cregit-Linux how code gets into the kernel

Release 4.14 drivers/block/brd.c

Directory: drivers/block
/*
 * 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>
#ifdef CONFIG_BLK_DEV_RAM_DAX
#include <linux/pfn_t.h>
#include <linux/dax.h>
#include <linux/uio.h>
#endif

#include <linux/uaccess.h>


#define SECTOR_SHIFT		9

#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;
#ifdef CONFIG_BLK_DEV_RAM_DAX
	
struct dax_device	*dax_dev;
#endif
	
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 DEFINE_MUTEX(brd_mutex);

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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin4164.06%120.00%
Linus Torvalds1218.75%120.00%
Andrew Morton1117.19%360.00%
Total64100.00%5100.00%

/* * 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. * * Cannot support DAX and highmem, because our ->direct_access * routine for DAX must return memory that is always addressable. * If DAX was reworked to use pfns and kmap throughout, this * restriction might be able to be lifted. */ gfp_flags = GFP_NOIO | __GFP_ZERO; #ifndef CONFIG_BLK_DEV_RAM_DAX gfp_flags |= __GFP_HIGHMEM; #endif 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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin11063.58%225.00%
Andrew Morton3721.39%225.00%
Linus Torvalds179.83%112.50%
Brian Behlendorf63.47%112.50%
Matthew Wilcox21.16%112.50%
Petr Tesarik10.58%112.50%
Total173100.00%8100.00%

/* * 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++; /* * 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); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin13093.53%150.00%
Andrew Morton96.47%150.00%
Total139100.00%2100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin7377.66%120.00%
Andrew Morton1515.96%240.00%
Linus Torvalds44.26%120.00%
Matthew Wilcox22.13%120.00%
Total94100.00%5100.00%

/* * 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); } }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin8452.17%110.00%
Linus Torvalds5232.30%330.00%
Andrew Morton116.83%220.00%
Al Viro74.35%110.00%
Christian Bornträger53.11%110.00%
Russell King10.62%110.00%
Christoph Hellwig10.62%110.00%
Total161100.00%10100.00%

/* * 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); } }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin13172.78%114.29%
Linus Torvalds2715.00%342.86%
Al Viro137.22%114.29%
Linus Torvalds (pre-git)95.00%228.57%
Total180100.00%7100.00%

/* * 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, bool is_write, sector_t sector) { void *mem; int err = 0; if (is_write) { err = copy_to_brd_setup(brd, sector, len); if (err) goto out; } mem = kmap_atomic(page); if (!is_write) { 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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin9474.60%220.00%
Linus Torvalds (pre-git)1814.29%220.00%
Linus Torvalds53.97%220.00%
Al Viro43.17%220.00%
Jens Axboe43.17%110.00%
Michael Christie10.79%110.00%
Total126100.00%10100.00%


static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) { struct brd_device *brd = bio->bi_disk->private_data; struct bio_vec bvec; sector_t sector; struct bvec_iter iter; sector = bio->bi_iter.bi_sector; if (bio_end_sector(bio) > get_capacity(bio->bi_disk)) goto io_error; bio_for_each_segment(bvec, bio, iter) { unsigned int len = bvec.bv_len; int err; err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset, op_is_write(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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin9869.01%111.11%
Christoph Hellwig1812.68%222.22%
Kent Overstreet128.45%333.33%
Jens Axboe107.04%222.22%
Michael Christie42.82%111.11%
Total142100.00%9100.00%


static int brd_rw_page(struct block_device *bdev, sector_t sector, struct page *page, bool is_write) { 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, is_write, sector); page_endio(page, is_write, err); return err; }

Contributors

PersonTokensPropCommitsCommitProp
Matthew Wilcox5673.68%125.00%
Huang Ying1519.74%125.00%
Jens Axboe45.26%125.00%
Kirill A. Shutemov11.32%125.00%
Total76100.00%4100.00%

#ifdef CONFIG_BLK_DEV_RAM_DAX
static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { struct page *page; if (!brd) return -ENODEV; page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT); if (!page) return -ENOSPC; *kaddr = page_address(page); *pfn = page_to_pfn_t(page); return 1; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin4959.76%114.29%
Jared Hulbert1417.07%114.29%
Dan J Williams1214.63%228.57%
Mikulas Patocka56.10%114.29%
Matthew Wilcox22.44%228.57%
Total82100.00%7100.00%


static long brd_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { struct brd_device *brd = dax_get_private(dax_dev); return __brd_direct_access(brd, pgoff, nr_pages, kaddr, pfn); }

Contributors

PersonTokensPropCommitsCommitProp
Dan J Williams50100.00%1100.00%
Total50100.00%1100.00%


static size_t brd_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { return copy_from_iter(addr, bytes, i); }

Contributors

PersonTokensPropCommitsCommitProp
Dan J Williams36100.00%1100.00%
Total36100.00%1100.00%

static const struct dax_operations brd_dax_ops = { .direct_access = brd_dax_direct_access, .copy_from_iter = brd_dax_copy_from_iter, }; #endif static const struct block_device_operations brd_fops = { .owner = THIS_MODULE, .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, S_IRUGO); MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices"); unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE; module_param(rd_size, ulong, S_IRUGO); MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes."); static int max_part = 1; module_param(max_part, int, S_IRUGO); 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; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin2288.00%150.00%
Linus Torvalds312.00%150.00%
Total25100.00%2100.00%

__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(GFP_KERNEL); if (!brd->brd_queue) goto out_free_dev; blk_queue_make_request(brd->brd_queue, brd_make_request); blk_queue_max_hw_sectors(brd->brd_queue, 1024); /* 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->queue = brd->brd_queue; disk->flags = GENHD_FL_EXT_DEVT; sprintf(disk->disk_name, "ram%d", i); set_capacity(disk, rd_size * 2); #ifdef CONFIG_BLK_DEV_RAM_DAX queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue); brd->dax_dev = alloc_dax(brd, disk->disk_name, &brd_dax_ops); if (!brd->dax_dev) goto out_free_inode; #endif return brd; #ifdef CONFIG_BLK_DEV_RAM_DAX out_free_inode: kill_dax(brd->dax_dev); put_dax(brd->dax_dev); #endif out_free_queue: blk_cleanup_queue(brd->brd_queue); out_free_dev: kfree(brd); out: return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin14351.44%14.55%
Dan J Williams5319.06%14.55%
Andrew Morton186.47%29.09%
Boaz Harrosh155.40%29.09%
Al Viro124.32%522.73%
Linus Torvalds93.24%313.64%
Linus Torvalds (pre-git)82.88%418.18%
Gerald Schaefer82.88%14.55%
Eric W. Biedermann72.52%14.55%
Marcin Krol41.44%14.55%
Martin K. Petersen10.36%14.55%
Total278100.00%22100.00%


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); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin3291.43%150.00%
Linus Torvalds (pre-git)38.57%150.00%
Total35100.00%2100.00%


static struct brd_device *brd_init_one(int i, bool *new) { struct brd_device *brd; *new = false; list_for_each_entry(brd, &brd_devices, brd_list) { if (brd->brd_number == i) goto out; } brd = brd_alloc(i); if (brd) { add_disk(brd->brd_disk); list_add_tail(&brd->brd_list, &brd_devices); } *new = true; out: return brd; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin5057.47%19.09%
Boaz Harrosh1416.09%19.09%
Al Viro89.20%327.27%
Linus Torvalds (pre-git)66.90%327.27%
Linus Torvalds66.90%218.18%
Jeff Garzik33.45%19.09%
Total87100.00%11100.00%


static void brd_del_one(struct brd_device *brd) { list_del(&brd->brd_list); #ifdef CONFIG_BLK_DEV_RAM_DAX kill_dax(brd->dax_dev); put_dax(brd->dax_dev); #endif del_gendisk(brd->brd_disk); brd_free(brd); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin2142.00%125.00%
Dan J Williams1938.00%125.00%
Peter Zijlstra612.00%125.00%
Linus Torvalds (pre-git)48.00%125.00%
Total50100.00%4100.00%


static struct kobject *brd_probe(dev_t dev, int *part, void *data) { struct brd_device *brd; struct kobject *kobj; bool new; mutex_lock(&brd_devices_mutex); brd = brd_init_one(MINOR(dev) / max_part, &new); kobj = brd ? get_disk(brd->brd_disk) : NULL; mutex_unlock(&brd_devices_mutex); if (new) *part = 0; return kobj; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin4553.57%111.11%
Boaz Harrosh1214.29%111.11%
Peter Zijlstra1113.10%111.11%
Linus Torvalds (pre-git)1113.10%333.33%
Namhyung Kim33.57%111.11%
Mikulas Patocka11.19%111.11%
Linus Torvalds11.19%111.11%
Total84100.00%9100.00%


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")) return -EIO; if (unlikely(!max_part)) max_part = 1; 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) add_disk(brd->brd_disk); blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS, THIS_MODULE, brd_probe, NULL, NULL); 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); } unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); pr_info("brd: module NOT loaded !!!\n"); return -ENOMEM; }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin10358.52%15.26%
Boaz Harrosh2614.77%15.26%
Linus Torvalds (pre-git)169.09%526.32%
Al Viro116.25%526.32%
Peter Zijlstra73.98%15.26%
Linus Torvalds73.98%15.26%
Andrew Morton42.27%315.79%
Akinobu Mita10.57%15.26%
Christoph Hellwig10.57%15.26%
Total176100.00%19100.00%


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); blk_unregister_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS); unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); pr_info("brd: module unloaded\n"); }

Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin2746.55%116.67%
Linus Torvalds1220.69%116.67%
Linus Torvalds (pre-git)1118.97%350.00%
Boaz Harrosh813.79%116.67%
Total58100.00%6100.00%

module_init(brd_init); module_exit(brd_exit);

Overall Contributors

PersonTokensPropCommitsCommitProp
Nicholas Piggin138757.82%43.77%
Dan J Williams2128.84%32.83%
Linus Torvalds1656.88%98.49%
Andrew Morton1184.92%1514.15%
Linus Torvalds (pre-git)953.96%1716.04%
Boaz Harrosh873.63%21.89%
Matthew Wilcox672.79%43.77%
Al Viro582.42%1110.38%
Christoph Hellwig291.21%65.66%
Peter Zijlstra241.00%10.94%
Jens Axboe180.75%21.89%
Huang Ying150.63%10.94%
Jared Hulbert140.58%10.94%
Dmitriy Monakhov140.58%10.94%
Kent Overstreet120.50%32.83%
Arnd Bergmann90.38%21.89%
Gerald Schaefer80.33%10.94%
Eric W. Biedermann70.29%10.94%
Mikulas Patocka60.25%21.89%
Brian Behlendorf60.25%10.94%
Stephen Hemminger60.25%10.94%
Namhyung Kim50.21%21.89%
Michael Christie50.21%10.94%
Christian Bornträger50.21%10.94%
Marcin Krol40.17%10.94%
Bart Van Assche30.13%10.94%
Robert P. J. Day30.13%21.89%
Tejun Heo30.13%10.94%
Jeff Garzik30.13%10.94%
Jan Kara30.13%10.94%
Laurent Vivier20.08%10.94%
Russell King10.04%10.94%
Petr Tesarik10.04%10.94%
Akinobu Mita10.04%10.94%
Kirill A. Shutemov10.04%10.94%
Alexey Dobriyan10.04%10.94%
Martin K. Petersen10.04%10.94%
Total2399100.00%106100.00%
Directory: drivers/block
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.