Permalink
Browse files

Merge tag 'driver-core-3.14-rc1' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/gregkh/driver-core

Pull driver core / sysfs patches from Greg KH:
 "Here's the big driver core and sysfs patch set for 3.14-rc1.

  There's a lot of work here moving sysfs logic out into a "kernfs" to
  allow other subsystems to also have a virtual filesystem with the same
  attributes of sysfs (handle device disconnect, dynamic creation /
  removal as needed / unneeded, etc)

  This is primarily being done for the cgroups filesystem, but the goal
  is to also move debugfs to it when it is ready, solving all of the
  known issues in that filesystem as well.  The code isn't completed
  yet, but all should be stable now (there is a big section that was
  reverted due to problems found when testing)

  There's also some other smaller fixes, and a driver core addition that
  allows for a "collection" of objects, that the DRM people will be
  using soon (it's in this tree to make merges after -rc1 easier)

  All of this has been in linux-next with no reported issues"

* tag 'driver-core-3.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (113 commits)
  kernfs: associate a new kernfs_node with its parent on creation
  kernfs: add struct dentry declaration in kernfs.h
  kernfs: fix get_active failure handling in kernfs_seq_*()
  Revert "kernfs: fix get_active failure handling in kernfs_seq_*()"
  Revert "kernfs: replace kernfs_node->u.completion with kernfs_root->deactivate_waitq"
  Revert "kernfs: remove KERNFS_ACTIVE_REF and add kernfs_lockdep()"
  Revert "kernfs: remove KERNFS_REMOVED"
  Revert "kernfs: restructure removal path to fix possible premature return"
  Revert "kernfs: invoke kernfs_unmap_bin_file() directly from __kernfs_remove()"
  Revert "kernfs: remove kernfs_addrm_cxt"
  Revert "kernfs: make kernfs_get_active() block if the node is deactivated but not removed"
  Revert "kernfs: implement kernfs_{de|re}activate[_self]()"
  Revert "kernfs, sysfs, driver-core: implement kernfs_remove_self() and its wrappers"
  Revert "pci: use device_remove_file_self() instead of device_schedule_callback()"
  Revert "scsi: use device_remove_file_self() instead of device_schedule_callback()"
  Revert "s390: use device_remove_file_self() instead of device_schedule_callback()"
  Revert "sysfs, driver-core: remove unused {sysfs|device}_schedule_callback_owner()"
  Revert "kernfs: remove unnecessary NULL check in __kernfs_remove()"
  kernfs: remove unnecessary NULL check in __kernfs_remove()
  drivers/base: provide an infrastructure for componentised subsystems
  ...
  • Loading branch information...
2 parents 9f67627 + db4aad2 commit d3bad75a6d57416cf7478ca2a1e42f699bc17ec5 @torvalds committed Jan 20, 2014
View
116 Documentation/driver-model/design-patterns.txt
@@ -0,0 +1,116 @@
+
+Device Driver Design Patterns
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This document describes a few common design patterns found in device drivers.
+It is likely that subsystem maintainers will ask driver developers to
+conform to these design patterns.
+
+1. State Container
+2. container_of()
+
+
+1. State Container
+~~~~~~~~~~~~~~~~~~
+
+While the kernel contains a few device drivers that assume that they will
+only be probed() once on a certain system (singletons), it is custom to assume
+that the device the driver binds to will appear in several instances. This
+means that the probe() function and all callbacks need to be reentrant.
+
+The most common way to achieve this is to use the state container design
+pattern. It usually has this form:
+
+struct foo {
+ spinlock_t lock; /* Example member */
+ (...)
+};
+
+static int foo_probe(...)
+{
+ struct foo *foo;
+
+ foo = devm_kzalloc(dev, sizeof(*foo), GFP_KERNEL);
+ if (!foo)
+ return -ENOMEM;
+ spin_lock_init(&foo->lock);
+ (...)
+}
+
+This will create an instance of struct foo in memory every time probe() is
+called. This is our state container for this instance of the device driver.
+Of course it is then necessary to always pass this instance of the
+state around to all functions that need access to the state and its members.
+
+For example, if the driver is registering an interrupt handler, you would
+pass around a pointer to struct foo like this:
+
+static irqreturn_t foo_handler(int irq, void *arg)
+{
+ struct foo *foo = arg;
+ (...)
+}
+
+static int foo_probe(...)
+{
+ struct foo *foo;
+
+ (...)
+ ret = request_irq(irq, foo_handler, 0, "foo", foo);
+}
+
+This way you always get a pointer back to the correct instance of foo in
+your interrupt handler.
+
+
+2. container_of()
+~~~~~~~~~~~~~~~~~
+
+Continuing on the above example we add an offloaded work:
+
+struct foo {
+ spinlock_t lock;
+ struct workqueue_struct *wq;
+ struct work_struct offload;
+ (...)
+};
+
+static void foo_work(struct work_struct *work)
+{
+ struct foo *foo = container_of(work, struct foo, offload);
+
+ (...)
+}
+
+static irqreturn_t foo_handler(int irq, void *arg)
+{
+ struct foo *foo = arg;
+
+ queue_work(foo->wq, &foo->offload);
+ (...)
+}
+
+static int foo_probe(...)
+{
+ struct foo *foo;
+
+ foo->wq = create_singlethread_workqueue("foo-wq");
+ INIT_WORK(&foo->offload, foo_work);
+ (...)
+}
+
+The design pattern is the same for an hrtimer or something similar that will
+return a single argument which is a pointer to a struct member in the
+callback.
+
+container_of() is a macro defined in <linux/kernel.h>
+
+What container_of() does is to obtain a pointer to the containing struct from
+a pointer to a member by a simple subtraction using the offsetof() macro from
+standard C, which allows something similar to object oriented behaviours.
+Notice that the contained member must not be a pointer, but an actual member
+for this to work.
+
+We can see here that we avoid having global pointers to our struct foo *
+instance this way, while still keeping the number of parameters passed to the
+work function to a single pointer.
View
5 Documentation/kobject.txt
@@ -342,7 +342,10 @@ kset use:
When you are finished with the kset, call:
void kset_unregister(struct kset *kset);
-to destroy it.
+to destroy it. This removes the kset from sysfs and decrements its reference
+count. When the reference count goes to zero, the kset will be released.
+Because other references to the kset may still exist, the release may happen
+after kset_unregister() returns.
An example of using a kset can be seen in the
samples/kobject/kset-example.c file in the kernel tree.
View
2 arch/x86/kernel/cpu/microcode/amd.c
@@ -433,7 +433,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
if (c->x86 >= 0x15)
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
- if (request_firmware(&fw, (const char *)fw_name, device)) {
+ if (request_firmware_direct(&fw, (const char *)fw_name, device)) {
pr_debug("failed to load file %s\n", fw_name);
goto out;
}
View
2 arch/x86/kernel/cpu/microcode/intel.c
@@ -278,7 +278,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
sprintf(name, "intel-ucode/%02x-%02x-%02x",
c->x86, c->x86_model, c->x86_mask);
- if (request_firmware(&firmware, name, device)) {
+ if (request_firmware_direct(&firmware, name, device)) {
pr_debug("data file %s load failed\n", name);
return UCODE_NFOUND;
}
View
2 drivers/base/Makefile
@@ -1,6 +1,6 @@
# Makefile for the Linux device tree
-obj-y := core.o bus.o dd.o syscore.o \
+obj-y := component.o core.o bus.o dd.o syscore.o \
driver.o class.o platform.o \
cpu.o firmware.o init.o map.o devres.o \
attribute_container.o transport_class.o \
View
13 drivers/base/bus.c
@@ -146,8 +146,19 @@ void bus_remove_file(struct bus_type *bus, struct bus_attribute *attr)
}
EXPORT_SYMBOL_GPL(bus_remove_file);
+static void bus_release(struct kobject *kobj)
+{
+ struct subsys_private *priv =
+ container_of(kobj, typeof(*priv), subsys.kobj);
+ struct bus_type *bus = priv->bus;
+
+ kfree(priv);
+ bus->p = NULL;
+}
+
static struct kobj_type bus_ktype = {
.sysfs_ops = &bus_sysfs_ops,
+ .release = bus_release,
};
static int bus_uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -953,8 +964,6 @@ void bus_unregister(struct bus_type *bus)
kset_unregister(bus->p->devices_kset);
bus_remove_file(bus, &bus_attr_uevent);
kset_unregister(&bus->p->subsys);
- kfree(bus->p);
- bus->p = NULL;
}
EXPORT_SYMBOL_GPL(bus_unregister);
View
382 drivers/base/component.c
@@ -0,0 +1,382 @@
+/*
+ * Componentized device handling.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This is work in progress. We gather up the component devices into a list,
+ * and bind them when instructed. At the moment, we're specific to the DRM
+ * subsystem, and only handles one master device, but this doesn't have to be
+ * the case.
+ */
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+struct master {
+ struct list_head node;
+ struct list_head components;
+ bool bound;
+
+ const struct component_master_ops *ops;
+ struct device *dev;
+};
+
+struct component {
+ struct list_head node;
+ struct list_head master_node;
+ struct master *master;
+ bool bound;
+
+ const struct component_ops *ops;
+ struct device *dev;
+};
+
+static DEFINE_MUTEX(component_mutex);
+static LIST_HEAD(component_list);
+static LIST_HEAD(masters);
+
+static struct master *__master_find(struct device *dev,
+ const struct component_master_ops *ops)
+{
+ struct master *m;
+
+ list_for_each_entry(m, &masters, node)
+ if (m->dev == dev && (!ops || m->ops == ops))
+ return m;
+
+ return NULL;
+}
+
+/* Attach an unattached component to a master. */
+static void component_attach_master(struct master *master, struct component *c)
+{
+ c->master = master;
+
+ list_add_tail(&c->master_node, &master->components);
+}
+
+/* Detach a component from a master. */
+static void component_detach_master(struct master *master, struct component *c)
+{
+ list_del(&c->master_node);
+
+ c->master = NULL;
+}
+
+int component_master_add_child(struct master *master,
+ int (*compare)(struct device *, void *), void *compare_data)
+{
+ struct component *c;
+ int ret = -ENXIO;
+
+ list_for_each_entry(c, &component_list, node) {
+ if (c->master)
+ continue;
+
+ if (compare(c->dev, compare_data)) {
+ component_attach_master(master, c);
+ ret = 0;
+ break;
+ }
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(component_master_add_child);
+
+/* Detach all attached components from this master */
+static void master_remove_components(struct master *master)
+{
+ while (!list_empty(&master->components)) {
+ struct component *c = list_first_entry(&master->components,
+ struct component, master_node);
+
+ WARN_ON(c->master != master);
+
+ component_detach_master(master, c);
+ }
+}
+
+/*
+ * Try to bring up a master. If component is NULL, we're interested in
+ * this master, otherwise it's a component which must be present to try
+ * and bring up the master.
+ *
+ * Returns 1 for successful bringup, 0 if not ready, or -ve errno.
+ */
+static int try_to_bring_up_master(struct master *master,
+ struct component *component)
+{
+ int ret = 0;
+
+ if (!master->bound) {
+ /*
+ * Search the list of components, looking for components that
+ * belong to this master, and attach them to the master.
+ */
+ if (master->ops->add_components(master->dev, master)) {
+ /* Failed to find all components */
+ master_remove_components(master);
+ ret = 0;
+ goto out;
+ }
+
+ if (component && component->master != master) {
+ master_remove_components(master);
+ ret = 0;
+ goto out;
+ }
+
+ /* Found all components */
+ ret = master->ops->bind(master->dev);
+ if (ret < 0) {
+ master_remove_components(master);
+ goto out;
+ }
+
+ master->bound = true;
+ ret = 1;
+ }
+out:
+
+ return ret;
+}
+
+static int try_to_bring_up_masters(struct component *component)
+{
+ struct master *m;
+ int ret = 0;
+
+ list_for_each_entry(m, &masters, node) {
+ ret = try_to_bring_up_master(m, component);
+ if (ret != 0)
+ break;
+ }
+
+ return ret;
+}
+
+static void take_down_master(struct master *master)
+{
+ if (master->bound) {
+ master->ops->unbind(master->dev);
+ master->bound = false;
+ }
+
+ master_remove_components(master);
+}
+
+int component_master_add(struct device *dev,
+ const struct component_master_ops *ops)
+{
+ struct master *master;
+ int ret;
+
+ master = kzalloc(sizeof(*master), GFP_KERNEL);
+ if (!master)
+ return -ENOMEM;
+
+ master->dev = dev;
+ master->ops = ops;
+ INIT_LIST_HEAD(&master->components);
+
+ /* Add to the list of available masters. */
+ mutex_lock(&component_mutex);
+ list_add(&master->node, &masters);
+
+ ret = try_to_bring_up_master(master, NULL);
+
+ if (ret < 0) {
+ /* Delete off the list if we weren't successful */
+ list_del(&master->node);
+ kfree(master);
+ }
+ mutex_unlock(&component_mutex);
+
+ return ret < 0 ? ret : 0;
+}
+EXPORT_SYMBOL_GPL(component_master_add);
+
+void component_master_del(struct device *dev,
+ const struct component_master_ops *ops)
+{
+ struct master *master;
+
+ mutex_lock(&component_mutex);
+ master = __master_find(dev, ops);
+ if (master) {
+ take_down_master(master);
+
+ list_del(&master->node);
+ kfree(master);
+ }
+ mutex_unlock(&component_mutex);
+}
+EXPORT_SYMBOL_GPL(component_master_del);
+
+static void component_unbind(struct component *component,
+ struct master *master, void *data)
+{
+ WARN_ON(!component->bound);
+
+ component->ops->unbind(component->dev, master->dev, data);
+ component->bound = false;
+
+ /* Release all resources claimed in the binding of this component */
+ devres_release_group(component->dev, component);
+}
+
+void component_unbind_all(struct device *master_dev, void *data)
+{
+ struct master *master;
+ struct component *c;
+
+ WARN_ON(!mutex_is_locked(&component_mutex));
+
+ master = __master_find(master_dev, NULL);
+ if (!master)
+ return;
+
+ list_for_each_entry_reverse(c, &master->components, master_node)
+ component_unbind(c, master, data);
+}
+EXPORT_SYMBOL_GPL(component_unbind_all);
+
+static int component_bind(struct component *component, struct master *master,
+ void *data)
+{
+ int ret;
+
+ /*
+ * Each component initialises inside its own devres group.
+ * This allows us to roll-back a failed component without
+ * affecting anything else.
+ */
+ if (!devres_open_group(master->dev, NULL, GFP_KERNEL))
+ return -ENOMEM;
+
+ /*
+ * Also open a group for the device itself: this allows us
+ * to release the resources claimed against the sub-device
+ * at the appropriate moment.
+ */
+ if (!devres_open_group(component->dev, component, GFP_KERNEL)) {
+ devres_release_group(master->dev, NULL);
+ return -ENOMEM;
+ }
+
+ dev_dbg(master->dev, "binding %s (ops %ps)\n",
+ dev_name(component->dev), component->ops);
+
+ ret = component->ops->bind(component->dev, master->dev, data);
+ if (!ret) {
+ component->bound = true;
+
+ /*
+ * Close the component device's group so that resources
+ * allocated in the binding are encapsulated for removal
+ * at unbind. Remove the group on the DRM device as we
+ * can clean those resources up independently.
+ */
+ devres_close_group(component->dev, NULL);
+ devres_remove_group(master->dev, NULL);
+
+ dev_info(master->dev, "bound %s (ops %ps)\n",
+ dev_name(component->dev), component->ops);
+ } else {
+ devres_release_group(component->dev, NULL);
+ devres_release_group(master->dev, NULL);
+
+ dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
+ dev_name(component->dev), component->ops, ret);
+ }
+
+ return ret;
+}
+
+int component_bind_all(struct device *master_dev, void *data)
+{
+ struct master *master;
+ struct component *c;
+ int ret = 0;
+
+ WARN_ON(!mutex_is_locked(&component_mutex));
+
+ master = __master_find(master_dev, NULL);
+ if (!master)
+ return -EINVAL;
+
+ list_for_each_entry(c, &master->components, master_node) {
+ ret = component_bind(c, master, data);
+ if (ret)
+ break;
+ }
+
+ if (ret != 0) {
+ list_for_each_entry_continue_reverse(c, &master->components,
+ master_node)
+ component_unbind(c, master, data);
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(component_bind_all);
+
+int component_add(struct device *dev, const struct component_ops *ops)
+{
+ struct component *component;
+ int ret;
+
+ component = kzalloc(sizeof(*component), GFP_KERNEL);
+ if (!component)
+ return -ENOMEM;
+
+ component->ops = ops;
+ component->dev = dev;
+
+ dev_dbg(dev, "adding component (ops %ps)\n", ops);
+
+ mutex_lock(&component_mutex);
+ list_add_tail(&component->node, &component_list);
+
+ ret = try_to_bring_up_masters(component);
+ if (ret < 0) {
+ list_del(&component->node);
+
+ kfree(component);
+ }
+ mutex_unlock(&component_mutex);
+
+ return ret < 0 ? ret : 0;
+}
+EXPORT_SYMBOL_GPL(component_add);
+
+void component_del(struct device *dev, const struct component_ops *ops)
+{
+ struct component *c, *component = NULL;
+
+ mutex_lock(&component_mutex);
+ list_for_each_entry(c, &component_list, node)
+ if (c->dev == dev && c->ops == ops) {
+ list_del(&c->node);
+ component = c;
+ break;
+ }
+
+ if (component && component->master)
+ take_down_master(component->master);
+
+ mutex_unlock(&component_mutex);
+
+ WARN_ON(!component);
+ kfree(component);
+}
+EXPORT_SYMBOL_GPL(component_del);
+
+MODULE_LICENSE("GPL v2");
View
7 drivers/base/core.c
@@ -491,11 +491,13 @@ static int device_add_attrs(struct device *dev)
if (device_supports_offline(dev) && !dev->offline_disabled) {
error = device_create_file(dev, &dev_attr_online);
if (error)
- goto err_remove_type_groups;
+ goto err_remove_dev_groups;
}
return 0;
+ err_remove_dev_groups:
+ device_remove_groups(dev, dev->groups);
err_remove_type_groups:
if (type)
device_remove_groups(dev, type->groups);
@@ -1603,6 +1605,7 @@ device_create_groups_vargs(struct class *class, struct device *parent,
goto error;
}
+ device_initialize(dev);
dev->devt = devt;
dev->class = class;
dev->parent = parent;
@@ -1614,7 +1617,7 @@ device_create_groups_vargs(struct class *class, struct device *parent,
if (retval)
goto error;
- retval = device_register(dev);
+ retval = device_add(dev);
if (retval)
goto error;
View
2 drivers/base/devtmpfs.c
@@ -299,7 +299,7 @@ static int handle_remove(const char *nodename, struct device *dev)
{
struct path parent;
struct dentry *dentry;
- int deleted = 1;
+ int deleted = 0;
int err;
dentry = kern_path_locked(nodename, &parent);
View
93 drivers/base/firmware_class.c
@@ -96,6 +96,15 @@ static inline long firmware_loading_timeout(void)
return loading_timeout > 0 ? loading_timeout * HZ : MAX_SCHEDULE_TIMEOUT;
}
+/* firmware behavior options */
+#define FW_OPT_UEVENT (1U << 0)
+#define FW_OPT_NOWAIT (1U << 1)
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+#define FW_OPT_FALLBACK (1U << 2)
+#else
+#define FW_OPT_FALLBACK 0
+#endif
+
struct firmware_cache {
/* firmware_buf instance will be added into the below list */
spinlock_t lock;
@@ -219,6 +228,7 @@ static int fw_lookup_and_allocate_buf(const char *fw_name,
}
static void __fw_free_buf(struct kref *ref)
+ __releases(&fwc->lock)
{
struct firmware_buf *buf = to_fwbuf(ref);
struct firmware_cache *fwc = buf->fwc;
@@ -270,21 +280,21 @@ module_param_string(path, fw_path_para, sizeof(fw_path_para), 0644);
MODULE_PARM_DESC(path, "customized firmware image search path with a higher priority than default path");
/* Don't inline this: 'struct kstat' is biggish */
-static noinline_for_stack long fw_file_size(struct file *file)
+static noinline_for_stack int fw_file_size(struct file *file)
{
struct kstat st;
if (vfs_getattr(&file->f_path, &st))
return -1;
if (!S_ISREG(st.mode))
return -1;
- if (st.size != (long)st.size)
+ if (st.size != (int)st.size)
return -1;
return st.size;
}
static int fw_read_file_contents(struct file *file, struct firmware_buf *fw_buf)
{
- long size;
+ int size;
char *buf;
int rc;
@@ -820,7 +830,7 @@ static void firmware_class_timeout_work(struct work_struct *work)
static struct firmware_priv *
fw_create_instance(struct firmware *firmware, const char *fw_name,
- struct device *device, bool uevent, bool nowait)
+ struct device *device, unsigned int opt_flags)
{
struct firmware_priv *fw_priv;
struct device *f_dev;
@@ -832,7 +842,7 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
goto exit;
}
- fw_priv->nowait = nowait;
+ fw_priv->nowait = !!(opt_flags & FW_OPT_NOWAIT);
fw_priv->fw = firmware;
INIT_DELAYED_WORK(&fw_priv->timeout_work,
firmware_class_timeout_work);
@@ -848,8 +858,8 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
}
/* load a firmware via user helper */
-static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
- long timeout)
+static int _request_firmware_load(struct firmware_priv *fw_priv,
+ unsigned int opt_flags, long timeout)
{
int retval = 0;
struct device *f_dev = &fw_priv->dev;
@@ -885,7 +895,7 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
goto err_del_bin_attr;
}
- if (uevent) {
+ if (opt_flags & FW_OPT_UEVENT) {
buf->need_uevent = true;
dev_set_uevent_suppress(f_dev, false);
dev_dbg(f_dev, "firmware: requesting %s\n", buf->fw_id);
@@ -911,16 +921,16 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
static int fw_load_from_user_helper(struct firmware *firmware,
const char *name, struct device *device,
- bool uevent, bool nowait, long timeout)
+ unsigned int opt_flags, long timeout)
{
struct firmware_priv *fw_priv;
- fw_priv = fw_create_instance(firmware, name, device, uevent, nowait);
+ fw_priv = fw_create_instance(firmware, name, device, opt_flags);
if (IS_ERR(fw_priv))
return PTR_ERR(fw_priv);
fw_priv->buf = firmware->priv;
- return _request_firmware_load(fw_priv, uevent, timeout);
+ return _request_firmware_load(fw_priv, opt_flags, timeout);
}
#ifdef CONFIG_PM_SLEEP
@@ -942,7 +952,7 @@ static void kill_requests_without_uevent(void)
#else /* CONFIG_FW_LOADER_USER_HELPER */
static inline int
fw_load_from_user_helper(struct firmware *firmware, const char *name,
- struct device *device, bool uevent, bool nowait,
+ struct device *device, unsigned int opt_flags,
long timeout)
{
return -ENOENT;
@@ -1023,7 +1033,7 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
}
static int assign_firmware_buf(struct firmware *fw, struct device *device,
- bool skip_cache)
+ unsigned int opt_flags)
{
struct firmware_buf *buf = fw->priv;
@@ -1040,7 +1050,8 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
* device may has been deleted already, but the problem
* should be fixed in devres or driver core.
*/
- if (device && !skip_cache)
+ /* don't cache firmware handled without uevent */
+ if (device && (opt_flags & FW_OPT_UEVENT))
fw_add_devm_name(device, buf->fw_id);
/*
@@ -1061,7 +1072,7 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
/* called from request_firmware() and request_firmware_work_func() */
static int
_request_firmware(const struct firmware **firmware_p, const char *name,
- struct device *device, bool uevent, bool nowait)
+ struct device *device, unsigned int opt_flags)
{
struct firmware *fw;
long timeout;
@@ -1076,7 +1087,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
ret = 0;
timeout = firmware_loading_timeout();
- if (nowait) {
+ if (opt_flags & FW_OPT_NOWAIT) {
timeout = usermodehelper_read_lock_wait(timeout);
if (!timeout) {
dev_dbg(device, "firmware: %s loading timed out\n",
@@ -1095,16 +1106,18 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
ret = fw_get_filesystem_firmware(device, fw->priv);
if (ret) {
- dev_warn(device, "Direct firmware load failed with error %d\n",
- ret);
- dev_warn(device, "Falling back to user helper\n");
- ret = fw_load_from_user_helper(fw, name, device,
- uevent, nowait, timeout);
+ if (opt_flags & FW_OPT_FALLBACK) {
+ dev_warn(device,
+ "Direct firmware load failed with error %d\n",
+ ret);
+ dev_warn(device, "Falling back to user helper\n");
+ ret = fw_load_from_user_helper(fw, name, device,
+ opt_flags, timeout);
+ }
}
- /* don't cache firmware handled without uevent */
if (!ret)
- ret = assign_firmware_buf(fw, device, !uevent);
+ ret = assign_firmware_buf(fw, device, opt_flags);
usermodehelper_read_unlock();
@@ -1146,12 +1159,37 @@ request_firmware(const struct firmware **firmware_p, const char *name,
/* Need to pin this module until return */
__module_get(THIS_MODULE);
- ret = _request_firmware(firmware_p, name, device, true, false);
+ ret = _request_firmware(firmware_p, name, device,
+ FW_OPT_UEVENT | FW_OPT_FALLBACK);
module_put(THIS_MODULE);
return ret;
}
EXPORT_SYMBOL(request_firmware);
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+/**
+ * request_firmware: - load firmware directly without usermode helper
+ * @firmware_p: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded
+ *
+ * This function works pretty much like request_firmware(), but this doesn't
+ * fall back to usermode helper even if the firmware couldn't be loaded
+ * directly from fs. Hence it's useful for loading optional firmwares, which
+ * aren't always present, without extra long timeouts of udev.
+ **/
+int request_firmware_direct(const struct firmware **firmware_p,
+ const char *name, struct device *device)
+{
+ int ret;
+ __module_get(THIS_MODULE);
+ ret = _request_firmware(firmware_p, name, device, FW_OPT_UEVENT);
+ module_put(THIS_MODULE);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(request_firmware_direct);
+#endif
+
/**
* release_firmware: - release the resource associated with a firmware image
* @fw: firmware resource to release
@@ -1174,7 +1212,7 @@ struct firmware_work {
struct device *device;
void *context;
void (*cont)(const struct firmware *fw, void *context);
- bool uevent;
+ unsigned int opt_flags;
};
static void request_firmware_work_func(struct work_struct *work)
@@ -1185,7 +1223,7 @@ static void request_firmware_work_func(struct work_struct *work)
fw_work = container_of(work, struct firmware_work, work);
_request_firmware(&fw, fw_work->name, fw_work->device,
- fw_work->uevent, true);
+ fw_work->opt_flags);
fw_work->cont(fw, fw_work->context);
put_device(fw_work->device); /* taken in request_firmware_nowait() */
@@ -1233,7 +1271,8 @@ request_firmware_nowait(
fw_work->device = device;
fw_work->context = context;
fw_work->cont = cont;
- fw_work->uevent = uevent;
+ fw_work->opt_flags = FW_OPT_NOWAIT | FW_OPT_FALLBACK |
+ (uevent ? FW_OPT_UEVENT : 0);
if (!try_module_get(module)) {
kfree(fw_work);
View
3 drivers/firmware/dmi-sysfs.c
@@ -553,7 +553,7 @@ static const struct bin_attribute dmi_entry_raw_attr = {
static void dmi_sysfs_entry_release(struct kobject *kobj)
{
struct dmi_sysfs_entry *entry = to_entry(kobj);
- sysfs_remove_bin_file(&entry->kobj, &dmi_entry_raw_attr);
+
spin_lock(&entry_list_lock);
list_del(&entry->list);
spin_unlock(&entry_list_lock);
@@ -685,6 +685,7 @@ static void __exit dmi_sysfs_exit(void)
pr_debug("dmi-sysfs: unloading.\n");
cleanup_entry_list();
kset_unregister(dmi_kset);
+ kobject_del(dmi_kobj);
kobject_put(dmi_kobj);
}
View
4 drivers/gpio/gpiolib.c
@@ -393,7 +393,7 @@ static const DEVICE_ATTR(value, 0644,
static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
{
- struct sysfs_dirent *value_sd = priv;
+ struct kernfs_node *value_sd = priv;
sysfs_notify_dirent(value_sd);
return IRQ_HANDLED;
@@ -402,7 +402,7 @@ static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
unsigned long gpio_flags)
{
- struct sysfs_dirent *value_sd;
+ struct kernfs_node *value_sd;
unsigned long irq_flags;
int ret, irq, id;
View
2 drivers/md/bitmap.c
@@ -1635,7 +1635,7 @@ int bitmap_create(struct mddev *mddev)
sector_t blocks = mddev->resync_max_sectors;
struct file *file = mddev->bitmap_info.file;
int err;
- struct sysfs_dirent *bm = NULL;
+ struct kernfs_node *bm = NULL;
BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
View
2 drivers/md/bitmap.h
@@ -225,7 +225,7 @@ struct bitmap {
wait_queue_head_t overflow_wait;
wait_queue_head_t behind_wait;
- struct sysfs_dirent *sysfs_can_clear;
+ struct kernfs_node *sysfs_can_clear;
};
/* the bitmap API */
View
10 drivers/md/md.h
@@ -106,7 +106,7 @@ struct md_rdev {
*/
struct work_struct del_work; /* used for delayed sysfs removal */
- struct sysfs_dirent *sysfs_state; /* handle for 'state'
+ struct kernfs_node *sysfs_state; /* handle for 'state'
* sysfs entry */
struct badblocks {
@@ -379,10 +379,10 @@ struct mddev {
sector_t resync_max; /* resync should pause
* when it gets here */
- struct sysfs_dirent *sysfs_state; /* handle for 'array_state'
+ struct kernfs_node *sysfs_state; /* handle for 'array_state'
* file in sysfs.
*/
- struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */
+ struct kernfs_node *sysfs_action; /* handle for 'sync_action' */
struct work_struct del_work; /* used for delayed sysfs removal */
@@ -501,13 +501,13 @@ struct md_sysfs_entry {
};
extern struct attribute_group md_bitmap_group;
-static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
+static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name)
{
if (sd)
return sysfs_get_dirent(sd, name);
return sd;
}
-static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
+static inline void sysfs_notify_dirent_safe(struct kernfs_node *sd)
{
if (sd)
sysfs_notify_dirent(sd);
View
2 drivers/misc/mic/host/mic_device.h
@@ -112,7 +112,7 @@ struct mic_device {
struct work_struct shutdown_work;
u8 state;
u8 shutdown_status;
- struct sysfs_dirent *state_sysfs;
+ struct kernfs_node *state_sysfs;
struct completion reset_wait;
void *log_buf_addr;
int *log_buf_len;
View
2 fs/Makefile
@@ -53,7 +53,7 @@ obj-$(CONFIG_FHANDLE) += fhandle.o
obj-y += quota/
obj-$(CONFIG_PROC_FS) += proc/
-obj-$(CONFIG_SYSFS) += sysfs/
+obj-$(CONFIG_SYSFS) += sysfs/ kernfs/
obj-$(CONFIG_CONFIGFS_FS) += configfs/
obj-y += devpts/
View
5 fs/kernfs/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the kernfs pseudo filesystem
+#
+
+obj-y := mount.o inode.o dir.o file.o symlink.o
View
1,073 fs/kernfs/dir.c
@@ -0,0 +1,1073 @@
+/*
+ * fs/kernfs/dir.c - kernfs directory implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/hash.h>
+
+#include "kernfs-internal.h"
+
+DEFINE_MUTEX(kernfs_mutex);
+
+#define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
+
+/**
+ * kernfs_name_hash
+ * @name: Null terminated string to hash
+ * @ns: Namespace tag to hash
+ *
+ * Returns 31 bit hash of ns + name (so it fits in an off_t )
+ */
+static unsigned int kernfs_name_hash(const char *name, const void *ns)
+{
+ unsigned long hash = init_name_hash();
+ unsigned int len = strlen(name);
+ while (len--)
+ hash = partial_name_hash(*name++, hash);
+ hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
+ hash &= 0x7fffffffU;
+ /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
+ if (hash < 1)
+ hash += 2;
+ if (hash >= INT_MAX)
+ hash = INT_MAX - 1;
+ return hash;
+}
+
+static int kernfs_name_compare(unsigned int hash, const char *name,
+ const void *ns, const struct kernfs_node *kn)
+{
+ if (hash != kn->hash)
+ return hash - kn->hash;
+ if (ns != kn->ns)
+ return ns - kn->ns;
+ return strcmp(name, kn->name);
+}
+
+static int kernfs_sd_compare(const struct kernfs_node *left,
+ const struct kernfs_node *right)
+{
+ return kernfs_name_compare(left->hash, left->name, left->ns, right);
+}
+
+/**
+ * kernfs_link_sibling - link kernfs_node into sibling rbtree
+ * @kn: kernfs_node of interest
+ *
+ * Link @kn into its sibling rbtree which starts from
+ * @kn->parent->dir.children.
+ *
+ * Locking:
+ * mutex_lock(kernfs_mutex)
+ *
+ * RETURNS:
+ * 0 on susccess -EEXIST on failure.
+ */
+static int kernfs_link_sibling(struct kernfs_node *kn)
+{
+ struct rb_node **node = &kn->parent->dir.children.rb_node;
+ struct rb_node *parent = NULL;
+
+ if (kernfs_type(kn) == KERNFS_DIR)
+ kn->parent->dir.subdirs++;
+
+ while (*node) {
+ struct kernfs_node *pos;
+ int result;
+
+ pos = rb_to_kn(*node);
+ parent = *node;
+ result = kernfs_sd_compare(kn, pos);
+ if (result < 0)
+ node = &pos->rb.rb_left;
+ else if (result > 0)
+ node = &pos->rb.rb_right;
+ else
+ return -EEXIST;
+ }
+ /* add new node and rebalance the tree */
+ rb_link_node(&kn->rb, parent, node);
+ rb_insert_color(&kn->rb, &kn->parent->dir.children);
+ return 0;
+}
+
+/**
+ * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree
+ * @kn: kernfs_node of interest
+ *
+ * Unlink @kn from its sibling rbtree which starts from
+ * kn->parent->dir.children.
+ *
+ * Locking:
+ * mutex_lock(kernfs_mutex)
+ */
+static void kernfs_unlink_sibling(struct kernfs_node *kn)
+{
+ if (kernfs_type(kn) == KERNFS_DIR)
+ kn->parent->dir.subdirs--;
+
+ rb_erase(&kn->rb, &kn->parent->dir.children);
+}
+
+/**
+ * kernfs_get_active - get an active reference to kernfs_node
+ * @kn: kernfs_node to get an active reference to
+ *
+ * Get an active reference of @kn. This function is noop if @kn
+ * is NULL.
+ *
+ * RETURNS:
+ * Pointer to @kn on success, NULL on failure.
+ */
+struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
+{
+ if (unlikely(!kn))
+ return NULL;
+
+ if (!atomic_inc_unless_negative(&kn->active))
+ return NULL;
+
+ if (kn->flags & KERNFS_LOCKDEP)
+ rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);
+ return kn;
+}
+
+/**
+ * kernfs_put_active - put an active reference to kernfs_node
+ * @kn: kernfs_node to put an active reference to
+ *
+ * Put an active reference to @kn. This function is noop if @kn
+ * is NULL.
+ */
+void kernfs_put_active(struct kernfs_node *kn)
+{
+ int v;
+
+ if (unlikely(!kn))
+ return;
+
+ if (kn->flags & KERNFS_LOCKDEP)
+ rwsem_release(&kn->dep_map, 1, _RET_IP_);
+ v = atomic_dec_return(&kn->active);
+ if (likely(v != KN_DEACTIVATED_BIAS))
+ return;
+
+ /*
+ * atomic_dec_return() is a mb(), we'll always see the updated
+ * kn->u.completion.
+ */
+ complete(kn->u.completion);
+}
+
+/**
+ * kernfs_deactivate - deactivate kernfs_node
+ * @kn: kernfs_node to deactivate
+ *
+ * Deny new active references and drain existing ones.
+ */
+static void kernfs_deactivate(struct kernfs_node *kn)
+{
+ DECLARE_COMPLETION_ONSTACK(wait);
+ int v;
+
+ BUG_ON(!(kn->flags & KERNFS_REMOVED));
+
+ if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
+ return;
+
+ kn->u.completion = (void *)&wait;
+
+ rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
+ /* atomic_add_return() is a mb(), put_active() will always see
+ * the updated kn->u.completion.
+ */
+ v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
+
+ if (v != KN_DEACTIVATED_BIAS) {
+ lock_contended(&kn->dep_map, _RET_IP_);
+ wait_for_completion(&wait);
+ }
+
+ lock_acquired(&kn->dep_map, _RET_IP_);
+ rwsem_release(&kn->dep_map, 1, _RET_IP_);
+}
+
+/**
+ * kernfs_get - get a reference count on a kernfs_node
+ * @kn: the target kernfs_node
+ */
+void kernfs_get(struct kernfs_node *kn)
+{
+ if (kn) {
+ WARN_ON(!atomic_read(&kn->count));
+ atomic_inc(&kn->count);
+ }
+}
+EXPORT_SYMBOL_GPL(kernfs_get);
+
+/**
+ * kernfs_put - put a reference count on a kernfs_node
+ * @kn: the target kernfs_node
+ *
+ * Put a reference count of @kn and destroy it if it reached zero.
+ */
+void kernfs_put(struct kernfs_node *kn)
+{
+ struct kernfs_node *parent;
+ struct kernfs_root *root;
+
+ if (!kn || !atomic_dec_and_test(&kn->count))
+ return;
+ root = kernfs_root(kn);
+ repeat:
+ /* Moving/renaming is always done while holding reference.
+ * kn->parent won't change beneath us.
+ */
+ parent = kn->parent;
+
+ WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n",
+ parent ? parent->name : "", kn->name);
+
+ if (kernfs_type(kn) == KERNFS_LINK)
+ kernfs_put(kn->symlink.target_kn);
+ if (!(kn->flags & KERNFS_STATIC_NAME))
+ kfree(kn->name);
+ if (kn->iattr) {
+ if (kn->iattr->ia_secdata)
+ security_release_secctx(kn->iattr->ia_secdata,
+ kn->iattr->ia_secdata_len);
+ simple_xattrs_free(&kn->iattr->xattrs);
+ }
+ kfree(kn->iattr);
+ ida_simple_remove(&root->ino_ida, kn->ino);
+ kmem_cache_free(kernfs_node_cache, kn);
+
+ kn = parent;
+ if (kn) {
+ if (atomic_dec_and_test(&kn->count))
+ goto repeat;
+ } else {
+ /* just released the root kn, free @root too */
+ ida_destroy(&root->ino_ida);
+ kfree(root);
+ }
+}
+EXPORT_SYMBOL_GPL(kernfs_put);
+
+static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ struct kernfs_node *kn;
+
+ if (flags & LOOKUP_RCU)
+ return -ECHILD;
+
+ /* Always perform fresh lookup for negatives */
+ if (!dentry->d_inode)
+ goto out_bad_unlocked;
+
+ kn = dentry->d_fsdata;
+ mutex_lock(&kernfs_mutex);
+
+ /* The kernfs node has been deleted */
+ if (kn->flags & KERNFS_REMOVED)
+ goto out_bad;
+
+ /* The kernfs node has been moved? */
+ if (dentry->d_parent->d_fsdata != kn->parent)
+ goto out_bad;
+
+ /* The kernfs node has been renamed */
+ if (strcmp(dentry->d_name.name, kn->name) != 0)
+ goto out_bad;
+
+ /* The kernfs node has been moved to a different namespace */
+ if (kn->parent && kernfs_ns_enabled(kn->parent) &&
+ kernfs_info(dentry->d_sb)->ns != kn->ns)
+ goto out_bad;
+
+ mutex_unlock(&kernfs_mutex);
+out_valid:
+ return 1;
+out_bad:
+ mutex_unlock(&kernfs_mutex);
+out_bad_unlocked:
+ /*
+ * @dentry doesn't match the underlying kernfs node, drop the
+ * dentry and force lookup. If we have submounts we must allow the
+ * vfs caches to lie about the state of the filesystem to prevent
+ * leaks and other nasty things, so use check_submounts_and_drop()
+ * instead of d_drop().
+ */
+ if (check_submounts_and_drop(dentry) != 0)
+ goto out_valid;
+
+ return 0;
+}
+
+static void kernfs_dop_release(struct dentry *dentry)
+{
+ kernfs_put(dentry->d_fsdata);
+}
+
+const struct dentry_operations kernfs_dops = {
+ .d_revalidate = kernfs_dop_revalidate,
+ .d_release = kernfs_dop_release,
+};
+
+static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
+ const char *name, umode_t mode,
+ unsigned flags)
+{
+ char *dup_name = NULL;
+ struct kernfs_node *kn;
+ int ret;
+
+ if (!(flags & KERNFS_STATIC_NAME)) {
+ name = dup_name = kstrdup(name, GFP_KERNEL);
+ if (!name)
+ return NULL;
+ }
+
+ kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL);
+ if (!kn)
+ goto err_out1;
+
+ ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL);
+ if (ret < 0)
+ goto err_out2;
+ kn->ino = ret;
+
+ atomic_set(&kn->count, 1);
+ atomic_set(&kn->active, 0);
+
+ kn->name = name;
+ kn->mode = mode;
+ kn->flags = flags | KERNFS_REMOVED;
+
+ return kn;
+
+ err_out2:
+ kmem_cache_free(kernfs_node_cache, kn);
+ err_out1:
+ kfree(dup_name);
+ return NULL;
+}
+
+struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
+ const char *name, umode_t mode,
+ unsigned flags)
+{
+ struct kernfs_node *kn;
+
+ kn = __kernfs_new_node(kernfs_root(parent), name, mode, flags);
+ if (kn) {
+ kernfs_get(parent);
+ kn->parent = parent;
+ }
+ return kn;
+}
+
+/**
+ * kernfs_addrm_start - prepare for kernfs_node add/remove
+ * @acxt: pointer to kernfs_addrm_cxt to be used
+ *
+ * This function is called when the caller is about to add or remove
+ * kernfs_node. This function acquires kernfs_mutex. @acxt is used
+ * to keep and pass context to other addrm functions.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep). kernfs_mutex is locked on
+ * return.
+ */
+void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt)
+ __acquires(kernfs_mutex)
+{
+ memset(acxt, 0, sizeof(*acxt));
+
+ mutex_lock(&kernfs_mutex);
+}
+
+/**
+ * kernfs_add_one - add kernfs_node to parent without warning
+ * @acxt: addrm context to use
+ * @kn: kernfs_node to be added
+ *
+ * The caller must already have initialized @kn->parent. This
+ * function increments nlink of the parent's inode if @kn is a
+ * directory and link into the children list of the parent.
+ *
+ * This function should be called between calls to
+ * kernfs_addrm_start() and kernfs_addrm_finish() and should be passed
+ * the same @acxt as passed to kernfs_addrm_start().
+ *
+ * LOCKING:
+ * Determined by kernfs_addrm_start().
+ *
+ * RETURNS:
+ * 0 on success, -EEXIST if entry with the given name already
+ * exists.
+ */
+int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
+{
+ struct kernfs_node *parent = kn->parent;
+ bool has_ns = kernfs_ns_enabled(parent);
+ struct kernfs_iattrs *ps_iattr;
+ int ret;
+
+ if (has_ns != (bool)kn->ns) {
+ WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+ has_ns ? "required" : "invalid", parent->name, kn->name);
+ return -EINVAL;
+ }
+
+ if (kernfs_type(parent) != KERNFS_DIR)
+ return -EINVAL;
+
+ if (parent->flags & KERNFS_REMOVED)
+ return -ENOENT;
+
+ kn->hash = kernfs_name_hash(kn->name, kn->ns);
+
+ ret = kernfs_link_sibling(kn);
+ if (ret)
+ return ret;
+
+ /* Update timestamps on the parent */
+ ps_iattr = parent->iattr;
+ if (ps_iattr) {
+ struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
+ ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+ }
+
+ /* Mark the entry added into directory tree */
+ kn->flags &= ~KERNFS_REMOVED;
+
+ return 0;
+}
+
+/**
+ * kernfs_remove_one - remove kernfs_node from parent
+ * @acxt: addrm context to use
+ * @kn: kernfs_node to be removed
+ *
+ * Mark @kn removed and drop nlink of parent inode if @kn is a
+ * directory. @kn is unlinked from the children list.
+ *
+ * This function should be called between calls to
+ * kernfs_addrm_start() and kernfs_addrm_finish() and should be
+ * passed the same @acxt as passed to kernfs_addrm_start().
+ *
+ * LOCKING:
+ * Determined by kernfs_addrm_start().
+ */
+static void kernfs_remove_one(struct kernfs_addrm_cxt *acxt,
+ struct kernfs_node *kn)
+{
+ struct kernfs_iattrs *ps_iattr;
+
+ /*
+ * Removal can be called multiple times on the same node. Only the
+ * first invocation is effective and puts the base ref.
+ */
+ if (kn->flags & KERNFS_REMOVED)
+ return;
+
+ if (kn->parent) {
+ kernfs_unlink_sibling(kn);
+
+ /* Update timestamps on the parent */
+ ps_iattr = kn->parent->iattr;
+ if (ps_iattr) {
+ ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
+ ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
+ }
+ }
+
+ kn->flags |= KERNFS_REMOVED;
+ kn->u.removed_list = acxt->removed;
+ acxt->removed = kn;
+}
+
+/**
+ * kernfs_addrm_finish - finish up kernfs_node add/remove
+ * @acxt: addrm context to finish up
+ *
+ * Finish up kernfs_node add/remove. Resources acquired by
+ * kernfs_addrm_start() are released and removed kernfs_nodes are
+ * cleaned up.
+ *
+ * LOCKING:
+ * kernfs_mutex is released.
+ */
+void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt)
+ __releases(kernfs_mutex)
+{
+ /* release resources acquired by kernfs_addrm_start() */
+ mutex_unlock(&kernfs_mutex);
+
+ /* kill removed kernfs_nodes */
+ while (acxt->removed) {
+ struct kernfs_node *kn = acxt->removed;
+
+ acxt->removed = kn->u.removed_list;
+
+ kernfs_deactivate(kn);
+ kernfs_unmap_bin_file(kn);
+ kernfs_put(kn);
+ }
+}
+
+/**
+ * kernfs_find_ns - find kernfs_node with the given name
+ * @parent: kernfs_node to search under
+ * @name: name to look for
+ * @ns: the namespace tag to use
+ *
+ * Look for kernfs_node with name @name under @parent. Returns pointer to
+ * the found kernfs_node on success, %NULL on failure.
+ */
+static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
+ const unsigned char *name,
+ const void *ns)
+{
+ struct rb_node *node = parent->dir.children.rb_node;
+ bool has_ns = kernfs_ns_enabled(parent);
+ unsigned int hash;
+
+ lockdep_assert_held(&kernfs_mutex);
+
+ if (has_ns != (bool)ns) {
+ WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+ has_ns ? "required" : "invalid", parent->name, name);
+ return NULL;
+ }
+
+ hash = kernfs_name_hash(name, ns);
+ while (node) {
+ struct kernfs_node *kn;
+ int result;
+
+ kn = rb_to_kn(node);
+ result = kernfs_name_compare(hash, name, ns, kn);
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return kn;
+ }
+ return NULL;
+}
+
+/**
+ * kernfs_find_and_get_ns - find and get kernfs_node with the given name
+ * @parent: kernfs_node to search under
+ * @name: name to look for
+ * @ns: the namespace tag to use
+ *
+ * Look for kernfs_node with name @name under @parent and get a reference
+ * if found. This function may sleep and returns pointer to the found
+ * kernfs_node on success, %NULL on failure.
+ */
+struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
+ const char *name, const void *ns)
+{
+ struct kernfs_node *kn;
+
+ mutex_lock(&kernfs_mutex);
+ kn = kernfs_find_ns(parent, name, ns);
+ kernfs_get(kn);
+ mutex_unlock(&kernfs_mutex);
+
+ return kn;
+}
+EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
+
+/**
+ * kernfs_create_root - create a new kernfs hierarchy
+ * @kdops: optional directory syscall operations for the hierarchy
+ * @priv: opaque data associated with the new directory
+ *
+ * Returns the root of the new hierarchy on success, ERR_PTR() value on
+ * failure.
+ */
+struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+{
+ struct kernfs_root *root;
+ struct kernfs_node *kn;
+
+ root = kzalloc(sizeof(*root), GFP_KERNEL);
+ if (!root)
+ return ERR_PTR(-ENOMEM);
+
+ ida_init(&root->ino_ida);
+
+ kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
+ KERNFS_DIR);
+ if (!kn) {
+ ida_destroy(&root->ino_ida);
+ kfree(root);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ kn->flags &= ~KERNFS_REMOVED;
+ kn->priv = priv;
+ kn->dir.root = root;
+
+ root->dir_ops = kdops;
+ root->kn = kn;
+
+ return root;
+}
+
+/**
+ * kernfs_destroy_root - destroy a kernfs hierarchy
+ * @root: root of the hierarchy to destroy
+ *
+ * Destroy the hierarchy anchored at @root by removing all existing
+ * directories and destroying @root.
+ */
+void kernfs_destroy_root(struct kernfs_root *root)
+{
+ kernfs_remove(root->kn); /* will also free @root */
+}
+
+/**
+ * kernfs_create_dir_ns - create a directory
+ * @parent: parent in which to create a new directory
+ * @name: name of the new directory
+ * @mode: mode of the new directory
+ * @priv: opaque data associated with the new directory
+ * @ns: optional namespace tag of the directory
+ *
+ * Returns the created node on success, ERR_PTR() value on failure.
+ */
+struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
+ const char *name, umode_t mode,
+ void *priv, const void *ns)
+{
+ struct kernfs_addrm_cxt acxt;
+ struct kernfs_node *kn;
+ int rc;
+
+ /* allocate */
+ kn = kernfs_new_node(parent, name, mode | S_IFDIR, KERNFS_DIR);
+ if (!kn)
+ return ERR_PTR(-ENOMEM);
+
+ kn->dir.root = parent->dir.root;
+ kn->ns = ns;
+ kn->priv = priv;
+
+ /* link in */
+ kernfs_addrm_start(&acxt);
+ rc = kernfs_add_one(&acxt, kn);
+ kernfs_addrm_finish(&acxt);
+
+ if (!rc)
+ return kn;
+
+ kernfs_put(kn);
+ return ERR_PTR(rc);
+}
+
+static struct dentry *kernfs_iop_lookup(struct inode *dir,
+ struct dentry *dentry,
+ unsigned int flags)
+{
+ struct dentry *ret;
+ struct kernfs_node *parent = dentry->d_parent->d_fsdata;
+ struct kernfs_node *kn;
+ struct inode *inode;
+ const void *ns = NULL;
+
+ mutex_lock(&kernfs_mutex);
+
+ if (kernfs_ns_enabled(parent))
+ ns = kernfs_info(dir->i_sb)->ns;
+
+ kn = kernfs_find_ns(parent, dentry->d_name.name, ns);
+
+ /* no such entry */
+ if (!kn) {
+ ret = NULL;
+ goto out_unlock;
+ }
+ kernfs_get(kn);
+ dentry->d_fsdata = kn;
+
+ /* attach dentry and inode */
+ inode = kernfs_get_inode(dir->i_sb, kn);
+ if (!inode) {
+ ret = ERR_PTR(-ENOMEM);
+ goto out_unlock;
+ }
+
+ /* instantiate and hash dentry */
+ ret = d_materialise_unique(dentry, inode);
+ out_unlock:
+ mutex_unlock(&kernfs_mutex);
+ return ret;
+}
+
+static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
+ umode_t mode)
+{
+ struct kernfs_node *parent = dir->i_private;
+ struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;
+
+ if (!kdops || !kdops->mkdir)
+ return -EPERM;
+
+ return kdops->mkdir(parent, dentry->d_name.name, mode);
+}
+
+static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+
+ if (!kdops || !kdops->rmdir)
+ return -EPERM;
+
+ return kdops->rmdir(kn);
+}
+
+static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
+{
+ struct kernfs_node *kn = old_dentry->d_fsdata;
+ struct kernfs_node *new_parent = new_dir->i_private;
+ struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+
+ if (!kdops || !kdops->rename)
+ return -EPERM;
+
+ return kdops->rename(kn, new_parent, new_dentry->d_name.name);
+}
+
+const struct inode_operations kernfs_dir_iops = {
+ .lookup = kernfs_iop_lookup,
+ .permission = kernfs_iop_permission,
+ .setattr = kernfs_iop_setattr,
+ .getattr = kernfs_iop_getattr,
+ .setxattr = kernfs_iop_setxattr,
+ .removexattr = kernfs_iop_removexattr,
+ .getxattr = kernfs_iop_getxattr,
+ .listxattr = kernfs_iop_listxattr,
+
+ .mkdir = kernfs_iop_mkdir,
+ .rmdir = kernfs_iop_rmdir,
+ .rename = kernfs_iop_rename,
+};
+
+static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos)
+{
+ struct kernfs_node *last;
+
+ while (true) {
+ struct rb_node *rbn;
+
+ last = pos;
+
+ if (kernfs_type(pos) != KERNFS_DIR)
+ break;
+
+ rbn = rb_first(&pos->dir.children);
+ if (!rbn)
+ break;
+
+ pos = rb_to_kn(rbn);
+ }
+
+ return last;
+}
+
+/**
+ * kernfs_next_descendant_post - find the next descendant for post-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @root: kernfs_node whose descendants to walk
+ *
+ * Find the next descendant to visit for post-order traversal of @root's
+ * descendants. @root is included in the iteration and the last node to be
+ * visited.
+ */
+static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
+ struct kernfs_node *root)
+{
+ struct rb_node *rbn;
+
+ lockdep_assert_held(&kernfs_mutex);
+
+ /* if first iteration, visit leftmost descendant which may be root */
+ if (!pos)
+ return kernfs_leftmost_descendant(root);
+
+ /* if we visited @root, we're done */
+ if (pos == root)
+ return NULL;
+
+ /* if there's an unvisited sibling, visit its leftmost descendant */
+ rbn = rb_next(&pos->rb);
+ if (rbn)
+ return kernfs_leftmost_descendant(rb_to_kn(rbn));
+
+ /* no sibling left, visit parent */
+ return pos->parent;
+}
+
+static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
+ struct kernfs_node *kn)
+{
+ struct kernfs_node *pos, *next;
+
+ if (!kn)
+ return;
+
+ pr_debug("kernfs %s: removing\n", kn->name);
+
+ next = NULL;
+ do {
+ pos = next;
+ next = kernfs_next_descendant_post(pos, kn);
+ if (pos)
+ kernfs_remove_one(acxt, pos);
+ } while (next);
+}
+
+/**
+ * kernfs_remove - remove a kernfs_node recursively
+ * @kn: the kernfs_node to remove
+ *
+ * Remove @kn along with all its subdirectories and files.
+ */
+void kernfs_remove(struct kernfs_node *kn)
+{
+ struct kernfs_addrm_cxt acxt;
+
+ kernfs_addrm_start(&acxt);
+ __kernfs_remove(&acxt, kn);
+ kernfs_addrm_finish(&acxt);
+}
+
+/**
+ * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it
+ * @parent: parent of the target
+ * @name: name of the kernfs_node to remove
+ * @ns: namespace tag of the kernfs_node to remove
+ *
+ * Look for the kernfs_node with @name and @ns under @parent and remove it.
+ * Returns 0 on success, -ENOENT if such entry doesn't exist.
+ */
+int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
+ const void *ns)
+{
+ struct kernfs_addrm_cxt acxt;
+ struct kernfs_node *kn;
+
+ if (!parent) {
+ WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n",
+ name);
+ return -ENOENT;
+ }
+
+ kernfs_addrm_start(&acxt);
+
+ kn = kernfs_find_ns(parent, name, ns);
+ if (kn)
+ __kernfs_remove(&acxt, kn);
+
+ kernfs_addrm_finish(&acxt);
+
+ if (kn)
+ return 0;
+ else
+ return -ENOENT;
+}
+
+/**
+ * kernfs_rename_ns - move and rename a kernfs_node
+ * @kn: target node
+ * @new_parent: new parent to put @sd under
+ * @new_name: new name
+ * @new_ns: new namespace tag
+ */
+int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
+ const char *new_name, const void *new_ns)
+{
+ int error;
+
+ mutex_lock(&kernfs_mutex);
+
+ error = -ENOENT;
+ if ((kn->flags | new_parent->flags) & KERNFS_REMOVED)
+ goto out;
+
+ error = 0;
+ if ((kn->parent == new_parent) && (kn->ns == new_ns) &&
+ (strcmp(kn->name, new_name) == 0))
+ goto out; /* nothing to rename */
+
+ error = -EEXIST;
+ if (kernfs_find_ns(new_parent, new_name, new_ns))
+ goto out;
+
+ /* rename kernfs_node */
+ if (strcmp(kn->name, new_name) != 0) {
+ error = -ENOMEM;
+ new_name = kstrdup(new_name, GFP_KERNEL);
+ if (!new_name)
+ goto out;
+
+ if (kn->flags & KERNFS_STATIC_NAME)
+ kn->flags &= ~KERNFS_STATIC_NAME;
+ else
+ kfree(kn->name);
+
+ kn->name = new_name;
+ }
+
+ /*
+ * Move to the appropriate place in the appropriate directories rbtree.
+ */
+ kernfs_unlink_sibling(kn);
+ kernfs_get(new_parent);
+ kernfs_put(kn->parent);
+ kn->ns = new_ns;
+ kn->hash = kernfs_name_hash(kn->name, kn->ns);
+ kn->parent = new_parent;
+ kernfs_link_sibling(kn);
+
+ error = 0;
+ out:
+ mutex_unlock(&kernfs_mutex);
+ return error;
+}
+
+/* Relationship between s_mode and the DT_xxx types */
+static inline unsigned char dt_type(struct kernfs_node *kn)
+{
+ return (kn->mode >> 12) & 15;
+}
+
+static int kernfs_dir_fop_release(struct inode *inode, struct file *filp)
+{
+ kernfs_put(filp->private_data);
+ return 0;
+}
+
+static struct kernfs_node *kernfs_dir_pos(const void *ns,
+ struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
+{
+ if (pos) {
+ int valid = !(pos->flags & KERNFS_REMOVED) &&
+ pos->parent == parent && hash == pos->hash;
+ kernfs_put(pos);
+ if (!valid)
+ pos = NULL;
+ }
+ if (!pos && (hash > 1) && (hash < INT_MAX)) {
+ struct rb_node *node = parent->dir.children.rb_node;
+ while (node) {
+ pos = rb_to_kn(node);
+
+ if (hash < pos->hash)
+ node = node->rb_left;
+ else if (hash > pos->hash)
+ node = node->rb_right;
+ else
+ break;
+ }
+ }
+ /* Skip over entries in the wrong namespace */
+ while (pos && pos->ns != ns) {
+ struct rb_node *node = rb_next(&pos->rb);
+ if (!node)
+ pos = NULL;
+ else
+ pos = rb_to_kn(node);
+ }
+ return pos;
+}
+
+static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
+ struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
+{
+ pos = kernfs_dir_pos(ns, parent, ino, pos);
+ if (pos)
+ do {
+ struct rb_node *node = rb_next(&pos->rb);
+ if (!node)
+ pos = NULL;
+ else
+ pos = rb_to_kn(node);
+ } while (pos && pos->ns != ns);
+ return pos;
+}
+
+static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
+{
+ struct dentry *dentry = file->f_path.dentry;
+ struct kernfs_node *parent = dentry->d_fsdata;
+ struct kernfs_node *pos = file->private_data;
+ const void *ns = NULL;
+
+ if (!dir_emit_dots(file, ctx))
+ return 0;
+ mutex_lock(&kernfs_mutex);
+
+ if (kernfs_ns_enabled(parent))
+ ns = kernfs_info(dentry->d_sb)->ns;
+
+ for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos);
+ pos;
+ pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) {
+ const char *name = pos->name;
+ unsigned int type = dt_type(pos);
+ int len = strlen(name);
+ ino_t ino = pos->ino;
+
+ ctx->pos = pos->hash;
+ file->private_data = pos;
+ kernfs_get(pos);
+
+ mutex_unlock(&kernfs_mutex);
+ if (!dir_emit(ctx, name, len, ino, type))
+ return 0;
+ mutex_lock(&kernfs_mutex);
+ }
+ mutex_unlock(&kernfs_mutex);
+ file->private_data = NULL;
+ ctx->pos = INT_MAX;
+ return 0;
+}
+
+static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset,
+ int whence)
+{
+ struct inode *inode = file_inode(file);
+ loff_t ret;
+
+ mutex_lock(&inode->i_mutex);
+ ret = generic_file_llseek(file, offset, whence);
+ mutex_unlock(&inode->i_mutex);
+
+ return ret;
+}
+
+const struct file_operations kernfs_dir_fops = {
+ .read = generic_read_dir,
+ .iterate = kernfs_fop_readdir,
+ .release = kernfs_dir_fop_release,
+ .llseek = kernfs_dir_fop_llseek,
+};
View
867 fs/kernfs/file.c
@@ -0,0 +1,867 @@
+/*
+ * fs/kernfs/file.c - kernfs file implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/pagemap.h>
+#include <linux/sched.h>
+
+#include "kernfs-internal.h"
+
+/*
+ * There's one kernfs_open_file for each open file and one kernfs_open_node
+ * for each kernfs_node with one or more open files.
+ *
+ * kernfs_node->attr.open points to kernfs_open_node. attr.open is
+ * protected by kernfs_open_node_lock.
+ *
+ * filp->private_data points to seq_file whose ->private points to
+ * kernfs_open_file. kernfs_open_files are chained at
+ * kernfs_open_node->files, which is protected by kernfs_open_file_mutex.
+ */
+static DEFINE_SPINLOCK(kernfs_open_node_lock);
+static DEFINE_MUTEX(kernfs_open_file_mutex);
+
+struct kernfs_open_node {
+ atomic_t refcnt;
+ atomic_t event;
+ wait_queue_head_t poll;
+ struct list_head files; /* goes through kernfs_open_file.list */
+};
+
+static struct kernfs_open_file *kernfs_of(struct file *file)
+{
+ return ((struct seq_file *)file->private_data)->private;
+}
+
+/*
+ * Determine the kernfs_ops for the given kernfs_node. This function must
+ * be called while holding an active reference.
+ */
+static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
+{
+ if (kn->flags & KERNFS_LOCKDEP)
+ lockdep_assert_held(kn);
+ return kn->attr.ops;
+}
+
+/*
+ * As kernfs_seq_stop() is also called after kernfs_seq_start() or
+ * kernfs_seq_next() failure, it needs to distinguish whether it's stopping
+ * a seq_file iteration which is fully initialized with an active reference
+ * or an aborted kernfs_seq_start() due to get_active failure. The
+ * position pointer is the only context for each seq_file iteration and
+ * thus the stop condition should be encoded in it. As the return value is
+ * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable
+ * choice to indicate get_active failure.
+ *
+ * Unfortunately, this is complicated due to the optional custom seq_file
+ * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop()
+ * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or
+ * custom seq_file operations and thus can't decide whether put_active
+ * should be performed or not only on ERR_PTR(-ENODEV).
+ *
+ * This is worked around by factoring out the custom seq_stop() and
+ * put_active part into kernfs_seq_stop_active(), skipping it from
+ * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after
+ * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures
+ * that kernfs_seq_stop_active() is skipped only after get_active failure.
+ */
+static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
+{
+ struct kernfs_open_file *of = sf->private;
+ const struct kernfs_ops *ops = kernfs_ops(of->kn);
+
+ if (ops->seq_stop)
+ ops->seq_stop(sf, v);
+ kernfs_put_active(of->kn);
+}
+
+static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
+{
+ struct kernfs_open_file *of = sf->private;
+ const struct kernfs_ops *ops;
+
+ /*
+ * @of->mutex nests outside active ref and is just to ensure that
+ * the ops aren't called concurrently for the same open file.
+ */
+ mutex_lock(&of->mutex);
+ if (!kernfs_get_active(of->kn))
+ return ERR_PTR(-ENODEV);
+
+ ops = kernfs_ops(of->kn);
+ if (ops->seq_start) {
+ void *next = ops->seq_start(sf, ppos);
+ /* see the comment above kernfs_seq_stop_active() */
+ if (next == ERR_PTR(-ENODEV))
+ kernfs_seq_stop_active(sf, next);
+ return next;
+ } else {
+ /*
+ * The same behavior and code as single_open(). Returns
+ * !NULL if pos is at the beginning; otherwise, NULL.
+ */
+ return NULL + !*ppos;
+ }
+}
+
+static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
+{
+ struct kernfs_open_file *of = sf->private;
+ const struct kernfs_ops *ops = kernfs_ops(of->kn);
+
+ if (ops->seq_next) {
+ void *next = ops->seq_next(sf, v, ppos);
+ /* see the comment above kernfs_seq_stop_active() */
+ if (next == ERR_PTR(-ENODEV))
+ kernfs_seq_stop_active(sf, next);
+ return next;
+ } else {
+ /*
+ * The same behavior and code as single_open(), always
+ * terminate after the initial read.
+ */
+ ++*ppos;
+ return NULL;
+ }
+}
+
+static void kernfs_seq_stop(struct seq_file *sf, void *v)
+{
+ struct kernfs_open_file *of = sf->private;
+
+ if (v != ERR_PTR(-ENODEV))
+ kernfs_seq_stop_active(sf, v);
+ mutex_unlock(&of->mutex);
+}
+
+static int kernfs_seq_show(struct seq_file *sf, void *v)
+{
+ struct kernfs_open_file *of = sf->private;
+
+ of->event = atomic_read(&of->kn->attr.open->event);
+
+ return of->kn->attr.ops->seq_show(sf, v);
+}
+
+static const struct seq_operations kernfs_seq_ops = {
+ .start = kernfs_seq_start,
+ .next = kernfs_seq_next,
+ .stop = kernfs_seq_stop,
+ .show = kernfs_seq_show,
+};
+
+/*
+ * As reading a bin file can have side-effects, the exact offset and bytes
+ * specified in read(2) call should be passed to the read callback making
+ * it difficult to use seq_file. Implement simplistic custom buffering for
+ * bin files.
+ */
+static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
+ char __user *user_buf, size_t count,
+ loff_t *ppos)
+{
+ ssize_t len = min_t(size_t, count, PAGE_SIZE);
+ const struct kernfs_ops *ops;
+ char *buf;
+
+ buf = kmalloc(len, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ /*
+ * @of->mutex nests outside active ref and is just to ensure that
+ * the ops aren't called concurrently for the same open file.
+ */
+ mutex_lock(&of->mutex);
+ if (!kernfs_get_active(of->kn)) {
+ len = -ENODEV;
+ mutex_unlock(&of->mutex);
+ goto out_free;
+ }
+
+ ops = kernfs_ops(of->kn);
+ if (ops->read)
+ len = ops->read(of, buf, len, *ppos);
+ else
+ len = -EINVAL;
+
+ kernfs_put_active(of->kn);
+ mutex_unlock(&of->mutex);
+
+ if (len < 0)
+ goto out_free;
+
+ if (copy_to_user(user_buf, buf, len)) {
+ len = -EFAULT;
+ goto out_free;
+ }
+
+ *ppos += len;
+
+ out_free:
+ kfree(buf);
+ return len;
+}
+
+/**
+ * kernfs_fop_read - kernfs vfs read callback
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ */
+static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct kernfs_open_file *of = kernfs_of(file);
+
+ if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
+ return seq_read(file, user_buf, count, ppos);
+ else
+ return kernfs_file_direct_read(of, user_buf, count, ppos);
+}
+
+/**
+ * kernfs_fop_write - kernfs vfs write callback
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ *
+ * Copy data in from userland and pass it to the matching kernfs write
+ * operation.
+ *
+ * There is no easy way for us to know if userspace is only doing a partial
+ * write, so we don't support them. We expect the entire buffer to come on
+ * the first write. Hint: if you're writing a value, first read the file,
+ * modify only the the value you're changing, then write entire buffer
+ * back.
+ */
+static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct kernfs_open_file *of = kernfs_of(file);
+ ssize_t len = min_t(size_t, count, PAGE_SIZE);
+ const struct kernfs_ops *ops;
+ char *buf;
+
+ buf = kmalloc(len + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, user_buf, len)) {
+ len = -EFAULT;
+ goto out_free;
+ }
+ buf[len] = '\0'; /* guarantee string termination */
+
+ /*
+ * @of->mutex nests outside active ref and is just to ensure that
+ * the ops aren't called concurrently for the same open file.
+ */
+ mutex_lock(&of->mutex);
+ if (!kernfs_get_active(of->kn)) {
+ mutex_unlock(&of->mutex);
+ len = -ENODEV;
+ goto out_free;
+ }
+
+ ops = kernfs_ops(of->kn);
+ if (ops->write)
+ len = ops->write(of, buf, len, *ppos);
+ else
+ len = -EINVAL;
+
+ kernfs_put_active(of->kn);