mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-09-12 02:35:41 -04:00
For really big read RPC ops that span multiple folios, netfslib allows the
filesystem to give progress notifications to wake up the collector thread
to do a collection of folios that have now been fetched, even if the RPC is
still ongoing, thereby allowing the application to make progress.
This works by taking the current rreq->cleaned_to value (which indicates
which folios have been unlocked) and adding the stashed size of the next
folio to it. cleaned_to, however, is subject to 64-bit tearing on a 32-bit
arch.
Fix this by stashing the next progress notification point as a size_t
(which won't tear) to be added to rreq->start (which won't change), with
the collector thread calculating that from cleaned_to plus the next folio
size.
Further, however, if the folios are small, the collector thread gets
constantly woken up - which has a negative performance impact on the
system.
Fix that too by setting a minimum trigger of 256KiB or the size of the
folio at the front of the queue, whichever is larger. Note that this has
an issue that different subreqs have different need-to-be-cached
properties; this is solved by a preceding patch that marks the property on
the folios whilst issuing subreqs rather than when collecting them.
Also, make sure rreq->cleaned_to is initialised up front, along with
rreq->collected_to and stream->collected_to.
Fixes: e2d46f2ec3 ("netfs: Change the read result collector to only use one work item")
Link: https://sashiko.dev/#/patchset/20260804100224.2748935-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260827134304.2075713-10-dhowells@redhat.com
Acked-by: Paulo Alcantara <pc@manguebit.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
269 lines
7.5 KiB
C
269 lines
7.5 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 "internal.h"
|
|
|
|
static void netfs_free_request(struct work_struct *work);
|
|
|
|
/*
|
|
* 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;
|
|
gfp_t gfp = GFP_KERNEL;
|
|
int ret;
|
|
|
|
/* Writeback is part of memory reclaim and must not fail due to ENOMEM. */
|
|
if (origin == NETFS_WRITEBACK || origin == NETFS_WRITEBACK_SINGLE) {
|
|
gfp = GFP_NOFS; /* Allows use of mempools. */
|
|
|
|
rreq = mempool_alloc(mempool, gfp);
|
|
} else {
|
|
rreq = mempool->alloc(gfp, mempool->pool_data);
|
|
if (!rreq)
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
memset(rreq, 0, kmem_cache_size(cache));
|
|
INIT_WORK(&rreq->cleanup_work, netfs_free_request);
|
|
rreq->gfp = gfp;
|
|
rreq->start = start;
|
|
rreq->collected_to = start;
|
|
rreq->cleaned_to = start;
|
|
rreq->len = len;
|
|
rreq->progress_at = 0;
|
|
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;
|
|
rreq->io_streams[0].sreq_max_len = ULONG_MAX;
|
|
rreq->io_streams[0].sreq_max_segs = 0;
|
|
spin_lock_init(&rreq->lock);
|
|
init_waitqueue_head(&rreq->waitq);
|
|
refcount_set(&rreq->ref, 2);
|
|
|
|
for (int s = 0; s < NR_IO_STREAMS; s++) {
|
|
struct netfs_io_stream *stream = &rreq->io_streams[s];
|
|
|
|
INIT_LIST_HEAD(&stream->subrequests);
|
|
stream->collected_to = rreq->start;
|
|
}
|
|
|
|
if (origin == NETFS_READAHEAD ||
|
|
origin == NETFS_READPAGE ||
|
|
origin == NETFS_READ_GAPS ||
|
|
origin == NETFS_READ_SINGLE ||
|
|
origin == NETFS_READ_FOR_WRITE ||
|
|
origin == NETFS_UNBUFFERED_READ ||
|
|
origin == NETFS_DIO_READ) {
|
|
INIT_WORK(&rreq->work, netfs_read_collection_worker);
|
|
rreq->io_streams[0].avail = true;
|
|
} else {
|
|
INIT_WORK(&rreq->work, netfs_write_collection_worker);
|
|
}
|
|
|
|
__set_bit(NETFS_RREQ_IN_PROGRESS, &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);
|
|
}
|
|
}
|
|
|
|
atomic_inc(&ctx->io_count);
|
|
trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), 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)
|
|
{
|
|
struct netfs_io_subrequest *subreq;
|
|
struct netfs_io_stream *stream;
|
|
int s;
|
|
|
|
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, 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_deinit_request(struct netfs_io_request *rreq)
|
|
{
|
|
struct netfs_inode *ictx = netfs_inode(rreq->inode);
|
|
unsigned int i;
|
|
|
|
trace_netfs_rreq(rreq, netfs_rreq_trace_free);
|
|
|
|
/* Cancel/flush the result collection worker. That does not carry a
|
|
* ref of its own, so we must wait for it somewhere.
|
|
*/
|
|
cancel_work_sync(&rreq->work);
|
|
|
|
netfs_proc_del_rreq(rreq);
|
|
netfs_clear_subrequests(rreq);
|
|
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);
|
|
}
|
|
rolling_buffer_clear(&rreq->buffer);
|
|
|
|
if (atomic_dec_and_test(&ictx->io_count))
|
|
wake_up_var(&ictx->io_count);
|
|
}
|
|
|
|
static void netfs_free_request(struct work_struct *work)
|
|
{
|
|
struct netfs_io_request *rreq =
|
|
container_of(work, struct netfs_io_request, cleanup_work);
|
|
|
|
netfs_deinit_request(rreq);
|
|
call_rcu(&rreq->rcu, netfs_free_request_rcu);
|
|
}
|
|
|
|
void netfs_put_request(struct netfs_io_request *rreq, 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)
|
|
WARN_ON(!queue_work(system_dfl_wq, &rreq->cleanup_work));
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Free a request (synchronously) that was just allocated but has
|
|
* failed before it could be submitted.
|
|
*/
|
|
void netfs_put_failed_request(struct netfs_io_request *rreq)
|
|
{
|
|
int r = refcount_read(&rreq->ref);
|
|
|
|
/* new requests have two references (see
|
|
* netfs_alloc_request(), and this function is only allowed on
|
|
* new request objects
|
|
*/
|
|
WARN_ON_ONCE(r != 2);
|
|
|
|
trace_netfs_rreq_ref(rreq->debug_id, r, netfs_rreq_trace_put_failed);
|
|
netfs_free_request(&rreq->cleanup_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;
|
|
|
|
if (rreq->gfp == GFP_KERNEL)
|
|
subreq = mempool->alloc(rreq->gfp, mempool->pool_data);
|
|
else
|
|
subreq = mempool_alloc(mempool, rreq->gfp);
|
|
if (!subreq)
|
|
return NULL;
|
|
|
|
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)
|
|
{
|
|
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, netfs_rreq_trace_put_subreq);
|
|
}
|
|
|
|
void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
|
|
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);
|
|
}
|