always succeed because we hold
+ * lock_module() to get the tp_cb address.
+ */
+ ret = try_module_get(__module_text_address(
+ (unsigned long)elem->tp_cb));
+ BUG_ON(!ret);
+ ret = tracepoint_probe_register_noupdate(
+ elem->tp_name,
+ elem->tp_cb);
+ } else {
+ ret = tracepoint_probe_unregister_noupdate(
+ elem->tp_name,
+ elem->tp_cb);
+ /*
+ * tracepoint_probe_update_all() must be called
+ * before the module containing tp_cb is unloaded.
+ */
+ module_put(__module_text_address(
+ (unsigned long)elem->tp_cb));
+ }
+ }
elem->state = active;
- return 0;
+ return ret;
}
/*
@@ -564,7 +575,24 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
*/
static void disable_marker(struct marker *elem)
{
+ int ret;
+
/* leave "call" as is. It is known statically. */
+ if (elem->tp_name && elem->state) {
+ WARN_ON(!elem->tp_cb);
+ /*
+ * It is ok to directly call the probe registration because type
+ * checking has been done in the __trace_mark_tp() macro.
+ */
+ ret = tracepoint_probe_unregister_noupdate(elem->tp_name,
+ elem->tp_cb);
+ WARN_ON(ret);
+ /*
+ * tracepoint_probe_update_all() must be called
+ * before the module containing tp_cb is unloaded.
+ */
+ module_put(__module_text_address((unsigned long)elem->tp_cb));
+ }
elem->state = 0;
elem->single.func = __mark_empty_function;
/* Update the function before setting the ptype */
@@ -594,8 +622,7 @@ void marker_update_probe_range(struct marker *begin,
for (iter = begin; iter < end; iter++) {
mark_entry = get_marker(iter->name);
if (mark_entry) {
- set_marker(&mark_entry, iter,
- !!mark_entry->refcount);
+ set_marker(mark_entry, iter, !!mark_entry->refcount);
/*
* ignore error, continue
*/
@@ -629,6 +656,7 @@ static void marker_update_probes(void)
marker_update_probe_range(__start___markers, __stop___markers);
/* Markers in modules. */
module_update_markers();
+ tracepoint_probe_update_all();
}
/**
@@ -657,7 +685,7 @@ int marker_probe_register(const char *name, const char *format,
ret = PTR_ERR(entry);
} else if (format) {
if (!entry->format)
- ret = marker_set_format(&entry, format);
+ ret = marker_set_format(entry, format);
else if (strcmp(entry->format, format))
ret = -EPERM;
}
@@ -676,10 +704,11 @@ int marker_probe_register(const char *name, const char *format,
goto end;
}
mutex_unlock(&markers_mutex);
- marker_update_probes(); /* may update entry */
+ marker_update_probes();
mutex_lock(&markers_mutex);
entry = get_marker(name);
- WARN_ON(!entry);
+ if (!entry)
+ goto end;
if (entry->rcu_pending)
rcu_barrier_sched();
entry->oldptr = old;
@@ -720,7 +749,7 @@ int marker_probe_unregister(const char *name,
rcu_barrier_sched();
old = marker_entry_remove_probe(entry, probe, probe_private);
mutex_unlock(&markers_mutex);
- marker_update_probes(); /* may update entry */
+ marker_update_probes();
mutex_lock(&markers_mutex);
entry = get_marker(name);
if (!entry)
@@ -801,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
rcu_barrier_sched();
old = marker_entry_remove_probe(entry, NULL, probe_private);
mutex_unlock(&markers_mutex);
- marker_update_probes(); /* may update entry */
+ marker_update_probes();
mutex_lock(&markers_mutex);
entry = get_marker_from_private_data(probe, probe_private);
- WARN_ON(!entry);
+ if (!entry)
+ goto end;
if (entry->rcu_pending)
rcu_barrier_sched();
entry->oldptr = old;
@@ -848,8 +878,6 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
if (!e->ptype) {
if (num == 0 && e->single.func == probe)
return e->single.probe_private;
- else
- break;
} else {
struct marker_probe_closure *closure;
int match = 0;
@@ -861,8 +889,42 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
return closure[i].probe_private;
}
}
+ break;
}
}
return ERR_PTR(-ENOENT);
}
EXPORT_SYMBOL_GPL(marker_get_private_data);
+
+#ifdef CONFIG_MODULES
+
+int marker_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ marker_update_probe_range(mod->markers,
+ mod->markers + mod->num_markers);
+ break;
+ case MODULE_STATE_GOING:
+ marker_update_probe_range(mod->markers,
+ mod->markers + mod->num_markers);
+ break;
+ }
+ return 0;
+}
+
+struct notifier_block marker_module_nb = {
+ .notifier_call = marker_module_notify,
+ .priority = 0,
+};
+
+static int init_markers(void)
+{
+ return register_module_notifier(&marker_module_nb);
+}
+__initcall(init_markers);
+
+#endif /* CONFIG_MODULES */
diff --git a/kernel/module.c b/kernel/module.c
index 1f4cc00e0c2..dd2a54155b5 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2184,24 +2184,15 @@ static noinline struct module *load_module(void __user *umod,
struct mod_debug *debug;
unsigned int num_debug;
-#ifdef CONFIG_MARKERS
- marker_update_probe_range(mod->markers,
- mod->markers + mod->num_markers);
-#endif
debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
sizeof(*debug), &num_debug);
dynamic_printk_setup(debug, num_debug);
-
-#ifdef CONFIG_TRACEPOINTS
- tracepoint_update_probe_range(mod->tracepoints,
- mod->tracepoints + mod->num_tracepoints);
-#endif
}
/* sechdrs[0].sh_size is always zero */
mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
sizeof(*mseg), &num_mcount);
- ftrace_init_module(mseg, mseg + num_mcount);
+ ftrace_init_module(mod, mseg, mseg + num_mcount);
err = module_finalize(hdr, sechdrs, mod);
if (err < 0)
@@ -2713,7 +2704,7 @@ int is_module_address(unsigned long addr)
/* Is this a valid kernel address? */
-struct module *__module_text_address(unsigned long addr)
+__notrace_funcgraph struct module *__module_text_address(unsigned long addr)
{
struct module *mod;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 1d3ef29a258..63598dca2d0 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -80,12 +80,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
goto out_pid;
}
- new_nsp->user_ns = copy_user_ns(flags, tsk->nsproxy->user_ns);
- if (IS_ERR(new_nsp->user_ns)) {
- err = PTR_ERR(new_nsp->user_ns);
- goto out_user;
- }
-
new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns);
if (IS_ERR(new_nsp->net_ns)) {
err = PTR_ERR(new_nsp->net_ns);
@@ -95,9 +89,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
return new_nsp;
out_net:
- if (new_nsp->user_ns)
- put_user_ns(new_nsp->user_ns);
-out_user:
if (new_nsp->pid_ns)
put_pid_ns(new_nsp->pid_ns);
out_pid:
@@ -130,7 +121,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
get_nsproxy(old_ns);
if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
- CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWNET)))
+ CLONE_NEWPID | CLONE_NEWNET)))
return 0;
if (!capable(CAP_SYS_ADMIN)) {
@@ -173,8 +164,6 @@ void free_nsproxy(struct nsproxy *ns)
put_ipc_ns(ns->ipc_ns);
if (ns->pid_ns)
put_pid_ns(ns->pid_ns);
- if (ns->user_ns)
- put_user_ns(ns->user_ns);
put_net(ns->net_ns);
kmem_cache_free(nsproxy_cachep, ns);
}
@@ -189,7 +178,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
int err = 0;
if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
- CLONE_NEWUSER | CLONE_NEWNET)))
+ CLONE_NEWNET)))
return 0;
if (!capable(CAP_SYS_ADMIN))
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 5e79c662294..a140e44eebb 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -197,6 +197,11 @@ static int common_timer_create(struct k_itimer *new_timer)
return 0;
}
+static int no_timer_create(struct k_itimer *new_timer)
+{
+ return -EOPNOTSUPP;
+}
+
/*
* Return nonzero if we know a priori this clockid_t value is bogus.
*/
@@ -248,6 +253,7 @@ static __init int init_posix_timers(void)
.clock_getres = hrtimer_get_res,
.clock_get = posix_get_monotonic_raw,
.clock_set = do_posix_clock_nosettime,
+ .timer_create = no_timer_create,
};
register_posix_clock(CLOCK_REALTIME, &clock_realtime);
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index c9d74083746..f77d3819ef5 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -22,7 +22,6 @@
#include <linux/console.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
-#include <linux/ftrace.h>
#include "power.h"
@@ -257,7 +256,7 @@ static int create_image(int platform_mode)
int hibernation_snapshot(int platform_mode)
{
- int error, ftrace_save;
+ int error;
/* Free memory before shutting down devices. */
error = swsusp_shrink_memory();
@@ -269,7 +268,6 @@ int hibernation_snapshot(int platform_mode)
goto Close;
suspend_console();
- ftrace_save = __ftrace_enabled_save();
error = device_suspend(PMSG_FREEZE);
if (error)
goto Recover_platform;
@@ -299,7 +297,6 @@ int hibernation_snapshot(int platform_mode)
Resume_devices:
device_resume(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
- __ftrace_enabled_restore(ftrace_save);
resume_console();
Close:
platform_end(platform_mode);
@@ -370,11 +367,10 @@ static int resume_target_kernel(void)
int hibernation_restore(int platform_mode)
{
- int error, ftrace_save;
+ int error;
pm_prepare_console();
suspend_console();
- ftrace_save = __ftrace_enabled_save();
error = device_suspend(PMSG_QUIESCE);
if (error)
goto Finish;
@@ -389,7 +385,6 @@ int hibernation_restore(int platform_mode)
platform_restore_cleanup(platform_mode);
device_resume(PMSG_RECOVER);
Finish:
- __ftrace_enabled_restore(ftrace_save);
resume_console();
pm_restore_console();
return error;
@@ -402,7 +397,7 @@ int hibernation_restore(int platform_mode)
int hibernation_platform_enter(void)
{
- int error, ftrace_save;
+ int error;
if (!hibernation_ops)
return -ENOSYS;
@@ -417,7 +412,6 @@ int hibernation_platform_enter(void)
goto Close;
suspend_console();
- ftrace_save = __ftrace_enabled_save();
error = device_suspend(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
@@ -452,7 +446,6 @@ int hibernation_platform_enter(void)
hibernation_ops->finish();
Resume_devices:
device_resume(PMSG_RESTORE);
- __ftrace_enabled_restore(ftrace_save);
resume_console();
Close:
hibernation_ops->end();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b8f7ce9473e..613f16941b8 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -22,7 +22,6 @@
#include <linux/freezer.h>
#include <linux/vmstat.h>
#include <linux/syscalls.h>
-#include <linux/ftrace.h>
#include "power.h"
@@ -317,7 +316,7 @@ static int suspend_enter(suspend_state_t state)
*/
int suspend_devices_and_enter(suspend_state_t state)
{
- int error, ftrace_save;
+ int error;
if (!suspend_ops)
return -ENOSYS;
@@ -328,7 +327,6 @@ int suspend_devices_and_enter(suspend_state_t state)
goto Close;
}
suspend_console();
- ftrace_save = __ftrace_enabled_save();
suspend_test_start();
error = device_suspend(PMSG_SUSPEND);
if (error) {
@@ -360,7 +358,6 @@ int suspend_devices_and_enter(suspend_state_t state)
suspend_test_start();
device_resume(PMSG_RESUME);
suspend_test_finish("resume devices");
- __ftrace_enabled_restore(ftrace_save);
resume_console();
Close:
if (suspend_ops->end)
diff --git a/kernel/profile.c b/kernel/profile.c
index 7d620dfdde5..4cb7d68fed8 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = {
};
#ifdef CONFIG_SMP
-static inline void profile_nop(void *unused)
+static void profile_nop(void *unused)
{
}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4c8bcd7dd8e..29dc700e198 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -25,6 +25,17 @@
#include <asm/pgtable.h>
#include <asm/uaccess.h>
+
+/*
+ * Initialize a new task whose father had been ptraced.
+ *
+ * Called from copy_process().
+ */
+void ptrace_fork(struct task_struct *child, unsigned long clone_flags)
+{
+ arch_ptrace_fork(child, clone_flags);
+}
+
/*
* ptrace a task: make the debugger its new parent and
* move it to the ptrace list.
@@ -72,6 +83,7 @@ void __ptrace_unlink(struct task_struct *child)
child->parent = child->real_parent;
list_del_init(&child->ptrace_entry);
+ arch_ptrace_untrace(child);
if (task_is_traced(child))
ptrace_untrace(child);
}
@@ -115,6 +127,8 @@ int ptrace_check_attach(struct task_struct *child, int kill)
int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
+ const struct cred *cred = current_cred(), *tcred;
+
/* May we inspect the given task?
* This check is used both for attaching with ptrace
* and for allowing access to sensitive information in /proc.
@@ -127,13 +141,19 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode)
/* Don't let security modules deny introspection */
if (task == current)
return 0;
- if (((current->uid != task->euid) ||
- (current->uid != task->suid) ||
- (current->uid != task->uid) ||
- (current->gid != task->egid) ||
- (current->gid != task->sgid) ||
- (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE))
+ rcu_read_lock();
+ tcred = __task_cred(task);
+ if ((cred->uid != tcred->euid ||
+ cred->uid != tcred->suid ||
+ cred->uid != tcred->uid ||
+ cred->gid != tcred->egid ||
+ cred->gid != tcred->sgid ||
+ cred->gid != tcred->gid) &&
+ !capable(CAP_SYS_PTRACE)) {
+ rcu_read_unlock();
return -EPERM;
+ }
+ rcu_read_unlock();
smp_rmb();
if (task->mm)
dumpable = get_dumpable(task->mm);
@@ -163,6 +183,14 @@ int ptrace_attach(struct task_struct *task)
if (same_thread_group(task, current))
goto out;
+ /* Protect exec's credential calculations against our interference;
+ * SUID, SGID and LSM creds get determined differently under ptrace.
+ */
+ retval = mutex_lock_interruptible(&current->cred_exec_mutex);
+ if (retval < 0)
+ goto out;
+
+ retval = -EPERM;
repeat:
/*
* Nasty, nasty.
@@ -202,6 +230,7 @@ repeat:
bad:
write_unlock_irqrestore(&tasklist_lock, flags);
task_unlock(task);
+ mutex_unlock(&current->cred_exec_mutex);
out:
return retval;
}
diff --git a/kernel/sched.c b/kernel/sched.c
index 42929239830..bdd180a0c6b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -118,6 +118,12 @@
*/
#define RUNTIME_INF ((u64)~0ULL)
+DEFINE_TRACE(sched_wait_task);
+DEFINE_TRACE(sched_wakeup);
+DEFINE_TRACE(sched_wakeup_new);
+DEFINE_TRACE(sched_switch);
+DEFINE_TRACE(sched_migrate_task);
+
#ifdef CONFIG_SMP
/*
* Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
@@ -261,6 +267,10 @@ struct task_group {
struct cgroup_subsys_state css;
#endif
+#ifdef CONFIG_USER_SCHED
+ uid_t uid;
+#endif
+
#ifdef CONFIG_FAIR_GROUP_SCHED
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
@@ -286,6 +296,12 @@ struct task_group {
#ifdef CONFIG_USER_SCHED
+/* Helper function to pass uid information to create_sched_user() */
+void set_tg_uid(struct user_struct *user)
+{
+ user->tg->uid = user->uid;
+}
+
/*
* Root task group.
* Every UID task group (including init_task_group aka UID-0) will
@@ -345,7 +361,9 @@ static inline struct task_group *task_group(struct task_struct *p)
struct task_group *tg;
#ifdef CONFIG_USER_SCHED
- tg = p->user->tg;
+ rcu_read_lock();
+ tg = __task_cred(p)->user->tg;
+ rcu_read_unlock();
#elif defined(CONFIG_CGROUP_SCHED)
tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
struct task_group, css);
@@ -586,6 +604,8 @@ struct rq {
#ifdef CONFIG_SCHEDSTATS
/* latency stats */
struct sched_info rq_sched_info;
+ unsigned long long rq_cpu_time;
+ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
unsigned int yld_exp_empty;
@@ -703,45 +723,18 @@ static __read_mostly char *sched_feat_names[] = {
#undef SCHED_FEAT
-static int sched_feat_open(struct inode *inode, struct file *filp)
-{
- filp->private_data = inode->i_private;
- return 0;
-}
-
-static ssize_t
-sched_feat_read(struct file *filp, char __user *ubuf,
- size_t cnt, loff_t *ppos)
+static int sched_feat_show(struct seq_file *m, void *v)
{
- char *buf;
- int r = 0;
- int len = 0;
int i;
for (i = 0; sched_feat_names[i]; i++) {
- len += strlen(sched_feat_names[i]);
- len += 4;
- }
-
- buf = kmalloc(len + 2, GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- for (i = 0; sched_feat_names[i]; i++) {
- if (sysctl_sched_features & (1UL << i))
- r += sprintf(buf + r, "%s ", sched_feat_names[i]);
- else
- r += sprintf(buf + r, "NO_%s ", sched_feat_names[i]);
+ if (!(sysctl_sched_features & (1UL << i)))
+ seq_puts(m, "NO_");
+ seq_printf(m, "%s ", sched_feat_names[i]);
}
+ seq_puts(m, "\n");
- r += sprintf(buf + r, "\n");
- WARN_ON(r >= len + 2);
-
- r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-
- kfree(buf);
-
- return r;
+ return 0;
}
static ssize_t
@@ -786,10 +779,17 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
return cnt;
}
+static int sched_feat_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, sched_feat_show, NULL);
+}
+
static struct file_operations sched_feat_fops = {
- .open = sched_feat_open,
- .read = sched_feat_read,
- .write = sched_feat_write,
+ .open = sched_feat_open,
+ .write = sched_feat_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
};
static __init int sched_init_debug(void)
@@ -1474,27 +1474,13 @@ static void
update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long sd_shares, unsigned long sd_rq_weight)
{
- int boost = 0;
unsigned long shares;
unsigned long rq_weight;
if (!tg->se[cpu])
return;
- rq_weight = tg->cfs_rq[cpu]->load.weight;
-
- /*
- * If there are currently no tasks on the cpu pretend there is one of
- * average load so that when a new task gets to run here it will not
- * get delayed by group starvation.
- */
- if (!rq_weight) {
- boost = 1;
- rq_weight = NICE_0_LOAD;
- }
-
- if (unlikely(rq_weight > sd_rq_weight))
- rq_weight = sd_rq_weight;
+ rq_weight = tg->cfs_rq[cpu]->rq_weight;
/*
* \Sum shares * rq_weight
@@ -1502,7 +1488,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
* \Sum rq_weight
*
*/
- shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
+ shares = (sd_shares * rq_weight) / sd_rq_weight;
shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
if (abs(shares - tg->se[cpu]->load.weight) >
@@ -1511,11 +1497,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long flags;
spin_lock_irqsave(&rq->lock, flags);
- /*
- * record the actual number of shares, not the boosted amount.
- */
- tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
- tg->cfs_rq[cpu]->rq_weight = rq_weight;
+ tg->cfs_rq[cpu]->shares = shares;
__set_se_shares(tg->se[cpu], shares);
spin_unlock_irqrestore(&rq->lock, flags);
@@ -1529,13 +1511,23 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long rq_weight = 0;
+ unsigned long weight, rq_weight = 0;
unsigned long shares = 0;
struct sched_domain *sd = data;
int i;
for_each_cpu_mask(i, sd->span) {
- rq_weight += tg->cfs_rq[i]->load.weight;
+ /*
+ * If there are currently no tasks on the cpu pretend there
+ * is one of average load so that when a new task gets to
+ * run here it will not get delayed by group starvation.
+ */
+ weight = tg->cfs_rq[i]->load.weight;
+ if (!weight)
+ weight = NICE_0_LOAD;
+
+ tg->cfs_rq[i]->rq_weight = weight;
+ rq_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
@@ -1545,9 +1537,6 @@ static int tg_shares_up(struct task_group *tg, void *data)
if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
shares = tg->shares;
- if (!rq_weight)
- rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;
-
for_each_cpu_mask(i, sd->span)
update_group_shares_cpu(tg, i, shares, rq_weight);
@@ -1612,6 +1601,39 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
#endif
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(this_rq->lock)
+ __acquires(busiest->lock)
+ __acquires(this_rq->lock)
+{
+ int ret = 0;
+
+ if (unlikely(!irqs_disabled())) {
+ /* printk() doesn't work good under rq->lock */
+ spin_unlock(&this_rq->lock);
+ BUG_ON(1);
+ }
+ if (unlikely(!spin_trylock(&busiest->lock))) {
+ if (busiest < this_rq) {
+ spin_unlock(&this_rq->lock);
+ spin_lock(&busiest->lock);
+ spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+ ret = 1;
+ } else
+ spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+ }
+ return ret;
+}
+
+static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(busiest->lock)
+{
+ spin_unlock(&busiest->lock);
+ lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1845,6 +1867,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
clock_offset = old_rq->clock - new_rq->clock;
+ trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
p->se.wait_start -= clock_offset;
@@ -2254,6 +2278,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
smp_wmb();
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
old_state = p->state;
if (!(old_state & state))
goto out;
@@ -2311,12 +2336,11 @@ out_activate:
schedstat_inc(p, se.nr_wakeups_local);
else
schedstat_inc(p, se.nr_wakeups_remote);
- update_rq_clock(rq);
activate_task(rq, p, 1);
success = 1;
out_running:
- trace_sched_wakeup(rq, p);
+ trace_sched_wakeup(rq, p, success);
check_preempt_curr(rq, p, sync);
p->state = TASK_RUNNING;
@@ -2449,7 +2473,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
p->sched_class->task_new(rq, p);
inc_nr_running(rq);
}
- trace_sched_wakeup_new(rq, p);
+ trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, 0);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
@@ -2812,40 +2836,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
}
/*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
- */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
- __releases(this_rq->lock)
- __acquires(busiest->lock)
- __acquires(this_rq->lock)
-{
- int ret = 0;
-
- if (unlikely(!irqs_disabled())) {
- /* printk() doesn't work good under rq->lock */
- spin_unlock(&this_rq->lock);
- BUG_ON(1);
- }
- if (unlikely(!spin_trylock(&busiest->lock))) {
- if (busiest < this_rq) {
- spin_unlock(&this_rq->lock);
- spin_lock(&busiest->lock);
- spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
- ret = 1;
- } else
- spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
- }
- return ret;
-}
-
-static void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
- __releases(busiest->lock)
-{
- spin_unlock(&busiest->lock);
- lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
-}
-
-/*
* If dest_cpu is allowed for this process, migrate the task to it.
* This is accomplished by forcing the cpu_allowed mask to only
* allow dest_cpu, which will force the cpu onto dest_cpu. Then
@@ -2862,7 +2852,6 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
|| unlikely(!cpu_active(dest_cpu)))
goto out;
- trace_sched_migrate_task(rq, p, dest_cpu);
/* force the process onto the specified CPU */
if (migrate_task(p, dest_cpu, &req)) {
/* Need to wait for migration thread (might exit: take ref). */
@@ -3707,7 +3696,7 @@ out_balanced:
static void idle_balance(int this_cpu, struct rq *this_rq)
{
struct sched_domain *sd;
- int pulled_task = -1;
+ int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
cpumask_t tmpmask;
@@ -5134,6 +5123,22 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
set_load_weight(p);
}
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+ const struct cred *cred = current_cred(), *pcred;
+ bool match;
+
+ rcu_read_lock();
+ pcred = __task_cred(p);
+ match = (cred->euid == pcred->euid ||
+ cred->euid == pcred->uid);
+ rcu_read_unlock();
+ return match;
+}
+
static int __sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param, bool user)
{
@@ -5193,8 +5198,7 @@ recheck:
return -EPERM;
/* can't change other user's priorities */
- if ((current->euid != p->euid) &&
- (current->euid != p->uid))
+ if (!check_same_owner(p))
return -EPERM;
}
@@ -5426,8 +5430,7 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
read_unlock(&tasklist_lock);
retval = -EPERM;
- if ((current->euid != p->euid) && (current->euid != p->uid) &&
- !capable(CAP_SYS_NICE))
+ if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
goto out_unlock;
retval = security_task_setscheduler(p, 0, NULL);
@@ -5896,6 +5899,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
+ ftrace_graph_init_task(idle);
}
/*
@@ -6126,7 +6130,6 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
/*
* Figure out where task on dead CPU should go, use force if necessary.
- * NOTE: interrupts should be disabled by the caller
*/
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
@@ -6638,28 +6641,6 @@ early_initcall(migration_init);
#ifdef CONFIG_SCHED_DEBUG
-static inline const char *sd_level_to_string(enum sched_domain_level lvl)
-{
- switch (lvl) {
- case SD_LV_NONE:
- return "NONE";
- case SD_LV_SIBLING:
- return "SIBLING";
- case SD_LV_MC:
- return "MC";
- case SD_LV_CPU:
- return "CPU";
- case SD_LV_NODE:
- return "NODE";
- case SD_LV_ALLNODES:
- return "ALLNODES";
- case SD_LV_MAX:
- return "MAX";
-
- }
- return "MAX";
-}
-
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
cpumask_t *groupmask)
{
@@ -6679,8 +6660,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
return -1;
}
- printk(KERN_CONT "span %s level %s\n",
- str, sd_level_to_string(sd->level));
+ printk(KERN_CONT "span %s level %s\n", str, sd->name);
if (!cpu_isset(cpu, sd->span)) {
printk(KERN_ERR "ERROR: domain->span does not contain "
@@ -6816,6 +6796,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
SD_BALANCE_EXEC |
SD_SHARE_CPUPOWER |
SD_SHARE_PKG_RESOURCES);
+ if (nr_node_ids == 1)
+ pflags &= ~SD_SERIALIZE;
}
if (~cflags & pflags)
return 0;
@@ -7336,13 +7318,21 @@ struct allmasks {
};
#if NR_CPUS > 128
-#define SCHED_CPUMASK_ALLOC 1
-#define SCHED_CPUMASK_FREE(v) kfree(v)
-#define SCHED_CPUMASK_DECLARE(v) struct allmasks *v
+#define SCHED_CPUMASK_DECLARE(v) struct allmasks *v
+static inline void sched_cpumask_alloc(struct allmasks **masks)
+{
+ *masks = kmalloc(sizeof(**masks), GFP_KERNEL);
+}
+static inline void sched_cpumask_free(struct allmasks *masks)
+{
+ kfree(masks);
+}
#else
-#define SCHED_CPUMASK_ALLOC 0
-#define SCHED_CPUMASK_FREE(v)
-#define SCHED_CPUMASK_DECLARE(v) struct allmasks _v, *v = &_v
+#define SCHED_CPUMASK_DECLARE(v) struct allmasks _v, *v = &_v
+static inline void sched_cpumask_alloc(struct allmasks **masks)
+{ }
+static inline void sched_cpumask_free(struct allmasks *masks)
+{ }
#endif
#define SCHED_CPUMASK_VAR(v, a) cpumask_t *v = (cpumask_t *) \
@@ -7418,9 +7408,8 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
return -ENOMEM;
}
-#if SCHED_CPUMASK_ALLOC
/* get space for all scratch cpumask variables */
- allmasks = kmalloc(sizeof(*allmasks), GFP_KERNEL);
+ sched_cpumask_alloc(&allmasks);
if (!allmasks) {
printk(KERN_WARNING "Cannot alloc cpumask array\n");
kfree(rd);
@@ -7429,7 +7418,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
#endif
return -ENOMEM;
}
-#endif
+
tmpmask = (cpumask_t *)allmasks;
@@ -7683,13 +7672,13 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
cpu_attach_domain(sd, rd, i);
}
- SCHED_CPUMASK_FREE((void *)allmasks);
+ sched_cpumask_free(allmasks);
return 0;
#ifdef CONFIG_NUMA
error:
free_sched_groups(cpu_map, tmpmask);
- SCHED_CPUMASK_FREE((void *)allmasks);
+ sched_cpumask_free(allmasks);
kfree(rd);
return -ENOMEM;
#endif
@@ -7712,8 +7701,14 @@ static struct sched_domain_attr *dattr_cur;
*/
static cpumask_t fallback_doms;
-void __attribute__((weak)) arch_update_cpu_topology(void)
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
{
+ return 0;
}
/*
@@ -7753,8 +7748,6 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
cpumask_t tmpmask;
int i;
- unregister_sched_domain_sysctl();
-
for_each_cpu_mask_nr(i, *cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
@@ -7807,17 +7800,21 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
struct sched_domain_attr *dattr_new)
{
int i, j, n;
+ int new_topology;
mutex_lock(&sched_domains_mutex);
/* always unregister in case we don't destroy any domains */
unregister_sched_domain_sysctl();
+ /* Let architecture update cpu core mappings. */
+ new_topology = arch_update_cpu_topology();
+
n = doms_new ? ndoms_new : 0;
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
- for (j = 0; j < n; j++) {
+ for (j = 0; j < n && !new_topology; j++) {
if (cpus_equal(doms_cur[i], doms_new[j])
&& dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
@@ -7832,12 +7829,12 @@ match1:
ndoms_cur = 0;
doms_new = &fallback_doms;
cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
- dattr_new = NULL;
+ WARN_ON_ONCE(dattr_new);
}
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
- for (j = 0; j < ndoms_cur; j++) {
+ for (j = 0; j < ndoms_cur && !new_topology; j++) {
if (cpus_equal(doms_new[i], doms_cur[j])
&& dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
@@ -8492,7 +8489,7 @@ static
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
struct cfs_rq *cfs_rq;
- struct sched_entity *se, *parent_se;
+ struct sched_entity *se;
struct rq *rq;
int i;
@@ -8508,18 +8505,17 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
for_each_possible_cpu(i) {
rq = cpu_rq(i);
- cfs_rq = kmalloc_node(sizeof(struct cfs_rq),
- GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
+ GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
goto err;
- se = kmalloc_node(sizeof(struct sched_entity),
- GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ se = kzalloc_node(sizeof(struct sched_entity),
+ GFP_KERNEL, cpu_to_node(i));
if (!se)
goto err;
- parent_se = parent ? parent->se[i] : NULL;
- init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent_se);
+ init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
}
return 1;
@@ -8580,7 +8576,7 @@ static
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
struct rt_rq *rt_rq;
- struct sched_rt_entity *rt_se, *parent_se;
+ struct sched_rt_entity *rt_se;
struct rq *rq;
int i;
@@ -8597,18 +8593,17 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
for_each_possible_cpu(i) {
rq = cpu_rq(i);
- rt_rq = kmalloc_node(sizeof(struct rt_rq),
- GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ rt_rq = kzalloc_node(sizeof(struct rt_rq),
+ GFP_KERNEL, cpu_to_node(i));
if (!rt_rq)
goto err;
- rt_se = kmalloc_node(sizeof(struct sched_rt_entity),
- GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
+ GFP_KERNEL, cpu_to_node(i));
if (!rt_se)
goto err;
- parent_se = parent ? parent->rt_se[i] : NULL;
- init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent_se);
+ init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
}
return 1;
@@ -9251,11 +9246,12 @@ struct cgroup_subsys cpu_cgroup_subsys = {
* (balbir@in.ibm.com).
*/
-/* track cpu usage of a group of tasks */
+/* track cpu usage of a group of tasks and its child groups */
struct cpuacct {
struct cgroup_subsys_state css;
/* cpuusage holds pointer to a u64-type object on every cpu */
u64 *cpuusage;
+ struct cpuacct *parent;
};
struct cgroup_subsys cpuacct_subsys;
@@ -9289,6 +9285,9 @@ static struct cgroup_subsys_state *cpuacct_create(
return ERR_PTR(-ENOMEM);
}
+ if (cgrp->parent)
+ ca->parent = cgroup_ca(cgrp->parent);
+
return &ca->css;
}
@@ -9302,6 +9301,41 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
kfree(ca);
}
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+ u64 data;
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ data = *cpuusage;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ data = *cpuusage;
+#endif
+
+ return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+ /*
+ * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+ */
+ spin_lock_irq(&cpu_rq(cpu)->lock);
+ *cpuusage = val;
+ spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+ *cpuusage = val;
+#endif
+}
+
/* return total cpu usage (in nanoseconds) of a group */
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
{
@@ -9309,17 +9343,8 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
u64 totalcpuusage = 0;
int i;
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
-
- /*
- * Take rq->lock to make 64-bit addition safe on 32-bit
- * platforms.
- */
- spin_lock_irq(&cpu_rq(i)->lock);
- totalcpuusage += *cpuusage;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
+ for_each_present_cpu(i)
+ totalcpuusage += cpuacct_cpuusage_read(ca, i);
return totalcpuusage;
}
@@ -9336,23 +9361,39 @@ static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
goto out;
}
- for_each_possible_cpu(i) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, i);
+ for_each_present_cpu(i)
+ cpuacct_cpuusage_write(ca, i, 0);
- spin_lock_irq(&cpu_rq(i)->lock);
- *cpuusage = 0;
- spin_unlock_irq(&cpu_rq(i)->lock);
- }
out:
return err;
}
+static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct cpuacct *ca = cgroup_ca(cgroup);
+ u64 percpu;
+ int i;
+
+ for_each_present_cpu(i) {
+ percpu = cpuacct_cpuusage_read(ca, i);
+ seq_printf(m, "%llu ", (unsigned long long) percpu);
+ }
+ seq_printf(m, "\n");
+ return 0;
+}
+
static struct cftype files[] = {
{
.name = "usage",
.read_u64 = cpuusage_read,
.write_u64 = cpuusage_write,
},
+ {
+ .name = "usage_percpu",
+ .read_seq_string = cpuacct_percpu_seq_read,
+ },
+
};
static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
@@ -9368,14 +9409,16 @@ static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
{
struct cpuacct *ca;
+ int cpu;
if (!cpuacct_subsys.active)
return;
+ cpu = task_cpu(tsk);
ca = task_ca(tsk);
- if (ca) {
- u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk));
+ for (; ca; ca = ca->parent) {
+ u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
*cpuusage += cputime;
}
}
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 81787248b60..e8ab096ddfe 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -118,13 +118,13 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
/*
* scd->clock = clamp(scd->tick_gtod + delta,
- * max(scd->tick_gtod, scd->clock),
- * max(scd->clock, scd->tick_gtod + TICK_NSEC));
+ * max(scd->tick_gtod, scd->clock),
+ * scd->tick_gtod + TICK_NSEC);
*/
clock = scd->tick_gtod + delta;
min_clock = wrap_max(scd->tick_gtod, scd->clock);
- max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);
+ max_clock = scd->tick_gtod + TICK_NSEC;
clock = wrap_max(clock, min_clock);
clock = wrap_min(clock, max_clock);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 26ed8e3d1c1..4293cfa9681 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -53,6 +53,40 @@ static unsigned long nsec_low(unsigned long long nsec)
#define SPLIT_NS(x) nsec_high(x), nsec_low(x)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void print_cfs_group_stats(struct seq_file *m, int cpu,
+ struct task_group *tg)
+{
+ struct sched_entity *se = tg->se[cpu];
+ if (!se)
+ return;
+
+#define P(F) \
+ SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F)
+#define PN(F) \
+ SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+
+ PN(se->exec_start);
+ PN(se->vruntime);
+ PN(se->sum_exec_runtime);
+#ifdef CONFIG_SCHEDSTATS
+ PN(se->wait_start);
+ PN(se->sleep_start);
+ PN(se->block_start);
+ PN(se->sleep_max);
+ PN(se->block_max);
+ PN(se->exec_max);
+ PN(se->slice_max);
+ PN(se->wait_max);
+ PN(se->wait_sum);
+ P(se->wait_count);
+#endif
+ P(se->load.weight);
+#undef PN
+#undef P
+}
+#endif
+
static void
print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
@@ -121,20 +155,19 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
char path[128] = "";
- struct cgroup *cgroup = NULL;
struct task_group *tg = cfs_rq->tg;
- if (tg)
- cgroup = tg->css.cgroup;
-
- if (cgroup)
- cgroup_path(cgroup, path, sizeof(path));
+ cgroup_path(tg->css.cgroup, path, sizeof(path));
SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
+#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
+ {
+ uid_t uid = cfs_rq->tg->uid;
+ SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
+ }
#else
SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
#endif
-
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock",
SPLIT_NS(cfs_rq->exec_clock));
@@ -168,6 +201,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
#ifdef CONFIG_SMP
SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares);
#endif
+ print_cfs_group_stats(m, cpu, cfs_rq->tg);
#endif
}
@@ -175,14 +209,9 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
{
#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
char path[128] = "";
- struct cgroup *cgroup = NULL;
struct task_group *tg = rt_rq->tg;
- if (tg)
- cgroup = tg->css.cgroup;
-
- if (cgroup)
- cgroup_path(cgroup, path, sizeof(path));
+ cgroup_path(tg->css.cgroup, path, sizeof(path));
SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
#else
@@ -272,7 +301,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
u64 now = ktime_to_ns(ktime_get());
int cpu;
- SEQ_printf(m, "Sched Debug Version: v0.07, %s %.*s\n",
+ SEQ_printf(m, "Sched Debug Version: v0.08, %s %.*s\n",
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 98345e45b05..5ad4440f0fc 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -492,6 +492,8 @@ static void update_curr(struct cfs_rq *cfs_rq)
* overflow on 32 bits):
*/
delta_exec = (unsigned long)(now - curr->exec_start);
+ if (!delta_exec)
+ return;
__update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
@@ -1345,12 +1347,11 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
{
struct task_struct *curr = rq->curr;
struct sched_entity *se = &curr->se, *pse = &p->se;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
- if (unlikely(rt_prio(p->prio))) {
- struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+ update_curr(cfs_rq);
- update_rq_clock(rq);
- update_curr(cfs_rq);
+ if (unlikely(rt_prio(p->prio))) {
resched_task(curr);
return;
}
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d9ba9d5f99d..51d2af3e619 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -77,7 +77,7 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
}
#define for_each_leaf_rt_rq(rt_rq, rq) \
- list_for_each_entry(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
+ list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
@@ -537,13 +537,13 @@ static void update_curr_rt(struct rq *rq)
for_each_sched_rt_entity(rt_se) {
rt_rq = rt_rq_of_se(rt_se);
- spin_lock(&rt_rq->rt_runtime_lock);
if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
+ spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_time += delta_exec;
if (sched_rt_runtime_exceeded(rt_rq))
resched_task(curr);
+ spin_unlock(&rt_rq->rt_runtime_lock);
}
- spin_unlock(&rt_rq->rt_runtime_lock);
}
}
@@ -909,9 +909,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
/* Only try algorithms three times */
#define RT_MAX_TRIES 3
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
-static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);
-
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 6beff1e4eea..b59fd9cdc1b 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -31,7 +31,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count,
rq->sched_switch, rq->sched_count, rq->sched_goidle,
rq->ttwu_count, rq->ttwu_local,
- rq->rq_sched_info.cpu_time,
+ rq->rq_cpu_time,
rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
seq_printf(seq, "\n");
@@ -123,7 +123,7 @@ static inline void
rq_sched_info_depart(struct rq *rq, unsigned long long delta)
{
if (rq)
- rq->rq_sched_info.cpu_time += delta;
+ rq->rq_cpu_time += delta;
}
static inline void
@@ -236,7 +236,6 @@ static inline void sched_info_depart(struct task_struct *t)
unsigned long long delta = task_rq(t)->clock -
t->sched_info.last_arrival;
- t->sched_info.cpu_time += delta;
rq_sched_info_depart(task_rq(t), delta);
if (t->state == TASK_RUNNING)
diff --git a/kernel/signal.c b/kernel/signal.c
index 4530fc65445..8e95855ff3c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -41,6 +41,8 @@
static struct kmem_cache *sigqueue_cachep;
+DEFINE_TRACE(sched_signal_send);
+
static void __user *sig_handler(struct task_struct *t, int sig)
{
return t->sighand->action[sig - 1].sa.sa_handler;
@@ -177,6 +179,11 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
return sig;
}
+/*
+ * allocate a new signal queue record
+ * - this may be called without locks if and only if t == current, otherwise an
+ * appopriate lock must be held to stop the target task from exiting
+ */
static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
int override_rlimit)
{
@@ -184,11 +191,12 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
struct user_struct *user;
/*
- * In order to avoid problems with "switch_user()", we want to make
- * sure that the compiler doesn't re-load "t->user"
+ * We won't get problems with the target's UID changing under us
+ * because changing it requires RCU be used, and if t != current, the
+ * caller must be holding the RCU readlock (by way of a spinlock) and
+ * we use RCU protection here
*/
- user = t->user;
- barrier();
+ user = get_uid(__task_cred(t)->user);
atomic_inc(&user->sigpending);
if (override_rlimit ||
atomic_read(&user->sigpending) <=
@@ -196,12 +204,14 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
q = kmem_cache_alloc(sigqueue_cachep, flags);
if (unlikely(q == NULL)) {
atomic_dec(&user->sigpending);
+ free_uid(user);
} else {
INIT_LIST_HEAD(&q->list);
q->flags = 0;
- q->user = get_uid(user);
+ q->user = user;
}
- return(q);
+
+ return q;
}
static void __sigqueue_free(struct sigqueue *q)
@@ -562,10 +572,12 @@ static int rm_from_queue(unsigned long mask, struct sigpending *s)
/*
* Bad permissions for sending the signal
+ * - the caller must hold at least the RCU read lock
*/
static int check_kill_permission(int sig, struct siginfo *info,
struct task_struct *t)
{
+ const struct cred *cred = current_cred(), *tcred;
struct pid *sid;
int error;
@@ -579,8 +591,11 @@ static int check_kill_permission(int sig, struct siginfo *info,
if (error)
return error;
- if ((current->euid ^ t->suid) && (current->euid ^ t->uid) &&
- (current->uid ^ t->suid) && (current->uid ^ t->uid) &&
+ tcred = __task_cred(t);
+ if ((cred->euid ^ tcred->suid) &&
+ (cred->euid ^ tcred->uid) &&
+ (cred->uid ^ tcred->suid) &&
+ (cred->uid ^ tcred->uid) &&
!capable(CAP_KILL)) {
switch (sig) {
case SIGCONT:
@@ -844,7 +859,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
q->info.si_errno = 0;
q->info.si_code = SI_USER;
q->info.si_pid = task_pid_vnr(current);
- q->info.si_uid = current->uid;
+ q->info.si_uid = current_uid();
break;
case (unsigned long) SEND_SIG_PRIV:
q->info.si_signo = sig;
@@ -1008,6 +1023,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long
return sighand;
}
+/*
+ * send signal info to all the members of a group
+ * - the caller must hold the RCU read lock at least
+ */
int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
{
unsigned long flags;
@@ -1029,8 +1048,8 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
/*
* __kill_pgrp_info() sends a signal to a process group: this is what the tty
* control characters do (^C, ^Z etc)
+ * - the caller must hold at least a readlock on tasklist_lock
*/
-
int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
{
struct task_struct *p = NULL;
@@ -1086,6 +1105,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
{
int ret = -EINVAL;
struct task_struct *p;
+ const struct cred *pcred;
if (!valid_signal(sig))
return ret;
@@ -1096,9 +1116,11 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
ret = -ESRCH;
goto out_unlock;
}
- if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
- && (euid != p->suid) && (euid != p->uid)
- && (uid != p->suid) && (uid != p->uid)) {
+ pcred = __task_cred(p);
+ if ((info == SEND_SIG_NOINFO ||
+ (!is_si_special(info) && SI_FROMUSER(info))) &&
+ euid != pcred->suid && euid != pcred->uid &&
+ uid != pcred->suid && uid != pcred->uid) {
ret = -EPERM;
goto out_unlock;
}
@@ -1369,10 +1391,9 @@ int do_notify_parent(struct task_struct *tsk, int sig)
*/
rcu_read_lock();
info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
+ info.si_uid = __task_cred(tsk)->uid;
rcu_read_unlock();
- info.si_uid = tsk->uid;
-
thread_group_cputime(tsk, &cputime);
info.si_utime = cputime_to_jiffies(cputime.utime);
info.si_stime = cputime_to_jiffies(cputime.stime);
@@ -1440,10 +1461,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why)
*/
rcu_read_lock();
info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns);
+ info.si_uid = __task_cred(tsk)->uid;
rcu_read_unlock();
- info.si_uid = tsk->uid;
-
info.si_utime = cputime_to_clock_t(tsk->utime);
info.si_stime = cputime_to_clock_t(tsk->stime);
@@ -1598,7 +1618,7 @@ void ptrace_notify(int exit_code)
info.si_signo = SIGTRAP;
info.si_code = exit_code;
info.si_pid = task_pid_vnr(current);
- info.si_uid = current->uid;
+ info.si_uid = current_uid();
/* Let the debugger run. */
spin_lock_irq(&current->sighand->siglock);
@@ -1710,7 +1730,7 @@ static int ptrace_signal(int signr, siginfo_t *info,
info->si_errno = 0;
info->si_code = SI_USER;
info->si_pid = task_pid_vnr(current->parent);
- info->si_uid = current->parent->uid;
+ info->si_uid = task_uid(current->parent);
}
/* If the (new) signal is now blocked, requeue it. */
@@ -2211,7 +2231,7 @@ sys_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 = current_uid();
return kill_something_info(sig, &info, pid);
}
@@ -2228,7 +2248,7 @@ 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 = current_uid();
rcu_read_lock();
p = find_task_by_vpid(pid);
diff --git a/kernel/sys.c b/kernel/sys.c
index 31deba8f7d1..ebe65c2c987 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -112,12 +112,17 @@ EXPORT_SYMBOL(cad_pid);
void (*pm_power_off_prepare)(void);
+/*
+ * set the priority of a task
+ * - the caller must hold the RCU read lock
+ */
static int set_one_prio(struct task_struct *p, int niceval, int error)
{
+ const struct cred *cred = current_cred(), *pcred = __task_cred(p);
int no_nice;
- if (p->uid != current->euid &&
- p->euid != current->euid && !capable(CAP_SYS_NICE)) {
+ if (pcred->uid != cred->euid &&
+ pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) {
error = -EPERM;
goto out;
}
@@ -141,6 +146,7 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
{
struct task_struct *g, *p;
struct user_struct *user;
+ const struct cred *cred = current_cred();
int error = -EINVAL;
struct pid *pgrp;
@@ -174,18 +180,18 @@ asmlinkage long sys_setpriority(int which, int who, int niceval)
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = current->user;
+ user = (struct user_struct *) cred->user;
if (!who)
- who = current->uid;
- else
- if ((who != current->uid) && !(user = find_user(who)))
- goto out_unlock; /* No processes for this user */
+ who = cred->uid;
+ else if ((who != cred->uid) &&
+ !(user = find_user(who)))
+ goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
- if (p->uid == who)
+ if (__task_cred(p)->uid == who)
error = set_one_prio(p, niceval, error);
while_each_thread(g, p);
- if (who != current->uid)
+ if (who != cred->uid)
free_uid(user); /* For find_user() */
break;
}
@@ -205,6 +211,7 @@ asmlinkage long sys_getpriority(int which, int who)
{
struct task_struct *g, *p;
struct user_struct *user;
+ const struct cred *cred = current_cred();
long niceval, retval = -ESRCH;
struct pid *pgrp;
@@ -236,21 +243,21 @@ asmlinkage long sys_getpriority(int which, int who)
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case PRIO_USER:
- user = current->user;
+ user = (struct user_struct *) cred->user;
if (!who)
- who = current->uid;
- else
- if ((who != current->uid) && !(user = find_user(who)))
- goto out_unlock; /* No processes for this user */
+ who = cred->uid;
+ else if ((who != cred->uid) &&
+ !(user = find_user(who)))
+ goto out_unlock; /* No processes for this user */
do_each_thread(g, p)
- if (p->uid == who) {
+ if (__task_cred(p)->uid == who) {
niceval = 20 - task_nice(p);
if (niceval > retval)
retval = niceval;
}
while_each_thread(g, p);
- if (who != current->uid)
+ if (who != cred->uid)
free_uid(user); /* for find_user() */
break;
}
@@ -472,46 +479,48 @@ void ctrl_alt_del(void)
*/
asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
{
- int old_rgid = current->gid;
- int old_egid = current->egid;
- int new_rgid = old_rgid;
- int new_egid = old_egid;
+ const struct cred *old;
+ struct cred *new;
int retval;
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+ old = current_cred();
+
retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
if (retval)
- return retval;
+ goto error;
+ retval = -EPERM;
if (rgid != (gid_t) -1) {
- if ((old_rgid == rgid) ||
- (current->egid==rgid) ||
+ if (old->gid == rgid ||
+ old->egid == rgid ||
capable(CAP_SETGID))
- new_rgid = rgid;
+ new->gid = rgid;
else
- return -EPERM;
+ goto error;
}
if (egid != (gid_t) -1) {
- if ((old_rgid == egid) ||
- (current->egid == egid) ||
- (current->sgid == egid) ||
+ if (old->gid == egid ||
+ old->egid == egid ||
+ old->sgid == egid ||
capable(CAP_SETGID))
- new_egid = egid;
+ new->egid = egid;
else
- return -EPERM;
- }
- if (new_egid != old_egid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
+ goto error;
}
+
if (rgid != (gid_t) -1 ||
- (egid != (gid_t) -1 && egid != old_rgid))
- current->sgid = new_egid;
- current->fsgid = new_egid;
- current->egid = new_egid;
- current->gid = new_rgid;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
- return 0;
+ (egid != (gid_t) -1 && egid != old->gid))
+ new->sgid = new->egid;
+ new->fsgid = new->egid;
+
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
/*
@@ -521,56 +530,54 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
*/
asmlinkage long sys_setgid(gid_t gid)
{
- int old_egid = current->egid;
+ const struct cred *old;
+ struct cred *new;
int retval;
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+ old = current_cred();
+
retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
if (retval)
- return retval;
+ goto error;
- if (capable(CAP_SETGID)) {
- if (old_egid != gid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->gid = current->egid = current->sgid = current->fsgid = gid;
- } else if ((gid == current->gid) || (gid == current->sgid)) {
- if (old_egid != gid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->egid = current->fsgid = gid;
- }
+ retval = -EPERM;
+ if (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;
else
- return -EPERM;
+ goto error;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
- return 0;
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
-static int set_user(uid_t new_ruid, int dumpclear)
+/*
+ * change the user struct in a credentials set to match the new UID
+ */
+static int set_user(struct cred *new)
{
struct user_struct *new_user;
- new_user = alloc_uid(current->nsproxy->user_ns, new_ruid);
+ new_user = alloc_uid(current_user_ns(), new->uid);
if (!new_user)
return -EAGAIN;
if (atomic_read(&new_user->processes) >=
current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
- new_user != current->nsproxy->user_ns->root_user) {
+ new_user != INIT_USER) {
free_uid(new_user);
return -EAGAIN;
}
- switch_uid(new_user);
-
- if (dumpclear) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->uid = new_ruid;
+ free_uid(new->user);
+ new->user = new_user;
return 0;
}
@@ -591,54 +598,56 @@ static int set_user(uid_t new_ruid, int dumpclear)
*/
asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
{
- int old_ruid, old_euid, old_suid, new_ruid, new_euid;
+ const struct cred *old;
+ struct cred *new;
int retval;
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+ old = current_cred();
+
retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
if (retval)
- return retval;
-
- new_ruid = old_ruid = current->uid;
- new_euid = old_euid = current->euid;
- old_suid = current->suid;
+ goto error;
+ retval = -EPERM;
if (ruid != (uid_t) -1) {
- new_ruid = ruid;
- if ((old_ruid != ruid) &&
- (current->euid != ruid) &&
+ new->uid = ruid;
+ if (old->uid != ruid &&
+ old->euid != ruid &&
!capable(CAP_SETUID))
- return -EPERM;
+ goto error;
}
if (euid != (uid_t) -1) {
- new_euid = euid;
- if ((old_ruid != euid) &&
- (current->euid != euid) &&
- (current->suid != euid) &&
+ new->euid = euid;
+ if (old->uid != euid &&
+ old->euid != euid &&
+ old->suid != euid &&
!capable(CAP_SETUID))
- return -EPERM;
+ goto error;
}
- if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
- return -EAGAIN;
+ retval = -EAGAIN;
+ if (new->uid != old->uid && set_user(new) < 0)
+ goto error;
- if (new_euid != old_euid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->fsuid = current->euid = new_euid;
if (ruid != (uid_t) -1 ||
- (euid != (uid_t) -1 && euid != old_ruid))
- current->suid = current->euid;
- current->fsuid = current->euid;
+ (euid != (uid_t) -1 && euid != old->uid))
+ new->suid = new->euid;
+ new->fsuid = new->euid;
- key_fsuid_changed(current);
- proc_id_connector(current, PROC_EVENT_UID);
-
- return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
-}
+ retval = security_task_fix_setuid(new, old, LSM_SETID_RE);
+ if (retval < 0)
+ goto error;
+ return commit_creds(new);
+error:
+ abort_creds(new);
+ return retval;
+}
/*
* setuid() is implemented like SysV with SAVED_IDS
@@ -653,36 +662,41 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
*/
asmlinkage long sys_setuid(uid_t uid)
{
- int old_euid = current->euid;
- int old_ruid, old_suid, new_suid;
+ const struct cred *old;
+ struct cred *new;
int retval;
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+ old = current_cred();
+
retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
if (retval)
- return retval;
+ goto error;
- old_ruid = current->uid;
- old_suid = current->suid;
- new_suid = old_suid;
-
+ retval = -EPERM;
if (capable(CAP_SETUID)) {
- if (uid != old_ruid && set_user(uid, old_euid != uid) < 0)
- return -EAGAIN;
- new_suid = uid;
- } else if ((uid != current->uid) && (uid != new_suid))
- return -EPERM;
-
- if (old_euid != uid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
+ new->suid = new->uid = uid;
+ if (uid != old->uid && set_user(new) < 0) {
+ retval = -EAGAIN;
+ goto error;
+ }
+ } else if (uid != old->uid && uid != new->suid) {
+ goto error;
}
- current->fsuid = current->euid = uid;
- current->suid = new_suid;
- key_fsuid_changed(current);
- proc_id_connector(current, PROC_EVENT_UID);
+ new->fsuid = new->euid = uid;
+
+ retval = security_task_fix_setuid(new, old, LSM_SETID_ID);
+ if (retval < 0)
+ goto error;
- return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
@@ -692,54 +706,63 @@ asmlinkage long sys_setuid(uid_t uid)
*/
asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
{
- int old_ruid = current->uid;
- int old_euid = current->euid;
- int old_suid = current->suid;
+ const struct cred *old;
+ struct cred *new;
int retval;
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+
retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
if (retval)
- return retval;
+ goto error;
+ old = current_cred();
+ retval = -EPERM;
if (!capable(CAP_SETUID)) {
- if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
- (ruid != current->euid) && (ruid != current->suid))
- return -EPERM;
- if ((euid != (uid_t) -1) && (euid != current->uid) &&
- (euid != current->euid) && (euid != current->suid))
- return -EPERM;
- if ((suid != (uid_t) -1) && (suid != current->uid) &&
- (suid != current->euid) && (suid != current->suid))
- return -EPERM;
+ if (ruid != (uid_t) -1 && ruid != old->uid &&
+ ruid != old->euid && ruid != old->suid)
+ goto error;
+ if (euid != (uid_t) -1 && euid != old->uid &&
+ euid != old->euid && euid != old->suid)
+ goto error;
+ if (suid != (uid_t) -1 && suid != old->uid &&
+ suid != old->euid && suid != old->suid)
+ goto error;
}
+
+ retval = -EAGAIN;
if (ruid != (uid_t) -1) {
- if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0)
- return -EAGAIN;
+ new->uid = ruid;
+ if (ruid != old->uid && set_user(new) < 0)
+ goto error;
}
- if (euid != (uid_t) -1) {
- if (euid != current->euid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->euid = euid;
- }
- current->fsuid = current->euid;
+ if (euid != (uid_t) -1)
+ new->euid = euid;
if (suid != (uid_t) -1)
- current->suid = suid;
+ new->suid = suid;
+ new->fsuid = new->euid;
+
+ retval = security_task_fix_setuid(new, old, LSM_SETID_RES);
+ if (retval < 0)
+ goto error;
- key_fsuid_changed(current);
- proc_id_connector(current, PROC_EVENT_UID);
+ return commit_creds(new);
- return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
+error:
+ abort_creds(new);
+ return retval;
}
asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
{
+ const struct cred *cred = current_cred();
int retval;
- if (!(retval = put_user(current->uid, ruid)) &&
- !(retval = put_user(current->euid, euid)))
- retval = put_user(current->suid, suid);
+ if (!(retval = put_user(cred->uid, ruid)) &&
+ !(retval = put_user(cred->euid, euid)))
+ retval = put_user(cred->suid, suid);
return retval;
}
@@ -749,48 +772,55 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us
*/
asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
{
+ const struct cred *old;
+ struct cred *new;
int retval;
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
+ old = current_cred();
+
retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
if (retval)
- return retval;
+ goto error;
+ retval = -EPERM;
if (!capable(CAP_SETGID)) {
- if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
- (rgid != current->egid) && (rgid != current->sgid))
- return -EPERM;
- if ((egid != (gid_t) -1) && (egid != current->gid) &&
- (egid != current->egid) && (egid != current->sgid))
- return -EPERM;
- if ((sgid != (gid_t) -1) && (sgid != current->gid) &&
- (sgid != current->egid) && (sgid != current->sgid))
- return -EPERM;
+ if (rgid != (gid_t) -1 && rgid != old->gid &&
+ rgid != old->egid && rgid != old->sgid)
+ goto error;
+ if (egid != (gid_t) -1 && egid != old->gid &&
+ egid != old->egid && egid != old->sgid)
+ goto error;
+ if (sgid != (gid_t) -1 && sgid != old->gid &&
+ sgid != old->egid && sgid != old->sgid)
+ goto error;
}
- if (egid != (gid_t) -1) {
- if (egid != current->egid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
- }
- current->egid = egid;
- }
- current->fsgid = current->egid;
+
if (rgid != (gid_t) -1)
- current->gid = rgid;
+ new->gid = rgid;
+ if (egid != (gid_t) -1)
+ new->egid = egid;
if (sgid != (gid_t) -1)
- current->sgid = sgid;
+ new->sgid = sgid;
+ new->fsgid = new->egid;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
- return 0;
+ return commit_creds(new);
+
+error:
+ abort_creds(new);
+ return retval;
}
asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
{
+ const struct cred *cred = current_cred();
int retval;
- if (!(retval = put_user(current->gid, rgid)) &&
- !(retval = put_user(current->egid, egid)))
- retval = put_user(current->sgid, sgid);
+ if (!(retval = put_user(cred->gid, rgid)) &&
+ !(retval = put_user(cred->egid, egid)))
+ retval = put_user(cred->sgid, sgid);
return retval;
}
@@ -804,27 +834,35 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us
*/
asmlinkage long sys_setfsuid(uid_t uid)
{
- int old_fsuid;
+ const struct cred *old;
+ struct cred *new;
+ uid_t old_fsuid;
- old_fsuid = current->fsuid;
- if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
- return old_fsuid;
+ new = prepare_creds();
+ if (!new)
+ return current_fsuid();
+ old = current_cred();
+ old_fsuid = old->fsuid;
- if (uid == current->uid || uid == current->euid ||
- uid == current->suid || uid == current->fsuid ||
+ if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0)
+ goto error;
+
+ if (uid == old->uid || uid == old->euid ||
+ uid == old->suid || uid == old->fsuid ||
capable(CAP_SETUID)) {
if (uid != old_fsuid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
+ new->fsuid = uid;
+ if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0)
+ goto change_okay;
}
- current->fsuid = uid;
}
- key_fsuid_changed(current);
- proc_id_connector(current, PROC_EVENT_UID);
-
- security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
+error:
+ abort_creds(new);
+ return old_fsuid;
+change_okay:
+ commit_creds(new);
return old_fsuid;
}
@@ -833,23 +871,34 @@ asmlinkage long sys_setfsuid(uid_t uid)
*/
asmlinkage long sys_setfsgid(gid_t gid)
{
- int old_fsgid;
+ const struct cred *old;
+ struct cred *new;
+ gid_t old_fsgid;
+
+ new = prepare_creds();
+ if (!new)
+ return current_fsgid();
+ old = current_cred();
+ old_fsgid = old->fsgid;
- old_fsgid = current->fsgid;
if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
- return old_fsgid;
+ goto error;
- if (gid == current->gid || gid == current->egid ||
- gid == current->sgid || gid == current->fsgid ||
+ if (gid == old->gid || gid == old->egid ||
+ gid == old->sgid || gid == old->fsgid ||
capable(CAP_SETGID)) {
if (gid != old_fsgid) {
- set_dumpable(current->mm, suid_dumpable);
- smp_wmb();
+ new->fsgid = gid;
+ goto change_okay;
}
- current->fsgid = gid;
- key_fsgid_changed(current);
- proc_id_connector(current, PROC_EVENT_GID);
}
+
+error:
+ abort_creds(new);
+ return old_fsgid;
+
+change_okay:
+ commit_creds(new);
return old_fsgid;
}
@@ -1118,7 +1167,7 @@ EXPORT_SYMBOL(groups_free);
/* export the group_info to a user-space array */
static int groups_to_user(gid_t __user *grouplist,
- struct group_info *group_info)
+ const struct group_info *group_info)
{
int i;
unsigned int count = group_info->ngroups;
@@ -1186,7 +1235,7 @@ static void groups_sort(struct group_info *group_info)
}
/* a simple bsearch */
-int groups_search(struct group_info *group_info, gid_t grp)
+int groups_search(const struct group_info *group_info, gid_t grp)
{
unsigned int left, right;
@@ -1208,51 +1257,74 @@ int groups_search(struct group_info *group_info, gid_t grp)
return 0;
}
-/* validate and set current->group_info */
-int set_current_groups(struct group_info *group_info)
+/**
+ * set_groups - Change a group subscription in a set of credentials
+ * @new: The newly prepared set of credentials to alter
+ * @group_info: The group list to install
+ *
+ * Validate a group subscription and, if valid, insert it into a set
+ * of credentials.
+ */
+int set_groups(struct cred *new, struct group_info *group_info)
{
int retval;
- struct group_info *old_info;
retval = security_task_setgroups(group_info);
if (retval)
return retval;
+ put_group_info(new->group_info);
groups_sort(group_info);
get_group_info(group_info);
+ new->group_info = group_info;
+ return 0;
+}
+
+EXPORT_SYMBOL(set_groups);
- task_lock(current);
- old_info = current->group_info;
- current->group_info = group_info;
- task_unlock(current);
+/**
+ * set_current_groups - Change current's group subscription
+ * @group_info: The group list to impose
+ *
+ * Validate a group subscription and, if valid, impose it upon current's task
+ * security record.
+ */
+int set_current_groups(struct group_info *group_info)
+{
+ struct cred *new;
+ int ret;
- put_group_info(old_info);
+ new = prepare_creds();
+ if (!new)
+ return -ENOMEM;
- return 0;
+ ret = set_groups(new, group_info);
+ if (ret < 0) {
+ abort_creds(new);
+ return ret;
+ }
+
+ return commit_creds(new);
}
EXPORT_SYMBOL(set_current_groups);
asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
{
- int i = 0;
-
- /*
- * SMP: Nobody else can change our grouplist. Thus we are
- * safe.
- */
+ const struct cred *cred = current_cred();
+ int i;
if (gidsetsize < 0)
return -EINVAL;
/* no need to grab task_lock here; it cannot change */
- i = current->group_info->ngroups;
+ i = cred->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
- if (groups_to_user(grouplist, current->group_info)) {
+ if (groups_to_user(grouplist, cred->group_info)) {
i = -EFAULT;
goto out;
}
@@ -1296,9 +1368,11 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
*/
int in_group_p(gid_t grp)
{
+ const struct cred *cred = current_cred();
int retval = 1;
- if (grp != current->fsgid)
- retval = groups_search(current->group_info, grp);
+
+ if (grp != cred->fsgid)
+ retval = groups_search(cred->group_info, grp);
return retval;
}
@@ -1306,9 +1380,11 @@ EXPORT_SYMBOL(in_group_p);
int in_egroup_p(gid_t grp)
{
+ const struct cred *cred = current_cred();
int retval = 1;
- if (grp != current->egid)
- retval = groups_search(current->group_info, grp);
+
+ if (grp != cred->egid)
+ retval = groups_search(cred->group_info, grp);
return retval;
}
@@ -1624,50 +1700,56 @@ asmlinkage long sys_umask(int mask)
asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
unsigned long arg4, unsigned long arg5)
{
- long error = 0;
+ struct task_struct *me = current;
+ unsigned char comm[sizeof(me->comm)];
+ long error;
- if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error))
+ error = security_task_prctl(option, arg2, arg3, arg4, arg5);
+ if (error != -ENOSYS)
return error;
+ error = 0;
switch (option) {
case PR_SET_PDEATHSIG:
if (!valid_signal(arg2)) {
error = -EINVAL;
break;
}
- current->pdeath_signal = arg2;
+ me->pdeath_signal = arg2;
+ error = 0;
break;
case PR_GET_PDEATHSIG:
- error = put_user(current->pdeath_signal, (int __user *)arg2);
+ error = put_user(me->pdeath_signal, (int __user *)arg2);
break;
case PR_GET_DUMPABLE:
- error = get_dumpable(current->mm);
+ error = get_dumpable(me->mm);
break;
case PR_SET_DUMPABLE:
if (arg2 < 0 || arg2 > 1) {
error = -EINVAL;
break;
}
- set_dumpable(current->mm, arg2);
+ set_dumpable(me->mm, arg2);
+ error = 0;
break;
case PR_SET_UNALIGN:
- error = SET_UNALIGN_CTL(current, arg2);
+ error = SET_UNALIGN_CTL(me, arg2);
break;
case PR_GET_UNALIGN:
- error = GET_UNALIGN_CTL(current, arg2);
+ error = GET_UNALIGN_CTL(me, arg2);
break;
case PR_SET_FPEMU:
- error = SET_FPEMU_CTL(current, arg2);
+ error = SET_FPEMU_CTL(me, arg2);
break;
case PR_GET_FPEMU:
- error = GET_FPEMU_CTL(current, arg2);
+ error = GET_FPEMU_CTL(me, arg2);
break;
case PR_SET_FPEXC:
- error = SET_FPEXC_CTL(current, arg2);
+ error = SET_FPEXC_CTL(me, arg2);
break;
case PR_GET_FPEXC:
- error = GET_FPEXC_CTL(current, arg2);
+ error = GET_FPEXC_CTL(me, arg2);
break;
case PR_GET_TIMING:
error = PR_TIMING_STATISTICAL;
@@ -1675,33 +1757,28 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
case PR_SET_TIMING:
if (arg2 != PR_TIMING_STATISTICAL)
error = -EINVAL;
+ else
+ error = 0;
break;
- case PR_SET_NAME: {
- struct task_struct *me = current;
- unsigned char ncomm[sizeof(me->comm)];
-
- ncomm[sizeof(me->comm)-1] = 0;
- if (strncpy_from_user(ncomm, (char __user *)arg2,
- sizeof(me->comm)-1) < 0)
+ case PR_SET_NAME:
+ comm[sizeof(me->comm)-1] = 0;
+ if (strncpy_from_user(comm, (char __user *)arg2,
+ sizeof(me->comm) - 1) < 0)
return -EFAULT;
- set_task_comm(me, ncomm);
+ set_task_comm(me, comm);
return 0;
- }
- case PR_GET_NAME: {
- struct task_struct *me = current;
- unsigned char tcomm[sizeof(me->comm)];
-
- get_task_comm(tcomm, me);
- if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
+ case PR_GET_NAME:
+ get_task_comm(comm, me);
+ if (copy_to_user((char __user *)arg2, comm,
+ sizeof(comm)))
return -EFAULT;
return 0;
- }
case PR_GET_ENDIAN:
- error = GET_ENDIAN(current, arg2);
+ error = GET_ENDIAN(me, arg2);
break;
case PR_SET_ENDIAN:
- error = SET_ENDIAN(current, arg2);
+ error = SET_ENDIAN(me, arg2);
break;
case PR_GET_SECCOMP:
@@ -1725,6 +1802,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
current->default_timer_slack_ns;
else
current->timer_slack_ns = arg2;
+ error = 0;
break;
default:
error = -EINVAL;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3d56fe7570d..0b627d9c93d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -487,6 +487,26 @@ static struct ctl_table kern_table[] = {
.proc_handler = &ftrace_enable_sysctl,
},
#endif
+#ifdef CONFIG_STACK_TRACER
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "stack_tracer_enabled",
+ .data = &stack_tracer_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &stack_trace_sysctl,
+ },
+#endif
+#ifdef CONFIG_TRACING
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "ftrace_dump_on_oops",
+ .data = &ftrace_dump_on_oops,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+#endif
#ifdef CONFIG_MODULES
{
.ctl_name = KERN_MODPROBE,
@@ -1651,7 +1671,7 @@ out:
static int test_perm(int mode, int op)
{
- if (!current->euid)
+ if (!current_euid())
mode >>= 6;
else if (in_egroup_p(0))
mode >>= 3;
diff --git a/kernel/timer.c b/kernel/timer.c
index dbd50fabe4c..566257d1dc1 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1192,25 +1192,25 @@ asmlinkage long sys_getppid(void)
asmlinkage long sys_getuid(void)
{
/* Only we change this so SMP safe */
- return current->uid;
+ return current_uid();
}
asmlinkage long sys_geteuid(void)
{
/* Only we change this so SMP safe */
- return current->euid;
+ return current_euid();
}
asmlinkage long sys_getgid(void)
{
/* Only we change this so SMP safe */
- return current->gid;
+ return current_gid();
}
asmlinkage long sys_getegid(void)
{
/* Only we change this so SMP safe */
- return current->egid;
+ return current_egid();
}
#endif
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 33dbefd471e..e2a4ff6fc3a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -3,18 +3,34 @@
# select HAVE_FUNCTION_TRACER:
#
+config USER_STACKTRACE_SUPPORT
+ bool
+
config NOP_TRACER
bool
config HAVE_FUNCTION_TRACER
bool
+config HAVE_FUNCTION_GRAPH_TRACER
+ bool
+
+config HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ bool
+ help
+ This gets selected when the arch tests the function_trace_stop
+ variable at the mcount call site. Otherwise, this variable
+ is tested by the called function.
+
config HAVE_DYNAMIC_FTRACE
bool
config HAVE_FTRACE_MCOUNT_RECORD
bool
+config HAVE_HW_BRANCH_TRACER
+ bool
+
config TRACER_MAX_TRACE
bool
@@ -47,6 +63,20 @@ config FUNCTION_TRACER
(the bootup default), then the overhead of the instructions is very
small and not measurable even in micro-benchmarks.
+config FUNCTION_GRAPH_TRACER
+ bool "Kernel Function Graph Tracer"
+ depends on HAVE_FUNCTION_GRAPH_TRACER
+ depends on FUNCTION_TRACER
+ default y
+ help
+ Enable the kernel to trace a function at both its return
+ and its entry.
+ It's first purpose is to trace the duration of functions and
+ draw a call graph for each thread with some informations like
+ the return value.
+ This is done by setting the current return address on the current
+ task structure into a stack of calls.
+
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
default n
@@ -138,6 +168,70 @@ config BOOT_TRACER
selected, because the self-tests are an initcall as well and that
would invalidate the boot trace. )
+config TRACE_BRANCH_PROFILING
+ bool "Trace likely/unlikely profiler"
+ depends on DEBUG_KERNEL
+ select TRACING
+ help
+ This tracer profiles all the the likely and unlikely macros
+ in the kernel. It will display the results in:
+
+ /debugfs/tracing/profile_annotated_branch
+
+ Note: this will add a significant overhead, only turn this
+ on if you need to profile the system's use of these macros.
+
+ Say N if unsure.
+
+config PROFILE_ALL_BRANCHES
+ bool "Profile all if conditionals"
+ depends on TRACE_BRANCH_PROFILING
+ help
+ This tracer profiles all branch conditions. Every if ()
+ taken in the kernel is recorded whether it hit or miss.
+ The results will be displayed in:
+
+ /debugfs/tracing/profile_branch
+
+ This configuration, when enabled, will impose a great overhead
+ on the system. This should only be enabled when the system
+ is to be analyzed
+
+ Say N if unsure.
+
+config TRACING_BRANCHES
+ bool
+ help
+ Selected by tracers that will trace the likely and unlikely
+ conditions. This prevents the tracers themselves from being
+ profiled. Profiling the tracing infrastructure can only happen
+ when the likelys and unlikelys are not being traced.
+
+config BRANCH_TRACER
+ bool "Trace likely/unlikely instances"
+ depends on TRACE_BRANCH_PROFILING
+ select TRACING_BRANCHES
+ help
+ This traces the events of likely and unlikely condition
+ calls in the kernel. The difference between this and the
+ "Trace likely/unlikely profiler" is that this is not a
+ histogram of the callers, but actually places the calling
+ events into a running trace buffer to see when and where the
+ events happened, as well as their results.
+
+ Say N if unsure.
+
+config POWER_TRACER
+ bool "Trace power consumption behavior"
+ depends on DEBUG_KERNEL
+ depends on X86
+ select TRACING
+ help
+ This tracer helps developers to analyze and optimize the kernels
+ power management decisions, specifically the C-state and P-state
+ behavior.
+
+
config STACK_TRACER
bool "Trace max stack"
depends on HAVE_FUNCTION_TRACER
@@ -150,13 +244,26 @@ config STACK_TRACER
This tracer works by hooking into every function call that the
kernel executes, and keeping a maximum stack depth value and
- stack-trace saved. Because this logic has to execute in every
- kernel function, all the time, this option can slow down the
- kernel measurably and is generally intended for kernel
- developers only.
+ stack-trace saved. If this is configured with DYNAMIC_FTRACE
+ then it will not have any overhead while the stack tracer
+ is disabled.
+
+ To enable the stack tracer on bootup, pass in 'stacktrace'
+ on the kernel command line.
+
+ The stack tracer can also be enabled or disabled via the
+ sysctl kernel.stack_tracer_enabled
Say N if unsure.
+config HW_BRANCH_TRACER
+ depends on HAVE_HW_BRANCH_TRACER
+ bool "Trace hw branches"
+ select TRACING
+ help
+ This tracer records all branches on the system in a circular
+ buffer giving access to the last N branches for each cpu.
+
config DYNAMIC_FTRACE
bool "enable/disable ftrace tracepoints dynamically"
depends on FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index c8228b1a49e..349d5a93653 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -10,6 +10,11 @@ CFLAGS_trace_selftest_dynamic.o = -pg
obj-y += trace_selftest_dynamic.o
endif
+# If unlikely tracing is enabled, do not trace these files
+ifdef CONFIG_TRACING_BRANCHES
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+endif
+
obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
@@ -24,5 +29,9 @@ obj-$(CONFIG_NOP_TRACER) += trace_nop.o
obj-$(CONFIG_STACK_TRACER) += trace_stack.o
obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
+obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
+obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
+obj-$(CONFIG_POWER_TRACER) += trace_power.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 78db083390f..2f32969c09d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -47,6 +47,13 @@
int ftrace_enabled __read_mostly;
static int last_ftrace_enabled;
+/* set when tracing only a pid */
+struct pid *ftrace_pid_trace;
+static struct pid * const ftrace_swapper_pid = &init_struct_pid;
+
+/* Quick disabling of function tracer. */
+int function_trace_stop;
+
/*
* ftrace_disabled is set when an anomaly is discovered.
* ftrace_disabled is much stronger than ftrace_enabled.
@@ -55,6 +62,7 @@ static int ftrace_disabled __read_mostly;
static DEFINE_SPINLOCK(ftrace_lock);
static DEFINE_MUTEX(ftrace_sysctl_lock);
+static DEFINE_MUTEX(ftrace_start_lock);
static struct ftrace_ops ftrace_list_end __read_mostly =
{
@@ -63,6 +71,8 @@ static struct ftrace_ops ftrace_list_end __read_mostly =
static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
{
@@ -79,6 +89,21 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
};
}
+static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
+{
+ if (!test_tsk_trace_trace(current))
+ return;
+
+ ftrace_pid_function(ip, parent_ip);
+}
+
+static void set_ftrace_pid_function(ftrace_func_t func)
+{
+ /* do not set ftrace_pid_function to itself! */
+ if (func != ftrace_pid_func)
+ ftrace_pid_function = func;
+}
+
/**
* clear_ftrace_function - reset the ftrace function
*
@@ -88,7 +113,23 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
void clear_ftrace_function(void)
{
ftrace_trace_function = ftrace_stub;
+ __ftrace_trace_function = ftrace_stub;
+ ftrace_pid_function = ftrace_stub;
+}
+
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+/*
+ * For those archs that do not test ftrace_trace_stop in their
+ * mcount call site, we need to do it from C.
+ */
+static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
+{
+ if (function_trace_stop)
+ return;
+
+ __ftrace_trace_function(ip, parent_ip);
}
+#endif
static int __register_ftrace_function(struct ftrace_ops *ops)
{
@@ -106,14 +147,28 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
ftrace_list = ops;
if (ftrace_enabled) {
+ ftrace_func_t func;
+
+ if (ops->next == &ftrace_list_end)
+ func = ops->func;
+ else
+ func = ftrace_list_func;
+
+ if (ftrace_pid_trace) {
+ set_ftrace_pid_function(func);
+ func = ftrace_pid_func;
+ }
+
/*
* For one func, simply call it directly.
* For more than one func, call the chain.
*/
- if (ops->next == &ftrace_list_end)
- ftrace_trace_function = ops->func;
- else
- ftrace_trace_function = ftrace_list_func;
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ftrace_trace_function = func;
+#else
+ __ftrace_trace_function = func;
+ ftrace_trace_function = ftrace_test_stop_func;
+#endif
}
spin_unlock(&ftrace_lock);
@@ -152,9 +207,19 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (ftrace_enabled) {
/* If we only have one func left, then call that directly */
- if (ftrace_list == &ftrace_list_end ||
- ftrace_list->next == &ftrace_list_end)
- ftrace_trace_function = ftrace_list->func;
+ if (ftrace_list->next == &ftrace_list_end) {
+ ftrace_func_t func = ftrace_list->func;
+
+ if (ftrace_pid_trace) {
+ set_ftrace_pid_function(func);
+ func = ftrace_pid_func;
+ }
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ftrace_trace_function = func;
+#else
+ __ftrace_trace_function = func;
+#endif
+ }
}
out:
@@ -163,6 +228,36 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
return ret;
}
+static void ftrace_update_pid_func(void)
+{
+ ftrace_func_t func;
+
+ /* should not be called from interrupt context */
+ spin_lock(&ftrace_lock);
+
+ if (ftrace_trace_function == ftrace_stub)
+ goto out;
+
+ func = ftrace_trace_function;
+
+ if (ftrace_pid_trace) {
+ set_ftrace_pid_function(func);
+ func = ftrace_pid_func;
+ } else {
+ if (func == ftrace_pid_func)
+ func = ftrace_pid_function;
+ }
+
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ftrace_trace_function = func;
+#else
+ __ftrace_trace_function = func;
+#endif
+
+ out:
+ spin_unlock(&ftrace_lock);
+}
+
#ifdef CONFIG_DYNAMIC_FTRACE
#ifndef CONFIG_FTRACE_MCOUNT_RECORD
# error Dynamic ftrace depends on MCOUNT_RECORD
@@ -182,6 +277,8 @@ enum {
FTRACE_UPDATE_TRACE_FUNC = (1 << 2),
FTRACE_ENABLE_MCOUNT = (1 << 3),
FTRACE_DISABLE_MCOUNT = (1 << 4),
+ FTRACE_START_FUNC_RET = (1 << 5),
+ FTRACE_STOP_FUNC_RET = (1 << 6),
};
static int ftrace_filtered;
@@ -308,7 +405,7 @@ ftrace_record_ip(unsigned long ip)
{
struct dyn_ftrace *rec;
- if (!ftrace_enabled || ftrace_disabled)
+ if (ftrace_disabled)
return NULL;
rec = ftrace_alloc_dyn_node(ip);
@@ -322,14 +419,51 @@ ftrace_record_ip(unsigned long ip)
return rec;
}
-#define FTRACE_ADDR ((long)(ftrace_caller))
+static void print_ip_ins(const char *fmt, unsigned char *p)
+{
+ int i;
+
+ printk(KERN_CONT "%s", fmt);
+
+ for (i = 0; i < MCOUNT_INSN_SIZE; i++)
+ printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
+}
+
+static void ftrace_bug(int failed, unsigned long ip)
+{
+ switch (failed) {
+ case -EFAULT:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace faulted on modifying ");
+ print_ip_sym(ip);
+ break;
+ case -EINVAL:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace failed to modify ");
+ print_ip_sym(ip);
+ print_ip_ins(" actual: ", (unsigned char *)ip);
+ printk(KERN_CONT "\n");
+ break;
+ case -EPERM:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace faulted on writing ");
+ print_ip_sym(ip);
+ break;
+ default:
+ FTRACE_WARN_ON_ONCE(1);
+ pr_info("ftrace faulted on unknown error ");
+ print_ip_sym(ip);
+ }
+}
+
static int
-__ftrace_replace_code(struct dyn_ftrace *rec,
- unsigned char *nop, int enable)
+__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
{
unsigned long ip, fl;
- unsigned char *call, *old, *new;
+ unsigned long ftrace_addr;
+
+ ftrace_addr = (unsigned long)ftrace_caller;
ip = rec->ip;
@@ -388,34 +522,28 @@ __ftrace_replace_code(struct dyn_ftrace *rec,
}
}
- call = ftrace_call_replace(ip, FTRACE_ADDR);
-
- if (rec->flags & FTRACE_FL_ENABLED) {
- old = nop;
- new = call;
- } else {
- old = call;
- new = nop;
- }
-
- return ftrace_modify_code(ip, old, new);
+ if (rec->flags & FTRACE_FL_ENABLED)
+ return ftrace_make_call(rec, ftrace_addr);
+ else
+ return ftrace_make_nop(NULL, rec, ftrace_addr);
}
static void ftrace_replace_code(int enable)
{
int i, failed;
- unsigned char *nop = NULL;
struct dyn_ftrace *rec;
struct ftrace_page *pg;
- nop = ftrace_nop_replace();
-
for (pg = ftrace_pages_start; pg; pg = pg->next) {
for (i = 0; i < pg->index; i++) {
rec = &pg->records[i];
- /* don't modify code that has already faulted */
- if (rec->flags & FTRACE_FL_FAILED)
+ /*
+ * Skip over free records and records that have
+ * failed.
+ */
+ if (rec->flags & FTRACE_FL_FREE ||
+ rec->flags & FTRACE_FL_FAILED)
continue;
/* ignore updates to this record's mcount site */
@@ -426,68 +554,30 @@ static void ftrace_replace_code(int enable)
unfreeze_record(rec);
}
- failed = __ftrace_replace_code(rec, nop, enable);
+ failed = __ftrace_replace_code(rec, enable);
if (failed && (rec->flags & FTRACE_FL_CONVERTED)) {
rec->flags |= FTRACE_FL_FAILED;
if ((system_state == SYSTEM_BOOTING) ||
!core_kernel_text(rec->ip)) {
ftrace_free_rec(rec);
- }
+ } else
+ ftrace_bug(failed, rec->ip);
}
}
}
}
-static void print_ip_ins(const char *fmt, unsigned char *p)
-{
- int i;
-
- printk(KERN_CONT "%s", fmt);
-
- for (i = 0; i < MCOUNT_INSN_SIZE; i++)
- printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
-}
-
static int
-ftrace_code_disable(struct dyn_ftrace *rec)
+ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
{
unsigned long ip;
- unsigned char *nop, *call;
int ret;
ip = rec->ip;
- nop = ftrace_nop_replace();
- call = ftrace_call_replace(ip, mcount_addr);
-
- ret = ftrace_modify_code(ip, call, nop);
+ ret = ftrace_make_nop(mod, rec, mcount_addr);
if (ret) {
- switch (ret) {
- case -EFAULT:
- FTRACE_WARN_ON_ONCE(1);
- pr_info("ftrace faulted on modifying ");
- print_ip_sym(ip);
- break;
- case -EINVAL:
- FTRACE_WARN_ON_ONCE(1);
- pr_info("ftrace failed to modify ");
- print_ip_sym(ip);
- print_ip_ins(" expected: ", call);
- print_ip_ins(" actual: ", (unsigned char *)ip);
- print_ip_ins(" replace: ", nop);
- printk(KERN_CONT "\n");
- break;
- case -EPERM:
- FTRACE_WARN_ON_ONCE(1);
- pr_info("ftrace faulted on writing ");
- print_ip_sym(ip);
- break;
- default:
- FTRACE_WARN_ON_ONCE(1);
- pr_info("ftrace faulted on unknown error ");
- print_ip_sym(ip);
- }
-
+ ftrace_bug(ret, ip);
rec->flags |= FTRACE_FL_FAILED;
return 0;
}
@@ -506,6 +596,11 @@ static int __ftrace_modify_code(void *data)
if (*command & FTRACE_UPDATE_TRACE_FUNC)
ftrace_update_ftrace_func(ftrace_trace_function);
+ if (*command & FTRACE_START_FUNC_RET)
+ ftrace_enable_ftrace_graph_caller();
+ else if (*command & FTRACE_STOP_FUNC_RET)
+ ftrace_disable_ftrace_graph_caller();
+
return 0;
}
@@ -515,43 +610,43 @@ static void ftrace_run_update_code(int command)
}
static ftrace_func_t saved_ftrace_func;
-static int ftrace_start;
-static DEFINE_MUTEX(ftrace_start_lock);
+static int ftrace_start_up;
-static void ftrace_startup(void)
+static void ftrace_startup_enable(int command)
{
- int command = 0;
-
- if (unlikely(ftrace_disabled))
- return;
-
- mutex_lock(&ftrace_start_lock);
- ftrace_start++;
- command |= FTRACE_ENABLE_CALLS;
-
if (saved_ftrace_func != ftrace_trace_function) {
saved_ftrace_func = ftrace_trace_function;
command |= FTRACE_UPDATE_TRACE_FUNC;
}
if (!command || !ftrace_enabled)
- goto out;
+ return;
ftrace_run_update_code(command);
- out:
- mutex_unlock(&ftrace_start_lock);
}
-static void ftrace_shutdown(void)
+static void ftrace_startup(int command)
{
- int command = 0;
+ if (unlikely(ftrace_disabled))
+ return;
+
+ mutex_lock(&ftrace_start_lock);
+ ftrace_start_up++;
+ command |= FTRACE_ENABLE_CALLS;
+ ftrace_startup_enable(command);
+
+ mutex_unlock(&ftrace_start_lock);
+}
+
+static void ftrace_shutdown(int command)
+{
if (unlikely(ftrace_disabled))
return;
mutex_lock(&ftrace_start_lock);
- ftrace_start--;
- if (!ftrace_start)
+ ftrace_start_up--;
+ if (!ftrace_start_up)
command |= FTRACE_DISABLE_CALLS;
if (saved_ftrace_func != ftrace_trace_function) {
@@ -577,8 +672,8 @@ static void ftrace_startup_sysctl(void)
mutex_lock(&ftrace_start_lock);
/* Force update next time */
saved_ftrace_func = NULL;
- /* ftrace_start is true if we want ftrace running */
- if (ftrace_start)
+ /* ftrace_start_up is true if we want ftrace running */
+ if (ftrace_start_up)
command |= FTRACE_ENABLE_CALLS;
ftrace_run_update_code(command);
@@ -593,8 +688,8 @@ static void ftrace_shutdown_sysctl(void)
return;
mutex_lock(&ftrace_start_lock);
- /* ftrace_start is true if ftrace is running */
- if (ftrace_start)
+ /* ftrace_start_up is true if ftrace is running */
+ if (ftrace_start_up)
command |= FTRACE_DISABLE_CALLS;
ftrace_run_update_code(command);
@@ -605,7 +700,7 @@ static cycle_t ftrace_update_time;
static unsigned long ftrace_update_cnt;
unsigned long ftrace_update_tot_cnt;
-static int ftrace_update_code(void)
+static int ftrace_update_code(struct module *mod)
{
struct dyn_ftrace *p, *t;
cycle_t start, stop;
@@ -622,7 +717,7 @@ static int ftrace_update_code(void)
list_del_init(&p->list);
/* convert record (i.e, patch mcount-call with NOP) */
- if (ftrace_code_disable(p)) {
+ if (ftrace_code_disable(mod, p)) {
p->flags |= FTRACE_FL_CONVERTED;
ftrace_update_cnt++;
} else
@@ -690,7 +785,6 @@ enum {
#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */
struct ftrace_iterator {
- loff_t pos;
struct ftrace_page *pg;
unsigned idx;
unsigned flags;
@@ -715,6 +809,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
iter->pg = iter->pg->next;
iter->idx = 0;
goto retry;
+ } else {
+ iter->idx = -1;
}
} else {
rec = &iter->pg->records[iter->idx++];
@@ -737,8 +833,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
}
spin_unlock(&ftrace_lock);
- iter->pos = *pos;
-
return rec;
}
@@ -746,13 +840,15 @@ static void *t_start(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
void *p = NULL;
- loff_t l = -1;
- if (*pos > iter->pos)
- *pos = iter->pos;
+ if (*pos > 0) {
+ if (iter->idx < 0)
+ return p;
+ (*pos)--;
+ iter->idx--;
+ }
- l = *pos;
- p = t_next(m, p, &l);
+ p = t_next(m, p, pos);
return p;
}
@@ -763,21 +859,15 @@ static void t_stop(struct seq_file *m, void *p)
static int t_show(struct seq_file *m, void *v)
{
- struct ftrace_iterator *iter = m->private;
struct dyn_ftrace *rec = v;
char str[KSYM_SYMBOL_LEN];
- int ret = 0;
if (!rec)
return 0;
kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
- ret = seq_printf(m, "%s\n", str);
- if (ret < 0) {
- iter->pos--;
- iter->idx--;
- }
+ seq_printf(m, "%s\n", str);
return 0;
}
@@ -803,7 +893,6 @@ ftrace_avail_open(struct inode *inode, struct file *file)
return -ENOMEM;
iter->pg = ftrace_pages_start;
- iter->pos = 0;
ret = seq_open(file, &show_ftrace_seq_ops);
if (!ret) {
@@ -890,7 +979,6 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
if (file->f_mode & FMODE_READ) {
iter->pg = ftrace_pages_start;
- iter->pos = 0;
iter->flags = enable ? FTRACE_ITER_FILTER :
FTRACE_ITER_NOTRACE;
@@ -959,6 +1047,13 @@ ftrace_match(unsigned char *buff, int len, int enable)
int type = MATCH_FULL;
unsigned long flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE;
unsigned i, match = 0, search_len = 0;
+ int not = 0;
+
+ if (buff[0] == '!') {
+ not = 1;
+ buff++;
+ len--;
+ }
for (i = 0; i < len; i++) {
if (buff[i] == '*') {
@@ -1012,8 +1107,12 @@ ftrace_match(unsigned char *buff, int len, int enable)
matched = 1;
break;
}
- if (matched)
- rec->flags |= flag;
+ if (matched) {
+ if (not)
+ rec->flags &= ~flag;
+ else
+ rec->flags |= flag;
+ }
}
pg = pg->next;
}
@@ -1181,7 +1280,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
mutex_lock(&ftrace_sysctl_lock);
mutex_lock(&ftrace_start_lock);
- if (ftrace_start && ftrace_enabled)
+ if (ftrace_start_up && ftrace_enabled)
ftrace_run_update_code(FTRACE_ENABLE_CALLS);
mutex_unlock(&ftrace_start_lock);
mutex_unlock(&ftrace_sysctl_lock);
@@ -1233,12 +1332,233 @@ static struct file_operations ftrace_notrace_fops = {
.release = ftrace_notrace_release,
};
-static __init int ftrace_init_debugfs(void)
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+static DEFINE_MUTEX(graph_lock);
+
+int ftrace_graph_count;
+unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
+
+static void *
+g_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct dentry *d_tracer;
- struct dentry *entry;
+ unsigned long *array = m->private;
+ int index = *pos;
- d_tracer = tracing_init_dentry();
+ (*pos)++;
+
+ if (index >= ftrace_graph_count)
+ return NULL;
+
+ return &array[index];
+}
+
+static void *g_start(struct seq_file *m, loff_t *pos)
+{
+ void *p = NULL;
+
+ mutex_lock(&graph_lock);
+
+ p = g_next(m, p, pos);
+
+ return p;
+}
+
+static void g_stop(struct seq_file *m, void *p)
+{
+ mutex_unlock(&graph_lock);
+}
+
+static int g_show(struct seq_file *m, void *v)
+{
+ unsigned long *ptr = v;
+ char str[KSYM_SYMBOL_LEN];
+
+ if (!ptr)
+ return 0;
+
+ kallsyms_lookup(*ptr, NULL, NULL, NULL, str);
+
+ seq_printf(m, "%s\n", str);
+
+ return 0;
+}
+
+static struct seq_operations ftrace_graph_seq_ops = {
+ .start = g_start,
+ .next = g_next,
+ .stop = g_stop,
+ .show = g_show,
+};
+
+static int
+ftrace_graph_open(struct inode *inode, struct file *file)
+{
+ int ret = 0;
+
+ if (unlikely(ftrace_disabled))
+ return -ENODEV;
+
+ mutex_lock(&graph_lock);
+ if ((file->f_mode & FMODE_WRITE) &&
+ !(file->f_flags & O_APPEND)) {
+ ftrace_graph_count = 0;
+ memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
+ }
+
+ if (file->f_mode & FMODE_READ) {
+ ret = seq_open(file, &ftrace_graph_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = ftrace_graph_funcs;
+ }
+ } else
+ file->private_data = ftrace_graph_funcs;
+ mutex_unlock(&graph_lock);
+
+ return ret;
+}
+
+static ssize_t
+ftrace_graph_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ if (file->f_mode & FMODE_READ)
+ return seq_read(file, ubuf, cnt, ppos);
+ else
+ return -EPERM;
+}
+
+static int
+ftrace_set_func(unsigned long *array, int idx, char *buffer)
+{
+ char str[KSYM_SYMBOL_LEN];
+ struct dyn_ftrace *rec;
+ struct ftrace_page *pg;
+ int found = 0;
+ int i, j;
+
+ if (ftrace_disabled)
+ return -ENODEV;
+
+ /* should not be called from interrupt context */
+ spin_lock(&ftrace_lock);
+
+ for (pg = ftrace_pages_start; pg; pg = pg->next) {
+ for (i = 0; i < pg->index; i++) {
+ rec = &pg->records[i];
+
+ if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
+ continue;
+
+ kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
+ if (strcmp(str, buffer) == 0) {
+ found = 1;
+ for (j = 0; j < idx; j++)
+ if (array[j] == rec->ip) {
+ found = 0;
+ break;
+ }
+ if (found)
+ array[idx] = rec->ip;
+ break;
+ }
+ }
+ }
+ spin_unlock(&ftrace_lock);
+
+ return found ? 0 : -EINVAL;
+}
+
+static ssize_t
+ftrace_graph_write(struct file *file, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ unsigned char buffer[FTRACE_BUFF_MAX+1];
+ unsigned long *array;
+ size_t read = 0;
+ ssize_t ret;
+ int index = 0;
+ char ch;
+
+ if (!cnt || cnt < 0)
+ return 0;
+
+ mutex_lock(&graph_lock);
+
+ if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ if (file->f_mode & FMODE_READ) {
+ struct seq_file *m = file->private_data;
+ array = m->private;
+ } else
+ array = file->private_data;
+
+ ret = get_user(ch, ubuf++);
+ if (ret)
+ goto out;
+ read++;
+ cnt--;
+
+ /* skip white space */
+ while (cnt && isspace(ch)) {
+ ret = get_user(ch, ubuf++);
+ if (ret)
+ goto out;
+ read++;
+ cnt--;
+ }
+
+ if (isspace(ch)) {
+ *ppos += read;
+ ret = read;
+ goto out;
+ }
+
+ while (cnt && !isspace(ch)) {
+ if (index < FTRACE_BUFF_MAX)
+ buffer[index++] = ch;
+ else {
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = get_user(ch, ubuf++);
+ if (ret)
+ goto out;
+ read++;
+ cnt--;
+ }
+ buffer[index] = 0;
+
+ /* we allow only one at a time */
+ ret = ftrace_set_func(array, ftrace_graph_count, buffer);
+ if (ret)
+ goto out;
+
+ ftrace_graph_count++;
+
+ file->f_pos += read;
+
+ ret = read;
+ out:
+ mutex_unlock(&graph_lock);
+
+ return ret;
+}
+
+static const struct file_operations ftrace_graph_fops = {
+ .open = ftrace_graph_open,
+ .read = ftrace_graph_read,
+ .write = ftrace_graph_write,
+};
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
+{
+ struct dentry *entry;
entry = debugfs_create_file("available_filter_functions", 0444,
d_tracer, NULL, &ftrace_avail_fops);
@@ -1263,12 +1583,20 @@ static __init int ftrace_init_debugfs(void)
pr_warning("Could not create debugfs "
"'set_ftrace_notrace' entry\n");
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ entry = debugfs_create_file("set_graph_function", 0444, d_tracer,
+ NULL,
+ &ftrace_graph_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'set_graph_function' entry\n");
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
return 0;
}
-fs_initcall(ftrace_init_debugfs);
-
-static int ftrace_convert_nops(unsigned long *start,
+static int ftrace_convert_nops(struct module *mod,
+ unsigned long *start,
unsigned long *end)
{
unsigned long *p;
@@ -1279,23 +1607,32 @@ static int ftrace_convert_nops(unsigned long *start,
p = start;
while (p < end) {
addr = ftrace_call_adjust(*p++);
+ /*
+ * Some architecture linkers will pad between
+ * the different mcount_loc sections of different
+ * object files to satisfy alignments.
+ * Skip any NULL pointers.
+ */
+ if (!addr)
+ continue;
ftrace_record_ip(addr);
}
/* disable interrupts to prevent kstop machine */
local_irq_save(flags);
- ftrace_update_code();
+ ftrace_update_code(mod);
local_irq_restore(flags);
mutex_unlock(&ftrace_start_lock);
return 0;
}
-void ftrace_init_module(unsigned long *start, unsigned long *end)
+void ftrace_init_module(struct module *mod,
+ unsigned long *start, unsigned long *end)
{
if (ftrace_disabled || start == end)
return;
- ftrace_convert_nops(start, end);
+ ftrace_convert_nops(mod, start, end);
}
extern unsigned long __start_mcount_loc[];
@@ -1325,7 +1662,8 @@ void __init ftrace_init(void)
last_ftrace_enabled = ftrace_enabled = 1;
- ret = ftrace_convert_nops(__start_mcount_loc,
+ ret = ftrace_convert_nops(NULL,
+ __start_mcount_loc,
__stop_mcount_loc);
return;
@@ -1342,12 +1680,186 @@ static int __init ftrace_nodyn_init(void)
}
device_initcall(ftrace_nodyn_init);
-# define ftrace_startup() do { } while (0)
-# define ftrace_shutdown() do { } while (0)
+static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
+static inline void ftrace_startup_enable(int command) { }
+/* Keep as macros so we do not need to define the commands */
+# define ftrace_startup(command) do { } while (0)
+# define ftrace_shutdown(command) do { } while (0)
# define ftrace_startup_sysctl() do { } while (0)
# define ftrace_shutdown_sysctl() do { } while (0)
#endif /* CONFIG_DYNAMIC_FTRACE */
+static ssize_t
+ftrace_pid_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[64];
+ int r;
+
+ if (ftrace_pid_trace == ftrace_swapper_pid)
+ r = sprintf(buf, "swapper tasks\n");
+ else if (ftrace_pid_trace)
+ r = sprintf(buf, "%u\n", pid_nr(ftrace_pid_trace));
+ else
+ r = sprintf(buf, "no pid\n");
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static void clear_ftrace_swapper(void)
+{
+ struct task_struct *p;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ p = idle_task(cpu);
+ clear_tsk_trace_trace(p);
+ }
+ put_online_cpus();
+}
+
+static void set_ftrace_swapper(void)
+{
+ struct task_struct *p;
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ p = idle_task(cpu);
+ set_tsk_trace_trace(p);
+ }
+ put_online_cpus();
+}
+
+static void clear_ftrace_pid(struct pid *pid)
+{
+ struct task_struct *p;
+
+ do_each_pid_task(pid, PIDTYPE_PID, p) {
+ clear_tsk_trace_trace(p);
+ } while_each_pid_task(pid, PIDTYPE_PID, p);
+ put_pid(pid);
+}
+
+static void set_ftrace_pid(struct pid *pid)
+{
+ struct task_struct *p;
+
+ do_each_pid_task(pid, PIDTYPE_PID, p) {
+ set_tsk_trace_trace(p);
+ } while_each_pid_task(pid, PIDTYPE_PID, p);
+}
+
+static void clear_ftrace_pid_task(struct pid **pid)
+{
+ if (*pid == ftrace_swapper_pid)
+ clear_ftrace_swapper();
+ else
+ clear_ftrace_pid(*pid);
+
+ *pid = NULL;
+}
+
+static void set_ftrace_pid_task(struct pid *pid)
+{
+ if (pid == ftrace_swapper_pid)
+ set_ftrace_swapper();
+ else
+ set_ftrace_pid(pid);
+}
+
+static ssize_t
+ftrace_pid_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct pid *pid;
+ char buf[64];
+ long val;
+ int ret;
+
+ if (cnt >= sizeof(buf))
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ ret = strict_strtol(buf, 10, &val);
+ if (ret < 0)
+ return ret;
+
+ mutex_lock(&ftrace_start_lock);
+ if (val < 0) {
+ /* disable pid tracing */
+ if (!ftrace_pid_trace)
+ goto out;
+
+ clear_ftrace_pid_task(&ftrace_pid_trace);
+
+ } else {
+ /* swapper task is special */
+ if (!val) {
+ pid = ftrace_swapper_pid;
+ if (pid == ftrace_pid_trace)
+ goto out;
+ } else {
+ pid = find_get_pid(val);
+
+ if (pid == ftrace_pid_trace) {
+ put_pid(pid);
+ goto out;
+ }
+ }
+
+ if (ftrace_pid_trace)
+ clear_ftrace_pid_task(&ftrace_pid_trace);
+
+ if (!pid)
+ goto out;
+
+ ftrace_pid_trace = pid;
+
+ set_ftrace_pid_task(ftrace_pid_trace);
+ }
+
+ /* update the function call */
+ ftrace_update_pid_func();
+ ftrace_startup_enable(0);
+
+ out:
+ mutex_unlock(&ftrace_start_lock);
+
+ return cnt;
+}
+
+static struct file_operations ftrace_pid_fops = {
+ .read = ftrace_pid_read,
+ .write = ftrace_pid_write,
+};
+
+static __init int ftrace_init_debugfs(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+ if (!d_tracer)
+ return 0;
+
+ ftrace_init_dyn_debugfs(d_tracer);
+
+ entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer,
+ NULL, &ftrace_pid_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'set_ftrace_pid' entry\n");
+ return 0;
+}
+
+fs_initcall(ftrace_init_debugfs);
+
/**
* ftrace_kill - kill ftrace
*
@@ -1381,10 +1893,11 @@ int register_ftrace_function(struct ftrace_ops *ops)
return -1;
mutex_lock(&ftrace_sysctl_lock);
+
ret = __register_ftrace_function(ops);
- ftrace_startup();
- mutex_unlock(&ftrace_sysctl_lock);
+ ftrace_startup(0);
+ mutex_unlock(&ftrace_sysctl_lock);
return ret;
}
@@ -1400,7 +1913,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops)
mutex_lock(&ftrace_sysctl_lock);
ret = __unregister_ftrace_function(ops);
- ftrace_shutdown();
+ ftrace_shutdown(0);
mutex_unlock(&ftrace_sysctl_lock);
return ret;
@@ -1449,3 +1962,153 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
return ret;
}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+static atomic_t ftrace_graph_active;
+
+int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
+{
+ return 0;
+}
+
+/* The callbacks that hook a function */
+trace_func_graph_ret_t ftrace_graph_return =
+ (trace_func_graph_ret_t)ftrace_stub;
+trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+
+/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
+static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
+{
+ int i;
+ int ret = 0;
+ unsigned long flags;
+ int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
+ struct task_struct *g, *t;
+
+ for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
+ ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH
+ * sizeof(struct ftrace_ret_stack),
+ GFP_KERNEL);
+ if (!ret_stack_list[i]) {
+ start = 0;
+ end = i;
+ ret = -ENOMEM;
+ goto free;
+ }
+ }
+
+ read_lock_irqsave(&tasklist_lock, flags);
+ do_each_thread(g, t) {
+ if (start == end) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
+
+ if (t->ret_stack == NULL) {
+ t->curr_ret_stack = -1;
+ /* Make sure IRQs see the -1 first: */
+ barrier();
+ t->ret_stack = ret_stack_list[start++];
+ atomic_set(&t->tracing_graph_pause, 0);
+ atomic_set(&t->trace_overrun, 0);
+ }
+ } while_each_thread(g, t);
+
+unlock:
+ read_unlock_irqrestore(&tasklist_lock, flags);
+free:
+ for (i = start; i < end; i++)
+ kfree(ret_stack_list[i]);
+ return ret;
+}
+
+/* Allocate a return stack for each task */
+static int start_graph_tracing(void)
+{
+ struct ftrace_ret_stack **ret_stack_list;
+ int ret;
+
+ ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
+ sizeof(struct ftrace_ret_stack *),
+ GFP_KERNEL);
+
+ if (!ret_stack_list)
+ return -ENOMEM;
+
+ do {
+ ret = alloc_retstack_tasklist(ret_stack_list);
+ } while (ret == -EAGAIN);
+
+ kfree(ret_stack_list);
+ return ret;
+}
+
+int register_ftrace_graph(trace_func_graph_ret_t retfunc,
+ trace_func_graph_ent_t entryfunc)
+{
+ int ret = 0;
+
+ mutex_lock(&ftrace_sysctl_lock);
+
+ atomic_inc(&ftrace_graph_active);
+ ret = start_graph_tracing();
+ if (ret) {
+ atomic_dec(&ftrace_graph_active);
+ goto out;
+ }
+
+ ftrace_graph_return = retfunc;
+ ftrace_graph_entry = entryfunc;
+
+ ftrace_startup(FTRACE_START_FUNC_RET);
+
+out:
+ mutex_unlock(&ftrace_sysctl_lock);
+ return ret;
+}
+
+void unregister_ftrace_graph(void)
+{
+ mutex_lock(&ftrace_sysctl_lock);
+
+ atomic_dec(&ftrace_graph_active);
+ ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
+ ftrace_graph_entry = ftrace_graph_entry_stub;
+ ftrace_shutdown(FTRACE_STOP_FUNC_RET);
+
+ mutex_unlock(&ftrace_sysctl_lock);
+}
+
+/* Allocate a return stack for newly created task */
+void ftrace_graph_init_task(struct task_struct *t)
+{
+ if (atomic_read(&ftrace_graph_active)) {
+ t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+ * sizeof(struct ftrace_ret_stack),
+ GFP_KERNEL);
+ if (!t->ret_stack)
+ return;
+ t->curr_ret_stack = -1;
+ atomic_set(&t->tracing_graph_pause, 0);
+ atomic_set(&t->trace_overrun, 0);
+ } else
+ t->ret_stack = NULL;
+}
+
+void ftrace_graph_exit_task(struct task_struct *t)
+{
+ struct ftrace_ret_stack *ret_stack = t->ret_stack;
+
+ t->ret_stack = NULL;
+ /* NULL must become visible to IRQs before we free it: */
+ barrier();
+
+ kfree(ret_stack);
+}
+
+void ftrace_graph_stop(void)
+{
+ ftrace_stop();
+}
+#endif
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 668bbb5ef2b..76f34c0ef29 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -18,8 +18,46 @@
#include "trace.h"
-/* Global flag to disable all recording to ring buffers */
-static int ring_buffers_off __read_mostly;
+/*
+ * A fast way to enable or disable all ring buffers is to
+ * call tracing_on or tracing_off. Turning off the ring buffers
+ * prevents all ring buffers from being recorded to.
+ * Turning this switch on, makes it OK to write to the
+ * ring buffer, if the ring buffer is enabled itself.
+ *
+ * There's three layers that must be on in order to write
+ * to the ring buffer.
+ *
+ * 1) This global flag must be set.
+ * 2) The ring buffer must be enabled for recording.
+ * 3) The per cpu buffer must be enabled for recording.
+ *
+ * In case of an anomaly, this global flag has a bit set that
+ * will permantly disable all ring buffers.
+ */
+
+/*
+ * Global flag to disable all recording to ring buffers
+ * This has two bits: ON, DISABLED
+ *
+ * ON DISABLED
+ * ---- ----------
+ * 0 0 : ring buffers are off
+ * 1 0 : ring buffers are on
+ * X 1 : ring buffers are permanently disabled
+ */
+
+enum {
+ RB_BUFFERS_ON_BIT = 0,
+ RB_BUFFERS_DISABLED_BIT = 1,
+};
+
+enum {
+ RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT,
+ RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT,
+};
+
+static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
/**
* tracing_on - enable all tracing buffers
@@ -29,7 +67,7 @@ static int ring_buffers_off __read_mostly;
*/
void tracing_on(void)
{
- ring_buffers_off = 0;
+ set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
}
/**
@@ -42,9 +80,22 @@ void tracing_on(void)
*/
void tracing_off(void)
{
- ring_buffers_off = 1;
+ clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
}
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanenty.
+ */
+void tracing_off_permanent(void)
+{
+ set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
+}
+
+#include "trace.h"
+
/* Up this if you want to test the TIME_EXTENTS and normalization */
#define DEBUG_SHIFT 0
@@ -56,7 +107,7 @@ u64 ring_buffer_time_stamp(int cpu)
preempt_disable_notrace();
/* shift to debug/test normalization and TIME_EXTENTS */
time = sched_clock() << DEBUG_SHIFT;
- preempt_enable_notrace();
+ preempt_enable_no_resched_notrace();
return time;
}
@@ -144,20 +195,24 @@ void *ring_buffer_event_data(struct ring_buffer_event *event)
#define TS_MASK ((1ULL << TS_SHIFT) - 1)
#define TS_DELTA_TEST (~TS_MASK)
-/*
- * This hack stolen from mm/slob.c.
- * We can store per page timing information in the page frame of the page.
- * Thanks to Peter Zijlstra for suggesting this idea.
- */
-struct buffer_page {
+struct buffer_data_page {
u64 time_stamp; /* page time stamp */
- local_t write; /* index for next write */
local_t commit; /* write commited index */
+ unsigned char data[]; /* data of buffer page */
+};
+
+struct buffer_page {
+ local_t write; /* index for next write */
unsigned read; /* index for next read */
struct list_head list; /* list of free pages */
- void *page; /* Actual data page */
+ struct buffer_data_page *page; /* Actual data page */
};
+static void rb_init_page(struct buffer_data_page *bpage)
+{
+ local_set(&bpage->commit, 0);
+}
+
/*
* Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
* this issue out.
@@ -179,7 +234,7 @@ static inline int test_time_stamp(u64 delta)
return 0;
}
-#define BUF_PAGE_SIZE PAGE_SIZE
+#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page))
/*
* head_page == tail_page && head == tail then buffer is empty.
@@ -187,7 +242,8 @@ static inline int test_time_stamp(u64 delta)
struct ring_buffer_per_cpu {
int cpu;
struct ring_buffer *buffer;
- spinlock_t lock;
+ spinlock_t reader_lock; /* serialize readers */
+ raw_spinlock_t lock;
struct lock_class_key lock_key;
struct list_head pages;
struct buffer_page *head_page; /* read from head */
@@ -202,7 +258,6 @@ struct ring_buffer_per_cpu {
};
struct ring_buffer {
- unsigned long size;
unsigned pages;
unsigned flags;
int cpus;
@@ -221,32 +276,16 @@ struct ring_buffer_iter {
u64 read_stamp;
};
+/* buffer may be either ring_buffer or ring_buffer_per_cpu */
#define RB_WARN_ON(buffer, cond) \
- do { \
- if (unlikely(cond)) { \
- atomic_inc(&buffer->record_disabled); \
- WARN_ON(1); \
- } \
- } while (0)
-
-#define RB_WARN_ON_RET(buffer, cond) \
- do { \
- if (unlikely(cond)) { \
- atomic_inc(&buffer->record_disabled); \
- WARN_ON(1); \
- return -1; \
- } \
- } while (0)
-
-#define RB_WARN_ON_ONCE(buffer, cond) \
- do { \
- static int once; \
- if (unlikely(cond) && !once) { \
- once++; \
+ ({ \
+ int _____ret = unlikely(cond); \
+ if (_____ret) { \
atomic_inc(&buffer->record_disabled); \
WARN_ON(1); \
} \
- } while (0)
+ _____ret; \
+ })
/**
* check_pages - integrity check of buffer pages
@@ -258,16 +297,20 @@ struct ring_buffer_iter {
static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
struct list_head *head = &cpu_buffer->pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
- RB_WARN_ON_RET(cpu_buffer, head->next->prev != head);
- RB_WARN_ON_RET(cpu_buffer, head->prev->next != head);
+ if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
+ return -1;
+ if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
+ return -1;
- list_for_each_entry_safe(page, tmp, head, list) {
- RB_WARN_ON_RET(cpu_buffer,
- page->list.next->prev != &page->list);
- RB_WARN_ON_RET(cpu_buffer,
- page->list.prev->next != &page->list);
+ list_for_each_entry_safe(bpage, tmp, head, list) {
+ if (RB_WARN_ON(cpu_buffer,
+ bpage->list.next->prev != &bpage->list))
+ return -1;
+ if (RB_WARN_ON(cpu_buffer,
+ bpage->list.prev->next != &bpage->list))
+ return -1;
}
return 0;
@@ -277,22 +320,23 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
unsigned nr_pages)
{
struct list_head *head = &cpu_buffer->pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
unsigned long addr;
LIST_HEAD(pages);
unsigned i;
for (i = 0; i < nr_pages; i++) {
- page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
- if (!page)
+ if (!bpage)
goto free_pages;
- list_add(&page->list, &pages);
+ list_add(&bpage->list, &pages);
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto free_pages;
- page->page = (void *)addr;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
}
list_splice(&pages, head);
@@ -302,9 +346,9 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
return 0;
free_pages:
- list_for_each_entry_safe(page, tmp, &pages, list) {
- list_del_init(&page->list);
- free_buffer_page(page);
+ list_for_each_entry_safe(bpage, tmp, &pages, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
return -ENOMEM;
}
@@ -313,7 +357,7 @@ static struct ring_buffer_per_cpu *
rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
- struct buffer_page *page;
+ struct buffer_page *bpage;
unsigned long addr;
int ret;
@@ -324,19 +368,21 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
cpu_buffer->cpu = cpu;
cpu_buffer->buffer = buffer;
- spin_lock_init(&cpu_buffer->lock);
+ spin_lock_init(&cpu_buffer->reader_lock);
+ cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
INIT_LIST_HEAD(&cpu_buffer->pages);
- page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu));
- if (!page)
+ if (!bpage)
goto fail_free_buffer;
- cpu_buffer->reader_page = page;
+ cpu_buffer->reader_page = bpage;
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto fail_free_reader;
- page->page = (void *)addr;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
@@ -361,14 +407,14 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
{
struct list_head *head = &cpu_buffer->pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
list_del_init(&cpu_buffer->reader_page->list);
free_buffer_page(cpu_buffer->reader_page);
- list_for_each_entry_safe(page, tmp, head, list) {
- list_del_init(&page->list);
- free_buffer_page(page);
+ list_for_each_entry_safe(bpage, tmp, head, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
kfree(cpu_buffer);
}
@@ -465,7 +511,7 @@ static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
static void
rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
{
- struct buffer_page *page;
+ struct buffer_page *bpage;
struct list_head *p;
unsigned i;
@@ -473,13 +519,15 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
synchronize_sched();
for (i = 0; i < nr_pages; i++) {
- BUG_ON(list_empty(&cpu_buffer->pages));
+ if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+ return;
p = cpu_buffer->pages.next;
- page = list_entry(p, struct buffer_page, list);
- list_del_init(&page->list);
- free_buffer_page(page);
+ bpage = list_entry(p, struct buffer_page, list);
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
- BUG_ON(list_empty(&cpu_buffer->pages));
+ if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+ return;
rb_reset_cpu(cpu_buffer);
@@ -493,7 +541,7 @@ static void
rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
struct list_head *pages, unsigned nr_pages)
{
- struct buffer_page *page;
+ struct buffer_page *bpage;
struct list_head *p;
unsigned i;
@@ -501,11 +549,12 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
synchronize_sched();
for (i = 0; i < nr_pages; i++) {
- BUG_ON(list_empty(pages));
+ if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
+ return;
p = pages->next;
- page = list_entry(p, struct buffer_page, list);
- list_del_init(&page->list);
- list_add_tail(&page->list, &cpu_buffer->pages);
+ bpage = list_entry(p, struct buffer_page, list);
+ list_del_init(&bpage->list);
+ list_add_tail(&bpage->list, &cpu_buffer->pages);
}
rb_reset_cpu(cpu_buffer);
@@ -532,7 +581,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
{
struct ring_buffer_per_cpu *cpu_buffer;
unsigned nr_pages, rm_pages, new_pages;
- struct buffer_page *page, *tmp;
+ struct buffer_page *bpage, *tmp;
unsigned long buffer_size;
unsigned long addr;
LIST_HEAD(pages);
@@ -562,7 +611,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
if (size < buffer_size) {
/* easy case, just free pages */
- BUG_ON(nr_pages >= buffer->pages);
+ if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) {
+ mutex_unlock(&buffer->mutex);
+ return -1;
+ }
rm_pages = buffer->pages - nr_pages;
@@ -581,21 +633,26 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
* add these pages to the cpu_buffers. Otherwise we just free
* them all and return -ENOMEM;
*/
- BUG_ON(nr_pages <= buffer->pages);
+ if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) {
+ mutex_unlock(&buffer->mutex);
+ return -1;
+ }
+
new_pages = nr_pages - buffer->pages;
for_each_buffer_cpu(buffer, cpu) {
for (i = 0; i < new_pages; i++) {
- page = kzalloc_node(ALIGN(sizeof(*page),
+ bpage = kzalloc_node(ALIGN(sizeof(*bpage),
cache_line_size()),
GFP_KERNEL, cpu_to_node(cpu));
- if (!page)
+ if (!bpage)
goto free_pages;
- list_add(&page->list, &pages);
+ list_add(&bpage->list, &pages);
addr = __get_free_page(GFP_KERNEL);
if (!addr)
goto free_pages;
- page->page = (void *)addr;
+ bpage->page = (void *)addr;
+ rb_init_page(bpage->page);
}
}
@@ -604,7 +661,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
rb_insert_pages(cpu_buffer, &pages, new_pages);
}
- BUG_ON(!list_empty(&pages));
+ if (RB_WARN_ON(buffer, !list_empty(&pages))) {
+ mutex_unlock(&buffer->mutex);
+ return -1;
+ }
out:
buffer->pages = nr_pages;
@@ -613,9 +673,9 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
return size;
free_pages:
- list_for_each_entry_safe(page, tmp, &pages, list) {
- list_del_init(&page->list);
- free_buffer_page(page);
+ list_for_each_entry_safe(bpage, tmp, &pages, list) {
+ list_del_init(&bpage->list);
+ free_buffer_page(bpage);
}
mutex_unlock(&buffer->mutex);
return -ENOMEM;
@@ -626,9 +686,15 @@ static inline int rb_null_event(struct ring_buffer_event *event)
return event->type == RINGBUF_TYPE_PADDING;
}
-static inline void *__rb_page_index(struct buffer_page *page, unsigned index)
+static inline void *
+__rb_data_page_index(struct buffer_data_page *bpage, unsigned index)
+{
+ return bpage->data + index;
+}
+
+static inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
{
- return page->page + index;
+ return bpage->page->data + index;
}
static inline struct ring_buffer_event *
@@ -658,7 +724,7 @@ static inline unsigned rb_page_write(struct buffer_page *bpage)
static inline unsigned rb_page_commit(struct buffer_page *bpage)
{
- return local_read(&bpage->commit);
+ return local_read(&bpage->page->commit);
}
/* Size is determined by what has been commited */
@@ -693,7 +759,8 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
head += rb_event_length(event)) {
event = __rb_page_index(cpu_buffer->head_page, head);
- BUG_ON(rb_null_event(event));
+ if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
+ return;
/* Only count data entries */
if (event->type != RINGBUF_TYPE_DATA)
continue;
@@ -703,14 +770,14 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
}
static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
- struct buffer_page **page)
+ struct buffer_page **bpage)
{
- struct list_head *p = (*page)->list.next;
+ struct list_head *p = (*bpage)->list.next;
if (p == &cpu_buffer->pages)
p = p->next;
- *page = list_entry(p, struct buffer_page, list);
+ *bpage = list_entry(p, struct buffer_page, list);
}
static inline unsigned
@@ -746,16 +813,18 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
addr &= PAGE_MASK;
while (cpu_buffer->commit_page->page != (void *)addr) {
- RB_WARN_ON(cpu_buffer,
- cpu_buffer->commit_page == cpu_buffer->tail_page);
- cpu_buffer->commit_page->commit =
+ if (RB_WARN_ON(cpu_buffer,
+ cpu_buffer->commit_page == cpu_buffer->tail_page))
+ return;
+ cpu_buffer->commit_page->page->commit =
cpu_buffer->commit_page->write;
rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
- cpu_buffer->write_stamp = cpu_buffer->commit_page->time_stamp;
+ cpu_buffer->write_stamp =
+ cpu_buffer->commit_page->page->time_stamp;
}
/* Now set the commit to the event's index */
- local_set(&cpu_buffer->commit_page->commit, index);
+ local_set(&cpu_buffer->commit_page->page->commit, index);
}
static inline void
@@ -769,25 +838,38 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
* back to us). This allows us to do a simple loop to
* assign the commit to the tail.
*/
+ again:
while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
- cpu_buffer->commit_page->commit =
+ cpu_buffer->commit_page->page->commit =
cpu_buffer->commit_page->write;
rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
- cpu_buffer->write_stamp = cpu_buffer->commit_page->time_stamp;
+ cpu_buffer->write_stamp =
+ cpu_buffer->commit_page->page->time_stamp;
/* add barrier to keep gcc from optimizing too much */
barrier();
}
while (rb_commit_index(cpu_buffer) !=
rb_page_write(cpu_buffer->commit_page)) {
- cpu_buffer->commit_page->commit =
+ cpu_buffer->commit_page->page->commit =
cpu_buffer->commit_page->write;
barrier();
}
+
+ /* again, keep gcc from optimizing */
+ barrier();
+
+ /*
+ * If an interrupt came in just after the first while loop
+ * and pushed the tail page forward, we will be left with
+ * a dangling commit that will never go forward.
+ */
+ if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page))
+ goto again;
}
static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
{
- cpu_buffer->read_stamp = cpu_buffer->reader_page->time_stamp;
+ cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp;
cpu_buffer->reader_page->read = 0;
}
@@ -806,7 +888,7 @@ static inline void rb_inc_iter(struct ring_buffer_iter *iter)
else
rb_inc_page(cpu_buffer, &iter->head_page);
- iter->read_stamp = iter->head_page->time_stamp;
+ iter->read_stamp = iter->head_page->page->time_stamp;
iter->head = 0;
}
@@ -880,12 +962,15 @@ static struct ring_buffer_event *
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
unsigned type, unsigned long length, u64 *ts)
{
- struct buffer_page *tail_page, *head_page, *reader_page;
+ struct buffer_page *tail_page, *head_page, *reader_page, *commit_page;
unsigned long tail, write;
struct ring_buffer *buffer = cpu_buffer->buffer;
struct ring_buffer_event *event;
unsigned long flags;
+ commit_page = cpu_buffer->commit_page;
+ /* we just need to protect against interrupts */
+ barrier();
tail_page = cpu_buffer->tail_page;
write = local_add_return(length, &tail_page->write);
tail = write - length;
@@ -894,7 +979,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
if (write > BUF_PAGE_SIZE) {
struct buffer_page *next_page = tail_page;
- spin_lock_irqsave(&cpu_buffer->lock, flags);
+ local_irq_save(flags);
+ __raw_spin_lock(&cpu_buffer->lock);
rb_inc_page(cpu_buffer, &next_page);
@@ -902,14 +988,15 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
reader_page = cpu_buffer->reader_page;
/* we grabbed the lock before incrementing */
- RB_WARN_ON(cpu_buffer, next_page == reader_page);
+ if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+ goto out_unlock;
/*
* If for some reason, we had an interrupt storm that made
* it all the way around the buffer, bail, and warn
* about it.
*/
- if (unlikely(next_page == cpu_buffer->commit_page)) {
+ if (unlikely(next_page == commit_page)) {
WARN_ON_ONCE(1);
goto out_unlock;
}
@@ -940,12 +1027,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
*/
if (tail_page == cpu_buffer->tail_page) {
local_set(&next_page->write, 0);
- local_set(&next_page->commit, 0);
+ local_set(&next_page->page->commit, 0);
cpu_buffer->tail_page = next_page;
/* reread the time stamp */
*ts = ring_buffer_time_stamp(cpu_buffer->cpu);
- cpu_buffer->tail_page->time_stamp = *ts;
+ cpu_buffer->tail_page->page->time_stamp = *ts;
}
/*
@@ -970,7 +1057,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
rb_set_commit_to_write(cpu_buffer);
}
- spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
/* fail and let the caller try again */
return ERR_PTR(-EAGAIN);
@@ -978,7 +1066,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
/* We reserved something on the buffer */
- BUG_ON(write > BUF_PAGE_SIZE);
+ if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
+ return NULL;
event = __rb_page_index(tail_page, tail);
rb_update_event(event, type, length);
@@ -988,12 +1077,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
* this page's time stamp.
*/
if (!tail && rb_is_commit(cpu_buffer, event))
- cpu_buffer->commit_page->time_stamp = *ts;
+ cpu_buffer->commit_page->page->time_stamp = *ts;
return event;
out_unlock:
- spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
return NULL;
}
@@ -1038,7 +1128,7 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
event->time_delta = *delta & TS_MASK;
event->array[0] = *delta >> TS_SHIFT;
} else {
- cpu_buffer->commit_page->time_stamp = *ts;
+ cpu_buffer->commit_page->page->time_stamp = *ts;
event->time_delta = 0;
event->array[0] = 0;
}
@@ -1076,10 +1166,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
* storm or we have something buggy.
* Bail!
*/
- if (unlikely(++nr_loops > 1000)) {
- RB_WARN_ON(cpu_buffer, 1);
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
return NULL;
- }
ts = ring_buffer_time_stamp(cpu_buffer->cpu);
@@ -1175,15 +1263,14 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
struct ring_buffer_event *event;
int cpu, resched;
- if (ring_buffers_off)
+ if (ring_buffer_flags != RB_BUFFERS_ON)
return NULL;
if (atomic_read(&buffer->record_disabled))
return NULL;
/* If we are tracing schedule, we don't want to recurse */
- resched = need_resched();
- preempt_disable_notrace();
+ resched = ftrace_preempt_disable();
cpu = raw_smp_processor_id();
@@ -1214,10 +1301,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
return event;
out:
- if (resched)
- preempt_enable_no_resched_notrace();
- else
- preempt_enable_notrace();
+ ftrace_preempt_enable(resched);
return NULL;
}
@@ -1259,12 +1343,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
/*
* Only the last preempt count needs to restore preemption.
*/
- if (preempt_count() == 1) {
- if (per_cpu(rb_need_resched, cpu))
- preempt_enable_no_resched_notrace();
- else
- preempt_enable_notrace();
- } else
+ if (preempt_count() == 1)
+ ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+ else
preempt_enable_no_resched_notrace();
return 0;
@@ -1294,14 +1375,13 @@ int ring_buffer_write(struct ring_buffer *buffer,
int ret = -EBUSY;
int cpu, resched;
- if (ring_buffers_off)
+ if (ring_buffer_flags != RB_BUFFERS_ON)
return -EBUSY;
if (atomic_read(&buffer->record_disabled))
return -EBUSY;
- resched = need_resched();
- preempt_disable_notrace();
+ resched = ftrace_preempt_disable();
cpu = raw_smp_processor_id();
@@ -1327,10 +1407,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
ret = 0;
out:
- if (resched)
- preempt_enable_no_resched_notrace();
- else
- preempt_enable_notrace();
+ ftrace_preempt_enable(resched);
return ret;
}
@@ -1489,14 +1566,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
return overruns;
}
-/**
- * ring_buffer_iter_reset - reset an iterator
- * @iter: The iterator to reset
- *
- * Resets the iterator, so that it will start from the beginning
- * again.
- */
-void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+static void rb_iter_reset(struct ring_buffer_iter *iter)
{
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
@@ -1511,7 +1581,24 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
if (iter->head)
iter->read_stamp = cpu_buffer->read_stamp;
else
- iter->read_stamp = iter->head_page->time_stamp;
+ iter->read_stamp = iter->head_page->page->time_stamp;
+}
+
+/**
+ * ring_buffer_iter_reset - reset an iterator
+ * @iter: The iterator to reset
+ *
+ * Resets the iterator, so that it will start from the beginning
+ * again.
+ */
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ rb_iter_reset(iter);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
/**
@@ -1597,7 +1684,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
unsigned long flags;
int nr_loops = 0;
- spin_lock_irqsave(&cpu_buffer->lock, flags);
+ local_irq_save(flags);
+ __raw_spin_lock(&cpu_buffer->lock);
again:
/*
@@ -1606,8 +1694,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
* a case where we will loop three times. There should be no
* reason to loop four times (that I know of).
*/
- if (unlikely(++nr_loops > 3)) {
- RB_WARN_ON(cpu_buffer, 1);
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
reader = NULL;
goto out;
}
@@ -1619,8 +1706,9 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
goto out;
/* Never should we have an index greater than the size */
- RB_WARN_ON(cpu_buffer,
- cpu_buffer->reader_page->read > rb_page_size(reader));
+ if (RB_WARN_ON(cpu_buffer,
+ cpu_buffer->reader_page->read > rb_page_size(reader)))
+ goto out;
/* check if we caught up to the tail */
reader = NULL;
@@ -1637,7 +1725,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->reader_page->list.prev = reader->list.prev;
local_set(&cpu_buffer->reader_page->write, 0);
- local_set(&cpu_buffer->reader_page->commit, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
/* Make the reader page now replace the head */
reader->list.prev->next = &cpu_buffer->reader_page->list;
@@ -1659,7 +1747,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
goto again;
out:
- spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+ __raw_spin_unlock(&cpu_buffer->lock);
+ local_irq_restore(flags);
return reader;
}
@@ -1673,7 +1762,8 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
reader = rb_get_reader_page(cpu_buffer);
/* This function should not be called when buffer is empty */
- BUG_ON(!reader);
+ if (RB_WARN_ON(cpu_buffer, !reader))
+ return;
event = rb_reader_event(cpu_buffer);
@@ -1700,7 +1790,9 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
* Check if we are at the end of the buffer.
*/
if (iter->head >= rb_page_size(iter->head_page)) {
- BUG_ON(iter->head_page == cpu_buffer->commit_page);
+ if (RB_WARN_ON(buffer,
+ iter->head_page == cpu_buffer->commit_page))
+ return;
rb_inc_iter(iter);
return;
}
@@ -1713,8 +1805,10 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
* This should not be called to advance the header if we are
* at the tail of the buffer.
*/
- BUG_ON((iter->head_page == cpu_buffer->commit_page) &&
- (iter->head + length > rb_commit_index(cpu_buffer)));
+ if (RB_WARN_ON(cpu_buffer,
+ (iter->head_page == cpu_buffer->commit_page) &&
+ (iter->head + length > rb_commit_index(cpu_buffer))))
+ return;
rb_update_iter_read_stamp(iter, event);
@@ -1726,17 +1820,8 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
rb_advance_iter(iter);
}
-/**
- * ring_buffer_peek - peek at the next event to be read
- * @buffer: The ring buffer to read
- * @cpu: The cpu to peak at
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not consume the data.
- */
-struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+static struct ring_buffer_event *
+rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_event *event;
@@ -1757,10 +1842,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
* can have. Nesting 10 deep of interrupts is clearly
* an anomaly.
*/
- if (unlikely(++nr_loops > 10)) {
- RB_WARN_ON(cpu_buffer, 1);
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
return NULL;
- }
reader = rb_get_reader_page(cpu_buffer);
if (!reader)
@@ -1798,16 +1881,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
return NULL;
}
-/**
- * ring_buffer_iter_peek - peek at the next event to be read
- * @iter: The ring buffer iterator
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not increment the iterator.
- */
-struct ring_buffer_event *
-ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+static struct ring_buffer_event *
+rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
{
struct ring_buffer *buffer;
struct ring_buffer_per_cpu *cpu_buffer;
@@ -1829,10 +1904,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
* can have. Nesting 10 deep of interrupts is clearly
* an anomaly.
*/
- if (unlikely(++nr_loops > 10)) {
- RB_WARN_ON(cpu_buffer, 1);
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
return NULL;
- }
if (rb_per_cpu_empty(cpu_buffer))
return NULL;
@@ -1869,6 +1942,51 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
}
/**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_buffer_peek(buffer, cpu, ts);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return event;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ struct ring_buffer_event *event;
+ unsigned long flags;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_iter_peek(iter, ts);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return event;
+}
+
+/**
* ring_buffer_consume - return an event and consume it
* @buffer: The ring buffer to get the next event from
*
@@ -1879,19 +1997,24 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
struct ring_buffer_event *
ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
{
- struct ring_buffer_per_cpu *cpu_buffer;
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct ring_buffer_event *event;
+ unsigned long flags;
if (!cpu_isset(cpu, buffer->cpumask))
return NULL;
- event = ring_buffer_peek(buffer, cpu, ts);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ event = rb_buffer_peek(buffer, cpu, ts);
if (!event)
- return NULL;
+ goto out;
- cpu_buffer = buffer->buffers[cpu];
rb_advance_reader(cpu_buffer);
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
return event;
}
@@ -1928,9 +2051,11 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
atomic_inc(&cpu_buffer->record_disabled);
synchronize_sched();
- spin_lock_irqsave(&cpu_buffer->lock, flags);
- ring_buffer_iter_reset(iter);
- spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ __raw_spin_lock(&cpu_buffer->lock);
+ rb_iter_reset(iter);
+ __raw_spin_unlock(&cpu_buffer->lock);
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
return iter;
}
@@ -1962,12 +2087,17 @@ struct ring_buffer_event *
ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
{
struct ring_buffer_event *event;
+ struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+ unsigned long flags;
- event = ring_buffer_iter_peek(iter, ts);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+ event = rb_iter_peek(iter, ts);
if (!event)
- return NULL;
+ goto out;
rb_advance_iter(iter);
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
return event;
}
@@ -1987,7 +2117,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
cpu_buffer->head_page
= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
local_set(&cpu_buffer->head_page->write, 0);
- local_set(&cpu_buffer->head_page->commit, 0);
+ local_set(&cpu_buffer->head_page->page->commit, 0);
cpu_buffer->head_page->read = 0;
@@ -1996,7 +2126,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
local_set(&cpu_buffer->reader_page->write, 0);
- local_set(&cpu_buffer->reader_page->commit, 0);
+ local_set(&cpu_buffer->reader_page->page->commit, 0);
cpu_buffer->reader_page->read = 0;
cpu_buffer->overrun = 0;
@@ -2016,11 +2146,15 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
if (!cpu_isset(cpu, buffer->cpumask))
return;
- spin_lock_irqsave(&cpu_buffer->lock, flags);
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ __raw_spin_lock(&cpu_buffer->lock);
rb_reset_cpu(cpu_buffer);
- spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+ __raw_spin_unlock(&cpu_buffer->lock);
+
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
/**
@@ -2090,8 +2224,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
return -EINVAL;
/* At least make sure the two buffers are somewhat the same */
- if (buffer_a->size != buffer_b->size ||
- buffer_a->pages != buffer_b->pages)
+ if (buffer_a->pages != buffer_b->pages)
return -EINVAL;
cpu_buffer_a = buffer_a->buffers[cpu];
@@ -2118,16 +2251,178 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
return 0;
}
+static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
+ struct buffer_data_page *bpage)
+{
+ struct ring_buffer_event *event;
+ unsigned long head;
+
+ __raw_spin_lock(&cpu_buffer->lock);
+ for (head = 0; head < local_read(&bpage->commit);
+ head += rb_event_length(event)) {
+
+ event = __rb_data_page_index(bpage, head);
+ if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
+ return;
+ /* Only count data entries */
+ if (event->type != RINGBUF_TYPE_DATA)
+ continue;
+ cpu_buffer->entries--;
+ }
+ __raw_spin_unlock(&cpu_buffer->lock);
+}
+
+/**
+ * ring_buffer_alloc_read_page - allocate a page to read from buffer
+ * @buffer: the buffer to allocate for.
+ *
+ * This function is used in conjunction with ring_buffer_read_page.
+ * When reading a full page from the ring buffer, these functions
+ * can be used to speed up the process. The calling function should
+ * allocate a few pages first with this function. Then when it
+ * needs to get pages from the ring buffer, it passes the result
+ * of this function into ring_buffer_read_page, which will swap
+ * the page that was allocated, with the read page of the buffer.
+ *
+ * Returns:
+ * The page allocated, or NULL on error.
+ */
+void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
+{
+ unsigned long addr;
+ struct buffer_data_page *bpage;
+
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ return NULL;
+
+ bpage = (void *)addr;
+
+ return bpage;
+}
+
+/**
+ * ring_buffer_free_read_page - free an allocated read page
+ * @buffer: the buffer the page was allocate for
+ * @data: the page to free
+ *
+ * Free a page allocated from ring_buffer_alloc_read_page.
+ */
+void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
+{
+ free_page((unsigned long)data);
+}
+
+/**
+ * ring_buffer_read_page - extract a page from the ring buffer
+ * @buffer: buffer to extract from
+ * @data_page: the page to use allocated from ring_buffer_alloc_read_page
+ * @cpu: the cpu of the buffer to extract
+ * @full: should the extraction only happen when the page is full.
+ *
+ * This function will pull out a page from the ring buffer and consume it.
+ * @data_page must be the address of the variable that was returned
+ * from ring_buffer_alloc_read_page. This is because the page might be used
+ * to swap with a page in the ring buffer.
+ *
+ * for example:
+ * rpage = ring_buffer_alloc_page(buffer);
+ * if (!rpage)
+ * return error;
+ * ret = ring_buffer_read_page(buffer, &rpage, cpu, 0);
+ * if (ret)
+ * process_page(rpage);
+ *
+ * When @full is set, the function will not return true unless
+ * the writer is off the reader page.
+ *
+ * Note: it is up to the calling functions to handle sleeps and wakeups.
+ * The ring buffer can be used anywhere in the kernel and can not
+ * blindly call wake_up. The layer that uses the ring buffer must be
+ * responsible for that.
+ *
+ * Returns:
+ * 1 if data has been transferred
+ * 0 if no data has been transferred.
+ */
+int ring_buffer_read_page(struct ring_buffer *buffer,
+ void **data_page, int cpu, int full)
+{
+ struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+ struct ring_buffer_event *event;
+ struct buffer_data_page *bpage;
+ unsigned long flags;
+ int ret = 0;
+
+ if (!data_page)
+ return 0;
+
+ bpage = *data_page;
+ if (!bpage)
+ return 0;
+
+ spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+ /*
+ * rb_buffer_peek will get the next ring buffer if
+ * the current reader page is empty.
+ */
+ event = rb_buffer_peek(buffer, cpu, NULL);
+ if (!event)
+ goto out;
+
+ /* check for data */
+ if (!local_read(&cpu_buffer->reader_page->page->commit))
+ goto out;
+ /*
+ * If the writer is already off of the read page, then simply
+ * switch the read page with the given page. Otherwise
+ * we need to copy the data from the reader to the writer.
+ */
+ if (cpu_buffer->reader_page == cpu_buffer->commit_page) {
+ unsigned int read = cpu_buffer->reader_page->read;
+
+ if (full)
+ goto out;
+ /* The writer is still on the reader page, we must copy */
+ bpage = cpu_buffer->reader_page->page;
+ memcpy(bpage->data,
+ cpu_buffer->reader_page->page->data + read,
+ local_read(&bpage->commit) - read);
+
+ /* consume what was read */
+ cpu_buffer->reader_page += read;
+
+ } else {
+ /* swap the pages */
+ rb_init_page(bpage);
+ bpage = cpu_buffer->reader_page->page;
+ cpu_buffer->reader_page->page = *data_page;
+ cpu_buffer->reader_page->read = 0;
+ *data_page = bpage;
+ }
+ ret = 1;
+
+ /* update the entry counter */
+ rb_remove_entries(cpu_buffer, bpage);
+ out:
+ spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+ return ret;
+}
+
static ssize_t
rb_simple_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- int *p = filp->private_data;
+ long *p = filp->private_data;
char buf[64];
int r;
- /* !ring_buffers_off == tracing_on */
- r = sprintf(buf, "%d\n", !*p);
+ if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
+ r = sprintf(buf, "permanently disabled\n");
+ else
+ r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -2136,7 +2431,7 @@ static ssize_t
rb_simple_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- int *p = filp->private_data;
+ long *p = filp->private_data;
char buf[64];
long val;
int ret;
@@ -2153,8 +2448,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
if (ret < 0)
return ret;
- /* !ring_buffers_off == tracing_on */
- *p = !val;
+ if (val)
+ set_bit(RB_BUFFERS_ON_BIT, p);
+ else
+ clear_bit(RB_BUFFERS_ON_BIT, p);
(*ppos)++;
@@ -2176,7 +2473,7 @@ static __init int rb_init_debugfs(void)
d_tracer = tracing_init_dentry();
entry = debugfs_create_file("tracing_on", 0644, d_tracer,
- &ring_buffers_off, &rb_simple_fops);
+ &ring_buffer_flags, &rb_simple_fops);
if (!entry)
pr_warning("Could not create debugfs 'tracing_on' entry\n");
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d2e75479dc5..c8760ec0e46 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,6 +30,7 @@
#include <linux/gfp.h>
#include <linux/fs.h>
#include <linux/kprobes.h>
+#include <linux/seq_file.h>
#include <linux/writeback.h>
#include <linux/stacktrace.h>
@@ -43,6 +44,38 @@
unsigned long __read_mostly tracing_max_latency = (cycle_t)ULONG_MAX;
unsigned long __read_mostly tracing_thresh;
+/*
+ * We need to change this state when a selftest is running.
+ * A selftest will lurk into the ring-buffer to count the
+ * entries inserted during the selftest although some concurrent
+ * insertions into the ring-buffer such as ftrace_printk could occurred
+ * at the same time, giving false positive or negative results.
+ */
+static bool __read_mostly tracing_selftest_running;
+
+/* For tracers that don't implement custom flags */
+static struct tracer_opt dummy_tracer_opt[] = {
+ { }
+};
+
+static struct tracer_flags dummy_tracer_flags = {
+ .val = 0,
+ .opts = dummy_tracer_opt
+};
+
+static int dummy_set_flag(u32 old_flags, u32 bit, int set)
+{
+ return 0;
+}
+
+/*
+ * Kill all tracing for good (never come back).
+ * It is initialized to 1 but will turn to zero if the initialization
+ * of the tracer is successful. But that is the only place that sets
+ * this back to zero.
+ */
+int tracing_disabled = 1;
+
static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
static inline void ftrace_disable_cpu(void)
@@ -62,7 +95,36 @@ static cpumask_t __read_mostly tracing_buffer_mask;
#define for_each_tracing_cpu(cpu) \
for_each_cpu_mask(cpu, tracing_buffer_mask)
-static int tracing_disabled = 1;
+/*
+ * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
+ *
+ * If there is an oops (or kernel panic) and the ftrace_dump_on_oops
+ * is set, then ftrace_dump is called. This will output the contents
+ * of the ftrace buffers to the console. This is very useful for
+ * capturing traces that lead to crashes and outputing it to a
+ * serial console.
+ *
+ * It is default off, but you can enable it with either specifying
+ * "ftrace_dump_on_oops" in the kernel command line, or setting
+ * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ */
+int ftrace_dump_on_oops;
+
+static int tracing_set_tracer(char *buf);
+
+static int __init set_ftrace(char *str)
+{
+ tracing_set_tracer(str);
+ return 1;
+}
+__setup("ftrace", set_ftrace);
+
+static int __init set_ftrace_dump_on_oops(char *str)
+{
+ ftrace_dump_on_oops = 1;
+ return 1;
+}
+__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
long
ns2usecs(cycle_t nsec)
@@ -112,6 +174,19 @@ static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
/* tracer_enabled is used to toggle activation of a tracer */
static int tracer_enabled = 1;
+/**
+ * tracing_is_enabled - return tracer_enabled status
+ *
+ * This function is used by other tracers to know the status
+ * of the tracer_enabled flag. Tracers may use this function
+ * to know if it should enable their features when starting
+ * up. See irqsoff tracer for an example (start_irqsoff_tracer).
+ */
+int tracing_is_enabled(void)
+{
+ return tracer_enabled;
+}
+
/* function tracing enabled */
int ftrace_function_enabled;
@@ -153,8 +228,9 @@ static DEFINE_MUTEX(trace_types_lock);
/* trace_wait is a waitqueue for tasks blocked on trace_poll */
static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
-/* trace_flags holds iter_ctrl options */
-unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
+/* trace_flags holds trace_options default values */
+unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
+ TRACE_ITER_ANNOTATE;
/**
* trace_wake_up - wake up tasks waiting for trace input
@@ -193,13 +269,6 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
return nsecs / 1000;
}
-/*
- * TRACE_ITER_SYM_MASK masks the options in trace_flags that
- * control the output of kernel symbols.
- */
-#define TRACE_ITER_SYM_MASK \
- (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
-
/* These must match the bit postions in trace_iterator_flags */
static const char *trace_options[] = {
"print-parent",
@@ -213,6 +282,12 @@ static const char *trace_options[] = {
"stacktrace",
"sched-tree",
"ftrace_printk",
+ "ftrace_preempt",
+ "branch",
+ "annotate",
+ "userstacktrace",
+ "sym-userobj",
+ "printk-msg-only",
NULL
};
@@ -246,7 +321,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
data->pid = tsk->pid;
- data->uid = tsk->uid;
+ data->uid = task_uid(tsk);
data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
data->policy = tsk->policy;
data->rt_priority = tsk->rt_priority;
@@ -359,6 +434,28 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
return trace_seq_putmem(s, hex, j);
}
+static int
+trace_seq_path(struct trace_seq *s, struct path *path)
+{
+ unsigned char *p;
+
+ if (s->len >= (PAGE_SIZE - 1))
+ return 0;
+ p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
+ if (!IS_ERR(p)) {
+ p = mangle_path(s->buffer + s->len, p, "\n");
+ if (p) {
+ s->len = p - s->buffer;
+ return 1;
+ }
+ } else {
+ s->buffer[s->len++] = '?';
+ return 1;
+ }
+
+ return 0;
+}
+
static void
trace_seq_reset(struct trace_seq *s)
{
@@ -470,7 +567,17 @@ int register_tracer(struct tracer *type)
return -1;
}
+ /*
+ * When this gets called we hold the BKL which means that
+ * preemption is disabled. Various trace selftests however
+ * need to disable and enable preemption for successful tests.
+ * So we drop the BKL here and grab it after the tests again.
+ */
+ unlock_kernel();
mutex_lock(&trace_types_lock);
+
+ tracing_selftest_running = true;
+
for (t = trace_types; t; t = t->next) {
if (strcmp(type->name, t->name) == 0) {
/* already found */
@@ -481,12 +588,20 @@ int register_tracer(struct tracer *type)
}
}
+ if (!type->set_flag)
+ type->set_flag = &dummy_set_flag;
+ if (!type->flags)
+ type->flags = &dummy_tracer_flags;
+ else
+ if (!type->flags->opts)
+ type->flags->opts = dummy_tracer_opt;
+
#ifdef CONFIG_FTRACE_STARTUP_TEST
if (type->selftest) {
struct tracer *saved_tracer = current_trace;
struct trace_array *tr = &global_trace;
- int saved_ctrl = tr->ctrl;
int i;
+
/*
* Run a selftest on this tracer.
* Here we reset the trace buffer, and set the current
@@ -494,25 +609,23 @@ int register_tracer(struct tracer *type)
* internal tracing to verify that everything is in order.
* If we fail, we do not register this tracer.
*/
- for_each_tracing_cpu(i) {
+ for_each_tracing_cpu(i)
tracing_reset(tr, i);
- }
+
current_trace = type;
- tr->ctrl = 0;
/* the test is responsible for initializing and enabling */
pr_info("Testing tracer %s: ", type->name);
ret = type->selftest(type, tr);
/* the test is responsible for resetting too */
current_trace = saved_tracer;
- tr->ctrl = saved_ctrl;
if (ret) {
printk(KERN_CONT "FAILED!\n");
goto out;
}
/* Only reset on passing, to avoid touching corrupted buffers */
- for_each_tracing_cpu(i) {
+ for_each_tracing_cpu(i)
tracing_reset(tr, i);
- }
+
printk(KERN_CONT "PASSED\n");
}
#endif
@@ -524,7 +637,9 @@ int register_tracer(struct tracer *type)
max_tracer_type_len = len;
out:
+ tracing_selftest_running = false;
mutex_unlock(&trace_types_lock);
+ lock_kernel();
return ret;
}
@@ -564,6 +679,16 @@ void tracing_reset(struct trace_array *tr, int cpu)
ftrace_enable_cpu();
}
+void tracing_reset_online_cpus(struct trace_array *tr)
+{
+ int cpu;
+
+ tr->time_start = ftrace_now(tr->cpu);
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr, cpu);
+}
+
#define SAVED_CMDLINES 128
static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
@@ -581,6 +706,91 @@ static void trace_init_cmdlines(void)
cmdline_idx = 0;
}
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
+/**
+ * ftrace_off_permanent - disable all ftrace code permanently
+ *
+ * This should only be called when a serious anomally has
+ * been detected. This will turn off the function tracing,
+ * ring buffers, and other tracing utilites. It takes no
+ * locks and can be called from any context.
+ */
+void ftrace_off_permanent(void)
+{
+ tracing_disabled = 1;
+ ftrace_stop();
+ tracing_off_permanent();
+}
+
+/**
+ * tracing_start - quick start of the tracer
+ *
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
+ */
+void tracing_start(void)
+{
+ struct ring_buffer *buffer;
+ unsigned long flags;
+
+ if (tracing_disabled)
+ return;
+
+ spin_lock_irqsave(&tracing_start_lock, flags);
+ if (--trace_stop_count)
+ goto out;
+
+ if (trace_stop_count < 0) {
+ /* Someone screwed up their debugging */
+ WARN_ON_ONCE(1);
+ trace_stop_count = 0;
+ goto out;
+ }
+
+
+ buffer = global_trace.buffer;
+ if (buffer)
+ ring_buffer_record_enable(buffer);
+
+ buffer = max_tr.buffer;
+ if (buffer)
+ ring_buffer_record_enable(buffer);
+
+ ftrace_start();
+ out:
+ spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
+{
+ struct ring_buffer *buffer;
+ unsigned long flags;
+
+ ftrace_stop();
+ spin_lock_irqsave(&tracing_start_lock, flags);
+ if (trace_stop_count++)
+ goto out;
+
+ buffer = global_trace.buffer;
+ if (buffer)
+ ring_buffer_record_disable(buffer);
+
+ buffer = max_tr.buffer;
+ if (buffer)
+ ring_buffer_record_disable(buffer);
+
+ out:
+ spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
void trace_stop_cmdline_recording(void);
static void trace_save_cmdline(struct task_struct *tsk)
@@ -618,7 +828,7 @@ static void trace_save_cmdline(struct task_struct *tsk)
spin_unlock(&trace_cmdline_lock);
}
-static char *trace_find_cmdline(int pid)
+char *trace_find_cmdline(int pid)
{
char *cmdline = "<...>";
unsigned map;
@@ -655,6 +865,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
entry->preempt_count = pc & 0xff;
entry->pid = (tsk) ? tsk->pid : 0;
+ entry->tgid = (tsk) ? tsk->tgid : 0;
entry->flags =
#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -691,6 +902,56 @@ trace_function(struct trace_array *tr, struct trace_array_cpu *data,
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void __trace_graph_entry(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ struct ftrace_graph_ent *trace,
+ unsigned long flags,
+ int pc)
+{
+ struct ring_buffer_event *event;
+ struct ftrace_graph_ent_entry *entry;
+ unsigned long irq_flags;
+
+ if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ return;
+
+ event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, flags, pc);
+ entry->ent.type = TRACE_GRAPH_ENT;
+ entry->graph_ent = *trace;
+ ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
+}
+
+static void __trace_graph_return(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ struct ftrace_graph_ret *trace,
+ unsigned long flags,
+ int pc)
+{
+ struct ring_buffer_event *event;
+ struct ftrace_graph_ret_entry *entry;
+ unsigned long irq_flags;
+
+ if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ return;
+
+ event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, flags, pc);
+ entry->ent.type = TRACE_GRAPH_RET;
+ entry->ret = *trace;
+ ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
+}
+#endif
+
void
ftrace(struct trace_array *tr, struct trace_array_cpu *data,
unsigned long ip, unsigned long parent_ip, unsigned long flags,
@@ -742,6 +1003,46 @@ void __trace_stack(struct trace_array *tr,
ftrace_trace_stack(tr, data, flags, skip, preempt_count());
}
+static void ftrace_trace_userstack(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ unsigned long flags, int pc)
+{
+#ifdef CONFIG_STACKTRACE
+ struct ring_buffer_event *event;
+ struct userstack_entry *entry;
+ struct stack_trace trace;
+ unsigned long irq_flags;
+
+ if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
+ return;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, flags, pc);
+ entry->ent.type = TRACE_USER_STACK;
+
+ memset(&entry->caller, 0, sizeof(entry->caller));
+
+ trace.nr_entries = 0;
+ trace.max_entries = FTRACE_STACK_ENTRIES;
+ trace.skip = 0;
+ trace.entries = entry->caller;
+
+ save_stack_trace_user(&trace);
+ ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+#endif
+}
+
+void __trace_userstack(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ unsigned long flags)
+{
+ ftrace_trace_userstack(tr, data, flags, preempt_count());
+}
+
static void
ftrace_trace_special(void *__tr, void *__data,
unsigned long arg1, unsigned long arg2, unsigned long arg3,
@@ -765,6 +1066,7 @@ ftrace_trace_special(void *__tr, void *__data,
entry->arg3 = arg3;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
ftrace_trace_stack(tr, data, irq_flags, 4, pc);
+ ftrace_trace_userstack(tr, data, irq_flags, pc);
trace_wake_up();
}
@@ -803,6 +1105,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
entry->next_cpu = task_cpu(next);
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
ftrace_trace_stack(tr, data, flags, 5, pc);
+ ftrace_trace_userstack(tr, data, flags, pc);
}
void
@@ -832,6 +1135,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
entry->next_cpu = task_cpu(wakee);
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
ftrace_trace_stack(tr, data, flags, 6, pc);
+ ftrace_trace_userstack(tr, data, flags, pc);
trace_wake_up();
}
@@ -841,26 +1145,28 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
{
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
+ unsigned long flags;
int cpu;
int pc;
- if (tracing_disabled || !tr->ctrl)
+ if (tracing_disabled)
return;
pc = preempt_count();
- preempt_disable_notrace();
+ local_irq_save(flags);
cpu = raw_smp_processor_id();
data = tr->data[cpu];
- if (likely(!atomic_read(&data->disabled)))
+ if (likely(atomic_inc_return(&data->disabled) == 1))
ftrace_trace_special(tr, data, arg1, arg2, arg3, pc);
- preempt_enable_notrace();
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
}
#ifdef CONFIG_FUNCTION_TRACER
static void
-function_trace_call(unsigned long ip, unsigned long parent_ip)
+function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
{
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
@@ -873,8 +1179,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
return;
pc = preempt_count();
- resched = need_resched();
- preempt_disable_notrace();
+ resched = ftrace_preempt_disable();
local_save_flags(flags);
cpu = raw_smp_processor_id();
data = tr->data[cpu];
@@ -884,12 +1189,97 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
trace_function(tr, data, ip, parent_ip, flags, pc);
atomic_dec(&data->disabled);
- if (resched)
- preempt_enable_no_resched_notrace();
- else
- preempt_enable_notrace();
+ ftrace_preempt_enable(resched);
}
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct trace_array *tr = &global_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ if (unlikely(!ftrace_function_enabled))
+ return;
+
+ /*
+ * Need to use raw, since this must be called before the
+ * recursive protection is performed.
+ */
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ trace_function(tr, data, ip, parent_ip, flags, pc);
+ }
+
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+int trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+ struct trace_array *tr = &global_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ if (!ftrace_trace_task(current))
+ return 0;
+
+ if (!ftrace_graph_addr(trace->func))
+ return 0;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ __trace_graph_entry(tr, data, trace, flags, pc);
+ }
+ /* Only do the atomic if it is not already set */
+ if (!test_tsk_trace_graph(current))
+ set_tsk_trace_graph(current);
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+
+ return 1;
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
+{
+ struct trace_array *tr = &global_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+ int pc;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+ if (likely(disabled == 1)) {
+ pc = preempt_count();
+ __trace_graph_return(tr, data, trace, flags, pc);
+ }
+ if (!trace->depth)
+ clear_tsk_trace_graph(current);
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
static struct ftrace_ops trace_ops __read_mostly =
{
.func = function_trace_call,
@@ -898,9 +1288,14 @@ static struct ftrace_ops trace_ops __read_mostly =
void tracing_start_function_trace(void)
{
ftrace_function_enabled = 0;
+
+ if (trace_flags & TRACE_ITER_PREEMPTONLY)
+ trace_ops.func = function_trace_call_preempt_only;
+ else
+ trace_ops.func = function_trace_call;
+
register_ftrace_function(&trace_ops);
- if (tracer_enabled)
- ftrace_function_enabled = 1;
+ ftrace_function_enabled = 1;
}
void tracing_stop_function_trace(void)
@@ -912,6 +1307,7 @@ void tracing_stop_function_trace(void)
enum trace_file_type {
TRACE_FILE_LAT_FMT = 1,
+ TRACE_FILE_ANNOTATE = 2,
};
static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
@@ -1047,10 +1443,6 @@ static void *s_start(struct seq_file *m, loff_t *pos)
atomic_inc(&trace_record_cmdline_disabled);
- /* let the tracer grab locks here if needed */
- if (current_trace->start)
- current_trace->start(iter);
-
if (*pos != iter->pos) {
iter->ent = NULL;
iter->cpu = 0;
@@ -1077,14 +1469,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
static void s_stop(struct seq_file *m, void *p)
{
- struct trace_iterator *iter = m->private;
-
atomic_dec(&trace_record_cmdline_disabled);
-
- /* let the tracer release locks here if needed */
- if (current_trace && current_trace == iter->trace && iter->trace->stop)
- iter->trace->stop(iter);
-
mutex_unlock(&trace_types_lock);
}
@@ -1143,7 +1528,7 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
# define IP_FMT "%016lx"
#endif
-static int
+int
seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
{
int ret;
@@ -1164,6 +1549,78 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
return ret;
}
+static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+ unsigned long ip, unsigned long sym_flags)
+{
+ struct file *file = NULL;
+ unsigned long vmstart = 0;
+ int ret = 1;
+
+ if (mm) {
+ const struct vm_area_struct *vma;
+
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, ip);
+ if (vma) {
+ file = vma->vm_file;
+ vmstart = vma->vm_start;
+ }
+ if (file) {
+ ret = trace_seq_path(s, &file->f_path);
+ if (ret)
+ ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart);
+ }
+ up_read(&mm->mmap_sem);
+ }
+ if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
+ ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+ return ret;
+}
+
+static int
+seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
+ unsigned long sym_flags)
+{
+ struct mm_struct *mm = NULL;
+ int ret = 1;
+ unsigned int i;
+
+ if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
+ struct task_struct *task;
+ /*
+ * we do the lookup on the thread group leader,
+ * since individual threads might have already quit!
+ */
+ rcu_read_lock();
+ task = find_task_by_vpid(entry->ent.tgid);
+ if (task)
+ mm = get_task_mm(task);
+ rcu_read_unlock();
+ }
+
+ for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+ unsigned long ip = entry->caller[i];
+
+ if (ip == ULONG_MAX || !ret)
+ break;
+ if (i && ret)
+ ret = trace_seq_puts(s, " <- ");
+ if (!ip) {
+ if (ret)
+ ret = trace_seq_puts(s, "??");
+ continue;
+ }
+ if (!ret)
+ break;
+ if (ret)
+ ret = seq_print_user_ip(s, mm, ip, sym_flags);
+ }
+
+ if (mm)
+ mmput(mm);
+ return ret;
+}
+
static void print_lat_help_header(struct seq_file *m)
{
seq_puts(m, "# _------=> CPU# \n");
@@ -1301,6 +1758,13 @@ lat_print_timestamp(struct trace_seq *s, u64 abs_usecs,
static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+static int task_state_char(unsigned long state)
+{
+ int bit = state ? __ffs(state) + 1 : 0;
+
+ return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
/*
* The message is supposed to contain an ending newline.
* If the printing stops prematurely, try to add a newline of our own.
@@ -1338,6 +1802,23 @@ void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter)
trace_seq_putc(s, '\n');
}
+static void test_cpu_buff_start(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+
+ if (!(trace_flags & TRACE_ITER_ANNOTATE))
+ return;
+
+ if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
+ return;
+
+ if (cpu_isset(iter->cpu, iter->started))
+ return;
+
+ cpu_set(iter->cpu, iter->started);
+ trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
+}
+
static enum print_line_t
print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
{
@@ -1352,11 +1833,12 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
char *comm;
int S, T;
int i;
- unsigned state;
if (entry->type == TRACE_CONT)
return TRACE_TYPE_HANDLED;
+ test_cpu_buff_start(iter);
+
next_entry = find_next_entry(iter, NULL, &next_ts);
if (!next_entry)
next_ts = iter->ts;
@@ -1396,12 +1878,8 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
trace_assign_type(field, entry);
- T = field->next_state < sizeof(state_to_char) ?
- state_to_char[field->next_state] : 'X';
-
- state = field->prev_state ?
- __ffs(field->prev_state) + 1 : 0;
- S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X';
+ T = task_state_char(field->next_state);
+ S = task_state_char(field->prev_state);
comm = trace_find_cmdline(field->next_pid);
trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
field->prev_pid,
@@ -1448,6 +1926,27 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
trace_seq_print_cont(s, iter);
break;
}
+ case TRACE_BRANCH: {
+ struct trace_branch *field;
+
+ trace_assign_type(field, entry);
+
+ trace_seq_printf(s, "[%s] %s:%s:%d\n",
+ field->correct ? " ok " : " MISS ",
+ field->func,
+ field->file,
+ field->line);
+ break;
+ }
+ case TRACE_USER_STACK: {
+ struct userstack_entry *field;
+
+ trace_assign_type(field, entry);
+
+ seq_print_userip_objs(field, s, sym_flags);
+ trace_seq_putc(s, '\n');
+ break;
+ }
default:
trace_seq_printf(s, "Unknown type %d\n", entry->type);
}
@@ -1472,6 +1971,8 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
if (entry->type == TRACE_CONT)
return TRACE_TYPE_HANDLED;
+ test_cpu_buff_start(iter);
+
comm = trace_find_cmdline(iter->ent->pid);
t = ns2usecs(iter->ts);
@@ -1519,10 +2020,8 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
trace_assign_type(field, entry);
- S = field->prev_state < sizeof(state_to_char) ?
- state_to_char[field->prev_state] : 'X';
- T = field->next_state < sizeof(state_to_char) ?
- state_to_char[field->next_state] : 'X';
+ T = task_state_char(field->next_state);
+ S = task_state_char(field->prev_state);
ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n",
field->prev_pid,
field->prev_prio,
@@ -1581,6 +2080,37 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
trace_seq_print_cont(s, iter);
break;
}
+ case TRACE_GRAPH_RET: {
+ return print_graph_function(iter);
+ }
+ case TRACE_GRAPH_ENT: {
+ return print_graph_function(iter);
+ }
+ case TRACE_BRANCH: {
+ struct trace_branch *field;
+
+ trace_assign_type(field, entry);
+
+ trace_seq_printf(s, "[%s] %s:%s:%d\n",
+ field->correct ? " ok " : " MISS ",
+ field->func,
+ field->file,
+ field->line);
+ break;
+ }
+ case TRACE_USER_STACK: {
+ struct userstack_entry *field;
+
+ trace_assign_type(field, entry);
+
+ ret = seq_print_userip_objs(field, s, sym_flags);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ ret = trace_seq_putc(s, '\n');
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ break;
+ }
}
return TRACE_TYPE_HANDLED;
}
@@ -1621,12 +2151,9 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
trace_assign_type(field, entry);
- S = field->prev_state < sizeof(state_to_char) ?
- state_to_char[field->prev_state] : 'X';
- T = field->next_state < sizeof(state_to_char) ?
- state_to_char[field->next_state] : 'X';
- if (entry->type == TRACE_WAKE)
- S = '+';
+ T = task_state_char(field->next_state);
+ S = entry->type == TRACE_WAKE ? '+' :
+ task_state_char(field->prev_state);
ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n",
field->prev_pid,
field->prev_prio,
@@ -1640,6 +2167,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
break;
}
case TRACE_SPECIAL:
+ case TRACE_USER_STACK:
case TRACE_STACK: {
struct special_entry *field;
@@ -1712,12 +2240,9 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
trace_assign_type(field, entry);
- S = field->prev_state < sizeof(state_to_char) ?
- state_to_char[field->prev_state] : 'X';
- T = field->next_state < sizeof(state_to_char) ?
- state_to_char[field->next_state] : 'X';
- if (entry->type == TRACE_WAKE)
- S = '+';
+ T = task_state_char(field->next_state);
+ S = entry->type == TRACE_WAKE ? '+' :
+ task_state_char(field->prev_state);
SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid);
SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio);
SEQ_PUT_HEX_FIELD_RET(s, S);
@@ -1728,6 +2253,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
break;
}
case TRACE_SPECIAL:
+ case TRACE_USER_STACK:
case TRACE_STACK: {
struct special_entry *field;
@@ -1744,6 +2270,25 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
return TRACE_TYPE_HANDLED;
}
+static enum print_line_t print_printk_msg_only(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct print_entry *field;
+ int ret;
+
+ trace_assign_type(field, entry);
+
+ ret = trace_seq_printf(s, field->buf);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (entry->flags & TRACE_FLAG_CONT)
+ trace_seq_print_cont(s, iter);
+
+ return TRACE_TYPE_HANDLED;
+}
+
static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
{
struct trace_seq *s = &iter->seq;
@@ -1782,6 +2327,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
break;
}
case TRACE_SPECIAL:
+ case TRACE_USER_STACK:
case TRACE_STACK: {
struct special_entry *field;
@@ -1823,6 +2369,11 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
return ret;
}
+ if (iter->ent->type == TRACE_PRINT &&
+ trace_flags & TRACE_ITER_PRINTK &&
+ trace_flags & TRACE_ITER_PRINTK_MSGONLY)
+ return print_printk_msg_only(iter);
+
if (trace_flags & TRACE_ITER_BIN)
return print_bin_fmt(iter);
@@ -1847,7 +2398,9 @@ static int s_show(struct seq_file *m, void *v)
seq_printf(m, "# tracer: %s\n", iter->trace->name);
seq_puts(m, "#\n");
}
- if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
+ if (iter->trace && iter->trace->print_header)
+ iter->trace->print_header(m);
+ else if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
/* print nothing if the buffers are empty */
if (trace_empty(iter))
return 0;
@@ -1899,6 +2452,15 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
iter->trace = current_trace;
iter->pos = -1;
+ /* Notify the tracer early; before we stop tracing. */
+ if (iter->trace && iter->trace->open)
+ iter->trace->open(iter);
+
+ /* Annotate start of buffers if we had overruns */
+ if (ring_buffer_overruns(iter->tr->buffer))
+ iter->iter_flags |= TRACE_FILE_ANNOTATE;
+
+
for_each_tracing_cpu(cpu) {
iter->buffer_iter[cpu] =
@@ -1917,13 +2479,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
m->private = iter;
/* stop the trace while dumping */
- if (iter->tr->ctrl) {
- tracer_enabled = 0;
- ftrace_function_enabled = 0;
- }
-
- if (iter->trace && iter->trace->open)
- iter->trace->open(iter);
+ tracing_stop();
mutex_unlock(&trace_types_lock);
@@ -1966,14 +2522,7 @@ int tracing_release(struct inode *inode, struct file *file)
iter->trace->close(iter);
/* reenable tracing if it was previously enabled */
- if (iter->tr->ctrl) {
- tracer_enabled = 1;
- /*
- * It is safe to enable function tracing even if it
- * isn't used
- */
- ftrace_function_enabled = 1;
- }
+ tracing_start();
mutex_unlock(&trace_types_lock);
seq_release(inode, file);
@@ -2151,7 +2700,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
if (err)
goto err_unlock;
- raw_local_irq_disable();
+ local_irq_disable();
__raw_spin_lock(&ftrace_max_lock);
for_each_tracing_cpu(cpu) {
/*
@@ -2168,7 +2717,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
}
}
__raw_spin_unlock(&ftrace_max_lock);
- raw_local_irq_enable();
+ local_irq_enable();
tracing_cpumask = tracing_cpumask_new;
@@ -2189,13 +2738,16 @@ static struct file_operations tracing_cpumask_fops = {
};
static ssize_t
-tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
+tracing_trace_options_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
+ int i;
char *buf;
int r = 0;
int len = 0;
- int i;
+ u32 tracer_flags = current_trace->flags->val;
+ struct tracer_opt *trace_opts = current_trace->flags->opts;
+
/* calulate max size */
for (i = 0; trace_options[i]; i++) {
@@ -2203,6 +2755,15 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
len += 3; /* "no" and space */
}
+ /*
+ * Increase the size with names of options specific
+ * of the current tracer.
+ */
+ for (i = 0; trace_opts[i].name; i++) {
+ len += strlen(trace_opts[i].name);
+ len += 3; /* "no" and space */
+ }
+
/* +2 for \n and \0 */
buf = kmalloc(len + 2, GFP_KERNEL);
if (!buf)
@@ -2215,6 +2776,15 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
r += sprintf(buf + r, "no%s ", trace_options[i]);
}
+ for (i = 0; trace_opts[i].name; i++) {
+ if (tracer_flags & trace_opts[i].bit)
+ r += sprintf(buf + r, "%s ",
+ trace_opts[i].name);
+ else
+ r += sprintf(buf + r, "no%s ",
+ trace_opts[i].name);
+ }
+
r += sprintf(buf + r, "\n");
WARN_ON(r >= len + 2);
@@ -2225,13 +2795,48 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
return r;
}
+/* Try to assign a tracer specific option */
+static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
+{
+ struct tracer_flags *trace_flags = trace->flags;
+ struct tracer_opt *opts = NULL;
+ int ret = 0, i = 0;
+ int len;
+
+ for (i = 0; trace_flags->opts[i].name; i++) {
+ opts = &trace_flags->opts[i];
+ len = strlen(opts->name);
+
+ if (strncmp(cmp, opts->name, len) == 0) {
+ ret = trace->set_flag(trace_flags->val,
+ opts->bit, !neg);
+ break;
+ }
+ }
+ /* Not found */
+ if (!trace_flags->opts[i].name)
+ return -EINVAL;
+
+ /* Refused to handle */
+ if (ret)
+ return ret;
+
+ if (neg)
+ trace_flags->val &= ~opts->bit;
+ else
+ trace_flags->val |= opts->bit;
+
+ return 0;
+}
+
static ssize_t
-tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
+tracing_trace_options_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
char buf[64];
char *cmp = buf;
int neg = 0;
+ int ret;
int i;
if (cnt >= sizeof(buf))
@@ -2258,11 +2863,13 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
break;
}
}
- /*
- * If no option could be set, return an error:
- */
- if (!trace_options[i])
- return -EINVAL;
+
+ /* If no option could be set, test the specific tracer options */
+ if (!trace_options[i]) {
+ ret = set_tracer_option(current_trace, cmp, neg);
+ if (ret)
+ return ret;
+ }
filp->f_pos += cnt;
@@ -2271,8 +2878,8 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
static struct file_operations tracing_iter_fops = {
.open = tracing_open_generic,
- .read = tracing_iter_ctrl_read,
- .write = tracing_iter_ctrl_write,
+ .read = tracing_trace_options_read,
+ .write = tracing_trace_options_write,
};
static const char readme_msg[] =
@@ -2286,9 +2893,9 @@ static const char readme_msg[] =
"# echo sched_switch > /debug/tracing/current_tracer\n"
"# cat /debug/tracing/current_tracer\n"
"sched_switch\n"
- "# cat /debug/tracing/iter_ctrl\n"
+ "# cat /debug/tracing/trace_options\n"
"noprint-parent nosym-offset nosym-addr noverbose\n"
- "# echo print-parent > /debug/tracing/iter_ctrl\n"
+ "# echo print-parent > /debug/tracing/trace_options\n"
"# echo 1 > /debug/tracing/tracing_enabled\n"
"# cat /debug/tracing/trace > /tmp/trace.txt\n"
"echo 0 > /debug/tracing/tracing_enabled\n"
@@ -2311,11 +2918,10 @@ static ssize_t
tracing_ctrl_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct trace_array *tr = filp->private_data;
char buf[64];
int r;
- r = sprintf(buf, "%ld\n", tr->ctrl);
+ r = sprintf(buf, "%u\n", tracer_enabled);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -2343,16 +2949,18 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
val = !!val;
mutex_lock(&trace_types_lock);
- if (tr->ctrl ^ val) {
- if (val)
+ if (tracer_enabled ^ val) {
+ if (val) {
tracer_enabled = 1;
- else
+ if (current_trace->start)
+ current_trace->start(tr);
+ tracing_start();
+ } else {
tracer_enabled = 0;
-
- tr->ctrl = val;
-
- if (current_trace && current_trace->ctrl_update)
- current_trace->ctrl_update(tr);
+ tracing_stop();
+ if (current_trace->stop)
+ current_trace->stop(tr);
+ }
}
mutex_unlock(&trace_types_lock);
@@ -2378,29 +2986,11 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
-static ssize_t
-tracing_set_trace_write(struct file *filp, const char __user *ubuf,
- size_t cnt, loff_t *ppos)
+static int tracing_set_tracer(char *buf)
{
struct trace_array *tr = &global_trace;
struct tracer *t;
- char buf[max_tracer_type_len+1];
- int i;
- size_t ret;
-
- ret = cnt;
-
- if (cnt > max_tracer_type_len)
- cnt = max_tracer_type_len;
-
- if (copy_from_user(&buf, ubuf, cnt))
- return -EFAULT;
-
- buf[cnt] = 0;
-
- /* strip ending whitespace. */
- for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
- buf[i] = 0;
+ int ret = 0;
mutex_lock(&trace_types_lock);
for (t = trace_types; t; t = t->next) {
@@ -2414,18 +3004,52 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
if (t == current_trace)
goto out;
+ trace_branch_disable();
if (current_trace && current_trace->reset)
current_trace->reset(tr);
current_trace = t;
- if (t->init)
- t->init(tr);
+ if (t->init) {
+ ret = t->init(tr);
+ if (ret)
+ goto out;
+ }
+ trace_branch_enable(tr);
out:
mutex_unlock(&trace_types_lock);
- if (ret > 0)
- filp->f_pos += ret;
+ return ret;
+}
+
+static ssize_t
+tracing_set_trace_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char buf[max_tracer_type_len+1];
+ int i;
+ size_t ret;
+ int err;
+
+ ret = cnt;
+
+ if (cnt > max_tracer_type_len)
+ cnt = max_tracer_type_len;
+
+ if (copy_from_user(&buf, ubuf, cnt))
+ return -EFAULT;
+
+ buf[cnt] = 0;
+
+ /* strip ending whitespace. */
+ for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
+ buf[i] = 0;
+
+ err = tracing_set_tracer(buf);
+ if (err)
+ return err;
+
+ filp->f_pos += ret;
return ret;
}
@@ -2492,6 +3116,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
return -ENOMEM;
mutex_lock(&trace_types_lock);
+
+ /* trace pipe does not show start of buffer */
+ cpus_setall(iter->started);
+
iter->tr = &global_trace;
iter->trace = current_trace;
filp->private_data = iter;
@@ -2667,7 +3295,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
char buf[64];
int r;
- r = sprintf(buf, "%lu\n", tr->entries);
+ r = sprintf(buf, "%lu\n", tr->entries >> 10);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -2678,7 +3306,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
unsigned long val;
char buf[64];
int ret, cpu;
- struct trace_array *tr = filp->private_data;
if (cnt >= sizeof(buf))
return -EINVAL;
@@ -2698,12 +3325,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
mutex_lock(&trace_types_lock);
- if (tr->ctrl) {
- cnt = -EBUSY;
- pr_info("ftrace: please disable tracing"
- " before modifying buffer size\n");
- goto out;
- }
+ tracing_stop();
/* disable all cpu buffers */
for_each_tracing_cpu(cpu) {
@@ -2713,6 +3335,9 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
atomic_inc(&max_tr.data[cpu]->disabled);
}
+ /* value is in KB */
+ val <<= 10;
+
if (val != global_trace.entries) {
ret = ring_buffer_resize(global_trace.buffer, val);
if (ret < 0) {
@@ -2751,6 +3376,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
atomic_dec(&max_tr.data[cpu]->disabled);
}
+ tracing_start();
max_tr.entries = global_trace.entries;
mutex_unlock(&trace_types_lock);
@@ -2762,7 +3388,7 @@ static int mark_printk(const char *fmt, ...)
int ret;
va_list args;
va_start(args, fmt);
- ret = trace_vprintk(0, fmt, args);
+ ret = trace_vprintk(0, -1, fmt, args);
va_end(args);
return ret;
}
@@ -2773,9 +3399,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
{
char *buf;
char *end;
- struct trace_array *tr = &global_trace;
- if (!tr->ctrl || tracing_disabled)
+ if (tracing_disabled)
return -EINVAL;
if (cnt > TRACE_BUF_SIZE)
@@ -2841,22 +3466,38 @@ static struct file_operations tracing_mark_fops = {
#ifdef CONFIG_DYNAMIC_FTRACE
+int __weak ftrace_arch_read_dyn_info(char *buf, int size)
+{
+ return 0;
+}
+
static ssize_t
-tracing_read_long(struct file *filp, char __user *ubuf,
+tracing_read_dyn_info(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
+ static char ftrace_dyn_info_buffer[1024];
+ static DEFINE_MUTEX(dyn_info_mutex);
unsigned long *p = filp->private_data;
- char buf[64];
+ char *buf = ftrace_dyn_info_buffer;
+ int size = ARRAY_SIZE(ftrace_dyn_info_buffer);
int r;
- r = sprintf(buf, "%ld\n", *p);
+ mutex_lock(&dyn_info_mutex);
+ r = sprintf(buf, "%ld ", *p);
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+ r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r);
+ buf[r++] = '\n';
+
+ r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+
+ mutex_unlock(&dyn_info_mutex);
+
+ return r;
}
-static struct file_operations tracing_read_long_fops = {
+static struct file_operations tracing_dyn_info_fops = {
.open = tracing_open_generic,
- .read = tracing_read_long,
+ .read = tracing_read_dyn_info,
};
#endif
@@ -2897,10 +3538,10 @@ static __init int tracer_init_debugfs(void)
if (!entry)
pr_warning("Could not create debugfs 'tracing_enabled' entry\n");
- entry = debugfs_create_file("iter_ctrl", 0644, d_tracer,
+ entry = debugfs_create_file("trace_options", 0644, d_tracer,
NULL, &tracing_iter_fops);
if (!entry)
- pr_warning("Could not create debugfs 'iter_ctrl' entry\n");
+ pr_warning("Could not create debugfs 'trace_options' entry\n");
entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
NULL, &tracing_cpumask_fops);
@@ -2950,11 +3591,11 @@ static __init int tracer_init_debugfs(void)
pr_warning("Could not create debugfs "
"'trace_pipe' entry\n");
- entry = debugfs_create_file("trace_entries", 0644, d_tracer,
+ entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer,
&global_trace, &tracing_entries_fops);
if (!entry)
pr_warning("Could not create debugfs "
- "'trace_entries' entry\n");
+ "'buffer_size_kb' entry\n");
entry = debugfs_create_file("trace_marker", 0220, d_tracer,
NULL, &tracing_mark_fops);
@@ -2965,7 +3606,7 @@ static __init int tracer_init_debugfs(void)
#ifdef CONFIG_DYNAMIC_FTRACE
entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
&ftrace_update_tot_cnt,
- &tracing_read_long_fops);
+ &tracing_dyn_info_fops);
if (!entry)
pr_warning("Could not create debugfs "
"'dyn_ftrace_total_info' entry\n");
@@ -2976,7 +3617,7 @@ static __init int tracer_init_debugfs(void)
return 0;
}
-int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args)
{
static DEFINE_SPINLOCK(trace_buf_lock);
static char trace_buf[TRACE_BUF_SIZE];
@@ -2984,11 +3625,11 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
struct ring_buffer_event *event;
struct trace_array *tr = &global_trace;
struct trace_array_cpu *data;
- struct print_entry *entry;
- unsigned long flags, irq_flags;
int cpu, len = 0, size, pc;
+ struct print_entry *entry;
+ unsigned long irq_flags;
- if (!tr->ctrl || tracing_disabled)
+ if (tracing_disabled || tracing_selftest_running)
return 0;
pc = preempt_count();
@@ -2999,7 +3640,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
if (unlikely(atomic_read(&data->disabled)))
goto out;
- spin_lock_irqsave(&trace_buf_lock, flags);
+ pause_graph_tracing();
+ spin_lock_irqsave(&trace_buf_lock, irq_flags);
len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
len = min(len, TRACE_BUF_SIZE-1);
@@ -3010,17 +3652,18 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
if (!event)
goto out_unlock;
entry = ring_buffer_event_data(event);
- tracing_generic_entry_update(&entry->ent, flags, pc);
+ tracing_generic_entry_update(&entry->ent, irq_flags, pc);
entry->ent.type = TRACE_PRINT;
entry->ip = ip;
+ entry->depth = depth;
memcpy(&entry->buf, trace_buf, len);
entry->buf[len] = 0;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
out_unlock:
- spin_unlock_irqrestore(&trace_buf_lock, flags);
-
+ spin_unlock_irqrestore(&trace_buf_lock, irq_flags);
+ unpause_graph_tracing();
out:
preempt_enable_notrace();
@@ -3037,7 +3680,7 @@ int __ftrace_printk(unsigned long ip, const char *fmt, ...)
return 0;
va_start(ap, fmt);
- ret = trace_vprintk(ip, fmt, ap);
+ ret = trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap);
va_end(ap);
return ret;
}
@@ -3046,7 +3689,8 @@ EXPORT_SYMBOL_GPL(__ftrace_printk);
static int trace_panic_handler(struct notifier_block *this,
unsigned long event, void *unused)
{
- ftrace_dump();
+ if (ftrace_dump_on_oops)
+ ftrace_dump();
return NOTIFY_OK;
}
@@ -3062,7 +3706,8 @@ static int trace_die_handler(struct notifier_block *self,
{
switch (val) {
case DIE_OOPS:
- ftrace_dump();
+ if (ftrace_dump_on_oops)
+ ftrace_dump();
break;
default:
break;
@@ -3103,7 +3748,6 @@ trace_printk_seq(struct trace_seq *s)
trace_seq_reset(s);
}
-
void ftrace_dump(void)
{
static DEFINE_SPINLOCK(ftrace_dump_lock);
@@ -3128,6 +3772,9 @@ void ftrace_dump(void)
atomic_inc(&global_trace.data[cpu]->disabled);
}
+ /* don't look at user memory in panic mode */
+ trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
printk(KERN_TRACE "Dumping ftrace buffer:\n");
iter.tr = &global_trace;
@@ -3221,7 +3868,6 @@ __init static int tracer_alloc_buffers(void)
#endif
/* All seems OK, enable tracing */
- global_trace.ctrl = tracer_enabled;
tracing_disabled = 0;
atomic_notifier_chain_register(&panic_notifier_list,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8465ad05270..cc7a4f86403 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -8,6 +8,7 @@
#include <linux/ring_buffer.h>
#include <linux/mmiotrace.h>
#include <linux/ftrace.h>
+#include <trace/boot.h>
enum trace_type {
__TRACE_FIRST_TYPE = 0,
@@ -21,7 +22,14 @@ enum trace_type {
TRACE_SPECIAL,
TRACE_MMIO_RW,
TRACE_MMIO_MAP,
- TRACE_BOOT,
+ TRACE_BRANCH,
+ TRACE_BOOT_CALL,
+ TRACE_BOOT_RET,
+ TRACE_GRAPH_RET,
+ TRACE_GRAPH_ENT,
+ TRACE_USER_STACK,
+ TRACE_HW_BRANCHES,
+ TRACE_POWER,
__TRACE_LAST_TYPE
};
@@ -38,6 +46,7 @@ struct trace_entry {
unsigned char flags;
unsigned char preempt_count;
int pid;
+ int tgid;
};
/*
@@ -48,6 +57,18 @@ struct ftrace_entry {
unsigned long ip;
unsigned long parent_ip;
};
+
+/* Function call entry */
+struct ftrace_graph_ent_entry {
+ struct trace_entry ent;
+ struct ftrace_graph_ent graph_ent;
+};
+
+/* Function return entry */
+struct ftrace_graph_ret_entry {
+ struct trace_entry ent;
+ struct ftrace_graph_ret ret;
+};
extern struct tracer boot_tracer;
/*
@@ -85,12 +106,18 @@ struct stack_entry {
unsigned long caller[FTRACE_STACK_ENTRIES];
};
+struct userstack_entry {
+ struct trace_entry ent;
+ unsigned long caller[FTRACE_STACK_ENTRIES];
+};
+
/*
* ftrace_printk entry:
*/
struct print_entry {
struct trace_entry ent;
unsigned long ip;
+ int depth;
char buf[];
};
@@ -112,9 +139,35 @@ struct trace_mmiotrace_map {
struct mmiotrace_map map;
};
-struct trace_boot {
+struct trace_boot_call {
struct trace_entry ent;
- struct boot_trace initcall;
+ struct boot_trace_call boot_call;
+};
+
+struct trace_boot_ret {
+ struct trace_entry ent;
+ struct boot_trace_ret boot_ret;
+};
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+struct trace_branch {
+ struct trace_entry ent;
+ unsigned line;
+ char func[TRACE_FUNC_SIZE+1];
+ char file[TRACE_FILE_SIZE+1];
+ char correct;
+};
+
+struct hw_branch_entry {
+ struct trace_entry ent;
+ u64 from;
+ u64 to;
+};
+
+struct trace_power {
+ struct trace_entry ent;
+ struct power_trace state_data;
};
/*
@@ -172,7 +225,6 @@ struct trace_iterator;
struct trace_array {
struct ring_buffer *buffer;
unsigned long entries;
- long ctrl;
int cpu;
cycle_t time_start;
struct task_struct *waiter;
@@ -212,13 +264,22 @@ extern void __ftrace_bad_type(void);
IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \
IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \
+ IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
IF_ASSIGN(var, ent, struct special_entry, 0); \
IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
TRACE_MMIO_RW); \
IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \
TRACE_MMIO_MAP); \
- IF_ASSIGN(var, ent, struct trace_boot, TRACE_BOOT); \
+ IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
+ IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
+ IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
+ IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \
+ TRACE_GRAPH_ENT); \
+ IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \
+ TRACE_GRAPH_RET); \
+ IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
+ IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
__ftrace_bad_type(); \
} while (0)
@@ -229,29 +290,56 @@ enum print_line_t {
TRACE_TYPE_UNHANDLED = 2 /* Relay to other output functions */
};
+
+/*
+ * An option specific to a tracer. This is a boolean value.
+ * The bit is the bit index that sets its value on the
+ * flags value in struct tracer_flags.
+ */
+struct tracer_opt {
+ const char *name; /* Will appear on the trace_options file */
+ u32 bit; /* Mask assigned in val field in tracer_flags */
+};
+
+/*
+ * The set of specific options for a tracer. Your tracer
+ * have to set the initial value of the flags val.
+ */
+struct tracer_flags {
+ u32 val;
+ struct tracer_opt *opts;
+};
+
+/* Makes more easy to define a tracer opt */
+#define TRACER_OPT(s, b) .name = #s, .bit = b
+
/*
* A specific tracer, represented by methods that operate on a trace array:
*/
struct tracer {
const char *name;
- void (*init)(struct trace_array *tr);
+ /* Your tracer should raise a warning if init fails */
+ int (*init)(struct trace_array *tr);
void (*reset)(struct trace_array *tr);
+ void (*start)(struct trace_array *tr);
+ void (*stop)(struct trace_array *tr);
void (*open)(struct trace_iterator *iter);
void (*pipe_open)(struct trace_iterator *iter);
void (*close)(struct trace_iterator *iter);
- void (*start)(struct trace_iterator *iter);
- void (*stop)(struct trace_iterator *iter);
ssize_t (*read)(struct trace_iterator *iter,
struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos);
- void (*ctrl_update)(struct trace_array *tr);
#ifdef CONFIG_FTRACE_STARTUP_TEST
int (*selftest)(struct tracer *trace,
struct trace_array *tr);
#endif
+ void (*print_header)(struct seq_file *m);
enum print_line_t (*print_line)(struct trace_iterator *iter);
+ /* If you handled the flag setting, return 0 */
+ int (*set_flag)(u32 old_flags, u32 bit, int set);
struct tracer *next;
int print_max;
+ struct tracer_flags *flags;
};
struct trace_seq {
@@ -279,10 +367,14 @@ struct trace_iterator {
unsigned long iter_flags;
loff_t pos;
long idx;
+
+ cpumask_t started;
};
+int tracing_is_enabled(void);
void trace_wake_up(void);
void tracing_reset(struct trace_array *tr, int cpu);
+void tracing_reset_online_cpus(struct trace_array *tr);
int tracing_open_generic(struct inode *inode, struct file *filp);
struct dentry *tracing_init_dentry(void);
void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
@@ -321,8 +413,15 @@ void trace_function(struct trace_array *tr,
unsigned long parent_ip,
unsigned long flags, int pc);
+void trace_graph_return(struct ftrace_graph_ret *trace);
+int trace_graph_entry(struct ftrace_graph_ent *trace);
+void trace_hw_branch(struct trace_array *tr, u64 from, u64 to);
+
void tracing_start_cmdline_record(void);
void tracing_stop_cmdline_record(void);
+void tracing_sched_switch_assign_trace(struct trace_array *tr);
+void tracing_stop_sched_switch_record(void);
+void tracing_start_sched_switch_record(void);
int register_tracer(struct tracer *type);
void unregister_tracer(struct tracer *type);
@@ -358,6 +457,7 @@ struct tracer_switch_ops {
struct tracer_switch_ops *next;
};
+char *trace_find_cmdline(int pid);
#endif /* CONFIG_CONTEXT_SWITCH_TRACER */
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -383,19 +483,79 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace,
struct trace_array *tr);
extern int trace_selftest_startup_sysprof(struct tracer *trace,
struct trace_array *tr);
+extern int trace_selftest_startup_branch(struct tracer *trace,
+ struct trace_array *tr);
#endif /* CONFIG_FTRACE_STARTUP_TEST */
extern void *head_page(struct trace_array_cpu *data);
extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
extern void trace_seq_print_cont(struct trace_seq *s,
struct trace_iterator *iter);
+
+extern int
+seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
+ unsigned long sym_flags);
extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
size_t cnt);
extern long ns2usecs(cycle_t nsec);
-extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args);
extern unsigned long trace_flags;
+/* Standard output formatting function used for function return traces */
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+extern enum print_line_t print_graph_function(struct trace_iterator *iter);
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/* TODO: make this variable */
+#define FTRACE_GRAPH_MAX_FUNCS 32
+extern int ftrace_graph_count;
+extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
+
+static inline int ftrace_graph_addr(unsigned long addr)
+{
+ int i;
+
+ if (!ftrace_graph_count || test_tsk_trace_graph(current))
+ return 1;
+
+ for (i = 0; i < ftrace_graph_count; i++) {
+ if (addr == ftrace_graph_funcs[i])
+ return 1;
+ }
+
+ return 0;
+}
+#else
+static inline int ftrace_trace_addr(unsigned long addr)
+{
+ return 1;
+}
+static inline int ftrace_graph_addr(unsigned long addr)
+{
+ return 1;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#else /* CONFIG_FUNCTION_GRAPH_TRACER */
+static inline enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+ return TRACE_TYPE_UNHANDLED;
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+extern struct pid *ftrace_pid_trace;
+
+static inline int ftrace_trace_task(struct task_struct *task)
+{
+ if (!ftrace_pid_trace)
+ return 1;
+
+ return test_tsk_trace_trace(task);
+}
+
/*
* trace_iterator_flags is an enumeration that defines bit
* positions into trace_flags that controls the output.
@@ -415,8 +575,93 @@ enum trace_iterator_flags {
TRACE_ITER_STACKTRACE = 0x100,
TRACE_ITER_SCHED_TREE = 0x200,
TRACE_ITER_PRINTK = 0x400,
+ TRACE_ITER_PREEMPTONLY = 0x800,
+ TRACE_ITER_BRANCH = 0x1000,
+ TRACE_ITER_ANNOTATE = 0x2000,
+ TRACE_ITER_USERSTACKTRACE = 0x4000,
+ TRACE_ITER_SYM_USEROBJ = 0x8000,
+ TRACE_ITER_PRINTK_MSGONLY = 0x10000
};
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
+#define TRACE_ITER_SYM_MASK \
+ (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
+
extern struct tracer nop_trace;
+/**
+ * ftrace_preempt_disable - disable preemption scheduler safe
+ *
+ * When tracing can happen inside the scheduler, there exists
+ * cases that the tracing might happen before the need_resched
+ * flag is checked. If this happens and the tracer calls
+ * preempt_enable (after a disable), a schedule might take place
+ * causing an infinite recursion.
+ *
+ * To prevent this, we read the need_recshed flag before
+ * disabling preemption. When we want to enable preemption we
+ * check the flag, if it is set, then we call preempt_enable_no_resched.
+ * Otherwise, we call preempt_enable.
+ *
+ * The rational for doing the above is that if need resched is set
+ * and we have yet to reschedule, we are either in an atomic location
+ * (where we do not need to check for scheduling) or we are inside
+ * the scheduler and do not want to resched.
+ */
+static inline int ftrace_preempt_disable(void)
+{
+ int resched;
+
+ resched = need_resched();
+ preempt_disable_notrace();
+
+ return resched;
+}
+
+/**
+ * ftrace_preempt_enable - enable preemption scheduler safe
+ * @resched: the return value from ftrace_preempt_disable
+ *
+ * This is a scheduler safe way to enable preemption and not miss
+ * any preemption checks. The disabled saved the state of preemption.
+ * If resched is set, then we were either inside an atomic or
+ * are inside the scheduler (we would have already scheduled
+ * otherwise). In this case, we do not want to call normal
+ * preempt_enable, but preempt_enable_no_resched instead.
+ */
+static inline void ftrace_preempt_enable(int resched)
+{
+ if (resched)
+ preempt_enable_no_resched_notrace();
+ else
+ preempt_enable_notrace();
+}
+
+#ifdef CONFIG_BRANCH_TRACER
+extern int enable_branch_tracing(struct trace_array *tr);
+extern void disable_branch_tracing(void);
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+ if (trace_flags & TRACE_ITER_BRANCH)
+ return enable_branch_tracing(tr);
+ return 0;
+}
+static inline void trace_branch_disable(void)
+{
+ /* due to races, always disable */
+ disable_branch_tracing();
+}
+#else
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+ return 0;
+}
+static inline void trace_branch_disable(void)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index d0a5e50eeff..3ccebde2848 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -13,101 +13,161 @@
#include "trace.h"
static struct trace_array *boot_trace;
-static int trace_boot_enabled;
+static bool pre_initcalls_finished;
-
-/* Should be started after do_pre_smp_initcalls() in init/main.c */
+/* Tells the boot tracer that the pre_smp_initcalls are finished.
+ * So we are ready .
+ * It doesn't enable sched events tracing however.
+ * You have to call enable_boot_trace to do so.
+ */
void start_boot_trace(void)
{
- trace_boot_enabled = 1;
+ pre_initcalls_finished = true;
}
-void stop_boot_trace(void)
+void enable_boot_trace(void)
{
- trace_boot_enabled = 0;
+ if (pre_initcalls_finished)
+ tracing_start_sched_switch_record();
}
-void reset_boot_trace(struct trace_array *tr)
+void disable_boot_trace(void)
{
- stop_boot_trace();
+ if (pre_initcalls_finished)
+ tracing_stop_sched_switch_record();
}
-static void boot_trace_init(struct trace_array *tr)
+static int boot_trace_init(struct trace_array *tr)
{
int cpu;
boot_trace = tr;
- trace_boot_enabled = 0;
-
for_each_cpu_mask(cpu, cpu_possible_map)
tracing_reset(tr, cpu);
+
+ tracing_sched_switch_assign_trace(tr);
+ return 0;
}
-static void boot_trace_ctrl_update(struct trace_array *tr)
+static enum print_line_t
+initcall_call_print_line(struct trace_iterator *iter)
{
- if (tr->ctrl)
- start_boot_trace();
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *s = &iter->seq;
+ struct trace_boot_call *field;
+ struct boot_trace_call *call;
+ u64 ts;
+ unsigned long nsec_rem;
+ int ret;
+
+ trace_assign_type(field, entry);
+ call = &field->boot_call;
+ ts = iter->ts;
+ nsec_rem = do_div(ts, 1000000000);
+
+ ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n",
+ (unsigned long)ts, nsec_rem, call->func, call->caller);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
else
- stop_boot_trace();
+ return TRACE_TYPE_HANDLED;
}
-static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+static enum print_line_t
+initcall_ret_print_line(struct trace_iterator *iter)
{
- int ret;
struct trace_entry *entry = iter->ent;
- struct trace_boot *field = (struct trace_boot *)entry;
- struct boot_trace *it = &field->initcall;
struct trace_seq *s = &iter->seq;
- struct timespec calltime = ktime_to_timespec(it->calltime);
- struct timespec rettime = ktime_to_timespec(it->rettime);
-
- if (entry->type == TRACE_BOOT) {
- ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n",
- calltime.tv_sec,
- calltime.tv_nsec,
- it->func, it->caller);
- if (!ret)
- return TRACE_TYPE_PARTIAL_LINE;
-
- ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
- "returned %d after %lld msecs\n",
- rettime.tv_sec,
- rettime.tv_nsec,
- it->func, it->result, it->duration);
-
- if (!ret)
- return TRACE_TYPE_PARTIAL_LINE;
+ struct trace_boot_ret *field;
+ struct boot_trace_ret *init_ret;
+ u64 ts;
+ unsigned long nsec_rem;
+ int ret;
+
+ trace_assign_type(field, entry);
+ init_ret = &field->boot_ret;
+ ts = iter->ts;
+ nsec_rem = do_div(ts, 1000000000);
+
+ ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
+ "returned %d after %llu msecs\n",
+ (unsigned long) ts,
+ nsec_rem,
+ init_ret->func, init_ret->result, init_ret->duration);
+
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ else
return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+
+ switch (entry->type) {
+ case TRACE_BOOT_CALL:
+ return initcall_call_print_line(iter);
+ case TRACE_BOOT_RET:
+ return initcall_ret_print_line(iter);
+ default:
+ return TRACE_TYPE_UNHANDLED;
}
- return TRACE_TYPE_UNHANDLED;
}
struct tracer boot_tracer __read_mostly =
{
.name = "initcall",
.init = boot_trace_init,
- .reset = reset_boot_trace,
- .ctrl_update = boot_trace_ctrl_update,
+ .reset = tracing_reset_online_cpus,
.print_line = initcall_print_line,
};
-void trace_boot(struct boot_trace *it, initcall_t fn)
+void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
{
struct ring_buffer_event *event;
- struct trace_boot *entry;
- struct trace_array_cpu *data;
+ struct trace_boot_call *entry;
unsigned long irq_flags;
struct trace_array *tr = boot_trace;
- if (!trace_boot_enabled)
+ if (!pre_initcalls_finished)
return;
/* Get its name now since this function could
* disappear because it is in the .init section.
*/
- sprint_symbol(it->func, (unsigned long)fn);
+ sprint_symbol(bt->func, (unsigned long)fn);
+ preempt_disable();
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+ entry->ent.type = TRACE_BOOT_CALL;
+ entry->boot_call = *bt;
+ ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ trace_wake_up();
+
+ out:
+ preempt_enable();
+}
+
+void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
+{
+ struct ring_buffer_event *event;
+ struct trace_boot_ret *entry;
+ unsigned long irq_flags;
+ struct trace_array *tr = boot_trace;
+
+ if (!pre_initcalls_finished)
+ return;
+
+ sprint_symbol(bt->func, (unsigned long)fn);
preempt_disable();
- data = tr->data[smp_processor_id()];
event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
&irq_flags);
@@ -115,8 +175,8 @@ void trace_boot(struct boot_trace *it, initcall_t fn)
goto out;
entry = ring_buffer_event_data(event);
tracing_generic_entry_update(&entry->ent, 0, 0);
- entry->ent.type = TRACE_BOOT;
- entry->initcall = *it;
+ entry->ent.type = TRACE_BOOT_RET;
+ entry->boot_ret = *bt;
ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
trace_wake_up();
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
new file mode 100644
index 00000000000..6c00feb3bac
--- /dev/null
+++ b/kernel/trace/trace_branch.c
@@ -0,0 +1,342 @@
+/*
+ * unlikely profiler
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/irqflags.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/hash.h>
+#include <linux/fs.h>
+#include <asm/local.h>
+#include "trace.h"
+
+#ifdef CONFIG_BRANCH_TRACER
+
+static int branch_tracing_enabled __read_mostly;
+static DEFINE_MUTEX(branch_tracing_mutex);
+static struct trace_array *branch_tracer;
+
+static void
+probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+ struct trace_array *tr = branch_tracer;
+ struct ring_buffer_event *event;
+ struct trace_branch *entry;
+ unsigned long flags, irq_flags;
+ int cpu, pc;
+ const char *p;
+
+ /*
+ * I would love to save just the ftrace_likely_data pointer, but
+ * this code can also be used by modules. Ugly things can happen
+ * if the module is unloaded, and then we go and read the
+ * pointer. This is slower, but much safer.
+ */
+
+ if (unlikely(!tr))
+ return;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+ goto out;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ goto out;
+
+ pc = preempt_count();
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, flags, pc);
+ entry->ent.type = TRACE_BRANCH;
+
+ /* Strip off the path, only save the file */
+ p = f->file + strlen(f->file);
+ while (p >= f->file && *p != '/')
+ p--;
+ p++;
+
+ strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
+ strncpy(entry->file, p, TRACE_FILE_SIZE);
+ entry->func[TRACE_FUNC_SIZE] = 0;
+ entry->file[TRACE_FILE_SIZE] = 0;
+ entry->line = f->line;
+ entry->correct = val == expect;
+
+ ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ out:
+ atomic_dec(&tr->data[cpu]->disabled);
+ local_irq_restore(flags);
+}
+
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+ if (!branch_tracing_enabled)
+ return;
+
+ probe_likely_condition(f, val, expect);
+}
+
+int enable_branch_tracing(struct trace_array *tr)
+{
+ int ret = 0;
+
+ mutex_lock(&branch_tracing_mutex);
+ branch_tracer = tr;
+ /*
+ * Must be seen before enabling. The reader is a condition
+ * where we do not need a matching rmb()
+ */
+ smp_wmb();
+ branch_tracing_enabled++;
+ mutex_unlock(&branch_tracing_mutex);
+
+ return ret;
+}
+
+void disable_branch_tracing(void)
+{
+ mutex_lock(&branch_tracing_mutex);
+
+ if (!branch_tracing_enabled)
+ goto out_unlock;
+
+ branch_tracing_enabled--;
+
+ out_unlock:
+ mutex_unlock(&branch_tracing_mutex);
+}
+
+static void start_branch_trace(struct trace_array *tr)
+{
+ enable_branch_tracing(tr);
+}
+
+static void stop_branch_trace(struct trace_array *tr)
+{
+ disable_branch_tracing();
+}
+
+static int branch_trace_init(struct trace_array *tr)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr, cpu);
+
+ start_branch_trace(tr);
+ return 0;
+}
+
+static void branch_trace_reset(struct trace_array *tr)
+{
+ stop_branch_trace(tr);
+}
+
+struct tracer branch_trace __read_mostly =
+{
+ .name = "branch",
+ .init = branch_trace_init,
+ .reset = branch_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+ .selftest = trace_selftest_startup_branch,
+#endif
+};
+
+__init static int init_branch_trace(void)
+{
+ return register_tracer(&branch_trace);
+}
+
+device_initcall(init_branch_trace);
+#else
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
+{
+ /*
+ * I would love to have a trace point here instead, but the
+ * trace point code is so inundated with unlikely and likely
+ * conditions that the recursive nightmare that exists is too
+ * much to try to get working. At least for now.
+ */
+ trace_likely_condition(f, val, expect);
+
+ /* FIXME: Make this atomic! */
+ if (val == expect)
+ f->correct++;
+ else
+ f->incorrect++;
+}
+EXPORT_SYMBOL(ftrace_likely_update);
+
+struct ftrace_pointer {
+ void *start;
+ void *stop;
+ int hit;
+};
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ const struct ftrace_pointer *f = m->private;
+ struct ftrace_branch_data *p = v;
+
+ (*pos)++;
+
+ if (v == (void *)1)
+ return f->start;
+
+ ++p;
+
+ if ((void *)p >= (void *)f->stop)
+ return NULL;
+
+ return p;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+ void *t = (void *)1;
+ loff_t l = 0;
+
+ for (; t && l < *pos; t = t_next(m, t, &l))
+ ;
+
+ return t;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+ const struct ftrace_pointer *fp = m->private;
+ struct ftrace_branch_data *p = v;
+ const char *f;
+ long percent;
+
+ if (v == (void *)1) {
+ if (fp->hit)
+ seq_printf(m, " miss hit %% ");
+ else
+ seq_printf(m, " correct incorrect %% ");
+ seq_printf(m, " Function "
+ " File Line\n"
+ " ------- --------- - "
+ " -------- "
+ " ---- ----\n");
+ return 0;
+ }
+
+ /* Only print the file, not the path */
+ f = p->file + strlen(p->file);
+ while (f >= p->file && *f != '/')
+ f--;
+ f++;
+
+ /*
+ * The miss is overlayed on correct, and hit on incorrect.
+ */
+ if (p->correct) {
+ percent = p->incorrect * 100;
+ percent /= p->correct + p->incorrect;
+ } else
+ percent = p->incorrect ? 100 : -1;
+
+ seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect);
+ if (percent < 0)
+ seq_printf(m, " X ");
+ else
+ seq_printf(m, "%3ld ", percent);
+ seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
+ return 0;
+}
+
+static struct seq_operations tracing_likely_seq_ops = {
+ .start = t_start,
+ .next = t_next,
+ .stop = t_stop,
+ .show = t_show,
+};
+
+static int tracing_branch_open(struct inode *inode, struct file *file)
+{
+ int ret;
+
+ ret = seq_open(file, &tracing_likely_seq_ops);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = (void *)inode->i_private;
+ }
+
+ return ret;
+}
+
+static const struct file_operations tracing_branch_fops = {
+ .open = tracing_branch_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+};
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+extern unsigned long __start_branch_profile[];
+extern unsigned long __stop_branch_profile[];
+
+static const struct ftrace_pointer ftrace_branch_pos = {
+ .start = __start_branch_profile,
+ .stop = __stop_branch_profile,
+ .hit = 1,
+};
+
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
+
+extern unsigned long __start_annotated_branch_profile[];
+extern unsigned long __stop_annotated_branch_profile[];
+
+static const struct ftrace_pointer ftrace_annotated_branch_pos = {
+ .start = __start_annotated_branch_profile,
+ .stop = __stop_annotated_branch_profile,
+};
+
+static __init int ftrace_branch_init(void)
+{
+ struct dentry *d_tracer;
+ struct dentry *entry;
+
+ d_tracer = tracing_init_dentry();
+
+ entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer,
+ (void *)&ftrace_annotated_branch_pos,
+ &tracing_branch_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs "
+ "'profile_annotatet_branch' entry\n");
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+ entry = debugfs_create_file("profile_branch", 0444, d_tracer,
+ (void *)&ftrace_branch_pos,
+ &tracing_branch_fops);
+ if (!entry)
+ pr_warning("Could not create debugfs"
+ " 'profile_branch' entry\n");
+#endif
+
+ return 0;
+}
+
+device_initcall(ftrace_branch_init);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 0f85a64003d..9236d7e25a1 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -16,20 +16,10 @@
#include "trace.h"
-static void function_reset(struct trace_array *tr)
-{
- int cpu;
-
- tr->time_start = ftrace_now(tr->cpu);
-
- for_each_online_cpu(cpu)
- tracing_reset(tr, cpu);
-}
-
static void start_function_trace(struct trace_array *tr)
{
tr->cpu = get_cpu();
- function_reset(tr);
+ tracing_reset_online_cpus(tr);
put_cpu();
tracing_start_cmdline_record();
@@ -42,24 +32,20 @@ static void stop_function_trace(struct trace_array *tr)
tracing_stop_cmdline_record();
}
-static void function_trace_init(struct trace_array *tr)
+static int function_trace_init(struct trace_array *tr)
{
- if (tr->ctrl)
- start_function_trace(tr);
+ start_function_trace(tr);
+ return 0;
}
static void function_trace_reset(struct trace_array *tr)
{
- if (tr->ctrl)
- stop_function_trace(tr);
+ stop_function_trace(tr);
}
-static void function_trace_ctrl_update(struct trace_array *tr)
+static void function_trace_start(struct trace_array *tr)
{
- if (tr->ctrl)
- start_function_trace(tr);
- else
- stop_function_trace(tr);
+ tracing_reset_online_cpus(tr);
}
static struct tracer function_trace __read_mostly =
@@ -67,7 +53,7 @@ static struct tracer function_trace __read_mostly =
.name = "function",
.init = function_trace_init,
.reset = function_trace_reset,
- .ctrl_update = function_trace_ctrl_update,
+ .start = function_trace_start,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_function,
#endif
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
new file mode 100644
index 00000000000..4bf39fcae97
--- /dev/null
+++ b/kernel/trace/trace_functions_graph.c
@@ -0,0 +1,669 @@
+/*
+ *
+ * Function graph tracer.
+ * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Mostly borrowed from function tracer which
+ * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+#define TRACE_GRAPH_INDENT 2
+
+/* Flag options */
+#define TRACE_GRAPH_PRINT_OVERRUN 0x1
+#define TRACE_GRAPH_PRINT_CPU 0x2
+#define TRACE_GRAPH_PRINT_OVERHEAD 0x4
+#define TRACE_GRAPH_PRINT_PROC 0x8
+
+static struct tracer_opt trace_opts[] = {
+ /* Display overruns ? */
+ { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
+ /* Display CPU ? */
+ { TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) },
+ /* Display Overhead ? */
+ { TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) },
+ /* Display proc name/pid */
+ { TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) },
+ { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+ /* Don't display overruns and proc by default */
+ .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD,
+ .opts = trace_opts
+};
+
+/* pid on the last trace processed */
+static pid_t last_pid[NR_CPUS] = { [0 ... NR_CPUS-1] = -1 };
+
+static int graph_trace_init(struct trace_array *tr)
+{
+ int cpu, ret;
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr, cpu);
+
+ ret = register_ftrace_graph(&trace_graph_return,
+ &trace_graph_entry);
+ if (ret)
+ return ret;
+ tracing_start_cmdline_record();
+
+ return 0;
+}
+
+static void graph_trace_reset(struct trace_array *tr)
+{
+ tracing_stop_cmdline_record();
+ unregister_ftrace_graph();
+}
+
+static inline int log10_cpu(int nb)
+{
+ if (nb / 100)
+ return 3;
+ if (nb / 10)
+ return 2;
+ return 1;
+}
+
+static enum print_line_t
+print_graph_cpu(struct trace_seq *s, int cpu)
+{
+ int i;
+ int ret;
+ int log10_this = log10_cpu(cpu);
+ int log10_all = log10_cpu(cpus_weight_nr(cpu_online_map));
+
+
+ /*
+ * Start with a space character - to make it stand out
+ * to the right a bit when trace output is pasted into
+ * email:
+ */
+ ret = trace_seq_printf(s, " ");
+
+ /*
+ * Tricky - we space the CPU field according to the max
+ * number of online CPUs. On a 2-cpu system it would take
+ * a maximum of 1 digit - on a 128 cpu system it would
+ * take up to 3 digits:
+ */
+ for (i = 0; i < log10_all - log10_this; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ ret = trace_seq_printf(s, "%d) ", cpu);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+#define TRACE_GRAPH_PROCINFO_LENGTH 14
+
+static enum print_line_t
+print_graph_proc(struct trace_seq *s, pid_t pid)
+{
+ int i;
+ int ret;
+ int len;
+ char comm[8];
+ int spaces = 0;
+ /* sign + log10(MAX_INT) + '\0' */
+ char pid_str[11];
+
+ strncpy(comm, trace_find_cmdline(pid), 7);
+ comm[7] = '\0';
+ sprintf(pid_str, "%d", pid);
+
+ /* 1 stands for the "-" character */
+ len = strlen(comm) + strlen(pid_str) + 1;
+
+ if (len < TRACE_GRAPH_PROCINFO_LENGTH)
+ spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;
+
+ /* First spaces to align center */
+ for (i = 0; i < spaces / 2; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "%s-%s", comm, pid_str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Last spaces to align center */
+ for (i = 0; i < spaces - (spaces / 2); i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ return TRACE_TYPE_HANDLED;
+}
+
+
+/* If the pid changed since the last trace, output this event */
+static enum print_line_t
+verif_pid(struct trace_seq *s, pid_t pid, int cpu)
+{
+ pid_t prev_pid;
+ int ret;
+
+ if (last_pid[cpu] != -1 && last_pid[cpu] == pid)
+ return TRACE_TYPE_HANDLED;
+
+ prev_pid = last_pid[cpu];
+ last_pid[cpu] = pid;
+
+/*
+ * Context-switch trace line:
+
+ ------------------------------------------
+ | 1) migration/0--1 => sshd-1755
+ ------------------------------------------
+
+ */
+ ret = trace_seq_printf(s,
+ " ------------------------------------------\n");
+ if (!ret)
+ TRACE_TYPE_PARTIAL_LINE;
+
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ TRACE_TYPE_PARTIAL_LINE;
+
+ ret = print_graph_proc(s, prev_pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " => ");
+ if (!ret)
+ TRACE_TYPE_PARTIAL_LINE;
+
+ ret = print_graph_proc(s, pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s,
+ "\n ------------------------------------------\n\n");
+ if (!ret)
+ TRACE_TYPE_PARTIAL_LINE;
+
+ return ret;
+}
+
+static bool
+trace_branch_is_leaf(struct trace_iterator *iter,
+ struct ftrace_graph_ent_entry *curr)
+{
+ struct ring_buffer_iter *ring_iter;
+ struct ring_buffer_event *event;
+ struct ftrace_graph_ret_entry *next;
+
+ ring_iter = iter->buffer_iter[iter->cpu];
+
+ if (!ring_iter)
+ return false;
+
+ event = ring_buffer_iter_peek(ring_iter, NULL);
+
+ if (!event)
+ return false;
+
+ next = ring_buffer_event_data(event);
+
+ if (next->ent.type != TRACE_GRAPH_RET)
+ return false;
+
+ if (curr->ent.pid != next->ent.pid ||
+ curr->graph_ent.func != next->ret.func)
+ return false;
+
+ return true;
+}
+
+static enum print_line_t
+print_graph_irq(struct trace_seq *s, unsigned long addr,
+ enum trace_type type, int cpu, pid_t pid)
+{
+ int ret;
+
+ if (addr < (unsigned long)__irqentry_text_start ||
+ addr >= (unsigned long)__irqentry_text_end)
+ return TRACE_TYPE_UNHANDLED;
+
+ if (type == TRACE_GRAPH_ENT) {
+ ret = trace_seq_printf(s, "==========> | ");
+ } else {
+ /* Cpu */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+ /* Proc */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ ret = print_graph_proc(s, pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* No overhead */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "<========== |\n");
+ }
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s)
+{
+ unsigned long nsecs_rem = do_div(duration, 1000);
+ /* log10(ULONG_MAX) + '\0' */
+ char msecs_str[21];
+ char nsecs_str[5];
+ int ret, len;
+ int i;
+
+ sprintf(msecs_str, "%lu", (unsigned long) duration);
+
+ /* Print msecs */
+ ret = trace_seq_printf(s, msecs_str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ len = strlen(msecs_str);
+
+ /* Print nsecs (we don't want to exceed 7 numbers) */
+ if (len < 7) {
+ snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
+ ret = trace_seq_printf(s, ".%s", nsecs_str);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ len += strlen(nsecs_str);
+ }
+
+ ret = trace_seq_printf(s, " us ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Print remaining spaces to fit the row's width */
+ for (i = len; i < 7; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "| ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ return TRACE_TYPE_HANDLED;
+
+}
+
+/* Signal a overhead of time execution to the output */
+static int
+print_graph_overhead(unsigned long long duration, struct trace_seq *s)
+{
+ /* Duration exceeded 100 msecs */
+ if (duration > 100000ULL)
+ return trace_seq_printf(s, "! ");
+
+ /* Duration exceeded 10 msecs */
+ if (duration > 10000ULL)
+ return trace_seq_printf(s, "+ ");
+
+ return trace_seq_printf(s, " ");
+}
+
+/* Case of a leaf function on its call entry */
+static enum print_line_t
+print_graph_entry_leaf(struct trace_iterator *iter,
+ struct ftrace_graph_ent_entry *entry, struct trace_seq *s)
+{
+ struct ftrace_graph_ret_entry *ret_entry;
+ struct ftrace_graph_ret *graph_ret;
+ struct ring_buffer_event *event;
+ struct ftrace_graph_ent *call;
+ unsigned long long duration;
+ int ret;
+ int i;
+
+ event = ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+ ret_entry = ring_buffer_event_data(event);
+ graph_ret = &ret_entry->ret;
+ call = &entry->graph_ent;
+ duration = graph_ret->rettime - graph_ret->calltime;
+
+ /* Overhead */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ ret = print_graph_overhead(duration, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Duration */
+ ret = print_graph_duration(duration, s);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Function */
+ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = seq_print_ip_sym(s, call->func, 0);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, "();\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_entry_nested(struct ftrace_graph_ent_entry *entry,
+ struct trace_seq *s, pid_t pid, int cpu)
+{
+ int i;
+ int ret;
+ struct ftrace_graph_ent *call = &entry->graph_ent;
+
+ /* No overhead */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Interrupt */
+ ret = print_graph_irq(s, call->func, TRACE_GRAPH_ENT, cpu, pid);
+ if (ret == TRACE_TYPE_UNHANDLED) {
+ /* No time */
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ } else {
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+
+ /* Function */
+ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = seq_print_ip_sym(s, call->func, 0);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, "() {\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
+ struct trace_iterator *iter, int cpu)
+{
+ int ret;
+ struct trace_entry *ent = iter->ent;
+
+ /* Pid */
+ if (verif_pid(s, ent->pid, cpu) == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Cpu */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Proc */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ ret = print_graph_proc(s, ent->pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ if (trace_branch_is_leaf(iter, field))
+ return print_graph_entry_leaf(iter, field, s);
+ else
+ return print_graph_entry_nested(field, s, iter->ent->pid, cpu);
+
+}
+
+static enum print_line_t
+print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
+ struct trace_entry *ent, int cpu)
+{
+ int i;
+ int ret;
+ unsigned long long duration = trace->rettime - trace->calltime;
+
+ /* Pid */
+ if (verif_pid(s, ent->pid, cpu) == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Cpu */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ ret = print_graph_cpu(s, cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Proc */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ ret = print_graph_proc(s, ent->pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Overhead */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ ret = print_graph_overhead(duration, s);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Duration */
+ ret = print_graph_duration(duration, s);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Closing brace */
+ for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = trace_seq_printf(s, "}\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Overrun */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
+ ret = trace_seq_printf(s, " (Overruns: %lu)\n",
+ trace->overrun);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ ret = print_graph_irq(s, trace->func, TRACE_GRAPH_RET, cpu, ent->pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+print_graph_comment(struct print_entry *trace, struct trace_seq *s,
+ struct trace_entry *ent, struct trace_iterator *iter)
+{
+ int i;
+ int ret;
+
+ /* Pid */
+ if (verif_pid(s, ent->pid, iter->cpu) == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Cpu */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) {
+ ret = print_graph_cpu(s, iter->cpu);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* Proc */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) {
+ ret = print_graph_proc(s, ent->pid);
+ if (ret == TRACE_TYPE_PARTIAL_LINE)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* No overhead */
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* No time */
+ ret = trace_seq_printf(s, " | ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ /* Indentation */
+ if (trace->depth > 0)
+ for (i = 0; i < (trace->depth + 1) * TRACE_GRAPH_INDENT; i++) {
+ ret = trace_seq_printf(s, " ");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ }
+
+ /* The comment */
+ ret = trace_seq_printf(s, "/* %s", trace->buf);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (ent->flags & TRACE_FLAG_CONT)
+ trace_seq_print_cont(s, iter);
+
+ ret = trace_seq_printf(s, " */\n");
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+
+enum print_line_t
+print_graph_function(struct trace_iterator *iter)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+
+ switch (entry->type) {
+ case TRACE_GRAPH_ENT: {
+ struct ftrace_graph_ent_entry *field;
+ trace_assign_type(field, entry);
+ return print_graph_entry(field, s, iter,
+ iter->cpu);
+ }
+ case TRACE_GRAPH_RET: {
+ struct ftrace_graph_ret_entry *field;
+ trace_assign_type(field, entry);
+ return print_graph_return(&field->ret, s, entry, iter->cpu);
+ }
+ case TRACE_PRINT: {
+ struct print_entry *field;
+ trace_assign_type(field, entry);
+ return print_graph_comment(field, s, entry, iter);
+ }
+ default:
+ return TRACE_TYPE_UNHANDLED;
+ }
+}
+
+static void print_graph_headers(struct seq_file *s)
+{
+ /* 1st line */
+ seq_printf(s, "# ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ seq_printf(s, "CPU ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ seq_printf(s, "TASK/PID ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD)
+ seq_printf(s, "OVERHEAD/");
+ seq_printf(s, "DURATION FUNCTION CALLS\n");
+
+ /* 2nd line */
+ seq_printf(s, "# ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU)
+ seq_printf(s, "| ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC)
+ seq_printf(s, "| | ");
+ if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) {
+ seq_printf(s, "| ");
+ seq_printf(s, "| | | | |\n");
+ } else
+ seq_printf(s, " | | | | |\n");
+}
+static struct tracer graph_trace __read_mostly = {
+ .name = "function_graph",
+ .init = graph_trace_init,
+ .reset = graph_trace_reset,
+ .print_line = print_graph_function,
+ .print_header = print_graph_headers,
+ .flags = &tracer_flags,
+};
+
+static __init int init_graph_trace(void)
+{
+ return register_tracer(&graph_trace);
+}
+
+device_initcall(init_graph_trace);
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
new file mode 100644
index 00000000000..b6a3e20a49a
--- /dev/null
+++ b/kernel/trace/trace_hw_branches.c
@@ -0,0 +1,195 @@
+/*
+ * h/w branch tracer for x86 based on bts
+ *
+ * Copyright (C) 2008 Markus Metzger <markus.t.metzger@gmail.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+
+#include <asm/ds.h>
+
+#include "trace.h"
+
+
+#define SIZEOF_BTS (1 << 13)
+
+static DEFINE_PER_CPU(struct bts_tracer *, tracer);
+static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer);
+
+#define this_tracer per_cpu(tracer, smp_processor_id())
+#define this_buffer per_cpu(buffer, smp_processor_id())
+
+
+static void bts_trace_start_cpu(void *arg)
+{
+ if (this_tracer)
+ ds_release_bts(this_tracer);
+
+ this_tracer =
+ ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS,
+ /* ovfl = */ NULL, /* th = */ (size_t)-1,
+ BTS_KERNEL);
+ if (IS_ERR(this_tracer)) {
+ this_tracer = NULL;
+ return;
+ }
+}
+
+static void bts_trace_start(struct trace_array *tr)
+{
+ int cpu;
+
+ tracing_reset_online_cpus(tr);
+
+ for_each_cpu_mask(cpu, cpu_possible_map)
+ smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
+}
+
+static void bts_trace_stop_cpu(void *arg)
+{
+ if (this_tracer) {
+ ds_release_bts(this_tracer);
+ this_tracer = NULL;
+ }
+}
+
+static void bts_trace_stop(struct trace_array *tr)
+{
+ int cpu;
+
+ for_each_cpu_mask(cpu, cpu_possible_map)
+ smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
+}
+
+static int bts_trace_init(struct trace_array *tr)
+{
+ tracing_reset_online_cpus(tr);
+ bts_trace_start(tr);
+
+ return 0;
+}
+
+static void bts_trace_print_header(struct seq_file *m)
+{
+ seq_puts(m,
+ "# CPU# FROM TO FUNCTION\n");
+ seq_puts(m,
+ "# | | | |\n");
+}
+
+static enum print_line_t bts_trace_print_line(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct trace_seq *seq = &iter->seq;
+ struct hw_branch_entry *it;
+
+ trace_assign_type(it, entry);
+
+ if (entry->type == TRACE_HW_BRANCHES) {
+ if (trace_seq_printf(seq, "%4d ", entry->cpu) &&
+ trace_seq_printf(seq, "0x%016llx -> 0x%016llx ",
+ it->from, it->to) &&
+ (!it->from ||
+ seq_print_ip_sym(seq, it->from, /* sym_flags = */ 0)) &&
+ trace_seq_printf(seq, "\n"))
+ return TRACE_TYPE_HANDLED;
+ return TRACE_TYPE_PARTIAL_LINE;;
+ }
+ return TRACE_TYPE_UNHANDLED;
+}
+
+void trace_hw_branch(struct trace_array *tr, u64 from, u64 to)
+{
+ struct ring_buffer_event *event;
+ struct hw_branch_entry *entry;
+ unsigned long irq;
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq);
+ if (!event)
+ return;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, from);
+ entry->ent.type = TRACE_HW_BRANCHES;
+ entry->ent.cpu = smp_processor_id();
+ entry->from = from;
+ entry->to = to;
+ ring_buffer_unlock_commit(tr->buffer, event, irq);
+}
+
+static void trace_bts_at(struct trace_array *tr,
+ const struct bts_trace *trace, void *at)
+{
+ struct bts_struct bts;
+ int err = 0;
+
+ WARN_ON_ONCE(!trace->read);
+ if (!trace->read)
+ return;
+
+ err = trace->read(this_tracer, at, &bts);
+ if (err < 0)
+ return;
+
+ switch (bts.qualifier) {
+ case BTS_BRANCH:
+ trace_hw_branch(tr, bts.variant.lbr.from, bts.variant.lbr.to);
+ break;
+ }
+}
+
+static void trace_bts_cpu(void *arg)
+{
+ struct trace_array *tr = (struct trace_array *) arg;
+ const struct bts_trace *trace;
+ unsigned char *at;
+
+ if (!this_tracer)
+ return;
+
+ ds_suspend_bts(this_tracer);
+ trace = ds_read_bts(this_tracer);
+ if (!trace)
+ goto out;
+
+ for (at = trace->ds.top; (void *)at < trace->ds.end;
+ at += trace->ds.size)
+ trace_bts_at(tr, trace, at);
+
+ for (at = trace->ds.begin; (void *)at < trace->ds.top;
+ at += trace->ds.size)
+ trace_bts_at(tr, trace, at);
+
+out:
+ ds_resume_bts(this_tracer);
+}
+
+static void trace_bts_prepare(struct trace_iterator *iter)
+{
+ int cpu;
+
+ for_each_cpu_mask(cpu, cpu_possible_map)
+ smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1);
+}
+
+struct tracer bts_tracer __read_mostly =
+{
+ .name = "hw-branch-tracer",
+ .init = bts_trace_init,
+ .reset = bts_trace_stop,
+ .print_header = bts_trace_print_header,
+ .print_line = bts_trace_print_line,
+ .start = bts_trace_start,
+ .stop = bts_trace_stop,
+ .open = trace_bts_prepare
+};
+
+__init static int init_bts_trace(void)
+{
+ return register_tracer(&bts_tracer);
+}
+device_initcall(init_bts_trace);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 9c74071c10e..7c2e326bbc8 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -353,15 +353,28 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
}
#endif /* CONFIG_PREEMPT_TRACER */
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
static void start_irqsoff_tracer(struct trace_array *tr)
{
register_ftrace_function(&trace_ops);
- tracer_enabled = 1;
+ if (tracing_is_enabled()) {
+ tracer_enabled = 1;
+ save_tracer_enabled = 1;
+ } else {
+ tracer_enabled = 0;
+ save_tracer_enabled = 0;
+ }
}
static void stop_irqsoff_tracer(struct trace_array *tr)
{
tracer_enabled = 0;
+ save_tracer_enabled = 0;
unregister_ftrace_function(&trace_ops);
}
@@ -370,53 +383,55 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
irqsoff_trace = tr;
/* make sure that the tracer is visible */
smp_wmb();
-
- if (tr->ctrl)
- start_irqsoff_tracer(tr);
+ start_irqsoff_tracer(tr);
}
static void irqsoff_tracer_reset(struct trace_array *tr)
{
- if (tr->ctrl)
- stop_irqsoff_tracer(tr);
+ stop_irqsoff_tracer(tr);
}
-static void irqsoff_tracer_ctrl_update(struct trace_array *tr)
+static void irqsoff_tracer_start(struct trace_array *tr)
{
- if (tr->ctrl)
- start_irqsoff_tracer(tr);
- else
- stop_irqsoff_tracer(tr);
+ tracer_enabled = 1;
+ save_tracer_enabled = 1;
+}
+
+static void irqsoff_tracer_stop(struct trace_array *tr)
+{
+ tracer_enabled = 0;
+ save_tracer_enabled = 0;
}
static void irqsoff_tracer_open(struct trace_iterator *iter)
{
/* stop the trace while dumping */
- if (iter->tr->ctrl)
- stop_irqsoff_tracer(iter->tr);
+ tracer_enabled = 0;
}
static void irqsoff_tracer_close(struct trace_iterator *iter)
{
- if (iter->tr->ctrl)
- start_irqsoff_tracer(iter->tr);
+ /* restart tracing */
+ tracer_enabled = save_tracer_enabled;
}
#ifdef CONFIG_IRQSOFF_TRACER
-static void irqsoff_tracer_init(struct trace_array *tr)
+static int irqsoff_tracer_init(struct trace_array *tr)
{
trace_type = TRACER_IRQS_OFF;
__irqsoff_tracer_init(tr);
+ return 0;
}
static struct tracer irqsoff_tracer __read_mostly =
{
.name = "irqsoff",
.init = irqsoff_tracer_init,
.reset = irqsoff_tracer_reset,
+ .start = irqsoff_tracer_start,
+ .stop = irqsoff_tracer_stop,
.open = irqsoff_tracer_open,
.close = irqsoff_tracer_close,
- .ctrl_update = irqsoff_tracer_ctrl_update,
.print_max = 1,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_irqsoff,
@@ -428,11 +443,12 @@ static struct tracer irqsoff_tracer __read_mostly =
#endif
#ifdef CONFIG_PREEMPT_TRACER
-static void preemptoff_tracer_init(struct trace_array *tr)
+static int preemptoff_tracer_init(struct trace_array *tr)
{
trace_type = TRACER_PREEMPT_OFF;
__irqsoff_tracer_init(tr);
+ return 0;
}
static struct tracer preemptoff_tracer __read_mostly =
@@ -440,9 +456,10 @@ static struct tracer preemptoff_tracer __read_mostly =
.name = "preemptoff",
.init = preemptoff_tracer_init,
.reset = irqsoff_tracer_reset,
+ .start = irqsoff_tracer_start,
+ .stop = irqsoff_tracer_stop,
.open = irqsoff_tracer_open,
.close = irqsoff_tracer_close,
- .ctrl_update = irqsoff_tracer_ctrl_update,
.print_max = 1,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptoff,
@@ -456,11 +473,12 @@ static struct tracer preemptoff_tracer __read_mostly =
#if defined(CONFIG_IRQSOFF_TRACER) && \
defined(CONFIG_PREEMPT_TRACER)
-static void preemptirqsoff_tracer_init(struct trace_array *tr)
+static int preemptirqsoff_tracer_init(struct trace_array *tr)
{
trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
__irqsoff_tracer_init(tr);
+ return 0;
}
static struct tracer preemptirqsoff_tracer __read_mostly =
@@ -468,9 +486,10 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
.name = "preemptirqsoff",
.init = preemptirqsoff_tracer_init,
.reset = irqsoff_tracer_reset,
+ .start = irqsoff_tracer_start,
+ .stop = irqsoff_tracer_stop,
.open = irqsoff_tracer_open,
.close = irqsoff_tracer_close,
- .ctrl_update = irqsoff_tracer_ctrl_update,
.print_max = 1,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_preemptirqsoff,
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index e62cbf78eab..fffcb069f1d 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -22,44 +22,35 @@ static unsigned long prev_overruns;
static void mmio_reset_data(struct trace_array *tr)
{
- int cpu;
-
overrun_detected = false;
prev_overruns = 0;
- tr->time_start = ftrace_now(tr->cpu);
- for_each_online_cpu(cpu)
- tracing_reset(tr, cpu);
+ tracing_reset_online_cpus(tr);
}
-static void mmio_trace_init(struct trace_array *tr)
+static int mmio_trace_init(struct trace_array *tr)
{
pr_debug("in %s\n", __func__);
mmio_trace_array = tr;
- if (tr->ctrl) {
- mmio_reset_data(tr);
- enable_mmiotrace();
- }
+
+ mmio_reset_data(tr);
+ enable_mmiotrace();
+ return 0;
}
static void mmio_trace_reset(struct trace_array *tr)
{
pr_debug("in %s\n", __func__);
- if (tr->ctrl)
- disable_mmiotrace();
+
+ disable_mmiotrace();
mmio_reset_data(tr);
mmio_trace_array = NULL;
}
-static void mmio_trace_ctrl_update(struct trace_array *tr)
+static void mmio_trace_start(struct trace_array *tr)
{
pr_debug("in %s\n", __func__);
- if (tr->ctrl) {
- mmio_reset_data(tr);
- enable_mmiotrace();
- } else {
- disable_mmiotrace();
- }
+ mmio_reset_data(tr);
}
static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
@@ -296,10 +287,10 @@ static struct tracer mmio_tracer __read_mostly =
.name = "mmiotrace",
.init = mmio_trace_init,
.reset = mmio_trace_reset,
+ .start = mmio_trace_start,
.pipe_open = mmio_pipe_open,
.close = mmio_close,
.read = mmio_read,
- .ctrl_update = mmio_trace_ctrl_update,
.print_line = mmio_print_line,
};
@@ -371,5 +362,5 @@ void mmio_trace_mapping(struct mmiotrace_map *map)
int mmio_trace_printk(const char *fmt, va_list args)
{
- return trace_vprintk(0, fmt, args);
+ return trace_vprintk(0, -1, fmt, args);
}
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 4592b486251..b9767acd30a 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -12,6 +12,27 @@
#include "trace.h"
+/* Our two options */
+enum {
+ TRACE_NOP_OPT_ACCEPT = 0x1,
+ TRACE_NOP_OPT_REFUSE = 0x2
+};
+
+/* Options for the tracer (see trace_options file) */
+static struct tracer_opt nop_opts[] = {
+ /* Option that will be accepted by set_flag callback */
+ { TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) },
+ /* Option that will be refused by set_flag callback */
+ { TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) },
+ { } /* Always set a last empty entry */
+};
+
+static struct tracer_flags nop_flags = {
+ /* You can check your flags value here when you want. */
+ .val = 0, /* By default: all flags disabled */
+ .opts = nop_opts
+};
+
static struct trace_array *ctx_trace;
static void start_nop_trace(struct trace_array *tr)
@@ -24,7 +45,7 @@ static void stop_nop_trace(struct trace_array *tr)
/* Nothing to do! */
}
-static void nop_trace_init(struct trace_array *tr)
+static int nop_trace_init(struct trace_array *tr)
{
int cpu;
ctx_trace = tr;
@@ -32,33 +53,53 @@ static void nop_trace_init(struct trace_array *tr)
for_each_online_cpu(cpu)
tracing_reset(tr, cpu);
- if (tr->ctrl)
- start_nop_trace(tr);
+ start_nop_trace(tr);
+ return 0;
}
static void nop_trace_reset(struct trace_array *tr)
{
- if (tr->ctrl)
- stop_nop_trace(tr);
+ stop_nop_trace(tr);
}
-static void nop_trace_ctrl_update(struct trace_array *tr)
+/* It only serves as a signal handler and a callback to
+ * accept or refuse tthe setting of a flag.
+ * If you don't implement it, then the flag setting will be
+ * automatically accepted.
+ */
+static int nop_set_flag(u32 old_flags, u32 bit, int set)
{
- /* When starting a new trace, reset the buffers */
- if (tr->ctrl)
- start_nop_trace(tr);
- else
- stop_nop_trace(tr);
+ /*
+ * Note that you don't need to update nop_flags.val yourself.
+ * The tracing Api will do it automatically if you return 0
+ */
+ if (bit == TRACE_NOP_OPT_ACCEPT) {
+ printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept."
+ " Now cat trace_options to see the result\n",
+ set);
+ return 0;
+ }
+
+ if (bit == TRACE_NOP_OPT_REFUSE) {
+ printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
+ "Now cat trace_options to see the result\n",
+ set);
+ return -EINVAL;
+ }
+
+ return 0;
}
+
struct tracer nop_trace __read_mostly =
{
.name = "nop",
.init = nop_trace_init,
.reset = nop_trace_reset,
- .ctrl_update = nop_trace_ctrl_update,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_nop,
#endif
+ .flags = &nop_flags,
+ .set_flag = nop_set_flag
};
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
new file mode 100644
index 00000000000..a7172a352f6
--- /dev/null
+++ b/kernel/trace/trace_power.c
@@ -0,0 +1,179 @@
+/*
+ * ring buffer based C-state tracer
+ *
+ * Arjan van de Ven <arjan@linux.intel.com>
+ * Copyright (C) 2008 Intel Corporation
+ *
+ * Much is borrowed from trace_boot.c which is
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+
+#include "trace.h"
+
+static struct trace_array *power_trace;
+static int __read_mostly trace_power_enabled;
+
+
+static void start_power_trace(struct trace_array *tr)
+{
+ trace_power_enabled = 1;
+}
+
+static void stop_power_trace(struct trace_array *tr)
+{
+ trace_power_enabled = 0;
+}
+
+
+static int power_trace_init(struct trace_array *tr)
+{
+ int cpu;
+ power_trace = tr;
+
+ trace_power_enabled = 1;
+
+ for_each_cpu_mask(cpu, cpu_possible_map)
+ tracing_reset(tr, cpu);
+ return 0;
+}
+
+static enum print_line_t power_print_line(struct trace_iterator *iter)
+{
+ int ret = 0;
+ struct trace_entry *entry = iter->ent;
+ struct trace_power *field ;
+ struct power_trace *it;
+ struct trace_seq *s = &iter->seq;
+ struct timespec stamp;
+ struct timespec duration;
+
+ trace_assign_type(field, entry);
+ it = &field->state_data;
+ stamp = ktime_to_timespec(it->stamp);
+ duration = ktime_to_timespec(ktime_sub(it->end, it->stamp));
+
+ if (entry->type == TRACE_POWER) {
+ if (it->type == POWER_CSTATE)
+ ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n",
+ stamp.tv_sec,
+ stamp.tv_nsec,
+ it->state, iter->cpu,
+ duration.tv_sec,
+ duration.tv_nsec);
+ if (it->type == POWER_PSTATE)
+ ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n",
+ stamp.tv_sec,
+ stamp.tv_nsec,
+ it->state, iter->cpu);
+ if (!ret)
+ return TRACE_TYPE_PARTIAL_LINE;
+ return TRACE_TYPE_HANDLED;
+ }
+ return TRACE_TYPE_UNHANDLED;
+}
+
+static struct tracer power_tracer __read_mostly =
+{
+ .name = "power",
+ .init = power_trace_init,
+ .start = start_power_trace,
+ .stop = stop_power_trace,
+ .reset = stop_power_trace,
+ .print_line = power_print_line,
+};
+
+static int init_power_trace(void)
+{
+ return register_tracer(&power_tracer);
+}
+device_initcall(init_power_trace);
+
+void trace_power_start(struct power_trace *it, unsigned int type,
+ unsigned int level)
+{
+ if (!trace_power_enabled)
+ return;
+
+ memset(it, 0, sizeof(struct power_trace));
+ it->state = level;
+ it->type = type;
+ it->stamp = ktime_get();
+}
+EXPORT_SYMBOL_GPL(trace_power_start);
+
+
+void trace_power_end(struct power_trace *it)
+{
+ struct ring_buffer_event *event;
+ struct trace_power *entry;
+ struct trace_array_cpu *data;
+ unsigned long irq_flags;
+ struct trace_array *tr = power_trace;
+
+ if (!trace_power_enabled)
+ return;
+
+ preempt_disable();
+ it->end = ktime_get();
+ data = tr->data[smp_processor_id()];
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+ entry->ent.type = TRACE_POWER;
+ entry->state_data = *it;
+ ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ trace_wake_up();
+
+ out:
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(trace_power_end);
+
+void trace_power_mark(struct power_trace *it, unsigned int type,
+ unsigned int level)
+{
+ struct ring_buffer_event *event;
+ struct trace_power *entry;
+ struct trace_array_cpu *data;
+ unsigned long irq_flags;
+ struct trace_array *tr = power_trace;
+
+ if (!trace_power_enabled)
+ return;
+
+ memset(it, 0, sizeof(struct power_trace));
+ it->state = level;
+ it->type = type;
+ it->stamp = ktime_get();
+ preempt_disable();
+ it->end = it->stamp;
+ data = tr->data[smp_processor_id()];
+
+ event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+ &irq_flags);
+ if (!event)
+ goto out;
+ entry = ring_buffer_event_data(event);
+ tracing_generic_entry_update(&entry->ent, 0, 0);
+ entry->ent.type = TRACE_POWER;
+ entry->state_data = *it;
+ ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ trace_wake_up();
+
+ out:
+ preempt_enable();
+}
+EXPORT_SYMBOL_GPL(trace_power_mark);
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index b8f56beb1a6..df175cb4564 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -16,7 +16,8 @@
static struct trace_array *ctx_trace;
static int __read_mostly tracer_enabled;
-static atomic_t sched_ref;
+static int sched_ref;
+static DEFINE_MUTEX(sched_register_mutex);
static void
probe_sched_switch(struct rq *__rq, struct task_struct *prev,
@@ -27,7 +28,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
int cpu;
int pc;
- if (!atomic_read(&sched_ref))
+ if (!sched_ref)
return;
tracing_record_cmdline(prev);
@@ -48,7 +49,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
}
static void
-probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee)
+probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
{
struct trace_array_cpu *data;
unsigned long flags;
@@ -71,16 +72,6 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee)
local_irq_restore(flags);
}
-static void sched_switch_reset(struct trace_array *tr)
-{
- int cpu;
-
- tr->time_start = ftrace_now(tr->cpu);
-
- for_each_online_cpu(cpu)
- tracing_reset(tr, cpu);
-}
-
static int tracing_sched_register(void)
{
int ret;
@@ -123,20 +114,18 @@ static void tracing_sched_unregister(void)
static void tracing_start_sched_switch(void)
{
- long ref;
-
- ref = atomic_inc_return(&sched_ref);
- if (ref == 1)
+ mutex_lock(&sched_register_mutex);
+ if (!(sched_ref++))
tracing_sched_register();
+ mutex_unlock(&sched_register_mutex);
}
static void tracing_stop_sched_switch(void)
{
- long ref;
-
- ref = atomic_dec_and_test(&sched_ref);
- if (ref)
+ mutex_lock(&sched_register_mutex);
+ if (!(--sched_ref))
tracing_sched_unregister();
+ mutex_unlock(&sched_register_mutex);
}
void tracing_start_cmdline_record(void)
@@ -149,40 +138,86 @@ void tracing_stop_cmdline_record(void)
tracing_stop_sched_switch();
}
+/**
+ * tracing_start_sched_switch_record - start tracing context switches
+ *
+ * Turns on context switch tracing for a tracer.
+ */
+void tracing_start_sched_switch_record(void)
+{
+ if (unlikely(!ctx_trace)) {
+ WARN_ON(1);
+ return;
+ }
+
+ tracing_start_sched_switch();
+
+ mutex_lock(&sched_register_mutex);
+ tracer_enabled++;
+ mutex_unlock(&sched_register_mutex);
+}
+
+/**
+ * tracing_stop_sched_switch_record - start tracing context switches
+ *
+ * Turns off context switch tracing for a tracer.
+ */
+void tracing_stop_sched_switch_record(void)
+{
+ mutex_lock(&sched_register_mutex);
+ tracer_enabled--;
+ WARN_ON(tracer_enabled < 0);
+ mutex_unlock(&sched_register_mutex);
+
+ tracing_stop_sched_switch();
+}
+
+/**
+ * tracing_sched_switch_assign_trace - assign a trace array for ctx switch
+ * @tr: trace array pointer to assign
+ *
+ * Some tracers might want to record the context switches in their
+ * trace. This function lets those tracers assign the trace array
+ * to use.
+ */
+void tracing_sched_switch_assign_trace(struct trace_array *tr)
+{
+ ctx_trace = tr;
+}
+
static void start_sched_trace(struct trace_array *tr)
{
- sched_switch_reset(tr);
- tracing_start_cmdline_record();
- tracer_enabled = 1;
+ tracing_reset_online_cpus(tr);
+ tracing_start_sched_switch_record();
}
static void stop_sched_trace(struct trace_array *tr)
{
- tracer_enabled = 0;
- tracing_stop_cmdline_record();
+ tracing_stop_sched_switch_record();
}
-static void sched_switch_trace_init(struct trace_array *tr)
+static int sched_switch_trace_init(struct trace_array *tr)
{
ctx_trace = tr;
-
- if (tr->ctrl)
- start_sched_trace(tr);
+ start_sched_trace(tr);
+ return 0;
}
static void sched_switch_trace_reset(struct trace_array *tr)
{
- if (tr->ctrl)
+ if (sched_ref)
stop_sched_trace(tr);
}
-static void sched_switch_trace_ctrl_update(struct trace_array *tr)
+static void sched_switch_trace_start(struct trace_array *tr)
{
- /* When starting a new trace, reset the buffers */
- if (tr->ctrl)
- start_sched_trace(tr);
- else
- stop_sched_trace(tr);
+ tracing_reset_online_cpus(tr);
+ tracing_start_sched_switch();
+}
+
+static void sched_switch_trace_stop(struct trace_array *tr)
+{
+ tracing_stop_sched_switch();
}
static struct tracer sched_switch_trace __read_mostly =
@@ -190,7 +225,8 @@ static struct tracer sched_switch_trace __read_mostly =
.name = "sched_switch",
.init = sched_switch_trace_init,
.reset = sched_switch_trace_reset,
- .ctrl_update = sched_switch_trace_ctrl_update,
+ .start = sched_switch_trace_start,
+ .stop = sched_switch_trace_stop,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_sched_switch,
#endif
@@ -198,14 +234,7 @@ static struct tracer sched_switch_trace __read_mostly =
__init static int init_sched_switch_trace(void)
{
- int ret = 0;
-
- if (atomic_read(&sched_ref))
- ret = tracing_sched_register();
- if (ret) {
- pr_info("error registering scheduler trace\n");
- return ret;
- }
return register_tracer(&sched_switch_trace);
}
device_initcall(init_sched_switch_trace);
+
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3ae93f16b56..43586b689e3 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -50,8 +50,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
return;
pc = preempt_count();
- resched = need_resched();
- preempt_disable_notrace();
+ resched = ftrace_preempt_disable();
cpu = raw_smp_processor_id();
data = tr->data[cpu];
@@ -81,15 +80,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
out:
atomic_dec(&data->disabled);
- /*
- * To prevent recursion from the scheduler, if the
- * resched flag was set before we entered, then
- * don't reschedule.
- */
- if (resched)
- preempt_enable_no_resched_notrace();
- else
- preempt_enable_notrace();
+ ftrace_preempt_enable(resched);
}
static struct ftrace_ops trace_ops __read_mostly =
@@ -220,7 +211,7 @@ static void wakeup_reset(struct trace_array *tr)
}
static void
-probe_wakeup(struct rq *rq, struct task_struct *p)
+probe_wakeup(struct rq *rq, struct task_struct *p, int success)
{
int cpu = smp_processor_id();
unsigned long flags;
@@ -271,6 +262,12 @@ out:
atomic_dec(&wakeup_trace->data[cpu]->disabled);
}
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
static void start_wakeup_tracer(struct trace_array *tr)
{
int ret;
@@ -309,7 +306,13 @@ static void start_wakeup_tracer(struct trace_array *tr)
register_ftrace_function(&trace_ops);
- tracer_enabled = 1;
+ if (tracing_is_enabled()) {
+ tracer_enabled = 1;
+ save_tracer_enabled = 1;
+ } else {
+ tracer_enabled = 0;
+ save_tracer_enabled = 0;
+ }
return;
fail_deprobe_wake_new:
@@ -321,49 +324,53 @@ fail_deprobe:
static void stop_wakeup_tracer(struct trace_array *tr)
{
tracer_enabled = 0;
+ save_tracer_enabled = 0;
unregister_ftrace_function(&trace_ops);
unregister_trace_sched_switch(probe_wakeup_sched_switch);
unregister_trace_sched_wakeup_new(probe_wakeup);
unregister_trace_sched_wakeup(probe_wakeup);
}
-static void wakeup_tracer_init(struct trace_array *tr)
+static int wakeup_tracer_init(struct trace_array *tr)
{
wakeup_trace = tr;
-
- if (tr->ctrl)
- start_wakeup_tracer(tr);
+ start_wakeup_tracer(tr);
+ return 0;
}
static void wakeup_tracer_reset(struct trace_array *tr)
{
- if (tr->ctrl) {
- stop_wakeup_tracer(tr);
- /* make sure we put back any tasks we are tracing */
- wakeup_reset(tr);
- }
+ stop_wakeup_tracer(tr);
+ /* make sure we put back any tasks we are tracing */
+ wakeup_reset(tr);
+}
+
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+ wakeup_reset(tr);
+ tracer_enabled = 1;
+ save_tracer_enabled = 1;
}
-static void wakeup_tracer_ctrl_update(struct trace_array *tr)
+static void wakeup_tracer_stop(struct trace_array *tr)
{
- if (tr->ctrl)
- start_wakeup_tracer(tr);
- else
- stop_wakeup_tracer(tr);
+ tracer_enabled = 0;
+ save_tracer_enabled = 0;
}
static void wakeup_tracer_open(struct trace_iterator *iter)
{
/* stop the trace while dumping */
- if (iter->tr->ctrl)
- stop_wakeup_tracer(iter->tr);
+ tracer_enabled = 0;
}
static void wakeup_tracer_close(struct trace_iterator *iter)
{
/* forget about any processes we were recording */
- if (iter->tr->ctrl)
- start_wakeup_tracer(iter->tr);
+ if (save_tracer_enabled) {
+ wakeup_reset(iter->tr);
+ tracer_enabled = 1;
+ }
}
static struct tracer wakeup_tracer __read_mostly =
@@ -371,9 +378,10 @@ static struct tracer wakeup_tracer __read_mostly =
.name = "wakeup",
.init = wakeup_tracer_init,
.reset = wakeup_tracer_reset,
+ .start = wakeup_tracer_start,
+ .stop = wakeup_tracer_stop,
.open = wakeup_tracer_open,
.close = wakeup_tracer_close,
- .ctrl_update = wakeup_tracer_ctrl_update,
.print_max = 1,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_wakeup,
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 90bc752a758..88c8eb70f54 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -13,6 +13,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
case TRACE_STACK:
case TRACE_PRINT:
case TRACE_SPECIAL:
+ case TRACE_BRANCH:
return 1;
}
return 0;
@@ -51,7 +52,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
int cpu, ret = 0;
/* Don't allow flipping of max traces now */
- raw_local_irq_save(flags);
+ local_irq_save(flags);
__raw_spin_lock(&ftrace_max_lock);
cnt = ring_buffer_entries(tr->buffer);
@@ -62,7 +63,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
break;
}
__raw_spin_unlock(&ftrace_max_lock);
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
if (count)
*count = cnt;
@@ -70,6 +71,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
return ret;
}
+static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
+{
+ printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n",
+ trace->name, init_ret);
+}
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -110,8 +116,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
ftrace_set_filter(func_name, strlen(func_name), 1);
/* enable tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out;
+ }
/* Sleep for a 1/10 of a second */
msleep(100);
@@ -134,13 +143,13 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
msleep(100);
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
ftrace_enabled = 0;
/* check the trace buffer */
ret = trace_test_buffer(tr, &count);
trace->reset(tr);
+ tracing_start();
/* we should only have one item */
if (!ret && count != 1) {
@@ -148,6 +157,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
ret = -1;
goto out;
}
+
out:
ftrace_enabled = save_ftrace_enabled;
tracer_enabled = save_tracer_enabled;
@@ -180,18 +190,22 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
ftrace_enabled = 1;
tracer_enabled = 1;
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out;
+ }
+
/* Sleep for a 1/10 of a second */
msleep(100);
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
ftrace_enabled = 0;
/* check the trace buffer */
ret = trace_test_buffer(tr, &count);
trace->reset(tr);
+ tracing_start();
if (!ret && !count) {
printk(KERN_CONT ".. no entries found ..");
@@ -223,8 +237,12 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
int ret;
/* start the tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
/* reset the max latency */
tracing_max_latency = 0;
/* disable interrupts for a bit */
@@ -232,13 +250,13 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
udelay(100);
local_irq_enable();
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check both trace buffers */
ret = trace_test_buffer(tr, NULL);
if (!ret)
ret = trace_test_buffer(&max_tr, &count);
trace->reset(tr);
+ tracing_start();
if (!ret && !count) {
printk(KERN_CONT ".. no entries found ..");
@@ -259,9 +277,26 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
unsigned long count;
int ret;
+ /*
+ * Now that the big kernel lock is no longer preemptable,
+ * and this is called with the BKL held, it will always
+ * fail. If preemption is already disabled, simply
+ * pass the test. When the BKL is removed, or becomes
+ * preemptible again, we will once again test this,
+ * so keep it in.
+ */
+ if (preempt_count()) {
+ printk(KERN_CONT "can not test ... force ");
+ return 0;
+ }
+
/* start the tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
/* reset the max latency */
tracing_max_latency = 0;
/* disable preemption for a bit */
@@ -269,13 +304,13 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
udelay(100);
preempt_enable();
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check both trace buffers */
ret = trace_test_buffer(tr, NULL);
if (!ret)
ret = trace_test_buffer(&max_tr, &count);
trace->reset(tr);
+ tracing_start();
if (!ret && !count) {
printk(KERN_CONT ".. no entries found ..");
@@ -296,9 +331,25 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
unsigned long count;
int ret;
+ /*
+ * Now that the big kernel lock is no longer preemptable,
+ * and this is called with the BKL held, it will always
+ * fail. If preemption is already disabled, simply
+ * pass the test. When the BKL is removed, or becomes
+ * preemptible again, we will once again test this,
+ * so keep it in.
+ */
+ if (preempt_count()) {
+ printk(KERN_CONT "can not test ... force ");
+ return 0;
+ }
+
/* start the tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ goto out;
+ }
/* reset the max latency */
tracing_max_latency = 0;
@@ -312,27 +363,30 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
local_irq_enable();
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check both trace buffers */
ret = trace_test_buffer(tr, NULL);
- if (ret)
+ if (ret) {
+ tracing_start();
goto out;
+ }
ret = trace_test_buffer(&max_tr, &count);
- if (ret)
+ if (ret) {
+ tracing_start();
goto out;
+ }
if (!ret && !count) {
printk(KERN_CONT ".. no entries found ..");
ret = -1;
+ tracing_start();
goto out;
}
/* do the test by disabling interrupts first this time */
tracing_max_latency = 0;
- tr->ctrl = 1;
- trace->ctrl_update(tr);
+ tracing_start();
preempt_disable();
local_irq_disable();
udelay(100);
@@ -341,8 +395,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
local_irq_enable();
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check both trace buffers */
ret = trace_test_buffer(tr, NULL);
if (ret)
@@ -358,6 +411,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
out:
trace->reset(tr);
+ tracing_start();
tracing_max_latency = save_max;
return ret;
@@ -423,8 +477,12 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
wait_for_completion(&isrt);
/* start the tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
/* reset the max latency */
tracing_max_latency = 0;
@@ -448,8 +506,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
msleep(100);
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check both trace buffers */
ret = trace_test_buffer(tr, NULL);
if (!ret)
@@ -457,6 +514,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
trace->reset(tr);
+ tracing_start();
tracing_max_latency = save_max;
@@ -480,16 +538,20 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
int ret;
/* start the tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
/* Sleep for a 1/10 of a second */
msleep(100);
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check the trace buffer */
ret = trace_test_buffer(tr, &count);
trace->reset(tr);
+ tracing_start();
if (!ret && !count) {
printk(KERN_CONT ".. no entries found ..");
@@ -508,17 +570,48 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr)
int ret;
/* start the tracing */
- tr->ctrl = 1;
- trace->init(tr);
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return 0;
+ }
+
/* Sleep for a 1/10 of a second */
msleep(100);
/* stop the tracing. */
- tr->ctrl = 0;
- trace->ctrl_update(tr);
+ tracing_stop();
/* check the trace buffer */
ret = trace_test_buffer(tr, &count);
trace->reset(tr);
+ tracing_start();
return ret;
}
#endif /* CONFIG_SYSPROF_TRACER */
+
+#ifdef CONFIG_BRANCH_TRACER
+int
+trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
+{
+ unsigned long count;
+ int ret;
+
+ /* start the tracing */
+ ret = trace->init(tr);
+ if (ret) {
+ warn_failed_init_tracer(trace, ret);
+ return ret;
+ }
+
+ /* Sleep for a 1/10 of a second */
+ msleep(100);
+ /* stop the tracing. */
+ tracing_stop();
+ /* check the trace buffer */
+ ret = trace_test_buffer(tr, &count);
+ trace->reset(tr);
+ tracing_start();
+
+ return ret;
+}
+#endif /* CONFIG_BRANCH_TRACER */
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 3bdb44bde4b..d0871bc0aca 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -10,6 +10,7 @@
#include <linux/debugfs.h>
#include <linux/ftrace.h>
#include <linux/module.h>
+#include <linux/sysctl.h>
#include <linux/init.h>
#include <linux/fs.h>
#include "trace.h"
@@ -31,6 +32,10 @@ static raw_spinlock_t max_stack_lock =
static int stack_trace_disabled __read_mostly;
static DEFINE_PER_CPU(int, trace_active);
+static DEFINE_MUTEX(stack_sysctl_mutex);
+
+int stack_tracer_enabled;
+static int last_stack_tracer_enabled;
static inline void check_stack(void)
{
@@ -48,7 +53,7 @@ static inline void check_stack(void)
if (!object_is_on_stack(&this_size))
return;
- raw_local_irq_save(flags);
+ local_irq_save(flags);
__raw_spin_lock(&max_stack_lock);
/* a race could have already updated it */
@@ -78,6 +83,7 @@ static inline void check_stack(void)
* on a new max, so it is far from a fast path.
*/
while (i < max_stack_trace.nr_entries) {
+ int found = 0;
stack_dump_index[i] = this_size;
p = start;
@@ -86,17 +92,19 @@ static inline void check_stack(void)
if (*p == stack_dump_trace[i]) {
this_size = stack_dump_index[i++] =
(top - p) * sizeof(unsigned long);
+ found = 1;
/* Start the search from here */
start = p + 1;
}
}
- i++;
+ if (!found)
+ i++;
}
out:
__raw_spin_unlock(&max_stack_lock);
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
}
static void
@@ -107,8 +115,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
if (unlikely(!ftrace_enabled || stack_trace_disabled))
return;
- resched = need_resched();
- preempt_disable_notrace();
+ resched = ftrace_preempt_disable();
cpu = raw_smp_processor_id();
/* no atomic needed, we only modify this variable by this cpu */
@@ -120,10 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
out:
per_cpu(trace_active, cpu)--;
/* prevent recursion in schedule */
- if (resched)
- preempt_enable_no_resched_notrace();
- else
- preempt_enable_notrace();
+ ftrace_preempt_enable(resched);
}
static struct ftrace_ops trace_ops __read_mostly =
@@ -166,16 +170,16 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
if (ret < 0)
return ret;
- raw_local_irq_save(flags);
+ local_irq_save(flags);
__raw_spin_lock(&max_stack_lock);
*ptr = val;
__raw_spin_unlock(&max_stack_lock);
- raw_local_irq_restore(flags);
+ local_irq_restore(flags);
return count;
}
-static struct file_operations stack_max_size_fops = {
+static const struct file_operations stack_max_size_fops = {
.open = tracing_open_generic,
.read = stack_max_size_read,
.write = stack_max_size_write,
@@ -273,7 +277,7 @@ static int t_show(struct seq_file *m, void *v)
return 0;
}
-static struct seq_operations stack_trace_seq_ops = {
+static const struct seq_operations stack_trace_seq_ops = {
.start = t_start,
.next = t_next,
.stop = t_stop,
@@ -289,12 +293,47 @@ static int stack_trace_open(struct inode *inode, struct file *file)
return ret;
}
-static struct file_operations stack_trace_fops = {
+static const struct file_operations stack_trace_fops = {
.open = stack_trace_open,
.read = seq_read,
.llseek = seq_lseek,
};
+int
+stack_trace_sysctl(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+
+ mutex_lock(&stack_sysctl_mutex);
+
+ ret = proc_dointvec(table, write, file, buffer, lenp, ppos);
+
+ if (ret || !write ||
+ (last_stack_tracer_enabled == stack_tracer_enabled))
+ goto out;
+
+ last_stack_tracer_enabled = stack_tracer_enabled;
+
+ if (stack_tracer_enabled)
+ register_ftrace_function(&trace_ops);
+ else
+ unregister_ftrace_function(&trace_ops);
+
+ out:
+ mutex_unlock(&stack_sysctl_mutex);
+ return ret;
+}
+
+static __init int enable_stacktrace(char *str)
+{
+ stack_tracer_enabled = 1;
+ last_stack_tracer_enabled = 1;
+ return 1;
+}
+__setup("stacktrace", enable_stacktrace);
+
static __init int stack_trace_init(void)
{
struct dentry *d_tracer;
@@ -312,7 +351,8 @@ static __init int stack_trace_init(void)
if (!entry)
pr_warning("Could not create debugfs 'stack_trace' entry\n");
- register_ftrace_function(&trace_ops);
+ if (stack_tracer_enabled)
+ register_ftrace_function(&trace_ops);
return 0;
}
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 9587d3bcba5..01becf1f19f 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -234,20 +234,10 @@ static void stop_stack_timers(void)
stop_stack_timer(cpu);
}
-static void stack_reset(struct trace_array *tr)
-{
- int cpu;
-
- tr->time_start = ftrace_now(tr->cpu);
-
- for_each_online_cpu(cpu)
- tracing_reset(tr, cpu);
-}
-
static void start_stack_trace(struct trace_array *tr)
{
mutex_lock(&sample_timer_lock);
- stack_reset(tr);
+ tracing_reset_online_cpus(tr);
start_stack_timers();
tracer_enabled = 1;
mutex_unlock(&sample_timer_lock);
@@ -261,27 +251,17 @@ static void stop_stack_trace(struct trace_array *tr)
mutex_unlock(&sample_timer_lock);
}
-static void stack_trace_init(struct trace_array *tr)
+static int stack_trace_init(struct trace_array *tr)
{
sysprof_trace = tr;
- if (tr->ctrl)
- start_stack_trace(tr);
+ start_stack_trace(tr);
+ return 0;
}
static void stack_trace_reset(struct trace_array *tr)
{
- if (tr->ctrl)
- stop_stack_trace(tr);
-}
-
-static void stack_trace_ctrl_update(struct trace_array *tr)
-{
- /* When starting a new trace, reset the buffers */
- if (tr->ctrl)
- start_stack_trace(tr);
- else
- stop_stack_trace(tr);
+ stop_stack_trace(tr);
}
static struct tracer stack_trace __read_mostly =
@@ -289,7 +269,6 @@ static struct tracer stack_trace __read_mostly =
.name = "sysprof",
.init = stack_trace_init,
.reset = stack_trace_reset,
- .ctrl_update = stack_trace_ctrl_update,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_sysprof,
#endif
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index af8c8566488..79602740bbb 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -43,6 +43,7 @@ static DEFINE_MUTEX(tracepoints_mutex);
*/
#define TRACEPOINT_HASH_BITS 6
#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
+static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
/*
* Note about RCU :
@@ -54,40 +55,43 @@ struct tracepoint_entry {
struct hlist_node hlist;
void **funcs;
int refcount; /* Number of times armed. 0 if disarmed. */
- struct rcu_head rcu;
- void *oldptr;
- unsigned char rcu_pending:1;
char name[0];
};
-static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+struct tp_probes {
+ union {
+ struct rcu_head rcu;
+ struct list_head list;
+ } u;
+ void *probes[0];
+};
-static void free_old_closure(struct rcu_head *head)
+static inline void *allocate_probes(int count)
{
- struct tracepoint_entry *entry = container_of(head,
- struct tracepoint_entry, rcu);
- kfree(entry->oldptr);
- /* Make sure we free the data before setting the pending flag to 0 */
- smp_wmb();
- entry->rcu_pending = 0;
+ struct tp_probes *p = kmalloc(count * sizeof(void *)
+ + sizeof(struct tp_probes), GFP_KERNEL);
+ return p == NULL ? NULL : p->probes;
}
-static void tracepoint_entry_free_old(struct tracepoint_entry *entry, void *old)
+static void rcu_free_old_probes(struct rcu_head *head)
{
- if (!old)
- return;
- entry->oldptr = old;
- entry->rcu_pending = 1;
- /* write rcu_pending before calling the RCU callback */
- smp_wmb();
- call_rcu_sched(&entry->rcu, free_old_closure);
+ kfree(container_of(head, struct tp_probes, u.rcu));
+}
+
+static inline void release_probes(void *old)
+{
+ if (old) {
+ struct tp_probes *tp_probes = container_of(old,
+ struct tp_probes, probes[0]);
+ call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes);
+ }
}
static void debug_print_probes(struct tracepoint_entry *entry)
{
int i;
- if (!tracepoint_debug)
+ if (!tracepoint_debug || !entry->funcs)
return;
for (i = 0; entry->funcs[i]; i++)
@@ -111,12 +115,13 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
return ERR_PTR(-EEXIST);
}
/* + 2 : one for new probe, one for NULL func */
- new = kzalloc((nr_probes + 2) * sizeof(void *), GFP_KERNEL);
+ new = allocate_probes(nr_probes + 2);
if (new == NULL)
return ERR_PTR(-ENOMEM);
if (old)
memcpy(new, old, nr_probes * sizeof(void *));
new[nr_probes] = probe;
+ new[nr_probes + 1] = NULL;
entry->refcount = nr_probes + 1;
entry->funcs = new;
debug_print_probes(entry);
@@ -132,7 +137,7 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
old = entry->funcs;
if (!old)
- return NULL;
+ return ERR_PTR(-ENOENT);
debug_print_probes(entry);
/* (N -> M), (N > 1, M >= 0) probes */
@@ -151,13 +156,13 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
int j = 0;
/* N -> M, (N > 1, M > 0) */
/* + 1 for NULL */
- new = kzalloc((nr_probes - nr_del + 1)
- * sizeof(void *), GFP_KERNEL);
+ new = allocate_probes(nr_probes - nr_del + 1);
if (new == NULL)
return ERR_PTR(-ENOMEM);
for (i = 0; old[i]; i++)
if ((probe && old[i] != probe))
new[j++] = old[i];
+ new[nr_probes - nr_del] = NULL;
entry->refcount = nr_probes - nr_del;
entry->funcs = new;
}
@@ -215,7 +220,6 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
memcpy(&e->name[0], name, name_len);
e->funcs = NULL;
e->refcount = 0;
- e->rcu_pending = 0;
hlist_add_head(&e->hlist, head);
return e;
}
@@ -224,32 +228,10 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
* Remove the tracepoint from the tracepoint hash table. Must be called with
* mutex_lock held.
*/
-static int remove_tracepoint(const char *name)
+static inline void remove_tracepoint(struct tracepoint_entry *e)
{
- struct hlist_head *head;
- struct hlist_node *node;
- struct tracepoint_entry *e;
- int found = 0;
- size_t len = strlen(name) + 1;
- u32 hash = jhash(name, len-1, 0);
-
- head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
- hlist_for_each_entry(e, node, head, hlist) {
- if (!strcmp(name, e->name)) {
- found = 1;
- break;
- }
- }
- if (!found)
- return -ENOENT;
- if (e->refcount)
- return -EBUSY;
hlist_del(&e->hlist);
- /* Make sure the call_rcu_sched has been executed */
- if (e->rcu_pending)
- rcu_barrier_sched();
kfree(e);
- return 0;
}
/*
@@ -280,6 +262,7 @@ static void set_tracepoint(struct tracepoint_entry **entry,
static void disable_tracepoint(struct tracepoint *elem)
{
elem->state = 0;
+ rcu_assign_pointer(elem->funcs, NULL);
}
/**
@@ -320,6 +303,23 @@ static void tracepoint_update_probes(void)
module_update_tracepoints();
}
+static void *tracepoint_add_probe(const char *name, void *probe)
+{
+ struct tracepoint_entry *entry;
+ void *old;
+
+ entry = get_tracepoint(name);
+ if (!entry) {
+ entry = add_tracepoint(name);
+ if (IS_ERR(entry))
+ return entry;
+ }
+ old = tracepoint_entry_add_probe(entry, probe);
+ if (IS_ERR(old) && !entry->refcount)
+ remove_tracepoint(entry);
+ return old;
+}
+
/**
* tracepoint_probe_register - Connect a probe to a tracepoint
* @name: tracepoint name
@@ -330,44 +330,36 @@ static void tracepoint_update_probes(void)
*/
int tracepoint_probe_register(const char *name, void *probe)
{
- struct tracepoint_entry *entry;
- int ret = 0;
void *old;
mutex_lock(&tracepoints_mutex);
- entry = get_tracepoint(name);
- if (!entry) {
- entry = add_tracepoint(name);
- if (IS_ERR(entry)) {
- ret = PTR_ERR(entry);
- goto end;
- }
- }
- /*
- * If we detect that a call_rcu_sched is pending for this tracepoint,
- * make sure it's executed now.
- */
- if (entry->rcu_pending)
- rcu_barrier_sched();
- old = tracepoint_entry_add_probe(entry, probe);
- if (IS_ERR(old)) {
- ret = PTR_ERR(old);
- goto end;
- }
+ old = tracepoint_add_probe(name, probe);
mutex_unlock(&tracepoints_mutex);
+ if (IS_ERR(old))
+ return PTR_ERR(old);
+
tracepoint_update_probes(); /* may update entry */
- mutex_lock(&tracepoints_mutex);
- entry = get_tracepoint(name);
- WARN_ON(!entry);
- if (entry->rcu_pending)
- rcu_barrier_sched();
- tracepoint_entry_free_old(entry, old);
-end:
- mutex_unlock(&tracepoints_mutex);
- return ret;
+ release_probes(old);
+ return 0;
}
EXPORT_SYMBOL_GPL(tracepoint_probe_register);
+static void *tracepoint_remove_probe(const char *name, void *probe)
+{
+ struct tracepoint_entry *entry;
+ void *old;
+
+ entry = get_tracepoint(name);
+ if (!entry)
+ return ERR_PTR(-ENOENT);
+ old = tracepoint_entry_remove_probe(entry, probe);
+ if (IS_ERR(old))
+ return old;
+ if (!entry->refcount)
+ remove_tracepoint(entry);
+ return old;
+}
+
/**
* tracepoint_probe_unregister - Disconnect a probe from a tracepoint
* @name: tracepoint name
@@ -380,38 +372,104 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register);
*/
int tracepoint_probe_unregister(const char *name, void *probe)
{
- struct tracepoint_entry *entry;
void *old;
- int ret = -ENOENT;
mutex_lock(&tracepoints_mutex);
- entry = get_tracepoint(name);
- if (!entry)
- goto end;
- if (entry->rcu_pending)
- rcu_barrier_sched();
- old = tracepoint_entry_remove_probe(entry, probe);
- if (!old) {
- printk(KERN_WARNING "Warning: Trying to unregister a probe"
- "that doesn't exist\n");
- goto end;
- }
+ old = tracepoint_remove_probe(name, probe);
mutex_unlock(&tracepoints_mutex);
+ if (IS_ERR(old))
+ return PTR_ERR(old);
+
tracepoint_update_probes(); /* may update entry */
+ release_probes(old);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+
+static LIST_HEAD(old_probes);
+static int need_update;
+
+static void tracepoint_add_old_probes(void *old)
+{
+ need_update = 1;
+ if (old) {
+ struct tp_probes *tp_probes = container_of(old,
+ struct tp_probes, probes[0]);
+ list_add(&tp_probes->u.list, &old_probes);
+ }
+}
+
+/**
+ * tracepoint_probe_register_noupdate - register a probe but not connect
+ * @name: tracepoint name
+ * @probe: probe handler
+ *
+ * caller must call tracepoint_probe_update_all()
+ */
+int tracepoint_probe_register_noupdate(const char *name, void *probe)
+{
+ void *old;
+
mutex_lock(&tracepoints_mutex);
- entry = get_tracepoint(name);
- if (!entry)
- goto end;
- if (entry->rcu_pending)
- rcu_barrier_sched();
- tracepoint_entry_free_old(entry, old);
- remove_tracepoint(name); /* Ignore busy error message */
- ret = 0;
-end:
+ old = tracepoint_add_probe(name, probe);
+ if (IS_ERR(old)) {
+ mutex_unlock(&tracepoints_mutex);
+ return PTR_ERR(old);
+ }
+ tracepoint_add_old_probes(old);
mutex_unlock(&tracepoints_mutex);
- return ret;
+ return 0;
}
-EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
+
+/**
+ * tracepoint_probe_unregister_noupdate - remove a probe but not disconnect
+ * @name: tracepoint name
+ * @probe: probe function pointer
+ *
+ * caller must call tracepoint_probe_update_all()
+ */
+int tracepoint_probe_unregister_noupdate(const char *name, void *probe)
+{
+ void *old;
+
+ mutex_lock(&tracepoints_mutex);
+ old = tracepoint_remove_probe(name, probe);
+ if (IS_ERR(old)) {
+ mutex_unlock(&tracepoints_mutex);
+ return PTR_ERR(old);
+ }
+ tracepoint_add_old_probes(old);
+ mutex_unlock(&tracepoints_mutex);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate);
+
+/**
+ * tracepoint_probe_update_all - update tracepoints
+ */
+void tracepoint_probe_update_all(void)
+{
+ LIST_HEAD(release_probes);
+ struct tp_probes *pos, *next;
+
+ mutex_lock(&tracepoints_mutex);
+ if (!need_update) {
+ mutex_unlock(&tracepoints_mutex);
+ return;
+ }
+ if (!list_empty(&old_probes))
+ list_replace_init(&old_probes, &release_probes);
+ need_update = 0;
+ mutex_unlock(&tracepoints_mutex);
+
+ tracepoint_update_probes();
+ list_for_each_entry_safe(pos, next, &release_probes, u.list) {
+ list_del(&pos->u.list);
+ call_rcu_sched(&pos->u.rcu, rcu_free_old_probes);
+ }
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
/**
* tracepoint_get_iter_range - Get a next tracepoint iterator given a range.
@@ -483,3 +541,36 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
iter->tracepoint = NULL;
}
EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
+
+#ifdef CONFIG_MODULES
+
+int tracepoint_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ tracepoint_update_probe_range(mod->tracepoints,
+ mod->tracepoints + mod->num_tracepoints);
+ break;
+ case MODULE_STATE_GOING:
+ tracepoint_update_probe_range(mod->tracepoints,
+ mod->tracepoints + mod->num_tracepoints);
+ break;
+ }
+ return 0;
+}
+
+struct notifier_block tracepoint_module_nb = {
+ .notifier_call = tracepoint_module_notify,
+ .priority = 0,
+};
+
+static int init_tracepoints(void)
+{
+ return register_module_notifier(&tracepoint_module_nb);
+}
+__initcall(init_tracepoints);
+
+#endif /* CONFIG_MODULES */
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 8ebcd8532df..2dc06ab3571 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -27,6 +27,7 @@
*/
void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
{
+ const struct cred *tcred;
struct timespec uptime, ts;
u64 ac_etime;
@@ -53,10 +54,11 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk)
stats->ac_flag |= AXSIG;
stats->ac_nice = task_nice(tsk);
stats->ac_sched = tsk->policy;
- stats->ac_uid = tsk->uid;
- stats->ac_gid = tsk->gid;
stats->ac_pid = tsk->pid;
rcu_read_lock();
+ tcred = __task_cred(tsk);
+ stats->ac_uid = tcred->uid;
+ stats->ac_gid = tcred->gid;
stats->ac_ppid = pid_alive(tsk) ?
rcu_dereference(tsk->real_parent)->tgid : 0;
rcu_read_unlock();
diff --git a/kernel/uid16.c b/kernel/uid16.c
index 3e41c1673e2..2460c3199b5 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -84,11 +84,12 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid)
asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid, old_uid_t __user *suid)
{
+ const struct cred *cred = current_cred();
int retval;
- if (!(retval = put_user(high2lowuid(current->uid), ruid)) &&
- !(retval = put_user(high2lowuid(current->euid), euid)))
- retval = put_user(high2lowuid(current->suid), suid);
+ if (!(retval = put_user(high2lowuid(cred->uid), ruid)) &&
+ !(retval = put_user(high2lowuid(cred->euid), euid)))
+ retval = put_user(high2lowuid(cred->suid), suid);
return retval;
}
@@ -104,11 +105,12 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid)
asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid, old_gid_t __user *sgid)
{
+ const struct cred *cred = current_cred();
int retval;
- if (!(retval = put_user(high2lowgid(current->gid), rgid)) &&
- !(retval = put_user(high2lowgid(current->egid), egid)))
- retval = put_user(high2lowgid(current->sgid), sgid);
+ if (!(retval = put_user(high2lowgid(cred->gid), rgid)) &&
+ !(retval = put_user(high2lowgid(cred->egid), egid)))
+ retval = put_user(high2lowgid(cred->sgid), sgid);
return retval;
}
@@ -161,25 +163,24 @@ static int groups16_from_user(struct group_info *group_info,
asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist)
{
- int i = 0;
+ const struct cred *cred = current_cred();
+ int i;
if (gidsetsize < 0)
return -EINVAL;
- get_group_info(current->group_info);
- i = current->group_info->ngroups;
+ i = cred->group_info->ngroups;
if (gidsetsize) {
if (i > gidsetsize) {
i = -EINVAL;
goto out;
}
- if (groups16_to_user(grouplist, current->group_info)) {
+ if (groups16_to_user(grouplist, cred->group_info)) {
i = -EFAULT;
goto out;
}
}
out:
- put_group_info(current->group_info);
return i;
}
@@ -210,20 +211,20 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist)
asmlinkage long sys_getuid16(void)
{
- return high2lowuid(current->uid);
+ return high2lowuid(current_uid());
}
asmlinkage long sys_geteuid16(void)
{
- return high2lowuid(current->euid);
+ return high2lowuid(current_euid());
}
asmlinkage long sys_getgid16(void)
{
- return high2lowgid(current->gid);
+ return high2lowgid(current_gid());
}
asmlinkage long sys_getegid16(void)
{
- return high2lowgid(current->egid);
+ return high2lowgid(current_egid());
}
diff --git a/kernel/user.c b/kernel/user.c
index 39d6159fae4..477b6660f44 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,12 +16,13 @@
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/user_namespace.h>
+#include "cred-internals.h"
struct user_namespace init_user_ns = {
.kref = {
- .refcount = ATOMIC_INIT(2),
+ .refcount = ATOMIC_INIT(1),
},
- .root_user = &root_user,
+ .creator = &root_user,
};
EXPORT_SYMBOL_GPL(init_user_ns);
@@ -47,12 +48,14 @@ 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->creator */
struct user_struct root_user = {
- .__count = ATOMIC_INIT(1),
+ .__count = ATOMIC_INIT(2),
.processes = ATOMIC_INIT(1),
.files = ATOMIC_INIT(0),
.sigpending = ATOMIC_INIT(0),
.locked_shm = 0,
+ .user_ns = &init_user_ns,
#ifdef CONFIG_USER_SCHED
.tg = &init_task_group,
#endif
@@ -101,19 +104,15 @@ static int sched_create_user(struct user_struct *up)
if (IS_ERR(up->tg))
rc = -ENOMEM;
- return rc;
-}
+ set_tg_uid(up);
-static void sched_switch_user(struct task_struct *p)
-{
- sched_move_task(p);
+ return rc;
}
#else /* CONFIG_USER_SCHED */
static void sched_destroy_user(struct user_struct *up) { }
static int sched_create_user(struct user_struct *up) { return 0; }
-static void sched_switch_user(struct task_struct *p) { }
#endif /* CONFIG_USER_SCHED */
@@ -242,13 +241,21 @@ static struct kobj_type uids_ktype = {
.release = uids_release,
};
-/* create /sys/kernel/uids/<uid>/cpu_share file for this user */
+/*
+ * Create /sys/kernel/uids/<uid>/cpu_share file for this user
+ * We do not create this file for users in a user namespace (until
+ * sysfs tagging is implemented).
+ *
+ * See Documentation/scheduler/sched-design-CFS.txt for ramifications.
+ */
static int uids_user_create(struct user_struct *up)
{
struct kobject *kobj = &up->kobj;
int error;
memset(kobj, 0, sizeof(struct kobject));
+ if (up->user_ns != &init_user_ns)
+ return 0;
kobj->kset = uids_kset;
error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid);
if (error) {
@@ -284,6 +291,8 @@ static void remove_user_sysfs_dir(struct work_struct *w)
unsigned long flags;
int remove_user = 0;
+ if (up->user_ns != &init_user_ns)
+ return;
/* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
* atomic.
*/
@@ -319,12 +328,13 @@ done:
* IRQ state (as stored in flags) is restored and uidhash_lock released
* upon function exit.
*/
-static inline void free_user(struct user_struct *up, unsigned long flags)
+static void free_user(struct user_struct *up, unsigned long flags)
{
/* restore back the count */
atomic_inc(&up->__count);
spin_unlock_irqrestore(&uidhash_lock, flags);
+ put_user_ns(up->user_ns);
INIT_WORK(&up->work, remove_user_sysfs_dir);
schedule_work(&up->work);
}
@@ -340,13 +350,14 @@ static inline void uids_mutex_unlock(void) { }
* IRQ state (as stored in flags) is restored and uidhash_lock released
* upon function exit.
*/
-static inline void free_user(struct user_struct *up, unsigned long flags)
+static void free_user(struct user_struct *up, unsigned long flags)
{
uid_hash_remove(up);
spin_unlock_irqrestore(&uidhash_lock, flags);
sched_destroy_user(up);
key_put(up->uid_keyring);
key_put(up->session_keyring);
+ put_user_ns(up->user_ns);
kmem_cache_free(uid_cachep, up);
}
@@ -362,7 +373,7 @@ struct user_struct *find_user(uid_t uid)
{
struct user_struct *ret;
unsigned long flags;
- struct user_namespace *ns = current->nsproxy->user_ns;
+ struct user_namespace *ns = current_user_ns();
spin_lock_irqsave(&uidhash_lock, flags);
ret = uid_hash_find(uid, uidhashentry(ns, uid));
@@ -409,6 +420,8 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
if (sched_create_user(new) < 0)
goto out_free_user;
+ new->user_ns = get_user_ns(ns);
+
if (uids_user_create(new))
goto out_destoy_sched;
@@ -432,7 +445,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
up = new;
}
spin_unlock_irq(&uidhash_lock);
-
}
uids_mutex_unlock();
@@ -441,6 +453,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
out_destoy_sched:
sched_destroy_user(new);
+ put_user_ns(new->user_ns);
out_free_user:
kmem_cache_free(uid_cachep, new);
out_unlock:
@@ -448,63 +461,6 @@ out_unlock:
return NULL;
}
-void switch_uid(struct user_struct *new_user)
-{
- struct user_struct *old_user;
-
- /* What if a process setreuid()'s and this brings the
- * new uid over his NPROC rlimit? We can check this now
- * cheaply with the new uid cache, so if it matters
- * we should be checking for it. -DaveM
- */
- old_user = current->user;
- atomic_inc(&new_user->processes);
- atomic_dec(&old_user->processes);
- switch_uid_keyring(new_user);
- current->user = new_user;
- sched_switch_user(current);
-
- /*
- * We need to synchronize with __sigqueue_alloc()
- * doing a get_uid(p->user).. If that saw the old
- * user value, we need to wait until it has exited
- * its critical region before we can free the old
- * structure.
- */
- smp_mb();
- spin_unlock_wait(&current->sighand->siglock);
-
- free_uid(old_user);
- suid_keys(current);
-}
-
-#ifdef CONFIG_USER_NS
-void release_uids(struct user_namespace *ns)
-{
- int i;
- unsigned long flags;
- struct hlist_head *head;
- struct hlist_node *nd;
-
- spin_lock_irqsave(&uidhash_lock, flags);
- /*
- * collapse the chains so that the user_struct-s will
- * be still alive, but not in hashes. subsequent free_uid()
- * will free them.
- */
- for (i = 0; i < UIDHASH_SZ; i++) {
- head = ns->uidhash_table + i;
- while (!hlist_empty(head)) {
- nd = head->first;
- hlist_del_init(nd);
- }
- }
- spin_unlock_irqrestore(&uidhash_lock, flags);
-
- free_uid(ns->root_user);
-}
-#endif
-
static int __init uid_cache_init(void)
{
int n;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 532858fa5b8..79084311ee5 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,60 +9,55 @@
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <linux/user_namespace.h>
+#include <linux/cred.h>
/*
- * Clone a new ns copying an original user ns, setting refcount to 1
- * @old_ns: namespace to clone
- * Return NULL on error (failure to kmalloc), new ns otherwise
+ * 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
+ * new namespace.
+ *
+ * This is called by copy_creds(), which will finish setting the target task's
+ * credentials.
*/
-static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
+int create_user_ns(struct cred *new)
{
struct user_namespace *ns;
- struct user_struct *new_user;
+ struct user_struct *root_user;
int n;
ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL);
if (!ns)
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
kref_init(&ns->kref);
for (n = 0; n < UIDHASH_SZ; ++n)
INIT_HLIST_HEAD(ns->uidhash_table + n);
- /* Insert new root user. */
- ns->root_user = alloc_uid(ns, 0);
- if (!ns->root_user) {
+ /* Alloc new root user. */
+ root_user = alloc_uid(ns, 0);
+ if (!root_user) {
kfree(ns);
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
}
- /* Reset current->user with a new one */
- new_user = alloc_uid(ns, current->uid);
- if (!new_user) {
- free_uid(ns->root_user);
- kfree(ns);
- return ERR_PTR(-ENOMEM);
- }
-
- switch_uid(new_user);
- return ns;
-}
-
-struct user_namespace * copy_user_ns(int flags, struct user_namespace *old_ns)
-{
- struct user_namespace *new_ns;
-
- BUG_ON(!old_ns);
- get_user_ns(old_ns);
-
- if (!(flags & CLONE_NEWUSER))
- return old_ns;
+ /* 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);
+#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 */
- new_ns = clone_user_ns(old_ns);
+ /* alloc_uid() incremented the userns refcount. Just set it to 1 */
+ kref_set(&ns->kref, 1);
- put_user_ns(old_ns);
- return new_ns;
+ return 0;
}
void free_user_ns(struct kref *kref)
@@ -70,7 +65,7 @@ void free_user_ns(struct kref *kref)
struct user_namespace *ns;
ns = container_of(kref, struct user_namespace, kref);
- release_uids(ns);
+ free_uid(ns->creator);
kfree(ns);
}
EXPORT_SYMBOL(free_user_ns);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index d4dc69ddebd..4952322cba4 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -84,21 +84,21 @@ static cpumask_t cpu_singlethread_map __read_mostly;
static cpumask_t cpu_populated_map __read_mostly;
/* If it's single threaded, it isn't in the list of workqueues. */
-static inline int is_single_threaded(struct workqueue_struct *wq)
+static inline int is_wq_single_threaded(struct workqueue_struct *wq)
{
return wq->singlethread;
}
static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
{
- return is_single_threaded(wq)
+ return is_wq_single_threaded(wq)
? &cpu_singlethread_map : &cpu_populated_map;
}
static
struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu)
{
- if (unlikely(is_single_threaded(wq)))
+ if (unlikely(is_wq_single_threaded(wq)))
cpu = singlethread_cpu;
return per_cpu_ptr(wq->cpu_wq, cpu);
}
@@ -769,7 +769,7 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
struct workqueue_struct *wq = cwq->wq;
- const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d";
+ const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d";
struct task_struct *p;
p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu);