From 6c92f7dbf25c36f35320e4ae0b508676410bac04 Mon Sep 17 00:00:00 2001 From: Dave Carroll Date: Fri, 15 Sep 2017 11:04:28 -0600 Subject: scsi: aacraid: Fix 2T+ drives on SmartIOC-2000 The logic for supporting large drives was previously tied to 4Kn support for SmartIOC-2000. As SmartIOC-2000 does not support volumes using 4Kn drives, use the intended option flag AAC_OPT_NEW_COMM_64 to determine support for volumes greater than 2T. Cc: Signed-off-by: Dave Carroll Reviewed-by: Christoph Hellwig Reviewed-by: Raghava Aditya Renukunta Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/aachba.c | 12 ++++++------ drivers/scsi/aacraid/aacraid.h | 5 +++++ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index a64285ab0728..af3e4d3f9735 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -699,13 +699,13 @@ static void _aac_probe_container1(void * context, struct fib * fibptr) int status; dresp = (struct aac_mount *) fib_data(fibptr); - if (!(fibptr->dev->supplement_adapter_info.supported_options2 & - AAC_OPTION_VARIABLE_BLOCK_SIZE)) + if (!aac_supports_2T(fibptr->dev)) { dresp->mnt[0].capacityhigh = 0; - if ((le32_to_cpu(dresp->status) != ST_OK) || - (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { - _aac_probe_container2(context, fibptr); - return; + if ((le32_to_cpu(dresp->status) == ST_OK) && + (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) { + _aac_probe_container2(context, fibptr); + return; + } } scsicmd = (struct scsi_cmnd *) context; diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 92fabf2b0c24..403a639574e5 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2701,6 +2701,11 @@ static inline int aac_is_src(struct aac_dev *dev) return 0; } +static inline int aac_supports_2T(struct aac_dev *dev) +{ + return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64); +} + char * get_container_type(unsigned type); extern int numacb; extern char aac_driver_version[]; -- cgit v1.2.1 From 5c756065e47dc3e84b00577bd109f0a8e69903d7 Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Wed, 6 Sep 2017 11:02:56 +0200 Subject: scsi: lpfc: Don't return internal MBXERR_ERROR code from probe function Internal error codes happen to be positive, thus the PCI driver core won't treat them as failure, but we do. This would cause a crash later on as lpfc_pci_remove_one() is called (e.g. as shutdown function). Fixes: 6d368e532168 ("[SCSI] lpfc 8.3.24: Add resource extent support") Signed-off-by: Stefano Brivio Reviewed-by: Johannes Thumshirn Acked-by: Dick Kennedy Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_init.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/scsi') diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 7e7ae786121b..100bc4c8798d 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -6131,6 +6131,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba) "Extents and RPI headers enabled.\n"); } mempool_free(mboxq, phba->mbox_mem_pool); + rc = -EIO; goto out_free_bsmbx; } -- cgit v1.2.1 From 4cb433e856bce5974ea035181cc8eb406496dccc Mon Sep 17 00:00:00 2001 From: Nikola Pajkovsky Date: Wed, 13 Sep 2017 10:46:17 +0200 Subject: scsi: aacraid: error: testing array offset 'bus' after use Fix possible indexing array of bound for &aac->hba_map[bus][cid], where bus and cid boundary check happens later. Fixes: 0d643ff3c353 ("scsi: aacraid: use aac_tmf_callback for reset fib") Signed-off-by: Nikola Pajkovsky Reviewed-by: Dave Carroll Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/linit.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 87cc4a93e637..62beb2596466 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -906,12 +906,14 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", @@ -962,12 +964,14 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) bus = aac_logical_to_phys(scmd_channel(cmd)); cid = scmd_id(cmd); - info = &aac->hba_map[bus][cid]; - if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || - info->devtype != AAC_DEVTYPE_NATIVE_RAW) + + if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS) return FAILED; - if (info->reset_state > 0) + info = &aac->hba_map[bus][cid]; + + if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && + info->reset_state > 0) return FAILED; pr_err("%s: Host adapter reset request. SCSI hang ?\n", -- cgit v1.2.1 From c88f0e6b06f4092995688211a631bb436125d77b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 27 Aug 2017 20:25:26 +0800 Subject: scsi: scsi_transport_iscsi: fix the issue that iscsi_if_rx doesn't parse nlmsg properly ChunYu found a kernel crash by syzkaller: [ 651.617875] kasan: CONFIG_KASAN_INLINE enabled [ 651.618217] kasan: GPF could be caused by NULL-ptr deref or user memory access [ 651.618731] general protection fault: 0000 [#1] SMP KASAN [ 651.621543] CPU: 1 PID: 9539 Comm: scsi Not tainted 4.11.0.cov #32 [ 651.621938] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 651.622309] task: ffff880117780000 task.stack: ffff8800a3188000 [ 651.622762] RIP: 0010:skb_release_data+0x26c/0x590 [...] [ 651.627260] Call Trace: [ 651.629156] skb_release_all+0x4f/0x60 [ 651.629450] consume_skb+0x1a5/0x600 [ 651.630705] netlink_unicast+0x505/0x720 [ 651.632345] netlink_sendmsg+0xab2/0xe70 [ 651.633704] sock_sendmsg+0xcf/0x110 [ 651.633942] ___sys_sendmsg+0x833/0x980 [ 651.637117] __sys_sendmsg+0xf3/0x240 [ 651.638820] SyS_sendmsg+0x32/0x50 [ 651.639048] entry_SYSCALL_64_fastpath+0x1f/0xc2 It's caused by skb_shared_info at the end of sk_buff was overwritten by ISCSI_KEVENT_IF_ERROR when parsing nlmsg info from skb in iscsi_if_rx. During the loop if skb->len == nlh->nlmsg_len and both are sizeof(*nlh), ev = nlmsg_data(nlh) will acutally get skb_shinfo(SKB) instead and set a new value to skb_shinfo(SKB)->nr_frags by ev->type. This patch is to fix it by checking nlh->nlmsg_len properly there to avoid over accessing sk_buff. Reported-by: ChunYu Wang Signed-off-by: Xin Long Acked-by: Chris Leech Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_iscsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 8934f19bce8e..0190aeff5f7f 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -3689,7 +3689,7 @@ iscsi_if_rx(struct sk_buff *skb) uint32_t group; nlh = nlmsg_hdr(skb); - if (nlh->nlmsg_len < sizeof(*nlh) || + if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) || skb->len < nlh->nlmsg_len) { break; } -- cgit v1.2.1 From 675195d0be27391d48d8d23c7c62991505168528 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 20 Sep 2017 08:58:53 +0200 Subject: scsi: scsi_transport_fc: set scsi_target_id upon rescan When an rport is found in the bindings array there is no guarantee that it had been a target port, so we need to call fc_remote_port_rolechg() here to ensure the scsi_target_id is set correctly. Otherwise the port will never be scanned. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Tested-by: Chad Dupuis Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_fc.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index ba9d70f8a6a1..e74fffc32c75 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2876,7 +2876,6 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, memcpy(&rport->port_name, &ids->port_name, sizeof(rport->port_name)); rport->port_id = ids->port_id; - rport->roles = ids->roles; rport->port_state = FC_PORTSTATE_ONLINE; rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT; @@ -2885,15 +2884,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, fci->f->dd_fcrport_size); spin_unlock_irqrestore(shost->host_lock, flags); - if (ids->roles & FC_PORT_ROLE_FCP_TARGET) { - scsi_target_unblock(&rport->dev, SDEV_RUNNING); - - /* initiate a scan of the target */ - spin_lock_irqsave(shost->host_lock, flags); - rport->flags |= FC_RPORT_SCAN_PENDING; - scsi_queue_work(shost, &rport->scan_work); - spin_unlock_irqrestore(shost->host_lock, flags); - } + fc_remote_port_rolechg(rport, ids->roles); return rport; } } -- cgit v1.2.1 From f091fb8c344ce13cbf058d304c6cbb042be97058 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 25 Sep 2017 13:47:23 +0200 Subject: scsi: scsi_transport_fc: Also check for NOTPRESENT in fc_remote_port_add() During failover there is a small race window between fc_remote_port_add() and fc_timeout_deleted_rport(); the latter drops the lock after setting the port to NOTPRESENT, so if fc_remote_port_add() is called right at that time it will fail to detect the existing rport and happily adding a new structure, causing rports to get registered twice. Signed-off-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_transport_fc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index e74fffc32c75..cbd4495d0ff9 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -2739,7 +2739,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel, list_for_each_entry(rport, &fc_host->rports, peers) { - if ((rport->port_state == FC_PORTSTATE_BLOCKED) && + if ((rport->port_state == FC_PORTSTATE_BLOCKED || + rport->port_state == FC_PORTSTATE_NOTPRESENT) && (rport->channel == channel)) { switch (fc_host->tgtid_bind_type) { -- cgit v1.2.1 From d1b490939d8c117a06dfc562c41d933f71d30289 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Tue, 19 Sep 2017 12:11:55 -0300 Subject: scsi: aacraid: Add a small delay after IOP reset Commit 0e9973ed3382 ("scsi: aacraid: Add periodic checks to see IOP reset status") changed the way driver checks if a reset succeeded. Now, after an IOP reset, aacraid immediately start polling a register to verify the reset is complete. This behavior cause regressions on the reset path in PowerPC (at least). Since the delay after the IOP reset was removed by the aforementioned patch, the fact driver just starts to read a register instantly after the reset was issued (by writing in another register) "corrupts" the reset procedure, which ends up failing all the time. The issue highly impacted kdump on PowerPC, since on kdump path we proactively issue a reset in adapter (through the reset_devices kernel parameter). This patch (re-)adds a delay right after IOP reset is issued. Empirically we measured that 3 seconds is enough, but for safety reasons we delay for 5s (and since it was 30s before, 5s is still a small amount). For reference, without this patch we observe the following messages on kdump kernel boot process: [ 76.294] aacraid 0003:01:00.0: IOP reset failed [ 76.294] aacraid 0003:01:00.0: ARC Reset attempt failed [ 86.524] aacraid 0003:01:00.0: adapter kernel panic'd ff. [ 86.524] aacraid 0003:01:00.0: Controller reset type is 3 [ 86.524] aacraid 0003:01:00.0: Issuing IOP reset [146.534] aacraid 0003:01:00.0: IOP reset failed [146.534] aacraid 0003:01:00.0: ARC Reset attempt failed Fixes: 0e9973ed3382 ("scsi: aacraid: Add periodic checks to see IOP reset status") Cc: stable@vger.kernel.org # v4.13+ Signed-off-by: Guilherme G. Piccoli Acked-by: Dave Carroll Signed-off-by: Martin K. Petersen --- drivers/scsi/aacraid/src.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/scsi') diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 48c2b2b34b72..0c9361c87ec8 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -740,6 +740,8 @@ static void aac_send_iop_reset(struct aac_dev *dev) aac_set_intx_mode(dev); src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK); + + msleep(5000); } static void aac_send_hardware_soft_reset(struct aac_dev *dev) -- cgit v1.2.1 From d0b7a9095c0730b92a0a2eecaba2e6b77ed87339 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Wed, 27 Sep 2017 14:44:19 +0200 Subject: scsi: ILLEGAL REQUEST + ASC==27 => target failure ASC 0x27 is "WRITE PROTECTED". This error code is returned e.g. by Fujitsu ETERNUS systems under certain conditions for WRITE SAME 16 commands with UNMAP bit set. It should not be treated as a path error. In general, it makes sense to assume that being write protected is a target rather than a path property. Signed-off-by: Martin Wilck Acked-by: Lee Duncan Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_error.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/scsi') diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 38942050b265..dab876c65473 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -580,7 +580,8 @@ int scsi_check_sense(struct scsi_cmnd *scmd) if (sshdr.asc == 0x20 || /* Invalid command operation code */ sshdr.asc == 0x21 || /* Logical block address out of range */ sshdr.asc == 0x24 || /* Invalid field in cdb */ - sshdr.asc == 0x26) { /* Parameter value invalid */ + sshdr.asc == 0x26 || /* Parameter value invalid */ + sshdr.asc == 0x27) { /* Write protected */ set_host_byte(scmd, DID_TARGET_FAILURE); } return SUCCESS; -- cgit v1.2.1