Commit c0f7e49f authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'block-5.15-2021-09-11' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Christoph:
     - fix nvmet command set reporting for passthrough controllers (Adam Manzanares)
     - update a MAINTAINERS email address (Chaitanya Kulkarni)
     - set QUEUE_FLAG_NOWAIT for nvme-multipth (me)
     - handle errors from add_disk() (Luis Chamberlain)
     - update the keep alive interval when kato is modified (Tatsuya Sasaki)
     - fix a buffer overrun in nvmet_subsys_attr_serial (Hannes Reinecke)
     - do not reset transport on data digest errors in nvme-tcp (Daniel Wagner)
     - only call synchronize_srcu when clearing current path (Daniel Wagner)
     - revalidate paths during rescan (Hannes Reinecke)

 - Split out the fs/block_dev into block/fops.c and block/bdev.c, which
   has been long overdue. Do this now before -rc1, to avoid annoying
   conflicts due to this (Christoph)

 - blk-throtl use-after-free fix (Li)

 - Improve plug depth for multi-device plugs, greatly increasing md
   resync performance (Song)

 - blkdev_show() locking fix (Tetsuo)

 - n64cart error check fix (Yang)

* tag 'block-5.15-2021-09-11' of git://git.kernel.dk/linux-block:
  n64cart: fix return value check in n64cart_probe()
  blk-mq: allow 4x BLK_MAX_REQUEST_COUNT at blk_plug for multiple_queues
  block: move fs/block_dev.c to block/bdev.c
  block: split out operations on block special files
  blk-throttle: fix UAF by deleteing timer in blk_throtl_exit()
  block: genhd: don't call blkdev_show() with major_names_lock held
  nvme: update MAINTAINERS email address
  nvme: add error handling support for add_disk()
  nvme: only call synchronize_srcu when clearing current path
  nvme: update keep alive interval when kato is modified
  nvme-tcp: Do not reset transport on data digest errors
  nvmet: fixup buffer overrun in nvmet_subsys_attr_serial()
  nvmet: return bool from nvmet_passthru_ctrl and nvmet_is_passthru_req
  nvmet: looks at the passthrough controller when initializing CAP
  nvme: move nvme_multi_css into nvme.h
  nvme-multipath: revalidate paths during rescan
  nvme-multipath: set QUEUE_FLAG_NOWAIT
parents 8177a5c9 221e8360
......@@ -315,6 +315,9 @@ Block Devices
.. kernel-doc:: block/genhd.c
:export:
.. kernel-doc:: block/bdev.c
:export:
Char devices
============
......
......@@ -71,9 +71,6 @@ Other Functions
.. kernel-doc:: fs/fs-writeback.c
:export:
.. kernel-doc:: fs/block_dev.c
:export:
.. kernel-doc:: fs/anon_inodes.c
:export:
......
......@@ -3313,7 +3313,6 @@ S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
F: block/
F: drivers/block/
F: fs/block_dev.c
F: include/linux/blk*
F: kernel/trace/blktrace.c
F: lib/sbitmap.c
......@@ -13409,7 +13408,7 @@ F: include/linux/nvme-fc.h
NVM EXPRESS TARGET DRIVER
M: Christoph Hellwig <hch@lst.de>
M: Sagi Grimberg <sagi@grimberg.me>
M: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
M: Chaitanya Kulkarni <kch@nvidia.com>
L: linux-nvme@lists.infradead.org
S: Supported
W: http://git.infradead.org/nvme.git
......
......@@ -3,7 +3,7 @@
# Makefile for the kernel block layer
#
obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
obj-$(CONFIG_BLOCK) := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
blk-exec.o blk-merge.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
......
......@@ -7,12 +7,10 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/major.h>
#include <linux/device_cgroup.h>
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
......@@ -20,30 +18,22 @@
#include <linux/magic.h>
#include <linux/buffer_head.h>
#include <linux/swap.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/cleancache.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/falloc.h>
#include <linux/part_stat.h>
#include <linux/uaccess.h>
#include <linux/suspend.h>
#include "internal.h"
#include "../block/blk.h"
#include "../fs/internal.h"
#include "blk.h"
struct bdev_inode {
struct block_device bdev;
struct inode vfs_inode;
};
static const struct address_space_operations def_blk_aops;
static inline struct bdev_inode *BDEV_I(struct inode *inode)
{
return container_of(inode, struct bdev_inode, vfs_inode);
......@@ -194,332 +184,6 @@ int sb_min_blocksize(struct super_block *sb, int size)
EXPORT_SYMBOL(sb_min_blocksize);
static int
blkdev_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
bh->b_bdev = I_BDEV(inode);
bh->b_blocknr = iblock;
set_buffer_mapped(bh);
return 0;
}
static struct inode *bdev_file_inode(struct file *file)
{
return file->f_mapping->host;
}
static unsigned int dio_bio_write_op(struct kiocb *iocb)
{
unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
/* avoid the need for a I/O completion work item */
if (iocb->ki_flags & IOCB_DSYNC)
op |= REQ_FUA;
return op;
}
#define DIO_INLINE_BIO_VECS 4
static void blkdev_bio_end_io_simple(struct bio *bio)
{
struct task_struct *waiter = bio->bi_private;
WRITE_ONCE(bio->bi_private, NULL);
blk_wake_io_task(waiter);
}
static ssize_t
__blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
unsigned int nr_pages)
{
struct file *file = iocb->ki_filp;
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
loff_t pos = iocb->ki_pos;
bool should_dirty = false;
struct bio bio;
ssize_t ret;
blk_qc_t qc;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
if (nr_pages <= DIO_INLINE_BIO_VECS)
vecs = inline_vecs;
else {
vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
GFP_KERNEL);
if (!vecs)
return -ENOMEM;
}
bio_init(&bio, vecs, nr_pages);
bio_set_dev(&bio, bdev);
bio.bi_iter.bi_sector = pos >> 9;
bio.bi_write_hint = iocb->ki_hint;
bio.bi_private = current;
bio.bi_end_io = blkdev_bio_end_io_simple;
bio.bi_ioprio = iocb->ki_ioprio;
ret = bio_iov_iter_get_pages(&bio, iter);
if (unlikely(ret))
goto out;
ret = bio.bi_iter.bi_size;
if (iov_iter_rw(iter) == READ) {
bio.bi_opf = REQ_OP_READ;
if (iter_is_iovec(iter))
should_dirty = true;
} else {
bio.bi_opf = dio_bio_write_op(iocb);
task_io_account_write(ret);
}
if (iocb->ki_flags & IOCB_NOWAIT)
bio.bi_opf |= REQ_NOWAIT;
if (iocb->ki_flags & IOCB_HIPRI)
bio_set_polled(&bio, iocb);
qc = submit_bio(&bio);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio.bi_private))
break;
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!blk_poll(bdev_get_queue(bdev), qc, true))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
bio_release_pages(&bio, should_dirty);
if (unlikely(bio.bi_status))
ret = blk_status_to_errno(bio.bi_status);
out:
if (vecs != inline_vecs)
kfree(vecs);
bio_uninit(&bio);
return ret;
}
struct blkdev_dio {
union {
struct kiocb *iocb;
struct task_struct *waiter;
};
size_t size;
atomic_t ref;
bool multi_bio : 1;
bool should_dirty : 1;
bool is_sync : 1;
struct bio bio;
};
static struct bio_set blkdev_dio_pool;
static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
{
struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
struct request_queue *q = bdev_get_queue(bdev);
return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
}
static void blkdev_bio_end_io(struct bio *bio)
{
struct blkdev_dio *dio = bio->bi_private;
bool should_dirty = dio->should_dirty;
if (bio->bi_status && !dio->bio.bi_status)
dio->bio.bi_status = bio->bi_status;
if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
if (!dio->is_sync) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
if (likely(!dio->bio.bi_status)) {
ret = dio->size;
iocb->ki_pos += ret;
} else {
ret = blk_status_to_errno(dio->bio.bi_status);
}
dio->iocb->ki_complete(iocb, ret, 0);
if (dio->multi_bio)
bio_put(&dio->bio);
} else {
struct task_struct *waiter = dio->waiter;
WRITE_ONCE(dio->waiter, NULL);
blk_wake_io_task(waiter);
}
}
if (should_dirty) {
bio_check_pages_dirty(bio);
} else {
bio_release_pages(bio, false);
bio_put(bio);
}
}
static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
unsigned int nr_pages)
{
struct file *file = iocb->ki_filp;
struct inode *inode = bdev_file_inode(file);
struct block_device *bdev = I_BDEV(inode);
struct blk_plug plug;
struct blkdev_dio *dio;
struct bio *bio;
bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
loff_t pos = iocb->ki_pos;
blk_qc_t qc = BLK_QC_T_NONE;
int ret = 0;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
dio = container_of(bio, struct blkdev_dio, bio);
dio->is_sync = is_sync = is_sync_kiocb(iocb);
if (dio->is_sync) {
dio->waiter = current;
bio_get(bio);
} else {
dio->iocb = iocb;
}
dio->size = 0;
dio->multi_bio = false;
dio->should_dirty = is_read && iter_is_iovec(iter);
/*
* Don't plug for HIPRI/polled IO, as those should go straight
* to issue
*/
if (!is_poll)
blk_start_plug(&plug);
for (;;) {
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = pos >> 9;
bio->bi_write_hint = iocb->ki_hint;
bio->bi_private = dio;
bio->bi_end_io = blkdev_bio_end_io;
bio->bi_ioprio = iocb->ki_ioprio;
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
break;
}
if (is_read) {
bio->bi_opf = REQ_OP_READ;
if (dio->should_dirty)
bio_set_pages_dirty(bio);
} else {
bio->bi_opf = dio_bio_write_op(iocb);
task_io_account_write(bio->bi_iter.bi_size);
}
if (iocb->ki_flags & IOCB_NOWAIT)
bio->bi_opf |= REQ_NOWAIT;
dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
if (!nr_pages) {
bool polled = false;
if (iocb->ki_flags & IOCB_HIPRI) {
bio_set_polled(bio, iocb);
polled = true;
}
qc = submit_bio(bio);
if (polled)
WRITE_ONCE(iocb->ki_cookie, qc);
break;
}
if (!dio->multi_bio) {
/*
* AIO needs an extra reference to ensure the dio
* structure which is embedded into the first bio
* stays around.
*/
if (!is_sync)
bio_get(bio);
dio->multi_bio = true;
atomic_set(&dio->ref, 2);
} else {
atomic_inc(&dio->ref);
}
submit_bio(bio);
bio = bio_alloc(GFP_KERNEL, nr_pages);
}
if (!is_poll)
blk_finish_plug(&plug);
if (!is_sync)
return -EIOCBQUEUED;
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(dio->waiter))
break;
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!blk_poll(bdev_get_queue(bdev), qc, true))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
if (!ret)
ret = blk_status_to_errno(dio->bio.bi_status);
if (likely(!ret))
ret = dio->size;
bio_put(&dio->bio);
return ret;
}
static ssize_t
blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
unsigned int nr_pages;
if (!iov_iter_count(iter))
return 0;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
}
static __init int blkdev_init(void)
{
return bioset_init(&blkdev_dio_pool, 4,
offsetof(struct blkdev_dio, bio),
BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE);
}
module_init(blkdev_init);
int __sync_blockdev(struct block_device *bdev, int wait)
{
if (!bdev)
......@@ -637,81 +301,6 @@ int thaw_bdev(struct block_device *bdev)
}
EXPORT_SYMBOL(thaw_bdev);
static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, blkdev_get_block, wbc);
}
static int blkdev_readpage(struct file * file, struct page * page)
{
return block_read_full_page(page, blkdev_get_block);
}
static void blkdev_readahead(struct readahead_control *rac)
{
mpage_readahead(rac, blkdev_get_block);
}
static int blkdev_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
return block_write_begin(mapping, pos, len, flags, pagep,
blkdev_get_block);
}
static int blkdev_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
int ret;
ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
unlock_page(page);
put_page(page);
return ret;
}
/*
* private llseek:
* for a block special file file_inode(file)->i_size is zero
* so we compute the size by hand (just as in block_read/write above)
*/
static loff_t block_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *bd_inode = bdev_file_inode(file);
loff_t retval;
inode_lock(bd_inode);
retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
inode_unlock(bd_inode);
return retval;
}
static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
struct inode *bd_inode = bdev_file_inode(filp);
struct block_device *bdev = I_BDEV(bd_inode);
int error;
error = file_write_and_wait_range(filp, start, end);
if (error)
return error;
/*
* There is no need to serialise calls to blkdev_issue_flush with
* i_mutex and doing so causes performance issues with concurrent
* O_SYNC writers to a block device.
*/
error = blkdev_issue_flush(bdev);
if (error == -EOPNOTSUPP)
error = 0;
return error;
}
/**
* bdev_read_page() - Start reading a page from a block device
* @bdev: The device to read the page from
......@@ -1305,35 +894,6 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
}
EXPORT_SYMBOL(blkdev_get_by_path);
static int blkdev_open(struct inode * inode, struct file * filp)
{
struct block_device *bdev;
/*
* Preserve backwards compatibility and allow large file access
* even if userspace doesn't ask for it explicitly. Some mkfs
* binary needs it. We might want to drop this workaround
* during an unstable branch.
*/
filp->f_flags |= O_LARGEFILE;
filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
if (filp->f_flags & O_NDELAY)
filp->f_mode |= FMODE_NDELAY;
if (filp->f_flags & O_EXCL)
filp->f_mode |= FMODE_EXCL;
if ((filp->f_flags & O_ACCMODE) == 3)
filp->f_mode |= FMODE_WRITE_IOCTL;
bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
filp->f_mapping = bdev->bd_inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
return 0;
}
void blkdev_put(struct block_device *bdev, fmode_t mode)
{
struct gendisk *disk = bdev->bd_disk;
......@@ -1397,203 +957,6 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
}
EXPORT_SYMBOL(blkdev_put);
static int blkdev_close(struct inode * inode, struct file * filp)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
blkdev_put(bdev, filp->f_mode);
return 0;
}
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
fmode_t mode = file->f_mode;
/*
* O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
* to updated it before every ioctl.
*/
if (file->f_flags & O_NDELAY)
mode |= FMODE_NDELAY;
else
mode &= ~FMODE_NDELAY;
return blkdev_ioctl(bdev, mode, cmd, arg);
}
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
*
* Does not take i_mutex for the write and thus is not for general purpose
* use.
*/
static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
struct blk_plug plug;
size_t shorted = 0;
ssize_t ret;
if (bdev_read_only(I_BDEV(bd_inode)))
return -EPERM;
if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
return -ETXTBSY;
if (!iov_iter_count(from))
return 0;
if (iocb->ki_pos >= size)
return -ENOSPC;
if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
return -EOPNOTSUPP;
size -= iocb->ki_pos;
if (iov_iter_count(from) > size) {
shorted = iov_iter_count(from) - size;
iov_iter_truncate(from, size);
}
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
iov_iter_reexpand(from, iov_iter_count(from) + shorted);
blk_finish_plug(&plug);
return ret;
}
static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
loff_t pos = iocb->ki_pos;
size_t shorted = 0;
ssize_t ret;
if (pos >= size)
return 0;
size -= pos;
if (iov_iter_count(to) > size) {
shorted = iov_iter_count(to) - size;
iov_iter_truncate(to, size);
}
ret = generic_file_read_iter(iocb, to);
iov_iter_reexpand(to, iov_iter_count(to) + shorted);
return ret;
}
static int blkdev_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
return generic_writepages(mapping, wbc);
}
static const struct address_space_operations def_blk_aops = {
.set_page_dirty = __set_page_dirty_buffers,
.readpage = blkdev_readpage,
.readahead = blkdev_readahead,
.writepage = blkdev_writepage,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
.writepages = blkdev_writepages,
.direct_IO = blkdev_direct_IO,
.migratepage = buffer_migrate_page_norefs,
.is_dirty_writeback = buffer_check_dirty_writeback,
};
#define BLKDEV_FALLOC_FL_SUPPORTED \
(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \
FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
static long blkdev_fallocate(struct file *file, int mode, loff_t start,
loff_t len)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
loff_t end = start + len - 1;
loff_t isize;
int error;
/* Fail if we don't recognize the flags. */
if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
return -EOPNOTSUPP;
/* Don't go off the end of the device. */
isize = i_size_read(bdev->bd_inode);
if (start >= isize)
return -EINVAL;
if (end >= isize) {
if (mode & FALLOC_FL_KEEP_SIZE) {
len = isize - start;
end = start + len - 1;
} else
return -EINVAL;
}
/*
* Don't allow IO that isn't aligned to logical block size.
*/
if ((start | len) & (bdev_logical_block_size(bdev) - 1))
return -EINVAL;
/* Invalidate the page cache, including dirty pages. */
error = truncate_bdev_range(bdev, file->f_mode, start, end);
if (error)
return error;
switch (mode) {
case FALLOC_FL_ZERO_RANGE:
case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
GFP_KERNEL, 0);
break;
default:
return -EOPNOTSUPP;
}
if (error)
return error;
/*
* Invalidate the page cache again; if someone wandered in and dirtied
* a page, we just discard it - userspace has no way of knowing whether
* the write happened before or after discard completing...
*/
return truncate_bdev_range(bdev, file->f_mode, start, end);
}
const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = block_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
.iopoll = blkdev_iopoll,
.mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_blkdev_ioctl,
#endif
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = blkdev_fallocate,
};
/**
* lookup_bdev - lookup a struct block_device by name
* @pathname: special file representing the block device
......
......@@ -2135,6 +2135,18 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
}
}
/*
* Allow 4x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
* queues. This is important for md arrays to benefit from merging
* requests.
*/
static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
{
if (plug->multiple_queues)
return BLK_MAX_REQUEST_COUNT * 4;
return BLK_MAX_REQUEST_COUNT;
}
/**
* blk_mq_submit_bio - Create and send a request to block device.
* @bio: Bio pointer.
......@@ -2231,7 +2243,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
else
last = list_entry_rq(plug->mq_list.prev);
if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
if (request_count >= blk_plug_max_rq_count(plug) || (last &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_flush_plug_list(plug, false);
trace_block_plug(q);
......
......@@ -2458,6 +2458,7 @@ int blk_throtl_init(struct request_queue *q)
void blk_throtl_exit(struct request_queue *q)
{
BUG_ON(!q->td);
del_timer_sync(&q->td->service_queue.pending_timer);
throtl_shutdown_wq(q);
blkcg_deactivate_policy(q, &blkcg_policy_throtl);
free_percpu(q->td->latency_buckets[READ]);
......
......@@ -373,4 +373,6 @@ static inline void bio_clear_hipri(struct bio *bio)
bio->bi_opf &= ~REQ_HIPRI;
}
extern const struct address_space_operations def_blk_aops;
#endif /* BLK_INTERNAL_H */
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
* Copyright (C) 2016 - 2020 Christoph Hellwig
*/
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/falloc.h>
#include <linux/suspend.h>
#include "blk.h"
static struct inode *bdev_file_inode(struct file *file)
{
return file->f_mapping->host;
}
static int blkdev_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
bh->b_bdev = I_BDEV(inode);
bh->b_blocknr = iblock;
set_buffer_mapped(bh);
return 0;
}
static unsigned int dio_bio_write_op(struct kiocb *iocb)
{
unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
/* avoid the need for a I/O completion work item */
if (iocb->ki_flags & IOCB_DSYNC)
op |= REQ_FUA;
return op;
}
#define DIO_INLINE_BIO_VECS 4
static void blkdev_bio_end_io_simple(struct bio *bio)
{
struct task_struct *waiter = bio->bi_private;
WRITE_ONCE(bio->bi_private, NULL);
blk_wake_io_task(waiter);
}
static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
struct iov_iter *iter, unsigned int nr_pages)
{
struct file *file = iocb->ki_filp;
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
loff_t pos = iocb->ki_pos;
bool should_dirty = false;
struct bio bio;
ssize_t ret;
blk_qc_t qc;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
if (nr_pages <= DIO_INLINE_BIO_VECS)
vecs = inline_vecs;
else {
vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
GFP_KERNEL);
if (!vecs)
return -ENOMEM;
}
bio_init(&bio, vecs, nr_pages);
bio_set_dev(&bio, bdev);
bio.bi_iter.bi_sector = pos >> 9;
bio.bi_write_hint = iocb->ki_hint;
bio.bi_private = current;
bio.bi_end_io = blkdev_bio_end_io_simple;
bio.bi_ioprio = iocb->ki_ioprio;
ret = bio_iov_iter_get_pages(&bio, iter);
if (unlikely(ret))
goto out;
ret = bio.bi_iter.bi_size;
if (iov_iter_rw(iter) == READ) {
bio.bi_opf = REQ_OP_READ;
if (iter_is_iovec(iter))
should_dirty = true;
} else {
bio.bi_opf = dio_bio_write_op(iocb);
task_io_account_write(ret);
}
if (iocb->ki_flags & IOCB_NOWAIT)
bio.bi_opf |= REQ_NOWAIT;
if (iocb->ki_flags & IOCB_HIPRI)
bio_set_polled(&bio, iocb);
qc = submit_bio(&bio);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio.bi_private))
break;
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!blk_poll(bdev_get_queue(bdev), qc, true))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
bio_release_pages(&bio, should_dirty);
if (unlikely(bio.bi_status))
ret = blk_status_to_errno(bio.bi_status);
out:
if (vecs != inline_vecs)
kfree(vecs);
bio_uninit(&bio);
return ret;
}
struct blkdev_dio {
union {
struct kiocb *iocb;
struct task_struct *waiter;
};
size_t size;
atomic_t ref;
bool multi_bio : 1;
bool should_dirty : 1;
bool is_sync : 1;
struct bio bio;
};
static struct bio_set blkdev_dio_pool;
static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
{
struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
struct request_queue *q = bdev_get_queue(bdev);
return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
}
static void blkdev_bio_end_io(struct bio *bio)
{
struct blkdev_dio *dio = bio->bi_private;
bool should_dirty = dio->should_dirty;
if (bio->bi_status && !dio->bio.bi_status)
dio->bio.bi_status = bio->bi_status;
if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
if (!dio->is_sync) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
if (likely(!dio->bio.bi_status)) {
ret = dio->size;
iocb->ki_pos += ret;
} else {
ret = blk_status_to_errno(dio->bio.bi_status);
}
dio->iocb->ki_complete(iocb, ret, 0);
if (dio->multi_bio)
bio_put(&dio->bio);
} else {
struct task_struct *waiter = dio->waiter;
WRITE_ONCE(dio->waiter, NULL);
blk_wake_io_task(waiter);
}
}
if (should_dirty) {
bio_check_pages_dirty(bio);
} else {
bio_release_pages(bio, false);
bio_put(bio);
}
}
static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
unsigned int nr_pages)
{
struct file *file = iocb->ki_filp;
struct inode *inode = bdev_file_inode(file);
struct block_device *bdev = I_BDEV(inode);
struct blk_plug plug;
struct blkdev_dio *dio;
struct bio *bio;
bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
loff_t pos = iocb->ki_pos;
blk_qc_t qc = BLK_QC_T_NONE;
int ret = 0;
if ((pos | iov_iter_alignment(iter)) &
(bdev_logical_block_size(bdev) - 1))
return -EINVAL;
bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
dio = container_of(bio, struct blkdev_dio, bio);
dio->is_sync = is_sync = is_sync_kiocb(iocb);
if (dio->is_sync) {
dio->waiter = current;
bio_get(bio);
} else {
dio->iocb = iocb;
}
dio->size = 0;
dio->multi_bio = false;
dio->should_dirty = is_read && iter_is_iovec(iter);
/*
* Don't plug for HIPRI/polled IO, as those should go straight
* to issue
*/
if (!is_poll)
blk_start_plug(&plug);
for (;;) {
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = pos >> 9;
bio->bi_write_hint = iocb->ki_hint;
bio->bi_private = dio;
bio->bi_end_io = blkdev_bio_end_io;
bio->bi_ioprio = iocb->ki_ioprio;
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
break;
}
if (is_read) {
bio->bi_opf = REQ_OP_READ;
if (dio->should_dirty)
bio_set_pages_dirty(bio);
} else {
bio->bi_opf = dio_bio_write_op(iocb);
task_io_account_write(bio->bi_iter.bi_size);
}
if (iocb->ki_flags & IOCB_NOWAIT)
bio->bi_opf |= REQ_NOWAIT;
dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
if (!nr_pages) {
bool polled = false;
if (iocb->ki_flags & IOCB_HIPRI) {
bio_set_polled(bio, iocb);
polled = true;
}
qc = submit_bio(bio);
if (polled)
WRITE_ONCE(iocb->ki_cookie, qc);
break;
}
if (!dio->multi_bio) {
/*
* AIO needs an extra reference to ensure the dio
* structure which is embedded into the first bio
* stays around.
*/
if (!is_sync)
bio_get(bio);
dio->multi_bio = true;
atomic_set(&dio->ref, 2);
} else {
atomic_inc(&dio->ref);
}
submit_bio(bio);
bio = bio_alloc(GFP_KERNEL, nr_pages);
}
if (!is_poll)
blk_finish_plug(&plug);
if (!is_sync)
return -EIOCBQUEUED;
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(dio->waiter))
break;
if (!(iocb->ki_flags & IOCB_HIPRI) ||
!blk_poll(bdev_get_queue(bdev), qc, true))
blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
if (!ret)
ret = blk_status_to_errno(dio->bio.bi_status);
if (likely(!ret))
ret = dio->size;
bio_put(&dio->bio);
return ret;
}
static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
unsigned int nr_pages;
if (!iov_iter_count(iter))
return 0;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
}
static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
{
return block_write_full_page(page, blkdev_get_block, wbc);
}
static int blkdev_readpage(struct file * file, struct page * page)
{
return block_read_full_page(page, blkdev_get_block);
}
static void blkdev_readahead(struct readahead_control *rac)
{
mpage_readahead(rac, blkdev_get_block);
}
static int blkdev_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags, struct page **pagep,
void **fsdata)
{
return block_write_begin(mapping, pos, len, flags, pagep,
blkdev_get_block);
}
static int blkdev_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied, struct page *page,
void *fsdata)
{
int ret;
ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
unlock_page(page);
put_page(page);
return ret;
}
static int blkdev_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
return generic_writepages(mapping, wbc);
}
const struct address_space_operations def_blk_aops = {
.set_page_dirty = __set_page_dirty_buffers,
.readpage = blkdev_readpage,
.readahead = blkdev_readahead,
.writepage = blkdev_writepage,
.write_begin = blkdev_write_begin,
.write_end = blkdev_write_end,
.writepages = blkdev_writepages,
.direct_IO = blkdev_direct_IO,
.migratepage = buffer_migrate_page_norefs,
.is_dirty_writeback = buffer_check_dirty_writeback,
};
/*
* for a block special file file_inode(file)->i_size is zero
* so we compute the size by hand (just as in block_read/write above)
*/
static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *bd_inode = bdev_file_inode(file);
loff_t retval;
inode_lock(bd_inode);
retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
inode_unlock(bd_inode);
return retval;
}
static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
int datasync)
{
struct inode *bd_inode = bdev_file_inode(filp);
struct block_device *bdev = I_BDEV(bd_inode);
int error;
error = file_write_and_wait_range(filp, start, end);
if (error)
return error;
/*
* There is no need to serialise calls to blkdev_issue_flush with
* i_mutex and doing so causes performance issues with concurrent
* O_SYNC writers to a block device.
*/
error = blkdev_issue_flush(bdev);
if (error == -EOPNOTSUPP)
error = 0;
return error;
}
static int blkdev_open(struct inode *inode, struct file *filp)
{
struct block_device *bdev;
/*
* Preserve backwards compatibility and allow large file access
* even if userspace doesn't ask for it explicitly. Some mkfs
* binary needs it. We might want to drop this workaround
* during an unstable branch.
*/
filp->f_flags |= O_LARGEFILE;
filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
if (filp->f_flags & O_NDELAY)
filp->f_mode |= FMODE_NDELAY;
if (filp->f_flags & O_EXCL)
filp->f_mode |= FMODE_EXCL;
if ((filp->f_flags & O_ACCMODE) == 3)
filp->f_mode |= FMODE_WRITE_IOCTL;
bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
filp->f_mapping = bdev->bd_inode->i_mapping;
filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
return 0;
}
static int blkdev_close(struct inode *inode, struct file *filp)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
blkdev_put(bdev, filp->f_mode);
return 0;
}
static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
fmode_t mode = file->f_mode;
/*
* O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
* to updated it before every ioctl.
*/
if (file->f_flags & O_NDELAY)
mode |= FMODE_NDELAY;
else
mode &= ~FMODE_NDELAY;
return blkdev_ioctl(bdev, mode, cmd, arg);
}
/*
* Write data to the block device. Only intended for the block device itself
* and the raw driver which basically is a fake block device.
*
* Does not take i_mutex for the write and thus is not for general purpose
* use.
*/
static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
struct blk_plug plug;
size_t shorted = 0;
ssize_t ret;
if (bdev_read_only(I_BDEV(bd_inode)))
return -EPERM;
if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
return -ETXTBSY;
if (!iov_iter_count(from))
return 0;
if (iocb->ki_pos >= size)
return -ENOSPC;
if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
return -EOPNOTSUPP;
size -= iocb->ki_pos;
if (iov_iter_count(from) > size) {
shorted = iov_iter_count(from) - size;
iov_iter_truncate(from, size);
}
blk_start_plug(&plug);
ret = __generic_file_write_iter(iocb, from);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
iov_iter_reexpand(from, iov_iter_count(from) + shorted);
blk_finish_plug(&plug);
return ret;
}
static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *bd_inode = bdev_file_inode(file);
loff_t size = i_size_read(bd_inode);
loff_t pos = iocb->ki_pos;
size_t shorted = 0;
ssize_t ret;
if (pos >= size)
return 0;
size -= pos;
if (iov_iter_count(to) > size) {
shorted = iov_iter_count(to) - size;
iov_iter_truncate(to, size);
}
ret = generic_file_read_iter(iocb, to);
iov_iter_reexpand(to, iov_iter_count(to) + shorted);
return ret;
}
#define BLKDEV_FALLOC_FL_SUPPORTED \
(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \
FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
static long blkdev_fallocate(struct file *file, int mode, loff_t start,
loff_t len)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
loff_t end = start + len - 1;
loff_t isize;
int error;
/* Fail if we don't recognize the flags. */
if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
return -EOPNOTSUPP;
/* Don't go off the end of the device. */
isize = i_size_read(bdev->bd_inode);
if (start >= isize)
return -EINVAL;
if (end >= isize) {
if (mode & FALLOC_FL_KEEP_SIZE) {
len = isize - start;
end = start + len - 1;
} else
return -EINVAL;
}
/*
* Don't allow IO that isn't aligned to logical block size.
*/
if ((start | len) & (bdev_logical_block_size(bdev) - 1))
return -EINVAL;
/* Invalidate the page cache, including dirty pages. */
error = truncate_bdev_range(bdev, file->f_mode, start, end);
if (error)
return error;
switch (mode) {
case FALLOC_FL_ZERO_RANGE:
case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
GFP_KERNEL, 0);
break;
default:
return -EOPNOTSUPP;
}
if (error)
return error;
/*
* Invalidate the page cache again; if someone wandered in and dirtied
* a page, we just discard it - userspace has no way of knowing whether
* the write happened before or after discard completing...
*/
return truncate_bdev_range(bdev, file->f_mode, start, end);
}
const struct file_operations def_blk_fops = {
.open = blkdev_open,
.release = blkdev_close,
.llseek = blkdev_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
.iopoll = blkdev_iopoll,
.mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = compat_blkdev_ioctl,
#endif
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = blkdev_fallocate,
};
static __init int blkdev_init(void)
{
return bioset_init(&blkdev_dio_pool, 4,
offsetof(struct blkdev_dio, bio),
BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE);
}
module_init(blkdev_init);
......@@ -183,6 +183,7 @@ static struct blk_major_name {
void (*probe)(dev_t devt);
} *major_names[BLKDEV_MAJOR_HASH_SIZE];
static DEFINE_MUTEX(major_names_lock);
static DEFINE_SPINLOCK(major_names_spinlock);
/* index in the above - for now: assume no multimajor ranges */
static inline int major_to_index(unsigned major)
......@@ -195,11 +196,11 @@ void blkdev_show(struct seq_file *seqf, off_t offset)
{
struct blk_major_name *dp;
mutex_lock(&major_names_lock);
spin_lock(&major_names_spinlock);
for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
if (dp->major == offset)
seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
mutex_unlock(&major_names_lock);
spin_unlock(&major_names_spinlock);
}
#endif /* CONFIG_PROC_FS */
......@@ -271,6 +272,7 @@ int __register_blkdev(unsigned int major, const char *name,
p->next = NULL;
index = major_to_index(major);
spin_lock(&major_names_spinlock);
for (n = &major_names[index]; *n; n = &(*n)->next) {
if ((*n)->major == major)
break;
......@@ -279,6 +281,7 @@ int __register_blkdev(unsigned int major, const char *name,
*n = p;
else
ret = -EBUSY;
spin_unlock(&major_names_spinlock);
if (ret < 0) {
printk("register_blkdev: cannot get major %u for %s\n",
......@@ -298,6 +301,7 @@ void unregister_blkdev(unsigned int major, const char *name)
int index = major_to_index(major);
mutex_lock(&major_names_lock);
spin_lock(&major_names_spinlock);
for (n = &major_names[index]; *n; n = &(*n)->next)
if ((*n)->major == major)
break;
......@@ -307,6 +311,7 @@ void unregister_blkdev(unsigned int major, const char *name)
p = *n;
*n = p->next;
}
spin_unlock(&major_names_spinlock);
mutex_unlock(&major_names_lock);
kfree(p);
}
......
......@@ -129,8 +129,8 @@ static int __init n64cart_probe(struct platform_device *pdev)
}
reg_base = devm_platform_ioremap_resource(pdev, 0);
if (!reg_base)
return -EINVAL;
if (IS_ERR(reg_base))
return PTR_ERR(reg_base);
disk = blk_alloc_disk(NUMA_NO_NODE);
if (!disk)
......
......@@ -116,6 +116,8 @@ static struct class *nvme_ns_chr_class;
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
unsigned nsid);
static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
struct nvme_command *cmd);
/*
* Prepare a queue for teardown.
......@@ -1152,7 +1154,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
return effects;
}
static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
struct nvme_command *cmd, int status)
{
if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
nvme_unfreeze(ctrl);
......@@ -1167,6 +1170,26 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
nvme_queue_scan(ctrl);
flush_work(&ctrl->scan_work);
}
switch (cmd->common.opcode) {
case nvme_admin_set_features:
switch (le32_to_cpu(cmd->common.cdw10) & 0xFF) {
case NVME_FEAT_KATO:
/*
* Keep alive commands interval on the host should be
* updated when KATO is modified by Set Features
* commands.
*/
if (!status)
nvme_update_keep_alive(ctrl, cmd);
break;
default:
break;
}
break;
default:
break;
}
}
int nvme_execute_passthru_rq(struct request *rq)
......@@ -1181,7 +1204,7 @@ int nvme_execute_passthru_rq(struct request *rq)
effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
ret = nvme_execute_rq(disk, rq, false);
if (effects) /* nothing to be done for zero cmd effects */
nvme_passthru_end(ctrl, effects);
nvme_passthru_end(ctrl, effects, cmd, ret);
return ret;
}
......@@ -1269,6 +1292,21 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
struct nvme_command *cmd)
{
unsigned int new_kato =
DIV_ROUND_UP(le32_to_cpu(cmd->common.cdw11), 1000);
dev_info(ctrl->device,
"keep alive interval updated from %u ms to %u ms\n",
ctrl->kato * 1000 / 2, new_kato * 1000 / 2);
nvme_stop_keep_alive(ctrl);
ctrl->kato = new_kato;
nvme_start_keep_alive(ctrl);
}
/*
* In NVMe 1.0 the CNS field was just a binary controller or namespace
* flag, thus sending any new CNS opcodes has a big chance of not working.
......@@ -1302,11 +1340,6 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
return error;
}
static bool nvme_multi_css(struct nvme_ctrl *ctrl)
{
return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
}
static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
struct nvme_ns_id_desc *cur, bool *csi_seen)
{
......@@ -1874,6 +1907,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
goto out_unfreeze;
}
set_bit(NVME_NS_READY, &ns->flags);
blk_mq_unfreeze_queue(ns->disk->queue);
if (blk_queue_is_zoned(ns->queue)) {
......@@ -1885,6 +1919,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id)
if (nvme_ns_head_multipath(ns->head)) {
blk_mq_freeze_queue(ns->head->disk->queue);
nvme_update_disk_info(ns->head->disk, ns, id);
nvme_mpath_revalidate_paths(ns);
blk_stack_limits(&ns->head->disk->queue->limits,
&ns->queue->limits, 0);
disk_update_readahead(ns->head->disk);
......@@ -3763,7 +3798,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
nvme_get_ctrl(ctrl);
device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);
if (device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups))
goto out_cleanup_ns_from_list;
if (!nvme_ns_head_multipath(ns->head))
nvme_add_ns_cdev(ns);
......@@ -3773,6 +3810,11 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
return;
out_cleanup_ns_from_list:
nvme_put_ctrl(ctrl);
down_write(&ctrl->namespaces_rwsem);
list_del_init(&ns->list);
up_write(&ctrl->namespaces_rwsem);
out_unlink_ns:
mutex_lock(&ctrl->subsys->lock);
list_del_rcu(&ns->siblings);
......@@ -3795,6 +3837,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
clear_bit(NVME_NS_READY, &ns->flags);
set_capacity(ns->disk, 0);
nvme_fault_inject_fini(&ns->fault_inject);
......@@ -3802,9 +3845,12 @@ static void nvme_ns_remove(struct nvme_ns *ns)
list_del_rcu(&ns->siblings);
mutex_unlock(&ns->ctrl->subsys->lock);
synchronize_rcu(); /* guarantee not available in head->list */
nvme_mpath_clear_current_path(ns);
synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
/* guarantee not available in head->list */
synchronize_rcu();
/* wait for concurrent submissions */
if (nvme_mpath_clear_current_path(ns))
synchronize_srcu(&ns->head->srcu);
if (!nvme_ns_head_multipath(ns->head))
nvme_cdev_del(&ns->cdev, &ns->cdev_device);
......
......@@ -147,6 +147,21 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
mutex_unlock(&ctrl->scan_lock);
}
void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
{
struct nvme_ns_head *head = ns->head;
sector_t capacity = get_capacity(head->disk);
int node;
list_for_each_entry_rcu(ns, &head->list, siblings) {
if (capacity != get_capacity(ns->disk))
clear_bit(NVME_NS_READY, &ns->flags);
}
for_each_node(node)
rcu_assign_pointer(head->current_path[node], NULL);
}
static bool nvme_path_is_disabled(struct nvme_ns *ns)
{
/*
......@@ -158,7 +173,7 @@ static bool nvme_path_is_disabled(struct nvme_ns *ns)
ns->ctrl->state != NVME_CTRL_DELETING)
return true;
if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
test_bit(NVME_NS_REMOVING, &ns->flags))
!test_bit(NVME_NS_READY, &ns->flags))
return true;
return false;
}
......@@ -465,6 +480,8 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
ctrl->subsys->instance, head->instance);
blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
/* set to a default value of 512 until the disk is validated */
blk_queue_logical_block_size(head->disk->queue, 512);
blk_set_stacking_limits(&head->disk->queue->limits);
......
......@@ -456,6 +456,7 @@ struct nvme_ns {
#define NVME_NS_DEAD 1
#define NVME_NS_ANA_PENDING 2
#define NVME_NS_FORCE_RO 3
#define NVME_NS_READY 4
struct cdev cdev;
struct device cdev_device;
......@@ -748,6 +749,7 @@ void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl);
void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
void nvme_mpath_stop(struct nvme_ctrl *ctrl);
bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
void nvme_mpath_revalidate_paths(struct nvme_ns *ns);
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
......@@ -795,6 +797,9 @@ static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
{
return false;
}
static inline void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
{
}
static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
}
......@@ -887,4 +892,9 @@ struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
void nvme_put_ns(struct nvme_ns *ns);
static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
{
return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
}
#endif /* _NVME_H */
......@@ -45,6 +45,7 @@ struct nvme_tcp_request {
u32 pdu_len;
u32 pdu_sent;
u16 ttag;
__le16 status;
struct list_head entry;
struct llist_node lentry;
__le32 ddgst;
......@@ -485,6 +486,7 @@ static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl)
static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
struct nvme_completion *cqe)
{
struct nvme_tcp_request *req;
struct request *rq;
rq = nvme_find_rq(nvme_tcp_tagset(queue), cqe->command_id);
......@@ -496,7 +498,11 @@ static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
return -EINVAL;
}
if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
req = blk_mq_rq_to_pdu(rq);
if (req->status == cpu_to_le16(NVME_SC_SUCCESS))
req->status = cqe->status;
if (!nvme_try_complete_req(rq, req->status, cqe->result))
nvme_complete_rq(rq);
queue->nr_cqe++;
......@@ -758,7 +764,8 @@ static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb,
queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
} else {
if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
nvme_tcp_end_request(rq,
le16_to_cpu(req->status));
queue->nr_cqe++;
}
nvme_tcp_init_recv_ctx(queue);
......@@ -788,18 +795,24 @@ static int nvme_tcp_recv_ddgst(struct nvme_tcp_queue *queue,
return 0;
if (queue->recv_ddgst != queue->exp_ddgst) {
struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
pdu->command_id);
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
req->status = cpu_to_le16(NVME_SC_DATA_XFER_ERROR);
dev_err(queue->ctrl->ctrl.device,
"data digest error: recv %#x expected %#x\n",
le32_to_cpu(queue->recv_ddgst),
le32_to_cpu(queue->exp_ddgst));
return -EIO;
}
if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
pdu->command_id);
struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
nvme_tcp_end_request(rq, le16_to_cpu(req->status));
queue->nr_cqe++;
}
......@@ -2293,6 +2306,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
return ret;
req->state = NVME_TCP_SEND_CMD_PDU;
req->status = cpu_to_le16(NVME_SC_SUCCESS);
req->offset = 0;
req->data_sent = 0;
req->pdu_len = 0;
......
......@@ -1015,7 +1015,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
if (unlikely(ret))
return ret;
if (nvmet_req_passthru_ctrl(req))
if (nvmet_is_passthru_req(req))
return nvmet_parse_passthru_admin_cmd(req);
switch (cmd->common.opcode) {
......
......@@ -1028,7 +1028,7 @@ nvmet_subsys_attr_version_store_locked(struct nvmet_subsys *subsys,
}
/* passthru subsystems use the underlying controller's version */
if (nvmet_passthru_ctrl(subsys))
if (nvmet_is_passthru_subsys(subsys))
return -EINVAL;
ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary);
......@@ -1067,7 +1067,8 @@ static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item,
{
struct nvmet_subsys *subsys = to_subsys(item);
return snprintf(page, PAGE_SIZE, "%s\n", subsys->serial);
return snprintf(page, PAGE_SIZE, "%*s\n",
NVMET_SN_MAX_SIZE, subsys->serial);
}
static ssize_t
......
......@@ -553,7 +553,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
mutex_lock(&subsys->lock);
ret = 0;
if (nvmet_passthru_ctrl(subsys)) {
if (nvmet_is_passthru_subsys(subsys)) {
pr_info("cannot enable both passthru and regular namespaces for a single subsystem");
goto out_unlock;
}
......@@ -869,7 +869,7 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
if (unlikely(ret))
return ret;
if (nvmet_req_passthru_ctrl(req))
if (nvmet_is_passthru_req(req))
return nvmet_parse_passthru_io_cmd(req);
ret = nvmet_req_find_ns(req);
......@@ -1206,6 +1206,9 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
ctrl->cap |= (15ULL << 24);
/* maximum queue entries supported: */
ctrl->cap |= NVMET_QUEUE_SIZE - 1;
if (nvmet_is_passthru_subsys(ctrl->subsys))
nvmet_passthrough_override_cap(ctrl);
}
struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn,
......@@ -1363,8 +1366,6 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
goto out_put_subsystem;
mutex_init(&ctrl->lock);
nvmet_init_cap(ctrl);
ctrl->port = req->port;
INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
......@@ -1378,6 +1379,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
nvmet_init_cap(ctrl);
WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
ctrl->changed_ns_list = kmalloc_array(NVME_MAX_CHANGED_NAMESPACES,
......
......@@ -582,7 +582,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys);
void nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys);
u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req);
u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req);
static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys)
static inline bool nvmet_is_passthru_subsys(struct nvmet_subsys *subsys)
{
return subsys->passthru_ctrl;
}
......@@ -601,18 +601,19 @@ static inline u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
{
return 0;
}
static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys)
static inline bool nvmet_is_passthru_subsys(struct nvmet_subsys *subsys)
{
return NULL;
}
#endif /* CONFIG_NVME_TARGET_PASSTHRU */
static inline struct nvme_ctrl *
nvmet_req_passthru_ctrl(struct nvmet_req *req)
static inline bool nvmet_is_passthru_req(struct nvmet_req *req)
{
return nvmet_passthru_ctrl(nvmet_req_subsys(req));
return nvmet_is_passthru_subsys(nvmet_req_subsys(req));
}
void nvmet_passthrough_override_cap(struct nvmet_ctrl *ctrl);
u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
u16 nvmet_report_invalid_opcode(struct nvmet_req *req);
......
......@@ -20,6 +20,16 @@ MODULE_IMPORT_NS(NVME_TARGET_PASSTHRU);
*/
static DEFINE_XARRAY(passthru_subsystems);
void nvmet_passthrough_override_cap(struct nvmet_ctrl *ctrl)
{
/*
* Multiple command set support can only be declared if the underlying
* controller actually supports it.
*/
if (!nvme_multi_css(ctrl->subsys->passthru_ctrl))
ctrl->cap &= ~(1ULL << 43);
}
static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
......@@ -218,7 +228,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq)
static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
{
struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
struct nvme_ctrl *ctrl = nvmet_req_subsys(req)->passthru_ctrl;
struct request_queue *q = ctrl->admin_q;
struct nvme_ns *ns = NULL;
struct request *rq = NULL;
......@@ -299,7 +309,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
*/
static void nvmet_passthru_set_host_behaviour(struct nvmet_req *req)
{
struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
struct nvme_ctrl *ctrl = nvmet_req_subsys(req)->passthru_ctrl;
struct nvme_feat_host_behavior *host;
u16 status = NVME_SC_INTERNAL;
int ret;
......
......@@ -17,7 +17,7 @@ obj-y := open.o read_write.o file_table.o super.o \
kernel_read_file.o remap_range.o
ifeq ($(CONFIG_BLOCK),y)
obj-y += buffer.o block_dev.o direct-io.o mpage.o
obj-y += buffer.o direct-io.o mpage.o
else
obj-y += no-block.o
endif
......
......@@ -18,7 +18,7 @@ struct user_namespace;
struct pipe_inode_info;
/*
* block_dev.c
* block/bdev.c
*/
#ifdef CONFIG_BLOCK
extern void __init bdev_cache_init(void);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment