summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile2
-rw-r--r--kernel/auditsc.c3
-rw-r--r--kernel/cgroup.c10
-rw-r--r--kernel/configs/xen.config48
-rw-r--r--kernel/events/core.c10
-rw-r--r--kernel/events/internal.h10
-rw-r--r--kernel/events/ring_buffer.c27
-rw-r--r--kernel/gcov/base.c6
-rw-r--r--kernel/gcov/gcc_4_7.c4
-rw-r--r--kernel/jump_label.c10
-rw-r--r--kernel/kexec.c11
-rw-r--r--kernel/module.c310
-rw-r--r--kernel/panic.c5
-rw-r--r--kernel/params.c116
-rw-r--r--kernel/power/Kconfig2
-rw-r--r--kernel/power/hibernate.c4
-rw-r--r--kernel/printk/printk.c8
-rw-r--r--kernel/relay.c5
-rw-r--r--kernel/sched/core.c19
-rw-r--r--kernel/sched/debug.c40
-rw-r--r--kernel/sched/fair.c22
-rw-r--r--kernel/sched/sched.h13
-rw-r--r--kernel/sched/stats.h4
-rw-r--r--kernel/sysctl.c8
-rw-r--r--kernel/time/Makefile2
-rw-r--r--kernel/time/timekeeping.c29
-rw-r--r--kernel/time/timer.c3
-rw-r--r--kernel/workqueue.c7
28 files changed, 524 insertions, 214 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 60c302cfb4d3..43c4c920f30a 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -137,7 +137,7 @@ endif
ifneq ($(wildcard $(obj)/.x509.list),)
ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES))
-$(info X.509 certificate list changed)
+$(warning X.509 certificate list changed to "$(X509_CERTIFICATES)" from "$(shell cat $(obj)/.x509.list)")
$(shell rm $(obj)/.x509.list)
endif
endif
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 09c65640cad6..e85bdfd15fed 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1021,8 +1021,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
* for strings that are too long, we should not have created
* any.
*/
- if (unlikely((len == 0) || len > MAX_ARG_STRLEN - 1)) {
- WARN_ON(1);
+ if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
send_sig(SIGKILL, current, 0);
return -1;
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9ef9fc8a774b..f89d9292eee6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1939,8 +1939,6 @@ static struct file_system_type cgroup_fs_type = {
.kill_sb = cgroup_kill_sb,
};
-static struct kobject *cgroup_kobj;
-
/**
* task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
* @task: target task
@@ -5070,13 +5068,13 @@ int __init cgroup_init(void)
ss->bind(init_css_set.subsys[ssid]);
}
- cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
- if (!cgroup_kobj)
- return -ENOMEM;
+ err = sysfs_create_mount_point(fs_kobj, "cgroup");
+ if (err)
+ return err;
err = register_filesystem(&cgroup_fs_type);
if (err < 0) {
- kobject_put(cgroup_kobj);
+ sysfs_remove_mount_point(fs_kobj, "cgroup");
return err;
}
diff --git a/kernel/configs/xen.config b/kernel/configs/xen.config
new file mode 100644
index 000000000000..ff756221f112
--- /dev/null
+++ b/kernel/configs/xen.config
@@ -0,0 +1,48 @@
+# global stuff - these enable us to allow some
+# of the not so generic stuff below for xen
+CONFIG_PARAVIRT=y
+CONFIG_NET=y
+CONFIG_NET_CORE=y
+CONFIG_NETDEVICES=y
+CONFIG_BLOCK=y
+CONFIG_WATCHDOG=y
+CONFIG_TARGET_CORE=y
+CONFIG_SCSI=y
+CONFIG_FB=y
+CONFIG_INPUT_MISC=y
+CONFIG_MEMORY_HOTPLUG=y
+CONFIG_TTY=y
+# Technically not required but otherwise produces
+# pretty useless systems starting from allnoconfig
+# You want TCP/IP and ELF binaries right?
+CONFIG_INET=y
+CONFIG_BINFMT_ELF=y
+# generic config
+CONFIG_XEN=y
+CONFIG_XEN_DOM0=y
+# backend drivers
+CONFIG_XEN_BACKEND=y
+CONFIG_XEN_BLKDEV_BACKEND=m
+CONFIG_XEN_NETDEV_BACKEND=m
+CONFIG_HVC_XEN=y
+CONFIG_XEN_WDT=m
+CONFIG_XEN_SCSI_BACKEND=m
+# frontend drivers
+CONFIG_XEN_FBDEV_FRONTEND=m
+CONFIG_HVC_XEN_FRONTEND=y
+CONFIG_INPUT_XEN_KBDDEV_FRONTEND=m
+CONFIG_XEN_SCSI_FRONTEND=m
+# others
+CONFIG_XEN_BALLOON=y
+CONFIG_XEN_SCRUB_PAGES=y
+CONFIG_XEN_DEV_EVTCHN=m
+CONFIG_XEN_BLKDEV_FRONTEND=m
+CONFIG_XEN_NETDEV_FRONTEND=m
+CONFIG_XENFS=m
+CONFIG_XEN_COMPAT_XENFS=y
+CONFIG_XEN_SYS_HYPERVISOR=y
+CONFIG_XEN_XENBUS_FRONTEND=y
+CONFIG_XEN_GNTDEV=m
+CONFIG_XEN_GRANT_DEV_ALLOC=m
+CONFIG_SWIOTLB_XEN=y
+CONFIG_XEN_PRIVCMD=m
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d1f37ddd1960..d3dae3419b99 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4358,14 +4358,6 @@ static void ring_buffer_wakeup(struct perf_event *event)
rcu_read_unlock();
}
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
- struct ring_buffer *rb;
-
- rb = container_of(rcu_head, struct ring_buffer, rcu_head);
- rb_free(rb);
-}
-
struct ring_buffer *ring_buffer_get(struct perf_event *event)
{
struct ring_buffer *rb;
@@ -5794,7 +5786,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
* need to add enough zero bytes after the string to handle
* the 64bit alignment we do later.
*/
- name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64));
+ name = file_path(file, buf, PATH_MAX - sizeof(u64));
if (IS_ERR(name)) {
name = "//toolong";
goto cpy_name;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2deb24c7a40d..2bbad9c1274c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
struct ring_buffer {
atomic_t refcount;
struct rcu_head rcu_head;
+ struct irq_work irq_work;
#ifdef CONFIG_PERF_USE_VMALLOC
struct work_struct work;
int page_order; /* allocation order */
@@ -55,6 +56,15 @@ struct ring_buffer {
};
extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+ struct ring_buffer *rb;
+
+ rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+ rb_free(rb);
+}
+
extern struct ring_buffer *
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 96472824a752..b2be01b1aa9d 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -221,6 +221,8 @@ void perf_output_end(struct perf_output_handle *handle)
rcu_read_unlock();
}
+static void rb_irq_work(struct irq_work *work);
+
static void
ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
{
@@ -241,6 +243,16 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
INIT_LIST_HEAD(&rb->event_list);
spin_lock_init(&rb->event_lock);
+ init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+ if (!atomic_dec_and_test(&rb->refcount))
+ return;
+
+ rb->rcu_head.next = (void *)rb;
+ irq_work_queue(&rb->irq_work);
}
/*
@@ -319,7 +331,7 @@ err_put:
rb_free_aux(rb);
err:
- ring_buffer_put(rb);
+ ring_buffer_put_async(rb);
handle->event = NULL;
return NULL;
@@ -370,7 +382,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
local_set(&rb->aux_nest, 0);
rb_free_aux(rb);
- ring_buffer_put(rb);
+ ring_buffer_put_async(rb);
}
/*
@@ -557,7 +569,18 @@ static void __rb_free_aux(struct ring_buffer *rb)
void rb_free_aux(struct ring_buffer *rb)
{
if (atomic_dec_and_test(&rb->aux_refcount))
+ irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+ struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+ if (!atomic_read(&rb->aux_refcount))
__rb_free_aux(rb);
+
+ if (rb->rcu_head.next == (void *)rb)
+ call_rcu(&rb->rcu_head, rb_free_rcu);
}
#ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index a744098e4eb7..7080ae1eb6c1 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -92,6 +92,12 @@ void __gcov_merge_time_profile(gcov_type *counters, unsigned int n_counters)
}
EXPORT_SYMBOL(__gcov_merge_time_profile);
+void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_icall_topn);
+
/**
* gcov_enable_events - enable event reporting through gcov_event()
*
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 826ba9fb5e32..e25e92fb44fa 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,9 @@
#include <linux/vmalloc.h>
#include "gcov.h"
-#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9
+#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1
+#define GCOV_COUNTERS 10
+#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
#define GCOV_COUNTERS 9
#else
#define GCOV_COUNTERS 8
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 9019f15deab2..52ebaca1b9fc 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -302,7 +302,7 @@ static int jump_label_add_module(struct module *mod)
continue;
key = iterk;
- if (__module_address(iter->key) == mod) {
+ if (within_module(iter->key, mod)) {
/*
* Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
*/
@@ -339,7 +339,7 @@ static void jump_label_del_module(struct module *mod)
key = (struct static_key *)(unsigned long)iter->key;
- if (__module_address(iter->key) == mod)
+ if (within_module(iter->key, mod))
continue;
prev = &key->next;
@@ -443,14 +443,16 @@ static void jump_label_update(struct static_key *key, int enable)
{
struct jump_entry *stop = __stop___jump_table;
struct jump_entry *entry = jump_label_get_entries(key);
-
#ifdef CONFIG_MODULES
- struct module *mod = __module_address((unsigned long)key);
+ struct module *mod;
__jump_label_mod_update(key, enable);
+ preempt_disable();
+ mod = __module_address((unsigned long)key);
if (mod)
stop = mod->jump_entries + mod->num_jump_entries;
+ preempt_enable();
#endif
/* if there are no users, entry can be NULL */
if (entry)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 7a36fdcca5bf..a785c1015e25 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -84,6 +84,17 @@ struct resource crashk_low_res = {
int kexec_should_crash(struct task_struct *p)
{
+ /*
+ * If crash_kexec_post_notifiers is enabled, don't run
+ * crash_kexec() here yet, which must be run after panic
+ * notifiers in panic().
+ */
+ if (crash_kexec_post_notifiers)
+ return 0;
+ /*
+ * There are 4 panic() calls in do_exit() path, each of which
+ * corresponds to each of these 4 conditions.
+ */
if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
return 1;
return 0;
diff --git a/kernel/module.c b/kernel/module.c
index f80a97f7da1f..4d2b82e610e2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -101,48 +101,201 @@
DEFINE_MUTEX(module_mutex);
EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
-#ifdef CONFIG_KGDB_KDB
-struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
-#endif /* CONFIG_KGDB_KDB */
-#ifdef CONFIG_MODULE_SIG
-#ifdef CONFIG_MODULE_SIG_FORCE
-static bool sig_enforce = true;
-#else
-static bool sig_enforce = false;
+#ifdef CONFIG_MODULES_TREE_LOOKUP
+
+/*
+ * Use a latched RB-tree for __module_address(); this allows us to use
+ * RCU-sched lookups of the address from any context.
+ *
+ * Because modules have two address ranges: init and core, we need two
+ * latch_tree_nodes entries. Therefore we need the back-pointer from
+ * mod_tree_node.
+ *
+ * Because init ranges are short lived we mark them unlikely and have placed
+ * them outside the critical cacheline in struct module.
+ *
+ * This is conditional on PERF_EVENTS || TRACING because those can really hit
+ * __module_address() hard by doing a lot of stack unwinding; potentially from
+ * NMI context.
+ */
-static int param_set_bool_enable_only(const char *val,
- const struct kernel_param *kp)
+static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n)
{
- int err;
- bool test;
- struct kernel_param dummy_kp = *kp;
+ struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node);
+ struct module *mod = mtn->mod;
- dummy_kp.arg = &test;
+ if (unlikely(mtn == &mod->mtn_init))
+ return (unsigned long)mod->module_init;
- err = param_set_bool(val, &dummy_kp);
- if (err)
- return err;
+ return (unsigned long)mod->module_core;
+}
+
+static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n)
+{
+ struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node);
+ struct module *mod = mtn->mod;
- /* Don't let them unset it once it's set! */
- if (!test && sig_enforce)
- return -EROFS;
+ if (unlikely(mtn == &mod->mtn_init))
+ return (unsigned long)mod->init_size;
+
+ return (unsigned long)mod->core_size;
+}
+
+static __always_inline bool
+mod_tree_less(struct latch_tree_node *a, struct latch_tree_node *b)
+{
+ return __mod_tree_val(a) < __mod_tree_val(b);
+}
+
+static __always_inline int
+mod_tree_comp(void *key, struct latch_tree_node *n)
+{
+ unsigned long val = (unsigned long)key;
+ unsigned long start, end;
+
+ start = __mod_tree_val(n);
+ if (val < start)
+ return -1;
+
+ end = start + __mod_tree_size(n);
+ if (val >= end)
+ return 1;
- if (test)
- sig_enforce = true;
return 0;
}
-static const struct kernel_param_ops param_ops_bool_enable_only = {
- .flags = KERNEL_PARAM_OPS_FL_NOARG,
- .set = param_set_bool_enable_only,
- .get = param_get_bool,
+static const struct latch_tree_ops mod_tree_ops = {
+ .less = mod_tree_less,
+ .comp = mod_tree_comp,
};
-#define param_check_bool_enable_only param_check_bool
+static struct mod_tree_root {
+ struct latch_tree_root root;
+ unsigned long addr_min;
+ unsigned long addr_max;
+} mod_tree __cacheline_aligned = {
+ .addr_min = -1UL,
+};
+
+#define module_addr_min mod_tree.addr_min
+#define module_addr_max mod_tree.addr_max
+
+static noinline void __mod_tree_insert(struct mod_tree_node *node)
+{
+ latch_tree_insert(&node->node, &mod_tree.root, &mod_tree_ops);
+}
+
+static void __mod_tree_remove(struct mod_tree_node *node)
+{
+ latch_tree_erase(&node->node, &mod_tree.root, &mod_tree_ops);
+}
+
+/*
+ * These modifications: insert, remove_init and remove; are serialized by the
+ * module_mutex.
+ */
+static void mod_tree_insert(struct module *mod)
+{
+ mod->mtn_core.mod = mod;
+ mod->mtn_init.mod = mod;
+
+ __mod_tree_insert(&mod->mtn_core);
+ if (mod->init_size)
+ __mod_tree_insert(&mod->mtn_init);
+}
+
+static void mod_tree_remove_init(struct module *mod)
+{
+ if (mod->init_size)
+ __mod_tree_remove(&mod->mtn_init);
+}
+
+static void mod_tree_remove(struct module *mod)
+{
+ __mod_tree_remove(&mod->mtn_core);
+ mod_tree_remove_init(mod);
+}
+
+static struct module *mod_find(unsigned long addr)
+{
+ struct latch_tree_node *ltn;
+
+ ltn = latch_tree_find((void *)addr, &mod_tree.root, &mod_tree_ops);
+ if (!ltn)
+ return NULL;
+
+ return container_of(ltn, struct mod_tree_node, node)->mod;
+}
+
+#else /* MODULES_TREE_LOOKUP */
+
+static unsigned long module_addr_min = -1UL, module_addr_max = 0;
+
+static void mod_tree_insert(struct module *mod) { }
+static void mod_tree_remove_init(struct module *mod) { }
+static void mod_tree_remove(struct module *mod) { }
+
+static struct module *mod_find(unsigned long addr)
+{
+ struct module *mod;
+
+ list_for_each_entry_rcu(mod, &modules, list) {
+ if (within_module(addr, mod))
+ return mod;
+ }
+
+ return NULL;
+}
+
+#endif /* MODULES_TREE_LOOKUP */
+
+/*
+ * Bounds of module text, for speeding up __module_address.
+ * Protected by module_mutex.
+ */
+static void __mod_update_bounds(void *base, unsigned int size)
+{
+ unsigned long min = (unsigned long)base;
+ unsigned long max = min + size;
+
+ if (min < module_addr_min)
+ module_addr_min = min;
+ if (max > module_addr_max)
+ module_addr_max = max;
+}
+
+static void mod_update_bounds(struct module *mod)
+{
+ __mod_update_bounds(mod->module_core, mod->core_size);
+ if (mod->init_size)
+ __mod_update_bounds(mod->module_init, mod->init_size);
+}
+
+#ifdef CONFIG_KGDB_KDB
+struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
+#endif /* CONFIG_KGDB_KDB */
+
+static void module_assert_mutex(void)
+{
+ lockdep_assert_held(&module_mutex);
+}
+
+static void module_assert_mutex_or_preempt(void)
+{
+#ifdef CONFIG_LOCKDEP
+ if (unlikely(!debug_locks))
+ return;
+
+ WARN_ON(!rcu_read_lock_sched_held() &&
+ !lockdep_is_held(&module_mutex));
+#endif
+}
+
+static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE);
+#ifndef CONFIG_MODULE_SIG_FORCE
module_param(sig_enforce, bool_enable_only, 0644);
#endif /* !CONFIG_MODULE_SIG_FORCE */
-#endif /* CONFIG_MODULE_SIG */
/* Block module loading/unloading? */
int modules_disabled = 0;
@@ -153,10 +306,6 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq);
static BLOCKING_NOTIFIER_HEAD(module_notify_list);
-/* Bounds of module allocation, for speeding __module_address.
- * Protected by module_mutex. */
-static unsigned long module_addr_min = -1UL, module_addr_max = 0;
-
int register_module_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&module_notify_list, nb);
@@ -318,6 +467,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
#endif
};
+ module_assert_mutex_or_preempt();
+
if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
return true;
@@ -457,6 +608,8 @@ static struct module *find_module_all(const char *name, size_t len,
{
struct module *mod;
+ module_assert_mutex();
+
list_for_each_entry(mod, &modules, list) {
if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
continue;
@@ -1169,11 +1322,17 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
{
const unsigned long *crc;
- /* Since this should be found in kernel (which can't be removed),
- * no locking is necessary. */
+ /*
+ * Since this should be found in kernel (which can't be removed), no
+ * locking is necessary -- use preempt_disable() to placate lockdep.
+ */
+ preempt_disable();
if (!find_symbol(VMLINUX_SYMBOL_STR(module_layout), NULL,
- &crc, true, false))
+ &crc, true, false)) {
+ preempt_enable();
BUG();
+ }
+ preempt_enable();
return check_version(sechdrs, versindex,
VMLINUX_SYMBOL_STR(module_layout), mod, crc,
NULL);
@@ -1661,6 +1820,10 @@ static void mod_sysfs_fini(struct module *mod)
mod_kobject_put(mod);
}
+static void init_param_lock(struct module *mod)
+{
+ mutex_init(&mod->param_lock);
+}
#else /* !CONFIG_SYSFS */
static int mod_sysfs_setup(struct module *mod,
@@ -1683,6 +1846,9 @@ static void del_usage_links(struct module *mod)
{
}
+static void init_param_lock(struct module *mod)
+{
+}
#endif /* CONFIG_SYSFS */
static void mod_sysfs_teardown(struct module *mod)
@@ -1852,10 +2018,11 @@ static void free_module(struct module *mod)
mutex_lock(&module_mutex);
/* Unlink carefully: kallsyms could be walking list. */
list_del_rcu(&mod->list);
+ mod_tree_remove(mod);
/* Remove this module from bug list, this uses list_del_rcu */
module_bug_cleanup(mod);
- /* Wait for RCU synchronizing before releasing mod->list and buglist. */
- synchronize_rcu();
+ /* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */
+ synchronize_sched();
mutex_unlock(&module_mutex);
/* This may be NULL, but that's OK */
@@ -2384,22 +2551,6 @@ void * __weak module_alloc(unsigned long size)
return vmalloc_exec(size);
}
-static void *module_alloc_update_bounds(unsigned long size)
-{
- void *ret = module_alloc(size);
-
- if (ret) {
- mutex_lock(&module_mutex);
- /* Update module bounds. */
- if ((unsigned long)ret < module_addr_min)
- module_addr_min = (unsigned long)ret;
- if ((unsigned long)ret + size > module_addr_max)
- module_addr_max = (unsigned long)ret + size;
- mutex_unlock(&module_mutex);
- }
- return ret;
-}
-
#ifdef CONFIG_DEBUG_KMEMLEAK
static void kmemleak_load_module(const struct module *mod,
const struct load_info *info)
@@ -2805,7 +2956,7 @@ static int move_module(struct module *mod, struct load_info *info)
void *ptr;
/* Do the allocs. */
- ptr = module_alloc_update_bounds(mod->core_size);
+ ptr = module_alloc(mod->core_size);
/*
* The pointer to this block is stored in the module structure
* which is inside the block. Just mark it as not being a
@@ -2819,7 +2970,7 @@ static int move_module(struct module *mod, struct load_info *info)
mod->module_core = ptr;
if (mod->init_size) {
- ptr = module_alloc_update_bounds(mod->init_size);
+ ptr = module_alloc(mod->init_size);
/*
* The pointer to this block is stored in the module structure
* which is inside the block. This block doesn't need to be
@@ -3119,6 +3270,7 @@ static noinline int do_init_module(struct module *mod)
mod->symtab = mod->core_symtab;
mod->strtab = mod->core_strtab;
#endif
+ mod_tree_remove_init(mod);
unset_module_init_ro_nx(mod);
module_arch_freeing_init(mod);
mod->module_init = NULL;
@@ -3127,11 +3279,11 @@ static noinline int do_init_module(struct module *mod)
mod->init_text_size = 0;
/*
* We want to free module_init, but be aware that kallsyms may be
- * walking this with preempt disabled. In all the failure paths,
- * we call synchronize_rcu/synchronize_sched, but we don't want
- * to slow down the success path, so use actual RCU here.
+ * walking this with preempt disabled. In all the failure paths, we
+ * call synchronize_sched(), but we don't want to slow down the success
+ * path, so use actual RCU here.
*/
- call_rcu(&freeinit->rcu, do_free_init);
+ call_rcu_sched(&freeinit->rcu, do_free_init);
mutex_unlock(&module_mutex);
wake_up_all(&module_wq);
@@ -3188,7 +3340,9 @@ again:
err = -EEXIST;
goto out;
}
+ mod_update_bounds(mod);
list_add_rcu(&mod->list, &modules);
+ mod_tree_insert(mod);
err = 0;
out:
@@ -3304,6 +3458,8 @@ static int load_module(struct load_info *info, const char __user *uargs,
if (err)
goto unlink_mod;
+ init_param_lock(mod);
+
/* Now we've got everything in the final locations, we can
* find optional sections. */
err = find_module_sections(mod, info);
@@ -3401,9 +3557,10 @@ static int load_module(struct load_info *info, const char __user *uargs,
mutex_lock(&module_mutex);
/* Unlink carefully: kallsyms could be walking list. */
list_del_rcu(&mod->list);
+ mod_tree_remove(mod);
wake_up_all(&module_wq);
- /* Wait for RCU synchronizing before releasing mod->list. */
- synchronize_rcu();
+ /* Wait for RCU-sched synchronizing before releasing mod->list. */
+ synchronize_sched();
mutex_unlock(&module_mutex);
free_module:
/* Free lock-classes; relies on the preceding sync_rcu() */
@@ -3527,19 +3684,15 @@ const char *module_address_lookup(unsigned long addr,
char **modname,
char *namebuf)
{
- struct module *mod;
const char *ret = NULL;
+ struct module *mod;
preempt_disable();
- list_for_each_entry_rcu(mod, &modules, list) {
- if (mod->state == MODULE_STATE_UNFORMED)
- continue;
- if (within_module(addr, mod)) {
- if (modname)
- *modname = mod->name;
- ret = get_ksymbol(mod, addr, size, offset);
- break;
- }
+ mod = __module_address(addr);
+ if (mod) {
+ if (modname)
+ *modname = mod->name;
+ ret = get_ksymbol(mod, addr, size, offset);
}
/* Make a copy in here where it's safe */
if (ret) {
@@ -3547,6 +3700,7 @@ const char *module_address_lookup(unsigned long addr,
ret = namebuf;
}
preempt_enable();
+
return ret;
}
@@ -3670,6 +3824,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
unsigned int i;
int ret;
+ module_assert_mutex();
+
list_for_each_entry(mod, &modules, list) {
if (mod->state == MODULE_STATE_UNFORMED)
continue;
@@ -3844,13 +4000,15 @@ struct module *__module_address(unsigned long addr)
if (addr < module_addr_min || addr > module_addr_max)
return NULL;
- list_for_each_entry_rcu(mod, &modules, list) {
+ module_assert_mutex_or_preempt();
+
+ mod = mod_find(addr);
+ if (mod) {
+ BUG_ON(!within_module(addr, mod));
if (mod->state == MODULE_STATE_UNFORMED)
- continue;
- if (within_module(addr, mod))
- return mod;
+ mod = NULL;
}
- return NULL;
+ return mod;
}
EXPORT_SYMBOL_GPL(__module_address);
diff --git a/kernel/panic.c b/kernel/panic.c
index 8136ad76e5fd..04e91ff7560b 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -32,7 +32,7 @@ static unsigned long tainted_mask;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
-static bool crash_kexec_post_notifiers;
+bool crash_kexec_post_notifiers;
int panic_on_warn __read_mostly;
int panic_timeout = CONFIG_PANIC_TIMEOUT;
@@ -142,7 +142,8 @@ void panic(const char *fmt, ...)
* Note: since some panic_notifiers can make crashed kernel
* more unstable, it can increase risks of the kdump failure too.
*/
- crash_kexec(NULL);
+ if (crash_kexec_post_notifiers)
+ crash_kexec(NULL);
bust_spinlocks(0);
diff --git a/kernel/params.c b/kernel/params.c
index 30288c1e15dd..b6554aa71094 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -25,15 +25,34 @@
#include <linux/slab.h>
#include <linux/ctype.h>
-/* Protects all parameters, and incidentally kmalloced_param list. */
+#ifdef CONFIG_SYSFS
+/* Protects all built-in parameters, modules use their own param_lock */
static DEFINE_MUTEX(param_lock);
+/* Use the module's mutex, or if built-in use the built-in mutex */
+#ifdef CONFIG_MODULES
+#define KPARAM_MUTEX(mod) ((mod) ? &(mod)->param_lock : &param_lock)
+#else
+#define KPARAM_MUTEX(mod) (&param_lock)
+#endif
+
+static inline void check_kparam_locked(struct module *mod)
+{
+ BUG_ON(!mutex_is_locked(KPARAM_MUTEX(mod)));
+}
+#else
+static inline void check_kparam_locked(struct module *mod)
+{
+}
+#endif /* !CONFIG_SYSFS */
+
/* This just allows us to keep track of which parameters are kmalloced. */
struct kmalloced_param {
struct list_head list;
char val[];
};
static LIST_HEAD(kmalloced_params);
+static DEFINE_SPINLOCK(kmalloced_params_lock);
static void *kmalloc_parameter(unsigned int size)
{
@@ -43,7 +62,10 @@ static void *kmalloc_parameter(unsigned int size)
if (!p)
return NULL;
+ spin_lock(&kmalloced_params_lock);
list_add(&p->list, &kmalloced_params);
+ spin_unlock(&kmalloced_params_lock);
+
return p->val;
}
@@ -52,6 +74,7 @@ static void maybe_kfree_parameter(void *param)
{
struct kmalloced_param *p;
+ spin_lock(&kmalloced_params_lock);
list_for_each_entry(p, &kmalloced_params, list) {
if (p->val == param) {
list_del(&p->list);
@@ -59,6 +82,7 @@ static void maybe_kfree_parameter(void *param)
break;
}
}
+ spin_unlock(&kmalloced_params_lock);
}
static char dash2underscore(char c)
@@ -119,10 +143,10 @@ static int parse_one(char *param,
return -EINVAL;
pr_debug("handling %s with %p\n", param,
params[i].ops->set);
- mutex_lock(&param_lock);
+ kernel_param_lock(params[i].mod);
param_check_unsafe(&params[i]);
err = params[i].ops->set(val, &params[i]);
- mutex_unlock(&param_lock);
+ kernel_param_unlock(params[i].mod);
return err;
}
}
@@ -254,7 +278,7 @@ char *parse_args(const char *doing,
return scnprintf(buffer, PAGE_SIZE, format, \
*((type *)kp->arg)); \
} \
- struct kernel_param_ops param_ops_##name = { \
+ const struct kernel_param_ops param_ops_##name = { \
.set = param_set_##name, \
.get = param_get_##name, \
}; \
@@ -306,7 +330,7 @@ static void param_free_charp(void *arg)
maybe_kfree_parameter(*((char **)arg));
}
-struct kernel_param_ops param_ops_charp = {
+const struct kernel_param_ops param_ops_charp = {
.set = param_set_charp,
.get = param_get_charp,
.free = param_free_charp,
@@ -331,13 +355,44 @@ int param_get_bool(char *buffer, const struct kernel_param *kp)
}
EXPORT_SYMBOL(param_get_bool);
-struct kernel_param_ops param_ops_bool = {
+const struct kernel_param_ops param_ops_bool = {
.flags = KERNEL_PARAM_OPS_FL_NOARG,
.set = param_set_bool,
.get = param_get_bool,
};
EXPORT_SYMBOL(param_ops_bool);
+int param_set_bool_enable_only(const char *val, const struct kernel_param *kp)
+{
+ int err = 0;
+ bool new_value;
+ bool orig_value = *(bool *)kp->arg;
+ struct kernel_param dummy_kp = *kp;
+
+ dummy_kp.arg = &new_value;
+
+ err = param_set_bool(val, &dummy_kp);
+ if (err)
+ return err;
+
+ /* Don't let them unset it once it's set! */
+ if (!new_value && orig_value)
+ return -EROFS;
+
+ if (new_value)
+ err = param_set_bool(val, kp);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(param_set_bool_enable_only);
+
+const struct kernel_param_ops param_ops_bool_enable_only = {
+ .flags = KERNEL_PARAM_OPS_FL_NOARG,
+ .set = param_set_bool_enable_only,
+ .get = param_get_bool,
+};
+EXPORT_SYMBOL_GPL(param_ops_bool_enable_only);
+
/* This one must be bool. */
int param_set_invbool(const char *val, const struct kernel_param *kp)
{
@@ -359,7 +414,7 @@ int param_get_invbool(char *buffer, const struct kernel_param *kp)
}
EXPORT_SYMBOL(param_get_invbool);
-struct kernel_param_ops param_ops_invbool = {
+const struct kernel_param_ops param_ops_invbool = {
.set = param_set_invbool,
.get = param_get_invbool,
};
@@ -367,12 +422,11 @@ EXPORT_SYMBOL(param_ops_invbool);
int param_set_bint(const char *val, const struct kernel_param *kp)
{
- struct kernel_param boolkp;
+ /* Match bool exactly, by re-using it. */
+ struct kernel_param boolkp = *kp;
bool v;
int ret;
- /* Match bool exactly, by re-using it. */
- boolkp = *kp;
boolkp.arg = &v;
ret = param_set_bool(val, &boolkp);
@@ -382,7 +436,7 @@ int param_set_bint(const char *val, const struct kernel_param *kp)
}
EXPORT_SYMBOL(param_set_bint);
-struct kernel_param_ops param_ops_bint = {
+const struct kernel_param_ops param_ops_bint = {
.flags = KERNEL_PARAM_OPS_FL_NOARG,
.set = param_set_bint,
.get = param_get_int,
@@ -390,7 +444,8 @@ struct kernel_param_ops param_ops_bint = {
EXPORT_SYMBOL(param_ops_bint);
/* We break the rule and mangle the string. */
-static int param_array(const char *name,
+static int param_array(struct module *mod,
+ const char *name,
const char *val,
unsigned int min, unsigned int max,
void *elem, int elemsize,
@@ -421,7 +476,7 @@ static int param_array(const char *name,
/* nul-terminate and parse */
save = val[len];
((char *)val)[len] = '\0';
- BUG_ON(!mutex_is_locked(&param_lock));
+ check_kparam_locked(mod);
ret = set(val, &kp);
if (ret != 0)
@@ -443,7 +498,7 @@ static int param_array_set(const char *val, const struct kernel_param *kp)
const struct kparam_array *arr = kp->arr;
unsigned int temp_num;
- return param_array(kp->name, val, 1, arr->max, arr->elem,
+ return param_array(kp->mod, kp->name, val, 1, arr->max, arr->elem,
arr->elemsize, arr->ops->set, kp->level,
arr->num ?: &temp_num);
}
@@ -452,14 +507,13 @@ static int param_array_get(char *buffer, const struct kernel_param *kp)
{
int i, off, ret;
const struct kparam_array *arr = kp->arr;
- struct kernel_param p;
+ struct kernel_param p = *kp;
- p = *kp;
for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) {
if (i)
buffer[off++] = ',';
p.arg = arr->elem + arr->elemsize * i;
- BUG_ON(!mutex_is_locked(&param_lock));
+ check_kparam_locked(p.mod);
ret = arr->ops->get(buffer + off, &p);
if (ret < 0)
return ret;
@@ -479,7 +533,7 @@ static void param_array_free(void *arg)
arr->ops->free(arr->elem + arr->elemsize * i);
}
-struct kernel_param_ops param_array_ops = {
+const struct kernel_param_ops param_array_ops = {
.set = param_array_set,
.get = param_array_get,
.free = param_array_free,
@@ -507,7 +561,7 @@ int param_get_string(char *buffer, const struct kernel_param *kp)
}
EXPORT_SYMBOL(param_get_string);
-struct kernel_param_ops param_ops_string = {
+const struct kernel_param_ops param_ops_string = {
.set = param_set_copystring,
.get = param_get_string,
};
@@ -542,9 +596,9 @@ static ssize_t param_attr_show(struct module_attribute *mattr,
if (!attribute->param->ops->get)
return -EPERM;
- mutex_lock(&param_lock);
+ kernel_param_lock(mk->mod);
count = attribute->param->ops->get(buf, attribute->param);
- mutex_unlock(&param_lock);
+ kernel_param_unlock(mk->mod);
if (count > 0) {
strcat(buf, "\n");
++count;
@@ -554,7 +608,7 @@ static ssize_t param_attr_show(struct module_attribute *mattr,
/* sysfs always hands a nul-terminated string in buf. We rely on that. */
static ssize_t param_attr_store(struct module_attribute *mattr,
- struct module_kobject *km,
+ struct module_kobject *mk,
const char *buf, size_t len)
{
int err;
@@ -563,10 +617,10 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
if (!attribute->param->ops->set)
return -EPERM;
- mutex_lock(&param_lock);
+ kernel_param_lock(mk->mod);
param_check_unsafe(attribute->param);
err = attribute->param->ops->set(buf, attribute->param);
- mutex_unlock(&param_lock);
+ kernel_param_unlock(mk->mod);
if (!err)
return len;
return err;
@@ -580,17 +634,18 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
#endif
#ifdef CONFIG_SYSFS
-void __kernel_param_lock(void)
+void kernel_param_lock(struct module *mod)
{
- mutex_lock(&param_lock);
+ mutex_lock(KPARAM_MUTEX(mod));
}
-EXPORT_SYMBOL(__kernel_param_lock);
-void __kernel_param_unlock(void)
+void kernel_param_unlock(struct module *mod)
{
- mutex_unlock(&param_lock);
+ mutex_unlock(KPARAM_MUTEX(mod));
}
-EXPORT_SYMBOL(__kernel_param_unlock);
+
+EXPORT_SYMBOL(kernel_param_lock);
+EXPORT_SYMBOL(kernel_param_unlock);
/*
* add_sysfs_param - add a parameter to sysfs
@@ -856,6 +911,7 @@ static void __init version_sysfs_builtin(void)
mk = locate_module_kobject(vattr->module_name);
if (mk) {
err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
+ WARN_ON_ONCE(err);
kobject_uevent(&mk->kobj, KOBJ_ADD);
kobject_put(&mk->kobj);
}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 7e01f78f0417..9e302315e33d 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -187,7 +187,7 @@ config DPM_WATCHDOG
config DPM_WATCHDOG_TIMEOUT
int "Watchdog timeout in seconds"
range 1 120
- default 12
+ default 60
depends on DPM_WATCHDOG
config PM_TRACE
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 2329daae5255..690f78f210f2 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -552,7 +552,7 @@ int hibernation_platform_enter(void)
error = disable_nonboot_cpus();
if (error)
- goto Platform_finish;
+ goto Enable_cpus;
local_irq_disable();
syscore_suspend();
@@ -568,6 +568,8 @@ int hibernation_platform_enter(void)
Power_up:
syscore_resume();
local_irq_enable();
+
+ Enable_cpus:
enable_nonboot_cpus();
Platform_finish:
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index de553849f3ac..cf8c24203368 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -207,14 +207,14 @@ static int console_may_schedule;
* need to be changed in the future, when the requirements change.
*
* /dev/kmsg exports the structured data in the following line format:
- * "<level>,<sequnum>,<timestamp>,<contflag>;<message text>\n"
+ * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n"
+ *
+ * Users of the export format should ignore possible additional values
+ * separated by ',', and find the message after the ';' character.
*
* The optional key/value pairs are attached as continuation lines starting
* with a space character and terminated by a newline. All possible
* non-prinatable characters are escaped in the "\xff" notation.
- *
- * Users of the export format should ignore possible additional values
- * separated by ',', and find the message after the ';' character.
*/
enum log_flags {
diff --git a/kernel/relay.c b/kernel/relay.c
index e9dbaeb8fd65..0b4570cfacae 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -81,10 +81,7 @@ static struct page **relay_alloc_page_array(unsigned int n_pages)
*/
static void relay_free_page_array(struct page **array)
{
- if (is_vmalloc_addr(array))
- vfree(array);
- else
- kfree(array);
+ kvfree(array);
}
/**
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b803e1b8ab0c..78b4bad10081 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2164,7 +2164,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
set_task_cpu(p, cpu);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
@@ -2320,13 +2320,27 @@ void wake_up_new_task(struct task_struct *p)
static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
+void preempt_notifier_inc(void)
+{
+ static_key_slow_inc(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_inc);
+
+void preempt_notifier_dec(void)
+{
+ static_key_slow_dec(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_dec);
+
/**
* preempt_notifier_register - tell me when current is being preempted & rescheduled
* @notifier: notifier struct to register
*/
void preempt_notifier_register(struct preempt_notifier *notifier)
{
- static_key_slow_inc(&preempt_notifier_key);
+ if (!static_key_false(&preempt_notifier_key))
+ WARN(1, "registering preempt_notifier while notifiers disabled\n");
+
hlist_add_head(&notifier->link, &current->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);
@@ -2340,7 +2354,6 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register);
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
hlist_del(&notifier->link);
- static_key_slow_dec(&preempt_notifier_key);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 315c68e015d9..4222ec50ab88 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -142,7 +142,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
- SEQ_printf(m, " %d", task_node(p));
+ SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
#endif
#ifdef CONFIG_CGROUP_SCHED
SEQ_printf(m, " %s", task_group_path(task_group(p)));
@@ -517,11 +517,21 @@ __initcall(init_sched_debug_procfs);
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#ifdef CONFIG_NUMA_BALANCING
+void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+ unsigned long tpf, unsigned long gsf, unsigned long gpf)
+{
+ SEQ_printf(m, "numa_faults node=%d ", node);
+ SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
+ SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+}
+#endif
+
+
static void sched_show_numa(struct task_struct *p, struct seq_file *m)
{
#ifdef CONFIG_NUMA_BALANCING
struct mempolicy *pol;
- int node, i;
if (p->mm)
P(mm->numa_scan_seq);
@@ -533,26 +543,12 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
mpol_get(pol);
task_unlock(p);
- SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
-
- for_each_online_node(node) {
- for (i = 0; i < 2; i++) {
- unsigned long nr_faults = -1;
- int cpu_current, home_node;
-
- if (p->numa_faults)
- nr_faults = p->numa_faults[2*node + i];
-
- cpu_current = !i ? (task_node(p) == node) :
- (pol && node_isset(node, pol->v.nodes));
-
- home_node = (p->numa_preferred_nid == node);
-
- SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
- i, node, cpu_current, home_node, nr_faults);
- }
- }
-
+ P(numa_pages_migrated);
+ P(numa_preferred_nid);
+ P(total_numa_faults);
+ SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
+ task_node(p), task_numa_group_id(p));
+ show_numa_stats(p, m);
mpol_put(pol);
#endif
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3d57cc0ca0a6..65c8f3ebdc3c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8473,7 +8473,27 @@ void print_cfs_stats(struct seq_file *m, int cpu)
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}
-#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+void show_numa_stats(struct task_struct *p, struct seq_file *m)
+{
+ int node;
+ unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
+
+ for_each_online_node(node) {
+ if (p->numa_faults) {
+ tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
+ tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+ if (p->numa_group) {
+ gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
+ gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+ print_numa_stats(m, node, tsf, tpf, gsf, gpf);
+ }
+}
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
__init void init_sched_fair_class(void)
{
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 885889190a1f..84d48790bb6d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1689,9 +1689,22 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
+
+#ifdef CONFIG_SCHED_DEBUG
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void print_dl_stats(struct seq_file *m, int cpu);
+extern void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+
+#ifdef CONFIG_NUMA_BALANCING
+extern void
+show_numa_stats(struct task_struct *p, struct seq_file *m);
+extern void
+print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+ unsigned long tpf, unsigned long gsf, unsigned long gpf);
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 077ebbd5e10f..b0fbc7632de5 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -47,7 +47,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
# define schedstat_set(var, val) do { } while (0)
#endif
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
t->sched_info.last_queued = 0;
@@ -156,7 +156,7 @@ sched_info_switch(struct rq *rq,
#define sched_info_depart(rq, t) do { } while (0)
#define sched_info_arrive(rq, next) do { } while (0)
#define sched_info_switch(rq, t, next) do { } while (0)
-#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
+#endif /* CONFIG_SCHED_INFO */
/*
* The following are functions that support scheduler-internal time accounting.
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 812fcc3fd390..19b62b522158 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1538,12 +1538,6 @@ static struct ctl_table vm_table[] = {
{ }
};
-#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
-static struct ctl_table binfmt_misc_table[] = {
- { }
-};
-#endif
-
static struct ctl_table fs_table[] = {
{
.procname = "inode-nr",
@@ -1697,7 +1691,7 @@ static struct ctl_table fs_table[] = {
{
.procname = "binfmt_misc",
.mode = 0555,
- .child = binfmt_misc_table,
+ .child = sysctl_mount_point,
},
#endif
{
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ffc4cc3dcd47..49eca0beed32 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -12,5 +12,3 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o
obj-$(CONFIG_TIMER_STATS) += timer_stats.o
obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o
obj-$(CONFIG_TEST_UDELAY) += test_udelay.o
-
-$(obj)/time.o: $(objtree)/include/config/
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 30b7a409bf1e..bca3667a2de1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -319,32 +319,7 @@ static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
* We want to use this from any context including NMI and tracing /
* instrumenting the timekeeping code itself.
*
- * So we handle this differently than the other timekeeping accessor
- * functions which retry when the sequence count has changed. The
- * update side does:
- *
- * smp_wmb(); <- Ensure that the last base[1] update is visible
- * tkf->seq++;
- * smp_wmb(); <- Ensure that the seqcount update is visible
- * update(tkf->base[0], tkr);
- * smp_wmb(); <- Ensure that the base[0] update is visible
- * tkf->seq++;
- * smp_wmb(); <- Ensure that the seqcount update is visible
- * update(tkf->base[1], tkr);
- *
- * The reader side does:
- *
- * do {
- * seq = tkf->seq;
- * smp_rmb();
- * idx = seq & 0x01;
- * now = now(tkf->base[idx]);
- * smp_rmb();
- * } while (seq != tkf->seq)
- *
- * As long as we update base[0] readers are forced off to
- * base[1]. Once base[0] is updated readers are redirected to base[0]
- * and the base[1] update takes place.
+ * Employ the latch technique; see @raw_write_seqcount_latch.
*
* So if a NMI hits the update of base[0] then it will use base[1]
* which is still consistent. In the worst case this can result is a
@@ -407,7 +382,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
u64 now;
do {
- seq = raw_read_seqcount(&tkf->seq);
+ seq = raw_read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
} while (read_seqcount_retry(&tkf->seq, seq));
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 520499dd85af..5e097fa9faf7 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1566,7 +1566,7 @@ static void migrate_timers(int cpu)
BUG_ON(cpu_online(cpu));
old_base = per_cpu_ptr(&tvec_bases, cpu);
- new_base = this_cpu_ptr(&tvec_bases);
+ new_base = get_cpu_ptr(&tvec_bases);
/*
* The caller is globally serialized and nobody else
* takes two locks at once, deadlock is not possible.
@@ -1590,6 +1590,7 @@ static void migrate_timers(int cpu)
spin_unlock(&old_base->lock);
spin_unlock_irq(&new_base->lock);
+ put_cpu_ptr(&tvec_bases);
}
static int timer_cpu_notify(struct notifier_block *self,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 5243d4b03087..4c4f06176f74 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -285,12 +285,7 @@ static bool wq_disable_numa;
module_param_named(disable_numa, wq_disable_numa, bool, 0444);
/* see the comment above the definition of WQ_POWER_EFFICIENT */
-#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT
-static bool wq_power_efficient = true;
-#else
-static bool wq_power_efficient;
-#endif
-
+static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
module_param_named(power_efficient, wq_power_efficient, bool, 0444);
static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-23 10:54:34 +0100