[PATCH openEuler-1.0-LTS 1/2] scsi: hisi_sas: Fix normally completed I/O analysed as failed
From: Xingui Yang yangxingui@huawei.com
driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7GS2V CVE: NA
-------------------------------------------------------------------
pio read command has no response frame and the struct iu[1024] won't be filled, and it's found that I/Os that are normally completed will be analysed as failed in sas_ata_task_done() when iu contain abnormal dirty data. So ending_fis should not be filled by iu when the response frame hasn't been written to the memory.
Fixes: d380f55503ed ("scsi: hisi_sas: Don't bother clearing status buffer IU in task prep") Signed-off-by: Xingui Yang yangxingui@huawei.com Reviewed-by: Xiang Chen chenxiang66@hisilicon.com Reviewed-by: kang fenglong kangfenglong@huawei.com Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com --- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 23 ++++++++++++++++------- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 23 +++++++++++++++-------- 2 files changed, 31 insertions(+), 15 deletions(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 2df70c4873f5..f9867176fa14 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2033,6 +2033,11 @@ static void slot_err_v2_hw(struct hisi_hba *hisi_hba, u16 dma_tx_err_type = cpu_to_le16(err_record->dma_tx_err_type); u16 sipc_rx_err_type = cpu_to_le16(err_record->sipc_rx_err_type); u32 dma_rx_err_type = cpu_to_le32(err_record->dma_rx_err_type); + struct hisi_sas_complete_v2_hdr *complete_queue = + hisi_hba->complete_hdr[slot->cmplt_queue]; + struct hisi_sas_complete_v2_hdr *complete_hdr = + &complete_queue[slot->cmplt_queue_slot]; + u32 dw0 = le32_to_cpu(complete_hdr->dw0); int error = -1;
if (err_phase == 1) { @@ -2318,7 +2323,8 @@ static void slot_err_v2_hw(struct hisi_hba *hisi_hba, break; } } - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); } break; default: @@ -2342,6 +2348,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) &complete_queue[slot->cmplt_queue_slot]; unsigned long flags; bool is_internal = slot->is_internal; + u32 dw0;
if (unlikely(!task || !task->lldd_task || !task->dev)) return -EINVAL; @@ -2366,7 +2373,8 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) }
/* Use SAS+TMF status codes */ - switch ((complete_hdr->dw0 & CMPLT_HDR_ABORT_STAT_MSK) + dw0 = le32_to_cpu(complete_hdr->dw0); + switch ((dw0 & CMPLT_HDR_ABORT_STAT_MSK) >> CMPLT_HDR_ABORT_STAT_OFF) { case STAT_IO_ABORTED: /* this io has been aborted by abort command */ @@ -2392,9 +2400,9 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) break; }
- if ((complete_hdr->dw0 & CMPLT_HDR_ERX_MSK) && - (!(complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK))) { - u32 err_phase = (complete_hdr->dw0 & CMPLT_HDR_ERR_PHASE_MSK) + if ((dw0 & CMPLT_HDR_ERX_MSK) && + (!(dw0 & CMPLT_HDR_RSPNS_XFRD_MSK))) { + u32 err_phase = (dw0 & CMPLT_HDR_ERR_PHASE_MSK) >> CMPLT_HDR_ERR_PHASE_OFF; u32 *error_info = hisi_sas_status_buf_addr_mem(slot);
@@ -2409,7 +2417,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) "CQ hdr: 0x%x 0x%x 0x%x 0x%x " "Error info: 0x%x 0x%x 0x%x 0x%x\n", slot->idx, task, sas_dev->device_id, - complete_hdr->dw0, complete_hdr->dw1, + dw0, complete_hdr->dw1, complete_hdr->act, complete_hdr->dw3, error_info[0], error_info[1], error_info[2], error_info[3]); @@ -2456,7 +2464,8 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: { ts->stat = SAM_STAT_GOOD; - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); break; } default: diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 5e2488fd2466..f79060fca001 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2353,7 +2353,8 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, ts->stat = SAS_OPEN_REJECT; ts->open_rej_reason = SAS_OREJ_RSVD_RETRY; } - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); break; case SAS_PROTOCOL_SMP: ts->stat = SAM_STAT_CHECK_CONDITION; @@ -2402,6 +2403,7 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) &complete_queue[slot->cmplt_queue_slot]; unsigned long flags; bool is_internal = slot->is_internal; + u32 dw0, dw1, dw3;
if (unlikely(!task || !task->lldd_task || !task->dev)) return -EINVAL; @@ -2425,10 +2427,14 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) goto out; }
+ dw0 = le32_to_cpu(complete_hdr->dw0); + dw1 = le32_to_cpu(complete_hdr->dw1); + dw3 = le32_to_cpu(complete_hdr->dw3); + /* * Use SAS+TMF status codes */ - switch ((complete_hdr->dw0 & CMPLT_HDR_ABORT_STAT_MSK) + switch ((dw0 & CMPLT_HDR_ABORT_STAT_MSK) >> CMPLT_HDR_ABORT_STAT_OFF) { case STAT_IO_ABORTED: /* this IO has been aborted by abort command */ @@ -2452,9 +2458,9 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) }
/* check for erroneous completion, 0x3 means abnormal */ - if ((complete_hdr->dw0 & CMPLT_HDR_CMPLT_MSK) == 0x3) { + if ((dw0 & CMPLT_HDR_CMPLT_MSK) == 0x3) { u32 *error_info = hisi_sas_status_buf_addr_mem(slot); - u32 device_id = (complete_hdr->dw1 & 0xffff0000) >> 16; + u32 device_id = (dw1 & 0xffff0000) >> 16; struct hisi_sas_itct *itct = &hisi_hba->itct[device_id];
set_aborted_iptt(hisi_hba, slot); @@ -2464,12 +2470,12 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) "Error info: 0x%x 0x%x 0x%x 0x%x\n", slot->idx, task, sas_dev->device_id, itct->sas_addr, - complete_hdr->dw0, complete_hdr->dw1, - complete_hdr->act, complete_hdr->dw3, + dw0, dw1, + complete_hdr->act, dw3, error_info[0], error_info[1], error_info[2], error_info[3]);
- if ((complete_hdr->dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && + if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && (task->task_proto & SAS_PROTOCOL_SATA || task->task_proto & SAS_PROTOCOL_STP)) { struct hisi_sas_status_buffer *status_buf = @@ -2559,7 +2565,8 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) case SAS_PROTOCOL_STP: case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: ts->stat = SAM_STAT_GOOD; - hisi_sas_sata_done(task, slot); + if (dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) + hisi_sas_sata_done(task, slot); break; default: ts->stat = SAM_STAT_CHECK_CONDITION;
From: Xingui Yang yangxingui@huawei.com
driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I7GRU1 CVE: NA
---------------------------------------------------------------------
If init debugfs failed and call debugfs_remove_recursive() when device register. We found it will trigger NULL point exception after calling debugfs_remove_recursive() again when device remove.
[ 1665.467244] hisi_sas_v3_hw 0000:b4:02.0: failed to init debugfs!
[ 1669.836708] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0 [ 1669.872669] pc : down_write+0x24/0x70 [ 1669.876315] lr : down_write+0x1c/0x70 [ 1669.879961] sp : ffff000036f53a30 [ 1669.883260] x29: ffff000036f53a30 x28: ffffa027c31549f8 [ 1669.888547] x27: ffffa027c3140000 x26: 0000000000000000 [ 1669.893834] x25: ffffa027bf37c270 x24: ffffa027bf37c270 [ 1669.899122] x23: ffff0000095406b8 x22: ffff0000095406a8 [ 1669.904408] x21: 0000000000000000 x20: ffffa027bf37c310 [ 1669.909695] x19: 00000000000000a0 x18: ffff8027dcd86f10 [ 1669.914982] x17: 0000000000000000 x16: 0000000000000000 [ 1669.920268] x15: 0000000000000000 x14: ffffa0274014f870 [ 1669.925555] x13: 0000000000000040 x12: 0000000000000228 [ 1669.930842] x11: 0000000000000020 x10: 0000000000000bb0 [ 1669.936129] x9 : ffff000036f537f0 x8 : ffff80273088ca10 [ 1669.941416] x7 : 000000000000001d x6 : 00000000ffffffff [ 1669.946702] x5 : ffff000008a36310 x4 : ffff80273088be00 [ 1669.951989] x3 : ffff000009513e90 x2 : 0000000000000000 [ 1669.957276] x1 : 00000000000000a0 x0 : ffffffff00000001 [ 1669.962563] Call trace: [ 1669.965000] down_write+0x24/0x70 [ 1669.968301] debugfs_remove_recursive+0x5c/0x1b0 [ 1669.972905] hisi_sas_debugfs_exit+0x24/0x30 [hisi_sas_main] [ 1669.978541] hisi_sas_v3_remove+0x130/0x150 [hisi_sas_v3_hw] [ 1669.984175] pci_device_remove+0x48/0xd8 [ 1669.988082] device_release_driver_internal+0x1b4/0x250 [ 1669.993282] device_release_driver+0x28/0x38 [ 1669.997534] pci_stop_bus_device+0x84/0xb8 [ 1670.001611] pci_stop_and_remove_bus_device_locked+0x24/0x40 [ 1670.007244] remove_store+0xfc/0x140 [ 1670.010802] dev_attr_store+0x44/0x60 [ 1670.014448] sysfs_kf_write+0x58/0x80 [ 1670.018095] kernfs_fop_write+0xe8/0x1f0 [ 1670.022000] __vfs_write+0x60/0x190 [ 1670.025472] vfs_write+0xac/0x1c0 [ 1670.028771] ksys_write+0x6c/0xd8 [ 1670.032071] __arm64_sys_write+0x24/0x30 [ 1670.035977] el0_svc_common+0x78/0x130 [ 1670.039710] el0_svc_handler+0x38/0x78 [ 1670.043442] el0_svc+0x8/0xc
To fix this by set debugfs_dir to NULL after call debugfs_remove_recursive().
Signed-off-by: Xingui Yang yangxingui@huawei.com Reviewed-by: kang fenglong kangfenglong@huawei.com Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com --- drivers/scsi/hisi_sas/hisi_sas_main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index b00bf3b0f418..6bccd36556f2 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -3559,7 +3559,7 @@ static void hisi_sas_debugfs_create_files(struct hisi_hba *hisi_hba)
return; fail: - debugfs_remove_recursive(hisi_hba->debugfs_dir); + hisi_sas_debugfs_exit(hisi_hba); }
static void hisi_sas_debugfs_snapshot_regs(struct hisi_hba *hisi_hba) @@ -3741,14 +3741,15 @@ void hisi_sas_debugfs_init(struct hisi_hba *hisi_hba) devm_kfree(dev, hisi_hba->debugfs_port_reg[i]); devm_kfree(dev, hisi_hba->debugfs_global_reg); fail_global: - debugfs_remove_recursive(hisi_hba->debugfs_dir); - dev_dbg(dev, "failed to init debugfs!\n"); + hisi_sas_debugfs_exit(hisi_hba); + dev_info(dev, "failed to init debugfs!\n"); } EXPORT_SYMBOL_GPL(hisi_sas_debugfs_init);
void hisi_sas_debugfs_exit(struct hisi_hba *hisi_hba) { debugfs_remove_recursive(hisi_hba->debugfs_dir); + hisi_hba->debugfs_dir = NULL; } EXPORT_SYMBOL_GPL(hisi_sas_debugfs_exit);
-
Yongqiang Liu