OpenCloudOS-Kernel/drivers/mtd/mtdcore.c

1340 lines
35 KiB
C
Raw Normal View History

/*
* Core registration and callback routines for MTD
* drivers and users.
*
* Copyright © 1999-2010 David Woodhouse <dwmw2@infradead.org>
* Copyright © 2006 Red Hat UK Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/ptrace.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/major.h>
#include <linux/fs.h>
#include <linux/err.h>
#include <linux/ioctl.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/idr.h>
#include <linux/backing-dev.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/reboot.h>
#include <linux/kconfig.h>
#include <linux/mtd/mtd.h>
#include <linux/mtd/partitions.h>
#include "mtdcore.h"
mtd: merge mtdchar module with mtdcore The MTD subsystem has historically tried to be as configurable as possible. The side-effect of this is that its configuration menu is rather large, and we are gradually shrinking it. For example, we recently merged partitions support with the mtdcore. This patch does the next step - it merges the mtdchar module to mtdcore. And in this case this is not only about eliminating too fine-grained separation and simplifying the configuration menu. This is also about eliminating seemingly useless kernel module. Indeed, mtdchar is a module that allows user-space making use of MTD devices via /dev/mtd* character devices. If users do not enable it, they simply cannot use MTD devices at all. They cannot read or write the flash contents. Is it a sane and useful setup? I believe not. And everyone just enables mtdchar. Having mtdchar separate is also a little bit harmful. People sometimes miss the fact that they need to enable an additional configuration option to have user-space MTD interfaces, and then they wonder why on earth the kernel does not allow using the flash? They spend time asking around. Thus, let's just get rid of this module and make it part of mtd core. Note, mtdchar had additional configuration option to enable OTP interfaces, which are present on some flashes. I removed that option as well - it saves a really tiny amount space. [dwmw2: Strictly speaking, you can mount file systems on MTD devices just fine without the mtdchar (or mtdblock) devices; you just can't do other manipulations directly on the underlying device. But still I agree that it makes sense to make this unconditional. And Yay! we get to kill off an instance of checking CONFIG_foo_MODULE, which is an abomination that should never happen.] Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2013-03-14 19:27:40 +08:00
static struct backing_dev_info mtd_bdi = {
};
#ifdef CONFIG_PM_SLEEP
static int mtd_cls_suspend(struct device *dev)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return mtd ? mtd_suspend(mtd) : 0;
}
static int mtd_cls_resume(struct device *dev)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
if (mtd)
mtd_resume(mtd);
return 0;
}
static SIMPLE_DEV_PM_OPS(mtd_cls_pm_ops, mtd_cls_suspend, mtd_cls_resume);
#define MTD_CLS_PM_OPS (&mtd_cls_pm_ops)
#else
#define MTD_CLS_PM_OPS NULL
#endif
static struct class mtd_class = {
.name = "mtd",
.owner = THIS_MODULE,
.pm = MTD_CLS_PM_OPS,
};
static DEFINE_IDR(mtd_idr);
/* These are exported solely for the purpose of mtd_blkdevs.c. You
should not use them for _anything_ else */
DEFINE_MUTEX(mtd_table_mutex);
EXPORT_SYMBOL_GPL(mtd_table_mutex);
struct mtd_info *__mtd_next_device(int i)
{
return idr_get_next(&mtd_idr, &i);
}
EXPORT_SYMBOL_GPL(__mtd_next_device);
static LIST_HEAD(mtd_notifiers);
#define MTD_DEVT(index) MKDEV(MTD_CHAR_MAJOR, (index)*2)
/* REVISIT once MTD uses the driver model better, whoever allocates
* the mtd_info will probably want to use the release() hook...
*/
static void mtd_release(struct device *dev)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
dev_t index = MTD_DEVT(mtd->index);
/* remove /dev/mtdXro node */
device_destroy(&mtd_class, index + 1);
}
static ssize_t mtd_type_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
char *type;
switch (mtd->type) {
case MTD_ABSENT:
type = "absent";
break;
case MTD_RAM:
type = "ram";
break;
case MTD_ROM:
type = "rom";
break;
case MTD_NORFLASH:
type = "nor";
break;
case MTD_NANDFLASH:
type = "nand";
break;
case MTD_DATAFLASH:
type = "dataflash";
break;
case MTD_UBIVOLUME:
type = "ubi";
break;
case MTD_MLCNANDFLASH:
type = "mlc-nand";
break;
default:
type = "unknown";
}
return snprintf(buf, PAGE_SIZE, "%s\n", type);
}
static DEVICE_ATTR(type, S_IRUGO, mtd_type_show, NULL);
static ssize_t mtd_flags_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "0x%lx\n", (unsigned long)mtd->flags);
}
static DEVICE_ATTR(flags, S_IRUGO, mtd_flags_show, NULL);
static ssize_t mtd_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)mtd->size);
}
static DEVICE_ATTR(size, S_IRUGO, mtd_size_show, NULL);
static ssize_t mtd_erasesize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%lu\n", (unsigned long)mtd->erasesize);
}
static DEVICE_ATTR(erasesize, S_IRUGO, mtd_erasesize_show, NULL);
static ssize_t mtd_writesize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%lu\n", (unsigned long)mtd->writesize);
}
static DEVICE_ATTR(writesize, S_IRUGO, mtd_writesize_show, NULL);
static ssize_t mtd_subpagesize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
unsigned int subpagesize = mtd->writesize >> mtd->subpage_sft;
return snprintf(buf, PAGE_SIZE, "%u\n", subpagesize);
}
static DEVICE_ATTR(subpagesize, S_IRUGO, mtd_subpagesize_show, NULL);
static ssize_t mtd_oobsize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%lu\n", (unsigned long)mtd->oobsize);
}
static DEVICE_ATTR(oobsize, S_IRUGO, mtd_oobsize_show, NULL);
static ssize_t mtd_numeraseregions_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%u\n", mtd->numeraseregions);
}
static DEVICE_ATTR(numeraseregions, S_IRUGO, mtd_numeraseregions_show,
NULL);
static ssize_t mtd_name_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%s\n", mtd->name);
}
static DEVICE_ATTR(name, S_IRUGO, mtd_name_show, NULL);
static ssize_t mtd_ecc_strength_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%u\n", mtd->ecc_strength);
}
static DEVICE_ATTR(ecc_strength, S_IRUGO, mtd_ecc_strength_show, NULL);
static ssize_t mtd_bitflip_threshold_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%u\n", mtd->bitflip_threshold);
}
static ssize_t mtd_bitflip_threshold_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
unsigned int bitflip_threshold;
int retval;
retval = kstrtouint(buf, 0, &bitflip_threshold);
if (retval)
return retval;
mtd->bitflip_threshold = bitflip_threshold;
return count;
}
static DEVICE_ATTR(bitflip_threshold, S_IRUGO | S_IWUSR,
mtd_bitflip_threshold_show,
mtd_bitflip_threshold_store);
static ssize_t mtd_ecc_step_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
return snprintf(buf, PAGE_SIZE, "%u\n", mtd->ecc_step_size);
}
static DEVICE_ATTR(ecc_step_size, S_IRUGO, mtd_ecc_step_size_show, NULL);
static ssize_t mtd_ecc_stats_corrected_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats;
return snprintf(buf, PAGE_SIZE, "%u\n", ecc_stats->corrected);
}
static DEVICE_ATTR(corrected_bits, S_IRUGO,
mtd_ecc_stats_corrected_show, NULL);
static ssize_t mtd_ecc_stats_errors_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats;
return snprintf(buf, PAGE_SIZE, "%u\n", ecc_stats->failed);
}
static DEVICE_ATTR(ecc_failures, S_IRUGO, mtd_ecc_stats_errors_show, NULL);
static ssize_t mtd_badblocks_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats;
return snprintf(buf, PAGE_SIZE, "%u\n", ecc_stats->badblocks);
}
static DEVICE_ATTR(bad_blocks, S_IRUGO, mtd_badblocks_show, NULL);
static ssize_t mtd_bbtblocks_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct mtd_info *mtd = dev_get_drvdata(dev);
struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats;
return snprintf(buf, PAGE_SIZE, "%u\n", ecc_stats->bbtblocks);
}
static DEVICE_ATTR(bbt_blocks, S_IRUGO, mtd_bbtblocks_show, NULL);
static struct attribute *mtd_attrs[] = {
&dev_attr_type.attr,
&dev_attr_flags.attr,
&dev_attr_size.attr,
&dev_attr_erasesize.attr,
&dev_attr_writesize.attr,
&dev_attr_subpagesize.attr,
&dev_attr_oobsize.attr,
&dev_attr_numeraseregions.attr,
&dev_attr_name.attr,
&dev_attr_ecc_strength.attr,
&dev_attr_ecc_step_size.attr,
&dev_attr_corrected_bits.attr,
&dev_attr_ecc_failures.attr,
&dev_attr_bad_blocks.attr,
&dev_attr_bbt_blocks.attr,
&dev_attr_bitflip_threshold.attr,
NULL,
};
ATTRIBUTE_GROUPS(mtd);
static struct device_type mtd_devtype = {
.name = "mtd",
.groups = mtd_groups,
.release = mtd_release,
};
#ifndef CONFIG_MMU
unsigned mtd_mmap_capabilities(struct mtd_info *mtd)
{
switch (mtd->type) {
case MTD_RAM:
return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
NOMMU_MAP_READ | NOMMU_MAP_WRITE;
case MTD_ROM:
return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
NOMMU_MAP_READ;
default:
return NOMMU_MAP_COPY;
}
}
EXPORT_SYMBOL_GPL(mtd_mmap_capabilities);
#endif
static int mtd_reboot_notifier(struct notifier_block *n, unsigned long state,
void *cmd)
{
struct mtd_info *mtd;
mtd = container_of(n, struct mtd_info, reboot_notifier);
mtd->_reboot(mtd);
return NOTIFY_DONE;
}
/**
* add_mtd_device - register an MTD device
* @mtd: pointer to new MTD device info structure
*
* Add a device to the list of MTD devices present in the system, and
* notify each currently active MTD 'user' of its arrival. Returns
* zero on success or non-zero on failure.
*/
int add_mtd_device(struct mtd_info *mtd)
{
struct mtd_notifier *not;
int i, error;
/*
* May occur, for instance, on buggy drivers which call
* mtd_device_parse_register() multiple times on the same master MTD,
* especially with CONFIG_MTD_PARTITIONED_MASTER=y.
*/
if (WARN_ONCE(mtd->backing_dev_info, "MTD already registered\n"))
return -EEXIST;
mtd->backing_dev_info = &mtd_bdi;
BUG_ON(mtd->writesize == 0);
mutex_lock(&mtd_table_mutex);
i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
if (i < 0) {
error = i;
goto fail_locked;
}
mtd->index = i;
mtd->usecount = 0;
/* default value if not set by driver */
if (mtd->bitflip_threshold == 0)
mtd->bitflip_threshold = mtd->ecc_strength;
if (is_power_of_2(mtd->erasesize))
mtd->erasesize_shift = ffs(mtd->erasesize) - 1;
else
mtd->erasesize_shift = 0;
if (is_power_of_2(mtd->writesize))
mtd->writesize_shift = ffs(mtd->writesize) - 1;
else
mtd->writesize_shift = 0;
mtd->erasesize_mask = (1 << mtd->erasesize_shift) - 1;
mtd->writesize_mask = (1 << mtd->writesize_shift) - 1;
if (mtd->dev.parent) {
if (!mtd->owner && mtd->dev.parent->driver)
mtd->owner = mtd->dev.parent->driver->owner;
if (!mtd->name)
mtd->name = dev_name(mtd->dev.parent);
} else {
pr_debug("mtd device won't show a device symlink in sysfs\n");
}
/* Some chips always power up locked. Unlock them now */
if ((mtd->flags & MTD_WRITEABLE) && (mtd->flags & MTD_POWERUP_LOCK)) {
error = mtd_unlock(mtd, 0, mtd->size);
if (error && error != -EOPNOTSUPP)
printk(KERN_WARNING
"%s: unlock failed, writes may not work\n",
mtd->name);
/* Ignore unlock failures? */
error = 0;
}
/* Caller should have set dev.parent to match the
* physical device, if appropriate.
*/
mtd->dev.type = &mtd_devtype;
mtd->dev.class = &mtd_class;
mtd->dev.devt = MTD_DEVT(i);
dev_set_name(&mtd->dev, "mtd%d", i);
dev_set_drvdata(&mtd->dev, mtd);
error = device_register(&mtd->dev);
if (error)
goto fail_added;
device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
"mtd%dro", i);
pr_debug("mtd: Giving out device %d to %s\n", i, mtd->name);
/* No need to get a refcount on the module containing
the notifier, since we hold the mtd_table_mutex */
list_for_each_entry(not, &mtd_notifiers, list)
not->add(mtd);
mutex_unlock(&mtd_table_mutex);
/* We _know_ we aren't being removed, because
our caller is still holding us here. So none
of this try_ nonsense, and no bitching about it
either. :) */
__module_get(THIS_MODULE);
return 0;
fail_added:
idr_remove(&mtd_idr, i);
fail_locked:
mutex_unlock(&mtd_table_mutex);
return error;
}
/**
* del_mtd_device - unregister an MTD device
* @mtd: pointer to MTD device info structure
*
* Remove a device from the list of MTD devices present in the system,
* and notify each currently active MTD 'user' of its departure.
* Returns zero on success or 1 on failure, which currently will happen
* if the requested device does not appear to be present in the list.
*/
int del_mtd_device(struct mtd_info *mtd)
{
int ret;
struct mtd_notifier *not;
mutex_lock(&mtd_table_mutex);
if (idr_find(&mtd_idr, mtd->index) != mtd) {
ret = -ENODEV;
goto out_error;
}
/* No need to get a refcount on the module containing
the notifier, since we hold the mtd_table_mutex */
list_for_each_entry(not, &mtd_notifiers, list)
not->remove(mtd);
if (mtd->usecount) {
printk(KERN_NOTICE "Removing MTD device #%d (%s) with use count %d\n",
mtd->index, mtd->name, mtd->usecount);
ret = -EBUSY;
} else {
device_unregister(&mtd->dev);
idr_remove(&mtd_idr, mtd->index);
module_put(THIS_MODULE);
ret = 0;
}
out_error:
mutex_unlock(&mtd_table_mutex);
return ret;
}
static int mtd_add_device_partitions(struct mtd_info *mtd,
struct mtd_partition *real_parts,
int nbparts)
{
int ret;
if (nbparts == 0 || IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) {
ret = add_mtd_device(mtd);
if (ret)
return ret;
}
if (nbparts > 0) {
ret = add_mtd_partitions(mtd, real_parts, nbparts);
if (ret && IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
del_mtd_device(mtd);
return ret;
}
return 0;
}
/**
* mtd_device_parse_register - parse partitions and register an MTD device.
*
* @mtd: the MTD device to register
* @types: the list of MTD partition probes to try, see
* 'parse_mtd_partitions()' for more information
* @parser_data: MTD partition parser-specific data
* @parts: fallback partition information to register, if parsing fails;
* only valid if %nr_parts > %0
* @nr_parts: the number of partitions in parts, if zero then the full
* MTD device is registered if no partition info is found
*
* This function aggregates MTD partitions parsing (done by
* 'parse_mtd_partitions()') and MTD device and partitions registering. It
* basically follows the most common pattern found in many MTD drivers:
*
* * It first tries to probe partitions on MTD device @mtd using parsers
* specified in @types (if @types is %NULL, then the default list of parsers
* is used, see 'parse_mtd_partitions()' for more information). If none are
* found this functions tries to fallback to information specified in
* @parts/@nr_parts.
* * If any partitioning info was found, this function registers the found
* partitions. If the MTD_PARTITIONED_MASTER option is set, then the device
* as a whole is registered first.
* * If no partitions were found this function just registers the MTD device
* @mtd and exits.
*
* Returns zero in case of success and a negative error code in case of failure.
*/
int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
struct mtd_part_parser_data *parser_data,
const struct mtd_partition *parts,
int nr_parts)
{
int ret;
struct mtd_partition *real_parts = NULL;
ret = parse_mtd_partitions(mtd, types, &real_parts, parser_data);
if (ret <= 0 && nr_parts && parts) {
real_parts = kmemdup(parts, sizeof(*parts) * nr_parts,
GFP_KERNEL);
if (!real_parts)
ret = -ENOMEM;
else
ret = nr_parts;
}
/* Didn't come up with either parsed OR fallback partitions */
if (ret < 0) {
pr_info("mtd: failed to find partitions; one or more parsers reports errors (%d)\n",
ret);
/* Don't abort on errors; we can still use unpartitioned MTD */
ret = 0;
}
ret = mtd_add_device_partitions(mtd, real_parts, ret);
if (ret)
goto out;
/*
* FIXME: some drivers unfortunately call this function more than once.
* So we have to check if we've already assigned the reboot notifier.
*
* Generally, we can make multiple calls work for most cases, but it
* does cause problems with parse_mtd_partitions() above (e.g.,
* cmdlineparts will register partitions more than once).
*/
mtd: don't WARN about overloaded users of mtd->reboot_notifier.notifier_call There are multiple types of users of mtd->reboot_notifier.notifier_call: (1) A while back, the cfi_cmdset_000{1,2} chip drivers implemented a reboot notifier to (on a best effort basis) attempt to reset their flash chips before rebooting. (2) More recently, we implemented a common _reboot() hook so that MTD drivers (particularly, NAND flash) could better halt I/O operations without having to reimplement the same notifier boilerplate. Currently, the WARN_ONCE() condition here was written to handle (2), but at the same time it mis-diagnosed case (1) as an already-registered MTD. Let's fix this by having the WARN_ONCE() condition better imitate the condition that immediately follows it. (Wow, I don't know how I missed that one.) (Side note: Unfortunately, we can't yet combine the reboot notifier code for (1) and (2) with a patch like [1], because some users of (1) also use mtdconcat, and so the mtd_info struct from cfi_cmdset_000{1,2} won't actually get registered with mtdcore, and therefore their reboot notifier won't get registered.) [1] http://patchwork.ozlabs.org/patch/417981/ Suggested-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Brian Norris <computersforpeace@gmail.com> Cc: Jesper Nilsson <jespern@axis.com> Cc: linux-cris-kernel@axis.com Tested-by: Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> Tested-by: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Brian Norris <computersforpeace@gmail.com>
2015-11-04 09:01:53 +08:00
WARN_ONCE(mtd->_reboot && mtd->reboot_notifier.notifier_call,
"MTD already registered\n");
if (mtd->_reboot && !mtd->reboot_notifier.notifier_call) {
mtd->reboot_notifier.notifier_call = mtd_reboot_notifier;
register_reboot_notifier(&mtd->reboot_notifier);
}
out:
kfree(real_parts);
return ret;
}
EXPORT_SYMBOL_GPL(mtd_device_parse_register);
/**
* mtd_device_unregister - unregister an existing MTD device.
*
* @master: the MTD device to unregister. This will unregister both the master
* and any partitions if registered.
*/
int mtd_device_unregister(struct mtd_info *master)
{
int err;
if (master->_reboot)
unregister_reboot_notifier(&master->reboot_notifier);
err = del_mtd_partitions(master);
if (err)
return err;
if (!device_is_registered(&master->dev))
return 0;
return del_mtd_device(master);
}
EXPORT_SYMBOL_GPL(mtd_device_unregister);
/**
* register_mtd_user - register a 'user' of MTD devices.
* @new: pointer to notifier info structure
*
* Registers a pair of callbacks function to be called upon addition
* or removal of MTD devices. Causes the 'add' callback to be immediately
* invoked for each MTD device currently present in the system.
*/
void register_mtd_user (struct mtd_notifier *new)
{
struct mtd_info *mtd;
mutex_lock(&mtd_table_mutex);
list_add(&new->list, &mtd_notifiers);
__module_get(THIS_MODULE);
mtd_for_each_device(mtd)
new->add(mtd);
mutex_unlock(&mtd_table_mutex);
}
EXPORT_SYMBOL_GPL(register_mtd_user);
/**
* unregister_mtd_user - unregister a 'user' of MTD devices.
* @old: pointer to notifier info structure
*
* Removes a callback function pair from the list of 'users' to be
* notified upon addition or removal of MTD devices. Causes the
* 'remove' callback to be immediately invoked for each MTD device
* currently present in the system.
*/
int unregister_mtd_user (struct mtd_notifier *old)
{
struct mtd_info *mtd;
mutex_lock(&mtd_table_mutex);
module_put(THIS_MODULE);
mtd_for_each_device(mtd)
old->remove(mtd);
list_del(&old->list);
mutex_unlock(&mtd_table_mutex);
return 0;
}
EXPORT_SYMBOL_GPL(unregister_mtd_user);
/**
* get_mtd_device - obtain a validated handle for an MTD device
* @mtd: last known address of the required MTD device
* @num: internal device number of the required MTD device
*
* Given a number and NULL address, return the num'th entry in the device
* table, if any. Given an address and num == -1, search the device table
* for a device with that address and return if it's still present. Given
* both, return the num'th driver only if its address matches. Return
* error code if not.
*/
struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num)
{
struct mtd_info *ret = NULL, *other;
int err = -ENODEV;
mutex_lock(&mtd_table_mutex);
if (num == -1) {
mtd_for_each_device(other) {
if (other == mtd) {
ret = mtd;
break;
}
}
} else if (num >= 0) {
ret = idr_find(&mtd_idr, num);
if (mtd && mtd != ret)
ret = NULL;
}
if (!ret) {
ret = ERR_PTR(err);
goto out;
}
err = __get_mtd_device(ret);
if (err)
ret = ERR_PTR(err);
out:
mutex_unlock(&mtd_table_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(get_mtd_device);
int __get_mtd_device(struct mtd_info *mtd)
{
int err;
if (!try_module_get(mtd->owner))
return -ENODEV;
if (mtd->_get_device) {
err = mtd->_get_device(mtd);
if (err) {
module_put(mtd->owner);
return err;
}
}
mtd->usecount++;
return 0;
}
EXPORT_SYMBOL_GPL(__get_mtd_device);
/**
* get_mtd_device_nm - obtain a validated handle for an MTD device by
* device name
* @name: MTD device name to open
*
* This function returns MTD device description structure in case of
* success and an error code in case of failure.
*/
struct mtd_info *get_mtd_device_nm(const char *name)
{
int err = -ENODEV;
struct mtd_info *mtd = NULL, *other;
mutex_lock(&mtd_table_mutex);
mtd_for_each_device(other) {
if (!strcmp(name, other->name)) {
mtd = other;
break;
}
}
if (!mtd)
goto out_unlock;
err = __get_mtd_device(mtd);
if (err)
goto out_unlock;
mutex_unlock(&mtd_table_mutex);
return mtd;
out_unlock:
mutex_unlock(&mtd_table_mutex);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(get_mtd_device_nm);
void put_mtd_device(struct mtd_info *mtd)
{
mutex_lock(&mtd_table_mutex);
__put_mtd_device(mtd);
mutex_unlock(&mtd_table_mutex);
}
EXPORT_SYMBOL_GPL(put_mtd_device);
void __put_mtd_device(struct mtd_info *mtd)
{
--mtd->usecount;
BUG_ON(mtd->usecount < 0);
if (mtd->_put_device)
mtd->_put_device(mtd);
module_put(mtd->owner);
}
EXPORT_SYMBOL_GPL(__put_mtd_device);
/*
* Erase is an asynchronous operation. Device drivers are supposed
* to call instr->callback() whenever the operation completes, even
* if it completes with a failure.
* Callers are supposed to pass a callback function and wait for it
* to be called before writing to the block.
*/
int mtd_erase(struct mtd_info *mtd, struct erase_info *instr)
{
if (instr->addr >= mtd->size || instr->len > mtd->size - instr->addr)
return -EINVAL;
if (!(mtd->flags & MTD_WRITEABLE))
return -EROFS;
instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
if (!instr->len) {
instr->state = MTD_ERASE_DONE;
mtd_erase_callback(instr);
return 0;
}
return mtd->_erase(mtd, instr);
}
EXPORT_SYMBOL_GPL(mtd_erase);
/*
* This stuff for eXecute-In-Place. phys is optional and may be set to NULL.
*/
int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
void **virt, resource_size_t *phys)
{
*retlen = 0;
*virt = NULL;
if (phys)
*phys = 0;
if (!mtd->_point)
return -EOPNOTSUPP;
if (from < 0 || from >= mtd->size || len > mtd->size - from)
return -EINVAL;
if (!len)
return 0;
return mtd->_point(mtd, from, len, retlen, virt, phys);
}
EXPORT_SYMBOL_GPL(mtd_point);
/* We probably shouldn't allow XIP if the unpoint isn't a NULL */
int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
{
if (!mtd->_point)
return -EOPNOTSUPP;
if (from < 0 || from >= mtd->size || len > mtd->size - from)
return -EINVAL;
if (!len)
return 0;
return mtd->_unpoint(mtd, from, len);
}
EXPORT_SYMBOL_GPL(mtd_unpoint);
/*
* Allow NOMMU mmap() to directly map the device (if not NULL)
* - return the address to which the offset maps
* - return -ENOSYS to indicate refusal to do the mapping
*/
unsigned long mtd_get_unmapped_area(struct mtd_info *mtd, unsigned long len,
unsigned long offset, unsigned long flags)
{
if (!mtd->_get_unmapped_area)
return -EOPNOTSUPP;
if (offset >= mtd->size || len > mtd->size - offset)
return -EINVAL;
return mtd->_get_unmapped_area(mtd, len, offset, flags);
}
EXPORT_SYMBOL_GPL(mtd_get_unmapped_area);
int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen,
u_char *buf)
{
int ret_code;
*retlen = 0;
if (from < 0 || from >= mtd->size || len > mtd->size - from)
return -EINVAL;
if (!len)
return 0;
/*
* In the absence of an error, drivers return a non-negative integer
* representing the maximum number of bitflips that were corrected on
* any one ecc region (if applicable; zero otherwise).
*/
ret_code = mtd->_read(mtd, from, len, retlen, buf);
if (unlikely(ret_code < 0))
return ret_code;
if (mtd->ecc_strength == 0)
return 0; /* device lacks ecc */
return ret_code >= mtd->bitflip_threshold ? -EUCLEAN : 0;
}
EXPORT_SYMBOL_GPL(mtd_read);
int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
const u_char *buf)
{
*retlen = 0;
if (to < 0 || to >= mtd->size || len > mtd->size - to)
return -EINVAL;
if (!mtd->_write || !(mtd->flags & MTD_WRITEABLE))
return -EROFS;
if (!len)
return 0;
return mtd->_write(mtd, to, len, retlen, buf);
}
EXPORT_SYMBOL_GPL(mtd_write);
/*
* In blackbox flight recorder like scenarios we want to make successful writes
* in interrupt context. panic_write() is only intended to be called when its
* known the kernel is about to panic and we need the write to succeed. Since
* the kernel is not going to be running for much longer, this function can
* break locks and delay to ensure the write succeeds (but not sleep).
*/
int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen,
const u_char *buf)
{
*retlen = 0;
if (!mtd->_panic_write)
return -EOPNOTSUPP;
if (to < 0 || to >= mtd->size || len > mtd->size - to)
return -EINVAL;
if (!(mtd->flags & MTD_WRITEABLE))
return -EROFS;
if (!len)
return 0;
return mtd->_panic_write(mtd, to, len, retlen, buf);
}
EXPORT_SYMBOL_GPL(mtd_panic_write);
int mtd_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops)
{
int ret_code;
ops->retlen = ops->oobretlen = 0;
if (!mtd->_read_oob)
return -EOPNOTSUPP;
/*
* In cases where ops->datbuf != NULL, mtd->_read_oob() has semantics
* similar to mtd->_read(), returning a non-negative integer
* representing max bitflips. In other cases, mtd->_read_oob() may
* return -EUCLEAN. In all cases, perform similar logic to mtd_read().
*/
ret_code = mtd->_read_oob(mtd, from, ops);
if (unlikely(ret_code < 0))
return ret_code;
if (mtd->ecc_strength == 0)
return 0; /* device lacks ecc */
return ret_code >= mtd->bitflip_threshold ? -EUCLEAN : 0;
}
EXPORT_SYMBOL_GPL(mtd_read_oob);
/*
* Method to access the protection register area, present in some flash
* devices. The user data is one time programmable but the factory data is read
* only.
*/
int mtd_get_fact_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen,
struct otp_info *buf)
{
if (!mtd->_get_fact_prot_info)
return -EOPNOTSUPP;
if (!len)
return 0;
return mtd->_get_fact_prot_info(mtd, len, retlen, buf);
}
EXPORT_SYMBOL_GPL(mtd_get_fact_prot_info);
int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
size_t *retlen, u_char *buf)
{
*retlen = 0;
if (!mtd->_read_fact_prot_reg)
return -EOPNOTSUPP;
if (!len)
return 0;
return mtd->_read_fact_prot_reg(mtd, from, len, retlen, buf);
}
EXPORT_SYMBOL_GPL(mtd_read_fact_prot_reg);
int mtd_get_user_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen,
struct otp_info *buf)
{
if (!mtd->_get_user_prot_info)
return -EOPNOTSUPP;
if (!len)
return 0;
return mtd->_get_user_prot_info(mtd, len, retlen, buf);
}
EXPORT_SYMBOL_GPL(mtd_get_user_prot_info);
int mtd_read_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
size_t *retlen, u_char *buf)
{
*retlen = 0;
if (!mtd->_read_user_prot_reg)
return -EOPNOTSUPP;
if (!len)
return 0;
return mtd->_read_user_prot_reg(mtd, from, len, retlen, buf);
}
EXPORT_SYMBOL_GPL(mtd_read_user_prot_reg);
int mtd_write_user_prot_reg(struct mtd_info *mtd, loff_t to, size_t len,
size_t *retlen, u_char *buf)
{
mtd: Fix the behavior of OTP write if there is not enough room for data If a write to one time programmable memory (OTP) hits the end of this memory area, no more data can be written. The count variable in mtdchar_write() in drivers/mtd/mtdchar.c is not decreased anymore. We are trapped in the loop forever, mtdchar_write() will never return in this case. The desired behavior of a write in such a case is described in [1]: - Try to write as much data as possible, truncate the write to fit into the available memory and return the number of bytes that actually have been written. - If no data could be written at all, return -ENOSPC. This patch fixes the behavior of OTP write if there is not enough space for all data: 1) mtd_write_user_prot_reg() in drivers/mtd/mtdcore.c is modified to return -ENOSPC if no data could be written at all. 2) mtdchar_write() is modified to handle -ENOSPC correctly. Exit if a write returned -ENOSPC and yield the correct return value, either then number of bytes that could be written, or -ENOSPC, if no data could be written at all. Furthermore the patch harmonizes the behavior of the OTP memory write in drivers/mtd/devices/mtd_dataflash.c with the other implementations and the requirements from [1]. Instead of returning -EINVAL if the data does not fit into the OTP memory, we try to write as much data as possible/truncate the write. [1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/write.html Signed-off-by: Christian Riesch <christian.riesch@omicron.at> Signed-off-by: Brian Norris <computersforpeace@gmail.com>
2014-03-06 19:42:37 +08:00
int ret;
*retlen = 0;
if (!mtd->_write_user_prot_reg)
return -EOPNOTSUPP;
if (!len)
return 0;
mtd: Fix the behavior of OTP write if there is not enough room for data If a write to one time programmable memory (OTP) hits the end of this memory area, no more data can be written. The count variable in mtdchar_write() in drivers/mtd/mtdchar.c is not decreased anymore. We are trapped in the loop forever, mtdchar_write() will never return in this case. The desired behavior of a write in such a case is described in [1]: - Try to write as much data as possible, truncate the write to fit into the available memory and return the number of bytes that actually have been written. - If no data could be written at all, return -ENOSPC. This patch fixes the behavior of OTP write if there is not enough space for all data: 1) mtd_write_user_prot_reg() in drivers/mtd/mtdcore.c is modified to return -ENOSPC if no data could be written at all. 2) mtdchar_write() is modified to handle -ENOSPC correctly. Exit if a write returned -ENOSPC and yield the correct return value, either then number of bytes that could be written, or -ENOSPC, if no data could be written at all. Furthermore the patch harmonizes the behavior of the OTP memory write in drivers/mtd/devices/mtd_dataflash.c with the other implementations and the requirements from [1]. Instead of returning -EINVAL if the data does not fit into the OTP memory, we try to write as much data as possible/truncate the write. [1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/write.html Signed-off-by: Christian Riesch <christian.riesch@omicron.at> Signed-off-by: Brian Norris <computersforpeace@gmail.com>
2014-03-06 19:42:37 +08:00
ret = mtd->_write_user_prot_reg(mtd, to, len, retlen, buf);
if (ret)
return ret;
/*
* If no data could be written at all, we are out of memory and
* must return -ENOSPC.
*/
return (*retlen) ? 0 : -ENOSPC;
}
EXPORT_SYMBOL_GPL(mtd_write_user_prot_reg);
int mtd_lock_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len)
{
if (!mtd->_lock_user_prot_reg)
return -EOPNOTSUPP;
if (!len)
return 0;
return mtd->_lock_user_prot_reg(mtd, from, len);
}
EXPORT_SYMBOL_GPL(mtd_lock_user_prot_reg);
/* Chip-supported device locking */
int mtd_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
{
if (!mtd->_lock)
return -EOPNOTSUPP;
if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs)
return -EINVAL;
if (!len)
return 0;
return mtd->_lock(mtd, ofs, len);
}
EXPORT_SYMBOL_GPL(mtd_lock);
int mtd_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
{
if (!mtd->_unlock)
return -EOPNOTSUPP;
if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs)
return -EINVAL;
if (!len)
return 0;
return mtd->_unlock(mtd, ofs, len);
}
EXPORT_SYMBOL_GPL(mtd_unlock);
int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
{
if (!mtd->_is_locked)
return -EOPNOTSUPP;
if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs)
return -EINVAL;
if (!len)
return 0;
return mtd->_is_locked(mtd, ofs, len);
}
EXPORT_SYMBOL_GPL(mtd_is_locked);
int mtd_block_isreserved(struct mtd_info *mtd, loff_t ofs)
{
if (ofs < 0 || ofs >= mtd->size)
return -EINVAL;
if (!mtd->_block_isreserved)
return 0;
return mtd->_block_isreserved(mtd, ofs);
}
EXPORT_SYMBOL_GPL(mtd_block_isreserved);
int mtd_block_isbad(struct mtd_info *mtd, loff_t ofs)
{
if (ofs < 0 || ofs >= mtd->size)
return -EINVAL;
if (!mtd->_block_isbad)
return 0;
return mtd->_block_isbad(mtd, ofs);
}
EXPORT_SYMBOL_GPL(mtd_block_isbad);
int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs)
{
if (!mtd->_block_markbad)
return -EOPNOTSUPP;
if (ofs < 0 || ofs >= mtd->size)
return -EINVAL;
if (!(mtd->flags & MTD_WRITEABLE))
return -EROFS;
return mtd->_block_markbad(mtd, ofs);
}
EXPORT_SYMBOL_GPL(mtd_block_markbad);
/*
* default_mtd_writev - the default writev method
* @mtd: mtd device description object pointer
* @vecs: the vectors to write
* @count: count of vectors in @vecs
* @to: the MTD device offset to write to
* @retlen: on exit contains the count of bytes written to the MTD device.
*
* This function returns zero in case of success and a negative error code in
* case of failure.
*/
static int default_mtd_writev(struct mtd_info *mtd, const struct kvec *vecs,
unsigned long count, loff_t to, size_t *retlen)
{
unsigned long i;
size_t totlen = 0, thislen;
int ret = 0;
for (i = 0; i < count; i++) {
if (!vecs[i].iov_len)
continue;
ret = mtd_write(mtd, to, vecs[i].iov_len, &thislen,
vecs[i].iov_base);
totlen += thislen;
if (ret || thislen != vecs[i].iov_len)
break;
to += vecs[i].iov_len;
}
*retlen = totlen;
return ret;
}
/*
* mtd_writev - the vector-based MTD write method
* @mtd: mtd device description object pointer
* @vecs: the vectors to write
* @count: count of vectors in @vecs
* @to: the MTD device offset to write to
* @retlen: on exit contains the count of bytes written to the MTD device.
*
* This function returns zero in case of success and a negative error code in
* case of failure.
*/
int mtd_writev(struct mtd_info *mtd, const struct kvec *vecs,
unsigned long count, loff_t to, size_t *retlen)
{
*retlen = 0;
if (!(mtd->flags & MTD_WRITEABLE))
return -EROFS;
if (!mtd->_writev)
return default_mtd_writev(mtd, vecs, count, to, retlen);
return mtd->_writev(mtd, vecs, count, to, retlen);
}
EXPORT_SYMBOL_GPL(mtd_writev);
mtd: create function to perform large allocations Introduce a common function to handle large, contiguous kmalloc buffer allocations by exponentially backing off on the size of the requested kernel transfer buffer until it succeeds or until the requested transfer buffer size falls below the page size. This helps ensure the operation can succeed under low-memory, highly- fragmented situations albeit somewhat more slowly. Artem: so this patch solves the problem that the kernel tries to kmalloc too large buffers, which (a) may fail and does fail - people complain about this, and (b) slows down the system in case of high memory fragmentation, because the kernel starts dropping caches, writing back, swapping, etc. But we do not really have to allocate a lot of memory to do the I/O, we may do this even with as little as one min. I/O unit (NAND page) of RAM. So the idea of this patch is that if the user asks to read or write a lot, we try to kmalloc a lot, with GFP flags which make the kernel _not_ drop caches, etc. If we can allocate it - good, if not - we try to allocate twice as less, and so on, until we reach the min. I/O unit size, which is our last resort allocation and use the normal GFP_KERNEL flag. Artem: re-write the allocation function so that it makes sure the allocated buffer is aligned to the min. I/O size of the flash. Signed-off-by: Grant Erickson <marathon96@gmail.com> Tested-by: Ben Gardiner <bengardiner@nanometrics.ca> Tested-by: Stefano Babic <sbabic@denx.de> Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2011-04-08 23:51:32 +08:00
/**
* mtd_kmalloc_up_to - allocate a contiguous buffer up to the specified size
* @mtd: mtd device description object pointer
* @size: a pointer to the ideal or maximum size of the allocation, points
mtd: create function to perform large allocations Introduce a common function to handle large, contiguous kmalloc buffer allocations by exponentially backing off on the size of the requested kernel transfer buffer until it succeeds or until the requested transfer buffer size falls below the page size. This helps ensure the operation can succeed under low-memory, highly- fragmented situations albeit somewhat more slowly. Artem: so this patch solves the problem that the kernel tries to kmalloc too large buffers, which (a) may fail and does fail - people complain about this, and (b) slows down the system in case of high memory fragmentation, because the kernel starts dropping caches, writing back, swapping, etc. But we do not really have to allocate a lot of memory to do the I/O, we may do this even with as little as one min. I/O unit (NAND page) of RAM. So the idea of this patch is that if the user asks to read or write a lot, we try to kmalloc a lot, with GFP flags which make the kernel _not_ drop caches, etc. If we can allocate it - good, if not - we try to allocate twice as less, and so on, until we reach the min. I/O unit size, which is our last resort allocation and use the normal GFP_KERNEL flag. Artem: re-write the allocation function so that it makes sure the allocated buffer is aligned to the min. I/O size of the flash. Signed-off-by: Grant Erickson <marathon96@gmail.com> Tested-by: Ben Gardiner <bengardiner@nanometrics.ca> Tested-by: Stefano Babic <sbabic@denx.de> Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2011-04-08 23:51:32 +08:00
* to the actual allocation size on success.
*
* This routine attempts to allocate a contiguous kernel buffer up to
* the specified size, backing off the size of the request exponentially
* until the request succeeds or until the allocation size falls below
* the system page size. This attempts to make sure it does not adversely
* impact system performance, so when allocating more than one page, we
* ask the memory allocator to avoid re-trying, swapping, writing back
* or performing I/O.
mtd: create function to perform large allocations Introduce a common function to handle large, contiguous kmalloc buffer allocations by exponentially backing off on the size of the requested kernel transfer buffer until it succeeds or until the requested transfer buffer size falls below the page size. This helps ensure the operation can succeed under low-memory, highly- fragmented situations albeit somewhat more slowly. Artem: so this patch solves the problem that the kernel tries to kmalloc too large buffers, which (a) may fail and does fail - people complain about this, and (b) slows down the system in case of high memory fragmentation, because the kernel starts dropping caches, writing back, swapping, etc. But we do not really have to allocate a lot of memory to do the I/O, we may do this even with as little as one min. I/O unit (NAND page) of RAM. So the idea of this patch is that if the user asks to read or write a lot, we try to kmalloc a lot, with GFP flags which make the kernel _not_ drop caches, etc. If we can allocate it - good, if not - we try to allocate twice as less, and so on, until we reach the min. I/O unit size, which is our last resort allocation and use the normal GFP_KERNEL flag. Artem: re-write the allocation function so that it makes sure the allocated buffer is aligned to the min. I/O size of the flash. Signed-off-by: Grant Erickson <marathon96@gmail.com> Tested-by: Ben Gardiner <bengardiner@nanometrics.ca> Tested-by: Stefano Babic <sbabic@denx.de> Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2011-04-08 23:51:32 +08:00
*
* Note, this function also makes sure that the allocated buffer is aligned to
* the MTD device's min. I/O unit, i.e. the "mtd->writesize" value.
*
* This is called, for example by mtd_{read,write} and jffs2_scan_medium,
* to handle smaller (i.e. degraded) buffer allocations under low- or
* fragmented-memory situations where such reduced allocations, from a
* requested ideal, are allowed.
*
* Returns a pointer to the allocated buffer on success; otherwise, NULL.
*/
void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
{
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 08:28:21 +08:00
gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY;
mtd: create function to perform large allocations Introduce a common function to handle large, contiguous kmalloc buffer allocations by exponentially backing off on the size of the requested kernel transfer buffer until it succeeds or until the requested transfer buffer size falls below the page size. This helps ensure the operation can succeed under low-memory, highly- fragmented situations albeit somewhat more slowly. Artem: so this patch solves the problem that the kernel tries to kmalloc too large buffers, which (a) may fail and does fail - people complain about this, and (b) slows down the system in case of high memory fragmentation, because the kernel starts dropping caches, writing back, swapping, etc. But we do not really have to allocate a lot of memory to do the I/O, we may do this even with as little as one min. I/O unit (NAND page) of RAM. So the idea of this patch is that if the user asks to read or write a lot, we try to kmalloc a lot, with GFP flags which make the kernel _not_ drop caches, etc. If we can allocate it - good, if not - we try to allocate twice as less, and so on, until we reach the min. I/O unit size, which is our last resort allocation and use the normal GFP_KERNEL flag. Artem: re-write the allocation function so that it makes sure the allocated buffer is aligned to the min. I/O size of the flash. Signed-off-by: Grant Erickson <marathon96@gmail.com> Tested-by: Ben Gardiner <bengardiner@nanometrics.ca> Tested-by: Stefano Babic <sbabic@denx.de> Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2011-04-08 23:51:32 +08:00
size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
void *kbuf;
*size = min_t(size_t, *size, KMALLOC_MAX_SIZE);
while (*size > min_alloc) {
kbuf = kmalloc(*size, flags);
if (kbuf)
return kbuf;
*size >>= 1;
*size = ALIGN(*size, mtd->writesize);
}
/*
* For the last resort allocation allow 'kmalloc()' to do all sorts of
* things (write-back, dropping caches, etc) by using GFP_KERNEL.
*/
return kmalloc(*size, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(mtd_kmalloc_up_to);
#ifdef CONFIG_PROC_FS
/*====================================================================*/
/* Support for /proc/mtd */
static int mtd_proc_show(struct seq_file *m, void *v)
{
struct mtd_info *mtd;
seq_puts(m, "dev: size erasesize name\n");
mutex_lock(&mtd_table_mutex);
mtd_for_each_device(mtd) {
seq_printf(m, "mtd%d: %8.8llx %8.8x \"%s\"\n",
mtd->index, (unsigned long long)mtd->size,
mtd->erasesize, mtd->name);
}
mutex_unlock(&mtd_table_mutex);
return 0;
}
static int mtd_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, mtd_proc_show, NULL);
}
static const struct file_operations mtd_proc_ops = {
.open = mtd_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
#endif /* CONFIG_PROC_FS */
/*====================================================================*/
/* Init code */
static int __init mtd_bdi_init(struct backing_dev_info *bdi, const char *name)
{
int ret;
ret = bdi_init(bdi);
if (!ret)
ret = bdi_register(bdi, NULL, "%s", name);
if (ret)
bdi_destroy(bdi);
return ret;
}
static struct proc_dir_entry *proc_mtd;
static int __init init_mtd(void)
{
int ret;
ret = class_register(&mtd_class);
if (ret)
goto err_reg;
ret = mtd_bdi_init(&mtd_bdi, "mtd");
if (ret)
goto err_bdi;
proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
mtd: merge mtdchar module with mtdcore The MTD subsystem has historically tried to be as configurable as possible. The side-effect of this is that its configuration menu is rather large, and we are gradually shrinking it. For example, we recently merged partitions support with the mtdcore. This patch does the next step - it merges the mtdchar module to mtdcore. And in this case this is not only about eliminating too fine-grained separation and simplifying the configuration menu. This is also about eliminating seemingly useless kernel module. Indeed, mtdchar is a module that allows user-space making use of MTD devices via /dev/mtd* character devices. If users do not enable it, they simply cannot use MTD devices at all. They cannot read or write the flash contents. Is it a sane and useful setup? I believe not. And everyone just enables mtdchar. Having mtdchar separate is also a little bit harmful. People sometimes miss the fact that they need to enable an additional configuration option to have user-space MTD interfaces, and then they wonder why on earth the kernel does not allow using the flash? They spend time asking around. Thus, let's just get rid of this module and make it part of mtd core. Note, mtdchar had additional configuration option to enable OTP interfaces, which are present on some flashes. I removed that option as well - it saves a really tiny amount space. [dwmw2: Strictly speaking, you can mount file systems on MTD devices just fine without the mtdchar (or mtdblock) devices; you just can't do other manipulations directly on the underlying device. But still I agree that it makes sense to make this unconditional. And Yay! we get to kill off an instance of checking CONFIG_foo_MODULE, which is an abomination that should never happen.] Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2013-03-14 19:27:40 +08:00
ret = init_mtdchar();
if (ret)
goto out_procfs;
return 0;
mtd: merge mtdchar module with mtdcore The MTD subsystem has historically tried to be as configurable as possible. The side-effect of this is that its configuration menu is rather large, and we are gradually shrinking it. For example, we recently merged partitions support with the mtdcore. This patch does the next step - it merges the mtdchar module to mtdcore. And in this case this is not only about eliminating too fine-grained separation and simplifying the configuration menu. This is also about eliminating seemingly useless kernel module. Indeed, mtdchar is a module that allows user-space making use of MTD devices via /dev/mtd* character devices. If users do not enable it, they simply cannot use MTD devices at all. They cannot read or write the flash contents. Is it a sane and useful setup? I believe not. And everyone just enables mtdchar. Having mtdchar separate is also a little bit harmful. People sometimes miss the fact that they need to enable an additional configuration option to have user-space MTD interfaces, and then they wonder why on earth the kernel does not allow using the flash? They spend time asking around. Thus, let's just get rid of this module and make it part of mtd core. Note, mtdchar had additional configuration option to enable OTP interfaces, which are present on some flashes. I removed that option as well - it saves a really tiny amount space. [dwmw2: Strictly speaking, you can mount file systems on MTD devices just fine without the mtdchar (or mtdblock) devices; you just can't do other manipulations directly on the underlying device. But still I agree that it makes sense to make this unconditional. And Yay! we get to kill off an instance of checking CONFIG_foo_MODULE, which is an abomination that should never happen.] Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2013-03-14 19:27:40 +08:00
out_procfs:
if (proc_mtd)
remove_proc_entry("mtd", NULL);
err_bdi:
class_unregister(&mtd_class);
err_reg:
pr_err("Error registering mtd class or bdi: %d\n", ret);
return ret;
}
static void __exit cleanup_mtd(void)
{
mtd: merge mtdchar module with mtdcore The MTD subsystem has historically tried to be as configurable as possible. The side-effect of this is that its configuration menu is rather large, and we are gradually shrinking it. For example, we recently merged partitions support with the mtdcore. This patch does the next step - it merges the mtdchar module to mtdcore. And in this case this is not only about eliminating too fine-grained separation and simplifying the configuration menu. This is also about eliminating seemingly useless kernel module. Indeed, mtdchar is a module that allows user-space making use of MTD devices via /dev/mtd* character devices. If users do not enable it, they simply cannot use MTD devices at all. They cannot read or write the flash contents. Is it a sane and useful setup? I believe not. And everyone just enables mtdchar. Having mtdchar separate is also a little bit harmful. People sometimes miss the fact that they need to enable an additional configuration option to have user-space MTD interfaces, and then they wonder why on earth the kernel does not allow using the flash? They spend time asking around. Thus, let's just get rid of this module and make it part of mtd core. Note, mtdchar had additional configuration option to enable OTP interfaces, which are present on some flashes. I removed that option as well - it saves a really tiny amount space. [dwmw2: Strictly speaking, you can mount file systems on MTD devices just fine without the mtdchar (or mtdblock) devices; you just can't do other manipulations directly on the underlying device. But still I agree that it makes sense to make this unconditional. And Yay! we get to kill off an instance of checking CONFIG_foo_MODULE, which is an abomination that should never happen.] Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
2013-03-14 19:27:40 +08:00
cleanup_mtdchar();
if (proc_mtd)
remove_proc_entry("mtd", NULL);
class_unregister(&mtd_class);
bdi_destroy(&mtd_bdi);
idr_destroy(&mtd_idr);
}
module_init(init_mtd);
module_exit(cleanup_mtd);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
MODULE_DESCRIPTION("Core MTD registration and access routines");