mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 03:10:12 +00:00
![Christoph Hellwig](/assets/img/avatar_default.png)
Replace the gendisk pointer in struct bio with a pointer to the newly improved struct block device. From that the gendisk can be trivially accessed with an extra indirection, but it also allows to directly look up all information related to partition remapping. Signed-off-by: Christoph Hellwig <hch@lst.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
547 lines
13 KiB
C
547 lines
13 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Ram backed block device driver.
|
|
*
|
|
* Copyright (C) 2007 Nick Piggin
|
|
* Copyright (C) 2007 Novell Inc.
|
|
*
|
|
* Parts derived from drivers/block/rd.c, and drivers/block/loop.c, copyright
|
|
* of their respective owners.
|
|
*/
|
|
|
|
#include <linux/init.h>
|
|
#include <linux/initrd.h>
|
|
#include <linux/module.h>
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/major.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/backing-dev.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
|
|
#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
|
|
|
|
/*
|
|
* Each block ramdisk device has a radix_tree brd_pages of pages that stores
|
|
* the pages containing the block device's contents. A brd page's ->index is
|
|
* its offset in PAGE_SIZE units. This is similar to, but in no way connected
|
|
* with, the kernel's pagecache or buffer cache (which sit above our block
|
|
* device).
|
|
*/
|
|
struct brd_device {
|
|
int brd_number;
|
|
|
|
struct request_queue *brd_queue;
|
|
struct gendisk *brd_disk;
|
|
struct list_head brd_list;
|
|
|
|
/*
|
|
* Backing store of pages and lock to protect it. This is the contents
|
|
* of the block device.
|
|
*/
|
|
spinlock_t brd_lock;
|
|
struct radix_tree_root brd_pages;
|
|
};
|
|
|
|
/*
|
|
* Look up and return a brd's page for a given sector.
|
|
*/
|
|
static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
|
|
{
|
|
pgoff_t idx;
|
|
struct page *page;
|
|
|
|
/*
|
|
* The page lifetime is protected by the fact that we have opened the
|
|
* device node -- brd pages will never be deleted under us, so we
|
|
* don't need any further locking or refcounting.
|
|
*
|
|
* This is strictly true for the radix-tree nodes as well (ie. we
|
|
* don't actually need the rcu_read_lock()), however that is not a
|
|
* documented feature of the radix-tree API so it is better to be
|
|
* safe here (we don't have total exclusion from radix tree updates
|
|
* here, only deletes).
|
|
*/
|
|
rcu_read_lock();
|
|
idx = sector >> PAGE_SECTORS_SHIFT; /* sector to page index */
|
|
page = radix_tree_lookup(&brd->brd_pages, idx);
|
|
rcu_read_unlock();
|
|
|
|
BUG_ON(page && page->index != idx);
|
|
|
|
return page;
|
|
}
|
|
|
|
/*
|
|
* Look up and return a brd's page for a given sector.
|
|
* If one does not exist, allocate an empty page, and insert that. Then
|
|
* return it.
|
|
*/
|
|
static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
|
|
{
|
|
pgoff_t idx;
|
|
struct page *page;
|
|
gfp_t gfp_flags;
|
|
|
|
page = brd_lookup_page(brd, sector);
|
|
if (page)
|
|
return page;
|
|
|
|
/*
|
|
* Must use NOIO because we don't want to recurse back into the
|
|
* block or filesystem layers from page reclaim.
|
|
*/
|
|
gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM;
|
|
page = alloc_page(gfp_flags);
|
|
if (!page)
|
|
return NULL;
|
|
|
|
if (radix_tree_preload(GFP_NOIO)) {
|
|
__free_page(page);
|
|
return NULL;
|
|
}
|
|
|
|
spin_lock(&brd->brd_lock);
|
|
idx = sector >> PAGE_SECTORS_SHIFT;
|
|
page->index = idx;
|
|
if (radix_tree_insert(&brd->brd_pages, idx, page)) {
|
|
__free_page(page);
|
|
page = radix_tree_lookup(&brd->brd_pages, idx);
|
|
BUG_ON(!page);
|
|
BUG_ON(page->index != idx);
|
|
}
|
|
spin_unlock(&brd->brd_lock);
|
|
|
|
radix_tree_preload_end();
|
|
|
|
return page;
|
|
}
|
|
|
|
/*
|
|
* Free all backing store pages and radix tree. This must only be called when
|
|
* there are no other users of the device.
|
|
*/
|
|
#define FREE_BATCH 16
|
|
static void brd_free_pages(struct brd_device *brd)
|
|
{
|
|
unsigned long pos = 0;
|
|
struct page *pages[FREE_BATCH];
|
|
int nr_pages;
|
|
|
|
do {
|
|
int i;
|
|
|
|
nr_pages = radix_tree_gang_lookup(&brd->brd_pages,
|
|
(void **)pages, pos, FREE_BATCH);
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
void *ret;
|
|
|
|
BUG_ON(pages[i]->index < pos);
|
|
pos = pages[i]->index;
|
|
ret = radix_tree_delete(&brd->brd_pages, pos);
|
|
BUG_ON(!ret || ret != pages[i]);
|
|
__free_page(pages[i]);
|
|
}
|
|
|
|
pos++;
|
|
|
|
/*
|
|
* It takes 3.4 seconds to remove 80GiB ramdisk.
|
|
* So, we need cond_resched to avoid stalling the CPU.
|
|
*/
|
|
cond_resched();
|
|
|
|
/*
|
|
* This assumes radix_tree_gang_lookup always returns as
|
|
* many pages as possible. If the radix-tree code changes,
|
|
* so will this have to.
|
|
*/
|
|
} while (nr_pages == FREE_BATCH);
|
|
}
|
|
|
|
/*
|
|
* copy_to_brd_setup must be called before copy_to_brd. It may sleep.
|
|
*/
|
|
static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
|
|
{
|
|
unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
|
|
size_t copy;
|
|
|
|
copy = min_t(size_t, n, PAGE_SIZE - offset);
|
|
if (!brd_insert_page(brd, sector))
|
|
return -ENOSPC;
|
|
if (copy < n) {
|
|
sector += copy >> SECTOR_SHIFT;
|
|
if (!brd_insert_page(brd, sector))
|
|
return -ENOSPC;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Copy n bytes from src to the brd starting at sector. Does not sleep.
|
|
*/
|
|
static void copy_to_brd(struct brd_device *brd, const void *src,
|
|
sector_t sector, size_t n)
|
|
{
|
|
struct page *page;
|
|
void *dst;
|
|
unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
|
|
size_t copy;
|
|
|
|
copy = min_t(size_t, n, PAGE_SIZE - offset);
|
|
page = brd_lookup_page(brd, sector);
|
|
BUG_ON(!page);
|
|
|
|
dst = kmap_atomic(page);
|
|
memcpy(dst + offset, src, copy);
|
|
kunmap_atomic(dst);
|
|
|
|
if (copy < n) {
|
|
src += copy;
|
|
sector += copy >> SECTOR_SHIFT;
|
|
copy = n - copy;
|
|
page = brd_lookup_page(brd, sector);
|
|
BUG_ON(!page);
|
|
|
|
dst = kmap_atomic(page);
|
|
memcpy(dst, src, copy);
|
|
kunmap_atomic(dst);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Copy n bytes to dst from the brd starting at sector. Does not sleep.
|
|
*/
|
|
static void copy_from_brd(void *dst, struct brd_device *brd,
|
|
sector_t sector, size_t n)
|
|
{
|
|
struct page *page;
|
|
void *src;
|
|
unsigned int offset = (sector & (PAGE_SECTORS-1)) << SECTOR_SHIFT;
|
|
size_t copy;
|
|
|
|
copy = min_t(size_t, n, PAGE_SIZE - offset);
|
|
page = brd_lookup_page(brd, sector);
|
|
if (page) {
|
|
src = kmap_atomic(page);
|
|
memcpy(dst, src + offset, copy);
|
|
kunmap_atomic(src);
|
|
} else
|
|
memset(dst, 0, copy);
|
|
|
|
if (copy < n) {
|
|
dst += copy;
|
|
sector += copy >> SECTOR_SHIFT;
|
|
copy = n - copy;
|
|
page = brd_lookup_page(brd, sector);
|
|
if (page) {
|
|
src = kmap_atomic(page);
|
|
memcpy(dst, src, copy);
|
|
kunmap_atomic(src);
|
|
} else
|
|
memset(dst, 0, copy);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Process a single bvec of a bio.
|
|
*/
|
|
static int brd_do_bvec(struct brd_device *brd, struct page *page,
|
|
unsigned int len, unsigned int off, unsigned int op,
|
|
sector_t sector)
|
|
{
|
|
void *mem;
|
|
int err = 0;
|
|
|
|
if (op_is_write(op)) {
|
|
err = copy_to_brd_setup(brd, sector, len);
|
|
if (err)
|
|
goto out;
|
|
}
|
|
|
|
mem = kmap_atomic(page);
|
|
if (!op_is_write(op)) {
|
|
copy_from_brd(mem + off, brd, sector, len);
|
|
flush_dcache_page(page);
|
|
} else {
|
|
flush_dcache_page(page);
|
|
copy_to_brd(brd, mem + off, sector, len);
|
|
}
|
|
kunmap_atomic(mem);
|
|
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static blk_qc_t brd_submit_bio(struct bio *bio)
|
|
{
|
|
struct brd_device *brd = bio->bi_bdev->bd_disk->private_data;
|
|
sector_t sector = bio->bi_iter.bi_sector;
|
|
struct bio_vec bvec;
|
|
struct bvec_iter iter;
|
|
|
|
bio_for_each_segment(bvec, bio, iter) {
|
|
unsigned int len = bvec.bv_len;
|
|
int err;
|
|
|
|
/* Don't support un-aligned buffer */
|
|
WARN_ON_ONCE((bvec.bv_offset & (SECTOR_SIZE - 1)) ||
|
|
(len & (SECTOR_SIZE - 1)));
|
|
|
|
err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
|
|
bio_op(bio), sector);
|
|
if (err)
|
|
goto io_error;
|
|
sector += len >> SECTOR_SHIFT;
|
|
}
|
|
|
|
bio_endio(bio);
|
|
return BLK_QC_T_NONE;
|
|
io_error:
|
|
bio_io_error(bio);
|
|
return BLK_QC_T_NONE;
|
|
}
|
|
|
|
static int brd_rw_page(struct block_device *bdev, sector_t sector,
|
|
struct page *page, unsigned int op)
|
|
{
|
|
struct brd_device *brd = bdev->bd_disk->private_data;
|
|
int err;
|
|
|
|
if (PageTransHuge(page))
|
|
return -ENOTSUPP;
|
|
err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
|
|
page_endio(page, op_is_write(op), err);
|
|
return err;
|
|
}
|
|
|
|
static const struct block_device_operations brd_fops = {
|
|
.owner = THIS_MODULE,
|
|
.submit_bio = brd_submit_bio,
|
|
.rw_page = brd_rw_page,
|
|
};
|
|
|
|
/*
|
|
* And now the modules code and kernel interface.
|
|
*/
|
|
static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT;
|
|
module_param(rd_nr, int, 0444);
|
|
MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices");
|
|
|
|
unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE;
|
|
module_param(rd_size, ulong, 0444);
|
|
MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes.");
|
|
|
|
static int max_part = 1;
|
|
module_param(max_part, int, 0444);
|
|
MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices");
|
|
|
|
MODULE_LICENSE("GPL");
|
|
MODULE_ALIAS_BLOCKDEV_MAJOR(RAMDISK_MAJOR);
|
|
MODULE_ALIAS("rd");
|
|
|
|
#ifndef MODULE
|
|
/* Legacy boot options - nonmodular */
|
|
static int __init ramdisk_size(char *str)
|
|
{
|
|
rd_size = simple_strtol(str, NULL, 0);
|
|
return 1;
|
|
}
|
|
__setup("ramdisk_size=", ramdisk_size);
|
|
#endif
|
|
|
|
/*
|
|
* The device scheme is derived from loop.c. Keep them in synch where possible
|
|
* (should share code eventually).
|
|
*/
|
|
static LIST_HEAD(brd_devices);
|
|
static DEFINE_MUTEX(brd_devices_mutex);
|
|
|
|
static struct brd_device *brd_alloc(int i)
|
|
{
|
|
struct brd_device *brd;
|
|
struct gendisk *disk;
|
|
|
|
brd = kzalloc(sizeof(*brd), GFP_KERNEL);
|
|
if (!brd)
|
|
goto out;
|
|
brd->brd_number = i;
|
|
spin_lock_init(&brd->brd_lock);
|
|
INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
|
|
|
|
brd->brd_queue = blk_alloc_queue(NUMA_NO_NODE);
|
|
if (!brd->brd_queue)
|
|
goto out_free_dev;
|
|
|
|
/* This is so fdisk will align partitions on 4k, because of
|
|
* direct_access API needing 4k alignment, returning a PFN
|
|
* (This is only a problem on very small devices <= 4M,
|
|
* otherwise fdisk will align on 1M. Regardless this call
|
|
* is harmless)
|
|
*/
|
|
blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
|
|
disk = brd->brd_disk = alloc_disk(max_part);
|
|
if (!disk)
|
|
goto out_free_queue;
|
|
disk->major = RAMDISK_MAJOR;
|
|
disk->first_minor = i * max_part;
|
|
disk->fops = &brd_fops;
|
|
disk->private_data = brd;
|
|
disk->flags = GENHD_FL_EXT_DEVT;
|
|
sprintf(disk->disk_name, "ram%d", i);
|
|
set_capacity(disk, rd_size * 2);
|
|
|
|
/* Tell the block layer that this is not a rotational device */
|
|
blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue);
|
|
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, brd->brd_queue);
|
|
|
|
return brd;
|
|
|
|
out_free_queue:
|
|
blk_cleanup_queue(brd->brd_queue);
|
|
out_free_dev:
|
|
kfree(brd);
|
|
out:
|
|
return NULL;
|
|
}
|
|
|
|
static void brd_free(struct brd_device *brd)
|
|
{
|
|
put_disk(brd->brd_disk);
|
|
blk_cleanup_queue(brd->brd_queue);
|
|
brd_free_pages(brd);
|
|
kfree(brd);
|
|
}
|
|
|
|
static void brd_probe(dev_t dev)
|
|
{
|
|
struct brd_device *brd;
|
|
int i = MINOR(dev) / max_part;
|
|
|
|
mutex_lock(&brd_devices_mutex);
|
|
list_for_each_entry(brd, &brd_devices, brd_list) {
|
|
if (brd->brd_number == i)
|
|
goto out_unlock;
|
|
}
|
|
|
|
brd = brd_alloc(i);
|
|
if (brd) {
|
|
brd->brd_disk->queue = brd->brd_queue;
|
|
add_disk(brd->brd_disk);
|
|
list_add_tail(&brd->brd_list, &brd_devices);
|
|
}
|
|
|
|
out_unlock:
|
|
mutex_unlock(&brd_devices_mutex);
|
|
}
|
|
|
|
static void brd_del_one(struct brd_device *brd)
|
|
{
|
|
list_del(&brd->brd_list);
|
|
del_gendisk(brd->brd_disk);
|
|
brd_free(brd);
|
|
}
|
|
|
|
static inline void brd_check_and_reset_par(void)
|
|
{
|
|
if (unlikely(!max_part))
|
|
max_part = 1;
|
|
|
|
/*
|
|
* make sure 'max_part' can be divided exactly by (1U << MINORBITS),
|
|
* otherwise, it is possiable to get same dev_t when adding partitions.
|
|
*/
|
|
if ((1U << MINORBITS) % max_part != 0)
|
|
max_part = 1UL << fls(max_part);
|
|
|
|
if (max_part > DISK_MAX_PARTS) {
|
|
pr_info("brd: max_part can't be larger than %d, reset max_part = %d.\n",
|
|
DISK_MAX_PARTS, DISK_MAX_PARTS);
|
|
max_part = DISK_MAX_PARTS;
|
|
}
|
|
}
|
|
|
|
static int __init brd_init(void)
|
|
{
|
|
struct brd_device *brd, *next;
|
|
int i;
|
|
|
|
/*
|
|
* brd module now has a feature to instantiate underlying device
|
|
* structure on-demand, provided that there is an access dev node.
|
|
*
|
|
* (1) if rd_nr is specified, create that many upfront. else
|
|
* it defaults to CONFIG_BLK_DEV_RAM_COUNT
|
|
* (2) User can further extend brd devices by create dev node themselves
|
|
* and have kernel automatically instantiate actual device
|
|
* on-demand. Example:
|
|
* mknod /path/devnod_name b 1 X # 1 is the rd major
|
|
* fdisk -l /path/devnod_name
|
|
* If (X / max_part) was not already created it will be created
|
|
* dynamically.
|
|
*/
|
|
|
|
if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe))
|
|
return -EIO;
|
|
|
|
brd_check_and_reset_par();
|
|
|
|
mutex_lock(&brd_devices_mutex);
|
|
for (i = 0; i < rd_nr; i++) {
|
|
brd = brd_alloc(i);
|
|
if (!brd)
|
|
goto out_free;
|
|
list_add_tail(&brd->brd_list, &brd_devices);
|
|
}
|
|
|
|
/* point of no return */
|
|
|
|
list_for_each_entry(brd, &brd_devices, brd_list) {
|
|
/*
|
|
* associate with queue just before adding disk for
|
|
* avoiding to mess up failure path
|
|
*/
|
|
brd->brd_disk->queue = brd->brd_queue;
|
|
add_disk(brd->brd_disk);
|
|
}
|
|
mutex_unlock(&brd_devices_mutex);
|
|
|
|
pr_info("brd: module loaded\n");
|
|
return 0;
|
|
|
|
out_free:
|
|
list_for_each_entry_safe(brd, next, &brd_devices, brd_list) {
|
|
list_del(&brd->brd_list);
|
|
brd_free(brd);
|
|
}
|
|
mutex_unlock(&brd_devices_mutex);
|
|
unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
|
|
|
|
pr_info("brd: module NOT loaded !!!\n");
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static void __exit brd_exit(void)
|
|
{
|
|
struct brd_device *brd, *next;
|
|
|
|
list_for_each_entry_safe(brd, next, &brd_devices, brd_list)
|
|
brd_del_one(brd);
|
|
|
|
unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
|
|
|
|
pr_info("brd: module unloaded\n");
|
|
}
|
|
|
|
module_init(brd_init);
|
|
module_exit(brd_exit);
|
|
|