summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/cgroup.c4
-rw-r--r--kernel/configs.c1
-rw-r--r--kernel/debug/debug_core.c139
-rw-r--r--kernel/debug/debug_core.h1
-rw-r--r--kernel/debug/kdb/kdb_debugger.c3
-rw-r--r--kernel/debug/kdb/kdb_io.c2
-rw-r--r--kernel/debug/kdb/kdb_main.c18
-rw-r--r--kernel/debug/kdb/kdb_private.h48
-rw-r--r--kernel/early_res.c590
-rw-r--r--kernel/gcov/fs.c1
-rw-r--r--kernel/kprobes.c1
-rw-r--r--kernel/pm_qos_params.c3
-rw-r--r--kernel/profile.c1
-rw-r--r--kernel/rtmutex-tester.c6
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/sys_ni.c1
-rw-r--r--kernel/trace/blktrace.c16
-rw-r--r--kernel/trace/ftrace.c2
-rw-r--r--kernel/trace/ring_buffer.c1
-rw-r--r--kernel/trace/trace_events.c6
-rw-r--r--kernel/trace/trace_kdb.c1
-rw-r--r--kernel/trace/trace_kprobe.c2
-rw-r--r--kernel/trace/trace_stack.c1
-rw-r--r--kernel/workqueue.c314
25 files changed, 312 insertions, 853 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index e2c9d52cfe9e..0b5ff083fa22 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -11,7 +11,6 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
async.o range.o jump_label.o
-obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
obj-y += groups.o
ifdef CONFIG_FUNCTION_TRACER
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 291ba3d04bea..7b69b8d0313d 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -52,7 +52,6 @@
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
-#include <linux/smp_lock.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
@@ -1222,7 +1221,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_sb_opts opts;
- lock_kernel();
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
@@ -1255,7 +1253,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
kfree(opts.name);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
- unlock_kernel();
return ret;
}
@@ -1568,7 +1565,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
out_err:
kfree(opts.release_agent);
kfree(opts.name);
-
return ret;
}
diff --git a/kernel/configs.c b/kernel/configs.c
index abaee684ecbf..b4066b44a99d 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -66,6 +66,7 @@ ikconfig_read_current(struct file *file, char __user *buf,
static const struct file_operations ikconfig_file_ops = {
.owner = THIS_MODULE,
.read = ikconfig_read_current,
+ .llseek = default_llseek,
};
static int __init ikconfig_init(void)
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index de407c78178d..fec596da9bd0 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -47,6 +47,7 @@
#include <linux/pid.h>
#include <linux/smp.h>
#include <linux/mm.h>
+#include <linux/rcupdate.h>
#include <asm/cacheflush.h>
#include <asm/byteorder.h>
@@ -109,13 +110,15 @@ static struct kgdb_bkpt kgdb_break[KGDB_MAX_BREAKPOINTS] = {
*/
atomic_t kgdb_active = ATOMIC_INIT(-1);
EXPORT_SYMBOL_GPL(kgdb_active);
+static DEFINE_RAW_SPINLOCK(dbg_master_lock);
+static DEFINE_RAW_SPINLOCK(dbg_slave_lock);
/*
* We use NR_CPUs not PERCPU, in case kgdb is used to debug early
* bootup code (which might not have percpu set up yet):
*/
-static atomic_t passive_cpu_wait[NR_CPUS];
-static atomic_t cpu_in_kgdb[NR_CPUS];
+static atomic_t masters_in_kgdb;
+static atomic_t slaves_in_kgdb;
static atomic_t kgdb_break_tasklet_var;
atomic_t kgdb_setting_breakpoint;
@@ -457,26 +460,32 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
return 1;
}
-static void dbg_cpu_switch(int cpu, int next_cpu)
+static void dbg_touch_watchdogs(void)
{
- /* Mark the cpu we are switching away from as a slave when it
- * holds the kgdb_active token. This must be done so that the
- * that all the cpus wait in for the debug core will not enter
- * again as the master. */
- if (cpu == atomic_read(&kgdb_active)) {
- kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
- kgdb_info[cpu].exception_state &= ~DCPU_WANT_MASTER;
- }
- kgdb_info[next_cpu].exception_state |= DCPU_NEXT_MASTER;
+ touch_softlockup_watchdog_sync();
+ clocksource_touch_watchdog();
+ rcu_cpu_stall_reset();
}
-static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
+ int exception_state)
{
unsigned long flags;
int sstep_tries = 100;
int error;
- int i, cpu;
+ int cpu;
int trace_on = 0;
+ int online_cpus = num_online_cpus();
+
+ kgdb_info[ks->cpu].enter_kgdb++;
+ kgdb_info[ks->cpu].exception_state |= exception_state;
+
+ if (exception_state == DCPU_WANT_MASTER)
+ atomic_inc(&masters_in_kgdb);
+ else
+ atomic_inc(&slaves_in_kgdb);
+ kgdb_disable_hw_debug(ks->linux_regs);
+
acquirelock:
/*
* Interrupts will be restored by the 'trap return' code, except when
@@ -489,14 +498,15 @@ acquirelock:
kgdb_info[cpu].task = current;
kgdb_info[cpu].ret_state = 0;
kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT;
- /*
- * Make sure the above info reaches the primary CPU before
- * our cpu_in_kgdb[] flag setting does:
- */
- atomic_inc(&cpu_in_kgdb[cpu]);
- if (exception_level == 1)
+ /* Make sure the above info reaches the primary CPU */
+ smp_mb();
+
+ if (exception_level == 1) {
+ if (raw_spin_trylock(&dbg_master_lock))
+ atomic_xchg(&kgdb_active, cpu);
goto cpu_master_loop;
+ }
/*
* CPU will loop if it is a slave or request to become a kgdb
@@ -508,10 +518,12 @@ cpu_loop:
kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER;
goto cpu_master_loop;
} else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
- if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+ if (raw_spin_trylock(&dbg_master_lock)) {
+ atomic_xchg(&kgdb_active, cpu);
break;
+ }
} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
- if (!atomic_read(&passive_cpu_wait[cpu]))
+ if (!raw_spin_is_locked(&dbg_slave_lock))
goto return_normal;
} else {
return_normal:
@@ -522,9 +534,12 @@ return_normal:
arch_kgdb_ops.correct_hw_break();
if (trace_on)
tracing_on();
- atomic_dec(&cpu_in_kgdb[cpu]);
- touch_softlockup_watchdog_sync();
- clocksource_touch_watchdog();
+ kgdb_info[cpu].exception_state &=
+ ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
+ kgdb_info[cpu].enter_kgdb--;
+ smp_mb__before_atomic_dec();
+ atomic_dec(&slaves_in_kgdb);
+ dbg_touch_watchdogs();
local_irq_restore(flags);
return 0;
}
@@ -541,8 +556,8 @@ return_normal:
(kgdb_info[cpu].task &&
kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
atomic_set(&kgdb_active, -1);
- touch_softlockup_watchdog_sync();
- clocksource_touch_watchdog();
+ raw_spin_unlock(&dbg_master_lock);
+ dbg_touch_watchdogs();
local_irq_restore(flags);
goto acquirelock;
@@ -563,16 +578,12 @@ return_normal:
if (dbg_io_ops->pre_exception)
dbg_io_ops->pre_exception();
- kgdb_disable_hw_debug(ks->linux_regs);
-
/*
* Get the passive CPU lock which will hold all the non-primary
* CPU in a spin state while the debugger is active
*/
- if (!kgdb_single_step) {
- for (i = 0; i < NR_CPUS; i++)
- atomic_inc(&passive_cpu_wait[i]);
- }
+ if (!kgdb_single_step)
+ raw_spin_lock(&dbg_slave_lock);
#ifdef CONFIG_SMP
/* Signal the other CPUs to enter kgdb_wait() */
@@ -583,10 +594,9 @@ return_normal:
/*
* Wait for the other CPUs to be notified and be waiting for us:
*/
- for_each_online_cpu(i) {
- while (kgdb_do_roundup && !atomic_read(&cpu_in_kgdb[i]))
- cpu_relax();
- }
+ while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
+ atomic_read(&slaves_in_kgdb)) != online_cpus)
+ cpu_relax();
/*
* At this point the primary processor is completely
@@ -615,7 +625,8 @@ cpu_master_loop:
if (error == DBG_PASS_EVENT) {
dbg_kdb_mode = !dbg_kdb_mode;
} else if (error == DBG_SWITCH_CPU_EVENT) {
- dbg_cpu_switch(cpu, dbg_switch_cpu);
+ kgdb_info[dbg_switch_cpu].exception_state |=
+ DCPU_NEXT_MASTER;
goto cpu_loop;
} else {
kgdb_info[cpu].ret_state = error;
@@ -627,24 +638,11 @@ cpu_master_loop:
if (dbg_io_ops->post_exception)
dbg_io_ops->post_exception();
- atomic_dec(&cpu_in_kgdb[ks->cpu]);
-
if (!kgdb_single_step) {
- for (i = NR_CPUS-1; i >= 0; i--)
- atomic_dec(&passive_cpu_wait[i]);
- /*
- * Wait till all the CPUs have quit from the debugger,
- * but allow a CPU that hit an exception and is
- * waiting to become the master to remain in the debug
- * core.
- */
- for_each_online_cpu(i) {
- while (kgdb_do_roundup &&
- atomic_read(&cpu_in_kgdb[i]) &&
- !(kgdb_info[i].exception_state &
- DCPU_WANT_MASTER))
- cpu_relax();
- }
+ raw_spin_unlock(&dbg_slave_lock);
+ /* Wait till all the CPUs have quit from the debugger. */
+ while (kgdb_do_roundup && atomic_read(&slaves_in_kgdb))
+ cpu_relax();
}
kgdb_restore:
@@ -655,12 +653,20 @@ kgdb_restore:
else
kgdb_sstep_pid = 0;
}
+ if (arch_kgdb_ops.correct_hw_break)
+ arch_kgdb_ops.correct_hw_break();
if (trace_on)
tracing_on();
+
+ kgdb_info[cpu].exception_state &=
+ ~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
+ kgdb_info[cpu].enter_kgdb--;
+ smp_mb__before_atomic_dec();
+ atomic_dec(&masters_in_kgdb);
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
- touch_softlockup_watchdog_sync();
- clocksource_touch_watchdog();
+ raw_spin_unlock(&dbg_master_lock);
+ dbg_touch_watchdogs();
local_irq_restore(flags);
return kgdb_info[cpu].ret_state;
@@ -678,7 +684,6 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
{
struct kgdb_state kgdb_var;
struct kgdb_state *ks = &kgdb_var;
- int ret;
ks->cpu = raw_smp_processor_id();
ks->ex_vector = evector;
@@ -689,11 +694,10 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
if (kgdb_reenter_check(ks))
return 0; /* Ouch, double exception ! */
- kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
- ret = kgdb_cpu_enter(ks, regs);
- kgdb_info[ks->cpu].exception_state &= ~(DCPU_WANT_MASTER |
- DCPU_IS_SLAVE);
- return ret;
+ if (kgdb_info[ks->cpu].enter_kgdb != 0)
+ return 0;
+
+ return kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
}
int kgdb_nmicallback(int cpu, void *regs)
@@ -706,12 +710,9 @@ int kgdb_nmicallback(int cpu, void *regs)
ks->cpu = cpu;
ks->linux_regs = regs;
- if (!atomic_read(&cpu_in_kgdb[cpu]) &&
- atomic_read(&kgdb_active) != -1 &&
- atomic_read(&kgdb_active) != cpu) {
- kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
- kgdb_cpu_enter(ks, regs);
- kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
+ if (kgdb_info[ks->cpu].enter_kgdb == 0 &&
+ raw_spin_is_locked(&dbg_master_lock)) {
+ kgdb_cpu_enter(ks, regs, DCPU_IS_SLAVE);
return 0;
}
#endif
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index c5d753d80f67..3494c28a7e7a 100644
--- a/kernel/debug/debug_core.h
+++ b/kernel/debug/debug_core.h
@@ -40,6 +40,7 @@ struct debuggerinfo_struct {
int exception_state;
int ret_state;
int irq_depth;
+ int enter_kgdb;
};
extern struct debuggerinfo_struct kgdb_info[];
diff --git a/kernel/debug/kdb/kdb_debugger.c b/kernel/debug/kdb/kdb_debugger.c
index bf6e8270e957..dd0b1b7dd02c 100644
--- a/kernel/debug/kdb/kdb_debugger.c
+++ b/kernel/debug/kdb/kdb_debugger.c
@@ -86,7 +86,7 @@ int kdb_stub(struct kgdb_state *ks)
}
/* Set initial kdb state variables */
KDB_STATE_CLEAR(KGDB_TRANS);
- kdb_initial_cpu = ks->cpu;
+ kdb_initial_cpu = atomic_read(&kgdb_active);
kdb_current_task = kgdb_info[ks->cpu].task;
kdb_current_regs = kgdb_info[ks->cpu].debuggerinfo;
/* Remove any breakpoints as needed by kdb and clear single step */
@@ -105,7 +105,6 @@ int kdb_stub(struct kgdb_state *ks)
ks->pass_exception = 1;
KDB_FLAG_SET(CATASTROPHIC);
}
- kdb_initial_cpu = ks->cpu;
if (KDB_STATE(SSBPT) && reason == KDB_REASON_SSTEP) {
KDB_STATE_CLEAR(SSBPT);
KDB_STATE_CLEAR(DOING_SS);
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index c9b7f4f90bba..96fdaac46a80 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -823,4 +823,4 @@ int kdb_printf(const char *fmt, ...)
return r;
}
-
+EXPORT_SYMBOL_GPL(kdb_printf);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index caf057a3de0e..d7bda21a106b 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1749,13 +1749,13 @@ static int kdb_go(int argc, const char **argv)
int nextarg;
long offset;
+ if (raw_smp_processor_id() != kdb_initial_cpu) {
+ kdb_printf("go must execute on the entry cpu, "
+ "please use \"cpu %d\" and then execute go\n",
+ kdb_initial_cpu);
+ return KDB_BADCPUNUM;
+ }
if (argc == 1) {
- if (raw_smp_processor_id() != kdb_initial_cpu) {
- kdb_printf("go <address> must be issued from the "
- "initial cpu, do cpu %d first\n",
- kdb_initial_cpu);
- return KDB_ARGCOUNT;
- }
nextarg = 1;
diag = kdbgetaddrarg(argc, argv, &nextarg,
&addr, &offset, NULL);
@@ -2783,6 +2783,8 @@ int kdb_register_repeat(char *cmd,
return 0;
}
+EXPORT_SYMBOL_GPL(kdb_register_repeat);
+
/*
* kdb_register - Compatibility register function for commands that do
@@ -2805,6 +2807,7 @@ int kdb_register(char *cmd,
return kdb_register_repeat(cmd, func, usage, help, minlen,
KDB_REPEAT_NONE);
}
+EXPORT_SYMBOL_GPL(kdb_register);
/*
* kdb_unregister - This function is used to unregister a kernel
@@ -2823,7 +2826,7 @@ int kdb_unregister(char *cmd)
/*
* find the command.
*/
- for (i = 0, kp = kdb_commands; i < kdb_max_commands; i++, kp++) {
+ for_each_kdbcmd(kp, i) {
if (kp->cmd_name && (strcmp(kp->cmd_name, cmd) == 0)) {
kp->cmd_name = NULL;
return 0;
@@ -2833,6 +2836,7 @@ int kdb_unregister(char *cmd)
/* Couldn't find it. */
return 1;
}
+EXPORT_SYMBOL_GPL(kdb_unregister);
/* Initialize the kdb command table. */
static void __init kdb_inittab(void)
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index be775f7e81e0..35d69ed1dfb5 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -15,29 +15,6 @@
#include <linux/kgdb.h>
#include "../debug_core.h"
-/* Kernel Debugger Error codes. Must not overlap with command codes. */
-#define KDB_NOTFOUND (-1)
-#define KDB_ARGCOUNT (-2)
-#define KDB_BADWIDTH (-3)
-#define KDB_BADRADIX (-4)
-#define KDB_NOTENV (-5)
-#define KDB_NOENVVALUE (-6)
-#define KDB_NOTIMP (-7)
-#define KDB_ENVFULL (-8)
-#define KDB_ENVBUFFULL (-9)
-#define KDB_TOOMANYBPT (-10)
-#define KDB_TOOMANYDBREGS (-11)
-#define KDB_DUPBPT (-12)
-#define KDB_BPTNOTFOUND (-13)
-#define KDB_BADMODE (-14)
-#define KDB_BADINT (-15)
-#define KDB_INVADDRFMT (-16)
-#define KDB_BADREG (-17)
-#define KDB_BADCPUNUM (-18)
-#define KDB_BADLENGTH (-19)
-#define KDB_NOBP (-20)
-#define KDB_BADADDR (-21)
-
/* Kernel Debugger Command codes. Must not overlap with error codes. */
#define KDB_CMD_GO (-1001)
#define KDB_CMD_CPU (-1002)
@@ -93,17 +70,6 @@
*/
#define KDB_MAXBPT 16
-/* Maximum number of arguments to a function */
-#define KDB_MAXARGS 16
-
-typedef enum {
- KDB_REPEAT_NONE = 0, /* Do not repeat this command */
- KDB_REPEAT_NO_ARGS, /* Repeat the command without arguments */
- KDB_REPEAT_WITH_ARGS, /* Repeat the command including its arguments */
-} kdb_repeat_t;
-
-typedef int (*kdb_func_t)(int, const char **);
-
/* Symbol table format returned by kallsyms. */
typedef struct __ksymtab {
unsigned long value; /* Address of symbol */
@@ -123,11 +89,6 @@ extern int kallsyms_symbol_next(char *prefix_name, int flag);
extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
/* Exported Symbols for kernel loadable modules to use. */
-extern int kdb_register(char *, kdb_func_t, char *, char *, short);
-extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
- short, kdb_repeat_t);
-extern int kdb_unregister(char *);
-
extern int kdb_getarea_size(void *, unsigned long, size_t);
extern int kdb_putarea_size(unsigned long, void *, size_t);
@@ -144,6 +105,7 @@ extern int kdb_getword(unsigned long *, unsigned long, size_t);
extern int kdb_putword(unsigned long, unsigned long, size_t);
extern int kdbgetularg(const char *, unsigned long *);
+extern int kdbgetu64arg(const char *, u64 *);
extern char *kdbgetenv(const char *);
extern int kdbgetaddrarg(int, const char **, int*, unsigned long *,
long *, char **);
@@ -255,14 +217,6 @@ extern void kdb_ps1(const struct task_struct *p);
extern void kdb_print_nameval(const char *name, unsigned long val);
extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info);
extern void kdb_meminfo_proc_show(void);
-#ifdef CONFIG_KALLSYMS
-extern const char *kdb_walk_kallsyms(loff_t *pos);
-#else /* ! CONFIG_KALLSYMS */
-static inline const char *kdb_walk_kallsyms(loff_t *pos)
-{
- return NULL;
-}
-#endif /* ! CONFIG_KALLSYMS */
extern char *kdb_getstr(char *, size_t, char *);
/* Defines for kdb_symbol_print */
diff --git a/kernel/early_res.c b/kernel/early_res.c
deleted file mode 100644
index 7bfae887f211..000000000000
--- a/kernel/early_res.c
+++ /dev/null
@@ -1,590 +0,0 @@
-/*
- * early_res, could be used to replace bootmem
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/early_res.h>
-#include <linux/slab.h>
-#include <linux/kmemleak.h>
-
-/*
- * Early reserved memory areas.
- */
-/*
- * need to make sure this one is bigger enough before
- * find_fw_memmap_area could be used
- */
-#define MAX_EARLY_RES_X 32
-
-struct early_res {
- u64 start, end;
- char name[15];
- char overlap_ok;
-};
-static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
-
-static int max_early_res __initdata = MAX_EARLY_RES_X;
-static struct early_res *early_res __initdata = &early_res_x[0];
-static int early_res_count __initdata;
-
-static int __init find_overlapped_early(u64 start, u64 end)
-{
- int i;
- struct early_res *r;
-
- for (i = 0; i < max_early_res && early_res[i].end; i++) {
- r = &early_res[i];
- if (end > r->start && start < r->end)
- break;
- }
-
- return i;
-}
-
-/*
- * Drop the i-th range from the early reservation map,
- * by copying any higher ranges down one over it, and
- * clearing what had been the last slot.
- */
-static void __init drop_range(int i)
-{
- int j;
-
- for (j = i + 1; j < max_early_res && early_res[j].end; j++)
- ;
-
- memmove(&early_res[i], &early_res[i + 1],
- (j - 1 - i) * sizeof(struct early_res));
-
- early_res[j - 1].end = 0;
- early_res_count--;
-}
-
-static void __init drop_range_partial(int i, u64 start, u64 end)
-{
- u64 common_start, common_end;
- u64 old_start, old_end;
-
- old_start = early_res[i].start;
- old_end = early_res[i].end;
- common_start = max(old_start, start);
- common_end = min(old_end, end);
-
- /* no overlap ? */
- if (common_start >= common_end)
- return;
-
- if (old_start < common_start) {
- /* make head segment */
- early_res[i].end = common_start;
- if (old_end > common_end) {
- char name[15];
-
- /*
- * Save a local copy of the name, since the
- * early_res array could get resized inside
- * reserve_early_without_check() ->
- * __check_and_double_early_res(), which would
- * make the current name pointer invalid.
- */
- strncpy(name, early_res[i].name,
- sizeof(early_res[i].name) - 1);
- /* add another for left over on tail */
- reserve_early_without_check(common_end, old_end, name);
- }
- return;
- } else {
- if (old_end > common_end) {
- /* reuse the entry for tail left */
- early_res[i].start = common_end;
- return;
- }
- /* all covered */
- drop_range(i);
- }
-}
-
-/*
- * Split any existing ranges that:
- * 1) are marked 'overlap_ok', and
- * 2) overlap with the stated range [start, end)
- * into whatever portion (if any) of the existing range is entirely
- * below or entirely above the stated range. Drop the portion
- * of the existing range that overlaps with the stated range,
- * which will allow the caller of this routine to then add that
- * stated range without conflicting with any existing range.
- */
-static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
-{
- int i;
- struct early_res *r;
- u64 lower_start, lower_end;
- u64 upper_start, upper_end;
- char name[15];
-
- for (i = 0; i < max_early_res && early_res[i].end; i++) {
- r = &early_res[i];
-
- /* Continue past non-overlapping ranges */
- if (end <= r->start || start >= r->end)
- continue;
-
- /*
- * Leave non-ok overlaps as is; let caller
- * panic "Overlapping early reservations"
- * when it hits this overlap.
- */
- if (!r->overlap_ok)
- return;
-
- /*
- * We have an ok overlap. We will drop it from the early
- * reservation map, and add back in any non-overlapping
- * portions (lower or upper) as separate, overlap_ok,
- * non-overlapping ranges.
- */
-
- /* 1. Note any non-overlapping (lower or upper) ranges. */
- strncpy(name, r->name, sizeof(name) - 1);
-
- lower_start = lower_end = 0;
- upper_start = upper_end = 0;
- if (r->start < start) {
- lower_start = r->start;
- lower_end = start;
- }
- if (r->end > end) {
- upper_start = end;
- upper_end = r->end;
- }
-
- /* 2. Drop the original ok overlapping range */
- drop_range(i);
-
- i--; /* resume for-loop on copied down entry */
-
- /* 3. Add back in any non-overlapping ranges. */
- if (lower_end)
- reserve_early_overlap_ok(lower_start, lower_end, name);
- if (upper_end)
- reserve_early_overlap_ok(upper_start, upper_end, name);
- }
-}
-
-static void __init __reserve_early(u64 start, u64 end, char *name,
- int overlap_ok)
-{
- int i;
- struct early_res *r;
-
- i = find_overlapped_early(start, end);
- if (i >= max_early_res)
- panic("Too many early reservations");
- r = &early_res[i];
- if (r->end)
- panic("Overlapping early reservations "
- "%llx-%llx %s to %llx-%llx %s\n",
- start, end - 1, name ? name : "", r->start,
- r->end - 1, r->name);
- r->start = start;
- r->end = end;
- r->overlap_ok = overlap_ok;
- if (name)
- strncpy(r->name, name, sizeof(r->name) - 1);
- early_res_count++;
-}
-
-/*
- * A few early reservtations come here.
- *
- * The 'overlap_ok' in the name of this routine does -not- mean it
- * is ok for these reservations to overlap an earlier reservation.
- * Rather it means that it is ok for subsequent reservations to
- * overlap this one.
- *
- * Use this entry point to reserve early ranges when you are doing
- * so out of "Paranoia", reserving perhaps more memory than you need,
- * just in case, and don't mind a subsequent overlapping reservation
- * that is known to be needed.
- *
- * The drop_overlaps_that_are_ok() call here isn't really needed.
- * It would be needed if we had two colliding 'overlap_ok'
- * reservations, so that the second such would not panic on the
- * overlap with the first. We don't have any such as of this
- * writing, but might as well tolerate such if it happens in
- * the future.
- */
-void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
-{
- drop_overlaps_that_are_ok(start, end);
- __reserve_early(start, end, name, 1);
-}
-
-static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
-{
- u64 start, end, size, mem;
- struct early_res *new;
-
- /* do we have enough slots left ? */
- if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
- return;
-
- /* double it */
- mem = -1ULL;
- size = sizeof(struct early_res) * max_early_res * 2;
- if (early_res == early_res_x)
- start = 0;
- else
- start = early_res[0].end;
- end = ex_start;
- if (start + size < end)
- mem = find_fw_memmap_area(start, end, size,
- sizeof(struct early_res));
- if (mem == -1ULL) {
- start = ex_end;
- end = get_max_mapped();
- if (start + size < end)
- mem = find_fw_memmap_area(start, end, size,
- sizeof(struct early_res));
- }
- if (mem == -1ULL)
- panic("can not find more space for early_res array");
-
- new = __va(mem);
- /* save the first one for own */
- new[0].start = mem;
- new[0].end = mem + size;
- new[0].overlap_ok = 0;
- /* copy old to new */
- if (early_res == early_res_x) {
- memcpy(&new[1], &early_res[0],
- sizeof(struct early_res) * max_early_res);
- memset(&new[max_early_res+1], 0,
- sizeof(struct early_res) * (max_early_res - 1));
- early_res_count++;
- } else {
- memcpy(&new[1], &early_res[1],
- sizeof(struct early_res) * (max_early_res - 1));
- memset(&new[max_early_res], 0,
- sizeof(struct early_res) * max_early_res);
- }
- memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
- early_res = new;
- max_early_res *= 2;
- printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
- max_early_res, mem, mem + size - 1);
-}
-
-/*
- * Most early reservations come here.
- *
- * We first have drop_overlaps_that_are_ok() drop any pre-existing
- * 'overlap_ok' ranges, so that we can then reserve this memory
- * range without risk of panic'ing on an overlapping overlap_ok
- * early reservation.
- */
-void __init reserve_early(u64 start, u64 end, char *name)
-{
- if (start >= end)
- return;
-
- __check_and_double_early_res(start, end);
-
- drop_overlaps_that_are_ok(start, end);
- __reserve_early(start, end, name, 0);
-}
-
-void __init reserve_early_without_check(u64 start, u64 end, char *name)
-{
- struct early_res *r;
-
- if (start >= end)
- return;
-
- __check_and_double_early_res(start, end);
-
- r = &early_res[early_res_count];
-
- r->start = start;
- r->end = end;
- r->overlap_ok = 0;
- if (name)
- strncpy(r->name, name, sizeof(r->name) - 1);
- early_res_count++;
-}
-
-void __init free_early(u64 start, u64 end)
-{
- struct early_res *r;
- int i;
-
- kmemleak_free_part(__va(start), end - start);
-
- i = find_overlapped_early(start, end);
- r = &early_res[i];
- if (i >= max_early_res || r->end != end || r->start != start)
- panic("free_early on not reserved area: %llx-%llx!",
- start, end - 1);
-
- drop_range(i);
-}
-
-void __init free_early_partial(u64 start, u64 end)
-{
- struct early_res *r;
- int i;
-
- kmemleak_free_part(__va(start), end - start);
-
- if (start == end)
- return;
-
- if (WARN_ONCE(start > end, " wrong range [%#llx, %#llx]\n", start, end))
- return;
-
-try_next:
- i = find_overlapped_early(start, end);
- if (i >= max_early_res)
- return;
-
- r = &early_res[i];
- /* hole ? */
- if (r->end >= end && r->start <= start) {
- drop_range_partial(i, start, end);
- return;
- }
-
- drop_range_partial(i, start, end);
- goto try_next;
-}
-
-#ifdef CONFIG_NO_BOOTMEM
-static void __init subtract_early_res(struct range *range, int az)
-{
- int i, count;
- u64 final_start, final_end;
- int idx = 0;
-
- count = 0;
- for (i = 0; i < max_early_res && early_res[i].end; i++)
- count++;
-
- /* need to skip first one ?*/
- if (early_res != early_res_x)
- idx = 1;
-
-#define DEBUG_PRINT_EARLY_RES 1
-
-#if DEBUG_PRINT_EARLY_RES
- printk(KERN_INFO "Subtract (%d early reservations)\n", count);
-#endif
- for (i = idx; i < count; i++) {
- struct early_res *r = &early_res[i];
-#if DEBUG_PRINT_EARLY_RES
- printk(KERN_INFO " #%d [%010llx - %010llx] %15s\n", i,
- r->start, r->end, r->name);
-#endif
- final_start = PFN_DOWN(r->start);
- final_end = PFN_UP(r->end);
- if (final_start >= final_end)
- continue;
- subtract_range(range, az, final_start, final_end);
- }
-
-}
-
-int __init get_free_all_memory_range(struct range **rangep, int nodeid)
-{
- int i, count;
- u64 start = 0, end;
- u64 size;
- u64 mem;
- struct range *range;
- int nr_range;
-
- count = 0;
- for (i = 0; i < max_early_res && early_res[i].end; i++)
- count++;
-
- count *= 2;
-
- size = sizeof(struct range) * count;
- end = get_max_mapped();
-#ifdef MAX_DMA32_PFN
- if (end > (MAX_DMA32_PFN << PAGE_SHIFT))
- start = MAX_DMA32_PFN << PAGE_SHIFT;
-#endif
- mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
- if (mem == -1ULL)
- panic("can not find more space for range free");
-
- range = __va(mem);
- /* use early_node_map[] and early_res to get range array at first */
- memset(range, 0, size);
- nr_range = 0;
-
- /* need to go over early_node_map to find out good range for node */
- nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
-#ifdef CONFIG_X86_32
- subtract_range(range, count, max_low_pfn, -1ULL);
-#endif
- subtract_early_res(range, count);
- nr_range = clean_sort_range(range, count);
-
- /* need to clear it ? */
- if (nodeid == MAX_NUMNODES) {
- memset(&early_res[0], 0,
- sizeof(struct early_res) * max_early_res);
- early_res = NULL;
- max_early_res = 0;
- }
-
- *rangep = range;
- return nr_range;
-}
-#else
-void __init early_res_to_bootmem(u64 start, u64 end)
-{
- int i, count;
- u64 final_start, final_end;
- int idx = 0;
-
- count = 0;
- for (i = 0; i < max_early_res && early_res[i].end; i++)
- count++;
-
- /* need to skip first one ?*/
- if (early_res != early_res_x)
- idx = 1;
-
- printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
- count - idx, max_early_res, start, end);
- for (i = idx; i < count; i++) {
- struct early_res *r = &early_res[i];
- printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i,
- r->start, r->end, r->name);
- final_start = max(start, r->start);
- final_end = min(end, r->end);
- if (final_start >= final_end) {
- printk(KERN_CONT "\n");
- continue;
- }
- printk(KERN_CONT " ==> [%010llx - %010llx]\n",
- final_start, final_end);
- reserve_bootmem_generic(final_start, final_end - final_start,
- BOOTMEM_DEFAULT);
- }
- /* clear them */
- memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
- early_res = NULL;
- max_early_res = 0;
- early_res_count = 0;
-}
-#endif
-
-/* Check for already reserved areas */
-static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
-{
- int i;
- u64 addr = *addrp;
- int changed = 0;
- struct early_res *r;
-again:
- i = find_overlapped_early(addr, addr + size);
- r = &early_res[i];
- if (i < max_early_res && r->end) {
- *addrp = addr = round_up(r->end, align);
- changed = 1;
- goto again;
- }
- return changed;
-}
-
-/* Check for already reserved areas */
-static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
-{
- int i;
- u64 addr = *addrp, last;
- u64 size = *sizep;
- int changed = 0;
-again:
- last = addr + size;
- for (i = 0; i < max_early_res && early_res[i].end; i++) {
- struct early_res *r = &early_res[i];
- if (last > r->start && addr < r->start) {
- size = r->start - addr;
- changed = 1;
- goto again;
- }
- if (last > r->end && addr < r->end) {
- addr = round_up(r->end, align);
- size = last - addr;
- changed = 1;
- goto again;
- }
- if (last <= r->end && addr >= r->start) {
- (*sizep)++;
- return 0;
- }
- }
- if (changed) {
- *addrp = addr;
- *sizep = size;
- }
- return changed;
-}
-
-/*
- * Find a free area with specified alignment in a specific range.
- * only with the area.between start to end is active range from early_node_map
- * so they are good as RAM
- */
-u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
- u64 size, u64 align)
-{
- u64 addr, last;
-
- addr = round_up(ei_start, align);
- if (addr < start)
- addr = round_up(start, align);
- if (addr >= ei_last)
- goto out;
- while (bad_addr(&addr, size, align) && addr+size <= ei_last)
- ;
- last = addr + size;
- if (last > ei_last)
- goto out;
- if (last > end)
- goto out;
-
- return addr;
-
-out:
- return -1ULL;
-}
-
-u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
- u64 *sizep, u64 align)
-{
- u64 addr, last;
-
- addr = round_up(ei_start, align);
- if (addr < start)
- addr = round_up(start, align);
- if (addr >= ei_last)
- goto out;
- *sizep = ei_last - addr;
- while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
- ;
- last = addr + *sizep;
- if (last > ei_last)
- goto out;
-
- return addr;
-
-out:
- return -1ULL;
-}
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index f83972b16564..9bd0934f6c33 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -561,6 +561,7 @@ static ssize_t reset_read(struct file *file, char __user *addr, size_t len,
static const struct file_operations gcov_reset_fops = {
.write = reset_write,
.read = reset_read,
+ .llseek = noop_llseek,
};
/*
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ec4210c6501e..56a891914273 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2000,6 +2000,7 @@ static ssize_t write_enabled_file_bool(struct file *file,
static const struct file_operations fops_kp = {
.read = read_enabled_file_bool,
.write = write_enabled_file_bool,
+ .llseek = default_llseek,
};
static int __kprobes debugfs_kprobe_init(void)
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index 645e541a45f6..c7a8f453919e 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -110,6 +110,7 @@ static const struct file_operations pm_qos_power_fops = {
.write = pm_qos_power_write,
.open = pm_qos_power_open,
.release = pm_qos_power_release,
+ .llseek = noop_llseek,
};
/* unlocked internal variant */
@@ -398,7 +399,7 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
} else
return -EINVAL;
- pm_qos_req = (struct pm_qos_request_list *)filp->private_data;
+ pm_qos_req = filp->private_data;
pm_qos_update_request(pm_qos_req, value);
return count;
diff --git a/kernel/profile.c b/kernel/profile.c
index b22a899934cc..66f841b7fbd3 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -555,6 +555,7 @@ static ssize_t write_profile(struct file *file, const char __user *buf,
static const struct file_operations proc_profile_operations = {
.read = read_profile,
.write = write_profile,
+ .llseek = default_llseek,
};
#ifdef CONFIG_SMP
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index a56f629b057a..66cb89bc5ef1 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -76,7 +76,9 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
}
if (!lockwakeup && td->bkl == 4) {
+#ifdef CONFIG_LOCK_KERNEL
unlock_kernel();
+#endif
td->bkl = 0;
}
return 0;
@@ -133,14 +135,18 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
if (td->bkl)
return 0;
td->bkl = 1;
+#ifdef CONFIG_LOCK_KERNEL
lock_kernel();
+#endif
td->bkl = 4;
return 0;
case RTTEST_UNLOCKBKL:
if (td->bkl != 4)
break;
+#ifdef CONFIG_LOCK_KERNEL
unlock_kernel();
+#endif
td->bkl = 0;
return 0;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index fc978889b194..f02a9dfa19bc 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -67,7 +67,7 @@ char *softirq_to_name[NR_SOFTIRQS] = {
* to the pending events, so lets the scheduler to balance
* the softirq load for us.
*/
-void wakeup_softirqd(void)
+static void wakeup_softirqd(void)
{
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index bad369ec5403..c782fe9924c7 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -50,6 +50,7 @@ cond_syscall(compat_sys_sendmsg);
cond_syscall(sys_recvmsg);
cond_syscall(sys_recvmmsg);
cond_syscall(compat_sys_recvmsg);
+cond_syscall(compat_sys_recv);
cond_syscall(compat_sys_recvfrom);
cond_syscall(compat_sys_recvmmsg);
cond_syscall(sys_socketcall);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 959f8d6c8cc1..bc251ed66724 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -23,7 +23,6 @@
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
-#include <linux/smp_lock.h>
#include <linux/time.h>
#include <linux/uaccess.h>
@@ -326,6 +325,7 @@ static const struct file_operations blk_dropped_fops = {
.owner = THIS_MODULE,
.open = blk_dropped_open,
.read = blk_dropped_read,
+ .llseek = default_llseek,
};
static int blk_msg_open(struct inode *inode, struct file *filp)
@@ -365,6 +365,7 @@ static const struct file_operations blk_msg_fops = {
.owner = THIS_MODULE,
.open = blk_msg_open,
.write = blk_msg_write,
+ .llseek = noop_llseek,
};
/*
@@ -639,7 +640,6 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
if (!q)
return -ENXIO;
- lock_kernel();
mutex_lock(&bdev->bd_mutex);
switch (cmd) {
@@ -667,7 +667,6 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
}
mutex_unlock(&bdev->bd_mutex);
- unlock_kernel();
return ret;
}
@@ -1652,10 +1651,9 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
struct block_device *bdev;
ssize_t ret = -ENXIO;
- lock_kernel();
bdev = bdget(part_devt(p));
if (bdev == NULL)
- goto out_unlock_kernel;
+ goto out;
q = blk_trace_get_queue(bdev);
if (q == NULL)
@@ -1683,8 +1681,7 @@ out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
out_bdput:
bdput(bdev);
-out_unlock_kernel:
- unlock_kernel();
+out:
return ret;
}
@@ -1714,11 +1711,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
ret = -ENXIO;
- lock_kernel();
p = dev_to_part(dev);
bdev = bdget(part_devt(p));
if (bdev == NULL)
- goto out_unlock_kernel;
+ goto out;
q = blk_trace_get_queue(bdev);
if (q == NULL)
@@ -1753,8 +1749,6 @@ out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
out_bdput:
bdput(bdev);
-out_unlock_kernel:
- unlock_kernel();
out:
return ret ? ret : count;
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ebd80d50c474..f3dadae83883 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -800,6 +800,7 @@ static const struct file_operations ftrace_profile_fops = {
.open = tracing_open_generic,
.read = ftrace_profile_read,
.write = ftrace_profile_write,
+ .llseek = default_llseek,
};
/* used to initialize the real stat files */
@@ -2669,6 +2670,7 @@ static const struct file_operations ftrace_graph_fops = {
.read = seq_read,
.write = ftrace_graph_write,
.release = ftrace_graph_release,
+ .llseek = seq_lseek,
};
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c5a632a669e1..c3dab054d18e 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3974,6 +3974,7 @@ static const struct file_operations rb_simple_fops = {
.open = tracing_open_generic,
.read = rb_simple_read,
.write = rb_simple_write,
+ .llseek = default_llseek,
};
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 398c0e8b332c..0725eeab1937 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -932,6 +932,7 @@ static const struct file_operations ftrace_enable_fops = {
.open = tracing_open_generic,
.read = event_enable_read,
.write = event_enable_write,
+ .llseek = default_llseek,
};
static const struct file_operations ftrace_event_format_fops = {
@@ -944,29 +945,34 @@ static const struct file_operations ftrace_event_format_fops = {
static const struct file_operations ftrace_event_id_fops = {
.open = tracing_open_generic,
.read = event_id_read,
+ .llseek = default_llseek,
};
static const struct file_operations ftrace_event_filter_fops = {
.open = tracing_open_generic,
.read = event_filter_read,
.write = event_filter_write,
+ .llseek = default_llseek,
};
static const struct file_operations ftrace_subsystem_filter_fops = {
.open = tracing_open_generic,
.read = subsystem_filter_read,
.write = subsystem_filter_write,
+ .llseek = default_llseek,
};
static const struct file_operations ftrace_system_enable_fops = {
.open = tracing_open_generic,
.read = system_enable_read,
.write = system_enable_write,
+ .llseek = default_llseek,
};
static const struct file_operations ftrace_show_header_fops = {
.open = tracing_open_generic,
.read = show_header,
+ .llseek = default_llseek,
};
static struct dentry *event_trace_events_dir(void)
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 7b8ecd751d93..3c5c5dfea0b3 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -13,7 +13,6 @@
#include <linux/kdb.h>
#include <linux/ftrace.h>
-#include "../debug/kdb/kdb_private.h"
#include "trace.h"
#include "trace_output.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 544301d29dee..b8d2852baa4a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -648,7 +648,7 @@ static int register_trace_probe(struct trace_probe *tp)
}
ret = register_probe_event(tp);
if (ret) {
- pr_warning("Faild to register probe event(%d)\n", ret);
+ pr_warning("Failed to register probe event(%d)\n", ret);
goto end;
}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index a6b7e0e0f3eb..4c5dead0c239 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -195,6 +195,7 @@ static const struct file_operations stack_max_size_fops = {
.open = tracing_open_generic,
.read = stack_max_size_read,
.write = stack_max_size_write,
+ .llseek = default_llseek,
};
static void *
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f77afd939229..e5ff2cbaadc2 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -42,9 +42,6 @@
#include <linux/lockdep.h>
#include <linux/idr.h>
-#define CREATE_TRACE_POINTS
-#include <trace/events/workqueue.h>
-
#include "workqueue_sched.h"
enum {
@@ -257,6 +254,9 @@ EXPORT_SYMBOL_GPL(system_long_wq);
EXPORT_SYMBOL_GPL(system_nrt_wq);
EXPORT_SYMBOL_GPL(system_unbound_wq);
+#define CREATE_TRACE_POINTS
+#include <trace/events/workqueue.h>
+
#define for_each_busy_worker(worker, i, pos, gcwq) \
for (i = 0; i < BUSY_WORKER_HASH_SIZE; i++) \
hlist_for_each_entry(worker, pos, &gcwq->busy_hash[i], hentry)
@@ -310,21 +310,6 @@ static inline int __next_wq_cpu(int cpu, const struct cpumask *mask,
(cpu) < WORK_CPU_NONE; \
(cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))
-#ifdef CONFIG_LOCKDEP
-/**
- * in_workqueue_context() - in context of specified workqueue?
- * @wq: the workqueue of interest
- *
- * Checks lockdep state to see if the current task is executing from
- * within a workqueue item. This function exists only if lockdep is
- * enabled.
- */
-int in_workqueue_context(struct workqueue_struct *wq)
-{
- return lock_is_held(&wq->lockdep_map);
-}
-#endif
-
#ifdef CONFIG_DEBUG_OBJECTS_WORK
static struct debug_obj_descr work_debug_descr;
@@ -604,7 +589,9 @@ static bool keep_working(struct global_cwq *gcwq)
{
atomic_t *nr_running = get_gcwq_nr_running(gcwq->cpu);
- return !list_empty(&gcwq->worklist) && atomic_read(nr_running) <= 1;
+ return !list_empty(&gcwq->worklist) &&
+ (atomic_read(nr_running) <= 1 ||
+ gcwq->flags & GCWQ_HIGHPRI_PENDING);
}
/* Do we need a new worker? Called from manager. */
@@ -997,6 +984,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
/* gcwq determined, get cwq and queue */
cwq = get_cwq(gcwq->cpu, wq);
+ trace_workqueue_queue_work(cpu, cwq, work);
BUG_ON(!list_empty(&work->entry));
@@ -1004,6 +992,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq,
work_flags = work_color_to_flags(cwq->work_color);
if (likely(cwq->nr_active < cwq->max_active)) {
+ trace_workqueue_activate_work(work);
cwq->nr_active++;
worklist = gcwq_determine_ins_pos(gcwq, cwq);
} else {
@@ -1679,6 +1668,7 @@ static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq)
struct work_struct, entry);
struct list_head *pos = gcwq_determine_ins_pos(cwq->gcwq, cwq);
+ trace_workqueue_activate_work(work);
move_linked_works(work, pos, NULL);
__clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work));
cwq->nr_active++;
@@ -2326,27 +2316,17 @@ out_unlock:
}
EXPORT_SYMBOL_GPL(flush_workqueue);
-/**
- * flush_work - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns false if @work has already terminated.
- *
- * It is expected that, prior to calling flush_work(), the caller has
- * arranged for the work to not be requeued, otherwise it doesn't make
- * sense to use this function.
- */
-int flush_work(struct work_struct *work)
+static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+ bool wait_executing)
{
struct worker *worker = NULL;
struct global_cwq *gcwq;
struct cpu_workqueue_struct *cwq;
- struct wq_barrier barr;
might_sleep();
gcwq = get_work_gcwq(work);
if (!gcwq)
- return 0;
+ return false;
spin_lock_irq(&gcwq->lock);
if (!list_empty(&work->entry)) {
@@ -2359,28 +2339,127 @@ int flush_work(struct work_struct *work)
cwq = get_work_cwq(work);
if (unlikely(!cwq || gcwq != cwq->gcwq))
goto already_gone;
- } else {
+ } else if (wait_executing) {
worker = find_worker_executing_work(gcwq, work);
if (!worker)
goto already_gone;
cwq = worker->current_cwq;
- }
+ } else
+ goto already_gone;
- insert_wq_barrier(cwq, &barr, work, worker);
+ insert_wq_barrier(cwq, barr, work, worker);
spin_unlock_irq(&gcwq->lock);
lock_map_acquire(&cwq->wq->lockdep_map);
lock_map_release(&cwq->wq->lockdep_map);
-
- wait_for_completion(&barr.done);
- destroy_work_on_stack(&barr.work);
- return 1;
+ return true;
already_gone:
spin_unlock_irq(&gcwq->lock);
- return 0;
+ return false;
+}
+
+/**
+ * flush_work - wait for a work to finish executing the last queueing instance
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution. This function considers
+ * only the last queueing instance of @work. If @work has been
+ * enqueued across different CPUs on a non-reentrant workqueue or on
+ * multiple workqueues, @work might still be executing on return on
+ * some of the CPUs from earlier queueing.
+ *
+ * If @work was queued only on a non-reentrant, ordered or unbound
+ * workqueue, @work is guaranteed to be idle on return if it hasn't
+ * been requeued since flush started.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work(struct work_struct *work)
+{
+ struct wq_barrier barr;
+
+ if (start_flush_work(work, &barr, true)) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ return true;
+ } else
+ return false;
}
EXPORT_SYMBOL_GPL(flush_work);
+static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
+{
+ struct wq_barrier barr;
+ struct worker *worker;
+
+ spin_lock_irq(&gcwq->lock);
+
+ worker = find_worker_executing_work(gcwq, work);
+ if (unlikely(worker))
+ insert_wq_barrier(worker->current_cwq, &barr, work, worker);
+
+ spin_unlock_irq(&gcwq->lock);
+
+ if (unlikely(worker)) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ return true;
+ } else
+ return false;
+}
+
+static bool wait_on_work(struct work_struct *work)
+{
+ bool ret = false;
+ int cpu;
+
+ might_sleep();
+
+ lock_map_acquire(&work->lockdep_map);
+ lock_map_release(&work->lockdep_map);
+
+ for_each_gcwq_cpu(cpu)
+ ret |= wait_on_cpu_work(get_gcwq(cpu), work);
+ return ret;
+}
+
+/**
+ * flush_work_sync - wait until a work has finished execution
+ * @work: the work to flush
+ *
+ * Wait until @work has finished execution. On return, it's
+ * guaranteed that all queueing instances of @work which happened
+ * before this function is called are finished. In other words, if
+ * @work hasn't been requeued since this function was called, @work is
+ * guaranteed to be idle on return.
+ *
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_work_sync(struct work_struct *work)
+{
+ struct wq_barrier barr;
+ bool pending, waited;
+
+ /* we'll wait for executions separately, queue barr only if pending */
+ pending = start_flush_work(work, &barr, false);
+
+ /* wait for executions to finish */
+ waited = wait_on_work(work);
+
+ /* wait for the pending one */
+ if (pending) {
+ wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
+
+ return pending || waited;
+}
+EXPORT_SYMBOL_GPL(flush_work_sync);
+
/*
* Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit,
* so this work can't be re-armed in any way.
@@ -2423,39 +2502,7 @@ static int try_to_grab_pending(struct work_struct *work)
return ret;
}
-static void wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work)
-{
- struct wq_barrier barr;
- struct worker *worker;
-
- spin_lock_irq(&gcwq->lock);
-
- worker = find_worker_executing_work(gcwq, work);
- if (unlikely(worker))
- insert_wq_barrier(worker->current_cwq, &barr, work, worker);
-
- spin_unlock_irq(&gcwq->lock);
-
- if (unlikely(worker)) {
- wait_for_completion(&barr.done);
- destroy_work_on_stack(&barr.work);
- }
-}
-
-static void wait_on_work(struct work_struct *work)
-{
- int cpu;
-
- might_sleep();
-
- lock_map_acquire(&work->lockdep_map);
- lock_map_release(&work->lockdep_map);
-
- for_each_gcwq_cpu(cpu)
- wait_on_cpu_work(get_gcwq(cpu), work);
-}
-
-static int __cancel_work_timer(struct work_struct *work,
+static bool __cancel_work_timer(struct work_struct *work,
struct timer_list* timer)
{
int ret;
@@ -2472,42 +2519,81 @@ static int __cancel_work_timer(struct work_struct *work,
}
/**
- * cancel_work_sync - block until a work_struct's callback has terminated
- * @work: the work which is to be flushed
- *
- * Returns true if @work was pending.
+ * cancel_work_sync - cancel a work and wait for it to finish
+ * @work: the work to cancel
*
- * cancel_work_sync() will cancel the work if it is queued. If the work's
- * callback appears to be running, cancel_work_sync() will block until it
- * has completed.
+ * Cancel @work and wait for its execution to finish. This function
+ * can be used even if the work re-queues itself or migrates to
+ * another workqueue. On return from this function, @work is
+ * guaranteed to be not pending or executing on any CPU.
*
- * It is possible to use this function if the work re-queues itself. It can
- * cancel the work even if it migrates to another workqueue, however in that
- * case it only guarantees that work->func() has completed on the last queued
- * workqueue.
+ * cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's. Use cancel_delayed_work_sync() instead.
*
- * cancel_work_sync(&delayed_work->work) should be used only if ->timer is not
- * pending, otherwise it goes into a busy-wait loop until the timer expires.
- *
- * The caller must ensure that workqueue_struct on which this work was last
+ * The caller must ensure that the workqueue on which @work was last
* queued can't be destroyed before this function returns.
+ *
+ * RETURNS:
+ * %true if @work was pending, %false otherwise.
*/
-int cancel_work_sync(struct work_struct *work)
+bool cancel_work_sync(struct work_struct *work)
{
return __cancel_work_timer(work, NULL);
}
EXPORT_SYMBOL_GPL(cancel_work_sync);
/**
- * cancel_delayed_work_sync - reliably kill off a delayed work.
- * @dwork: the delayed work struct
+ * flush_delayed_work - wait for a dwork to finish executing the last queueing
+ * @dwork: the delayed work to flush
+ *
+ * Delayed timer is cancelled and the pending work is queued for
+ * immediate execution. Like flush_work(), this function only
+ * considers the last queueing instance of @dwork.
+ *
+ * RETURNS:
+ * %true if flush_work() waited for the work to finish execution,
+ * %false if it was already idle.
+ */
+bool flush_delayed_work(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer))
+ __queue_work(raw_smp_processor_id(),
+ get_work_cwq(&dwork->work)->wq, &dwork->work);
+ return flush_work(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work);
+
+/**
+ * flush_delayed_work_sync - wait for a dwork to finish
+ * @dwork: the delayed work to flush
*
- * Returns true if @dwork was pending.
+ * Delayed timer is cancelled and the pending work is queued for
+ * execution immediately. Other than timer handling, its behavior
+ * is identical to flush_work_sync().
*
- * It is possible to use this function if @dwork rearms itself via queue_work()
- * or queue_delayed_work(). See also the comment for cancel_work_sync().
+ * RETURNS:
+ * %true if flush_work_sync() waited for the work to finish execution,
+ * %false if it was already idle.
*/
-int cancel_delayed_work_sync(struct delayed_work *dwork)
+bool flush_delayed_work_sync(struct delayed_work *dwork)
+{
+ if (del_timer_sync(&dwork->timer))
+ __queue_work(raw_smp_processor_id(),
+ get_work_cwq(&dwork->work)->wq, &dwork->work);
+ return flush_work_sync(&dwork->work);
+}
+EXPORT_SYMBOL(flush_delayed_work_sync);
+
+/**
+ * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish
+ * @dwork: the delayed work cancel
+ *
+ * This is cancel_work_sync() for delayed works.
+ *
+ * RETURNS:
+ * %true if @dwork was pending, %false otherwise.
+ */
+bool cancel_delayed_work_sync(struct delayed_work *dwork)
{
return __cancel_work_timer(&dwork->work, &dwork->timer);
}
@@ -2559,23 +2645,6 @@ int schedule_delayed_work(struct delayed_work *dwork,
EXPORT_SYMBOL(schedule_delayed_work);
/**
- * flush_delayed_work - block until a dwork_struct's callback has terminated
- * @dwork: the delayed work which is to be flushed
- *
- * Any timeout is cancelled, and any pending work is run immediately.
- */
-void flush_delayed_work(struct delayed_work *dwork)
-{
- if (del_timer_sync(&dwork->timer)) {
- __queue_work(get_cpu(), get_work_cwq(&dwork->work)->wq,
- &dwork->work);
- put_cpu();
- }
- flush_work(&dwork->work);
-}
-EXPORT_SYMBOL(flush_delayed_work);
-
-/**
* schedule_delayed_work_on - queue work in global workqueue on CPU after delay
* @cpu: cpu to use
* @dwork: job to be done
@@ -2592,13 +2661,15 @@ int schedule_delayed_work_on(int cpu,
EXPORT_SYMBOL(schedule_delayed_work_on);
/**
- * schedule_on_each_cpu - call a function on each online CPU from keventd
+ * schedule_on_each_cpu - execute a function synchronously on each online CPU
* @func: the function to call
*
- * Returns zero on success.
- * Returns -ve errno on failure.
- *
+ * schedule_on_each_cpu() executes @func on each online CPU using the
+ * system workqueue and blocks until all CPUs have completed.
* schedule_on_each_cpu() is very slow.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
*/
int schedule_on_each_cpu(work_func_t func)
{
@@ -2720,7 +2791,9 @@ static int alloc_cwqs(struct workqueue_struct *wq)
}
}
- /* just in case, make sure it's actually aligned */
+ /* just in case, make sure it's actually aligned
+ * - this is affected by PERCPU() alignment in vmlinux.lds.S
+ */
BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align));
return wq->cpu_wq.v ? 0 : -ENOMEM;
}
@@ -2764,6 +2837,13 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
unsigned int cpu;
/*
+ * Workqueues which may be used during memory reclaim should
+ * have a rescuer to guarantee forward progress.
+ */
+ if (flags & WQ_MEM_RECLAIM)
+ flags |= WQ_RESCUER;
+
+ /*
* Unbound workqueues aren't concurrency managed and should be
* dispatched to workers immediately.
*/
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-25 18:51:25 +0000