From f6c73a11133ef991284311387ca707b48bf53912 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:42 -0700 Subject: [PATCH 1/3] fs.h: Add TRACE_IOCB_STRINGS for use in trace points Add TRACE_IOCB_STRINGS macro which can be used in the trace point patch to print different flag values with meaningful string output. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong [djwong: line up strings all prettylike] Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..75d24fa082e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -340,6 +340,20 @@ enum rw_hint { /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + struct kiocb { struct file *ki_filp; loff_t ki_pos; From d3bff1fc50d4fcaccddbd63917dd94172e80c40e Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:43 -0700 Subject: [PATCH 2/3] iomap: Remove IOMAP_DIO_NOSYNC unused dio flag IOMAP_DIO_NOSYNC earlier was added for use in btrfs. But it seems for aio dsync writes this is not useful anyway. For aio dsync case, we we queue the request and return -EIOCBQUEUED. Now, since IOMAP_DIO_NOSYNC doesn't let iomap_dio_complete() to call generic_write_sync(), hence we may lose the sync write. Hence kill this flag as it is not in use by any FS now. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Darrick J. Wong --- fs/iomap/direct-io.c | 2 +- include/linux/iomap.h | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index f771001574d0..36ab1152dbea 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -541,7 +541,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } /* for data sync or sync, we need sync completion processing */ - if (iocb_is_dsync(iocb) && !(dio_flags & IOMAP_DIO_NOSYNC)) { + if (iocb_is_dsync(iocb)) { dio->flags |= IOMAP_DIO_NEED_SYNC; /* diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f8123504e5e..e2b836c2e119 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -377,12 +377,6 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) -/* - * The caller will sync the write if needed; do not sync it within - * iomap_dio_rw. Overrides IOMAP_DIO_FORCE_WAIT. - */ -#define IOMAP_DIO_NOSYNC (1 << 3) - ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); From 3fd41721cd5c30af37c860e6201c98db0a568fd2 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:43 -0700 Subject: [PATCH 3/3] iomap: Add DIO tracepoints Add trace_iomap_dio_rw_begin, trace_iomap_dio_rw_queued and trace_iomap_dio_complete tracepoint. trace_iomap_dio_rw_queued is mostly only to know that the request was queued and -EIOCBQUEUED was returned. It is mostly trace_iomap_dio_rw_begin & trace_iomap_dio_complete which has all the details. a.out-2073 [006] 134.225717: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x0 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT|WRITE dio_flags DIO_FORCE_WAIT aio 1 a.out-2073 [006] 134.226234: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT|WRITE aio 1 error 0 ret 4096 a.out-2074 [006] 136.225975: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 1 a.out-2074 [006] 136.226173: iomap_dio_rw_queued: dev 7:7 ino 0xe size 0x1000 offset 0x1000 length 0x0 ksoftirqd/3-31 [003] 136.226389: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 1 error 0 ret 4096 a.out-2075 [003] 141.674969: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT|WRITE dio_flags aio 1 a.out-2075 [003] 141.676085: iomap_dio_rw_queued: dev 7:7 ino 0xe size 0x1000 offset 0x1000 length 0x0 kworker/2:0-27 [002] 141.676432: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT|WRITE aio 1 error 0 ret 4096 a.out-2077 [006] 143.443746: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 1 a.out-2077 [006] 143.443866: iomap_dio_rw_queued: dev 7:7 ino 0xe size 0x1000 offset 0x1000 length 0x0 ksoftirqd/5-41 [005] 143.444134: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 1 error 0 ret 4096 a.out-2078 [007] 146.716833: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 0 a.out-2078 [007] 146.717639: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 0 error 0 ret 4096 a.out-2079 [006] 148.972605: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 0 a.out-2079 [006] 148.973099: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 0 error 0 ret 4096 Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong [djwong: line up strings all prettylike] Signed-off-by: Darrick J. Wong --- fs/iomap/direct-io.c | 7 +++- fs/iomap/trace.c | 1 + fs/iomap/trace.h | 78 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+), 1 deletion(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 36ab1152dbea..019cc87d0fb3 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -130,6 +130,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) if (ret > 0) ret += dio->done_before; + trace_iomap_dio_complete(iocb, dio->error, ret); kfree(dio); return ret; @@ -493,6 +494,8 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct blk_plug plug; struct iomap_dio *dio; + trace_iomap_dio_rw_begin(iocb, iter, dio_flags, done_before); + if (!iomi.len) return NULL; @@ -650,8 +653,10 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, */ dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { - if (!wait_for_completion) + if (!wait_for_completion) { + trace_iomap_dio_rw_queued(inode, iomi.pos, iomi.len); return ERR_PTR(-EIOCBQUEUED); + } for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); diff --git a/fs/iomap/trace.c b/fs/iomap/trace.c index da217246b1a9..728d5443daf5 100644 --- a/fs/iomap/trace.c +++ b/fs/iomap/trace.c @@ -3,6 +3,7 @@ * Copyright (c) 2019 Christoph Hellwig */ #include +#include /* * We include this last to have the helpers above available for the trace diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index f6ea9540d082..c16fd55f5595 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -83,6 +83,7 @@ DEFINE_RANGE_EVENT(iomap_writepage); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); +DEFINE_RANGE_EVENT(iomap_dio_rw_queued); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ @@ -107,6 +108,11 @@ DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } +#define IOMAP_DIO_STRINGS \ + {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ + {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ + {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" } + DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), @@ -183,6 +189,78 @@ TRACE_EVENT(iomap_iter, (void *)__entry->caller) ); +TRACE_EVENT(iomap_dio_rw_begin, + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, + unsigned int dio_flags, size_t done_before), + TP_ARGS(iocb, iter, dio_flags, done_before), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, isize) + __field(loff_t, pos) + __field(size_t, count) + __field(size_t, done_before) + __field(int, ki_flags) + __field(unsigned int, dio_flags) + __field(bool, aio) + ), + TP_fast_assign( + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = file_inode(iocb->ki_filp)->i_ino; + __entry->isize = file_inode(iocb->ki_filp)->i_size; + __entry->pos = iocb->ki_pos; + __entry->count = iov_iter_count(iter); + __entry->done_before = done_before; + __entry->ki_flags = iocb->ki_flags; + __entry->dio_flags = dio_flags; + __entry->aio = !is_sync_kiocb(iocb); + ), + TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->isize, + __entry->pos, + __entry->count, + __entry->done_before, + __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), + __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS), + __entry->aio) +); + +TRACE_EVENT(iomap_dio_complete, + TP_PROTO(struct kiocb *iocb, int error, ssize_t ret), + TP_ARGS(iocb, error, ret), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, isize) + __field(loff_t, pos) + __field(int, ki_flags) + __field(bool, aio) + __field(int, error) + __field(ssize_t, ret) + ), + TP_fast_assign( + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = file_inode(iocb->ki_filp)->i_ino; + __entry->isize = file_inode(iocb->ki_filp)->i_size; + __entry->pos = iocb->ki_pos; + __entry->ki_flags = iocb->ki_flags; + __entry->aio = !is_sync_kiocb(iocb); + __entry->error = error; + __entry->ret = ret; + ), + TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->isize, + __entry->pos, + __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), + __entry->aio, + __entry->error, + __entry->ret) +); + #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH