linux_dsm_epyc7002/block/blk-map.c
Linus Torvalds 0a4b6e2f80 Merge branch 'for-4.16/block' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
 "This is the main pull request for block IO related changes for the
  4.16 kernel. Nothing major in this pull request, but a good amount of
  improvements and fixes all over the map. This contains:

   - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and
     Paolo.

   - Support for SMR zones for deadline and mq-deadline from Damien and
     Christoph.

   - Set of fixes for bcache by way of Michael Lyle, including fixes
     from himself, Kent, Rui, Tang, and Coly.

   - Series from Matias for lightnvm with fixes from Hans Holmberg,
     Javier, and Matias. Mostly centered around pblk, and the removing
     rrpc 1.2 in preparation for supporting 2.0.

   - A couple of NVMe pull requests from Christoph. Nothing major in
     here, just fixes and cleanups, and support for command tracing from
     Johannes.

   - Support for blk-throttle for tracking reads and writes separately.
     From Joseph Qi. A few cleanups/fixes also for blk-throttle from
     Weiping.

   - Series from Mike Snitzer that enables dm to register its queue more
     logically, something that's alwways been problematic on dm since
     it's a stacked device.

   - Series from Ming cleaning up some of the bio accessor use, in
     preparation for supporting multipage bvecs.

   - Various fixes from Ming closing up holes around queue mapping and
     quiescing.

   - BSD partition fix from Richard Narron, fixing a problem where we
     can't mount newer (10/11) FreeBSD partitions.

   - Series from Tejun reworking blk-mq timeout handling. The previous
     scheme relied on atomic bits, but it had races where we would think
     a request had timed out if it to reused at the wrong time.

   - null_blk now supports faking timeouts, to enable us to better
     exercise and test that functionality separately. From me.

   - Kill the separate atomic poll bit in the request struct. After
     this, we don't use the atomic bits on blk-mq anymore at all. From
     me.

   - sgl_alloc/free helpers from Bart.

   - Heavily contended tag case scalability improvement from me.

   - Various little fixes and cleanups from Arnd, Bart, Corentin,
     Douglas, Eryu, Goldwyn, and myself"

* 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits)
  block: remove smart1,2.h
  nvme: add tracepoint for nvme_complete_rq
  nvme: add tracepoint for nvme_setup_cmd
  nvme-pci: introduce RECONNECTING state to mark initializing procedure
  nvme-rdma: remove redundant boolean for inline_data
  nvme: don't free uuid pointer before printing it
  nvme-pci: Suspend queues after deleting them
  bsg: use pr_debug instead of hand crafted macros
  blk-mq-debugfs: don't allow write on attributes with seq_operations set
  nvme-pci: Fix queue double allocations
  block: Set BIO_TRACE_COMPLETION on new bio during split
  blk-throttle: use queue_is_rq_based
  block: Remove kblockd_schedule_delayed_work{,_on}()
  blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays
  blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly()
  lib/scatterlist: Fix chaining support in sgl_alloc_order()
  blk-throttle: track read and write request individually
  block: add bdev_read_only() checks to common helpers
  block: fail op_is_write() requests to read-only partitions
  blk-throttle: export io_serviced_recursive, io_service_bytes_recursive
  ...
2018-01-29 11:51:49 -08:00

255 lines
5.9 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Functions related to mapping data to requests
*/
#include <linux/kernel.h>
#include <linux/sched/task_stack.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/uio.h>
#include "blk.h"
/*
* Append a bio to a passthrough request. Only works if the bio can be merged
* into the request based on the driver constraints.
*/
int blk_rq_append_bio(struct request *rq, struct bio **bio)
{
struct bio *orig_bio = *bio;
blk_queue_bounce(rq->q, bio);
if (!rq->bio) {
blk_rq_bio_prep(rq->q, rq, *bio);
} else {
if (!ll_back_merge_fn(rq->q, rq, *bio)) {
if (orig_bio != *bio) {
bio_put(*bio);
*bio = orig_bio;
}
return -EINVAL;
}
rq->biotail->bi_next = *bio;
rq->biotail = *bio;
rq->__data_len += (*bio)->bi_iter.bi_size;
}
return 0;
}
EXPORT_SYMBOL(blk_rq_append_bio);
static int __blk_rq_unmap_user(struct bio *bio)
{
int ret = 0;
if (bio) {
if (bio_flagged(bio, BIO_USER_MAPPED))
bio_unmap_user(bio);
else
ret = bio_uncopy_user(bio);
}
return ret;
}
static int __blk_rq_map_user_iov(struct request *rq,
struct rq_map_data *map_data, struct iov_iter *iter,
gfp_t gfp_mask, bool copy)
{
struct request_queue *q = rq->q;
struct bio *bio, *orig_bio;
int ret;
if (copy)
bio = bio_copy_user_iov(q, map_data, iter, gfp_mask);
else
bio = bio_map_user_iov(q, iter, gfp_mask);
if (IS_ERR(bio))
return PTR_ERR(bio);
bio->bi_opf &= ~REQ_OP_MASK;
bio->bi_opf |= req_op(rq);
orig_bio = bio;
/*
* We link the bounce buffer in and could have to traverse it
* later so we have to get a ref to prevent it from being freed
*/
ret = blk_rq_append_bio(rq, &bio);
if (ret) {
__blk_rq_unmap_user(orig_bio);
return ret;
}
bio_get(bio);
return 0;
}
/**
* blk_rq_map_user_iov - map user data to a request, for passthrough requests
* @q: request queue where request should be inserted
* @rq: request to map data to
* @map_data: pointer to the rq_map_data holding pages (if necessary)
* @iter: iovec iterator
* @gfp_mask: memory allocation flags
*
* Description:
* Data will be mapped directly for zero copy I/O, if possible. Otherwise
* a kernel bounce buffer is used.
*
* A matching blk_rq_unmap_user() must be issued at the end of I/O, while
* still in process context.
*
* Note: The mapped bio may need to be bounced through blk_queue_bounce()
* before being submitted to the device, as pages mapped may be out of
* reach. It's the callers responsibility to make sure this happens. The
* original bio must be passed back in to blk_rq_unmap_user() for proper
* unmapping.
*/
int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
struct rq_map_data *map_data,
const struct iov_iter *iter, gfp_t gfp_mask)
{
bool copy = false;
unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
struct bio *bio = NULL;
struct iov_iter i;
int ret = -EINVAL;
if (!iter_is_iovec(iter))
goto fail;
if (map_data)
copy = true;
else if (iov_iter_alignment(iter) & align)
copy = true;
else if (queue_virt_boundary(q))
copy = queue_virt_boundary(q) & iov_iter_gap_alignment(iter);
i = *iter;
do {
ret =__blk_rq_map_user_iov(rq, map_data, &i, gfp_mask, copy);
if (ret)
goto unmap_rq;
if (!bio)
bio = rq->bio;
} while (iov_iter_count(&i));
if (!bio_flagged(bio, BIO_USER_MAPPED))
rq->rq_flags |= RQF_COPY_USER;
return 0;
unmap_rq:
__blk_rq_unmap_user(bio);
fail:
rq->bio = NULL;
return ret;
}
EXPORT_SYMBOL(blk_rq_map_user_iov);
int blk_rq_map_user(struct request_queue *q, struct request *rq,
struct rq_map_data *map_data, void __user *ubuf,
unsigned long len, gfp_t gfp_mask)
{
struct iovec iov;
struct iov_iter i;
int ret = import_single_range(rq_data_dir(rq), ubuf, len, &iov, &i);
if (unlikely(ret < 0))
return ret;
return blk_rq_map_user_iov(q, rq, map_data, &i, gfp_mask);
}
EXPORT_SYMBOL(blk_rq_map_user);
/**
* blk_rq_unmap_user - unmap a request with user data
* @bio: start of bio list
*
* Description:
* Unmap a rq previously mapped by blk_rq_map_user(). The caller must
* supply the original rq->bio from the blk_rq_map_user() return, since
* the I/O completion may have changed rq->bio.
*/
int blk_rq_unmap_user(struct bio *bio)
{
struct bio *mapped_bio;
int ret = 0, ret2;
while (bio) {
mapped_bio = bio;
if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
mapped_bio = bio->bi_private;
ret2 = __blk_rq_unmap_user(mapped_bio);
if (ret2 && !ret)
ret = ret2;
mapped_bio = bio;
bio = bio->bi_next;
bio_put(mapped_bio);
}
return ret;
}
EXPORT_SYMBOL(blk_rq_unmap_user);
/**
* blk_rq_map_kern - map kernel data to a request, for passthrough requests
* @q: request queue where request should be inserted
* @rq: request to fill
* @kbuf: the kernel buffer
* @len: length of user data
* @gfp_mask: memory allocation flags
*
* Description:
* Data will be mapped directly if possible. Otherwise a bounce
* buffer is used. Can be called multiple times to append multiple
* buffers.
*/
int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
unsigned int len, gfp_t gfp_mask)
{
int reading = rq_data_dir(rq) == READ;
unsigned long addr = (unsigned long) kbuf;
int do_copy = 0;
struct bio *bio, *orig_bio;
int ret;
if (len > (queue_max_hw_sectors(q) << 9))
return -EINVAL;
if (!len || !kbuf)
return -EINVAL;
do_copy = !blk_rq_aligned(q, addr, len) || object_is_on_stack(kbuf);
if (do_copy)
bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
else
bio = bio_map_kern(q, kbuf, len, gfp_mask);
if (IS_ERR(bio))
return PTR_ERR(bio);
bio->bi_opf &= ~REQ_OP_MASK;
bio->bi_opf |= req_op(rq);
if (do_copy)
rq->rq_flags |= RQF_COPY_USER;
orig_bio = bio;
ret = blk_rq_append_bio(rq, &bio);
if (unlikely(ret)) {
/* request is too big */
bio_put(orig_bio);
return ret;
}
return 0;
}
EXPORT_SYMBOL(blk_rq_map_kern);