> -----Original Message-----
> From: Ming Lei [mailto:[email protected]]
> Sent: Tuesday, February 27, 2018 4:08 AM
> To: Jens Axboe <[email protected]>; [email protected]; Christoph
> Hellwig <[email protected]>; Mike Snitzer <[email protected]>
> Cc: [email protected]; Hannes Reinecke <[email protected]>; Arun Easi
> <[email protected]>; Omar Sandoval <[email protected]>; Martin K .
> Petersen <[email protected]>; James Bottomley
> <[email protected]>; Christoph Hellwig <[email protected]>;
> Don Brace <[email protected]>; Kashyap Desai
> <[email protected]>; Peter Rivera <[email protected]>;
> Laurence Oberman <[email protected]>; Ming Lei
> <[email protected]>; Meelis Roos <[email protected]>
> Subject: [PATCH V3 1/8] scsi: hpsa: fix selection of reply queue
>
> EXTERNAL EMAIL
>
>
> From 84676c1f21 (genirq/affinity: assign vectors to all possible CPUs),
> one msix vector can be created without any online CPU mapped, then one
> command's completion may not be notified.
>
> This patch setups mapping between cpu and reply queue according to irq
> affinity info retrived by pci_irq_get_affinity(), and uses this mapping
> table to choose reply queue for queuing one command.
>
> Then the chosen reply queue has to be active, and fixes IO hang caused
> by using inactive reply queue which doesn't have any online CPU mapped.
>
> Cc: Hannes Reinecke <[email protected]>
> Cc: Arun Easi <[email protected]>
> Cc: "Martin K. Petersen" <[email protected]>,
> Cc: James Bottomley <[email protected]>,
> Cc: Christoph Hellwig <[email protected]>,
> Cc: Don Brace <[email protected]>
> Cc: Kashyap Desai <[email protected]>
> Cc: Peter Rivera <[email protected]>
> Cc: Laurence Oberman <[email protected]>
> Cc: Meelis Roos <[email protected]>
> Fixes: 84676c1f21e8 ("genirq/affinity: assign vectors to all possible CPUs")
> Signed-off-by: Ming Lei <[email protected]>
I am getting some issues that need to be tracked down:
[ 1636.032984] hpsa 0000:87:00.0: Acknowledging event: 0xc0000032 (HP SSD Smart
Path configuration change)
[ 1638.510656] hpsa 0000:87:00.0: scsi 3:0:8:0: updated Direct-Access HP
MO0400JDVEU PHYS DRV SSDSmartPathCap- En- Exp=0
[ 1653.967695] hpsa 0000:87:00.0: Acknowledging event: 0x80000020 (HP SSD Smart
Path configuration change)
[ 1656.770377] hpsa 0000:87:00.0: scsi 3:0:8:0: updated Direct-Access HP
MO0400JDVEU PHYS DRV SSDSmartPathCap- En- Exp=0
[ 2839.762267] hpsa 0000:87:00.0: Acknowledging event: 0x80000020 (HP SSD Smart
Path configuration change)
[ 2840.841290] hpsa 0000:87:00.0: scsi 3:0:8:0: updated Direct-Access HP
MO0400JDVEU PHYS DRV SSDSmartPathCap- En- Exp=0
[ 2917.582653] hpsa 0000:87:00.0: Acknowledging event: 0xc0000020 (HP SSD Smart
Path configuration change)
[ 2919.087191] hpsa 0000:87:00.0: scsi 3:1:0:1: updated Direct-Access HP
LOGICAL VOLUME RAID-5 SSDSmartPathCap+ En+ Exp=1
[ 2919.142527] hpsa 0000:87:00.0: hpsa_figure_phys_disk_ptrs: [3:1:0:2] A phys
disk component of LV is missing, turning off offload_enabled for LV.
[ 2919.203915] hpsa 0000:87:00.0: hpsa_figure_phys_disk_ptrs: [3:1:0:2] A phys
disk component of LV is missing, turning off offload_enabled for LV.
[ 2919.266921] hpsa 0000:87:00.0: hpsa_figure_phys_disk_ptrs: [3:1:0:2] A phys
disk component of LV is missing, turning off offload_enabled for LV.
[ 2934.999629] hpsa 0000:87:00.0: Acknowledging event: 0x40000000 (HP SSD Smart
Path state change)
[ 2936.937333] hpsa 0000:87:00.0: hpsa_figure_phys_disk_ptrs: [3:1:0:2] A phys
disk component of LV is missing, turning off offload_enabled for LV.
[ 2936.998707] hpsa 0000:87:00.0: hpsa_figure_phys_disk_ptrs: [3:1:0:2] A phys
disk component of LV is missing, turning off offload_enabled for LV.
[ 2937.060101] hpsa 0000:87:00.0: hpsa_figure_phys_disk_ptrs: [3:1:0:2] A phys
disk component of LV is missing, turning off offload_enabled for LV.
[ 3619.711122] sd 3:1:0:3: [sde] tag#436 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3619.751150] sd 3:1:0:3: [sde] tag#436 Sense Key : Aborted Command [current]
[ 3619.784375] sd 3:1:0:3: [sde] tag#436 Add. Sense: Internal target failure
[ 3619.816530] sd 3:1:0:3: [sde] tag#436 CDB: Read(10) 28 00 01 1b ad af 00 00
01 00
[ 3619.852295] print_req_error: I/O error, dev sde, sector 18591151
[ 3619.880850] sd 3:1:0:3: [sde] tag#461 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3619.920981] sd 3:1:0:3: [sde] tag#461 Sense Key : Aborted Command [current]
[ 3619.955081] sd 3:1:0:3: [sde] tag#461 Add. Sense: Internal target failure
[ 3619.987054] sd 3:1:0:3: [sde] tag#461 CDB: Read(10) 28 00 02 15 31 40 00 00
01 00
[ 3620.022569] print_req_error: I/O error, dev sde, sector 34943296
[ 3620.050873] sd 3:1:0:3: [sde] tag#157 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3620.091124] sd 3:1:0:3: [sde] tag#157 Sense Key : Aborted Command [current]
[ 3620.124179] sd 3:1:0:3: [sde] tag#157 Add. Sense: Internal target failure
[ 3620.156203] sd 3:1:0:3: [sde] tag#157 CDB: Read(10) 28 00 03 65 9d 7e 00 00
01 00
[ 3620.191520] print_req_error: I/O error, dev sde, sector 56991102
[ 3620.220308] sd 3:1:0:3: [sde] tag#266 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3620.260273] sd 3:1:0:3: [sde] tag#266 Sense Key : Aborted Command [current]
[ 3620.294605] sd 3:1:0:3: [sde] tag#266 Add. Sense: Internal target failure
[ 3620.328353] sd 3:1:0:3: [sde] tag#266 CDB: Read(10) 28 00 09 92 94 70 00 00
01 00
[ 3620.364807] print_req_error: I/O error, dev sde, sector 160601200
[ 3620.394342] sd 3:1:0:3: [sde] tag#278 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3620.434462] sd 3:1:0:3: [sde] tag#278 Sense Key : Aborted Command [current]
[ 3620.469059] sd 3:1:0:3: [sde] tag#278 Add. Sense: Internal target failure
[ 3620.471761] sd 3:1:0:3: [sde] tag#467 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3620.502240] sd 3:1:0:3: [sde] tag#278 CDB: Read(10) 28 00 08 00 12 ea 00 00
01 00
[ 3620.543157] sd 3:1:0:3: [sde] tag#467 Sense Key : Aborted Command [current]
[ 3620.580375] print_req_error: I/O error, dev sde, sector 134222570
[ 3620.615355] sd 3:1:0:3: [sde] tag#467 Add. Sense: Internal target failure
[ 3620.645069] sd 3:1:0:3: [sde] tag#244 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3620.678696] sd 3:1:0:3: [sde] tag#467 CDB: Read(10) 28 00 10 3f 2b fc 00 00
01 00
[ 3620.720247] sd 3:1:0:3: [sde] tag#244 Sense Key : Aborted Command [current]
[ 3620.756776] print_req_error: I/O error, dev sde, sector 272575484
[ 3620.791857] sd 3:1:0:3: [sde] tag#244 Add. Sense: Internal target failure
[ 3620.822272] sd 3:1:0:3: [sde] tag#431 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3620.855200] sd 3:1:0:3: [sde] tag#244 CDB: Read(10) 28 00 08 31 86 d9 00 00
01 00
[ 3620.895823] sd 3:1:0:3: [sde] tag#431 Sense Key : Aborted Command [current]
[ 3620.931923] print_req_error: I/O error, dev sde, sector 137463513
[ 3620.966262] sd 3:1:0:3: [sde] tag#431 Add. Sense: Internal target failure
[ 3620.995715] sd 3:1:0:3: [sde] tag#226 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3621.028703] sd 3:1:0:3: [sde] tag#431 CDB: Read(10) 28 00 10 7c b2 b0 00 00
01 00
[ 3621.069686] sd 3:1:0:3: [sde] tag#226 Sense Key : Aborted Command [current]
[ 3621.106253] print_req_error: I/O error, dev sde, sector 276607664
[ 3621.140782] sd 3:1:0:3: [sde] tag#226 Add. Sense: Internal target failure
[ 3621.170241] sd 3:1:0:3: [sde] tag#408 FAILED Result: hostbyte=DID_OK
driverbyte=DRIVER_SENSE
[ 3621.202997] sd 3:1:0:3: [sde] tag#226 CDB: Read(10) 28 00 08 ba cf f2 00 00
01 00
[ 3621.243870] sd 3:1:0:3: [sde] tag#408 Sense Key : Aborted Command [current]
[ 3621.280015] print_req_error: I/O error, dev sde, sector 146460658
[ 3621.313941] sd 3:1:0:3: [sde] tag#408 Add. Sense: Internal target failure
[ 3621.343790] print_req_error: I/O error, dev sde, sector 98830586
[ 3621.376164] sd 3:1:0:3: [sde] tag#408 CDB: Read(10) 28 00 14 da 6a 53 00 00
01 00
[ 3641.714842] WARNING: CPU: 3 PID: 0 at kernel/rcu/tree.c:2713
rcu_process_callbacks+0x4d5/0x510
[ 3641.756175] Modules linked in: sg ip6t_rpfilter ip6t_REJECT nf_reject_ipv6
nf_conntrack_ipv6 nf_defrag_ipv6 ipt_REJECT nf_reject_ipv4 nf_conntrack_ipv4
nf_defrag_ipv4 xt_conntrack nf_conntrack cfg80211 rfkill ebtable_nat
ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_mangle
ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_mangle
iptable_security iptable_raw iptable_filter ip_tables sb_edac
x86_pkg_temp_thermal coretemp kvm_intel kvm irqbypass crct10dif_pclmul
crc32_pclmul ghash_clmulni_intel pcbc iTCO_wdt iTCO_vendor_support aesni_intel
crypto_simd glue_helper cryptd pcspkr hpilo hpwdt ioatdma shpchp ipmi_si
lpc_ich dca mfd_core wmi ipmi_msghandler acpi_power_meter pcc_cpufreq uinput
xfs libcrc32c mgag200 i2c_algo_bit drm_kms_helper sd_mod syscopyarea sysfillrect
[ 3642.094993] sysimgblt fb_sys_fops ttm drm crc32c_intel i2c_core tg3 hpsa
scsi_transport_sas usb_storage dm_mirror dm_region_hash dm_log dm_mod dax
[ 3642.158883] CPU: 3 PID: 0 Comm: swapper/3 Not tainted 4.16.0-rc3+ #18
[ 3642.190015] Hardware name: HP ProLiant DL580 Gen8, BIOS P79 08/18/2016
[ 3642.221949] RIP: 0010:rcu_process_callbacks+0x4d5/0x510
[ 3642.247606] RSP: 0018:ffff8e179f6c3f08 EFLAGS: 00010002
[ 3642.273087] RAX: 0000000000000000 RBX: ffff8e179f6e3180 RCX: ffff8e279d1e8918
[ 3642.307426] RDX: ffffffffffffd801 RSI: ffff8e179f6c3f18 RDI: ffff8e179f6e31b8
[ 3642.342219] RBP: ffffffffb70a31c0 R08: ffff8e279d1e8918 R09: 0000000000000100
[ 3642.376929] R10: 0000000000000004 R11: 0000000000000005 R12: ffff8e179f6e31b8
[ 3642.411598] R13: ffff8e179d20ad00 R14: 0000000000000001 R15: 7fffffffffffffff
[ 3642.445957] FS: 0000000000000000(0000) GS:ffff8e179f6c0000(0000)
knlGS:0000000000000000
[ 3642.485599] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3642.513678] CR2: 00007f30917b9008 CR3: 000000054900a006 CR4: 00000000001606e0
[ 3642.548189] Call Trace:
[ 3642.560411] <IRQ>
[ 3642.570588] __do_softirq+0xd1/0x275
[ 3642.588643] irq_exit+0xd5/0xe0
[ 3642.604134] smp_apic_timer_interrupt+0x60/0x120
[ 3642.626752] apic_timer_interrupt+0xf/0x20
[ 3642.646712] </IRQ>
[ 3642.657330] RIP: 0010:cpuidle_enter_state+0xd4/0x260
[ 3642.681389] RSP: 0018:ffffaed7c00e7ea0 EFLAGS: 00000246 ORIG_RAX:
ffffffffffffff12
[ 3642.717937] RAX: ffff8e179f6e2280 RBX: ffffcebfbfec1bb8 RCX: 000000000000001f
[ 3642.752525] RDX: 0000000000000000 RSI: ff6c3b1b90a53a78 RDI: 0000000000000000
[ 3642.787181] RBP: 0000000000000003 R08: 0000000000000005 R09: 0000000000000396
[ 3642.821442] R10: 00000000000003a7 R11: 0000000000000008 R12: 0000000000000003
[ 3642.856381] R13: 0000034fe70ea52c R14: 0000000000000003 R15: 0000034fe71d99d4
[ 3642.890830] do_idle+0x172/0x1e0
[ 3642.906714] cpu_startup_entry+0x6f/0x80
[ 3642.925835] start_secondary+0x187/0x1e0
[ 3642.944975] secondary_startup_64+0xa5/0xb0
[ 3642.965719] Code: e9 db fd ff ff 4c 89 f6 4c 89 e7 e8 96 b8 63 00 e9 56 fc
ff ff 0f 0b e9 34 fc ff ff 0f 0b 0f 1f 84 00 00 00 00 00 e9 e0 fb ff ff <0f> 0b
66 0f 1f 84 00 00 00 00 00 e9 e5 fd ff ff 0f 0b 66 0f 1f
[ 3643.056198] ---[ end trace 7bdac969b3138de7 ]---
[ 3735.745955] hpsa 0000:87:00.0: SCSI status: LUN:000000c000002601
CDB:12010000040000000000000000000000
[ 3735.790497] hpsa 0000:87:00.0: SCSI Status = 02, Sense key = 0x05, ASC =
0x25, ASCQ = 0x00
> ---
> drivers/scsi/hpsa.c | 73
> +++++++++++++++++++++++++++++++++++++++--------------
> drivers/scsi/hpsa.h | 1 +
> 2 files changed, 55 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
> index 5293e6827ce5..3a9eca163db8 100644
> --- a/drivers/scsi/hpsa.c
> +++ b/drivers/scsi/hpsa.c
> @@ -1045,11 +1045,7 @@ static void set_performant_mode(struct ctlr_info
> *h, struct CommandList *c,
> c->busaddr |= 1 | (h->blockFetchTable[c->Header.SGList] << 1);
> if (unlikely(!h->msix_vectors))
> return;
> - if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
> - c->Header.ReplyQueue =
> - raw_smp_processor_id() % h->nreply_queues;
> - else
> - c->Header.ReplyQueue = reply_queue % h->nreply_queues;
> + c->Header.ReplyQueue = reply_queue;
> }
> }
>
> @@ -1063,10 +1059,7 @@ static void set_ioaccel1_performant_mode(struct
> ctlr_info *h,
> * Tell the controller to post the reply to the queue for this
> * processor. This seems to give the best I/O throughput.
> */
> - if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
> - cp->ReplyQueue = smp_processor_id() % h->nreply_queues;
> - else
> - cp->ReplyQueue = reply_queue % h->nreply_queues;
> + cp->ReplyQueue = reply_queue;
> /*
> * Set the bits in the address sent down to include:
> * - performant mode bit (bit 0)
> @@ -1087,10 +1080,7 @@ static void
> set_ioaccel2_tmf_performant_mode(struct ctlr_info *h,
> /* Tell the controller to post the reply to the queue for this
> * processor. This seems to give the best I/O throughput.
> */
> - if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
> - cp->reply_queue = smp_processor_id() % h->nreply_queues;
> - else
> - cp->reply_queue = reply_queue % h->nreply_queues;
> + cp->reply_queue = reply_queue;
> /* Set the bits in the address sent down to include:
> * - performant mode bit not used in ioaccel mode 2
> * - pull count (bits 0-3)
> @@ -1109,10 +1099,7 @@ static void set_ioaccel2_performant_mode(struct
> ctlr_info *h,
> * Tell the controller to post the reply to the queue for this
> * processor. This seems to give the best I/O throughput.
> */
> - if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
> - cp->reply_queue = smp_processor_id() % h->nreply_queues;
> - else
> - cp->reply_queue = reply_queue % h->nreply_queues;
> + cp->reply_queue = reply_queue;
> /*
> * Set the bits in the address sent down to include:
> * - performant mode bit not used in ioaccel mode 2
> @@ -1157,6 +1144,8 @@ static void __enqueue_cmd_and_start_io(struct
> ctlr_info *h,
> {
> dial_down_lockup_detection_during_fw_flash(h, c);
> atomic_inc(&h->commands_outstanding);
> +
> + reply_queue = h->reply_map[raw_smp_processor_id()];
> switch (c->cmd_type) {
> case CMD_IOACCEL1:
> set_ioaccel1_performant_mode(h, c, reply_queue);
> @@ -7376,6 +7365,26 @@ static void hpsa_disable_interrupt_mode(struct
> ctlr_info *h)
> h->msix_vectors = 0;
> }
>
> +static void hpsa_setup_reply_map(struct ctlr_info *h)
> +{
> + const struct cpumask *mask;
> + unsigned int queue, cpu;
> +
> + for (queue = 0; queue < h->msix_vectors; queue++) {
> + mask = pci_irq_get_affinity(h->pdev, queue);
> + if (!mask)
> + goto fallback;
> +
> + for_each_cpu(cpu, mask)
> + h->reply_map[cpu] = queue;
> + }
> + return;
> +
> +fallback:
> + for_each_possible_cpu(cpu)
> + h->reply_map[cpu] = 0;
> +}
> +
> /* If MSI/MSI-X is supported by the kernel we will try to enable it on
> * controllers that are capable. If not, we use legacy INTx mode.
> */
> @@ -7771,6 +7780,10 @@ static int hpsa_pci_init(struct ctlr_info *h)
> err = hpsa_interrupt_mode(h);
> if (err)
> goto clean1;
> +
> + /* setup mapping between CPU and reply queue */
> + hpsa_setup_reply_map(h);
> +
> err = hpsa_pci_find_memory_BAR(h->pdev, &h->paddr);
> if (err)
> goto clean2; /* intmode+region, pci */
> @@ -8480,6 +8493,28 @@ static struct workqueue_struct
> *hpsa_create_controller_wq(struct ctlr_info *h,
> return wq;
> }
>
> +static void hpda_free_ctlr_info(struct ctlr_info *h)
> +{
> + kfree(h->reply_map);
> + kfree(h);
> +}
> +
> +static struct ctlr_info *hpda_alloc_ctlr_info(void)
> +{
> + struct ctlr_info *h;
> +
> + h = kzalloc(sizeof(*h), GFP_KERNEL);
> + if (!h)
> + return NULL;
> +
> + h->reply_map = kzalloc(sizeof(*h->reply_map) * nr_cpu_ids,
> GFP_KERNEL);
> + if (!h->reply_map) {
> + kfree(h);
> + return NULL;
> + }
> + return h;
> +}
> +
> static int hpsa_init_one(struct pci_dev *pdev, const struct pci_device_id
> *ent)
> {
> int dac, rc;
> @@ -8517,7 +8552,7 @@ static int hpsa_init_one(struct pci_dev *pdev, const
> struct pci_device_id *ent)
> * the driver. See comments in hpsa.h for more info.
> */
> BUILD_BUG_ON(sizeof(struct CommandList) %
> COMMANDLIST_ALIGNMENT);
> - h = kzalloc(sizeof(*h), GFP_KERNEL);
> + h = hpda_alloc_ctlr_info();
> if (!h) {
> dev_err(&pdev->dev, "Failed to allocate controller head\n");
> return -ENOMEM;
> @@ -8916,7 +8951,7 @@ static void hpsa_remove_one(struct pci_dev *pdev)
> h->lockup_detected = NULL; /* init_one 2 */
> /* (void) pci_disable_pcie_error_reporting(pdev); */ /* init_one 1
> */
>
> - kfree(h); /* init_one 1 */
> + hpda_free_ctlr_info(h); /* init_one 1 */
> }
>
> static int hpsa_suspend(__attribute__((unused)) struct pci_dev *pdev,
> diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
> index 018f980a701c..fb9f5e7f8209 100644
> --- a/drivers/scsi/hpsa.h
> +++ b/drivers/scsi/hpsa.h
> @@ -158,6 +158,7 @@ struct bmic_controller_parameters {
> #pragma pack()
>
> struct ctlr_info {
> + unsigned int *reply_map;
> int ctlr;
> char devname[8];
> char *product_name;
> --
> 2.9.5
