Re: [PATCH 0/4] Rework NVMe abort handling

reset. Byte, Johannes -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG Nürnberg) Key fingerprint

[PATCH 2/4] nvme: rdma: abort commands before resetting controller

Currently if a timeout on rdma happens we just go ahead and reset the underlying transport. Instead try to abort the timeout out command and if this fails as well continue the error path escalation and tear down the transport. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/rdma.c | 22

[PATCH 2/4] nvme: rdma: abort commands before resetting controller

Currently if a timeout on rdma happens we just go ahead and reset the underlying transport. Instead try to abort the timeout out command and if this fails as well continue the error path escalation and tear down the transport. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/rdma.c | 22

[PATCH 0/4] Rework NVMe abort handling

before trying to abort the NVMe command. Johannes Thumshirn (4): nvme: factor out pci abort handling into core nvme: rdma: abort commands before resetting controller nvmet: loop: abort commands before resetting controller nvme: fc: abort commands before resetting controller drivers/nvme

[PATCH 0/4] Rework NVMe abort handling

before trying to abort the NVMe command. Johannes Thumshirn (4): nvme: factor out pci abort handling into core nvme: rdma: abort commands before resetting controller nvmet: loop: abort commands before resetting controller nvme: fc: abort commands before resetting controller drivers/nvme

[PATCH 3/4] nvmet: loop: abort commands before resetting controller

Currently if a timeout on loop happens we just go ahead and reset the underlying transport. Instead try to abort the timeout out command and if this fails as well continue the error path escalation and tear down the transport. Signed-off-by: Johannes Thumshirn --- drivers/nvme/target/loop.c

[PATCH 1/4] nvme: factor out pci abort handling into core

Currently PCI is the only transport which does a more fine grained error handling than just resetting the controller. Factor out the command abort logic into nvme-core so other transports can benefit of it as well. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 47

[PATCH 1/4] nvme: factor out pci abort handling into core

Currently PCI is the only transport which does a more fine grained error handling than just resetting the controller. Factor out the command abort logic into nvme-core so other transports can benefit of it as well. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 47

[PATCH 3/4] nvmet: loop: abort commands before resetting controller

Currently if a timeout on loop happens we just go ahead and reset the underlying transport. Instead try to abort the timeout out command and if this fails as well continue the error path escalation and tear down the transport. Signed-off-by: Johannes Thumshirn --- drivers/nvme/target/loop.c

[PATCH 4/4] nvme: fc: abort commands before resetting controller

-by: Johannes Thumshirn --- drivers/nvme/host/fc.c | 9 + 1 file changed, 9 insertions(+) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 9cc33752539a..0ba0075c3b75 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2054,6 +2054,15 @@ nvme_fc_timeout(struct

[PATCH 4/4] nvme: fc: abort commands before resetting controller

-by: Johannes Thumshirn --- drivers/nvme/host/fc.c | 9 + 1 file changed, 9 insertions(+) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 9cc33752539a..0ba0075c3b75 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2054,6 +2054,15 @@ nvme_fc_timeout(struct

Re: [PATCH] watchdog: add driver for the MEN 16z069 IP-Core

other possibility would be to detect the current watchdog state > (and possibly timeout) and inform the watchdog core that the watchdog > is running. This way there is no gap in watchdog coverage if the > watchdog was already enabled in BIOS/ROMMON. This is a leftover from debugging the Qe

[PATCH v2] watchdog: add driver for the MEN 16z069 IP-Core

Add a driver for the MEN 16z069 Watchdog and Reset Controller IP-Core. Signed-off-by: Johannes Thumshirn --- Changes to v1: * Sorted includes alphabetically * Indented defines with tabs * Removed unnecessary timeout validation * Removed unnecessary masking of values * Fixed error return

Re: [PATCH] watchdog: add driver for the MEN 16z069 IP-Core

other possibility would be to detect the current watchdog state > (and possibly timeout) and inform the watchdog core that the watchdog > is running. This way there is no gap in watchdog coverage if the > watchdog was already enabled in BIOS/ROMMON. This is a leftover from debugging the Qe

[PATCH v2] watchdog: add driver for the MEN 16z069 IP-Core

Add a driver for the MEN 16z069 Watchdog and Reset Controller IP-Core. Signed-off-by: Johannes Thumshirn --- Changes to v1: * Sorted includes alphabetically * Indented defines with tabs * Removed unnecessary timeout validation * Removed unnecessary masking of values * Fixed error return

[PATCH] watchdog: add driver for the MEN 16z069 IP-Core

Add a driver for the MEN 16z069 Watchdog and Reset Controller IP-Core. Signed-off-by: Johannes Thumshirn --- MAINTAINERS | 6 ++ drivers/watchdog/Kconfig | 10 +++ drivers/watchdog/Makefile | 1 + drivers/watchdog/menz69_wdt.c | 175

[PATCH] watchdog: add driver for the MEN 16z069 IP-Core

Add a driver for the MEN 16z069 Watchdog and Reset Controller IP-Core. Signed-off-by: Johannes Thumshirn --- MAINTAINERS | 6 ++ drivers/watchdog/Kconfig | 10 +++ drivers/watchdog/Makefile | 1 + drivers/watchdog/menz69_wdt.c | 175

Re: [PATCHv2 4/4] nvme: add disk name to tracepoints

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCHv2 4/4] nvme: add disk name to tracepoints

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCHv2 3/4] nvme: trace controller name

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCHv2 3/4] nvme: trace controller name

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCHv2 1/4] nvme: trace nvme queue identifiers

On Thu, Jun 28, 2018 at 03:49:53PM -0600, Keith Busch wrote: > > +static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, > +unsigned nsid); This looks like a leftover from something different. Otherwise, Reviewed-by: Johannes

Re: [PATCHv2 2/4] nvme: cache struct nvme_ctrl reference to struct nvme_request

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCHv2 2/4] nvme: cache struct nvme_ctrl reference to struct nvme_request

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCHv2 1/4] nvme: trace nvme queue identifiers

On Thu, Jun 28, 2018 at 03:49:53PM -0600, Keith Busch wrote: > > +static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, > +unsigned nsid); This looks like a leftover from something different. Otherwise, Reviewed-by: Johannes

Re: [PATCH] nvme: trace: add disk name to tracepoints

> the two events. > > Here's an updated proposal and actually tested. I was also able to > combine admin and io submissions. Awesome, thanks. Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de

Re: [PATCH] nvme: trace: add disk name to tracepoints

> the two events. > > Here's an updated proposal and actually tested. I was also able to > combine admin and io submissions. Awesome, thanks. Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de

Re: [PATCH v5 2/2] nvme: trace: add disk name to tracepoints

On Wed, Jun 27, 2018 at 10:37:06AM -0600, Keith Busch wrote: > It looks like you want the # assigned to /dev/nvme<#>. Do you want to > use ctrl->instance here instead? Right. As it'll conflict with your other trace patch do you want me to wait with the resend? Johann

Re: [PATCH v5 2/2] nvme: trace: add disk name to tracepoints

On Wed, Jun 27, 2018 at 10:37:06AM -0600, Keith Busch wrote: > It looks like you want the # assigned to /dev/nvme<#>. Do you want to > use ctrl->instance here instead? Right. As it'll conflict with your other trace patch do you want me to wait with the resend? Johann

[PATCH v5 2/2] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output and admin commands which are represented without a disk name. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 39

[PATCH v5 2/2] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output and admin commands which are represented without a disk name. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 39

[PATCH v5 1/2] nvme: cache struct nvme_ctrl reference to struct nvme_request

From: Sagi Grimberg We will need to reference the controller in the setup and completion time for tracing and future traffic based keep alive support. Signed-off-by: Sagi Grimberg --- Changes to v4: - Move caching from nvme_setup_cmd to .init_request (Keith) --- drivers/nvme/host/core.c |

[PATCH v5 0/2] nvme: add controller id and disk name to tracepoints

the individual controllers and disks. The patches are relative to the nvme-4.19 branch. Changes to v4: * Move nvme_ctrl caching into init_request callouts * I decided against renaming the qid tag in the tracepints but opt-in for a hwqid once we have all the infor available Johannes Thumshirn (1

[PATCH v5 0/2] nvme: add controller id and disk name to tracepoints

the individual controllers and disks. The patches are relative to the nvme-4.19 branch. Changes to v4: * Move nvme_ctrl caching into init_request callouts * I decided against renaming the qid tag in the tracepints but opt-in for a hwqid once we have all the infor available Johannes Thumshirn (1

[PATCH v5 1/2] nvme: cache struct nvme_ctrl reference to struct nvme_request

From: Sagi Grimberg We will need to reference the controller in the setup and completion time for tracing and future traffic based keep alive support. Signed-off-by: Sagi Grimberg --- Changes to v4: - Move caching from nvme_setup_cmd to .init_request (Keith) --- drivers/nvme/host/core.c |

Re: [PATCH] nvme: trace: add disk name to tracepoints

On Wed, Jun 27, 2018 at 11:06:22AM +0300, Sagi Grimberg wrote: > Maybe change the display to request_queue_id=%d? request_queue_id is pretty long, how about rqid? -- Johannes Thumshirn Storage jthumsh...@suse.de+49

Re: [PATCH] nvme: trace: add disk name to tracepoints

On Wed, Jun 27, 2018 at 11:06:22AM +0300, Sagi Grimberg wrote: > Maybe change the display to request_queue_id=%d? request_queue_id is pretty long, how about rqid? -- Johannes Thumshirn Storage jthumsh...@suse.de+49

Re: [PATCH v4 1/2] nvme: cache struct nvme_ctrl reference to struct nvme_request

On Tue, Jun 26, 2018 at 08:55:32AM -0600, Keith Busch wrote: > On Tue, Jun 26, 2018 at 03:51:40PM +0200, Johannes Thumshirn wrote: > > @@ -652,6 +653,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct > > request *req, > > } > > > >

Re: [PATCH v4 1/2] nvme: cache struct nvme_ctrl reference to struct nvme_request

On Tue, Jun 26, 2018 at 08:55:32AM -0600, Keith Busch wrote: > On Tue, Jun 26, 2018 at 03:51:40PM +0200, Johannes Thumshirn wrote: > > @@ -652,6 +653,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct > > request *req, > > } > > > >

Re: [PATCH] nvme: trace: add disk name to tracepoints

; completion trace, it's actually a little confusing to see the qid in the > trace. It was actually requested by Martin so we can easily see which request got dispatched/completed on which request queue. -- Johannes Thumshirn Stora

Re: [PATCH] nvme: trace: add disk name to tracepoints

; completion trace, it's actually a little confusing to see the qid in the > trace. It was actually requested by Martin so we can easily see which request got dispatched/completed on which request queue. -- Johannes Thumshirn Stora

[PATCH v4 0/2] nvme: add controller id and disk name to tracepoints

the individual controllers and disks. The patches are relative to the nvme-4.19 branch. Johannes Thumshirn (1): nvme: trace: add disk name to tracepoints Sagi Grimberg (1): nvme: cache struct nvme_ctrl reference to struct nvme_request drivers/nvme/host/core.c | 10 ++ drivers/nvme/host

[PATCH v4 0/2] nvme: add controller id and disk name to tracepoints

the individual controllers and disks. The patches are relative to the nvme-4.19 branch. Johannes Thumshirn (1): nvme: trace: add disk name to tracepoints Sagi Grimberg (1): nvme: cache struct nvme_ctrl reference to struct nvme_request drivers/nvme/host/core.c | 10 ++ drivers/nvme/host

[PATCH] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output and admin commands which are represented without a disk name. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 39

[PATCH] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output and admin commands which are represented without a disk name. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 39

[PATCH v4 1/2] nvme: cache struct nvme_ctrl reference to struct nvme_request

From: Sagi Grimberg We will need to reference the controller in the setup and completion time for tracing and future traffic based keep alive support. Signed-off-by: Sagi Grimberg --- drivers/nvme/host/core.c | 6 -- drivers/nvme/host/fc.c | 2 +- drivers/nvme/host/nvme.h | 5

[PATCH v4 1/2] nvme: cache struct nvme_ctrl reference to struct nvme_request

From: Sagi Grimberg We will need to reference the controller in the setup and completion time for tracing and future traffic based keep alive support. Signed-off-by: Sagi Grimberg --- drivers/nvme/host/core.c | 6 -- drivers/nvme/host/fc.c | 2 +- drivers/nvme/host/nvme.h | 5

Re: [PATCH v4 1/1] nvme: trace: add disk name to tracepoints

On Tue, Jun 26, 2018 at 01:59:00PM +0300, Sagi Grimberg wrote: > You want to submit or should I? Whatever is easier for you -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr

Re: [PATCH v4 1/1] nvme: trace: add disk name to tracepoints

On Tue, Jun 26, 2018 at 01:59:00PM +0300, Sagi Grimberg wrote: > You want to submit or should I? Whatever is easier for you -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr

Re: [PATCH v4 1/1] nvme: trace: add disk name to tracepoints

On Mon, Jun 25, 2018 at 04:31:28PM +0300, Sagi Grimberg wrote: > > > On 06/25/2018 10:08 AM, Johannes Thumshirn wrote: > > On Tue, Jun 19, 2018 at 05:09:27PM +0300, Sagi Grimberg wrote: > > > We are going to need it for traffic based keep alive to update > > > t

Re: [PATCH v4 1/1] nvme: trace: add disk name to tracepoints

On Mon, Jun 25, 2018 at 04:31:28PM +0300, Sagi Grimberg wrote: > > > On 06/25/2018 10:08 AM, Johannes Thumshirn wrote: > > On Tue, Jun 19, 2018 at 05:09:27PM +0300, Sagi Grimberg wrote: > > > We are going to need it for traffic based keep alive to update > > > t

Re: [PATCH v4 1/1] nvme: trace: add disk name to tracepoints

't need to pass it to nvme_complete_req (that's what > I did for traffic based keep alive). Do you have a patch for this around? IIRC I started this (as Christoph also suggested it) but it turned out to be quite a big refactoring work. Byte, Johannes --

Re: [PATCH v4 1/1] nvme: trace: add disk name to tracepoints

't need to pass it to nvme_complete_req (that's what > I did for traffic based keep alive). Do you have a patch for this around? IIRC I started this (as Christoph also suggested it) but it turned out to be quite a big refactoring work. Byte, Johannes --

[PATCH v4 1/1] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn --- I'm not entirely sure if this adding the ctrl pointers to nvme_complete_rq() and nvme_setup_cmd() is a good idea, it's the fast-path after all. Changes

[PATCH v4 1/1] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn --- I'm not entirely sure if this adding the ctrl pointers to nvme_complete_rq() and nvme_setup_cmd() is a good idea, it's the fast-path after all. Changes

[PATCH v3] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn --- Changes to v2: * Pass nvme_ctrl to nvme_complete_rq() and nvme_setup_cmd() * Fixed typo in commit message (Sagi) * Dropped Sagi's R-b (it changed quite

[PATCH v3] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better distinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn --- Changes to v2: * Pass nvme_ctrl to nvme_complete_rq() and nvme_setup_cmd() * Fixed typo in commit message (Sagi) * Dropped Sagi's R-b (it changed quite

Re: [PATCH] pcmcia: add error handling for pcmcia_enable_device

ks if the device is locked, decrements the lock counter, clears the CONFIG_LOCKED bit in the PCMCIA config and sets the voltage to 0 without the first driver every noticing it. Byte, Johannes -- Johannes Thumshirn Storage jthumsh...@suse.de

Re: [PATCH] pcmcia: add error handling for pcmcia_enable_device

ks if the device is locked, decrements the lock counter, clears the CONFIG_LOCKED bit in the PCMCIA config and sets the voltage to 0 without the first driver every noticing it. Byte, Johannes -- Johannes Thumshirn Storage jthumsh...@suse.de

Re: [PATCH 0/3] Provide more fine grained control over multipathing

I said elsewhere and then see. Martin Wilck was already working on patches for this. -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smi

Re: [PATCH 0/3] Provide more fine grained control over multipathing

I said elsewhere and then see. Martin Wilck was already working on patches for this. -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smi

[PATCH v2] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better destinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg --- Changes to v1: * Rebase onto nvme-4.18 --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 32

[PATCH v2] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better destinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg --- Changes to v1: * Rebase onto nvme-4.18 --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 32

[PATCH] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better destinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 32 2 files changed, 22 insertions(+), 14 deletions

[PATCH] nvme: trace: add disk name to tracepoints

Add disk name to tracepoints so we can better destinguish between individual disks in the trace output. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/trace.h | 32 2 files changed, 22 insertions(+), 14 deletions

Re: [PATCH 3/8] scsi: libsas: always unregister the old device if going to discover new

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCH 3/8] scsi: libsas: always unregister the old device if going to discover new

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCH 0/3] Provide more fine grained control over multipathing

ething else than flamewars. Johannes -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG Nürnberg) Key f

Re: [PATCH 0/3] Provide more fine grained control over multipathing

ething else than flamewars. Johannes -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG Nürnberg) Key f

Re: [PATCH 0/3] Provide more fine grained control over multipathing

On Fri, May 25, 2018 at 03:05:35PM +0200, Christoph Hellwig wrote: > On Fri, May 25, 2018 at 02:53:19PM +0200, Johannes Thumshirn wrote: > > Hi, > > > > This patch series aims to provide a more fine grained control over > > nvme's native multipathing, by allowing i

Re: [PATCH 0/3] Provide more fine grained control over multipathing

On Fri, May 25, 2018 at 03:05:35PM +0200, Christoph Hellwig wrote: > On Fri, May 25, 2018 at 02:53:19PM +0200, Johannes Thumshirn wrote: > > Hi, > > > > This patch series aims to provide a more fine grained control over > > nvme's native multipathing, by allowing i

[PATCH 2/3] nvme multipath: added SUBSYS_ATTR_RW

From: Mike Snitzer Prep for adding dev_attr in addition to subsys_attr for 'mpath_personality'. Signed-off-by: Mike Snitzer --- drivers/nvme/host/core.c | 34 ++ 1 file changed, 18 insertions(+), 16 deletions(-) diff

[PATCH 2/3] nvme multipath: added SUBSYS_ATTR_RW

From: Mike Snitzer Prep for adding dev_attr in addition to subsys_attr for 'mpath_personality'. Signed-off-by: Mike Snitzer --- drivers/nvme/host/core.c | 34 ++ 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/nvme/host/core.c

[PATCH 3/3] nvme multipath: add dev_attr_mpath_personality

From: Mike Snitzer Allows the ability to consistently access 'mpath_personality' regardless of which mode we're in (native vs other), using: /sys/block/nvmeXn1/device/mpath_personality Signed-off-by: Mike Snitzer --- drivers/nvme/host/core.c | 57

[PATCH 3/3] nvme multipath: add dev_attr_mpath_personality

From: Mike Snitzer Allows the ability to consistently access 'mpath_personality' regardless of which mode we're in (native vs other), using: /sys/block/nvmeXn1/device/mpath_personality Signed-off-by: Mike Snitzer --- drivers/nvme/host/core.c | 57

[PATCH 1/3] nvme: provide a way to disable nvme mpath per subsystem

Provide a way to disable NVMe native multipathing on a per-subsystem basis to enable a user to use dm-mpath and nvme native multipathing on the same host for different nvme devices. Signed-off-by: Johannes Thumshirn <jthumsh...@suse.de> --- drivers/nvme/host/core.c

[PATCH 1/3] nvme: provide a way to disable nvme mpath per subsystem

Provide a way to disable NVMe native multipathing on a per-subsystem basis to enable a user to use dm-mpath and nvme native multipathing on the same host for different nvme devices. Signed-off-by: Johannes Thumshirn --- drivers/nvme/host/core.c | 63

[PATCH 0/3] Provide more fine grained control over multipathing

would need to uncomment the rmmods). Johannes Thumshirn (1): nvme: provide a way to disable nvme mpath per subsystem Mike Snitzer (2): nvme multipath: added SUBSYS_ATTR_RW nvme multipath: add dev_attr_mpath_personality drivers/nvme/host/core.c | 112

[PATCH 0/3] Provide more fine grained control over multipathing

would need to uncomment the rmmods). Johannes Thumshirn (1): nvme: provide a way to disable nvme mpath per subsystem Mike Snitzer (2): nvme multipath: added SUBSYS_ATTR_RW nvme multipath: add dev_attr_mpath_personality drivers/nvme/host/core.c | 112

Re: [PATCH v3] nvme: fix lockdep warning in nvme_mpath_clear_current_path

Keith, Sagi, Christoph ping? -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG Nürnberg) Key

Re: [PATCH v3] nvme: fix lockdep warning in nvme_mpath_clear_current_path

Keith, Sagi, Christoph ping? -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG Nürnberg) Key

Re: [PATCH 08/10] block: Add warning for bi_next not NULL in bio_endio()

Looks good, Reviewed-by: Johannes Thumshirn <jthumsh...@suse.de> -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard,

Re: [PATCH 08/10] block: Add warning for bi_next not NULL in bio_endio()

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCH 03/10] block: Add bioset_init()/bioset_exit()

Looks good, Reviewed-by: Johannes Thumshirn <jthumsh...@suse.de> -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard,

Re: [PATCH 03/10] block: Add bioset_init()/bioset_exit()

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCH 01/10] mempool: Add mempool_init()/mempool_exit()

Looks good, Reviewed-by: Johannes Thumshirn <jthumsh...@suse.de> -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard,

Re: [PATCH 01/10] mempool: Add mempool_init()/mempool_exit()

Looks good, Reviewed-by: Johannes Thumshirn -- Johannes Thumshirn Storage jthumsh...@suse.de+49 911 74053 689 SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg GF: Felix Imendörffer, Jane Smithard, Graham Norton HRB 21284 (AG

Re: [PATCH 02/10] block: Convert bio_set to mempool_init()

On Fri, May 18, 2018 at 03:49:01AM -0400, Kent Overstreet wrote: > Minor performance improvement by getting rid of pointer indirections > from allocation/freeing fastpaths. Reviewed-by: Johannes Thumshirn <jthumsh...@suse.de> Although I'd prefer numbers in the changelog w

Re: [PATCH 02/10] block: Convert bio_set to mempool_init()

On Fri, May 18, 2018 at 03:49:01AM -0400, Kent Overstreet wrote: > Minor performance improvement by getting rid of pointer indirections > from allocation/freeing fastpaths. Reviewed-by: Johannes Thumshirn Although I'd prefer numbers in the changelog when claiming a performance impro

[PATCH v3] nvme: fix lockdep warning in nvme_mpath_clear_current_path

pointer(), we're telling rcu and lockdep that we're only after the pointer falue. Fixes: 32acab3181c7 ("nvme: implement multipath access to nvme subsystems") Signed-off-by: Johannes Thumshirn <jthumsh...@suse.de> Suggested-by: Paul E. McKenney <paul...@linux.vnet.ibm.com> Revie

[PATCH v3] nvme: fix lockdep warning in nvme_mpath_clear_current_path

pointer(), we're telling rcu and lockdep that we're only after the pointer falue. Fixes: 32acab3181c7 ("nvme: implement multipath access to nvme subsystems") Signed-off-by: Johannes Thumshirn Suggested-by: Paul E. McKenney Reviewed-by: Christoph Hellwig --- Changes to v2: - Added Chri

Re: [PATCH 3/5] nvme: call nvmf_create_ctrl before checking for duplicate assignment

On Tue, May 15, 2018 at 09:50:55AM +0200, Christoph Hellwig wrote: > On Tue, May 15, 2018 at 09:40:41AM +0200, Johannes Thumshirn wrote: > > In nvmf_dev_write we did check if the /dev/nvme-fabrics device node's > > private data is already set and then create a controller dat

Re: [PATCH 3/5] nvme: call nvmf_create_ctrl before checking for duplicate assignment

On Tue, May 15, 2018 at 09:50:55AM +0200, Christoph Hellwig wrote: > On Tue, May 15, 2018 at 09:40:41AM +0200, Johannes Thumshirn wrote: > > In nvmf_dev_write we did check if the /dev/nvme-fabrics device node's > > private data is already set and then create a controller dat

[PATCH 2/5] nvme: don't hold nvmf_transports_rwsem for more than transport lookups

] ? security_file_permission+0x2f/0xb0 [9.741526] vfs_write+0xbd/0x1c0 [9.742095] ksys_write+0x40/0xa0 [9.742681] ? do_syscall_64+0xd/0x190 [9.743335] do_syscall_64+0x51/0x190 [9.744415] entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Johannes Thumshirn <jthumsh...@suse

[PATCH 2/5] nvme: don't hold nvmf_transports_rwsem for more than transport lookups

] ? security_file_permission+0x2f/0xb0 [9.741526] vfs_write+0xbd/0x1c0 [9.742095] ksys_write+0x40/0xa0 [9.742681] ? do_syscall_64+0xd/0x190 [9.743335] do_syscall_64+0x51/0x190 [9.744415] entry_SYSCALL_64_after_hwframe+0x49/0xbe Signed-off-by: Johannes Thumshirn --- drivers/nvme/host

[PATCHv2 1/5] nvme: fix lockdep warning in nvme_mpath_clear_current_path

: implement multipath access to nvme subsystems") Signed-off-by: Johannes Thumshirn <jthumsh...@suse.de> Suggested-by: Paul E. McKenney <paul...@linux.vnet.ibm.com> --- Changes to v1: - Change rcu_dereference_protected() to rc_access_pointer() (Paul) --- drivers/nvme/host/nvme.h

[PATCHv2 1/5] nvme: fix lockdep warning in nvme_mpath_clear_current_path

: implement multipath access to nvme subsystems") Signed-off-by: Johannes Thumshirn Suggested-by: Paul E. McKenney --- Changes to v1: - Change rcu_dereference_protected() to rc_access_pointer() (Paul) --- drivers/nvme/host/nvme.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff

[PATCH 5/5] nvmet: fcloop: use irqsave spinlocks

187280] R13: R14: 9f54f8b86200 R15: 9f54f8b86200 [ 11.188280] default_idle+0x18/0x180 [ 11.188806] do_idle+0x176/0x260 [ 11.189273] cpu_startup_entry+0x5a/0x60 [ 11.189832] start_secondary+0x18f/0x1b0 Signed-off-by: Johannes Thumshirn <jthumsh...@suse.de> Cc

[PATCH 3/5] nvme: call nvmf_create_ctrl before checking for duplicate assignment

-by: Johannes Thumshirn <jthumsh...@suse.de> --- drivers/nvme/host/fabrics.c | 11 +-- 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index febf82639b40..757a49b9c5a8 100644 --- a/drivers/nvme/host/fabrics.c

[PATCH 5/5] nvmet: fcloop: use irqsave spinlocks

187280] R13: R14: 9f54f8b86200 R15: 9f54f8b86200 [ 11.188280] default_idle+0x18/0x180 [ 11.188806] do_idle+0x176/0x260 [ 11.189273] cpu_startup_entry+0x5a/0x60 [ 11.189832] start_secondary+0x18f/0x1b0 Signed-off-by: Johannes Thumshirn Cc: James Smart ---

<    1   2   3   4   5   6   7   8   9   10   >