mirror of
https://github.com/torvalds/linux.git
synced 2024-11-26 06:02:05 +00:00
288ace2f57
The current netfslib writeback implementation creates writeback requests of contiguous folio data and then separately tiles subrequests over the space twice, once for the server and once for the cache. This creates a few issues: (1) Every time there's a discontiguity or a change between writing to only one destination or writing to both, it must create a new request. This makes it harder to do vectored writes. (2) The folios don't have the writeback mark removed until the end of the request - and a request could be hundreds of megabytes. (3) In future, I want to support a larger cache granularity, which will require aggregation of some folios that contain unmodified data (which only need to go to the cache) and some which contain modifications (which need to be uploaded and stored to the cache) - but, currently, these are treated as discontiguous. There's also a move to get everyone to use writeback_iter() to extract writable folios from the pagecache. That said, currently writeback_iter() has some issues that make it less than ideal: (1) there's no way to cancel the iteration, even if you find a "temporary" error that means the current folio and all subsequent folios are going to fail; (2) there's no way to filter the folios being written back - something that will impact Ceph with it's ordered snap system; (3) and if you get a folio you can't immediately deal with (say you need to flush the preceding writes), you are left with a folio hanging in the locked state for the duration, when really we should unlock it and relock it later. In this new implementation, I use writeback_iter() to pump folios, progressively creating two parallel, but separate streams and cleaning up the finished folios as the subrequests complete. Either or both streams can contain gaps, and the subrequests in each stream can be of variable size, don't need to align with each other and don't need to align with the folios. Indeed, subrequests can cross folio boundaries, may cover several folios or a folio may be spanned by multiple folios, e.g.: +---+---+-----+-----+---+----------+ Folios: | | | | | | | +---+---+-----+-----+---+----------+ +------+------+ +----+----+ Upload: | | |.....| | | +------+------+ +----+----+ +------+------+------+------+------+ Cache: | | | | | | +------+------+------+------+------+ The progressive subrequest construction permits the algorithm to be preparing both the next upload to the server and the next write to the cache whilst the previous ones are already in progress. Throttling can be applied to control the rate of production of subrequests - and, in any case, we probably want to write them to the server in ascending order, particularly if the file will be extended. Content crypto can also be prepared at the same time as the subrequests and run asynchronously, with the prepped requests being stalled until the crypto catches up with them. This might also be useful for transport crypto, but that happens at a lower layer, so probably would be harder to pull off. The algorithm is split into three parts: (1) The issuer. This walks through the data, packaging it up, encrypting it and creating subrequests. The part of this that generates subrequests only deals with file positions and spans and so is usable for DIO/unbuffered writes as well as buffered writes. (2) The collector. This asynchronously collects completed subrequests, unlocks folios, frees crypto buffers and performs any retries. This runs in a work queue so that the issuer can return to the caller for writeback (so that the VM can have its kswapd thread back) or async writes. (3) The retryer. This pauses the issuer, waits for all outstanding subrequests to complete and then goes through the failed subrequests to reissue them. This may involve reprepping them (with cifs, the credits must be renegotiated, and a subrequest may need splitting), and doing RMW for content crypto if there's a conflicting change on the server. [!] Note that some of the functions are prefixed with "new_" to avoid clashes with existing functions. These will be renamed in a later patch that cuts over to the new algorithm. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: Eric Van Hensbergen <ericvh@kernel.org> cc: Latchesar Ionkov <lucho@ionkov.net> cc: Dominique Martinet <asmadeus@codewreck.org> cc: Christian Schoenebeck <linux_oss@crudebyte.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: v9fs@lists.linux.dev cc: linux-afs@lists.infradead.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org
235 lines
6.6 KiB
C
235 lines
6.6 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Object lifetime handling and tracing.
|
|
*
|
|
* Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*/
|
|
|
|
#include <linux/slab.h>
|
|
#include <linux/mempool.h>
|
|
#include <linux/delay.h>
|
|
#include "internal.h"
|
|
|
|
/*
|
|
* Allocate an I/O request and initialise it.
|
|
*/
|
|
struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
|
|
struct file *file,
|
|
loff_t start, size_t len,
|
|
enum netfs_io_origin origin)
|
|
{
|
|
static atomic_t debug_ids;
|
|
struct inode *inode = file ? file_inode(file) : mapping->host;
|
|
struct netfs_inode *ctx = netfs_inode(inode);
|
|
struct netfs_io_request *rreq;
|
|
mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool;
|
|
struct kmem_cache *cache = mempool->pool_data;
|
|
bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE ||
|
|
origin == NETFS_DIO_READ ||
|
|
origin == NETFS_DIO_WRITE);
|
|
bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx);
|
|
int ret;
|
|
|
|
for (;;) {
|
|
rreq = mempool_alloc(mempool, GFP_KERNEL);
|
|
if (rreq)
|
|
break;
|
|
msleep(10);
|
|
}
|
|
|
|
memset(rreq, 0, kmem_cache_size(cache));
|
|
rreq->start = start;
|
|
rreq->len = len;
|
|
rreq->upper_len = len;
|
|
rreq->origin = origin;
|
|
rreq->netfs_ops = ctx->ops;
|
|
rreq->mapping = mapping;
|
|
rreq->inode = inode;
|
|
rreq->i_size = i_size_read(inode);
|
|
rreq->debug_id = atomic_inc_return(&debug_ids);
|
|
rreq->wsize = INT_MAX;
|
|
spin_lock_init(&rreq->lock);
|
|
INIT_LIST_HEAD(&rreq->io_streams[0].subrequests);
|
|
INIT_LIST_HEAD(&rreq->io_streams[1].subrequests);
|
|
INIT_LIST_HEAD(&rreq->subrequests);
|
|
INIT_WORK(&rreq->work, NULL);
|
|
refcount_set(&rreq->ref, 1);
|
|
|
|
__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
|
|
if (cached) {
|
|
__set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags);
|
|
if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags))
|
|
/* Filesystem uses deprecated PG_private_2 marking. */
|
|
__set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
|
|
}
|
|
if (file && file->f_flags & O_NONBLOCK)
|
|
__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
|
|
if (rreq->netfs_ops->init_request) {
|
|
ret = rreq->netfs_ops->init_request(rreq, file);
|
|
if (ret < 0) {
|
|
mempool_free(rreq, rreq->netfs_ops->request_pool ?: &netfs_request_pool);
|
|
return ERR_PTR(ret);
|
|
}
|
|
}
|
|
|
|
trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
|
|
netfs_proc_add_rreq(rreq);
|
|
netfs_stat(&netfs_n_rh_rreq);
|
|
return rreq;
|
|
}
|
|
|
|
void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what)
|
|
{
|
|
int r;
|
|
|
|
__refcount_inc(&rreq->ref, &r);
|
|
trace_netfs_rreq_ref(rreq->debug_id, r + 1, what);
|
|
}
|
|
|
|
void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async)
|
|
{
|
|
struct netfs_io_subrequest *subreq;
|
|
struct netfs_io_stream *stream;
|
|
int s;
|
|
|
|
while (!list_empty(&rreq->subrequests)) {
|
|
subreq = list_first_entry(&rreq->subrequests,
|
|
struct netfs_io_subrequest, rreq_link);
|
|
list_del(&subreq->rreq_link);
|
|
netfs_put_subrequest(subreq, was_async,
|
|
netfs_sreq_trace_put_clear);
|
|
}
|
|
|
|
for (s = 0; s < ARRAY_SIZE(rreq->io_streams); s++) {
|
|
stream = &rreq->io_streams[s];
|
|
while (!list_empty(&stream->subrequests)) {
|
|
subreq = list_first_entry(&stream->subrequests,
|
|
struct netfs_io_subrequest, rreq_link);
|
|
list_del(&subreq->rreq_link);
|
|
netfs_put_subrequest(subreq, was_async,
|
|
netfs_sreq_trace_put_clear);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void netfs_free_request_rcu(struct rcu_head *rcu)
|
|
{
|
|
struct netfs_io_request *rreq = container_of(rcu, struct netfs_io_request, rcu);
|
|
|
|
mempool_free(rreq, rreq->netfs_ops->request_pool ?: &netfs_request_pool);
|
|
netfs_stat_d(&netfs_n_rh_rreq);
|
|
}
|
|
|
|
static void netfs_free_request(struct work_struct *work)
|
|
{
|
|
struct netfs_io_request *rreq =
|
|
container_of(work, struct netfs_io_request, work);
|
|
unsigned int i;
|
|
|
|
trace_netfs_rreq(rreq, netfs_rreq_trace_free);
|
|
netfs_proc_del_rreq(rreq);
|
|
netfs_clear_subrequests(rreq, false);
|
|
if (rreq->netfs_ops->free_request)
|
|
rreq->netfs_ops->free_request(rreq);
|
|
if (rreq->cache_resources.ops)
|
|
rreq->cache_resources.ops->end_operation(&rreq->cache_resources);
|
|
if (rreq->direct_bv) {
|
|
for (i = 0; i < rreq->direct_bv_count; i++) {
|
|
if (rreq->direct_bv[i].bv_page) {
|
|
if (rreq->direct_bv_unpin)
|
|
unpin_user_page(rreq->direct_bv[i].bv_page);
|
|
}
|
|
}
|
|
kvfree(rreq->direct_bv);
|
|
}
|
|
call_rcu(&rreq->rcu, netfs_free_request_rcu);
|
|
}
|
|
|
|
void netfs_put_request(struct netfs_io_request *rreq, bool was_async,
|
|
enum netfs_rreq_ref_trace what)
|
|
{
|
|
unsigned int debug_id;
|
|
bool dead;
|
|
int r;
|
|
|
|
if (rreq) {
|
|
debug_id = rreq->debug_id;
|
|
dead = __refcount_dec_and_test(&rreq->ref, &r);
|
|
trace_netfs_rreq_ref(debug_id, r - 1, what);
|
|
if (dead) {
|
|
if (was_async) {
|
|
rreq->work.func = netfs_free_request;
|
|
if (!queue_work(system_unbound_wq, &rreq->work))
|
|
BUG();
|
|
} else {
|
|
netfs_free_request(&rreq->work);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Allocate and partially initialise an I/O request structure.
|
|
*/
|
|
struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq)
|
|
{
|
|
struct netfs_io_subrequest *subreq;
|
|
mempool_t *mempool = rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool;
|
|
struct kmem_cache *cache = mempool->pool_data;
|
|
|
|
for (;;) {
|
|
subreq = mempool_alloc(rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool,
|
|
GFP_KERNEL);
|
|
if (subreq)
|
|
break;
|
|
msleep(10);
|
|
}
|
|
|
|
memset(subreq, 0, kmem_cache_size(cache));
|
|
INIT_WORK(&subreq->work, NULL);
|
|
INIT_LIST_HEAD(&subreq->rreq_link);
|
|
refcount_set(&subreq->ref, 2);
|
|
subreq->rreq = rreq;
|
|
subreq->debug_index = atomic_inc_return(&rreq->subreq_counter);
|
|
netfs_get_request(rreq, netfs_rreq_trace_get_subreq);
|
|
netfs_stat(&netfs_n_rh_sreq);
|
|
return subreq;
|
|
}
|
|
|
|
void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
|
|
enum netfs_sreq_ref_trace what)
|
|
{
|
|
int r;
|
|
|
|
__refcount_inc(&subreq->ref, &r);
|
|
trace_netfs_sreq_ref(subreq->rreq->debug_id, subreq->debug_index, r + 1,
|
|
what);
|
|
}
|
|
|
|
static void netfs_free_subrequest(struct netfs_io_subrequest *subreq,
|
|
bool was_async)
|
|
{
|
|
struct netfs_io_request *rreq = subreq->rreq;
|
|
|
|
trace_netfs_sreq(subreq, netfs_sreq_trace_free);
|
|
if (rreq->netfs_ops->free_subrequest)
|
|
rreq->netfs_ops->free_subrequest(subreq);
|
|
mempool_free(subreq, rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool);
|
|
netfs_stat_d(&netfs_n_rh_sreq);
|
|
netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq);
|
|
}
|
|
|
|
void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async,
|
|
enum netfs_sreq_ref_trace what)
|
|
{
|
|
unsigned int debug_index = subreq->debug_index;
|
|
unsigned int debug_id = subreq->rreq->debug_id;
|
|
bool dead;
|
|
int r;
|
|
|
|
dead = __refcount_dec_and_test(&subreq->ref, &r);
|
|
trace_netfs_sreq_ref(debug_id, debug_index, r - 1, what);
|
|
if (dead)
|
|
netfs_free_subrequest(subreq, was_async);
|
|
}
|