From: Justin Tee <[email protected]>
[ Upstream commit bb011631435c705cdeddca68d5c85fd40a4320f9 ]
Typically when an out of resource CQE status is detected, the
lpfc_ramp_down_queue_handler() logic is called to help reduce I/O load by
reducing an sdev's queue_depth.
However, the current lpfc_rampdown_queue_depth() logic does not help reduce
queue_depth. num_cmd_success is never updated and is always zero, which
means new_queue_depth will always be set to sdev->queue_depth. So,
new_queue_depth = sdev->queue_depth - new_queue_depth always sets
new_queue_depth to zero. And, scsi_change_queue_depth(sdev, 0) is
essentially a no-op.
Change the lpfc_ramp_down_queue_handler() logic to set new_queue_depth
equal to sdev->queue_depth subtracted from number of times num_rsrc_err was
incremented. If num_rsrc_err is >= sdev->queue_depth, then set
new_queue_depth equal to 1. Eventually, the frequency of Good_Status
frames will signal SCSI upper layer to auto increase the queue_depth back
to the driver default of 64 via scsi_handle_queue_ramp_up().
Signed-off-by: Justin Tee <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Martin K. Petersen <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/scsi/lpfc/lpfc.h | 1 -
drivers/scsi/lpfc/lpfc_scsi.c | 13 ++++---------
2 files changed, 4 insertions(+), 10 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 53b661793268f..5698928d8029c 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -989,7 +989,6 @@ struct lpfc_hba {
unsigned long bit_flags;
#define FABRIC_COMANDS_BLOCKED 0
atomic_t num_rsrc_err;
- atomic_t num_cmd_success;
unsigned long last_rsrc_error_time;
unsigned long last_ramp_down_time;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 425b83618a2e5..02d067e1fc45c 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -303,11 +303,10 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
struct Scsi_Host *shost;
struct scsi_device *sdev;
unsigned long new_queue_depth;
- unsigned long num_rsrc_err, num_cmd_success;
+ unsigned long num_rsrc_err;
int i;
num_rsrc_err = atomic_read(&phba->num_rsrc_err);
- num_cmd_success = atomic_read(&phba->num_cmd_success);
/*
* The error and success command counters are global per
@@ -322,20 +321,16 @@ lpfc_ramp_down_queue_handler(struct lpfc_hba *phba)
for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
shost = lpfc_shost_from_vport(vports[i]);
shost_for_each_device(sdev, shost) {
- new_queue_depth =
- sdev->queue_depth * num_rsrc_err /
- (num_rsrc_err + num_cmd_success);
- if (!new_queue_depth)
- new_queue_depth = sdev->queue_depth - 1;
+ if (num_rsrc_err >= sdev->queue_depth)
+ new_queue_depth = 1;
else
new_queue_depth = sdev->queue_depth -
- new_queue_depth;
+ num_rsrc_err;
scsi_change_queue_depth(sdev, new_queue_depth);
}
}
lpfc_destroy_vport_work_array(phba, vports);
atomic_set(&phba->num_rsrc_err, 0);
- atomic_set(&phba->num_cmd_success, 0);
}
/**
--
2.43.0
From: Saurav Kashyap <[email protected]>
[ Upstream commit c214ed2a4dda35b308b0b28eed804d7ae66401f9 ]
The session resources are used by FW and driver when session is offloaded,
once session is uploaded these resources are not used. The lock is not
required as these fields won't be used any longer. The offload and upload
calls are sequential, hence lock is not required.
This will suppress following BUG_ON():
[ 449.843143] ------------[ cut here ]------------
[ 449.848302] kernel BUG at mm/vmalloc.c:2727!
[ 449.853072] invalid opcode: 0000 [#1] PREEMPT SMP PTI
[ 449.858712] CPU: 5 PID: 1996 Comm: kworker/u24:2 Not tainted 5.14.0-118.el9.x86_64 #1
Rebooting.
[ 449.867454] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.3.4 11/08/2016
[ 449.876966] Workqueue: fc_rport_eq fc_rport_work [libfc]
[ 449.882910] RIP: 0010:vunmap+0x2e/0x30
[ 449.887098] Code: 00 65 8b 05 14 a2 f0 4a a9 00 ff ff 00 75 1b 55 48 89 fd e8 34 36 79 00 48 85 ed 74 0b 48 89 ef 31 f6 5d e9 14 fc ff ff 5d c3 <0f> 0b 0f 1f 44 00 00 41 57 41 56 49 89 ce 41 55 49 89 fd 41 54 41
[ 449.908054] RSP: 0018:ffffb83d878b3d68 EFLAGS: 00010206
[ 449.913887] RAX: 0000000080000201 RBX: ffff8f4355133550 RCX: 000000000d400005
[ 449.921843] RDX: 0000000000000001 RSI: 0000000000001000 RDI: ffffb83da53f5000
[ 449.929808] RBP: ffff8f4ac6675800 R08: ffffb83d878b3d30 R09: 00000000000efbdf
[ 449.937774] R10: 0000000000000003 R11: ffff8f434573e000 R12: 0000000000001000
[ 449.945736] R13: 0000000000001000 R14: ffffb83da53f5000 R15: ffff8f43d4ea3ae0
[ 449.953701] FS: 0000000000000000(0000) GS:ffff8f529fc80000(0000) knlGS:0000000000000000
[ 449.962732] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 449.969138] CR2: 00007f8cf993e150 CR3: 0000000efbe10003 CR4: 00000000003706e0
[ 449.977102] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 449.985065] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 449.993028] Call Trace:
[ 449.995756] __iommu_dma_free+0x96/0x100
[ 450.000139] bnx2fc_free_session_resc+0x67/0x240 [bnx2fc]
[ 450.006171] bnx2fc_upload_session+0xce/0x100 [bnx2fc]
[ 450.011910] bnx2fc_rport_event_handler+0x9f/0x240 [bnx2fc]
[ 450.018136] fc_rport_work+0x103/0x5b0 [libfc]
[ 450.023103] process_one_work+0x1e8/0x3c0
[ 450.027581] worker_thread+0x50/0x3b0
[ 450.031669] ? rescuer_thread+0x370/0x370
[ 450.036143] kthread+0x149/0x170
[ 450.039744] ? set_kthread_struct+0x40/0x40
[ 450.044411] ret_from_fork+0x22/0x30
[ 450.048404] Modules linked in: vfat msdos fat xfs nfs_layout_nfsv41_files rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver dm_service_time qedf qed crc8 bnx2fc libfcoe libfc scsi_transport_fc intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp dcdbas rapl intel_cstate intel_uncore mei_me pcspkr mei ipmi_ssif lpc_ich ipmi_si fuse zram ext4 mbcache jbd2 loop nfsv3 nfs_acl nfs lockd grace fscache netfs irdma ice sd_mod t10_pi sg ib_uverbs ib_core 8021q garp mrp stp llc mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt mxm_wmi fb_sys_fops cec crct10dif_pclmul ahci crc32_pclmul bnx2x drm ghash_clmulni_intel libahci rfkill i40e libata megaraid_sas mdio wmi sunrpc lrw dm_crypt dm_round_robin dm_multipath dm_snapshot dm_bufio dm_mirror dm_region_hash dm_log dm_zero dm_mod linear raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid6_pq libcrc32c crc32c_intel raid1 raid0 iscsi_ibft squashfs be2iscsi bnx2i cnic uio cxgb4i cxgb4 tls
[ 450.048497] libcxgbi libcxgb qla4xxx iscsi_boot_sysfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi edd ipmi_devintf ipmi_msghandler
[ 450.159753] ---[ end trace 712de2c57c64abc8 ]---
Reported-by: Guangwu Zhang <[email protected]>
Signed-off-by: Saurav Kashyap <[email protected]>
Signed-off-by: Nilesh Javali <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Martin K. Petersen <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/scsi/bnx2fc/bnx2fc_tgt.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/scsi/bnx2fc/bnx2fc_tgt.c b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
index e3d1c7c440c8c..c7d6842b293da 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_tgt.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_tgt.c
@@ -834,7 +834,6 @@ static void bnx2fc_free_session_resc(struct bnx2fc_hba *hba,
BNX2FC_TGT_DBG(tgt, "Freeing up session resources\n");
- spin_lock_bh(&tgt->cq_lock);
ctx_base_ptr = tgt->ctx_base;
tgt->ctx_base = NULL;
@@ -890,7 +889,6 @@ static void bnx2fc_free_session_resc(struct bnx2fc_hba *hba,
tgt->sq, tgt->sq_dma);
tgt->sq = NULL;
}
- spin_unlock_bh(&tgt->cq_lock);
if (ctx_base_ptr)
iounmap(ctx_base_ptr);
--
2.43.0