Merge tag 'for-5.16/drivers-2021-10-29' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - paride driver cleanups (Christoph)

 - Remove cryptoloop support (Christoph)

 - null_blk poll support (me)

 - Now that add_disk() supports proper error handling, add it to various
   drivers (Luis)

 - Make ataflop actually work again (Michael)

 - s390 dasd fixes (Stefan, Heiko)

 - nbd fixes (Yu, Ye)

 - Remove redundant wq flush in mtip32xx (Christophe)

 - NVMe updates
      - fix a multipath partition scanning deadlock (Hannes Reinecke)
      - generate uevent once a multipath namespace is operational again
        (Hannes Reinecke)
      - support unique discovery controller NQNs (Hannes Reinecke)
      - fix use-after-free when a port is removed (Israel Rukshin)
      - clear shadow doorbell memory on resets (Keith Busch)
      - use struct_size (Len Baker)
      - add error handling support for add_disk (Luis Chamberlain)
      - limit the maximal queue size for RDMA controllers (Max Gurtovoy)
      - use a few more symbolic names (Max Gurtovoy)
      - fix error code in nvme_rdma_setup_ctrl (Max Gurtovoy)
      - add support for ->map_queues on FC (Saurav Kashyap)
      - support the current discovery subsystem entry (Hannes Reinecke)
      - use flex_array_size and struct_size (Len Baker)

 - bcache fixes (Christoph, Coly, Chao, Lin, Qing)

 - MD updates (Christoph, Guoqing, Xiao)

 - Misc fixes (Dan, Ding, Jiapeng, Shin'ichiro, Ye)

* tag 'for-5.16/drivers-2021-10-29' of git://git.kernel.dk/linux-block: (117 commits)
  null_blk: Fix handling of submit_queues and poll_queues attributes
  block: ataflop: Fix warning comparing pointer to 0
  bcache: replace snprintf in show functions with sysfs_emit
  bcache: move uapi header bcache.h to bcache code directory
  nvmet: use flex_array_size and struct_size
  nvmet: register discovery subsystem as 'current'
  nvmet: switch check for subsystem type
  nvme: add new discovery log page entry definitions
  block: ataflop: more blk-mq refactoring fixes
  block: remove support for cryptoloop and the xor transfer
  mtd: add add_disk() error handling
  rnbd: add error handling support for add_disk()
  um/drivers/ubd_kern: add error handling support for add_disk()
  m68k/emu/nfblock: add error handling support for add_disk()
  xen-blkfront: add error handling support for add_disk()
  bcache: add error handling support for add_disk()
  dm: add add_disk() error handling
  block: aoe: fixup coccinelle warnings
  nvmet: use struct_size over open coded arithmetic
  nvme: drop scan_lock and always kick requeue list when removing namespaces
  ...
This commit is contained in:
Linus Torvalds
2021-11-01 09:27:38 -07:00
80 changed files with 1529 additions and 1532 deletions

View File

@@ -133,58 +133,6 @@ static void loop_global_unlock(struct loop_device *lo, bool global)
static int max_part;
static int part_shift;
static int transfer_xor(struct loop_device *lo, int cmd,
struct page *raw_page, unsigned raw_off,
struct page *loop_page, unsigned loop_off,
int size, sector_t real_block)
{
char *raw_buf = kmap_atomic(raw_page) + raw_off;
char *loop_buf = kmap_atomic(loop_page) + loop_off;
char *in, *out, *key;
int i, keysize;
if (cmd == READ) {
in = raw_buf;
out = loop_buf;
} else {
in = loop_buf;
out = raw_buf;
}
key = lo->lo_encrypt_key;
keysize = lo->lo_encrypt_key_size;
for (i = 0; i < size; i++)
*out++ = *in++ ^ key[(i & 511) % keysize];
kunmap_atomic(loop_buf);
kunmap_atomic(raw_buf);
cond_resched();
return 0;
}
static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
{
if (unlikely(info->lo_encrypt_key_size <= 0))
return -EINVAL;
return 0;
}
static struct loop_func_table none_funcs = {
.number = LO_CRYPT_NONE,
};
static struct loop_func_table xor_funcs = {
.number = LO_CRYPT_XOR,
.transfer = transfer_xor,
.init = xor_init
};
/* xfer_funcs[0] is special - its release function is never called */
static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
&none_funcs,
&xor_funcs
};
static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
loff_t loopsize;
@@ -228,8 +176,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
/*
* We support direct I/O only if lo_offset is aligned with the
* logical I/O size of backing device, and the logical block
* size of loop is bigger than the backing device's and the loop
* needn't transform transfer.
* size of loop is bigger than the backing device's.
*
* TODO: the above condition may be loosed in the future, and
* direct I/O may be switched runtime at that time because most
@@ -238,8 +185,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
if (dio) {
if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
!(lo->lo_offset & dio_align) &&
mapping->a_ops->direct_IO &&
!lo->transfer)
mapping->a_ops->direct_IO)
use_dio = true;
else
use_dio = false;
@@ -286,24 +232,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
}
static inline int
lo_do_transfer(struct loop_device *lo, int cmd,
struct page *rpage, unsigned roffs,
struct page *lpage, unsigned loffs,
int size, sector_t rblock)
{
int ret;
ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
if (likely(!ret))
return 0;
printk_ratelimited(KERN_ERR
"loop: Transfer error at byte offset %llu, length %i.\n",
(unsigned long long)rblock << 9, size);
return ret;
}
static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
{
struct iov_iter i;
@@ -343,41 +271,6 @@ static int lo_write_simple(struct loop_device *lo, struct request *rq,
return ret;
}
/*
* This is the slow, transforming version that needs to double buffer the
* data as it cannot do the transformations in place without having direct
* access to the destination pages of the backing file.
*/
static int lo_write_transfer(struct loop_device *lo, struct request *rq,
loff_t pos)
{
struct bio_vec bvec, b;
struct req_iterator iter;
struct page *page;
int ret = 0;
page = alloc_page(GFP_NOIO);
if (unlikely(!page))
return -ENOMEM;
rq_for_each_segment(bvec, rq, iter) {
ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page,
bvec.bv_offset, bvec.bv_len, pos >> 9);
if (unlikely(ret))
break;
b.bv_page = page;
b.bv_offset = 0;
b.bv_len = bvec.bv_len;
ret = lo_write_bvec(lo->lo_backing_file, &b, &pos);
if (ret < 0)
break;
}
__free_page(page);
return ret;
}
static int lo_read_simple(struct loop_device *lo, struct request *rq,
loff_t pos)
{
@@ -407,64 +300,12 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq,
return 0;
}
static int lo_read_transfer(struct loop_device *lo, struct request *rq,
loff_t pos)
{
struct bio_vec bvec, b;
struct req_iterator iter;
struct iov_iter i;
struct page *page;
ssize_t len;
int ret = 0;
page = alloc_page(GFP_NOIO);
if (unlikely(!page))
return -ENOMEM;
rq_for_each_segment(bvec, rq, iter) {
loff_t offset = pos;
b.bv_page = page;
b.bv_offset = 0;
b.bv_len = bvec.bv_len;
iov_iter_bvec(&i, READ, &b, 1, b.bv_len);
len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
if (len < 0) {
ret = len;
goto out_free_page;
}
ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page,
bvec.bv_offset, len, offset >> 9);
if (ret)
goto out_free_page;
flush_dcache_page(bvec.bv_page);
if (len != bvec.bv_len) {
struct bio *bio;
__rq_for_each_bio(bio, rq)
zero_fill_bio(bio);
break;
}
}
ret = 0;
out_free_page:
__free_page(page);
return ret;
}
static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
int mode)
{
/*
* We use fallocate to manipulate the space mappings used by the image
* a.k.a. discard/zerorange. However we do not support this if
* encryption is enabled, because it may give an attacker useful
* information.
* a.k.a. discard/zerorange.
*/
struct file *file = lo->lo_backing_file;
struct request_queue *q = lo->lo_queue;
@@ -647,16 +488,12 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
case REQ_OP_DISCARD:
return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
case REQ_OP_WRITE:
if (lo->transfer)
return lo_write_transfer(lo, rq, pos);
else if (cmd->use_aio)
if (cmd->use_aio)
return lo_rw_aio(lo, cmd, pos, WRITE);
else
return lo_write_simple(lo, rq, pos);
case REQ_OP_READ:
if (lo->transfer)
return lo_read_transfer(lo, rq, pos);
else if (cmd->use_aio)
if (cmd->use_aio)
return lo_rw_aio(lo, cmd, pos, READ);
else
return lo_read_simple(lo, rq, pos);
@@ -921,7 +758,7 @@ static void loop_config_discard(struct loop_device *lo)
* not blkdev_issue_discard(). This maintains consistent behavior with
* file-backed loop devices: discarded regions read back as zero.
*/
if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
if (S_ISBLK(inode->i_mode)) {
struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
@@ -930,11 +767,9 @@ static void loop_config_discard(struct loop_device *lo)
/*
* We use punch hole to reclaim the free space used by the
* image a.k.a. discard. However we do not support discard if
* encryption is enabled, because it may give an attacker
* useful information.
* image a.k.a. discard.
*/
} else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
} else if (!file->f_op->fallocate) {
max_discard_sectors = 0;
granularity = 0;
@@ -1071,43 +906,6 @@ static void loop_update_rotational(struct loop_device *lo)
blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
}
static int
loop_release_xfer(struct loop_device *lo)
{
int err = 0;
struct loop_func_table *xfer = lo->lo_encryption;
if (xfer) {
if (xfer->release)
err = xfer->release(lo);
lo->transfer = NULL;
lo->lo_encryption = NULL;
module_put(xfer->owner);
}
return err;
}
static int
loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
const struct loop_info64 *i)
{
int err = 0;
if (xfer) {
struct module *owner = xfer->owner;
if (!try_module_get(owner))
return -EINVAL;
if (xfer->init)
err = xfer->init(lo, i);
if (err)
module_put(owner);
else
lo->lo_encryption = xfer;
}
return err;
}
/**
* loop_set_status_from_info - configure device from loop_info
* @lo: struct loop_device to configure
@@ -1120,55 +918,27 @@ static int
loop_set_status_from_info(struct loop_device *lo,
const struct loop_info64 *info)
{
int err;
struct loop_func_table *xfer;
kuid_t uid = current_uid();
if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
return -EINVAL;
err = loop_release_xfer(lo);
if (err)
return err;
if (info->lo_encrypt_type) {
unsigned int type = info->lo_encrypt_type;
if (type >= MAX_LO_CRYPT)
return -EINVAL;
xfer = xfer_funcs[type];
if (xfer == NULL)
return -EINVAL;
} else
xfer = NULL;
err = loop_init_xfer(lo, xfer, info);
if (err)
return err;
switch (info->lo_encrypt_type) {
case LO_CRYPT_NONE:
break;
case LO_CRYPT_XOR:
pr_warn("support for the xor transformation has been removed.\n");
return -EINVAL;
case LO_CRYPT_CRYPTOAPI:
pr_warn("support for cryptoloop has been removed. Use dm-crypt instead.\n");
return -EINVAL;
default:
return -EINVAL;
}
lo->lo_offset = info->lo_offset;
lo->lo_sizelimit = info->lo_sizelimit;
memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
lo->lo_file_name[LO_NAME_SIZE-1] = 0;
lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
if (!xfer)
xfer = &none_funcs;
lo->transfer = xfer->transfer;
lo->ioctl = xfer->ioctl;
lo->lo_flags = info->lo_flags;
lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
lo->lo_init[0] = info->lo_init[0];
lo->lo_init[1] = info->lo_init[1];
if (info->lo_encrypt_key_size) {
memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
info->lo_encrypt_key_size);
lo->lo_key_owner = uid;
}
return 0;
}
@@ -1367,16 +1137,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
lo->lo_backing_file = NULL;
spin_unlock_irq(&lo->lo_lock);
loop_release_xfer(lo);
lo->transfer = NULL;
lo->ioctl = NULL;
lo->lo_device = NULL;
lo->lo_encryption = NULL;
lo->lo_offset = 0;
lo->lo_sizelimit = 0;
lo->lo_encrypt_key_size = 0;
memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
blk_queue_logical_block_size(lo->lo_queue, 512);
blk_queue_physical_block_size(lo->lo_queue, 512);
@@ -1478,7 +1241,6 @@ static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
int err;
kuid_t uid = current_uid();
int prev_lo_flags;
bool partscan = false;
bool size_changed = false;
@@ -1486,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
err = mutex_lock_killable(&lo->lo_mutex);
if (err)
return err;
if (lo->lo_encrypt_key_size &&
!uid_eq(lo->lo_key_owner, uid) &&
!capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto out_unlock;
}
if (lo->lo_state != Lo_bound) {
err = -ENXIO;
goto out_unlock;
@@ -1577,14 +1333,6 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
info->lo_sizelimit = lo->lo_sizelimit;
info->lo_flags = lo->lo_flags;
memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE);
memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);
info->lo_encrypt_type =
lo->lo_encryption ? lo->lo_encryption->number : 0;
if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) {
info->lo_encrypt_key_size = lo->lo_encrypt_key_size;
memcpy(info->lo_encrypt_key, lo->lo_encrypt_key,
lo->lo_encrypt_key_size);
}
/* Drop lo_mutex while we call into the filesystem. */
path = lo->lo_backing_file->f_path;
@@ -1610,16 +1358,8 @@ loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64)
info64->lo_rdevice = info->lo_rdevice;
info64->lo_offset = info->lo_offset;
info64->lo_sizelimit = 0;
info64->lo_encrypt_type = info->lo_encrypt_type;
info64->lo_encrypt_key_size = info->lo_encrypt_key_size;
info64->lo_flags = info->lo_flags;
info64->lo_init[0] = info->lo_init[0];
info64->lo_init[1] = info->lo_init[1];
if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE);
else
memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE);
memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
}
static int
@@ -1631,16 +1371,8 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
info->lo_inode = info64->lo_inode;
info->lo_rdevice = info64->lo_rdevice;
info->lo_offset = info64->lo_offset;
info->lo_encrypt_type = info64->lo_encrypt_type;
info->lo_encrypt_key_size = info64->lo_encrypt_key_size;
info->lo_flags = info64->lo_flags;
info->lo_init[0] = info64->lo_init[0];
info->lo_init[1] = info64->lo_init[1];
if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
else
memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
/* error in case values were truncated */
if (info->lo_device != info64->lo_device ||
@@ -1789,7 +1521,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
err = loop_set_block_size(lo, arg);
break;
default:
err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
err = -EINVAL;
}
mutex_unlock(&lo->lo_mutex);
return err;
@@ -1865,7 +1597,6 @@ struct compat_loop_info {
compat_ulong_t lo_inode; /* ioctl r/o */
compat_dev_t lo_rdevice; /* ioctl r/o */
compat_int_t lo_offset;
compat_int_t lo_encrypt_type;
compat_int_t lo_encrypt_key_size; /* ioctl w/o */
compat_int_t lo_flags; /* ioctl r/o */
char lo_name[LO_NAME_SIZE];
@@ -1894,16 +1625,8 @@ loop_info64_from_compat(const struct compat_loop_info __user *arg,
info64->lo_rdevice = info.lo_rdevice;
info64->lo_offset = info.lo_offset;
info64->lo_sizelimit = 0;
info64->lo_encrypt_type = info.lo_encrypt_type;
info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
info64->lo_flags = info.lo_flags;
info64->lo_init[0] = info.lo_init[0];
info64->lo_init[1] = info.lo_init[1];
if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
else
memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
return 0;
}
@@ -1923,24 +1646,14 @@ loop_info64_to_compat(const struct loop_info64 *info64,
info.lo_inode = info64->lo_inode;
info.lo_rdevice = info64->lo_rdevice;
info.lo_offset = info64->lo_offset;
info.lo_encrypt_type = info64->lo_encrypt_type;
info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
info.lo_flags = info64->lo_flags;
info.lo_init[0] = info64->lo_init[0];
info.lo_init[1] = info64->lo_init[1];
if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
else
memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
/* error in case values were truncated */
if (info.lo_device != info64->lo_device ||
info.lo_rdevice != info64->lo_rdevice ||
info.lo_inode != info64->lo_inode ||
info.lo_offset != info64->lo_offset ||
info.lo_init[0] != info64->lo_init[0] ||
info.lo_init[1] != info64->lo_init[1])
info.lo_offset != info64->lo_offset)
return -EOVERFLOW;
if (copy_to_user(arg, &info, sizeof(info)))
@@ -2081,43 +1794,6 @@ MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
int loop_register_transfer(struct loop_func_table *funcs)
{
unsigned int n = funcs->number;
if (n >= MAX_LO_CRYPT || xfer_funcs[n])
return -EINVAL;
xfer_funcs[n] = funcs;
return 0;
}
int loop_unregister_transfer(int number)
{
unsigned int n = number;
struct loop_func_table *xfer;
if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
return -EINVAL;
/*
* This function is called from only cleanup_cryptoloop().
* Given that each loop device that has a transfer enabled holds a
* reference to the module implementing it we should never get here
* with a transfer that is set (unless forced module unloading is
* requested). Thus, check module's refcount and warn if this is
* not a clean unloading.
*/
#ifdef CONFIG_MODULE_UNLOAD
if (xfer->owner && module_refcount(xfer->owner) != -1)
pr_err("Danger! Unregistering an in use transfer function.\n");
#endif
xfer_funcs[n] = NULL;
return 0;
}
EXPORT_SYMBOL(loop_register_transfer);
EXPORT_SYMBOL(loop_unregister_transfer);
static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -2374,13 +2050,19 @@ static int loop_add(int i)
disk->event_flags = DISK_EVENT_FLAG_UEVENT;
sprintf(disk->disk_name, "loop%d", i);
/* Make this loop device reachable from pathname. */
add_disk(disk);
err = add_disk(disk);
if (err)
goto out_cleanup_disk;
/* Show this loop device. */
mutex_lock(&loop_ctl_mutex);
lo->idr_visible = true;
mutex_unlock(&loop_ctl_mutex);
return i;
out_cleanup_disk:
blk_cleanup_disk(disk);
out_cleanup_tags:
blk_mq_free_tag_set(&lo->tag_set);
out_free_idr: