6.2-stable patches

added patches:
	scsi-qla2xxx-perform-lockless-command-completion-in-abort-path.patch
	scsi-qla2xxx-synchronize-the-iocb-count-to-be-in-order.patch

diff --git a/queue-6.2/scsi-qla2xxx-perform-lockless-command-completion-in-abort-path.patch b/queue-6.2/scsi-qla2xxx-perform-lockless-command-completion-in-abort-path.patch
new file mode 100644 (file)
index 0000000..0349fcb
--- /dev/null
+++ b/queue-6.2/scsi-qla2xxx-perform-lockless-command-completion-in-abort-path.patch
@@ -0,0 +1,78 @@
+From 0367076b0817d5c75dfb83001ce7ce5c64d803a9 Mon Sep 17 00:00:00 2001
+From: Nilesh Javali <njavali@marvell.com>
+Date: Sun, 12 Mar 2023 21:37:10 -0700
+Subject: scsi: qla2xxx: Perform lockless command completion in abort path
+
+From: Nilesh Javali <njavali@marvell.com>
+
+commit 0367076b0817d5c75dfb83001ce7ce5c64d803a9 upstream.
+
+While adding and removing the controller, the following call trace was
+observed:
+
+WARNING: CPU: 3 PID: 623596 at kernel/dma/mapping.c:532 dma_free_attrs+0x33/0x50
+CPU: 3 PID: 623596 Comm: sh Kdump: loaded Not tainted 5.14.0-96.el9.x86_64 #1
+RIP: 0010:dma_free_attrs+0x33/0x50
+
+Call Trace:
+   qla2x00_async_sns_sp_done+0x107/0x1b0 [qla2xxx]
+   qla2x00_abort_srb+0x8e/0x250 [qla2xxx]
+   ? ql_dbg+0x70/0x100 [qla2xxx]
+   __qla2x00_abort_all_cmds+0x108/0x190 [qla2xxx]
+   qla2x00_abort_all_cmds+0x24/0x70 [qla2xxx]
+   qla2x00_abort_isp_cleanup+0x305/0x3e0 [qla2xxx]
+   qla2x00_remove_one+0x364/0x400 [qla2xxx]
+   pci_device_remove+0x36/0xa0
+   __device_release_driver+0x17a/0x230
+   device_release_driver+0x24/0x30
+   pci_stop_bus_device+0x68/0x90
+   pci_stop_and_remove_bus_device_locked+0x16/0x30
+   remove_store+0x75/0x90
+   kernfs_fop_write_iter+0x11c/0x1b0
+   new_sync_write+0x11f/0x1b0
+   vfs_write+0x1eb/0x280
+   ksys_write+0x5f/0xe0
+   do_syscall_64+0x5c/0x80
+   ? do_user_addr_fault+0x1d8/0x680
+   ? do_syscall_64+0x69/0x80
+   ? exc_page_fault+0x62/0x140
+   ? asm_exc_page_fault+0x8/0x30
+   entry_SYSCALL_64_after_hwframe+0x44/0xae
+
+The command was completed in the abort path during driver unload with a
+lock held, causing the warning in abort path. Hence complete the command
+without any lock held.
+
+Reported-by: Lin Li <lilin@redhat.com>
+Tested-by: Lin Li <lilin@redhat.com>
+Cc: stable@vger.kernel.org
+Signed-off-by: Nilesh Javali <njavali@marvell.com>
+Link: https://lore.kernel.org/r/20230313043711.13500-2-njavali@marvell.com
+Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
+Reviewed-by: John Meneghini <jmeneghi@redhat.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/scsi/qla2xxx/qla_os.c |   11 +++++++++++
+ 1 file changed, 11 insertions(+)
+
+--- a/drivers/scsi/qla2xxx/qla_os.c
++++ b/drivers/scsi/qla2xxx/qla_os.c
+@@ -1848,6 +1848,17 @@ __qla2x00_abort_all_cmds(struct qla_qpai
+       for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
+               sp = req->outstanding_cmds[cnt];
+               if (sp) {
++                      /*
++                       * perform lockless completion during driver unload
++                       */
++                      if (qla2x00_chip_is_down(vha)) {
++                              req->outstanding_cmds[cnt] = NULL;
++                              spin_unlock_irqrestore(qp->qp_lock_ptr, flags);
++                              sp->done(sp, res);
++                              spin_lock_irqsave(qp->qp_lock_ptr, flags);
++                              continue;
++                      }
++
+                       switch (sp->cmd_type) {
+                       case TYPE_SRB:
+                               qla2x00_abort_srb(qp, sp, res, &flags);

diff --git a/queue-6.2/scsi-qla2xxx-synchronize-the-iocb-count-to-be-in-order.patch b/queue-6.2/scsi-qla2xxx-synchronize-the-iocb-count-to-be-in-order.patch
new file mode 100644 (file)
index 0000000..32cdb51
--- /dev/null
+++ b/queue-6.2/scsi-qla2xxx-synchronize-the-iocb-count-to-be-in-order.patch
@@ -0,0 +1,94 @@
+From d3affdeb400f3adc925bd996f3839481f5291839 Mon Sep 17 00:00:00 2001
+From: Quinn Tran <qutran@marvell.com>
+Date: Sun, 12 Mar 2023 21:37:11 -0700
+Subject: scsi: qla2xxx: Synchronize the IOCB count to be in order
+
+From: Quinn Tran <qutran@marvell.com>
+
+commit d3affdeb400f3adc925bd996f3839481f5291839 upstream.
+
+A system hang was observed with the following call trace:
+
+BUG: kernel NULL pointer dereference, address: 0000000000000000
+PGD 0 P4D 0
+Oops: 0000 [#1] PREEMPT SMP NOPTI
+CPU: 15 PID: 86747 Comm: nvme Kdump: loaded Not tainted 6.2.0+ #1
+Hardware name: Dell Inc. PowerEdge R6515/04F3CJ, BIOS 2.7.3 03/31/2022
+RIP: 0010:__wake_up_common+0x55/0x190
+Code: 41 f6 01 04 0f 85 b2 00 00 00 48 8b 43 08 4c 8d
+      40 e8 48 8d 43 08 48 89 04 24 48 89 c6\
+      49 8d 40 18 48 39 c6 0f 84 e9 00 00 00 <49> 8b 40 18 89 6c 24 14 31
+      ed 4c 8d 60 e8 41 8b 18 f6 c3 04 75 5d
+RSP: 0018:ffffb05a82afbba0 EFLAGS: 00010082
+RAX: 0000000000000000 RBX: ffff8f9b83a00018 RCX: 0000000000000000
+RDX: 0000000000000001 RSI: ffff8f9b83a00020 RDI: ffff8f9b83a00018
+RBP: 0000000000000001 R08: ffffffffffffffe8 R09: ffffb05a82afbbf8
+R10: 70735f7472617473 R11: 5f30307832616c71 R12: 0000000000000001
+R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000
+FS:  00007f815cf4c740(0000) GS:ffff8f9eeed80000(0000)
+       knlGS:0000000000000000
+CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
+CR2: 0000000000000000 CR3: 000000010633a000 CR4: 0000000000350ee0
+Call Trace:
+    <TASK>
+    __wake_up_common_lock+0x83/0xd0
+    qla_nvme_ls_req+0x21b/0x2b0 [qla2xxx]
+    __nvme_fc_send_ls_req+0x1b5/0x350 [nvme_fc]
+    nvme_fc_xmt_disconnect_assoc+0xca/0x110 [nvme_fc]
+    nvme_fc_delete_association+0x1bf/0x220 [nvme_fc]
+    ? nvme_remove_namespaces+0x9f/0x140 [nvme_core]
+    nvme_do_delete_ctrl+0x5b/0xa0 [nvme_core]
+    nvme_sysfs_delete+0x5f/0x70 [nvme_core]
+    kernfs_fop_write_iter+0x12b/0x1c0
+    vfs_write+0x2a3/0x3b0
+    ksys_write+0x5f/0xe0
+    do_syscall_64+0x5c/0x90
+    ? syscall_exit_work+0x103/0x130
+    ? syscall_exit_to_user_mode+0x12/0x30
+    ? do_syscall_64+0x69/0x90
+    ? exit_to_user_mode_loop+0xd0/0x130
+    ? exit_to_user_mode_prepare+0xec/0x100
+    ? syscall_exit_to_user_mode+0x12/0x30
+    ? do_syscall_64+0x69/0x90
+    ? syscall_exit_to_user_mode+0x12/0x30
+    ? do_syscall_64+0x69/0x90
+    entry_SYSCALL_64_after_hwframe+0x72/0xdc
+    RIP: 0033:0x7f815cd3eb97
+
+The IOCB counts are out of order and that would block any commands from
+going out and subsequently hang the system. Synchronize the IOCB count to
+be in correct order.
+
+Fixes: 5f63a163ed2f ("scsi: qla2xxx: Fix exchange oversubscription for management commands")
+Cc: stable@vger.kernel.org
+Signed-off-by: Quinn Tran <qutran@marvell.com>
+Signed-off-by: Nilesh Javali <njavali@marvell.com>
+Link: https://lore.kernel.org/r/20230313043711.13500-3-njavali@marvell.com
+Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
+Reviewed-by: John Meneghini <jmeneghi@redhat.com>
+Tested-by: Lin Li <lilin@redhat.com>
+Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/scsi/qla2xxx/qla_isr.c |    3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/drivers/scsi/qla2xxx/qla_isr.c
++++ b/drivers/scsi/qla2xxx/qla_isr.c
+@@ -1900,6 +1900,8 @@ qla2x00_get_sp_from_handle(scsi_qla_host
+       }
+ 
+       req->outstanding_cmds[index] = NULL;
++
++      qla_put_fw_resources(sp->qpair, &sp->iores);
+       return sp;
+ }
+ 
+@@ -3112,7 +3114,6 @@ qla25xx_process_bidir_status_iocb(scsi_q
+       }
+       bsg_reply->reply_payload_rcv_len = 0;
+ 
+-      qla_put_fw_resources(sp->qpair, &sp->iores);
+ done:
+       /* Return the vendor specific reply to API */
+       bsg_reply->reply_data.vendor_reply.vendor_rsp[0] = rval;

diff --git a/queue-6.2/series b/queue-6.2/series
index ace7afa9d61b9a5021de66db59f24bf54fa5dc84..e5589785b379d48ff89bcdd3d5fcdf4492a08a0c 100644 (file)
--- a/queue-6.2/series
+++ b/queue-6.2/series
@@ -110,3 +110,5 @@ perf-x86-amd-core-always-clear-status-for-idx.patch
 entry-rcu-check-tif_resched-_after_-delayed-rcu-wake.patch
 hwmon-fix-potential-sensor-registration-fail-if-of_n.patch
 hwmon-it87-fix-voltage-scaling-for-chips-with-10.9mv.patch
+scsi-qla2xxx-synchronize-the-iocb-count-to-be-in-order.patch
+scsi-qla2xxx-perform-lockless-command-completion-in-abort-path.patch