From 3bd6f43f5cb3714f70c591514f344389df593501 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Mon, 4 Dec 2017 10:06:23 -0800 Subject: scsi: core: Ensure that the SCSI error handler gets woken up If scsi_eh_scmd_add() is called concurrently with scsi_host_queue_ready() while shost->host_blocked > 0 then it can happen that neither function wakes up the SCSI error handler. Fix this by making every function that decreases the host_busy counter wake up the error handler if necessary and by protecting the host_failed checks with the SCSI host lock. Reported-by: Pavel Tikhomirov References: https://marc.info/?l=linux-kernel&m=150461610630736 Fixes: commit 746650160866 ("scsi: convert host_busy to atomic_t") Signed-off-by: Bart Van Assche Reviewed-by: Pavel Tikhomirov Tested-by: Stuart Hayes Cc: Konstantin Khorenko Cc: Stuart Hayes Cc: Pavel Tikhomirov Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Signed-off-by: Martin K. Petersen --- include/scsi/scsi_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index a8b7bf879ced..1a1df0d21ee3 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -571,6 +571,8 @@ struct Scsi_Host { struct blk_mq_tag_set tag_set; }; + struct rcu_head rcu; + atomic_t host_busy; /* commands actually active on low-level */ atomic_t host_blocked; -- cgit v1.2.3 From e4c9470b9f21a0ee3b4625f6d29792c240b71c67 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 7 Dec 2017 15:59:31 -0800 Subject: scsi: core: Unexport scsi_initialize_rq() Commit 651a01364994 ("scsi: scsi_transport_sas: switch to bsg-lib for SMP passthrough") removed the only call to scsi_initialize_rq() from outside the SCSI core. Hence unexport scsi_initialize_rq(). Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 7fb57e905526..949a016dd7fa 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -171,7 +171,6 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count, extern void scsi_kunmap_atomic_sg(void *virt); extern int scsi_init_io(struct scsi_cmnd *cmd); -extern void scsi_initialize_rq(struct request *rq); extern int scsi_dma_map(struct scsi_cmnd *cmd); extern void scsi_dma_unmap(struct scsi_cmnd *cmd); -- cgit v1.2.3 From cc019a5a3b58670efe765f19aec42e28c16d7aed Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 21 Dec 2017 14:25:52 -0800 Subject: scsi: scsi_transport_fc: fix typos on 64/128 GBit define names The define names specified 64Bit/128Bit, not 64GBIT/128GBIT. Correct the names. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_fc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h index 8cf30215c177..15da45dc2a5d 100644 --- a/include/scsi/scsi_transport_fc.h +++ b/include/scsi/scsi_transport_fc.h @@ -139,8 +139,8 @@ enum fc_vport_state { #define FC_PORTSPEED_50GBIT 0x200 #define FC_PORTSPEED_100GBIT 0x400 #define FC_PORTSPEED_25GBIT 0x800 -#define FC_PORTSPEED_64BIT 0x1000 -#define FC_PORTSPEED_128BIT 0x2000 +#define FC_PORTSPEED_64GBIT 0x1000 +#define FC_PORTSPEED_128GBIT 0x2000 #define FC_PORTSPEED_NOT_NEGOTIATED (1 << 15) /* Speed not established */ /* -- cgit v1.2.3 From 1c393b970e0f4070e4376d45f89a2d19a5c895d0 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 8 Dec 2017 17:42:04 +0800 Subject: scsi: libsas: Use dynamic alloced work to avoid sas event lost Now libsas hotplug work is static, every sas event type has its own static work, LLDD driver queues the hotplug work into shost->work_q. If LLDD driver burst posts lots hotplug events to libsas, the hotplug events may pending in the workqueue like shost->work_q new work[PORTE_BYTES_DMAED] --> |[PHYE_LOSS_OF_SIGNAL][PORTE_BYTES_DMAED] -> processing |<-------wait worker to process-------->| In this case, a new PORTE_BYTES_DMAED event coming, libsas try to queue it to shost->work_q, but this work is already pending, so it would be lost. Finally, libsas delete the related sas port and sas devices, but LLDD driver expect libsas add the sas port and devices(last sas event). This patch use dynamic allocated work to avoid this issue. Signed-off-by: Yijing Wang CC: John Garry CC: Johannes Thumshirn CC: Ewan Milne CC: Christoph Hellwig CC: Tomas Henzl CC: Dan Williams Reviewed-by: Hannes Reinecke Signed-off-by: Jason Yan Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 0f9cbf96c093..ee1b25299dd6 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -292,6 +292,7 @@ struct asd_sas_port { struct asd_sas_event { struct sas_work work; struct asd_sas_phy *phy; + int event; }; static inline struct asd_sas_event *to_asd_sas_event(struct work_struct *work) @@ -301,17 +302,21 @@ static inline struct asd_sas_event *to_asd_sas_event(struct work_struct *work) return ev; } +static inline void INIT_SAS_EVENT(struct asd_sas_event *ev, + void (*fn)(struct work_struct *), + struct asd_sas_phy *phy, int event) +{ + INIT_SAS_WORK(&ev->work, fn); + ev->phy = phy; + ev->event = event; +} + + /* The phy pretty much is controlled by the LLDD. * The class only reads those fields. */ struct asd_sas_phy { /* private: */ - struct asd_sas_event port_events[PORT_NUM_EVENTS]; - struct asd_sas_event phy_events[PHY_NUM_EVENTS]; - - unsigned long port_events_pending; - unsigned long phy_events_pending; - int error; int suspended; -- cgit v1.2.3 From f12486e06ae87453530f00a6cb49b60ae3fe4551 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 8 Dec 2017 17:42:05 +0800 Subject: scsi: libsas: shut down the PHY if events reached the threshold If the PHY burst too many events, we will alloc a lot of events for the worker. This may leads to memory exhaustion. Dan Williams suggested to shut down the PHY if the events reached the threshold, because in this case the PHY may have gone into some erroneous state. Users can re-enable the PHY by sysfs if they want. We cannot use the fixed memory pool because if we run out of events, the shut down event and loss of signal event will lost too. The events still need to be allocated and processed in this case. Suggested-by: Dan Williams Signed-off-by: Jason Yan CC: John Garry CC: Johannes Thumshirn CC: Ewan Milne CC: Christoph Hellwig CC: Tomas Henzl Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index ee1b25299dd6..de8f043475c2 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -75,6 +75,7 @@ enum phy_event { PHYE_OOB_ERROR, PHYE_SPINUP_HOLD, /* hot plug SATA, no COMWAKE sent */ PHYE_RESUME_TIMEOUT, + PHYE_SHUTDOWN, PHY_NUM_EVENTS, }; @@ -311,12 +312,15 @@ static inline void INIT_SAS_EVENT(struct asd_sas_event *ev, ev->event = event; } +#define SAS_PHY_SHUTDOWN_THRES 1024 /* The phy pretty much is controlled by the LLDD. * The class only reads those fields. */ struct asd_sas_phy { /* private: */ + atomic_t event_nr; + int in_shutdown; int error; int suspended; @@ -404,6 +408,8 @@ struct sas_ha_struct { struct list_head eh_done_q; /* complete via scsi_eh_flush_done_q */ struct list_head eh_ata_q; /* scmds to promote from sas to ata eh */ + + int event_thres; }; #define SHOST_TO_SAS_HA(_shost) (*(struct sas_ha_struct **)(_shost)->hostdata) -- cgit v1.2.3 From 8eea9dd84e450e5262643823691108f2a208a2ac Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 8 Dec 2017 17:42:06 +0800 Subject: scsi: libsas: make the event threshold configurable Add a sysfs attr that LLDD can configure it for every host. We made an example in hisi_sas. Other LLDDs using libsas can implement it if they want. Suggested-by: Hannes Reinecke Signed-off-by: Jason Yan CC: John Garry CC: Johannes Thumshirn CC: Ewan Milne CC: Christoph Hellwig CC: Tomas Henzl CC: Dan Williams Acked-by: John Garry #for hisi_sas part Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index de8f043475c2..3769615d4ce9 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -681,6 +681,7 @@ extern int sas_bios_param(struct scsi_device *, sector_t capacity, int *hsc); extern struct scsi_transport_template * sas_domain_attach_transport(struct sas_domain_function_template *); +extern struct device_attribute dev_attr_phy_event_threshold; int sas_discover_root_expander(struct domain_device *); -- cgit v1.2.3 From 93bdbd06b1644ac15aa152e91faefed86cc04937 Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 8 Dec 2017 17:42:07 +0800 Subject: scsi: libsas: Use new workqueue to run sas event and disco event Now all libsas works are queued to scsi host workqueue, include sas event work post by LLDD and sas discovery work, and a sas hotplug flow may be divided into several works, e.g libsas receive a PORTE_BYTES_DMAED event, currently we process it as following steps: sas_form_port --- run in work in shost workq sas_discover_domain --- run in another work in shost workq ... sas_probe_devices --- run in new work in shost workq We found during hot-add a device, libsas may need run several works in same workqueue to add device in system, the process is not atomic, it may interrupt by other sas event works, like PHYE_LOSS_OF_SIGNAL. This patch is preparation of execute libsas sas event in sync. We need to use different workqueue to run sas event and disco event. Otherwise the work will be blocked for waiting another chained work in the same workqueue. Signed-off-by: Yijing Wang CC: John Garry CC: Johannes Thumshirn CC: Ewan Milne CC: Christoph Hellwig CC: Tomas Henzl CC: Dan Williams Signed-off-by: Jason Yan Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 3769615d4ce9..6255bb5ed1e4 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -389,6 +389,9 @@ struct sas_ha_struct { struct device *dev; /* should be set */ struct module *lldd_module; /* should be set */ + struct workqueue_struct *event_q; + struct workqueue_struct *disco_q; + u8 *sas_addr; /* must be set */ u8 hashed_sas_addr[HASHED_SAS_ADDR_SIZE]; -- cgit v1.2.3 From 0558f33c06bb910e2879e355192227a8e8f0219d Mon Sep 17 00:00:00 2001 From: Jason Yan Date: Fri, 8 Dec 2017 17:42:09 +0800 Subject: scsi: libsas: direct call probe and destruct In commit 87c8331fcf72 ("[SCSI] libsas: prevent domain rediscovery competing with ata error handling") introduced disco mutex to prevent rediscovery competing with ata error handling and put the whole revalidation in the mutex. But the rphy add/remove needs to wait for the error handling which also grabs the disco mutex. This may leads to dead lock.So the probe and destruct event were introduce to do the rphy add/remove asynchronously and out of the lock. The asynchronously processed workers makes the whole discovery process not atomic, the other events may interrupt the process. For example, if a loss of signal event inserted before the probe event, the sas_deform_port() is called and the port will be deleted. And sas_port_delete() may run before the destruct event, but the port-x:x is the top parent of end device or expander. This leads to a kernel WARNING such as: [ 82.042979] sysfs group 'power' not found for kobject 'phy-1:0:22' [ 82.042983] ------------[ cut here ]------------ [ 82.042986] WARNING: CPU: 54 PID: 1714 at fs/sysfs/group.c:237 sysfs_remove_group+0x94/0xa0 [ 82.043059] Call trace: [ 82.043082] [] sysfs_remove_group+0x94/0xa0 [ 82.043085] [] dpm_sysfs_remove+0x60/0x70 [ 82.043086] [] device_del+0x138/0x308 [ 82.043089] [] sas_phy_delete+0x38/0x60 [ 82.043091] [] do_sas_phy_delete+0x6c/0x80 [ 82.043093] [] device_for_each_child+0x58/0xa0 [ 82.043095] [] sas_remove_children+0x40/0x50 [ 82.043100] [] sas_destruct_devices+0x64/0xa0 [ 82.043102] [] process_one_work+0x1fc/0x4b0 [ 82.043104] [] worker_thread+0x50/0x490 [ 82.043105] [] kthread+0xfc/0x128 [ 82.043107] [] ret_from_fork+0x10/0x50 Make probe and destruct a direct call in the disco and revalidate function, but put them outside the lock. The whole discovery or revalidate won't be interrupted by other events. And the DISCE_PROBE and DISCE_DESTRUCT event are deleted as a result of the direct call. Introduce a new list to destruct the sas_port and put the port delete after the destruct. This makes sure the right order of destroying the sysfs kobject and fix the warning above. In sas_ex_revalidate_domain() have a loop to find all broadcasted device, and sometimes we have a chance to find the same expander twice. Because the sas_port will be deleted at the end of the whole revalidate process, sas_port with the same name cannot be added before this. Otherwise the sysfs will complain of creating duplicate filename. Since the LLDD will send broadcast for every device change, we can only process one expander's revalidation. [mkp: kbuild test robot warning] Signed-off-by: Jason Yan CC: John Garry CC: Johannes Thumshirn CC: Ewan Milne CC: Christoph Hellwig CC: Tomas Henzl CC: Dan Williams Reviewed-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 3 +-- include/scsi/scsi_transport_sas.h | 1 + 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 6255bb5ed1e4..1cab6f7af425 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -82,10 +82,8 @@ enum phy_event { enum discover_event { DISCE_DISCOVER_DOMAIN = 0U, DISCE_REVALIDATE_DOMAIN, - DISCE_PROBE, DISCE_SUSPEND, DISCE_RESUME, - DISCE_DESTRUCT, DISC_NUM_EVENTS, }; @@ -262,6 +260,7 @@ struct asd_sas_port { struct list_head dev_list; struct list_head disco_list; struct list_head destroy_list; + struct list_head sas_port_del_list; enum sas_linkrate linkrate; struct sas_work work; diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index 62895b405933..05ec927a3c72 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -156,6 +156,7 @@ struct sas_port { struct mutex phy_list_mutex; struct list_head phy_list; + struct list_head del_list; /* libsas only */ }; #define dev_to_sas_port(d) \ -- cgit v1.2.3 From d5c15c2c22a8d4e0e82ca95eac5a6ccd175c0762 Mon Sep 17 00:00:00 2001 From: chenxiang Date: Thu, 28 Dec 2017 18:20:46 +0800 Subject: scsi: ata: enhance the definition of SET MAX feature field value There are two other values for SET MAX feature field according to ata protocol. So definite them. Signed-off-by: Xiang Chen Signed-off-by: John Garry Acked-by: Tejun Heo Signed-off-by: Martin K. Petersen --- include/linux/ata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index c7a353825450..40d150ad7e07 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -448,6 +448,8 @@ enum { ATA_SET_MAX_LOCK = 0x02, ATA_SET_MAX_UNLOCK = 0x03, ATA_SET_MAX_FREEZE_LOCK = 0x04, + ATA_SET_MAX_PASSWD_DMA = 0x05, + ATA_SET_MAX_UNLOCK_DMA = 0x06, /* feature values for DEVICE CONFIGURATION OVERLAY */ ATA_DCO_RESTORE = 0xC0, -- cgit v1.2.3 From 9c661a49e4318f11934115adb4c5a91e15efc0cc Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 19 Jan 2018 16:11:10 +0100 Subject: scsi: core: Add VENDOR_SPECIFIC sense code definitions Some older devices will return vendor specific sense codes, so we should be adding a definition for it. Signed-off-by: Hannes Reinecke Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_proto.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index 1df8efb0ee01..c36860111932 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -236,6 +236,7 @@ struct scsi_varlen_cdb_hdr { #define UNIT_ATTENTION 0x06 #define DATA_PROTECT 0x07 #define BLANK_CHECK 0x08 +#define VENDOR_SPECIFIC 0x09 #define COPY_ABORTED 0x0a #define ABORTED_COMMAND 0x0b #define VOLUME_OVERFLOW 0x0d -- cgit v1.2.3