linux/fs/netfs/rolling_buffer.c
David Howells fed0b33e6c
netfs: Fix readahead synchronisation issues by loading all folios upfront
There are some synchronisation issues that derive from the app thread
adding more folios to the rolling buffer whilst the collector thread is
looking at them or trying to clear them, such as determining the setting of
front_folio_order when the next folio hasn't been added yet,

The reason for the rolling buffer approach is that loading the buffer
upfront and then dropping all the refs just acquired is quite a slow
operation, and loading progressively allows some of the cost to be deferred
until after at least some of the I/O is started.

Instead, a better way is to load all the folios into the rolling buffer
upfront - and then drop the refs later, once the I/O is in progress.  (Even
better would be for the refs not to be there at all.)

Fix this by changing the rolling buffer loader to load all the folios
selected by the VM for readahead upfront into the folio queue.  The folio
queue is allocated a batch worth at a time as we don't know how many folios
are involved (the readahead_control struct, alas, has a page count, not a
folio count).

The folio refs acquired from readahead are then dropped in bulk once the
first subrequest is dispatched as it's quite a slow operation.  The
collector waits for NETFS_RREQ_NEED_PUT_RA_REFS to be cleared so that it
doesn't unlock folios before the xarray has been scanned for them.

This simplifies the buffer handling later and isn't noticeably slower as
the xarray doesn't need to be modified and the folios are all already
pre-locked.

Fixes: ee4cdf7ba8 ("netfs: Speed up buffered reading")
Link: https://sashiko.dev/#/patchset/20260824120224.504575-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20260827134304.2075713-8-dhowells@redhat.com
Acked-by: Paulo Alcantara <pc@manguebit.org>
cc: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netfs@lists.linux.dev
cc: linux-mm@kvack.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
2026-08-31 09:54:38 +02:00

250 lines
6.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/* Rolling buffer helpers
*
* Copyright (C) 2024 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/bitops.h>
#include <linux/mempool.h>
#include <linux/pagemap.h>
#include <linux/rolling_buffer.h>
#include <linux/slab.h>
#include "internal.h"
static atomic_t debug_ids;
/**
* netfs_folioq_alloc - Allocate a folio_queue struct
* @rreq_id: Associated debugging ID for tracing purposes
* @gfp: Allocation constraints
* @trace: Trace tag to indicate the purpose of the allocation
*
* Allocate, initialise and account the folio_queue struct and log a trace line
* to mark the allocation.
*/
struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp,
unsigned int /*enum netfs_folioq_trace*/ trace)
{
struct folio_queue *fq;
if (gfp == GFP_KERNEL)
fq = netfs_folioq_pool.alloc(gfp, netfs_folioq_pool.pool_data);
else
fq = mempool_alloc(&netfs_folioq_pool, gfp);
if (fq) {
netfs_stat(&netfs_n_folioq);
folioq_init(fq, rreq_id);
fq->debug_id = atomic_inc_return(&debug_ids);
trace_netfs_folioq(fq, trace);
}
return fq;
}
EXPORT_SYMBOL(netfs_folioq_alloc);
/**
* netfs_folioq_free - Free a folio_queue struct
* @folioq: The object to free
* @trace: Trace tag to indicate which free
*
* Free and unaccount the folio_queue struct.
*/
void netfs_folioq_free(struct folio_queue *folioq,
unsigned int /*enum netfs_trace_folioq*/ trace)
{
trace_netfs_folioq(folioq, trace);
netfs_stat_d(&netfs_n_folioq);
mempool_free(folioq, &netfs_folioq_pool);
}
EXPORT_SYMBOL(netfs_folioq_free);
/*
* Initialise a rolling buffer. We allocate an empty folio queue struct to so
* that the pointers can be independently driven by the producer and the
* consumer.
*/
int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id,
unsigned int direction, gfp_t gfp)
{
struct folio_queue *fq;
fq = netfs_folioq_alloc(rreq_id, gfp, netfs_trace_folioq_rollbuf_init);
if (!fq)
return -ENOMEM;
roll->head = fq;
roll->tail = fq;
iov_iter_folio_queue(&roll->iter, direction, fq, 0, 0, 0);
return 0;
}
/*
* Add another folio_queue to a rolling buffer if there's no space left.
*/
int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp)
{
struct folio_queue *fq, *head = roll->head;
if (!folioq_full(head))
return 0;
fq = netfs_folioq_alloc(head->rreq_id, gfp, netfs_trace_folioq_make_space);
if (!fq)
return -ENOMEM;
fq->prev = head;
roll->head = fq;
if (folioq_full(head)) {
/* Make sure we don't leave the master iterator pointing to a
* block that might get immediately consumed.
*/
if (roll->iter.folioq == head &&
roll->iter.folioq_slot == folioq_nr_slots(head)) {
roll->iter.folioq = fq;
roll->iter.folioq_slot = 0;
}
}
/* Make sure the initialisation is stored before the next pointer.
*
* [!] NOTE: After we set head->next, the consumer is at liberty to
* immediately delete the old head.
*/
smp_store_release(&head->next, fq);
return 0;
}
/*
* Decant the entire list of folios to read into a rolling buffer.
*/
ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll,
struct readahead_control *ractl,
unsigned int rreq_id, gfp_t gfp)
{
struct folio_queue *fq;
ssize_t loaded = 0;
while (ractl->_nr_pages - ractl->_batch_count > 0) {
unsigned int nr;
/* Allocate a folioq to put some folios into and attach it to
* the rolling buffer.
*/
fq = netfs_folioq_alloc(rreq_id, gfp,
netfs_trace_folioq_make_space);
if (!fq)
goto nomem_unlock;
fq->prev = roll->head;
if (!roll->tail)
roll->tail = fq;
else
roll->head->next = fq;
roll->head = fq;
/* Get a batch of folios and note their orders. */
nr = __readahead_batch(ractl, (struct page **)fq->vec.folios,
folioq_nr_slots(fq));
if (WARN_ON_ONCE(!nr))
break;
fq->vec.nr = nr;
for (int slot = 0; slot < nr; slot++) {
struct folio *folio = folioq_folio(fq, slot);
unsigned int order;
order = folio_order(folio);
fq->orders[slot] = order;
loaded += PAGE_SIZE << order;
trace_netfs_folio(folio, netfs_folio_trace_read);
}
}
WRITE_ONCE(roll->iter.count, loaded);
iov_iter_folio_queue(&roll->iter, ITER_DEST, roll->tail, 0, 0, loaded);
return loaded;
nomem_unlock:
for (fq = roll->tail; fq; fq = fq->next) {
for (int slot = 0; slot < folioq_count(fq); slot++) {
folio_unlock(fq->vec.folios[slot]);
folioq_mark(fq, slot);
}
}
rolling_buffer_clear(roll);
roll->head = NULL;
roll->tail = NULL;
return -ENOMEM;
}
/*
* Append a folio to the rolling buffer.
*/
ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio,
unsigned int flags, gfp_t gfp)
{
ssize_t size = folio_size(folio);
int slot;
if (rolling_buffer_make_space(roll, gfp) < 0)
return -ENOMEM;
slot = folioq_append(roll->head, folio);
if (flags & ROLLBUF_MARK_1)
folioq_mark(roll->head, slot);
if (flags & ROLLBUF_MARK_2)
folioq_mark2(roll->head, slot);
WRITE_ONCE(roll->iter.count, roll->iter.count + size);
/* Store the counter after setting the slot. */
smp_store_release(&roll->next_head_slot, slot);
return size;
}
/*
* Delete a spent buffer from a rolling queue and return the next in line. We
* don't return the last buffer to keep the pointers independent, but return
* NULL instead.
*/
struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll)
{
struct folio_queue *spent = roll->tail, *next = READ_ONCE(spent->next);
if (!next)
return NULL;
next->prev = NULL;
netfs_folioq_free(spent, netfs_trace_folioq_delete);
roll->tail = next;
return next;
}
/*
* Clear out a rolling queue. Folios that have mark 1 set are put.
*/
void rolling_buffer_clear(struct rolling_buffer *roll)
{
struct folio_batch fbatch;
struct folio_queue *p;
folio_batch_init(&fbatch);
while ((p = roll->tail)) {
roll->tail = p->next;
for (int slot = 0; slot < folioq_count(p); slot++) {
struct folio *folio = folioq_folio(p, slot);
if (!folio)
continue;
if (folioq_is_marked(p, slot)) {
trace_netfs_folio(folio, netfs_folio_trace_put);
if (!folio_batch_add(&fbatch, folio))
folio_batch_release(&fbatch);
}
}
netfs_folioq_free(p, netfs_trace_folioq_clear);
}
folio_batch_release(&fbatch);
}