From 79edd00dc6a96644d76b4a1cb97d94d49e026768 Mon Sep 17 00:00:00 2001 From: Anoob Soman Date: Wed, 13 Feb 2019 13:21:39 +0800 Subject: scsi: libiscsi: Fix race between iscsi_xmit_task and iscsi_complete_task When a target sends Check Condition, whilst initiator is busy xmiting re-queued data, could lead to race between iscsi_complete_task() and iscsi_xmit_task() and eventually crashing with the following kernel backtrace. [3326150.987523] ALERT: BUG: unable to handle kernel NULL pointer dereference at 0000000000000078 [3326150.987549] ALERT: IP: [] iscsi_xmit_task+0x2d/0xc0 [libiscsi] [3326150.987571] WARN: PGD 569c8067 PUD 569c9067 PMD 0 [3326150.987582] WARN: Oops: 0002 [#1] SMP [3326150.987593] WARN: Modules linked in: tun nfsv3 nfs fscache dm_round_robin [3326150.987762] WARN: CPU: 2 PID: 8399 Comm: kworker/u32:1 Tainted: G O 4.4.0+2 #1 [3326150.987774] WARN: Hardware name: Dell Inc. PowerEdge R720/0W7JN5, BIOS 2.5.4 01/22/2016 [3326150.987790] WARN: Workqueue: iscsi_q_13 iscsi_xmitworker [libiscsi] [3326150.987799] WARN: task: ffff8801d50f3800 ti: ffff8801f5458000 task.ti: ffff8801f5458000 [3326150.987810] WARN: RIP: e030:[] [] iscsi_xmit_task+0x2d/0xc0 [libiscsi] [3326150.987825] WARN: RSP: e02b:ffff8801f545bdb0 EFLAGS: 00010246 [3326150.987831] WARN: RAX: 00000000ffffffc3 RBX: ffff880282d2ab20 RCX: ffff88026b6ac480 [3326150.987842] WARN: RDX: 0000000000000000 RSI: 00000000fffffe01 RDI: ffff880282d2ab20 [3326150.987852] WARN: RBP: ffff8801f545bdc8 R08: 0000000000000000 R09: 0000000000000008 [3326150.987862] WARN: R10: 0000000000000000 R11: 000000000000fe88 R12: 0000000000000000 [3326150.987872] WARN: R13: ffff880282d2abe8 R14: ffff880282d2abd8 R15: ffff880282d2ac08 [3326150.987890] WARN: FS: 00007f5a866b4840(0000) GS:ffff88028a640000(0000) knlGS:0000000000000000 [3326150.987900] WARN: CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 [3326150.987907] WARN: CR2: 0000000000000078 CR3: 0000000070244000 CR4: 0000000000042660 [3326150.987918] WARN: Stack: [3326150.987924] WARN: ffff880282d2ad58 ffff880282d2ab20 ffff880282d2abe8 ffff8801f545be18 [3326150.987938] WARN: ffffffffa05cea90 ffff880282d2abf8 ffff88026b59cc80 ffff88026b59cc00 [3326150.987951] WARN: ffff88022acf32c0 ffff880289491800 ffff880255a80800 0000000000000400 [3326150.987964] WARN: Call Trace: [3326150.987975] WARN: [] iscsi_xmitworker+0x2f0/0x360 [libiscsi] [3326150.987988] WARN: [] process_one_work+0x1fc/0x3b0 [3326150.987997] WARN: [] worker_thread+0x2a5/0x470 [3326150.988006] WARN: [] ? __schedule+0x648/0x870 [3326150.988015] WARN: [] ? rescuer_thread+0x300/0x300 [3326150.988023] WARN: [] kthread+0xd5/0xe0 [3326150.988031] WARN: [] ? kthread_stop+0x110/0x110 [3326150.988040] WARN: [] ret_from_fork+0x3f/0x70 [3326150.988048] WARN: [] ? kthread_stop+0x110/0x110 [3326150.988127] ALERT: RIP [] iscsi_xmit_task+0x2d/0xc0 [libiscsi] [3326150.988138] WARN: RSP [3326150.988144] WARN: CR2: 0000000000000078 [3326151.020366] WARN: ---[ end trace 1c60974d4678d81b ]--- Commit 6f8830f5bbab ("scsi: libiscsi: add lock around task lists to fix list corruption regression") introduced "taskqueuelock" to fix list corruption during the race, but this wasn't enough. Re-setting of conn->task to NULL, could race with iscsi_xmit_task(). iscsi_complete_task() { .... if (conn->task == task) conn->task = NULL; } conn->task in iscsi_xmit_task() could be NULL and so will be task. __iscsi_get_task(task) will crash (NullPtr de-ref), trying to access refcount. iscsi_xmit_task() { struct iscsi_task *task = conn->task; __iscsi_get_task(task); } This commit will take extra conn->session->back_lock in iscsi_xmit_task() to ensure iscsi_xmit_task() waits for iscsi_complete_task(), if iscsi_complete_task() wins the race. If iscsi_xmit_task() wins the race, iscsi_xmit_task() increments task->refcount (__iscsi_get_task) ensuring iscsi_complete_task() will not iscsi_free_task(). Signed-off-by: Anoob Soman Signed-off-by: Bob Liu Acked-by: Lee Duncan Signed-off-by: Martin K. Petersen --- drivers/scsi/libiscsi.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index b8d325ce8754..120fc520f27a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1459,7 +1459,13 @@ static int iscsi_xmit_task(struct iscsi_conn *conn) if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) return -ENODATA; + spin_lock_bh(&conn->session->back_lock); + if (conn->task == NULL) { + spin_unlock_bh(&conn->session->back_lock); + return -ENODATA; + } __iscsi_get_task(task); + spin_unlock_bh(&conn->session->back_lock); spin_unlock_bh(&conn->session->frwd_lock); rc = conn->session->tt->xmit_task(task); spin_lock_bh(&conn->session->frwd_lock); -- cgit v1.2.3 From 515ce60613128be7a176a8b82b20c7624f3b440d Mon Sep 17 00:00:00 2001 From: Masato Suzuki Date: Thu, 14 Feb 2019 15:01:18 +0900 Subject: scsi: sd_zbc: Fix sd_zbc_report_zones() buffer allocation The function sd_zbc_do_report_zones() issues a REPORT ZONES command with a buffer size calculated based on the number of zones requested by the caller. This value should however not exceed the capabilities of the hardware maximum command size, that is, should not exceed the max_hw_sectors limit of the device. This problem leads to failures of report zones commands when re-validating disks with some SAS HBAs. Fix this by limiting a report zone command buffer size to the minimum of the device max_hw_sectors and calculated value based on the requested number of zones. This does not change the semantic of the report_zones file operation as report zones can always return less zone reports than requested. Short reports are handled using a loop execution of the report_zones file operation in the function blk_report_zones(). [Damien] Before patch 'e76239a3748c ("block: add a report_zones method")', report zones buffer allocation was limited to max_sectors when allocated in blk_report_zones(). This however does not consider the actual format of the device reply which is interface dependent. Limiting the allocation based on the size of the expected reply format rather than the size of the array of generic sturct blkzone passed by blk_report_zones() makes more sense. Fixes: e76239a3748c ("block: add a report_zones method") Cc: stable@vger.kernel.org Signed-off-by: Masato Suzuki Signed-off-by: Damien Le Moal Signed-off-by: Martin K. Petersen --- drivers/scsi/sd_zbc.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index fff86940388b..a340af797a85 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -142,10 +142,12 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, return -EOPNOTSUPP; /* - * Get a reply buffer for the number of requested zones plus a header. - * For ATA, buffers must be aligned to 512B. + * Get a reply buffer for the number of requested zones plus a header, + * without exceeding the device maximum command size. For ATA disks, + * buffers must be aligned to 512B. */ - buflen = roundup((nrz + 1) * 64, 512); + buflen = min(queue_max_hw_sectors(disk->queue) << 9, + roundup((nrz + 1) * 64, 512)); buf = kmalloc(buflen, gfp_mask); if (!buf) return -ENOMEM; -- cgit v1.2.3 From ffeafdd2bf0b280d67ec1a47ea6287910d271f3f Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 15 Feb 2019 00:37:57 +0800 Subject: scsi: libsas: Fix rphy phy_identifier for PHYs with end devices attached The sysfs phy_identifier attribute for a sas_end_device comes from the rphy phy_identifier value. Currently this is not being set for rphys with an end device attached, so we see incorrect symlinks from systemd disk/by-path: root@localhost:~# ls -l /dev/disk/by-path/ total 0 lrwxrwxrwx 1 root root 9 Feb 13 12:26 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy0-lun-0 -> ../../sdb lrwxrwxrwx 1 root root 10 Feb 13 12:26 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy0-lun-0-part1 -> ../../sdb1 lrwxrwxrwx 1 root root 10 Feb 13 12:26 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy0-lun-0-part2 -> ../../sdb2 lrwxrwxrwx 1 root root 10 Feb 13 12:26 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy0-lun-0-part3 -> ../../sdc3 Indeed, each sas_end_device phy_identifier value is 0: root@localhost:/# more sys/class/sas_device/end_device-0\:0\:2/phy_identifier 0 root@localhost:/# more sys/class/sas_device/end_device-0\:0\:10/phy_identifier 0 This patch fixes the discovery code to set the phy_identifier. With this, we now get proper symlinks: root@localhost:~# ls -l /dev/disk/by-path/ total 0 lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy10-lun-0 -> ../../sdg lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy11-lun-0 -> ../../sdh lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy2-lun-0 -> ../../sda lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy2-lun-0-part1 -> ../../sda1 lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy3-lun-0 -> ../../sdb lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy3-lun-0-part1 -> ../../sdb1 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy3-lun-0-part2 -> ../../sdb2 lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy4-lun-0 -> ../../sdc lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy4-lun-0-part1 -> ../../sdc1 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy4-lun-0-part2 -> ../../sdc2 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy4-lun-0-part3 -> ../../sdc3 lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy5-lun-0 -> ../../sdd lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy7-lun-0 -> ../../sde lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy7-lun-0-part1 -> ../../sde1 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy7-lun-0-part2 -> ../../sde2 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy7-lun-0-part3 -> ../../sde3 lrwxrwxrwx 1 root root 9 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy8-lun-0 -> ../../sdf lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy8-lun-0-part1 -> ../../sdf1 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy8-lun-0-part2 -> ../../sdf2 lrwxrwxrwx 1 root root 10 Feb 13 11:53 platform-HISI0162:01-sas-exp0x500e004aaaaaaa1f-phy8-lun-0-part3 -> ../../sdf3 Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver") Reported-by: dann frazier Signed-off-by: John Garry Reviewed-by: Jason Yan Tested-by: dann frazier Signed-off-by: Martin K. Petersen --- drivers/scsi/libsas/sas_expander.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 17eb4185f29d..f21c93bbb35c 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -828,6 +828,7 @@ static struct domain_device *sas_ex_discover_end_dev( rphy = sas_end_device_alloc(phy->port); if (!rphy) goto out_free; + rphy->identify.phy_identifier = phy_id; child->rphy = rphy; get_device(&rphy->dev); @@ -854,6 +855,7 @@ static struct domain_device *sas_ex_discover_end_dev( child->rphy = rphy; get_device(&rphy->dev); + rphy->identify.phy_identifier = phy_id; sas_fill_in_rphy(child, rphy); list_add_tail(&child->disco_list_node, &parent->port->disco_list); -- cgit v1.2.3 From 4a067cf823d9d8e50d41cfb618011c0d4a969c72 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Thu, 14 Feb 2019 22:57:41 +0100 Subject: scsi: core: reset host byte in DID_NEXUS_FAILURE case Up to 4.12, __scsi_error_from_host_byte() would reset the host byte to DID_OK for various cases including DID_NEXUS_FAILURE. Commit 2a842acab109 ("block: introduce new block status code type") replaced this function with scsi_result_to_blk_status() and removed the host-byte resetting code for the DID_NEXUS_FAILURE case. As the line set_host_byte(cmd, DID_OK) was preserved for the other cases, I suppose this was an editing mistake. The fact that the host byte remains set after 4.13 is causing problems with the sg_persist tool, which now returns success rather then exit status 24 when a RESERVATION CONFLICT error is encountered. Fixes: 2a842acab109 "block: introduce new block status code type" Signed-off-by: Martin Wilck Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 6d65ac584eba..f8d51c3d5582 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -655,6 +655,7 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result) set_host_byte(cmd, DID_OK); return BLK_STS_TARGET; case DID_NEXUS_FAILURE: + set_host_byte(cmd, DID_OK); return BLK_STS_NEXUS; case DID_ALLOC_FAILURE: set_host_byte(cmd, DID_OK); -- cgit v1.2.3