* [PATCH 0/2] nvme: add set feature tracing support
@ 2021-07-05 3:15 Hou Pu
2021-07-05 3:15 ` [PATCH 1/2] " Hou Pu
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Hou Pu @ 2021-07-05 3:15 UTC (permalink / raw)
To: sagi, hch, chaitanya.kulkarni; +Cc: linux-nvme, houpu.main, maxg
Add set feature tracing support to host and controller side.
Also fix a style problem in nvmet_trace_admin_get_features.
Hou Pu (2):
nvme: add set feature tracing support
nvmet: add set feature tracing support
drivers/nvme/host/trace.c | 18 +++++++++++++++++-
drivers/nvme/target/trace.c | 18 +++++++++++++++++-
2 files changed, 34 insertions(+), 2 deletions(-)
--
2.28.0
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH 1/2] nvme: add set feature tracing support 2021-07-05 3:15 [PATCH 0/2] nvme: add set feature tracing support Hou Pu @ 2021-07-05 3:15 ` Hou Pu 2021-07-05 7:16 ` Max Gurtovoy 2021-07-05 3:15 ` [PATCH 2/2] nvmet: " Hou Pu 2021-07-16 7:53 ` [PATCH 0/2] nvme: " Christoph Hellwig 2 siblings, 1 reply; 6+ messages in thread From: Hou Pu @ 2021-07-05 3:15 UTC (permalink / raw) To: sagi, hch, chaitanya.kulkarni; +Cc: linux-nvme, houpu.main, maxg A nvme connect command produces following trace. Before: /sys/kernel/debug/tracing# cat trace | grep feature kworker/5:1H-98 [005] .... 3221.294844: nvme_setup_cmd: nvme0: qid=0, cmdid=25, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features cdw10=07 00 00 00 07 00 07 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) kworker/4:1H-124 [004] .... 3222.009186: nvme_setup_cmd: nvme0: qid=0, cmdid=17, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features cdw10=0b 00 00 00 00 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) After: /sys/kernel/debug/tracing# cat trace | grep feature kworker/0:1H-253 [000] .... 196.060509: nvme_setup_cmd: nvme0: qid=0, cmdid=29, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features fid=0x7, sv=0x0, cdw11=0x70007) kworker/0:1H-253 [000] .... 196.763947: nvme_setup_cmd: nvme0: qid=0, cmdid=29, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features fid=0xb, sv=0x0, cdw11=0x900) Using ',' to separate different field like others in nvmet_trace_admin_get_features. Signed-off-by: Hou Pu <houpu.main@gmail.com> --- drivers/nvme/host/trace.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 6543015b6121..2a89c5aa0790 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -72,6 +72,20 @@ static const char *nvme_trace_admin_identify(struct trace_seq *p, u8 *cdw10) return ret; } +static const char *nvme_trace_admin_set_features(struct trace_seq *p, + u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 fid = cdw10[0]; + u8 sv = cdw10[3] & 0x8; + u32 cdw11 = get_unaligned_le32(cdw10 + 4); + + trace_seq_printf(p, "fid=0x%x, sv=0x%x, cdw11=0x%x", fid, sv, cdw11); + trace_seq_putc(p, 0); + + return ret; +} + static const char *nvme_trace_admin_get_features(struct trace_seq *p, u8 *cdw10) { @@ -80,7 +94,7 @@ static const char *nvme_trace_admin_get_features(struct trace_seq *p, u8 sel = cdw10[1] & 0x7; u32 cdw11 = get_unaligned_le32(cdw10 + 4); - trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11); + trace_seq_printf(p, "fid=0x%x, sel=0x%x, cdw11=0x%x", fid, sel, cdw11); trace_seq_putc(p, 0); return ret; @@ -201,6 +215,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, return nvme_trace_create_cq(p, cdw10); case nvme_admin_identify: return nvme_trace_admin_identify(p, cdw10); + case nvme_admin_set_features: + return nvme_trace_admin_set_features(p, cdw10); case nvme_admin_get_features: return nvme_trace_admin_get_features(p, cdw10); case nvme_admin_get_lba_status: -- 2.28.0 _______________________________________________ Linux-nvme mailing list Linux-nvme@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-nvme ^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH 1/2] nvme: add set feature tracing support 2021-07-05 3:15 ` [PATCH 1/2] " Hou Pu @ 2021-07-05 7:16 ` Max Gurtovoy 2021-07-05 7:43 ` Hou Pu 0 siblings, 1 reply; 6+ messages in thread From: Max Gurtovoy @ 2021-07-05 7:16 UTC (permalink / raw) To: Hou Pu, sagi, hch, chaitanya.kulkarni; +Cc: linux-nvme, maxg On 7/5/2021 6:15 AM, Hou Pu wrote: > A nvme connect command produces following trace. > > Before: > /sys/kernel/debug/tracing# cat trace | grep feature > kworker/5:1H-98 [005] .... 3221.294844: nvme_setup_cmd: nvme0: qid=0, cmdid=25, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features cdw10=07 00 00 00 07 00 07 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) > kworker/4:1H-124 [004] .... 3222.009186: nvme_setup_cmd: nvme0: qid=0, cmdid=17, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features cdw10=0b 00 00 00 00 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) > > After: > /sys/kernel/debug/tracing# cat trace | grep feature > kworker/0:1H-253 [000] .... 196.060509: nvme_setup_cmd: nvme0: qid=0, cmdid=29, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features fid=0x7, sv=0x0, cdw11=0x70007) > kworker/0:1H-253 [000] .... 196.763947: nvme_setup_cmd: nvme0: qid=0, cmdid=29, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features fid=0xb, sv=0x0, cdw11=0x900) > > Using ',' to separate different field like others in > nvmet_trace_admin_get_features. > > Signed-off-by: Hou Pu <houpu.main@gmail.com> > --- > drivers/nvme/host/trace.c | 18 +++++++++++++++++- > 1 file changed, 17 insertions(+), 1 deletion(-) > > diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c > index 6543015b6121..2a89c5aa0790 100644 > --- a/drivers/nvme/host/trace.c > +++ b/drivers/nvme/host/trace.c > @@ -72,6 +72,20 @@ static const char *nvme_trace_admin_identify(struct trace_seq *p, u8 *cdw10) > return ret; > } > > +static const char *nvme_trace_admin_set_features(struct trace_seq *p, > + u8 *cdw10) > +{ > + const char *ret = trace_seq_buffer_ptr(p); > + u8 fid = cdw10[0]; > + u8 sv = cdw10[3] & 0x8; > + u32 cdw11 = get_unaligned_le32(cdw10 + 4); By the spec cdw10, 11, 12, 13, 14, 15 are used by set features command. At least lets print cdw11-cdw15 as raw data and not only cdw11. We don't want to loose information. > + > + trace_seq_printf(p, "fid=0x%x, sv=0x%x, cdw11=0x%x", fid, sv, cdw11); > + trace_seq_putc(p, 0); > + > + return ret; > +} > + > static const char *nvme_trace_admin_get_features(struct trace_seq *p, > u8 *cdw10) > { > @@ -80,7 +94,7 @@ static const char *nvme_trace_admin_get_features(struct trace_seq *p, > u8 sel = cdw10[1] & 0x7; > u32 cdw11 = get_unaligned_le32(cdw10 + 4); > > - trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11); > + trace_seq_printf(p, "fid=0x%x, sel=0x%x, cdw11=0x%x", fid, sel, cdw11); This can be done in separate commit. Also if you can fix the current status and print also cdw14 since it's used by get features by the spec (in separate commit). > trace_seq_putc(p, 0); > > return ret; > @@ -201,6 +215,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, > return nvme_trace_create_cq(p, cdw10); > case nvme_admin_identify: > return nvme_trace_admin_identify(p, cdw10); > + case nvme_admin_set_features: > + return nvme_trace_admin_set_features(p, cdw10); > case nvme_admin_get_features: > return nvme_trace_admin_get_features(p, cdw10); > case nvme_admin_get_lba_status: _______________________________________________ Linux-nvme mailing list Linux-nvme@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-nvme ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH 1/2] nvme: add set feature tracing support 2021-07-05 7:16 ` Max Gurtovoy @ 2021-07-05 7:43 ` Hou Pu 0 siblings, 0 replies; 6+ messages in thread From: Hou Pu @ 2021-07-05 7:43 UTC (permalink / raw) To: Max Gurtovoy; +Cc: Sagi Grimberg, hch, Chaitanya Kulkarni, linux-nvme, maxg On Mon, Jul 5, 2021 at 3:16 PM Max Gurtovoy <mgurtovoy@nvidia.com> wrote: > > > On 7/5/2021 6:15 AM, Hou Pu wrote: > > A nvme connect command produces following trace. > > > > Before: > > /sys/kernel/debug/tracing# cat trace | grep feature > > kworker/5:1H-98 [005] .... 3221.294844: nvme_setup_cmd: nvme0: qid=0, cmdid=25, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features cdw10=07 00 00 00 07 00 07 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) > > kworker/4:1H-124 [004] .... 3222.009186: nvme_setup_cmd: nvme0: qid=0, cmdid=17, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features cdw10=0b 00 00 00 00 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) > > > > After: > > /sys/kernel/debug/tracing# cat trace | grep feature > > kworker/0:1H-253 [000] .... 196.060509: nvme_setup_cmd: nvme0: qid=0, cmdid=29, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features fid=0x7, sv=0x0, cdw11=0x70007) > > kworker/0:1H-253 [000] .... 196.763947: nvme_setup_cmd: nvme0: qid=0, cmdid=29, nsid=0, flags=0x0, meta=0x0, cmd=(nvme_admin_set_features fid=0xb, sv=0x0, cdw11=0x900) > > > > Using ',' to separate different field like others in > > nvmet_trace_admin_get_features. > > > > Signed-off-by: Hou Pu <houpu.main@gmail.com> > > --- > > drivers/nvme/host/trace.c | 18 +++++++++++++++++- > > 1 file changed, 17 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c > > index 6543015b6121..2a89c5aa0790 100644 > > --- a/drivers/nvme/host/trace.c > > +++ b/drivers/nvme/host/trace.c > > @@ -72,6 +72,20 @@ static const char *nvme_trace_admin_identify(struct trace_seq *p, u8 *cdw10) > > return ret; > > } > > > > +static const char *nvme_trace_admin_set_features(struct trace_seq *p, > > + u8 *cdw10) > > +{ > > + const char *ret = trace_seq_buffer_ptr(p); > > + u8 fid = cdw10[0]; > > + u8 sv = cdw10[3] & 0x8; > > + u32 cdw11 = get_unaligned_le32(cdw10 + 4); > > By the spec cdw10, 11, 12, 13, 14, 15 are used by set features command. > > At least lets print cdw11-cdw15 as raw data and not only cdw11. > > We don't want to loose information. Yes, it's better to keep these although currently only cdw11 is used. Will change it in v2. Thanks. > > > + > > + trace_seq_printf(p, "fid=0x%x, sv=0x%x, cdw11=0x%x", fid, sv, cdw11); > > + trace_seq_putc(p, 0); > > + > > + return ret; > > +} > > + > > static const char *nvme_trace_admin_get_features(struct trace_seq *p, > > u8 *cdw10) > > { > > @@ -80,7 +94,7 @@ static const char *nvme_trace_admin_get_features(struct trace_seq *p, > > u8 sel = cdw10[1] & 0x7; > > u32 cdw11 = get_unaligned_le32(cdw10 + 4); > > > > - trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11); > > + trace_seq_printf(p, "fid=0x%x, sel=0x%x, cdw11=0x%x", fid, sel, cdw11); > > This can be done in separate commit. > > Also if you can fix the current status and print also cdw14 since it's > used by get features by the spec (in separate commit). OK. Thanks for the comment. > > > > trace_seq_putc(p, 0); > > > > return ret; > > @@ -201,6 +215,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, > > return nvme_trace_create_cq(p, cdw10); > > case nvme_admin_identify: > > return nvme_trace_admin_identify(p, cdw10); > > + case nvme_admin_set_features: > > + return nvme_trace_admin_set_features(p, cdw10); > > case nvme_admin_get_features: > > return nvme_trace_admin_get_features(p, cdw10); > > case nvme_admin_get_lba_status: _______________________________________________ Linux-nvme mailing list Linux-nvme@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-nvme ^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH 2/2] nvmet: add set feature tracing support 2021-07-05 3:15 [PATCH 0/2] nvme: add set feature tracing support Hou Pu 2021-07-05 3:15 ` [PATCH 1/2] " Hou Pu @ 2021-07-05 3:15 ` Hou Pu 2021-07-16 7:53 ` [PATCH 0/2] nvme: " Christoph Hellwig 2 siblings, 0 replies; 6+ messages in thread From: Hou Pu @ 2021-07-05 3:15 UTC (permalink / raw) To: sagi, hch, chaitanya.kulkarni; +Cc: linux-nvme, houpu.main, maxg A nvme connect command produces following trace from the target side. Before: kworker/0:1H-56 [000] .... 9012.155139: nvmet_req_init: nvmet1: qid=0, cmdid=16, nsid=0, flags=0x40, meta=0x0, cmd=(nvme_admin_set_features, cdw10=07 00 00 00 07 00 07 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) kworker/0:1H-56 [000] .... 9012.872272: nvmet_req_init: nvmet1: qid=0, cmdid=13, nsid=0, flags=0x40, meta=0x0, cmd=(nvme_admin_set_features, cdw10=0b 00 00 00 00 09 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00) cmdline:/sys/kernel/debug/tracing# cat trace | grep feature kworker/0:1H-56 [000] .... 203.493914: nvmet_req_init: nvmet1: qid=0, cmdid=29, nsid=0, flags=0x40, meta=0x0, cmd=(nvme_admin_set_features, fid=0x7, sv=0x0, cdw11=0x70007) kworker/0:1H-56 [000] .... 204.197079: nvmet_req_init: nvmet1: qid=0, cmdid=29, nsid=0, flags=0x40, meta=0x0, cmd=(nvme_admin_set_features, fid=0xb, sv=0x0, cdw11=0x900) Using ',' to separate different field like others in nvmet_trace_admin_get_features. Signed-off-by: Hou Pu <houpu.main@gmail.com> --- drivers/nvme/target/trace.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c index 1373a3c67962..bff454d46255 100644 --- a/drivers/nvme/target/trace.c +++ b/drivers/nvme/target/trace.c @@ -27,7 +27,7 @@ static const char *nvmet_trace_admin_get_features(struct trace_seq *p, u8 sel = cdw10[1] & 0x7; u32 cdw11 = get_unaligned_le32(cdw10 + 4); - trace_seq_printf(p, "fid=0x%x sel=0x%x cdw11=0x%x", fid, sel, cdw11); + trace_seq_printf(p, "fid=0x%x, sel=0x%x, cdw11=0x%x", fid, sel, cdw11); trace_seq_putc(p, 0); return ret; @@ -49,6 +49,20 @@ static const char *nvmet_trace_get_lba_status(struct trace_seq *p, return ret; } +static const char *nvmet_trace_admin_set_features(struct trace_seq *p, + u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u8 fid = cdw10[0]; + u8 sv = cdw10[3] & 0x8; + u32 cdw11 = get_unaligned_le32(cdw10 + 4); + + trace_seq_printf(p, "fid=0x%x, sv=0x%x, cdw11=0x%x", fid, sv, cdw11); + trace_seq_putc(p, 0); + + return ret; +} + static const char *nvmet_trace_read_write(struct trace_seq *p, u8 *cdw10) { const char *ret = trace_seq_buffer_ptr(p); @@ -94,6 +108,8 @@ const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p, switch (opcode) { case nvme_admin_identify: return nvmet_trace_admin_identify(p, cdw10); + case nvme_admin_set_features: + return nvmet_trace_admin_set_features(p, cdw10); case nvme_admin_get_features: return nvmet_trace_admin_get_features(p, cdw10); case nvme_admin_get_lba_status: -- 2.28.0 _______________________________________________ Linux-nvme mailing list Linux-nvme@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-nvme ^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH 0/2] nvme: add set feature tracing support 2021-07-05 3:15 [PATCH 0/2] nvme: add set feature tracing support Hou Pu 2021-07-05 3:15 ` [PATCH 1/2] " Hou Pu 2021-07-05 3:15 ` [PATCH 2/2] nvmet: " Hou Pu @ 2021-07-16 7:53 ` Christoph Hellwig 2 siblings, 0 replies; 6+ messages in thread From: Christoph Hellwig @ 2021-07-16 7:53 UTC (permalink / raw) To: Hou Pu; +Cc: sagi, hch, chaitanya.kulkarni, linux-nvme, maxg Thanks, applied to nvme-5.15. _______________________________________________ Linux-nvme mailing list Linux-nvme@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-nvme ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2021-07-16 7:54 UTC | newest] Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2021-07-05 3:15 [PATCH 0/2] nvme: add set feature tracing support Hou Pu 2021-07-05 3:15 ` [PATCH 1/2] " Hou Pu 2021-07-05 7:16 ` Max Gurtovoy 2021-07-05 7:43 ` Hou Pu 2021-07-05 3:15 ` [PATCH 2/2] nvmet: " Hou Pu 2021-07-16 7:53 ` [PATCH 0/2] nvme: " Christoph Hellwig
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.