netfs: Change the read result collector to only use one work item

Change the way netfslib collects read results to do all the collection for
a particular read request using a single work item that walks along the
subrequest queue as subrequests make progress or complete, unlocking folios
progressively rather than doing the unlock in parallel as parallel requests
come in.

The code is remodelled to be more like the write-side code, though only
using a single stream.  This makes it more directly comparable and thus
easier to duplicate fixes between the two sides.

This has a number of advantages:

 (1) It's simpler.  There doesn't need to be a complex donation mechanism
     to handle mismatches between the size and alignment of subrequests and
     folios.  The collector unlocks folios as the subrequests covering each
     complete.

 (2) It should cause less scheduler overhead as there's a single work item
     in play unlocking pages in parallel when a read gets split up into a
     lot of subrequests instead of one per subrequest.

     Whilst the parallellism is nice in theory, in practice, the vast
     majority of loads are sequential reads of the whole file, so
     committing a bunch of threads to unlocking folios out of order doesn't
     help in those cases.

 (3) It should make it easier to implement content decryption.  A folio
     cannot be decrypted until all the requests that contribute to it have
     completed - and, again, most loads are sequential and so, most of the
     time, we want to begin decryption sequentially (though it's great if
     the decryption can happen in parallel).

There is a disadvantage in that we're losing the ability to decrypt and
unlock things on an as-things-arrive basis which may affect some
applications.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/20241216204124.3752367-28-dhowells@redhat.com
cc: Jeff Layton <jlayton@kernel.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 12 insertions, 67 deletions

diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 6df2e7313371..6e699cadcb29 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -50,18 +50,23 @@
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
 	EM(netfs_rreq_trace_copy,		"COPY   ")	\
 	EM(netfs_rreq_trace_collect,		"COLLECT")	\
+	EM(netfs_rreq_trace_complete,		"COMPLET")	\
 	EM(netfs_rreq_trace_dirty,		"DIRTY  ")	\
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
+	EM(netfs_rreq_trace_set_abandon,	"S-ABNDN")	\
 	EM(netfs_rreq_trace_set_pause,		"PAUSE  ")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
 	EM(netfs_rreq_trace_unlock_pgpriv2,	"UNLCK-2")	\
 	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
 	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
 	EM(netfs_rreq_trace_wait_pause,		"WT-PAUS")	\
+	EM(netfs_rreq_trace_wait_queue,		"WAIT-Q ")	\
 	EM(netfs_rreq_trace_wake_ip,		"WAKE-IP")	\
+	EM(netfs_rreq_trace_wake_queue,		"WAKE-Q ")	\
+	EM(netfs_rreq_trace_woke_queue,		"WOKE-Q ")	\
 	EM(netfs_rreq_trace_unpause,		"UNPAUSE")	\
 	E_(netfs_rreq_trace_write_done,		"WR-DONE")
 
@@ -81,6 +86,7 @@
 	EM(netfs_sreq_trace_cache_nowrite,	"CA-NW")	\
 	EM(netfs_sreq_trace_cache_prepare,	"CA-PR")	\
 	EM(netfs_sreq_trace_cache_write,	"CA-WR")	\
+	EM(netfs_sreq_trace_cancel,		"CANCL")	\
 	EM(netfs_sreq_trace_clear,		"CLEAR")	\
 	EM(netfs_sreq_trace_discard,		"DSCRD")	\
 	EM(netfs_sreq_trace_donate_to_prev,	"DON-P")	\
@@ -91,6 +97,9 @@
 	EM(netfs_sreq_trace_hit_eof,		"EOF  ")	\
 	EM(netfs_sreq_trace_io_progress,	"IO   ")	\
 	EM(netfs_sreq_trace_limited,		"LIMIT")	\
+	EM(netfs_sreq_trace_need_clear,		"N-CLR")	\
+	EM(netfs_sreq_trace_partial_read,	"PARTR")	\
+	EM(netfs_sreq_trace_need_retry,		"NRTRY")	\
 	EM(netfs_sreq_trace_prepare,		"PREP ")	\
 	EM(netfs_sreq_trace_prep_failed,	"PRPFL")	\
 	EM(netfs_sreq_trace_progress,		"PRGRS")	\
@@ -136,6 +145,7 @@
 	EM(netfs_sreq_trace_get_submit,		"GET SUBMIT")	\
 	EM(netfs_sreq_trace_get_short_read,	"GET SHORTRD")	\
 	EM(netfs_sreq_trace_new,		"NEW        ")	\
+	EM(netfs_sreq_trace_put_abandon,	"PUT ABANDON")	\
 	EM(netfs_sreq_trace_put_cancel,		"PUT CANCEL ")	\
 	EM(netfs_sreq_trace_put_clear,		"PUT CLEAR  ")	\
 	EM(netfs_sreq_trace_put_consumed,	"PUT CONSUME")	\
@@ -176,6 +186,7 @@
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
 	EM(netfs_folio_trace_not_under_wback,	"!wback")	\
+	EM(netfs_folio_trace_not_locked,	"!locked")	\
 	EM(netfs_folio_trace_put,		"put")		\
 	EM(netfs_folio_trace_read,		"read")		\
 	EM(netfs_folio_trace_read_done,		"read-done")	\
@@ -204,7 +215,6 @@
 	EM(netfs_trace_folioq_clear,		"clear")	\
 	EM(netfs_trace_folioq_delete,		"delete")	\
 	EM(netfs_trace_folioq_make_space,	"make-space")	\
-	EM(netfs_trace_folioq_prep_write,	"prep-wr")	\
 	EM(netfs_trace_folioq_rollbuf_init,	"roll-init")	\
 	E_(netfs_trace_folioq_read_progress,	"r-progress")
 
@@ -352,7 +362,7 @@ TRACE_EVENT(netfs_sreq,
 		    __entry->len	= sreq->len;
 		    __entry->transferred = sreq->transferred;
 		    __entry->start	= sreq->start;
-		    __entry->slot	= sreq->curr_folioq_slot;
+		    __entry->slot	= sreq->io_iter.folioq_slot;
 			   ),
 
 	    TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx s=%u e=%d",
@@ -701,71 +711,6 @@ TRACE_EVENT(netfs_collect_stream,
 		      __entry->collected_to, __entry->front)
 	    );
 
-TRACE_EVENT(netfs_progress,
-	    TP_PROTO(const struct netfs_io_subrequest *subreq,
-		     unsigned long long start, size_t avail, size_t part),
-
-	    TP_ARGS(subreq, start, avail, part),
-
-	    TP_STRUCT__entry(
-		    __field(unsigned int,		rreq)
-		    __field(unsigned int,		subreq)
-		    __field(unsigned int,		consumed)
-		    __field(unsigned int,		transferred)
-		    __field(unsigned long long,		f_start)
-		    __field(unsigned int,		f_avail)
-		    __field(unsigned int,		f_part)
-		    __field(unsigned char,		slot)
-			     ),
-
-	    TP_fast_assign(
-		    __entry->rreq	= subreq->rreq->debug_id;
-		    __entry->subreq	= subreq->debug_index;
-		    __entry->consumed	= subreq->consumed;
-		    __entry->transferred = subreq->transferred;
-		    __entry->f_start	= start;
-		    __entry->f_avail	= avail;
-		    __entry->f_part	= part;
-		    __entry->slot	= subreq->curr_folioq_slot;
-			   ),
-
-	    TP_printk("R=%08x[%02x] s=%llx ct=%x/%x pa=%x/%x sl=%x",
-		      __entry->rreq, __entry->subreq, __entry->f_start,
-		      __entry->consumed, __entry->transferred,
-		      __entry->f_part, __entry->f_avail,  __entry->slot)
-	    );
-
-TRACE_EVENT(netfs_donate,
-	    TP_PROTO(const struct netfs_io_request *rreq,
-		     const struct netfs_io_subrequest *from,
-		     const struct netfs_io_subrequest *to,
-		     size_t amount,
-		     enum netfs_donate_trace trace),
-
-	    TP_ARGS(rreq, from, to, amount, trace),
-
-	    TP_STRUCT__entry(
-		    __field(unsigned int,		rreq)
-		    __field(unsigned int,		from)
-		    __field(unsigned int,		to)
-		    __field(unsigned int,		amount)
-		    __field(enum netfs_donate_trace,	trace)
-			     ),
-
-	    TP_fast_assign(
-		    __entry->rreq	= rreq->debug_id;
-		    __entry->from	= from->debug_index;
-		    __entry->to		= to ? to->debug_index : -1;
-		    __entry->amount	= amount;
-		    __entry->trace	= trace;
-			   ),
-
-	    TP_printk("R=%08x[%02x] -> [%02x] %s am=%x",
-		      __entry->rreq, __entry->from, __entry->to,
-		      __print_symbolic(__entry->trace, netfs_donate_traces),
-		      __entry->amount)
-	    );
-
 TRACE_EVENT(netfs_folioq,
 	    TP_PROTO(const struct folio_queue *fq,
 		     enum netfs_folioq_trace trace),