OpenCloudOS-Kernel/drivers/nvme/host/nvme.h

838 lines
22 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2011-2014, Intel Corporation.
*/
#ifndef _NVME_H
#define _NVME_H
#include <linux/nvme.h>
#include <linux/cdev.h>
#include <linux/pci.h>
#include <linux/kref.h>
#include <linux/blk-mq.h>
#include <linux/lightnvm.h>
#include <linux/sed-opal.h>
nvme: Add fault injection feature Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. This patch uses the framework to add error injection to NVMe driver. The fault injection source code is stored in a separate file and only linked if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected. Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no retry will be injected into the nvme_end_request. Users can change the default status code and no retry flag via debufs. Following example shows how to enable and inject an error. For more examples, refer to Documentation/fault-injection/nvme-fault-injection.txt How to enable nvme fault injection: First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config, recompile the kernel. After booting up the kernel, do the following. How to inject an error: mount /dev/nvme0n1 /mnt echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability cp a.file /mnt Expected Result: cp: cannot stat ‘/mnt/a.file’: Input/output error Message from dmesg: FAULT_INJECTION: forcing a failure. name fault_inject, interval 1, probability 100, space 0, times 1 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: <IRQ> dump_stack+0x5c/0x7d should_fail+0x148/0x170 nvme_should_fail+0x2f/0x50 [nvme_core] nvme_process_cq+0xe7/0x1d0 [nvme] nvme_irq+0x1e/0x40 [nvme] __handle_irq_event_percpu+0x3a/0x190 handle_irq_event_percpu+0x30/0x70 handle_irq_event+0x36/0x60 handle_fasteoi_irq+0x78/0x120 handle_irq+0xa7/0x130 ? tick_irq_enter+0xa8/0xc0 do_IRQ+0x43/0xc0 common_interrupt+0xa2/0xa2 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480 R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x4/0x4 default_idle+0x18/0xf0 do_idle+0x150/0x1d0 cpu_startup_entry+0x6f/0x80 start_kernel+0x4c4/0x4e4 ? set_init_arg+0x55/0x55 secondary_startup_64+0xa5/0xb0 print_req_error: I/O error, dev nvme0n1, sector 9240 EXT4-fs error (device nvme0n1): ext4_find_entry:1436: inode #2: comm cp: reading directory lblock 0 Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-09 02:38:29 +08:00
#include <linux/fault-inject.h>
#include <linux/rcupdate.h>
#include <linux/wait.h>
#include <linux/t10-pi.h>
#include <trace/events/block.h>
extern unsigned int nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
extern unsigned int admin_timeout;
#define NVME_ADMIN_TIMEOUT (admin_timeout * HZ)
#define NVME_DEFAULT_KATO 5
#define NVME_KATO_GRACE 10
#ifdef CONFIG_ARCH_NO_SG_CHAIN
#define NVME_INLINE_SG_CNT 0
#define NVME_INLINE_METADATA_SG_CNT 0
#else
#define NVME_INLINE_SG_CNT 2
#define NVME_INLINE_METADATA_SG_CNT 1
#endif
/*
* Default to a 4K page size, with the intention to update this
* path in the future to accommodate architectures with differing
* kernel and IO page sizes.
*/
#define NVME_CTRL_PAGE_SHIFT 12
#define NVME_CTRL_PAGE_SIZE (1 << NVME_CTRL_PAGE_SHIFT)
extern struct workqueue_struct *nvme_wq;
nvme: host delete_work and reset_work on separate workqueues We need to ensure that delete_work will be hosted on a different workqueue than all the works we flush or cancel from it. Otherwise we may hit a circular dependency warning [1]. Also, given that delete_work flushes reset_work, host reset_work on nvme_reset_wq and delete_work on nvme_delete_wq. In addition, fix the flushing in the individual drivers to flush nvme_delete_wq when draining queued deletes. [1]: [ 178.491942] ============================================= [ 178.492718] [ INFO: possible recursive locking detected ] [ 178.493495] 4.9.0-rc4-c844263313a8-lb #3 Tainted: G OE [ 178.494382] --------------------------------------------- [ 178.495160] kworker/5:1/135 is trying to acquire lock: [ 178.495894] ( [ 178.496120] "nvme-wq" [ 178.496471] ){++++.+} [ 178.496599] , at: [ 178.496921] [<ffffffffa70ac206>] flush_work+0x1a6/0x2d0 [ 178.497670] but task is already holding lock: [ 178.498499] ( [ 178.498724] "nvme-wq" [ 178.499074] ){++++.+} [ 178.499202] , at: [ 178.499520] [<ffffffffa70ad6c2>] process_one_work+0x162/0x6a0 [ 178.500343] other info that might help us debug this: [ 178.501269] Possible unsafe locking scenario: [ 178.502113] CPU0 [ 178.502472] ---- [ 178.502829] lock( [ 178.503115] "nvme-wq" [ 178.503467] ); [ 178.503716] lock( [ 178.504001] "nvme-wq" [ 178.504353] ); [ 178.504601] *** DEADLOCK *** [ 178.505441] May be due to missing lock nesting notation [ 178.506453] 2 locks held by kworker/5:1/135: [ 178.507068] #0: [ 178.507330] ( [ 178.507598] "nvme-wq" [ 178.507726] ){++++.+} [ 178.508079] , at: [ 178.508173] [<ffffffffa70ad6c2>] process_one_work+0x162/0x6a0 [ 178.509004] #1: [ 178.509265] ( [ 178.509532] (&ctrl->delete_work) [ 178.509795] ){+.+.+.} [ 178.510145] , at: [ 178.510239] [<ffffffffa70ad6c2>] process_one_work+0x162/0x6a0 [ 178.511070] stack backtrace: : [ 178.511693] CPU: 5 PID: 135 Comm: kworker/5:1 Tainted: G OE 4.9.0-rc4-c844263313a8-lb #3 [ 178.512974] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1ubuntu1 04/01/2014 [ 178.514247] Workqueue: nvme-wq nvme_del_ctrl_work [nvme_tcp] [ 178.515071] ffffc2668175bae0 ffffffffa7450823 ffffffffa88abd80 ffffffffa88abd80 [ 178.516195] ffffc2668175bb98 ffffffffa70eb012 ffffffffa8d8d90d ffff9c472e9ea700 [ 178.517318] ffff9c472e9ea700 ffff9c4700000000 ffff9c4700007200 ab83be61bec0d50e [ 178.518443] Call Trace: [ 178.518807] [<ffffffffa7450823>] dump_stack+0x85/0xc2 [ 178.519542] [<ffffffffa70eb012>] __lock_acquire+0x17d2/0x18f0 [ 178.520377] [<ffffffffa75839a7>] ? serial8250_console_putchar+0x27/0x30 [ 178.521330] [<ffffffffa7583980>] ? wait_for_xmitr+0xa0/0xa0 [ 178.522174] [<ffffffffa70ac1eb>] ? flush_work+0x18b/0x2d0 [ 178.522975] [<ffffffffa70eb7cb>] lock_acquire+0x11b/0x220 [ 178.523753] [<ffffffffa70ac206>] ? flush_work+0x1a6/0x2d0 [ 178.524535] [<ffffffffa70ac229>] flush_work+0x1c9/0x2d0 [ 178.525291] [<ffffffffa70ac206>] ? flush_work+0x1a6/0x2d0 [ 178.526077] [<ffffffffa70a9cf0>] ? flush_workqueue_prep_pwqs+0x220/0x220 [ 178.527040] [<ffffffffa70ae7cf>] __cancel_work_timer+0x10f/0x1d0 [ 178.527907] [<ffffffffa70fecb9>] ? vprintk_default+0x29/0x40 [ 178.528726] [<ffffffffa71cb507>] ? printk+0x48/0x50 [ 178.529434] [<ffffffffa70ae8c3>] cancel_delayed_work_sync+0x13/0x20 [ 178.530381] [<ffffffffc042100b>] nvme_stop_ctrl+0x5b/0x70 [nvme_core] [ 178.531314] [<ffffffffc0403dcc>] nvme_del_ctrl_work+0x2c/0x50 [nvme_tcp] [ 178.532271] [<ffffffffa70ad741>] process_one_work+0x1e1/0x6a0 [ 178.533101] [<ffffffffa70ad6c2>] ? process_one_work+0x162/0x6a0 [ 178.533954] [<ffffffffa70adc4e>] worker_thread+0x4e/0x490 [ 178.534735] [<ffffffffa70adc00>] ? process_one_work+0x6a0/0x6a0 [ 178.535588] [<ffffffffa70adc00>] ? process_one_work+0x6a0/0x6a0 [ 178.536441] [<ffffffffa70b48cf>] kthread+0xff/0x120 [ 178.537149] [<ffffffffa70b47d0>] ? kthread_park+0x60/0x60 [ 178.538094] [<ffffffffa70b47d0>] ? kthread_park+0x60/0x60 [ 178.538900] [<ffffffffa78e332a>] ret_from_fork+0x2a/0x40 Signed-off-by: Roy Shterman <roys@lightbitslabs.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-01-14 18:39:02 +08:00
extern struct workqueue_struct *nvme_reset_wq;
extern struct workqueue_struct *nvme_delete_wq;
enum {
NVME_NS_LBA = 0,
NVME_NS_LIGHTNVM = 1,
};
/*
* List of workarounds for devices that required behavior not specified in
* the standard.
*/
enum nvme_quirks {
/*
* Prefers I/O aligned to a stripe size specified in a vendor
* specific Identify field.
*/
NVME_QUIRK_STRIPE_SIZE = (1 << 0),
/*
* The controller doesn't handle Identify value others than 0 or 1
* correctly.
*/
NVME_QUIRK_IDENTIFY_CNS = (1 << 1),
/*
* The controller deterministically returns O's on reads to
* logical blocks that deallocate was called on.
*/
NVME_QUIRK_DEALLOCATE_ZEROES = (1 << 2),
/*
* The controller needs a delay before starts checking the device
* readiness, which is done by reading the NVME_CSTS_RDY bit.
*/
NVME_QUIRK_DELAY_BEFORE_CHK_RDY = (1 << 3),
nvme: Enable autonomous power state transitions NVMe devices can advertise multiple power states. These states can be either "operational" (the device is fully functional but possibly slow) or "non-operational" (the device is asleep until woken up). Some devices can automatically enter a non-operational state when idle for a specified amount of time and then automatically wake back up when needed. The hardware configuration is a table. For each state, an entry in the table indicates the next deeper non-operational state, if any, to autonomously transition to and the idle time required before transitioning. This patch teaches the driver to program APST so that each successive non-operational state will be entered after an idle time equal to 100% of the total latency (entry plus exit) associated with that state. The maximum acceptable latency is controlled using dev_pm_qos (e.g. power/pm_qos_latency_tolerance_us in sysfs); non-operational states with total latency greater than this value will not be used. As a special case, setting the latency tolerance to 0 will disable APST entirely. On hardware without APST support, the sysfs file will not be exposed. The latency tolerance for newly-probed devices is set by the module parameter nvme_core.default_ps_max_latency_us. In theory, the device can expose "default" APST table, but this doesn't seem to function correctly on my device (Samsung 950), nor does it seem particularly useful. There is also an optional mechanism by which a configuration can be "saved" so it will be automatically loaded on reset. This can be configured from userspace, but it doesn't seem useful to support in the driver. On my laptop, enabling APST seems to save nearly 1W. The hardware tables can be decoded in userspace with nvme-cli. 'nvme id-ctrl /dev/nvmeN' will show the power state table and 'nvme get-feature -f 0x0c -H /dev/nvme0' will show the current APST configuration. This feature is quirked off on a known-buggy Samsung device. Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-02-08 02:08:45 +08:00
/*
* APST should not be used.
*/
NVME_QUIRK_NO_APST = (1 << 4),
/*
* The deepest sleep state should not be used.
*/
NVME_QUIRK_NO_DEEPEST_PS = (1 << 5),
/*
* Supports the LighNVM command set if indicated in vs[1].
*/
NVME_QUIRK_LIGHTNVM = (1 << 6),
/*
* Set MEDIUM priority on SQ creation
*/
NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7),
/*
* Ignore device provided subnqn.
*/
NVME_QUIRK_IGNORE_DEV_SUBNQN = (1 << 8),
/*
* Broken Write Zeroes.
*/
NVME_QUIRK_DISABLE_WRITE_ZEROES = (1 << 9),
/*
* Force simple suspend/resume path.
*/
NVME_QUIRK_SIMPLE_SUSPEND = (1 << 10),
for-5.4/block-2019-09-16 -----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl1/no0QHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgpmo9EACFXMbdNmEEUMyRSdOkVLlr7ZlTyQi1tLpB YESDPxdBfybzpi0qa8JSaysGIfvSkSjmSAqBqrWPmASOSOL6CK4bbA4fTYbgPplk XeHUdgGiG34oCQUn8Xil5reYaTm7I6LQWnWTpVa5fIhAyUYaGJL+987ykoGmpQmB Dvf3YSc+8H0RTp9PCMVd6UCGPkZbVlLImGad3PF5ULvTEaE4RCXC2aiAgh0p1l5A J2CkRZ+/mio3zN2O4YN7VdPGfr1Wo1iZ834xbIGLegv1miHXagFk7jwTcC7zIt5t oSnJnqIg3iCe7SpWt4Bkzw/zy/2UqaspifbCMgw8vychlViVRUHFO5h85Yboo7kQ OMLEQPcwjm6dTHv5h1iXF9LW1O7NoiYmmgvApU9uOo1HUrl1X7PZ3JEfUsVHxkOO T4D5igf0Krsl1eAbiwEUQzy7vFZ8PlRHqrHgK+fkyotzHu1BJR7OQkYygEfGFOB/ EfMxplGDpmibYGuWCwDX2bPAmLV3SPUQENReHrfPJRDt5TD1UkFpVGv/PLLhbr0p cLYI78DKpDSigBpVMmwq5nTYpnex33eyDTTA8C0sakcsdzdmU5qv30y3wm4nTiep f6gZo6IMXwRg/rCgVVrd9SKQAr/8wEzVlsDW3qyi2pVT8sHIgm0tFv7paihXGdDV xsKgmTrQQQ== =Qt+h -----END PGP SIGNATURE----- Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block Pull block updates from Jens Axboe: - Two NVMe pull requests: - ana log parse fix from Anton - nvme quirks support for Apple devices from Ben - fix missing bio completion tracing for multipath stack devices from Hannes and Mikhail - IP TOS settings for nvme rdma and tcp transports from Israel - rq_dma_dir cleanups from Israel - tracing for Get LBA Status command from Minwoo - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself - Some consolidation between the fabrics transports for handling the CAP register - reset race with ns scanning fix for fabrics (move fabrics commands to a dedicated request queue with a different lifetime from the admin request queue)." - controller reset and namespace scan races fixes - nvme discovery log change uevent support - naming improvements from Keith - multiple discovery controllers reject fix from James - some regular cleanups from various people - Series fixing (and re-fixing) null_blk debug printing and nr_devices checks (André) - A few pull requests from Song, with fixes from Andy, Guoqing, Guilherme, Neil, Nigel, and Yufen. - REQ_OP_ZONE_RESET_ALL support (Chaitanya) - Bio merge handling unification (Christoph) - Pick default elevator correctly for devices with special needs (Damien) - Block stats fixes (Hou) - Timeout and support devices nbd fixes (Mike) - Series fixing races around elevator switching and device add/remove (Ming) - sed-opal cleanups (Revanth) - Per device weight support for BFQ (Fam) - Support for blk-iocost, a new model that can properly account cost of IO workloads. (Tejun) - blk-cgroup writeback fixes (Tejun) - paride queue init fixes (zhengbin) - blk_set_runtime_active() cleanup (Stanley) - Block segment mapping optimizations (Bart) - lightnvm fixes (Hans/Minwoo/YueHaibing) - Various little fixes and cleanups * tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits) null_blk: format pr_* logs with pr_fmt null_blk: match the type of parameter nr_devices null_blk: do not fail the module load with zero devices block: also check RQF_STATS in blk_mq_need_time_stamp() block: make rq sector size accessible for block stats bfq: Fix bfq linkage error raid5: use bio_end_sector in r5_next_bio raid5: remove STRIPE_OPS_REQ_PENDING md: add feature flag MD_FEATURE_RAID0_LAYOUT md/raid0: avoid RAID0 data corruption due to layout confusion. raid5: don't set STRIPE_HANDLE to stripe which is in batch list raid5: don't increment read_errors on EILSEQ return nvmet: fix a wrong error status returned in error log page nvme: send discovery log page change events to userspace nvme: add uevent variables for controller devices nvme: enable aen regardless of the presence of I/O queues nvme-fabrics: allow discovery subsystems accept a kato nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery() nvme: Remove redundant assignment of cq vector nvme: Assign subsys instance from first ctrl ...
2019-09-18 07:57:47 +08:00
/*
* Use only one interrupt vector for all queues
*/
for-5.4/block-2019-09-16 -----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl1/no0QHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgpmo9EACFXMbdNmEEUMyRSdOkVLlr7ZlTyQi1tLpB YESDPxdBfybzpi0qa8JSaysGIfvSkSjmSAqBqrWPmASOSOL6CK4bbA4fTYbgPplk XeHUdgGiG34oCQUn8Xil5reYaTm7I6LQWnWTpVa5fIhAyUYaGJL+987ykoGmpQmB Dvf3YSc+8H0RTp9PCMVd6UCGPkZbVlLImGad3PF5ULvTEaE4RCXC2aiAgh0p1l5A J2CkRZ+/mio3zN2O4YN7VdPGfr1Wo1iZ834xbIGLegv1miHXagFk7jwTcC7zIt5t oSnJnqIg3iCe7SpWt4Bkzw/zy/2UqaspifbCMgw8vychlViVRUHFO5h85Yboo7kQ OMLEQPcwjm6dTHv5h1iXF9LW1O7NoiYmmgvApU9uOo1HUrl1X7PZ3JEfUsVHxkOO T4D5igf0Krsl1eAbiwEUQzy7vFZ8PlRHqrHgK+fkyotzHu1BJR7OQkYygEfGFOB/ EfMxplGDpmibYGuWCwDX2bPAmLV3SPUQENReHrfPJRDt5TD1UkFpVGv/PLLhbr0p cLYI78DKpDSigBpVMmwq5nTYpnex33eyDTTA8C0sakcsdzdmU5qv30y3wm4nTiep f6gZo6IMXwRg/rCgVVrd9SKQAr/8wEzVlsDW3qyi2pVT8sHIgm0tFv7paihXGdDV xsKgmTrQQQ== =Qt+h -----END PGP SIGNATURE----- Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block Pull block updates from Jens Axboe: - Two NVMe pull requests: - ana log parse fix from Anton - nvme quirks support for Apple devices from Ben - fix missing bio completion tracing for multipath stack devices from Hannes and Mikhail - IP TOS settings for nvme rdma and tcp transports from Israel - rq_dma_dir cleanups from Israel - tracing for Get LBA Status command from Minwoo - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself - Some consolidation between the fabrics transports for handling the CAP register - reset race with ns scanning fix for fabrics (move fabrics commands to a dedicated request queue with a different lifetime from the admin request queue)." - controller reset and namespace scan races fixes - nvme discovery log change uevent support - naming improvements from Keith - multiple discovery controllers reject fix from James - some regular cleanups from various people - Series fixing (and re-fixing) null_blk debug printing and nr_devices checks (André) - A few pull requests from Song, with fixes from Andy, Guoqing, Guilherme, Neil, Nigel, and Yufen. - REQ_OP_ZONE_RESET_ALL support (Chaitanya) - Bio merge handling unification (Christoph) - Pick default elevator correctly for devices with special needs (Damien) - Block stats fixes (Hou) - Timeout and support devices nbd fixes (Mike) - Series fixing races around elevator switching and device add/remove (Ming) - sed-opal cleanups (Revanth) - Per device weight support for BFQ (Fam) - Support for blk-iocost, a new model that can properly account cost of IO workloads. (Tejun) - blk-cgroup writeback fixes (Tejun) - paride queue init fixes (zhengbin) - blk_set_runtime_active() cleanup (Stanley) - Block segment mapping optimizations (Bart) - lightnvm fixes (Hans/Minwoo/YueHaibing) - Various little fixes and cleanups * tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits) null_blk: format pr_* logs with pr_fmt null_blk: match the type of parameter nr_devices null_blk: do not fail the module load with zero devices block: also check RQF_STATS in blk_mq_need_time_stamp() block: make rq sector size accessible for block stats bfq: Fix bfq linkage error raid5: use bio_end_sector in r5_next_bio raid5: remove STRIPE_OPS_REQ_PENDING md: add feature flag MD_FEATURE_RAID0_LAYOUT md/raid0: avoid RAID0 data corruption due to layout confusion. raid5: don't set STRIPE_HANDLE to stripe which is in batch list raid5: don't increment read_errors on EILSEQ return nvmet: fix a wrong error status returned in error log page nvme: send discovery log page change events to userspace nvme: add uevent variables for controller devices nvme: enable aen regardless of the presence of I/O queues nvme-fabrics: allow discovery subsystems accept a kato nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery() nvme: Remove redundant assignment of cq vector nvme: Assign subsys instance from first ctrl ...
2019-09-18 07:57:47 +08:00
NVME_QUIRK_SINGLE_VECTOR = (1 << 11),
/*
* Use non-standard 128 bytes SQEs.
*/
for-5.4/block-2019-09-16 -----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl1/no0QHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgpmo9EACFXMbdNmEEUMyRSdOkVLlr7ZlTyQi1tLpB YESDPxdBfybzpi0qa8JSaysGIfvSkSjmSAqBqrWPmASOSOL6CK4bbA4fTYbgPplk XeHUdgGiG34oCQUn8Xil5reYaTm7I6LQWnWTpVa5fIhAyUYaGJL+987ykoGmpQmB Dvf3YSc+8H0RTp9PCMVd6UCGPkZbVlLImGad3PF5ULvTEaE4RCXC2aiAgh0p1l5A J2CkRZ+/mio3zN2O4YN7VdPGfr1Wo1iZ834xbIGLegv1miHXagFk7jwTcC7zIt5t oSnJnqIg3iCe7SpWt4Bkzw/zy/2UqaspifbCMgw8vychlViVRUHFO5h85Yboo7kQ OMLEQPcwjm6dTHv5h1iXF9LW1O7NoiYmmgvApU9uOo1HUrl1X7PZ3JEfUsVHxkOO T4D5igf0Krsl1eAbiwEUQzy7vFZ8PlRHqrHgK+fkyotzHu1BJR7OQkYygEfGFOB/ EfMxplGDpmibYGuWCwDX2bPAmLV3SPUQENReHrfPJRDt5TD1UkFpVGv/PLLhbr0p cLYI78DKpDSigBpVMmwq5nTYpnex33eyDTTA8C0sakcsdzdmU5qv30y3wm4nTiep f6gZo6IMXwRg/rCgVVrd9SKQAr/8wEzVlsDW3qyi2pVT8sHIgm0tFv7paihXGdDV xsKgmTrQQQ== =Qt+h -----END PGP SIGNATURE----- Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block Pull block updates from Jens Axboe: - Two NVMe pull requests: - ana log parse fix from Anton - nvme quirks support for Apple devices from Ben - fix missing bio completion tracing for multipath stack devices from Hannes and Mikhail - IP TOS settings for nvme rdma and tcp transports from Israel - rq_dma_dir cleanups from Israel - tracing for Get LBA Status command from Minwoo - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself - Some consolidation between the fabrics transports for handling the CAP register - reset race with ns scanning fix for fabrics (move fabrics commands to a dedicated request queue with a different lifetime from the admin request queue)." - controller reset and namespace scan races fixes - nvme discovery log change uevent support - naming improvements from Keith - multiple discovery controllers reject fix from James - some regular cleanups from various people - Series fixing (and re-fixing) null_blk debug printing and nr_devices checks (André) - A few pull requests from Song, with fixes from Andy, Guoqing, Guilherme, Neil, Nigel, and Yufen. - REQ_OP_ZONE_RESET_ALL support (Chaitanya) - Bio merge handling unification (Christoph) - Pick default elevator correctly for devices with special needs (Damien) - Block stats fixes (Hou) - Timeout and support devices nbd fixes (Mike) - Series fixing races around elevator switching and device add/remove (Ming) - sed-opal cleanups (Revanth) - Per device weight support for BFQ (Fam) - Support for blk-iocost, a new model that can properly account cost of IO workloads. (Tejun) - blk-cgroup writeback fixes (Tejun) - paride queue init fixes (zhengbin) - blk_set_runtime_active() cleanup (Stanley) - Block segment mapping optimizations (Bart) - lightnvm fixes (Hans/Minwoo/YueHaibing) - Various little fixes and cleanups * tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits) null_blk: format pr_* logs with pr_fmt null_blk: match the type of parameter nr_devices null_blk: do not fail the module load with zero devices block: also check RQF_STATS in blk_mq_need_time_stamp() block: make rq sector size accessible for block stats bfq: Fix bfq linkage error raid5: use bio_end_sector in r5_next_bio raid5: remove STRIPE_OPS_REQ_PENDING md: add feature flag MD_FEATURE_RAID0_LAYOUT md/raid0: avoid RAID0 data corruption due to layout confusion. raid5: don't set STRIPE_HANDLE to stripe which is in batch list raid5: don't increment read_errors on EILSEQ return nvmet: fix a wrong error status returned in error log page nvme: send discovery log page change events to userspace nvme: add uevent variables for controller devices nvme: enable aen regardless of the presence of I/O queues nvme-fabrics: allow discovery subsystems accept a kato nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery() nvme: Remove redundant assignment of cq vector nvme: Assign subsys instance from first ctrl ...
2019-09-18 07:57:47 +08:00
NVME_QUIRK_128_BYTES_SQES = (1 << 12),
/*
* Prevent tag overlap between queues
*/
for-5.4/block-2019-09-16 -----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl1/no0QHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgpmo9EACFXMbdNmEEUMyRSdOkVLlr7ZlTyQi1tLpB YESDPxdBfybzpi0qa8JSaysGIfvSkSjmSAqBqrWPmASOSOL6CK4bbA4fTYbgPplk XeHUdgGiG34oCQUn8Xil5reYaTm7I6LQWnWTpVa5fIhAyUYaGJL+987ykoGmpQmB Dvf3YSc+8H0RTp9PCMVd6UCGPkZbVlLImGad3PF5ULvTEaE4RCXC2aiAgh0p1l5A J2CkRZ+/mio3zN2O4YN7VdPGfr1Wo1iZ834xbIGLegv1miHXagFk7jwTcC7zIt5t oSnJnqIg3iCe7SpWt4Bkzw/zy/2UqaspifbCMgw8vychlViVRUHFO5h85Yboo7kQ OMLEQPcwjm6dTHv5h1iXF9LW1O7NoiYmmgvApU9uOo1HUrl1X7PZ3JEfUsVHxkOO T4D5igf0Krsl1eAbiwEUQzy7vFZ8PlRHqrHgK+fkyotzHu1BJR7OQkYygEfGFOB/ EfMxplGDpmibYGuWCwDX2bPAmLV3SPUQENReHrfPJRDt5TD1UkFpVGv/PLLhbr0p cLYI78DKpDSigBpVMmwq5nTYpnex33eyDTTA8C0sakcsdzdmU5qv30y3wm4nTiep f6gZo6IMXwRg/rCgVVrd9SKQAr/8wEzVlsDW3qyi2pVT8sHIgm0tFv7paihXGdDV xsKgmTrQQQ== =Qt+h -----END PGP SIGNATURE----- Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block Pull block updates from Jens Axboe: - Two NVMe pull requests: - ana log parse fix from Anton - nvme quirks support for Apple devices from Ben - fix missing bio completion tracing for multipath stack devices from Hannes and Mikhail - IP TOS settings for nvme rdma and tcp transports from Israel - rq_dma_dir cleanups from Israel - tracing for Get LBA Status command from Minwoo - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself - Some consolidation between the fabrics transports for handling the CAP register - reset race with ns scanning fix for fabrics (move fabrics commands to a dedicated request queue with a different lifetime from the admin request queue)." - controller reset and namespace scan races fixes - nvme discovery log change uevent support - naming improvements from Keith - multiple discovery controllers reject fix from James - some regular cleanups from various people - Series fixing (and re-fixing) null_blk debug printing and nr_devices checks (André) - A few pull requests from Song, with fixes from Andy, Guoqing, Guilherme, Neil, Nigel, and Yufen. - REQ_OP_ZONE_RESET_ALL support (Chaitanya) - Bio merge handling unification (Christoph) - Pick default elevator correctly for devices with special needs (Damien) - Block stats fixes (Hou) - Timeout and support devices nbd fixes (Mike) - Series fixing races around elevator switching and device add/remove (Ming) - sed-opal cleanups (Revanth) - Per device weight support for BFQ (Fam) - Support for blk-iocost, a new model that can properly account cost of IO workloads. (Tejun) - blk-cgroup writeback fixes (Tejun) - paride queue init fixes (zhengbin) - blk_set_runtime_active() cleanup (Stanley) - Block segment mapping optimizations (Bart) - lightnvm fixes (Hans/Minwoo/YueHaibing) - Various little fixes and cleanups * tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits) null_blk: format pr_* logs with pr_fmt null_blk: match the type of parameter nr_devices null_blk: do not fail the module load with zero devices block: also check RQF_STATS in blk_mq_need_time_stamp() block: make rq sector size accessible for block stats bfq: Fix bfq linkage error raid5: use bio_end_sector in r5_next_bio raid5: remove STRIPE_OPS_REQ_PENDING md: add feature flag MD_FEATURE_RAID0_LAYOUT md/raid0: avoid RAID0 data corruption due to layout confusion. raid5: don't set STRIPE_HANDLE to stripe which is in batch list raid5: don't increment read_errors on EILSEQ return nvmet: fix a wrong error status returned in error log page nvme: send discovery log page change events to userspace nvme: add uevent variables for controller devices nvme: enable aen regardless of the presence of I/O queues nvme-fabrics: allow discovery subsystems accept a kato nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery() nvme: Remove redundant assignment of cq vector nvme: Assign subsys instance from first ctrl ...
2019-09-18 07:57:47 +08:00
NVME_QUIRK_SHARED_TAGS = (1 << 13),
/*
* Don't change the value of the temperature threshold feature
*/
NVME_QUIRK_NO_TEMP_THRESH_CHANGE = (1 << 14),
/*
* The controller doesn't handle the Identify Namespace
* Identification Descriptor list subcommand despite claiming
* NVMe 1.3 compliance.
*/
NVME_QUIRK_NO_NS_DESC_LIST = (1 << 15),
};
/*
* Common request structure for NVMe passthrough. All drivers must have
* this structure as the first member of their request-private data.
*/
struct nvme_request {
struct nvme_command *cmd;
union nvme_result result;
u8 retries;
u8 flags;
u16 status;
struct nvme_ctrl *ctrl;
};
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
/*
* Mark a bio as coming in through the mpath node.
*/
#define REQ_NVME_MPATH REQ_DRV
enum {
NVME_REQ_CANCELLED = (1 << 0),
nvme: expand nvmf_check_if_ready checks The nvmf_check_if_ready() checks that were added are very simplistic. As such, the routine allows a lot of cases to fail ios during windows of reset or re-connection. In cases where there are not multi-path options present, the error goes back to the callee - the filesystem or application. Not good. The common routine was rewritten and calling syntax slightly expanded so that per-transport is_ready routines don't need to be present. The transports now call the routine directly. The routine is now a fabrics routine rather than an inline function. The routine now looks at controller state to decide the action to take. Some states mandate io failure. Others define the condition where a command can be accepted. When the decision is unclear, a generic queue-or-reject check is made to look for failfast or multipath ios and only fails the io if it is so marked. Otherwise, the io will be queued and wait for the controller state to resolve. Admin commands issued via ioctl share a live admin queue with commands from the transport for controller init. The ioctls could be intermixed with the initialization commands. It's possible for the ioctl cmd to be issued prior to the controller being enabled. To block this, the ioctl admin commands need to be distinguished from admin commands used for controller init. Added a USERCMD nvme_req(req)->rq_flags bit to reflect this division and set it on ioctls requests. As the nvmf_check_if_ready() routine is called prior to nvme_setup_cmd(), ensure that commands allocated by the ioctl path (actually anything in core.c) preps the nvme_req(req) before starting the io. This will preserve the USERCMD flag during execution and/or retry. Signed-off-by: James Smart <james.smart@broadcom.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.e> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-04-12 23:16:15 +08:00
NVME_REQ_USERCMD = (1 << 1),
};
static inline struct nvme_request *nvme_req(struct request *req)
{
return blk_mq_rq_to_pdu(req);
}
static inline u16 nvme_req_qid(struct request *req)
{
if (!req->q->queuedata)
return 0;
return req->mq_hctx->queue_num + 1;
}
/* The below value is the specific amount of delay needed before checking
* readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
* NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
* found empirically.
*/
#define NVME_QUIRK_DELAY_AMOUNT 2300
/*
* enum nvme_ctrl_state: Controller state
*
* @NVME_CTRL_NEW: New controller just allocated, initial state
* @NVME_CTRL_LIVE: Controller is connected and I/O capable
* @NVME_CTRL_RESETTING: Controller is resetting (or scheduled reset)
* @NVME_CTRL_CONNECTING: Controller is disconnected, now connecting the
* transport
* @NVME_CTRL_DELETING: Controller is deleting (or scheduled deletion)
nvme: fix deadlock in disconnect during scan_work and/or ana_work A deadlock happens in the following scenario with multipath: 1) scan_work(nvme0) detects a new nsid while nvme0 is an optimized path to it, path nvme1 happens to be inaccessible. 2) Before scan_work is complete nvme0 disconnect is initiated nvme_delete_ctrl_sync() sets nvme0 state to NVME_CTRL_DELETING 3) scan_work(1) attempts to submit IO, but nvme_path_is_optimized() observes nvme0 is not LIVE. Since nvme1 is a possible path IO is requeued and scan_work hangs. -- Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: efi_partition+0x1e6/0x708 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_set_ns_ana_state+0x1e/0x30 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: nvme_mpath_add_disk+0x47/0x90 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140 -- 4) Delete also hangs in flush_work(ctrl->scan_work) from nvme_remove_namespaces(). Similiarly a deadlock with ana_work may happen: if ana_work has started and calls nvme_mpath_set_live and device_add_disk, it will trigger I/O. When we trigger disconnect I/O will block because our accessible (optimized) path is disconnecting, but the alternate path is inaccessible, so I/O blocks. Then disconnect tries to flush the ana_work and hangs. [ 605.550896] Workqueue: nvme-wq nvme_ana_work [nvme_core] [ 605.552087] Call Trace: [ 605.552683] __schedule+0x2b9/0x6c0 [ 605.553507] schedule+0x42/0xb0 [ 605.554201] io_schedule+0x16/0x40 [ 605.555012] do_read_cache_page+0x438/0x830 [ 605.556925] read_cache_page+0x12/0x20 [ 605.557757] read_dev_sector+0x27/0xc0 [ 605.558587] amiga_partition+0x4d/0x4c5 [ 605.561278] check_partition+0x154/0x244 [ 605.562138] rescan_partitions+0xae/0x280 [ 605.563076] __blkdev_get+0x40f/0x560 [ 605.563830] blkdev_get+0x3d/0x140 [ 605.564500] __device_add_disk+0x388/0x480 [ 605.565316] device_add_disk+0x13/0x20 [ 605.566070] nvme_mpath_set_live+0x5e/0x130 [nvme_core] [ 605.567114] nvme_update_ns_ana_state+0x2c/0x30 [nvme_core] [ 605.568197] nvme_update_ana_state+0xca/0xe0 [nvme_core] [ 605.569360] nvme_parse_ana_log+0xa1/0x180 [nvme_core] [ 605.571385] nvme_read_ana_log+0x76/0x100 [nvme_core] [ 605.572376] nvme_ana_work+0x15/0x20 [nvme_core] [ 605.573330] process_one_work+0x1db/0x380 [ 605.574144] worker_thread+0x4d/0x400 [ 605.574896] kthread+0x104/0x140 [ 605.577205] ret_from_fork+0x35/0x40 [ 605.577955] INFO: task nvme:14044 blocked for more than 120 seconds. [ 605.579239] Tainted: G OE 5.3.5-050305-generic #201910071830 [ 605.580712] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 605.582320] nvme D 0 14044 14043 0x00000000 [ 605.583424] Call Trace: [ 605.583935] __schedule+0x2b9/0x6c0 [ 605.584625] schedule+0x42/0xb0 [ 605.585290] schedule_timeout+0x203/0x2f0 [ 605.588493] wait_for_completion+0xb1/0x120 [ 605.590066] __flush_work+0x123/0x1d0 [ 605.591758] __cancel_work_timer+0x10e/0x190 [ 605.593542] cancel_work_sync+0x10/0x20 [ 605.594347] nvme_mpath_stop+0x2f/0x40 [nvme_core] [ 605.595328] nvme_stop_ctrl+0x12/0x50 [nvme_core] [ 605.596262] nvme_do_delete_ctrl+0x3f/0x90 [nvme_core] [ 605.597333] nvme_sysfs_delete+0x5c/0x70 [nvme_core] [ 605.598320] dev_attr_store+0x17/0x30 Fix this by introducing a new state: NVME_CTRL_DELETE_NOIO, which will indicate the phase of controller deletion where I/O cannot be allowed to access the namespace. NVME_CTRL_DELETING still allows mpath I/O to be issued to the bottom device, and only after we flush the ana_work and scan_work (after nvme_stop_ctrl and nvme_prep_remove_namespaces) we change the state to NVME_CTRL_DELETING_NOIO. Also we prevent ana_work from re-firing by aborting early if we are not LIVE, so we should be safe here. In addition, change the transport drivers to follow the updated state machine. Fixes: 0d0b660f214d ("nvme: add ANA support") Reported-by: Anton Eidelman <anton@lightbitslabs.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de>
2020-07-23 07:32:19 +08:00
* @NVME_CTRL_DELETING_NOIO: Controller is deleting and I/O is not
* disabled/failed immediately. This state comes
* after all async event processing took place and
* before ns removal and the controller deletion
* progress
* @NVME_CTRL_DEAD: Controller is non-present/unresponsive during
* shutdown or removal. In this case we forcibly
* kill all inflight I/O as they have no chance to
* complete
*/
enum nvme_ctrl_state {
NVME_CTRL_NEW,
NVME_CTRL_LIVE,
NVME_CTRL_RESETTING,
NVME_CTRL_CONNECTING,
NVME_CTRL_DELETING,
nvme: fix deadlock in disconnect during scan_work and/or ana_work A deadlock happens in the following scenario with multipath: 1) scan_work(nvme0) detects a new nsid while nvme0 is an optimized path to it, path nvme1 happens to be inaccessible. 2) Before scan_work is complete nvme0 disconnect is initiated nvme_delete_ctrl_sync() sets nvme0 state to NVME_CTRL_DELETING 3) scan_work(1) attempts to submit IO, but nvme_path_is_optimized() observes nvme0 is not LIVE. Since nvme1 is a possible path IO is requeued and scan_work hangs. -- Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: efi_partition+0x1e6/0x708 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_set_ns_ana_state+0x1e/0x30 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: nvme_mpath_add_disk+0x47/0x90 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: nvme_scan_work+0x24f/0x380 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x249/0x400 kernel: kthread+0x104/0x140 -- 4) Delete also hangs in flush_work(ctrl->scan_work) from nvme_remove_namespaces(). Similiarly a deadlock with ana_work may happen: if ana_work has started and calls nvme_mpath_set_live and device_add_disk, it will trigger I/O. When we trigger disconnect I/O will block because our accessible (optimized) path is disconnecting, but the alternate path is inaccessible, so I/O blocks. Then disconnect tries to flush the ana_work and hangs. [ 605.550896] Workqueue: nvme-wq nvme_ana_work [nvme_core] [ 605.552087] Call Trace: [ 605.552683] __schedule+0x2b9/0x6c0 [ 605.553507] schedule+0x42/0xb0 [ 605.554201] io_schedule+0x16/0x40 [ 605.555012] do_read_cache_page+0x438/0x830 [ 605.556925] read_cache_page+0x12/0x20 [ 605.557757] read_dev_sector+0x27/0xc0 [ 605.558587] amiga_partition+0x4d/0x4c5 [ 605.561278] check_partition+0x154/0x244 [ 605.562138] rescan_partitions+0xae/0x280 [ 605.563076] __blkdev_get+0x40f/0x560 [ 605.563830] blkdev_get+0x3d/0x140 [ 605.564500] __device_add_disk+0x388/0x480 [ 605.565316] device_add_disk+0x13/0x20 [ 605.566070] nvme_mpath_set_live+0x5e/0x130 [nvme_core] [ 605.567114] nvme_update_ns_ana_state+0x2c/0x30 [nvme_core] [ 605.568197] nvme_update_ana_state+0xca/0xe0 [nvme_core] [ 605.569360] nvme_parse_ana_log+0xa1/0x180 [nvme_core] [ 605.571385] nvme_read_ana_log+0x76/0x100 [nvme_core] [ 605.572376] nvme_ana_work+0x15/0x20 [nvme_core] [ 605.573330] process_one_work+0x1db/0x380 [ 605.574144] worker_thread+0x4d/0x400 [ 605.574896] kthread+0x104/0x140 [ 605.577205] ret_from_fork+0x35/0x40 [ 605.577955] INFO: task nvme:14044 blocked for more than 120 seconds. [ 605.579239] Tainted: G OE 5.3.5-050305-generic #201910071830 [ 605.580712] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 605.582320] nvme D 0 14044 14043 0x00000000 [ 605.583424] Call Trace: [ 605.583935] __schedule+0x2b9/0x6c0 [ 605.584625] schedule+0x42/0xb0 [ 605.585290] schedule_timeout+0x203/0x2f0 [ 605.588493] wait_for_completion+0xb1/0x120 [ 605.590066] __flush_work+0x123/0x1d0 [ 605.591758] __cancel_work_timer+0x10e/0x190 [ 605.593542] cancel_work_sync+0x10/0x20 [ 605.594347] nvme_mpath_stop+0x2f/0x40 [nvme_core] [ 605.595328] nvme_stop_ctrl+0x12/0x50 [nvme_core] [ 605.596262] nvme_do_delete_ctrl+0x3f/0x90 [nvme_core] [ 605.597333] nvme_sysfs_delete+0x5c/0x70 [nvme_core] [ 605.598320] dev_attr_store+0x17/0x30 Fix this by introducing a new state: NVME_CTRL_DELETE_NOIO, which will indicate the phase of controller deletion where I/O cannot be allowed to access the namespace. NVME_CTRL_DELETING still allows mpath I/O to be issued to the bottom device, and only after we flush the ana_work and scan_work (after nvme_stop_ctrl and nvme_prep_remove_namespaces) we change the state to NVME_CTRL_DELETING_NOIO. Also we prevent ana_work from re-firing by aborting early if we are not LIVE, so we should be safe here. In addition, change the transport drivers to follow the updated state machine. Fixes: 0d0b660f214d ("nvme: add ANA support") Reported-by: Anton Eidelman <anton@lightbitslabs.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de>
2020-07-23 07:32:19 +08:00
NVME_CTRL_DELETING_NOIO,
NVME_CTRL_DEAD,
};
struct nvme_fault_inject {
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
struct fault_attr attr;
struct dentry *parent;
bool dont_retry; /* DNR, do not retry */
u16 status; /* status code */
#endif
};
struct nvme_ctrl {
bool comp_seen;
enum nvme_ctrl_state state;
bool identified;
spinlock_t lock;
struct mutex scan_lock;
const struct nvme_ctrl_ops *ops;
struct request_queue *admin_q;
struct request_queue *connect_q;
struct request_queue *fabrics_q;
struct device *dev;
int instance;
int numa_node;
struct blk_mq_tag_set *tagset;
struct blk_mq_tag_set *admin_tagset;
struct list_head namespaces;
struct rw_semaphore namespaces_rwsem;
struct device ctrl_device;
struct device *device; /* char device */
#ifdef CONFIG_NVME_HWMON
struct device *hwmon_device;
#endif
struct cdev cdev;
struct work_struct reset_work;
struct work_struct delete_work;
wait_queue_head_t state_wq;
struct nvme_subsystem *subsys;
struct list_head subsys_entry;
struct opal_dev *opal_dev;
char name[12];
u16 cntlid;
u32 ctrl_config;
u16 mtfa;
u32 queue_count;
u64 cap;
u32 max_hw_sectors;
u32 max_segments;
u32 max_integrity_segments;
#ifdef CONFIG_BLK_DEV_ZONED
u32 max_zone_append;
#endif
u16 crdt[3];
u16 oncs;
u16 oacs;
u16 nssa;
u16 nr_streams;
u16 sqsize;
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
u32 max_namespaces;
atomic_t abort_limit;
u8 vwc;
u32 vs;
u32 sgls;
u16 kas;
nvme: Enable autonomous power state transitions NVMe devices can advertise multiple power states. These states can be either "operational" (the device is fully functional but possibly slow) or "non-operational" (the device is asleep until woken up). Some devices can automatically enter a non-operational state when idle for a specified amount of time and then automatically wake back up when needed. The hardware configuration is a table. For each state, an entry in the table indicates the next deeper non-operational state, if any, to autonomously transition to and the idle time required before transitioning. This patch teaches the driver to program APST so that each successive non-operational state will be entered after an idle time equal to 100% of the total latency (entry plus exit) associated with that state. The maximum acceptable latency is controlled using dev_pm_qos (e.g. power/pm_qos_latency_tolerance_us in sysfs); non-operational states with total latency greater than this value will not be used. As a special case, setting the latency tolerance to 0 will disable APST entirely. On hardware without APST support, the sysfs file will not be exposed. The latency tolerance for newly-probed devices is set by the module parameter nvme_core.default_ps_max_latency_us. In theory, the device can expose "default" APST table, but this doesn't seem to function correctly on my device (Samsung 950), nor does it seem particularly useful. There is also an optional mechanism by which a configuration can be "saved" so it will be automatically loaded on reset. This can be configured from userspace, but it doesn't seem useful to support in the driver. On my laptop, enabling APST seems to save nearly 1W. The hardware tables can be decoded in userspace with nvme-cli. 'nvme id-ctrl /dev/nvmeN' will show the power state table and 'nvme get-feature -f 0x0c -H /dev/nvme0' will show the current APST configuration. This feature is quirked off on a known-buggy Samsung device. Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-02-08 02:08:45 +08:00
u8 npss;
u8 apsta;
u16 wctemp;
u16 cctemp;
u32 oaes;
u32 aen_result;
u32 ctratt;
unsigned int shutdown_timeout;
unsigned int kato;
bool subsystem;
unsigned long quirks;
nvme: Enable autonomous power state transitions NVMe devices can advertise multiple power states. These states can be either "operational" (the device is fully functional but possibly slow) or "non-operational" (the device is asleep until woken up). Some devices can automatically enter a non-operational state when idle for a specified amount of time and then automatically wake back up when needed. The hardware configuration is a table. For each state, an entry in the table indicates the next deeper non-operational state, if any, to autonomously transition to and the idle time required before transitioning. This patch teaches the driver to program APST so that each successive non-operational state will be entered after an idle time equal to 100% of the total latency (entry plus exit) associated with that state. The maximum acceptable latency is controlled using dev_pm_qos (e.g. power/pm_qos_latency_tolerance_us in sysfs); non-operational states with total latency greater than this value will not be used. As a special case, setting the latency tolerance to 0 will disable APST entirely. On hardware without APST support, the sysfs file will not be exposed. The latency tolerance for newly-probed devices is set by the module parameter nvme_core.default_ps_max_latency_us. In theory, the device can expose "default" APST table, but this doesn't seem to function correctly on my device (Samsung 950), nor does it seem particularly useful. There is also an optional mechanism by which a configuration can be "saved" so it will be automatically loaded on reset. This can be configured from userspace, but it doesn't seem useful to support in the driver. On my laptop, enabling APST seems to save nearly 1W. The hardware tables can be decoded in userspace with nvme-cli. 'nvme id-ctrl /dev/nvmeN' will show the power state table and 'nvme get-feature -f 0x0c -H /dev/nvme0' will show the current APST configuration. This feature is quirked off on a known-buggy Samsung device. Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-02-08 02:08:45 +08:00
struct nvme_id_power_state psd[32];
struct nvme_effects_log *effects;
struct xarray cels;
struct work_struct scan_work;
struct work_struct async_event_work;
struct delayed_work ka_work;
struct delayed_work failfast_work;
struct nvme_command ka_cmd;
struct work_struct fw_act_work;
unsigned long events;
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
#ifdef CONFIG_NVME_MULTIPATH
/* asymmetric namespace access: */
u8 anacap;
u8 anatt;
u32 anagrpmax;
u32 nanagrpid;
struct mutex ana_lock;
struct nvme_ana_rsp_hdr *ana_log_buf;
size_t ana_log_size;
struct timer_list anatt_timer;
struct work_struct ana_work;
#endif
nvme: Enable autonomous power state transitions NVMe devices can advertise multiple power states. These states can be either "operational" (the device is fully functional but possibly slow) or "non-operational" (the device is asleep until woken up). Some devices can automatically enter a non-operational state when idle for a specified amount of time and then automatically wake back up when needed. The hardware configuration is a table. For each state, an entry in the table indicates the next deeper non-operational state, if any, to autonomously transition to and the idle time required before transitioning. This patch teaches the driver to program APST so that each successive non-operational state will be entered after an idle time equal to 100% of the total latency (entry plus exit) associated with that state. The maximum acceptable latency is controlled using dev_pm_qos (e.g. power/pm_qos_latency_tolerance_us in sysfs); non-operational states with total latency greater than this value will not be used. As a special case, setting the latency tolerance to 0 will disable APST entirely. On hardware without APST support, the sysfs file will not be exposed. The latency tolerance for newly-probed devices is set by the module parameter nvme_core.default_ps_max_latency_us. In theory, the device can expose "default" APST table, but this doesn't seem to function correctly on my device (Samsung 950), nor does it seem particularly useful. There is also an optional mechanism by which a configuration can be "saved" so it will be automatically loaded on reset. This can be configured from userspace, but it doesn't seem useful to support in the driver. On my laptop, enabling APST seems to save nearly 1W. The hardware tables can be decoded in userspace with nvme-cli. 'nvme id-ctrl /dev/nvmeN' will show the power state table and 'nvme get-feature -f 0x0c -H /dev/nvme0' will show the current APST configuration. This feature is quirked off on a known-buggy Samsung device. Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-02-08 02:08:45 +08:00
/* Power saving configuration */
u64 ps_max_latency_us;
bool apst_enabled;
nvme: Enable autonomous power state transitions NVMe devices can advertise multiple power states. These states can be either "operational" (the device is fully functional but possibly slow) or "non-operational" (the device is asleep until woken up). Some devices can automatically enter a non-operational state when idle for a specified amount of time and then automatically wake back up when needed. The hardware configuration is a table. For each state, an entry in the table indicates the next deeper non-operational state, if any, to autonomously transition to and the idle time required before transitioning. This patch teaches the driver to program APST so that each successive non-operational state will be entered after an idle time equal to 100% of the total latency (entry plus exit) associated with that state. The maximum acceptable latency is controlled using dev_pm_qos (e.g. power/pm_qos_latency_tolerance_us in sysfs); non-operational states with total latency greater than this value will not be used. As a special case, setting the latency tolerance to 0 will disable APST entirely. On hardware without APST support, the sysfs file will not be exposed. The latency tolerance for newly-probed devices is set by the module parameter nvme_core.default_ps_max_latency_us. In theory, the device can expose "default" APST table, but this doesn't seem to function correctly on my device (Samsung 950), nor does it seem particularly useful. There is also an optional mechanism by which a configuration can be "saved" so it will be automatically loaded on reset. This can be configured from userspace, but it doesn't seem useful to support in the driver. On my laptop, enabling APST seems to save nearly 1W. The hardware tables can be decoded in userspace with nvme-cli. 'nvme id-ctrl /dev/nvmeN' will show the power state table and 'nvme get-feature -f 0x0c -H /dev/nvme0' will show the current APST configuration. This feature is quirked off on a known-buggy Samsung device. Signed-off-by: Andy Lutomirski <luto@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-02-08 02:08:45 +08:00
/* PCIe only: */
u32 hmpre;
u32 hmmin;
u32 hmminds;
u16 hmmaxd;
/* Fabrics only */
u32 ioccsz;
u32 iorcsz;
u16 icdoff;
u16 maxcmd;
int nr_reconnects;
unsigned long flags;
#define NVME_CTRL_FAILFAST_EXPIRED 0
struct nvmf_ctrl_options *opts;
struct page *discard_page;
unsigned long discard_page_busy;
struct nvme_fault_inject fault_inject;
};
enum nvme_iopolicy {
NVME_IOPOLICY_NUMA,
NVME_IOPOLICY_RR,
};
struct nvme_subsystem {
int instance;
struct device dev;
/*
* Because we unregister the device on the last put we need
* a separate refcount.
*/
struct kref ref;
struct list_head entry;
struct mutex lock;
struct list_head ctrls;
struct list_head nsheads;
char subnqn[NVMF_NQN_SIZE];
char serial[20];
char model[40];
char firmware_rev[8];
u8 cmic;
u16 vendor_id;
u16 awupf; /* 0's based awupf value. */
struct ida ns_ida;
#ifdef CONFIG_NVME_MULTIPATH
enum nvme_iopolicy iopolicy;
#endif
};
/*
* Container structure for uniqueue namespace identifiers.
*/
struct nvme_ns_ids {
u8 eui64[8];
u8 nguid[16];
uuid_t uuid;
u8 csi;
};
/*
* Anchor structure for namespaces. There is one for each namespace in a
* NVMe subsystem that any of our controllers can see, and the namespace
* structure for each controller is chained of it. For private namespaces
* there is a 1:1 relation to our namespace structures, that is ->list
* only ever has a single entry for private namespaces.
*/
struct nvme_ns_head {
struct list_head list;
struct srcu_struct srcu;
struct nvme_subsystem *subsys;
unsigned ns_id;
struct nvme_ns_ids ids;
struct list_head entry;
struct kref ref;
bool shared;
int instance;
struct nvme_effects_log *effects;
#ifdef CONFIG_NVME_MULTIPATH
struct gendisk *disk;
struct bio_list requeue_list;
spinlock_t requeue_lock;
struct work_struct requeue_work;
struct mutex lock;
nvme-multipath: fix deadlock due to head->lock In the following scenario scan_work and ana_work will deadlock: When scan_work calls nvme_mpath_add_disk() this holds ana_lock and invokes nvme_parse_ana_log(), which may issue IO in device_add_disk() and hang waiting for an accessible path. While nvme_mpath_set_live() only called when nvme_state_is_live(), a transition may cause NVME_SC_ANA_TRANSITION and requeue the IO. Since nvme_mpath_set_live() holds ns->head->lock, an ana_work on ANY ctrl will not be able to complete nvme_mpath_set_live() on the same ns->head, which is required in order to update the new accessible path and remove NVME_NS_ANA_PENDING.. Therefore IO never completes: deadlock [1]. Fix: Move device_add_disk out of the head->lock and protect it with an atomic test_and_set for a new NVME_NS_HEAD_HAS_DISK bit. [1]: kernel: INFO: task kworker/u8:2:160 blocked for more than 120 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u8:2 D 0 160 2 0x80004000 kernel: Workqueue: nvme-wq nvme_ana_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: schedule_preempt_disabled+0xe/0x10 kernel: __mutex_lock.isra.0+0x182/0x4f0 kernel: __mutex_lock_slowpath+0x13/0x20 kernel: mutex_lock+0x2e/0x40 kernel: nvme_update_ns_ana_state+0x22/0x60 [nvme_core] kernel: nvme_update_ana_state+0xca/0xe0 [nvme_core] kernel: nvme_parse_ana_log+0xa1/0x180 [nvme_core] kernel: nvme_read_ana_log+0x76/0x100 [nvme_core] kernel: nvme_ana_work+0x15/0x20 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x4d/0x400 kernel: kthread+0x104/0x140 kernel: ret_from_fork+0x35/0x40 kernel: INFO: task kworker/u8:4:439 blocked for more than 120 seconds. kernel: Tainted: G OE 5.3.5-050305-generic #201910071830 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kernel: kworker/u8:4 D 0 439 2 0x80004000 kernel: Workqueue: nvme-wq nvme_scan_work [nvme_core] kernel: Call Trace: kernel: __schedule+0x2b9/0x6c0 kernel: schedule+0x42/0xb0 kernel: io_schedule+0x16/0x40 kernel: do_read_cache_page+0x438/0x830 kernel: read_cache_page+0x12/0x20 kernel: read_dev_sector+0x27/0xc0 kernel: read_lba+0xc1/0x220 kernel: efi_partition+0x1e6/0x708 kernel: check_partition+0x154/0x244 kernel: rescan_partitions+0xae/0x280 kernel: __blkdev_get+0x40f/0x560 kernel: blkdev_get+0x3d/0x140 kernel: __device_add_disk+0x388/0x480 kernel: device_add_disk+0x13/0x20 kernel: nvme_mpath_set_live+0x119/0x140 [nvme_core] kernel: nvme_update_ns_ana_state+0x5c/0x60 [nvme_core] kernel: nvme_mpath_add_disk+0xbe/0x100 [nvme_core] kernel: nvme_validate_ns+0x396/0x940 [nvme_core] kernel: nvme_scan_work+0x256/0x390 [nvme_core] kernel: process_one_work+0x1db/0x380 kernel: worker_thread+0x4d/0x400 kernel: kthread+0x104/0x140 kernel: ret_from_fork+0x35/0x40 Fixes: 0d0b660f214d ("nvme: add ANA support") Signed-off-by: Anton Eidelman <anton@lightbitslabs.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Christoph Hellwig <hch@lst.de>
2020-06-24 16:53:11 +08:00
unsigned long flags;
#define NVME_NSHEAD_DISK_LIVE 0
struct nvme_ns __rcu *current_path[];
#endif
};
enum nvme_ns_features {
NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
};
struct nvme_ns {
struct list_head list;
struct nvme_ctrl *ctrl;
struct request_queue *queue;
struct gendisk *disk;
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
#ifdef CONFIG_NVME_MULTIPATH
enum nvme_ana_state ana_state;
u32 ana_grpid;
#endif
struct list_head siblings;
struct nvm_dev *ndev;
struct kref kref;
struct nvme_ns_head *head;
int lba_shift;
u16 ms;
u16 sgs;
u32 sws;
u8 pi_type;
#ifdef CONFIG_BLK_DEV_ZONED
u64 zsze;
#endif
unsigned long features;
unsigned long flags;
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
#define NVME_NS_REMOVING 0
#define NVME_NS_DEAD 1
#define NVME_NS_ANA_PENDING 2
#define NVME_NS_FORCE_RO 3
nvme: Add fault injection feature Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. This patch uses the framework to add error injection to NVMe driver. The fault injection source code is stored in a separate file and only linked if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected. Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no retry will be injected into the nvme_end_request. Users can change the default status code and no retry flag via debufs. Following example shows how to enable and inject an error. For more examples, refer to Documentation/fault-injection/nvme-fault-injection.txt How to enable nvme fault injection: First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config, recompile the kernel. After booting up the kernel, do the following. How to inject an error: mount /dev/nvme0n1 /mnt echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability cp a.file /mnt Expected Result: cp: cannot stat ‘/mnt/a.file’: Input/output error Message from dmesg: FAULT_INJECTION: forcing a failure. name fault_inject, interval 1, probability 100, space 0, times 1 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: <IRQ> dump_stack+0x5c/0x7d should_fail+0x148/0x170 nvme_should_fail+0x2f/0x50 [nvme_core] nvme_process_cq+0xe7/0x1d0 [nvme] nvme_irq+0x1e/0x40 [nvme] __handle_irq_event_percpu+0x3a/0x190 handle_irq_event_percpu+0x30/0x70 handle_irq_event+0x36/0x60 handle_fasteoi_irq+0x78/0x120 handle_irq+0xa7/0x130 ? tick_irq_enter+0xa8/0xc0 do_IRQ+0x43/0xc0 common_interrupt+0xa2/0xa2 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480 R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x4/0x4 default_idle+0x18/0xf0 do_idle+0x150/0x1d0 cpu_startup_entry+0x6f/0x80 start_kernel+0x4c4/0x4e4 ? set_init_arg+0x55/0x55 secondary_startup_64+0xa5/0xb0 print_req_error: I/O error, dev nvme0n1, sector 9240 EXT4-fs error (device nvme0n1): ext4_find_entry:1436: inode #2: comm cp: reading directory lblock 0 Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-09 02:38:29 +08:00
struct nvme_fault_inject fault_inject;
};
/* NVMe ns supports metadata actions by the controller (generate/strip) */
static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
{
return ns->pi_type && ns->ms == sizeof(struct t10_pi_tuple);
}
struct nvme_ctrl_ops {
const char *name;
struct module *module;
unsigned int flags;
#define NVME_F_FABRICS (1 << 0)
#define NVME_F_METADATA_SUPPORTED (1 << 1)
#define NVME_F_PCI_P2PDMA (1 << 2)
int (*reg_read32)(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val);
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
void (*free_ctrl)(struct nvme_ctrl *ctrl);
void (*submit_async_event)(struct nvme_ctrl *ctrl);
void (*delete_ctrl)(struct nvme_ctrl *ctrl);
int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size);
};
nvme: Add fault injection feature Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. This patch uses the framework to add error injection to NVMe driver. The fault injection source code is stored in a separate file and only linked if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected. Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no retry will be injected into the nvme_end_request. Users can change the default status code and no retry flag via debufs. Following example shows how to enable and inject an error. For more examples, refer to Documentation/fault-injection/nvme-fault-injection.txt How to enable nvme fault injection: First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config, recompile the kernel. After booting up the kernel, do the following. How to inject an error: mount /dev/nvme0n1 /mnt echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability cp a.file /mnt Expected Result: cp: cannot stat ‘/mnt/a.file’: Input/output error Message from dmesg: FAULT_INJECTION: forcing a failure. name fault_inject, interval 1, probability 100, space 0, times 1 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: <IRQ> dump_stack+0x5c/0x7d should_fail+0x148/0x170 nvme_should_fail+0x2f/0x50 [nvme_core] nvme_process_cq+0xe7/0x1d0 [nvme] nvme_irq+0x1e/0x40 [nvme] __handle_irq_event_percpu+0x3a/0x190 handle_irq_event_percpu+0x30/0x70 handle_irq_event+0x36/0x60 handle_fasteoi_irq+0x78/0x120 handle_irq+0xa7/0x130 ? tick_irq_enter+0xa8/0xc0 do_IRQ+0x43/0xc0 common_interrupt+0xa2/0xa2 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480 R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x4/0x4 default_idle+0x18/0xf0 do_idle+0x150/0x1d0 cpu_startup_entry+0x6f/0x80 start_kernel+0x4c4/0x4e4 ? set_init_arg+0x55/0x55 secondary_startup_64+0xa5/0xb0 print_req_error: I/O error, dev nvme0n1, sector 9240 EXT4-fs error (device nvme0n1): ext4_find_entry:1436: inode #2: comm cp: reading directory lblock 0 Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-09 02:38:29 +08:00
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
const char *dev_name);
void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject);
nvme: Add fault injection feature Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. This patch uses the framework to add error injection to NVMe driver. The fault injection source code is stored in a separate file and only linked if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected. Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no retry will be injected into the nvme_end_request. Users can change the default status code and no retry flag via debufs. Following example shows how to enable and inject an error. For more examples, refer to Documentation/fault-injection/nvme-fault-injection.txt How to enable nvme fault injection: First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config, recompile the kernel. After booting up the kernel, do the following. How to inject an error: mount /dev/nvme0n1 /mnt echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability cp a.file /mnt Expected Result: cp: cannot stat ‘/mnt/a.file’: Input/output error Message from dmesg: FAULT_INJECTION: forcing a failure. name fault_inject, interval 1, probability 100, space 0, times 1 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: <IRQ> dump_stack+0x5c/0x7d should_fail+0x148/0x170 nvme_should_fail+0x2f/0x50 [nvme_core] nvme_process_cq+0xe7/0x1d0 [nvme] nvme_irq+0x1e/0x40 [nvme] __handle_irq_event_percpu+0x3a/0x190 handle_irq_event_percpu+0x30/0x70 handle_irq_event+0x36/0x60 handle_fasteoi_irq+0x78/0x120 handle_irq+0xa7/0x130 ? tick_irq_enter+0xa8/0xc0 do_IRQ+0x43/0xc0 common_interrupt+0xa2/0xa2 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480 R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x4/0x4 default_idle+0x18/0xf0 do_idle+0x150/0x1d0 cpu_startup_entry+0x6f/0x80 start_kernel+0x4c4/0x4e4 ? set_init_arg+0x55/0x55 secondary_startup_64+0xa5/0xb0 print_req_error: I/O error, dev nvme0n1, sector 9240 EXT4-fs error (device nvme0n1): ext4_find_entry:1436: inode #2: comm cp: reading directory lblock 0 Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-09 02:38:29 +08:00
void nvme_should_fail(struct request *req);
#else
static inline void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
const char *dev_name)
{
}
static inline void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inj)
{
}
nvme: Add fault injection feature Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. This patch uses the framework to add error injection to NVMe driver. The fault injection source code is stored in a separate file and only linked if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected. Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no retry will be injected into the nvme_end_request. Users can change the default status code and no retry flag via debufs. Following example shows how to enable and inject an error. For more examples, refer to Documentation/fault-injection/nvme-fault-injection.txt How to enable nvme fault injection: First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config, recompile the kernel. After booting up the kernel, do the following. How to inject an error: mount /dev/nvme0n1 /mnt echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability cp a.file /mnt Expected Result: cp: cannot stat ‘/mnt/a.file’: Input/output error Message from dmesg: FAULT_INJECTION: forcing a failure. name fault_inject, interval 1, probability 100, space 0, times 1 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: <IRQ> dump_stack+0x5c/0x7d should_fail+0x148/0x170 nvme_should_fail+0x2f/0x50 [nvme_core] nvme_process_cq+0xe7/0x1d0 [nvme] nvme_irq+0x1e/0x40 [nvme] __handle_irq_event_percpu+0x3a/0x190 handle_irq_event_percpu+0x30/0x70 handle_irq_event+0x36/0x60 handle_fasteoi_irq+0x78/0x120 handle_irq+0xa7/0x130 ? tick_irq_enter+0xa8/0xc0 do_IRQ+0x43/0xc0 common_interrupt+0xa2/0xa2 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480 R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x4/0x4 default_idle+0x18/0xf0 do_idle+0x150/0x1d0 cpu_startup_entry+0x6f/0x80 start_kernel+0x4c4/0x4e4 ? set_init_arg+0x55/0x55 secondary_startup_64+0xa5/0xb0 print_req_error: I/O error, dev nvme0n1, sector 9240 EXT4-fs error (device nvme0n1): ext4_find_entry:1436: inode #2: comm cp: reading directory lblock 0 Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-09 02:38:29 +08:00
static inline void nvme_should_fail(struct request *req) {}
#endif
static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl)
{
if (!ctrl->subsystem)
return -ENOTTY;
return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65);
}
/*
* Convert a 512B sector number to a device logical block number.
*/
static inline u64 nvme_sect_to_lba(struct nvme_ns *ns, sector_t sector)
{
return sector >> (ns->lba_shift - SECTOR_SHIFT);
}
/*
* Convert a device logical block number to a 512B sector number.
*/
static inline sector_t nvme_lba_to_sect(struct nvme_ns *ns, u64 lba)
{
return lba << (ns->lba_shift - SECTOR_SHIFT);
}
/*
* Convert byte length to nvme's 0-based num dwords
*/
static inline u32 nvme_bytes_to_numd(size_t len)
{
return (len >> 2) - 1;
}
static inline bool nvme_is_ana_error(u16 status)
{
switch (status & 0x7ff) {
case NVME_SC_ANA_TRANSITION:
case NVME_SC_ANA_INACCESSIBLE:
case NVME_SC_ANA_PERSISTENT_LOSS:
return true;
default:
return false;
}
}
static inline bool nvme_is_path_error(u16 status)
{
/* check for a status code type of 'path related status' */
return (status & 0x700) == 0x300;
}
/*
* Fill in the status and result information from the CQE, and then figure out
* if blk-mq will need to use IPI magic to complete the request, and if yes do
* so. If not let the caller complete the request without an indirect function
* call.
*/
static inline bool nvme_try_complete_req(struct request *req, __le16 status,
union nvme_result result)
{
struct nvme_request *rq = nvme_req(req);
rq->status = le16_to_cpu(status) >> 1;
rq->result = result;
nvme: Add fault injection feature Linux's fault injection framework provides a systematic way to support error injection via debugfs in the /sys/kernel/debug directory. This patch uses the framework to add error injection to NVMe driver. The fault injection source code is stored in a separate file and only linked if CONFIG_FAULT_INJECTION_DEBUG_FS kernel config is selected. Once the error injection is enabled, NVME_SC_INVALID_OPCODE with no retry will be injected into the nvme_end_request. Users can change the default status code and no retry flag via debufs. Following example shows how to enable and inject an error. For more examples, refer to Documentation/fault-injection/nvme-fault-injection.txt How to enable nvme fault injection: First, enable CONFIG_FAULT_INJECTION_DEBUG_FS kernel config, recompile the kernel. After booting up the kernel, do the following. How to inject an error: mount /dev/nvme0n1 /mnt echo 1 > /sys/kernel/debug/nvme0n1/fault_inject/times echo 100 > /sys/kernel/debug/nvme0n1/fault_inject/probability cp a.file /mnt Expected Result: cp: cannot stat ‘/mnt/a.file’: Input/output error Message from dmesg: FAULT_INJECTION: forcing a failure. name fault_inject, interval 1, probability 100, space 0, times 1 CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.15.0-rc8+ #2 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: <IRQ> dump_stack+0x5c/0x7d should_fail+0x148/0x170 nvme_should_fail+0x2f/0x50 [nvme_core] nvme_process_cq+0xe7/0x1d0 [nvme] nvme_irq+0x1e/0x40 [nvme] __handle_irq_event_percpu+0x3a/0x190 handle_irq_event_percpu+0x30/0x70 handle_irq_event+0x36/0x60 handle_fasteoi_irq+0x78/0x120 handle_irq+0xa7/0x130 ? tick_irq_enter+0xa8/0xc0 do_IRQ+0x43/0xc0 common_interrupt+0xa2/0xa2 </IRQ> RIP: 0010:native_safe_halt+0x2/0x10 RSP: 0018:ffffffff82003e90 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd RAX: ffffffff817a10c0 RBX: ffffffff82012480 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: 000000008e38ce64 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff82012480 R13: ffffffff82012480 R14: 0000000000000000 R15: 0000000000000000 ? __sched_text_end+0x4/0x4 default_idle+0x18/0xf0 do_idle+0x150/0x1d0 cpu_startup_entry+0x6f/0x80 start_kernel+0x4c4/0x4e4 ? set_init_arg+0x55/0x55 secondary_startup_64+0xa5/0xb0 print_req_error: I/O error, dev nvme0n1, sector 9240 EXT4-fs error (device nvme0n1): ext4_find_entry:1436: inode #2: comm cp: reading directory lblock 0 Signed-off-by: Thomas Tai <thomas.tai@oracle.com> Reviewed-by: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Signed-off-by: Karl Volz <karl.volz@oracle.com> Reviewed-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-09 02:38:29 +08:00
/* inject error when permitted by fault injection framework */
nvme_should_fail(req);
if (unlikely(blk_should_fake_timeout(req->q)))
return true;
return blk_mq_complete_request_remote(req);
}
static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl)
{
get_device(ctrl->device);
}
static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl)
{
put_device(ctrl->device);
}
static inline bool nvme_is_aen_req(u16 qid, __u16 command_id)
{
return !qid && command_id >= NVME_AQ_BLK_MQ_DEPTH;
}
void nvme_complete_rq(struct request *req);
blk_status_t nvme_host_path_error(struct request *req);
bool nvme_cancel_request(struct request *req, void *data, bool reserved);
void nvme_cancel_tagset(struct nvme_ctrl *ctrl);
void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state);
bool nvme_wait_reset(struct nvme_ctrl *ctrl);
int nvme_disable_ctrl(struct nvme_ctrl *ctrl);
int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
const struct nvme_ctrl_ops *ops, unsigned long quirks);
void nvme_uninit_ctrl(struct nvme_ctrl *ctrl);
void nvme_start_ctrl(struct nvme_ctrl *ctrl);
void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
int nvme_init_identify(struct nvme_ctrl *ctrl);
void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
bool send);
void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
volatile union nvme_result *res);
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_sync_queues(struct nvme_ctrl *ctrl);
void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
void nvme_unfreeze(struct nvme_ctrl *ctrl);
void nvme_wait_freeze(struct nvme_ctrl *ctrl);
int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
void nvme_start_freeze(struct nvme_ctrl *ctrl);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
nvme: split nvme_alloc_request() Right now nvme_alloc_request() allocates a request from block layer based on the value of the qid. When qid set to NVME_QID_ANY it used blk_mq_alloc_request() else blk_mq_alloc_request_hctx(). The function nvme_alloc_request() is called from different context, The only place where it uses non NVME_QID_ANY value is for fabrics connect commands :- nvme_submit_sync_cmd() NVME_QID_ANY nvme_features() NVME_QID_ANY nvme_sec_submit() NVME_QID_ANY nvmf_reg_read32() NVME_QID_ANY nvmf_reg_read64() NVME_QID_ANY nvmf_reg_write32() NVME_QID_ANY nvmf_connect_admin_queue() NVME_QID_ANY nvme_submit_user_cmd() NVME_QID_ANY nvme_alloc_request() nvme_keep_alive() NVME_QID_ANY nvme_alloc_request() nvme_timeout() NVME_QID_ANY nvme_alloc_request() nvme_delete_queue() NVME_QID_ANY nvme_alloc_request() nvmet_passthru_execute_cmd() NVME_QID_ANY nvme_alloc_request() nvmf_connect_io_queue() QID __nvme_submit_sync_cmd() nvme_alloc_request() With passthru nvme_alloc_request() now falls into the I/O fast path such that blk_mq_alloc_request_hctx() is never gets called and that adds additional branch check in fast path. Split the nvme_alloc_request() into nvme_alloc_request() and nvme_alloc_request_qid(). Replace each call of the nvme_alloc_request() with NVME_QID_ANY param with a call to newly added nvme_alloc_request() without NVME_QID_ANY. Replace a call to nvme_alloc_request() with QID param with a call to newly added nvme_alloc_request() and nvme_alloc_request_qid() based on the qid value set in the __nvme_submit_sync_cmd(). Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2020-11-10 10:24:00 +08:00
struct nvme_command *cmd, blk_mq_req_flags_t flags);
void nvme_cleanup_cmd(struct request *req);
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmd);
int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
void *buf, unsigned bufflen);
int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
union nvme_result *result, void *buffer, unsigned bufflen,
unsigned timeout, int qid, int at_head,
blk_mq_req_flags_t flags, bool poll);
int nvme_set_features(struct nvme_ctrl *dev, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen,
u32 *result);
int nvme_get_features(struct nvme_ctrl *dev, unsigned int fid,
unsigned int dword11, void *buffer, size_t buflen,
u32 *result);
int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
void *log, size_t size, u64 offset);
struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
struct nvme_ns_head **head, int *srcu_idx);
void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
extern const struct attribute_group *nvme_ns_id_attr_groups[];
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
extern const struct block_device_operations nvme_ns_head_ops;
#ifdef CONFIG_NVME_MULTIPATH
nvme: fix multipath crash when ANA is deactivated Fix a crash with multipath activated. It happends when ANA log page is larger than MDTS and because of that ANA is disabled. The driver then tries to access unallocated buffer when connecting to a nvme target. The signature is as follows: [ 300.433586] nvme nvme0: ANA log page size (8208) larger than MDTS (8192). [ 300.435387] nvme nvme0: disabling ANA support. [ 300.437835] nvme nvme0: creating 4 I/O queues. [ 300.459132] nvme nvme0: new ctrl: NQN "nqn.0.0.0", addr 10.91.0.1:8009 [ 300.464609] BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 [ 300.466342] #PF error: [normal kernel read fault] [ 300.467385] PGD 0 P4D 0 [ 300.467987] Oops: 0000 [#1] SMP PTI [ 300.468787] CPU: 3 PID: 50 Comm: kworker/u8:1 Not tainted 5.0.20kalray+ #4 [ 300.470264] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 300.471532] Workqueue: nvme-wq nvme_scan_work [nvme_core] [ 300.472724] RIP: 0010:nvme_parse_ana_log+0x21/0x140 [nvme_core] [ 300.474038] Code: 45 01 d2 d8 48 98 c3 66 90 0f 1f 44 00 00 41 57 41 56 41 55 41 54 55 53 48 89 fb 48 83 ec 08 48 8b af 20 0a 00 00 48 89 34 24 <66> 83 7d 08 00 0f 84 c6 00 00 00 44 8b 7d 14 49 89 d5 8b 55 10 48 [ 300.477374] RSP: 0018:ffffa50e80fd7cb8 EFLAGS: 00010296 [ 300.478334] RAX: 0000000000000001 RBX: ffff9130f1872258 RCX: 0000000000000000 [ 300.479784] RDX: ffffffffc06c4c30 RSI: ffff9130edad4280 RDI: ffff9130f1872258 [ 300.481488] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 [ 300.483203] R10: 0000000000000220 R11: 0000000000000040 R12: ffff9130f18722c0 [ 300.484928] R13: ffff9130f18722d0 R14: ffff9130edad4280 R15: ffff9130f18722c0 [ 300.486626] FS: 0000000000000000(0000) GS:ffff9130f7b80000(0000) knlGS:0000000000000000 [ 300.488538] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 300.489907] CR2: 0000000000000008 CR3: 00000002365e6000 CR4: 00000000000006e0 [ 300.491612] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 300.493303] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 300.494991] Call Trace: [ 300.495645] nvme_mpath_add_disk+0x5c/0xb0 [nvme_core] [ 300.496880] nvme_validate_ns+0x2ef/0x550 [nvme_core] [ 300.498105] ? nvme_identify_ctrl.isra.45+0x6a/0xb0 [nvme_core] [ 300.499539] nvme_scan_work+0x2b4/0x370 [nvme_core] [ 300.500717] ? __switch_to_asm+0x35/0x70 [ 300.501663] process_one_work+0x171/0x380 [ 300.502340] worker_thread+0x49/0x3f0 [ 300.503079] kthread+0xf8/0x130 [ 300.503795] ? max_active_store+0x80/0x80 [ 300.504690] ? kthread_bind+0x10/0x10 [ 300.505502] ret_from_fork+0x35/0x40 [ 300.506280] Modules linked in: nvme_tcp nvme_rdma rdma_cm iw_cm ib_cm ib_core nvme_fabrics nvme_core xt_physdev ip6table_raw ip6table_mangle ip6table_filter ip6_tables xt_comment iptable_nat nf_nat_ipv4 nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_CHECKSUM iptable_mangle iptable_filter veth ebtable_filter ebtable_nat ebtables iptable_raw vxlan ip6_udp_tunnel udp_tunnel sunrpc joydev pcspkr virtio_balloon br_netfilter bridge stp llc ip_tables xfs libcrc32c ata_generic pata_acpi virtio_net virtio_console net_failover virtio_blk failover ata_piix serio_raw libata virtio_pci virtio_ring virtio [ 300.514984] CR2: 0000000000000008 [ 300.515569] ---[ end trace faa2eefad7e7f218 ]--- [ 300.516354] RIP: 0010:nvme_parse_ana_log+0x21/0x140 [nvme_core] [ 300.517330] Code: 45 01 d2 d8 48 98 c3 66 90 0f 1f 44 00 00 41 57 41 56 41 55 41 54 55 53 48 89 fb 48 83 ec 08 48 8b af 20 0a 00 00 48 89 34 24 <66> 83 7d 08 00 0f 84 c6 00 00 00 44 8b 7d 14 49 89 d5 8b 55 10 48 [ 300.520353] RSP: 0018:ffffa50e80fd7cb8 EFLAGS: 00010296 [ 300.521229] RAX: 0000000000000001 RBX: ffff9130f1872258 RCX: 0000000000000000 [ 300.522399] RDX: ffffffffc06c4c30 RSI: ffff9130edad4280 RDI: ffff9130f1872258 [ 300.523560] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000044 [ 300.524734] R10: 0000000000000220 R11: 0000000000000040 R12: ffff9130f18722c0 [ 300.525915] R13: ffff9130f18722d0 R14: ffff9130edad4280 R15: ffff9130f18722c0 [ 300.527084] FS: 0000000000000000(0000) GS:ffff9130f7b80000(0000) knlGS:0000000000000000 [ 300.528396] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 300.529440] CR2: 0000000000000008 CR3: 00000002365e6000 CR4: 00000000000006e0 [ 300.530739] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 300.531989] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 300.533264] Kernel panic - not syncing: Fatal exception [ 300.534338] Kernel Offset: 0x17c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 300.536227] ---[ end Kernel panic - not syncing: Fatal exception ]--- Condition check refactoring from Christoph Hellwig. Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu> Tested-by: Jean-Baptiste Riaux <jbriaux@kalray.eu> Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-07-23 13:41:20 +08:00
static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
{
return ctrl->ana_log_buf != NULL;
}
nvme: fix a possible deadlock when passthru commands sent to a multipath device When the user issues a command with side effects, we will end up freezing the namespace request queue when updating disk info (and the same for the corresponding mpath disk node). However, we are not freezing the mpath node request queue, which means that mpath I/O can still come in and block on blk_queue_enter (called from nvme_ns_head_make_request -> direct_make_request). This is a deadlock, because blk_queue_enter will block until the inner namespace request queue is unfroze, but that process is blocked because the namespace revalidation is trying to update the mpath disk info and freeze its request queue (which will never complete because of the I/O that is blocked on blk_queue_enter). Fix this by freezing all the subsystem nsheads request queues before executing the passthru command. Given that these commands are infrequent we should not worry about this temporary I/O freeze to keep things sane. Here is the matching hang traces: -- [ 374.465002] INFO: task systemd-udevd:17994 blocked for more than 122 seconds. [ 374.472975] Not tainted 5.2.0-rc3-mpdebug+ #42 [ 374.478522] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 374.487274] systemd-udevd D 0 17994 1 0x00000000 [ 374.493407] Call Trace: [ 374.496145] __schedule+0x2ef/0x620 [ 374.500047] schedule+0x38/0xa0 [ 374.503569] blk_queue_enter+0x139/0x220 [ 374.507959] ? remove_wait_queue+0x60/0x60 [ 374.512540] direct_make_request+0x60/0x130 [ 374.517219] nvme_ns_head_make_request+0x11d/0x420 [nvme_core] [ 374.523740] ? generic_make_request_checks+0x307/0x6f0 [ 374.529484] generic_make_request+0x10d/0x2e0 [ 374.534356] submit_bio+0x75/0x140 [ 374.538163] ? guard_bio_eod+0x32/0xe0 [ 374.542361] submit_bh_wbc+0x171/0x1b0 [ 374.546553] block_read_full_page+0x1ed/0x330 [ 374.551426] ? check_disk_change+0x70/0x70 [ 374.556008] ? scan_shadow_nodes+0x30/0x30 [ 374.560588] blkdev_readpage+0x18/0x20 [ 374.564783] do_read_cache_page+0x301/0x860 [ 374.569463] ? blkdev_writepages+0x10/0x10 [ 374.574037] ? prep_new_page+0x88/0x130 [ 374.578329] ? get_page_from_freelist+0xa2f/0x1280 [ 374.583688] ? __alloc_pages_nodemask+0x179/0x320 [ 374.588947] read_cache_page+0x12/0x20 [ 374.593142] read_dev_sector+0x2d/0xd0 [ 374.597337] read_lba+0x104/0x1f0 [ 374.601046] find_valid_gpt+0xfa/0x720 [ 374.605243] ? string_nocheck+0x58/0x70 [ 374.609534] ? find_valid_gpt+0x720/0x720 [ 374.614016] efi_partition+0x89/0x430 [ 374.618113] ? string+0x48/0x60 [ 374.621632] ? snprintf+0x49/0x70 [ 374.625339] ? find_valid_gpt+0x720/0x720 [ 374.629828] check_partition+0x116/0x210 [ 374.634214] rescan_partitions+0xb6/0x360 [ 374.638699] __blkdev_reread_part+0x64/0x70 [ 374.643377] blkdev_reread_part+0x23/0x40 [ 374.647860] blkdev_ioctl+0x48c/0x990 [ 374.651956] block_ioctl+0x41/0x50 [ 374.655766] do_vfs_ioctl+0xa7/0x600 [ 374.659766] ? locks_lock_inode_wait+0xb1/0x150 [ 374.664832] ksys_ioctl+0x67/0x90 [ 374.668539] __x64_sys_ioctl+0x1a/0x20 [ 374.672732] do_syscall_64+0x5a/0x1c0 [ 374.676828] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 374.738474] INFO: task nvmeadm:49141 blocked for more than 123 seconds. [ 374.745871] Not tainted 5.2.0-rc3-mpdebug+ #42 [ 374.751419] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 374.760170] nvmeadm D 0 49141 36333 0x00004080 [ 374.766301] Call Trace: [ 374.769038] __schedule+0x2ef/0x620 [ 374.772939] schedule+0x38/0xa0 [ 374.776452] blk_mq_freeze_queue_wait+0x59/0x100 [ 374.781614] ? remove_wait_queue+0x60/0x60 [ 374.786192] blk_mq_freeze_queue+0x1a/0x20 [ 374.790773] nvme_update_disk_info.isra.57+0x5f/0x350 [nvme_core] [ 374.797582] ? nvme_identify_ns.isra.50+0x71/0xc0 [nvme_core] [ 374.804006] __nvme_revalidate_disk+0xe5/0x110 [nvme_core] [ 374.810139] nvme_revalidate_disk+0xa6/0x120 [nvme_core] [ 374.816078] ? nvme_submit_user_cmd+0x11e/0x320 [nvme_core] [ 374.822299] nvme_user_cmd+0x264/0x370 [nvme_core] [ 374.827661] nvme_dev_ioctl+0x112/0x1d0 [nvme_core] [ 374.833114] do_vfs_ioctl+0xa7/0x600 [ 374.837117] ? __audit_syscall_entry+0xdd/0x130 [ 374.842184] ksys_ioctl+0x67/0x90 [ 374.845891] __x64_sys_ioctl+0x1a/0x20 [ 374.850082] do_syscall_64+0x5a/0x1c0 [ 374.854178] entry_SYSCALL_64_after_hwframe+0x44/0xa9 -- Reported-by: James Puthukattukaran <james.puthukattukaran@oracle.com> Tested-by: James Puthukattukaran <james.puthukattukaran@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2019-08-01 02:00:26 +08:00
void nvme_mpath_unfreeze(struct nvme_subsystem *subsys);
void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
void nvme_mpath_remove_disk(struct nvme_ns_head *head);
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
void nvme_mpath_stop(struct nvme_ctrl *ctrl);
nvme: fix controller removal race with scan work With multipath enabled, nvme_scan_work() can read from the device (through nvme_mpath_add_disk()) and hang [1]. However, with fabrics, once ctrl->state is set to NVME_CTRL_DELETING, the reads will hang (see nvmf_check_ready()) and the mpath stack device make_request will block if head->list is not empty. However, when the head->list consistst of only DELETING/DEAD controllers, we should actually not block, but rather fail immediately. In addition, before we go ahead and remove the namespaces, make sure to clear the current path and kick the requeue list so that the request will fast fail upon requeuing. [1]: -- INFO: task kworker/u4:3:166 blocked for more than 120 seconds. Not tainted 5.2.0-rc6-vmlocalyes-00005-g808c8c2dc0cf #316 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u4:3 D 0 166 2 0x80004000 Workqueue: nvme-wq nvme_scan_work Call Trace: __schedule+0x851/0x1400 schedule+0x99/0x210 io_schedule+0x21/0x70 do_read_cache_page+0xa57/0x1330 read_cache_page+0x4a/0x70 read_dev_sector+0xbf/0x380 amiga_partition+0xc4/0x1230 check_partition+0x30f/0x630 rescan_partitions+0x19a/0x980 __blkdev_get+0x85a/0x12f0 blkdev_get+0x2a5/0x790 __device_add_disk+0xe25/0x1250 device_add_disk+0x13/0x20 nvme_mpath_set_live+0x172/0x2b0 nvme_update_ns_ana_state+0x130/0x180 nvme_set_ns_ana_state+0x9a/0xb0 nvme_parse_ana_log+0x1c3/0x4a0 nvme_mpath_add_disk+0x157/0x290 nvme_validate_ns+0x1017/0x1bd0 nvme_scan_work+0x44d/0x6a0 process_one_work+0x7d7/0x1240 worker_thread+0x8e/0xff0 kthread+0x2c3/0x3b0 ret_from_fork+0x35/0x40 INFO: task kworker/u4:1:1034 blocked for more than 120 seconds. Not tainted 5.2.0-rc6-vmlocalyes-00005-g808c8c2dc0cf #316 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u4:1 D 0 1034 2 0x80004000 Workqueue: nvme-delete-wq nvme_delete_ctrl_work Call Trace: __schedule+0x851/0x1400 schedule+0x99/0x210 schedule_timeout+0x390/0x830 wait_for_completion+0x1a7/0x310 __flush_work+0x241/0x5d0 flush_work+0x10/0x20 nvme_remove_namespaces+0x85/0x3d0 nvme_do_delete_ctrl+0xb4/0x1e0 nvme_delete_ctrl_work+0x15/0x20 process_one_work+0x7d7/0x1240 worker_thread+0x8e/0xff0 kthread+0x2c3/0x3b0 ret_from_fork+0x35/0x40 -- Reported-by: Logan Gunthorpe <logang@deltatee.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2019-07-26 02:56:57 +08:00
bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
blk_qc_t nvme_ns_head_submit_bio(struct bio *bio);
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
{
struct nvme_ns_head *head = ns->head;
if (head->disk && list_empty(&head->list))
kblockd_schedule_work(&head->requeue_work);
}
static inline void nvme_trace_bio_complete(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
if (req->cmd_flags & REQ_NVME_MPATH)
trace_block_bio_complete(ns->head->disk->queue, req->bio);
}
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
extern struct device_attribute dev_attr_ana_grpid;
extern struct device_attribute dev_attr_ana_state;
extern struct device_attribute subsys_attr_iopolicy;
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
#else
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
{
return false;
}
/*
* Without the multipath code enabled, multiple controller per subsystems are
* visible as devices and thus we cannot use the subsystem instance.
*/
static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags)
{
sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
}
static inline void nvme_failover_req(struct request *req)
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
{
}
static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{
}
static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
struct nvme_ns_head *head)
{
return 0;
}
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
struct nvme_id_ns *id)
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
{
}
static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
{
}
nvme: fix controller removal race with scan work With multipath enabled, nvme_scan_work() can read from the device (through nvme_mpath_add_disk()) and hang [1]. However, with fabrics, once ctrl->state is set to NVME_CTRL_DELETING, the reads will hang (see nvmf_check_ready()) and the mpath stack device make_request will block if head->list is not empty. However, when the head->list consistst of only DELETING/DEAD controllers, we should actually not block, but rather fail immediately. In addition, before we go ahead and remove the namespaces, make sure to clear the current path and kick the requeue list so that the request will fast fail upon requeuing. [1]: -- INFO: task kworker/u4:3:166 blocked for more than 120 seconds. Not tainted 5.2.0-rc6-vmlocalyes-00005-g808c8c2dc0cf #316 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u4:3 D 0 166 2 0x80004000 Workqueue: nvme-wq nvme_scan_work Call Trace: __schedule+0x851/0x1400 schedule+0x99/0x210 io_schedule+0x21/0x70 do_read_cache_page+0xa57/0x1330 read_cache_page+0x4a/0x70 read_dev_sector+0xbf/0x380 amiga_partition+0xc4/0x1230 check_partition+0x30f/0x630 rescan_partitions+0x19a/0x980 __blkdev_get+0x85a/0x12f0 blkdev_get+0x2a5/0x790 __device_add_disk+0xe25/0x1250 device_add_disk+0x13/0x20 nvme_mpath_set_live+0x172/0x2b0 nvme_update_ns_ana_state+0x130/0x180 nvme_set_ns_ana_state+0x9a/0xb0 nvme_parse_ana_log+0x1c3/0x4a0 nvme_mpath_add_disk+0x157/0x290 nvme_validate_ns+0x1017/0x1bd0 nvme_scan_work+0x44d/0x6a0 process_one_work+0x7d7/0x1240 worker_thread+0x8e/0xff0 kthread+0x2c3/0x3b0 ret_from_fork+0x35/0x40 INFO: task kworker/u4:1:1034 blocked for more than 120 seconds. Not tainted 5.2.0-rc6-vmlocalyes-00005-g808c8c2dc0cf #316 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u4:1 D 0 1034 2 0x80004000 Workqueue: nvme-delete-wq nvme_delete_ctrl_work Call Trace: __schedule+0x851/0x1400 schedule+0x99/0x210 schedule_timeout+0x390/0x830 wait_for_completion+0x1a7/0x310 __flush_work+0x241/0x5d0 flush_work+0x10/0x20 nvme_remove_namespaces+0x85/0x3d0 nvme_do_delete_ctrl+0xb4/0x1e0 nvme_delete_ctrl_work+0x15/0x20 process_one_work+0x7d7/0x1240 worker_thread+0x8e/0xff0 kthread+0x2c3/0x3b0 ret_from_fork+0x35/0x40 -- Reported-by: Logan Gunthorpe <logang@deltatee.com> Tested-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2019-07-26 02:56:57 +08:00
static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
{
return false;
}
static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
}
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
{
}
static inline void nvme_trace_bio_complete(struct request *req)
{
}
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
struct nvme_id_ctrl *id)
{
if (ctrl->subsys->cmic & (1 << 3))
dev_warn(ctrl->device,
"Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n");
nvme: add ANA support Add support for Asynchronous Namespace Access as specified in NVMe 1.3 TP 4004. With ANA each namespace attached to a controller belongs to an ANA group that describes the characteristics of accessing the namespaces through this controller. In the optimized and non-optimized states namespaces can be accessed regularly, although in a multi-pathing environment we should always prefer to access a namespace through a controller where an optimized relationship exists. Namespaces in Inaccessible, Permanent-Loss or Change state for a given controller should not be accessed. The states are updated through reading the ANA log page, which is read once during controller initialization, whenever the ANA change notice AEN is received, or when one of the ANA specific status codes that signal a state change is received on a command. The ANA state is kept in the nvme_ns structure, which makes the checks in the fast path very simple. Updating the ANA state when reading the log page is also very simple, the only downside is that finding the initial ANA state when scanning for namespaces is a bit cumbersome. The gendisk for a ns_head is only registered once a live path for it exists. Without that the kernel would hang during partition scanning. Includes fixes and improvements from Hannes Reinecke. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
2018-05-14 14:48:54 +08:00
return 0;
}
static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
{
}
static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
{
}
nvme: fix a possible deadlock when passthru commands sent to a multipath device When the user issues a command with side effects, we will end up freezing the namespace request queue when updating disk info (and the same for the corresponding mpath disk node). However, we are not freezing the mpath node request queue, which means that mpath I/O can still come in and block on blk_queue_enter (called from nvme_ns_head_make_request -> direct_make_request). This is a deadlock, because blk_queue_enter will block until the inner namespace request queue is unfroze, but that process is blocked because the namespace revalidation is trying to update the mpath disk info and freeze its request queue (which will never complete because of the I/O that is blocked on blk_queue_enter). Fix this by freezing all the subsystem nsheads request queues before executing the passthru command. Given that these commands are infrequent we should not worry about this temporary I/O freeze to keep things sane. Here is the matching hang traces: -- [ 374.465002] INFO: task systemd-udevd:17994 blocked for more than 122 seconds. [ 374.472975] Not tainted 5.2.0-rc3-mpdebug+ #42 [ 374.478522] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 374.487274] systemd-udevd D 0 17994 1 0x00000000 [ 374.493407] Call Trace: [ 374.496145] __schedule+0x2ef/0x620 [ 374.500047] schedule+0x38/0xa0 [ 374.503569] blk_queue_enter+0x139/0x220 [ 374.507959] ? remove_wait_queue+0x60/0x60 [ 374.512540] direct_make_request+0x60/0x130 [ 374.517219] nvme_ns_head_make_request+0x11d/0x420 [nvme_core] [ 374.523740] ? generic_make_request_checks+0x307/0x6f0 [ 374.529484] generic_make_request+0x10d/0x2e0 [ 374.534356] submit_bio+0x75/0x140 [ 374.538163] ? guard_bio_eod+0x32/0xe0 [ 374.542361] submit_bh_wbc+0x171/0x1b0 [ 374.546553] block_read_full_page+0x1ed/0x330 [ 374.551426] ? check_disk_change+0x70/0x70 [ 374.556008] ? scan_shadow_nodes+0x30/0x30 [ 374.560588] blkdev_readpage+0x18/0x20 [ 374.564783] do_read_cache_page+0x301/0x860 [ 374.569463] ? blkdev_writepages+0x10/0x10 [ 374.574037] ? prep_new_page+0x88/0x130 [ 374.578329] ? get_page_from_freelist+0xa2f/0x1280 [ 374.583688] ? __alloc_pages_nodemask+0x179/0x320 [ 374.588947] read_cache_page+0x12/0x20 [ 374.593142] read_dev_sector+0x2d/0xd0 [ 374.597337] read_lba+0x104/0x1f0 [ 374.601046] find_valid_gpt+0xfa/0x720 [ 374.605243] ? string_nocheck+0x58/0x70 [ 374.609534] ? find_valid_gpt+0x720/0x720 [ 374.614016] efi_partition+0x89/0x430 [ 374.618113] ? string+0x48/0x60 [ 374.621632] ? snprintf+0x49/0x70 [ 374.625339] ? find_valid_gpt+0x720/0x720 [ 374.629828] check_partition+0x116/0x210 [ 374.634214] rescan_partitions+0xb6/0x360 [ 374.638699] __blkdev_reread_part+0x64/0x70 [ 374.643377] blkdev_reread_part+0x23/0x40 [ 374.647860] blkdev_ioctl+0x48c/0x990 [ 374.651956] block_ioctl+0x41/0x50 [ 374.655766] do_vfs_ioctl+0xa7/0x600 [ 374.659766] ? locks_lock_inode_wait+0xb1/0x150 [ 374.664832] ksys_ioctl+0x67/0x90 [ 374.668539] __x64_sys_ioctl+0x1a/0x20 [ 374.672732] do_syscall_64+0x5a/0x1c0 [ 374.676828] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 374.738474] INFO: task nvmeadm:49141 blocked for more than 123 seconds. [ 374.745871] Not tainted 5.2.0-rc3-mpdebug+ #42 [ 374.751419] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 374.760170] nvmeadm D 0 49141 36333 0x00004080 [ 374.766301] Call Trace: [ 374.769038] __schedule+0x2ef/0x620 [ 374.772939] schedule+0x38/0xa0 [ 374.776452] blk_mq_freeze_queue_wait+0x59/0x100 [ 374.781614] ? remove_wait_queue+0x60/0x60 [ 374.786192] blk_mq_freeze_queue+0x1a/0x20 [ 374.790773] nvme_update_disk_info.isra.57+0x5f/0x350 [nvme_core] [ 374.797582] ? nvme_identify_ns.isra.50+0x71/0xc0 [nvme_core] [ 374.804006] __nvme_revalidate_disk+0xe5/0x110 [nvme_core] [ 374.810139] nvme_revalidate_disk+0xa6/0x120 [nvme_core] [ 374.816078] ? nvme_submit_user_cmd+0x11e/0x320 [nvme_core] [ 374.822299] nvme_user_cmd+0x264/0x370 [nvme_core] [ 374.827661] nvme_dev_ioctl+0x112/0x1d0 [nvme_core] [ 374.833114] do_vfs_ioctl+0xa7/0x600 [ 374.837117] ? __audit_syscall_entry+0xdd/0x130 [ 374.842184] ksys_ioctl+0x67/0x90 [ 374.845891] __x64_sys_ioctl+0x1a/0x20 [ 374.850082] do_syscall_64+0x5a/0x1c0 [ 374.854178] entry_SYSCALL_64_after_hwframe+0x44/0xa9 -- Reported-by: James Puthukattukaran <james.puthukattukaran@oracle.com> Tested-by: James Puthukattukaran <james.puthukattukaran@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
2019-08-01 02:00:26 +08:00
static inline void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
{
}
static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
{
}
static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
{
}
nvme: implement multipath access to nvme subsystems This patch adds native multipath support to the nvme driver. For each namespace we create only single block device node, which can be used to access that namespace through any of the controllers that refer to it. The gendisk for each controllers path to the name space still exists inside the kernel, but is hidden from userspace. The character device nodes are still available on a per-controller basis. A new link from the sysfs directory for the subsystem allows to find all controllers for a given subsystem. Currently we will always send I/O to the first available path, this will be changed once the NVMe Asynchronous Namespace Access (ANA) TP is ratified and implemented, at which point we will look at the ANA state for each namespace. Another possibility that was prototyped is to use the path that is closes to the submitting NUMA code, which will be mostly interesting for PCI, but might also be useful for RDMA or FC transports in the future. There is not plan to implement round robin or I/O service time path selectors, as those are not scalable with the performance rates provided by NVMe. The multipath device will go away once all paths to it disappear, any delay to keep it alive needs to be implemented at the controller level. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-11-02 19:59:30 +08:00
#endif /* CONFIG_NVME_MULTIPATH */
int nvme_revalidate_zones(struct nvme_ns *ns);
#ifdef CONFIG_BLK_DEV_ZONED
int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
int nvme_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd,
enum nvme_zone_mgmt_action action);
#else
#define nvme_report_zones NULL
static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd,
enum nvme_zone_mgmt_action action)
{
return BLK_STS_NOTSUPP;
}
static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
{
dev_warn(ns->ctrl->device,
"Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
return -EPROTONOSUPPORT;
}
#endif
#ifdef CONFIG_NVM
int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
void nvme_nvm_unregister(struct nvme_ns *ns);
extern const struct attribute_group nvme_nvm_attr_group;
int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg);
#else
static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
int node)
{
return 0;
}
static inline void nvme_nvm_unregister(struct nvme_ns *ns) {};
static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
unsigned long arg)
{
return -ENOTTY;
}
#endif /* CONFIG_NVM */
lightnvm: expose device geometry through sysfs For a host to access an Open-Channel SSD, it has to know its geometry, so that it writes and reads at the appropriate device bounds. Currently, the geometry information is kept within the kernel, and not exported to user-space for consumption. This patch exposes the configuration through sysfs and enables user-space libraries, such as liblightnvm, to use the sysfs implementation to get the geometry of an Open-Channel SSD. The sysfs entries are stored within the device hierarchy, and can be found using the "lightnvm" device type. An example configuration looks like this: /sys/class/nvme/ └── nvme0n1 ├── capabilities: 3 ├── device_mode: 1 ├── erase_max: 1000000 ├── erase_typ: 1000000 ├── flash_media_type: 0 ├── media_capabilities: 0x00000001 ├── media_type: 0 ├── multiplane: 0x00010101 ├── num_blocks: 1022 ├── num_channels: 1 ├── num_luns: 4 ├── num_pages: 64 ├── num_planes: 1 ├── page_size: 4096 ├── prog_max: 100000 ├── prog_typ: 100000 ├── read_max: 10000 ├── read_typ: 10000 ├── sector_oob_size: 0 ├── sector_size: 4096 ├── media_manager: gennvm ├── ppa_format: 0x380830082808001010102008 ├── vendor_opcode: 0 ├── max_phys_secs: 64 └── version: 1 Signed-off-by: Simon A. F. Lund <slund@cnexlabs.com> Signed-off-by: Matias Bjørling <m@bjorling.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-09-16 20:25:08 +08:00
static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
{
return dev_to_disk(dev)->private_data;
}
#ifdef CONFIG_NVME_HWMON
int nvme_hwmon_init(struct nvme_ctrl *ctrl);
void nvme_hwmon_exit(struct nvme_ctrl *ctrl);
#else
static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl)
{
return 0;
}
static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
{
}
#endif
u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
u8 opcode);
void nvme_execute_passthru_rq(struct request *rq);
struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
void nvme_put_ns(struct nvme_ns *ns);
#endif /* _NVME_H */