iopoll is initially for small size, latency sensitive IO. It doesn't
work well for big IO, especially when it needs to be split to multiple
bios. In this case, the returned cookie of __submit_bio_noacct_mq() is
indeed the cookie of the last split bio. The completion of *this* last
split bio done by iopoll doesn't mean the whole original bio has
completed. Callers of iopoll still need to wait for completion of other
split bios.
Besides bio splitting may cause more trouble for iopoll which isn't
supposed to be used in case of big IO.
iopoll for split bio may cause potential race if CPU migration happens
during bio submission. Since the returned cookie is that of the last
split bio, polling on the corresponding hardware queue doesn't help
complete other split bios, if these split bios are enqueued into
different hardware queues. Since interrupts are disabled for polling
queues, the completion of these other split bios depends on timeout
mechanism, thus causing a potential hang.
iopoll for split bio may also cause hang for sync polling. Currently
both the blkdev and iomap-based fs (ext4/xfs, etc) support sync polling
in direct IO routine. These routines will submit bio without REQ_NOWAIT
flag set, and then start sync polling in current process context. The
process may hang in blk_mq_get_tag() if the submitted bio has to be
split into multiple bios and can rapidly exhaust the queue depth. The
process are waiting for the completion of the previously allocated
requests, which should be reaped by the following polling, and thus
causing a deadlock.
To avoid these subtle trouble described above, just disable iopoll for
split bio and return BLK_QC_T_NONE in this case. The side effect is that
non-HIPRI IO also returns BLK_QC_T_NONE now. It should be acceptable
since the returned cookie is never used for non-HIPRI IO.
Suggested-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
__htab_map_lookup_and_delete_batch() stores a user pointer in the local
variable ubatch and uses that in copy_{from,to}_user(), but ubatch misses a
__user annotation.
So, sparse warns in the various assignments and uses of ubatch:
kernel/bpf/hashtab.c:1415:24: warning: incorrect type in initializer
(different address spaces)
kernel/bpf/hashtab.c:1415:24: expected void *ubatch
kernel/bpf/hashtab.c:1415:24: got void [noderef] __user *
kernel/bpf/hashtab.c:1444:46: warning: incorrect type in argument 2
(different address spaces)
kernel/bpf/hashtab.c:1444:46: expected void const [noderef] __user *from
kernel/bpf/hashtab.c:1444:46: got void *ubatch
kernel/bpf/hashtab.c:1608:16: warning: incorrect type in assignment
(different address spaces)
kernel/bpf/hashtab.c:1608:16: expected void *ubatch
kernel/bpf/hashtab.c:1608:16: got void [noderef] __user *
kernel/bpf/hashtab.c:1609:26: warning: incorrect type in argument 1
(different address spaces)
kernel/bpf/hashtab.c:1609:26: expected void [noderef] __user *to
kernel/bpf/hashtab.c:1609:26: got void *ubatch
Add the __user annotation to repair this chain of propagating __user
annotations in __htab_map_lookup_and_delete_batch().
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20201207123720.19111-1-lukas.bulwahn@gmail.com
Saeed Mahameed says:
====================
mlx5-next auxbus support
This pull request is targeting net-next and rdma-next branches.
This series provides mlx5 support for auxiliary bus devices.
It starts with a merge commit of tag 'auxbus-5.11-rc1' from
gregkh/driver-core into mlx5-next, then the mlx5 patches that will convert
mlx5 ulp devices (netdev, rdma, vdpa) to use the proper auxbus
infrastructure instead of the internal mlx5 device and interface management
implementation, which Leon is deleting at the end of this patchset.
Link: https://lore.kernel.org/alsa-devel/20201026111849.1035786-1-leon@kernel.org/
Thanks to everyone for the joint effort !
* 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
RDMA/mlx5: Remove IB representors dead code
net/mlx5: Simplify eswitch mode check
net/mlx5: Delete custom device management logic
RDMA/mlx5: Convert mlx5_ib to use auxiliary bus
net/mlx5e: Connect ethernet part to auxiliary bus
vdpa/mlx5: Connect mlx5_vdpa to auxiliary bus
net/mlx5: Register mlx5 devices to auxiliary virtual bus
vdpa/mlx5: Make hardware definitions visible to all mlx5 devices
net/mlx5_core: Clean driver version and name
net/mlx5: Properly convey driver version to firmware
driver core: auxiliary bus: minor coding style tweaks
driver core: auxiliary bus: make remove function return void
driver core: auxiliary bus: move slab.h from include file
Add auxiliary bus support
====================
Link: https://lore.kernel.org/r/20201207053349.402772-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Steffen Klassert says:
====================
pull request (net): ipsec 2020-12-07
1) Sysbot reported fixes for the new 64/32 bit compat layer.
From Dmitry Safonov.
2) Fix a memory leak in xfrm_user_policy that was introduced
by adding the 64/32 bit compat layer. From Yu Kuai.
* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec:
net: xfrm: fix memory leak in xfrm_user_policy()
xfrm/compat: Don't allocate memory with __GFP_ZERO
xfrm/compat: memset(0) 64-bit padding at right place
xfrm/compat: Translate by copying XFRMA_UNSPEC attribute
====================
Link: https://lore.kernel.org/r/20201207093937.2874932-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
For when managed interrupts are used (and shost->nr_hw_queues is set), a
fixed queue - set per-device - is still used for internal I/Os.
If all the CPUs mapped to that queue are offlined, then the completions for
that queue are not serviced and any internal I/Os will time out.
Fix by selecting a queue for internal I/Os from the queue mapped from the
current CPU in this scenario.
This is still not ideal as it does not deal with CPU hotplug for inflight
internal I/Os, and needs proper support from [0].
[0] https://lore.kernel.org/linux-scsi/20200703130122.111448-1-hare@suse.de/T/#m7d77d049b18f33a24ef206af69ebb66d07440556
Link: https://lore.kernel.org/r/1607347855-59091-1-git-send-email-john.garry@huawei.com
Fixes: 8d98416a55 ("scsi: hisi_sas: Switch v3 hw to MQ")
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
All usages of the definition MAX_MSIX_P_PORT were removed.
It's not in use anymore. Remove it.
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Link: https://lore.kernel.org/r/20201206091254.12476-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We can remove one of the ifdef blocks here, and instead of setting both
the xfrm hw_features and features flags, then unsetting the feature
flags if not in AB, wait to set the features flags if we're actually in AB
mode.
Signed-off-by: Jarod Wilson <jarod@redhat.com>
Link: https://lore.kernel.org/r/20201205174003.578267-1-jarod@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When queuing I/O request to LLD, STS_RESOURCE may be returned because:
- Host is in recovery or blocked
- Target queue throttling or target is blocked
- LLD rejection
In these scenarios BLK_STS_DEV_RESOURCE is returned to the block layer to
avoid an unnecessary re-run of the queue. However, all of the requests
queued to this SCSI device may complete immediately after reading
'sdev->device_busy' and BLK_STS_DEV_RESOURCE is returned to block layer. In
that case the current I/O won't get a chance to get queued since it is
invisible at that time for both scsi_run_queue_async() and blk-mq's
RESTART.
Fix the issue by not returning BLK_STS_DEV_RESOURCE in this situation.
Link: https://lore.kernel.org/r/20201202100419.525144-1-ming.lei@redhat.com
Fixes: 86ff7c2a80 ("blk-mq: introduce BLK_STS_DEV_RESOURCE")
Cc: Hannes Reinecke <hare@suse.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Ewan Milne <emilne@redhat.com>
Cc: Long Li <longli@microsoft.com>
Reported-by: John Garry <john.garry@huawei.com>
Tested-by: "chenxiang (M)" <chenxiang66@hisilicon.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
The m250_sel mux clock uses bit 4 in the PRG_ETH0 register. Fix this by
shifting the PRG_ETH0_CLK_M250_SEL_MASK accordingly as the "mask" in
struct clk_mux expects the mask relative to the "shift" field in the
same struct.
While here, get rid of the PRG_ETH0_CLK_M250_SEL_SHIFT macro and use
__ffs() to determine it from the existing PRG_ETH0_CLK_M250_SEL_MASK
macro.
Fixes: 566e825162 ("net: stmmac: add a glue driver for the Amlogic Meson 8b / GXBB DWMAC")
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20201205213207.519341-1-martin.blumenstingl@googlemail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add an 'of_node_put()' call when a tested device node is not available.
Fixes: 94ae899b20 ("dpaa2-mac: add PCS support through the Lynx module")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://lore.kernel.org/r/20201206151339.44306-1-christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When do cat /proc/net/netstat, the output isn't append with a new line, it looks like this:
[root@localhost ~]# cat /proc/net/netstat
...
MPTcpExt: 0 0 0 0 0 0 0 0 0 0 0 0 0[root@localhost ~]#
This is because in mptcp_seq_show(), if mptcp isn't in use, net->mib.mptcp_statistics is NULL,
so it just puts all 0 after "MPTcpExt:", and return, forgot the '\n'.
After this patch:
[root@localhost ~]# cat /proc/net/netstat
...
MPTcpExt: 0 0 0 0 0 0 0 0 0 0 0 0 0
[root@localhost ~]#
Fixes: fc518953bc ("mptcp: add and use MIB counter infrastructure")
Signed-off-by: Jianguo Wu <wujianguo@chinatelecom.cn>
Acked-by: Florian Westphal <fw@strlen.de>
Link: https://lore.kernel.org/r/142e2fd9-58d9-bb13-fb75-951cccc2331e@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The macro use will already have a semicolon. Remove unneeded escaped
newline.
Link: https://lore.kernel.org/r/20201130205509.3447316-1-trix@redhat.com
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Tom Rix <trix@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Return a negative error code from the error handling case instead of 0 as
done elsewhere in this function.
Link: https://lore.kernel.org/r/1607068060-31203-1-git-send-email-zhangchangzhong@huawei.com
Fixes: 5df6d737dd ("[SCSI] fnic: Add new Cisco PCI-Express FCoE HBA")
Reported-by: Hulk Robot <hulkci@huawei.com>
Reviewed-by: Karan Tilak Kumar <kartilak@cisco.com>
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
clang complains about a possible code path in which a variable is used
without an initialization:
drivers/scsi/ufs/ufshcd.c:7690:3: error: variable 'sdp' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized]
BUG_ON(1);
^~~~~~~~~
include/asm-generic/bug.h:63:36: note: expanded from macro 'BUG_ON'
#define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while (0)
^~~~~~~~~~~~~~~~~~~
Turn the BUG_ON(1) into an unconditional BUG() that makes it clear to clang
that this code path is never hit.
Link: https://lore.kernel.org/r/20201203223137.1205933-1-arnd@kernel.org
Fixes: 4f3e900b62 ("scsi: ufs: Clear UAC for FFU and RPMB LUNs")
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
NCR5380_poll_politely2() uses in_interrupt() and irqs_disabled() to check
if it is safe to sleep.
Such usage in drivers is phased out and Linus clearly requested that code
which changes behaviour depending on context should either be separated, or
the context be explicitly conveyed in an argument passed by the caller.
Below is a context analysis of NCR5380_poll_politely2() uppermost callers:
- NCR5380_maybe_reset_bus(), task, invoked during device probe.
-> NCR5380_poll_politely()
-> do_abort()
- NCR5380_select(), task, but can only sleep in the "release, then
re-acquire" regions of the spinlock held by its caller.
Sleeping invocations (lock released):
-> NCR5380_poll_politely2()
Atomic invocations (lock acquired):
-> NCR5380_reselect()
-> NCR5380_poll_politely()
-> do_abort()
-> NCR5380_transfer_pio()
- NCR5380_intr(), interrupt handler
-> NCR5380_dma_complete()
-> NCR5380_transfer_pio()
-> NCR5380_poll_politely()
-> NCR5380_reselect() (see above)
- NCR5380_information_transfer(), task, but can only sleep in the
"release, then re-acquire" regions of the caller-held spinlock.
Sleeping invocations (lock released):
- NCR5380_transfer_pio() -> NCR5380_poll_politely()
- NCR5380_poll_politely()
Atomic invocations (lock acquired):
- NCR5380_transfer_dma()
-> NCR5380_dma_recv_setup()
=> generic_NCR5380_precv() -> NCR5380_poll_politely()
=> macscsi_pread() -> NCR5380_poll_politely()
-> NCR5380_dma_send_setup()
=> generic_NCR5380_psend -> NCR5380_poll_politely2()
=> macscsi_pwrite() -> NCR5380_poll_politely()
-> NCR5380_poll_politely2()
-> NCR5380_dma_complete()
-> NCR5380_transfer_pio()
-> NCR5380_poll_politely()
- NCR5380_transfer_pio() -> NCR5380_poll_politely
- NCR5380_reselect(), atomic, always called with hostdata spinlock
held.
Since NCR5380_poll_politely2() already takes a "wait" argument in jiffies,
use it to determine if the function can sleep. Modify atomic callers, which
passed an unused wait value in terms of HZ, to pass zero.
Link: https://lore.kernel.org/r/20201206075157.19067-1-a.darwish@linutronix.de
Cc: Michael Schmitz <schmitzmic@gmail.com>
Cc: <linux-m68k@lists.linux-m68k.org>
Suggested-by: Finn Thain <fthain@telegraphics.com.au>
Co-developed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Invalidation check of arguments should have been checked before
ufshcd_hold(). This can help to prevent ufshcd_hold()/ ufshcd_release()
from being invoked unnecessarily.
[mkp: removed unused out: labels]
Link: https://lore.kernel.org/r/1606973132-5937-1-git-send-email-user@jang-Samsung-DeskTop-System
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: jintae jang <jt77.jang@samsung.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
When enabling multicast snooping, bridge module deadlocks on multicast_lock
if 1) IPv6 is enabled, and 2) there is an existing querier on the same L2
network.
The deadlock was caused by the following sequence: While holding the lock,
br_multicast_open calls br_multicast_join_snoopers, which eventually causes
IP stack to (attempt to) send out a Listener Report (in igmp6_join_group).
Since the destination Ethernet address is a multicast address, br_dev_xmit
feeds the packet back to the bridge via br_multicast_rcv, which in turn
calls br_multicast_add_group, which then deadlocks on multicast_lock.
The fix is to move the call br_multicast_join_snoopers outside of the
critical section. This works since br_multicast_join_snoopers only deals
with IP and does not modify any multicast data structures of the bridge,
so there's no need to hold the lock.
Steps to reproduce:
1. sysctl net.ipv6.conf.all.force_mld_version=1
2. have another querier
3. ip link set dev bridge type bridge mcast_snooping 0 && \
ip link set dev bridge type bridge mcast_snooping 1 < deadlock >
A typical call trace looks like the following:
[ 936.251495] _raw_spin_lock+0x5c/0x68
[ 936.255221] br_multicast_add_group+0x40/0x170 [bridge]
[ 936.260491] br_multicast_rcv+0x7ac/0xe30 [bridge]
[ 936.265322] br_dev_xmit+0x140/0x368 [bridge]
[ 936.269689] dev_hard_start_xmit+0x94/0x158
[ 936.273876] __dev_queue_xmit+0x5ac/0x7f8
[ 936.277890] dev_queue_xmit+0x10/0x18
[ 936.281563] neigh_resolve_output+0xec/0x198
[ 936.285845] ip6_finish_output2+0x240/0x710
[ 936.290039] __ip6_finish_output+0x130/0x170
[ 936.294318] ip6_output+0x6c/0x1c8
[ 936.297731] NF_HOOK.constprop.0+0xd8/0xe8
[ 936.301834] igmp6_send+0x358/0x558
[ 936.305326] igmp6_join_group.part.0+0x30/0xf0
[ 936.309774] igmp6_group_added+0xfc/0x110
[ 936.313787] __ipv6_dev_mc_inc+0x1a4/0x290
[ 936.317885] ipv6_dev_mc_inc+0x10/0x18
[ 936.321677] br_multicast_open+0xbc/0x110 [bridge]
[ 936.326506] br_multicast_toggle+0xec/0x140 [bridge]
Fixes: 4effd28c12 ("bridge: join all-snoopers multicast address")
Signed-off-by: Joseph Huang <Joseph.Huang@garmin.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Link: https://lore.kernel.org/r/20201204235628.50653-1-Joseph.Huang@garmin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We sometimes run into situations where a soft/hard reset of the adapter
takes a long time or fails to complete. Having additional messages that
include important adapter state info will hopefully help understand what
is happening, reduce the guess work and minimize requests to reproduce
problems with debug patches.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Link: https://lore.kernel.org/r/20201205022235.2414110-1-sukadev@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add device tree bindings for global clock controller on SDX55 SoCs.
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20201126072844.35370-2-manivannan.sadhasivam@linaro.org
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Noticed some inconsistencies in packet statistics reporting.
This patch adds the missing Tx packet counter registers to
ethtool reporting and fixes the information strings for a
few of them.
Fixes: 16eb4c85c9 ("enetc: Add ethtool statistics")
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://lore.kernel.org/r/20201204171505.21389-1-claudiu.manoil@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add support for the FlexSPI clock on Freescale Layerscape SoCs. The
clock is a simple divider based one and is located inside the device
configuration space (DCFG).
This will allow switching the SCK frequencies for the FlexSPI interface
on the LS1028A and the LX2160A.
Signed-off-by: Michael Walle <michael@walle.cc>
Link: https://lore.kernel.org/r/20201108185113.31377-8-michael@walle.cc
[sboyd@kernel.org: Drop modalias, add module table]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
To avoid future mistakes in the device tree for the clockgen module, add
constants for the clockgen subtype as well as a macro for the PLL
divider.
Signed-off-by: Michael Walle <michael@walle.cc>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20201108185113.31377-4-michael@walle.cc
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
Move null_blk driver code into the new sub-directory
drivers/block/null_blk.
Suggested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add the module option and configfs attribute max_sectors to allow
configuring the maximum size of a command issued to a null_blk device.
This allows exercising the block layer BIO splitting with different
limits than the default BLK_SAFE_MAX_SECTORS. This is also useful for
testing the zone append write path of file systems as the max_hw_sectors
limit value is also used for the max_zone_append_sectors limit.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When memory backing is enabled, use null_handle_discard() to free the
backing memory used by a zone when the zone is being reset.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
null_handle_discard() is called from both null_handle_rq() and
null_handle_bio(). As these functions are only passed a nullb_cmd
structure, this forces pointer dereferences to identiify the discard
operation code and to access the sector range to be discarded.
Simplify all this by changing the interface of the functions
null_handle_discard() and null_handle_memory_backed() to pass along
the operation code, operation start sector and number of sectors. With
this change null_handle_discard() can be called directly from
null_handle_memory_backed().
Also add a message warning that the discard configuration attribute has
no effect when memory backing is disabled.
No functional change is introduced by this patch.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When open zone resource management is enabled, that is, when a null_blk
zoned device is created with zone_max_open different than 0, implicitly
or explicitly opening a zone may require implicitly closing a zone
that is already implicitly open. This operation is done using the
function null_close_first_imp_zone(), which search for an implicitly
open zone to close starting from the first sequential zone. This
implementation is simple but may result in the same being constantly
implicitly closed and then implicitly reopened on write, namely, the
lowest numbered zone that is being written.
Avoid this by starting the search for an implicitly open zone starting
from the zone following the last zone that was implicitly closed. The
function null_close_first_imp_zone() is renamed
null_close_imp_open_zone().
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With memory backing disabled, using a single spinlock for protecting
zone information and zone resource management prevents the parallel
execution on multiple queue of IO requests to different zones.
Furthermore, regardless of the use of memory backing, if a null_blk
device is created without limits on the number of open and active zones,
accounting for zone resource management is not necessary.
>From these observations, zone locking is changed as follows to improve
performance:
1) the zone_lock spinlock is renamed zone_res_lock and used only if
zone resource management is necessary, that is, if either
zone_max_open or zone_max_active are not 0. This is indicated using
the new boolean need_zone_res_mgmt in the nullb_device structure.
null_zone_write() is modified to reduce the amount of code executed
with the zone_res_lock spinlock held.
2) With memory backing disabled, per zone locking is changed to a
spinlock per zone.
3) Introduce the structure nullb_zone to replace the use of
struct blk_zone for zone information. This new structure includes a
union of a spinlock and a mutex for zone locking. The spinlock is
used when memory backing is disabled and the mutex is used with
memory backing.
With these changes, fio performance with zonemode=zbd for 4K random
read and random write on a dual socket (24 cores per socket) machine
using the none schedulder is as follows:
before patch:
write (psync x 96 jobs) = 465 KIOPS
read (libaio@qd=8 x 96 jobs) = 1361 KIOPS
after patch:
write (psync x 96 jobs) = 456 KIOPS
read (libaio@qd=8 x 96 jobs) = 4096 KIOPS
Write performance remains mostly unchanged but read performance is three
times higher. Performance when using the mq-deadline scheduler is not
changed by this patch as mq-deadline becomes the bottleneck for a
multi-queue device.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Block device drivers do not have to call blk_queue_max_hw_sectors() to
set a limit on request size if the default limit BLK_SAFE_MAX_SECTORS
is acceptable. However, this limit (255 sectors) may not be aligned
to the device logical block size which cannot be used as is for a
request maximum size. This is the case for the null_blk device driver.
Modify blk_queue_max_hw_sectors() to make sure that the request size
limits specified by the max_hw_sectors and max_sectors queue limits
are always aligned to the device logical block size. Additionally, to
avoid introducing a dependence on the execution order of this function
with blk_queue_logical_block_size(), also modify
blk_queue_logical_block_size() to perform the same alignment when the
logical block size is set after max_hw_sectors.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Conventional zones do not have a write pointer and so cannot accept zone
append writes. Make sure to fail any zone append write command issued to
a conventional zone.
Reported-by: Naohiro Aota <naohiro.aota@wdc.com>
Fixes: e0489ed5da ("null_blk: Support REQ_OP_ZONE_APPEND")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For a null_blk device with zoned mode enabled is currently initialized
with a number of zones equal to the device capacity divided by the zone
size, without considering if the device capacity is a multiple of the
zone size. If the zone size is not a divisor of the capacity, the zones
end up not covering the entire capacity, potentially resulting is out
of bounds accesses to the zone array.
Fix this by adding one last smaller zone with a size equal to the
remainder of the disk capacity divided by the zone size if the capacity
is not a multiple of the zone size. For such smaller last zone, the zone
capacity is also checked so that it does not exceed the smaller zone
size.
Reported-by: Naohiro Aota <naohiro.aota@wdc.com>
Fixes: ca4b2a0119 ("null_blk: add zone support")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Improves the checks on the zones of a zoned block device done in
blk_revalidate_disk_zones() by making sure that the device report_zones
method did report at least one zone and that the zones reported exactly
cover the entire disk capacity, that is, that there are no missing zones
at the end of the disk sector range.
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
__sbitmap_get_word() doesn't warp if it's starting from the beginning
(i.e. initial hint is 0). Instead of stashing the original hint just set
@wrap accordingly.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
sbitmap_deferred_clear() does CAS loop to propagate cleared bits,
replace it with equivalent atomic bitwise and. That's slightly faster
and makes wait-free instead of lock-free as before.
The atomic can be relaxed (i.e. barrier-less) because following
sbitmap_get*() deal with synchronisation, see comments in
sbitmap_queue_clear().
It's ok to cast to atomic_long_t, that's what bitops/lock.h does.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
map->swap_lock protects map->cleared from concurrent modification,
however sbitmap_deferred_clear() is already atomically drains it, so
it's guaranteed to not loose bits on concurrent
sbitmap_deferred_clear().
A one threaded tag heavy test on top of nullbk showed ~1.5% t-put
increase, and 3% -> 1% cycle reduction of sbitmap_get() according to perf.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Because of spinlocks and atomics sbitmap_deferred_clear() have to reload
&sb->map[index] on each access even though the map address won't change.
Pass in sbitmap_word instead of {sb, index}, so it's cached in a
variable. It also improves code generation of
sbitmap_find_bit_in_index().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If blk_poll() is not going to spin (i.e. @spin=false), it also must not
sleep in hybrid polling, otherwise it might be pretty suprising for
users trying to do a quick check and expecting no-wait behaviour.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Dump registers and states prior to leaving IRQ handler when an AH8 error
occurs.
Link: https://lore.kernel.org/r/1606910644-21185-4-git-send-email-cang@codeaurora.org
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Bao D. Nguyen <nguyenb@codeaurora.org>
Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>
Reviewed-by: Hongwu Su <hongwus@codeaurora.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
In current task abort routine, if task abort happens to the device W-LUN,
the code directly jumps to ufshcd_eh_host_reset_handler() to perform a full
reset and restore then returns FAIL or SUCCESS. Commands sent to the device
W-LUN are most likely the SSU cmds sent during UFS PM operations. If such
SSU cmd enters task abort routine when ufshcd_eh_host_reset_handler()
flushes eh_work, it will get stuck there since err_handler is serialized
with PM operations.
In order to unblock above call path, we merely clean up the lrb taken by
this cmd, queue the eh_work and return SUCCESS. Once the cmd is aborted,
the PM operation which sends out the cmd just errors out, then err_handler
shall be able to proceed with the full reset and restore.
In this scenario, the cmd is aborted even before it is actually cleared by
HW, set the lrb->in_use flag to prevent subsequent cmds, including SCSI
cmds and dev cmds, from taking the lrb released from abort. The flag shall
evetually be cleared in __ufshcd_transfer_req_compl() invoked by the full
reset and restore from err_handler.
[mkp: conflict with event logging series]
Link: https://lore.kernel.org/r/1606910644-21185-3-git-send-email-cang@codeaurora.org
Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Serialize eh_work with system PM events and async scan to make sure eh_work
does not run in parallel with them.
Link: https://lore.kernel.org/r/1606910644-21185-2-git-send-email-cang@codeaurora.org
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>
Reviewed-by: Hongwu Su <hongwus@codeaurora.org>
Signed-off-by: Can Guo <cang@codeaurora.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Building with W=2 prints a number of warnings for one function that
has a pointer type mismatch:
linux/seq_buf.h: In function 'seq_buf_init':
linux/seq_buf.h:35:12: warning: pointer targets in assignment from 'unsigned char *' to 'char *' differ in signedness [-Wpointer-sign]
Change the type in the function prototype according to the type in
the structure.
Link: https://lkml.kernel.org/r/20201026161108.3707783-1-arnd@kernel.org
Fixes: 9a7777935c ("tracing: Convert seq_buf fields to be like seq_file fields")
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
