As the 32MB flash layout will soon be exhausted, switch to 64MB layout.
Signed-off-by: Quan Nguyen <quan@os.amperecomputing.com>
Signed-off-by: Phong Vo <phong@os.amperecomputing.com>
Signed-off-by: Thang Q. Nguyen <thang@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20210517040036.13667-4-quan@os.amperecomputing.com
Signed-off-by: Joel Stanley <joel@jms.id.au>
Enable PSU support on Ampere's Mt. Jade BMC.
Signed-off-by: Quan Nguyen <quan@os.amperecomputing.com>
Signed-off-by: Phong Vo <phong@os.amperecomputing.com>
Signed-off-by: Thang Q. Nguyen <thang@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20210517040036.13667-3-quan@os.amperecomputing.com
Signed-off-by: Joel Stanley <joel@jms.id.au>
Enable OCP card support on Ampere's Mt. Jade BMC.
Signed-off-by: Quan Nguyen <quan@os.amperecomputing.com>
Signed-off-by: Phong Vo <phong@os.amperecomputing.com>
Signed-off-by: Thang Q. Nguyen <thang@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20210517040036.13667-2-quan@os.amperecomputing.com
Signed-off-by: Joel Stanley <joel@jms.id.au>
Move struct intel_dmc from i915_drv.h to intel_dmc.h.
v2: Add includes along with moving the struct.
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210526220256.4097-4-anusha.srivatsa@intel.com
We check for dmc_payload being there at various points in the driver.
Replace it with the helper.
v2: rebased.
v3: Move intel_dmc to intel_dmc.h in another patch (Lucas)
v4: Remove headers not needed from intel_dmc.h
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210526220256.4097-3-anusha.srivatsa@intel.com
Use new format of debug messages across intel_csr.
While at it, change some function definitions which now
need dev_priv for drm_err and drm_info etc.
v2: use container_of() (Jani)
v3: Indentation fixes. (Jani)
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Suggested-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210526220256.4097-2-anusha.srivatsa@intel.com
The of_device_id is included unconditionally by of.h header and used
in the driver as well. Remove of_match_ptr to fix W=1 compile test
warning with !CONFIG_OF:
drivers/phy/ralink/phy-mt7621-pci.c:341:34: warning: unused variable 'mt7621_pci_phy_ids' [-Wunused-const-variable]
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Link: https://lore.kernel.org/r/20210603043219.32646-1-sergio.paracuellos@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Most of the aspeed boards have copied the 'earlyprink' string in
the bootargs. However, there's no earlyprink driver configured in the
defconfigs, so this does nothing.
A combination of setting stdout in the chosen node and adding earlycon
to bootargs causes early serial output to appear early. This changes all
boards to use this option.
The console=ttyS4,115200 option is still required, as this is used by
the run time uart driver.
Signed-off-by: Joel Stanley <joel@jms.id.au>
Acked-by: Andrew Jeffery <andrew@aj.id.au>
Acked-by: Alexander Filippov <a.filippov@yadro.com>
Link: https://lore.kernel.org/r/20210526051220.136432-1-joel@jms.id.au
Signed-off-by: Joel Stanley <joel@jms.id.au>
AST2600 supports 2 SGPIO master interfaces and 2 SGPIO slave interfaces.
Currently, only SGPIO master 1 and SGPIO slve 1 in the pinctrl dtsi.
SGPIO master 2 and slave 2 should be added in pinctrl dtsi as well.
Signed-off-by: Steven Lee <steven_lee@aspeedtech.com>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Joel Stanley <joel@jms.id.au>
Link: https://lore.kernel.org/r/20210525055308.31069-3-steven_lee@aspeedtech.com
Signed-off-by: Joel Stanley <joel@jms.id.au>
Allow the compiler to verify the type of the second argument passed to
scsi_host_complete_all_commands().
Link: https://lore.kernel.org/r/20210524025457.11299-4-bvanassche@acm.org
Cc: Hannes Reinecke <hare@suse.com>
Cc: John Garry <john.garry@huawei.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Make it possible for the compiler to verify whether SAM and host
status codes are used correctly.
[mkp: resolve conflicts with Hannes' SCSI result series]
Link: https://lore.kernel.org/r/20210524025457.11299-3-bvanassche@acm.org
Cc: Hannes Reinecke <hare@suse.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
of_address_to_resource() and of_pci_address_to_resource() are almost the
same except the former takes an index and the latter takes a BAR number.
Now that __of_get_address() can take either one, refactor the functions
to use a common implementation.
Cc: Frank Rowand <frowand.list@gmail.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20210527194547.1287934-5-robh@kernel.org
Convert address.c to use IS_ENABLED() instead of ifdefs for the
public PCI functions. This simplifies the ifdefs in of_address.h.
Cc: Frank Rowand <frowand.list@gmail.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20210527194547.1287934-4-robh@kernel.org
of_get_address() and of_get_pci_address() are the same implementation
except of_get_pci_address() takes the PCI BAR number rather than an
index. Modify the of_get_address() implementation to work on either
index or BAR and provide wrapper functions for the existing functions.
Cc: Frank Rowand <frowand.list@gmail.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20210527194547.1287934-3-robh@kernel.org
Add an empty stub for pci_register_io_range() when !CONFIG_PCI. It's needed
to convert of_pci_range_to_resource() to use IS_ENABLED(CONFIG_PCI).
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: linux-pci@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20210527194547.1287934-2-robh@kernel.org
fdt_init_reserved_mem() and fdt_reserved_mem_save_node() are private to
the DT code, so move there declarations to of_private.h. There's no need
for the dummy functions as CONFIG_OF_RESERVED_MEM is always enabled for
CONFIG_OF_EARLY_FLATTREE.
Cc: Frank Rowand <frowand.list@gmail.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20210527193841.1284169-1-robh@kernel.org
Reserved memory regions can be used for more than just DMA regions, so
only enabling on DMA_DECLARE_COHERENT (via HAS_DMA) or DMA_CMA is wrong.
This effectively doesn't matter except for the few cases arches select
NO_DMA.
At least, these users of RESERVEDMEM_OF_DECLARE depend on reserved memory
support:
arch/riscv/mm/init.c:RESERVEDMEM_OF_DECLARE(elfcorehdr, "linux,elfcorehdr", elfcore_hdr_setup);
drivers/memory/tegra/tegra210-emc-table.c:RESERVEDMEM_OF_DECLARE(tegra210_emc_table, "nvidia,tegra210-emc-table",
drivers/soc/fsl/qbman/bman_ccsr.c:RESERVEDMEM_OF_DECLARE(bman_fbpr, "fsl,bman-fbpr", bman_fbpr);
drivers/soc/fsl/qbman/qman_ccsr.c:RESERVEDMEM_OF_DECLARE(qman_fqd, "fsl,qman-fqd", qman_fqd);
drivers/soc/fsl/qbman/qman_ccsr.c:RESERVEDMEM_OF_DECLARE(qman_pfdr, "fsl,qman-pfdr", qman_pfdr);
Let's simplify things and enable OF_RESERVED_MEM when OF_EARLY_FLATTREE is
enabled.
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20210527223217.1572631-1-robh@kernel.org
"amlogic,meson-gxbb-scp-shmem" is already in the Generic on-chip SRAM
binding though "amlogic,meson-gxbb-scpi" is missing which is now added.
Also remove the whole old text format binding for the same.
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Kevin Hilman <khilman@baylibre.com>
Cc: Neil Armstrong <narmstrong@baylibre.com>
Cc: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20210601224904.917990-5-sudeep.holla@arm.com
Signed-off-by: Rob Herring <robh@kernel.org>
Commit a90b15e0ad ("Documentation: bindings: decouple juno specific
details from generic binding") moved the juno specific bindings into
separate file. Though there was no need for juno specific binding, it
has been used unfortunately for whatever stupid reason I added it for.
Let us move the same to the generic sram.yaml schema and remove the
old text format binding.
Cc: Rob Herring <robh+dt@kernel.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20210601224904.917990-4-sudeep.holla@arm.com
Signed-off-by: Rob Herring <robh@kernel.org>
Move the SRAM and shared memory binding for SCMI into the existing
Generic on-chip SRAM. We just need to update the compatible list and
there-by remove the whole old text format binding for the same.
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Cristian Marussi <cristian.marussi@arm.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20210601224904.917990-3-sudeep.holla@arm.com
Signed-off-by: Rob Herring <robh@kernel.org>
Move the SRAM and shared memory binding for SCPI into the existing
Generic on-chip SRAM. We just need to update the compatible list and
there-by remove the whole old text format binding for the same.
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Kevin Hilman <khilman@baylibre.com>
Cc: Neil Armstrong <narmstrong@baylibre.com>
Cc: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20210601224904.917990-2-sudeep.holla@arm.com
Signed-off-by: Rob Herring <robh@kernel.org>
Convert the current OMAP Mailbox binding from text format to YAML
format/DT schema, and delete the legacy text binding file.
The new YAML binding conversion is an updated version compared to
the original. The descriptions for certain properties have been
improved to provide more clarity. Constraints are added to the
properties 'ti,mbox-num-users', 'ti,mbox-num-fifos' and 'interrupts'.
The 'ti,hwmods' is a legacy property and is retained only to reflect
the existing usage on some older OMAP2 and OMAP3 platforms.
All the existing examples have also been updated to reflect the
latest dts nodes (ti,hwmods removed from OMAP4 and AM33xx examples,
and interrupts value updated for AM65x SoCs).
Signed-off-by: Suman Anna <s-anna@ti.com>
[robh: Update ref in ti,omap-remoteproc.yaml]
Link: https://lore.kernel.org/r/20210520234348.4479-1-s-anna@ti.com
Signed-off-by: Rob Herring <robh@kernel.org>
When running generic/527 with fast_commit configuration, the following
issue is seen on Power. With fast_commit, during ext4_fc_replay()
(which can be called from ext4_fill_super()), if inode eviction
happens then it can access an uninitialized percpu counter variable.
This patch adds the check before accessing the counters in
ext4_free_inode() path.
[ 321.165371] run fstests generic/527 at 2021-04-29 08:38:43
[ 323.027786] EXT4-fs (dm-0): mounted filesystem with ordered data mode. Opts: block_validity. Quota mode: none.
[ 323.618772] BUG: Unable to handle kernel data access on read at 0x1fbd80000
[ 323.619767] Faulting instruction address: 0xc000000000bae78c
cpu 0x1: Vector: 300 (Data Access) at [c000000010706ef0]
pc: c000000000bae78c: percpu_counter_add_batch+0x3c/0x100
lr: c0000000006d0bb0: ext4_free_inode+0x780/0xb90
pid = 5593, comm = mount
ext4_free_inode+0x780/0xb90
ext4_evict_inode+0xa8c/0xc60
evict+0xfc/0x1e0
ext4_fc_replay+0xc50/0x20f0
do_one_pass+0xfe0/0x1350
jbd2_journal_recover+0x184/0x2e0
jbd2_journal_load+0x1c0/0x4a0
ext4_fill_super+0x2458/0x4200
mount_bdev+0x1dc/0x290
ext4_mount+0x28/0x40
legacy_get_tree+0x4c/0xa0
vfs_get_tree+0x4c/0x120
path_mount+0xcf8/0xd70
do_mount+0x80/0xd0
sys_mount+0x3fc/0x490
system_call_exception+0x384/0x3d0
system_call_common+0xec/0x278
Cc: stable@kernel.org
Fixes: 8016e29f43 ("ext4: fast commit recovery path")
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/6cceb9a75c54bef8fa9696c1b08c8df5ff6169e2.1619692410.git.riteshh@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Shiraz Saleem says:
====================
Add Intel Ethernet Protocol Driver for RDMA (irdma)
The following patch series introduces a unified Intel Ethernet Protocol
Driver for RDMA (irdma) for the X722 iWARP device and a new E810 device
which supports iWARP and RoCEv2. The irdma module replaces the legacy
i40iw module for X722 and extends the ABI already defined for i40iw. It is
backward compatible with legacy X722 rdma-core provider (libi40iw).
X722 and E810 are PCI network devices that are RDMA capable. The RDMA
block of this parent device is represented via an auxiliary device
exported to 'irdma' using the core auxiliary bus infrastructure recently
added for 5.11 kernel. The parent PCI netdev drivers 'i40e' and 'ice'
register auxiliary RDMA devices with private data/ops encapsulated that
bind to auxiliary drivers registered in irdma module.
Currently, default is RoCEv2 for E810. Runtime support for protocol switch
to iWARP will be made available via devlink in a future patch.
====================
Link: https://lore.kernel.org/r/20210602205138.889-1-shiraz.saleem@intel.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
* branch 'irdma':
RDMA/irdma: Update MAINTAINERS file
RDMA/irdma: Add irdma Kconfig/Makefile and remove i40iw
RDMA/irdma: Add ABI definitions
RDMA/irdma: Add dynamic tracing for CM
RDMA/irdma: Add miscellaneous utility definitions
RDMA/irdma: Add user/kernel shared libraries
RDMA/irdma: Add RoCEv2 UD OP support
RDMA/irdma: Implement device supported verb APIs
RDMA/irdma: Add PBLE resource manager
RDMA/irdma: Add connection manager
RDMA/irdma: Add QoS definitions
RDMA/irdma: Add privileged UDA queue implementation
RDMA/irdma: Add HMC backing store setup functions
RDMA/irdma: Implement HW Admin Queue OPs
RDMA/irdma: Implement device initialization definitions
RDMA/irdma: Register auxiliary driver and implement private channel OPs
i40e: Register auxiliary devices to provide RDMA
i40e: Prep i40e header for aux bus conversion
ice: Register auxiliary device to provide RDMA
ice: Implement iidc operations
ice: Initialize RDMA support
iidc: Introduce iidc.h
i40e: Replace one-element array with flexible-array member
Add Kconfig and Makefile to build irdma driver.
Remove i40iw driver and add an alias in irdma.
Remove legacy exported symbols i40e_register_client
and i40e_unregister_client from i40e as they are no
longer used.
irdma is the replacement driver that supports X722.
Link: https://lore.kernel.org/r/20210602205138.889-16-shiraz.saleem@intel.com
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This patch defines the new template fields xattrnames, xattrlengths and
xattrvalues, which contain respectively a list of xattr names (strings,
separated by |), lengths (u32, hex) and values (hex). If an xattr is not
present, the name and length are not displayed in the measurement list.
Reported-by: kernel test robot <lkp@intel.com> (Missing prototype def)
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
Building the WQE descriptors for different verb
operations are similar in kernel and user-space.
Add these shared libraries.
Link: https://lore.kernel.org/r/20210602205138.889-12-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add the header, data structures and functions
to populate the WQE descriptors and issue the
Control QP commands that support RoCEv2 UD operations.
Link: https://lore.kernel.org/r/20210602205138.889-11-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Implement device supported verb APIs. The supported APIs
vary based on the underlying transport the ibdev is
registered as (i.e. iWARP or RoCEv2).
Link: https://lore.kernel.org/r/20210602205138.889-10-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Implement a Physical Buffer List Entry (PBLE) resource manager
to manage a pool of PBLE HMC resource objects.
Link: https://lore.kernel.org/r/20210602205138.889-9-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add definitions for managing the RDMA HW work scheduler (WS) tree.
A WS node is created via a control QP operation with the bandwidth
allocation, arbitration scheme, and traffic class of the QP specified.
The Qset handle returned associates the QoS parameters for the QP.
The Qset is registered with the LAN and an equivalent node is created
in the LAN packet scheduler tree.
Link: https://lore.kernel.org/r/20210602205138.889-7-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
HW uses host memory as a backing store for a number of
protocol context objects and queue state tracking.
The Host Memory Cache (HMC) is a component responsible for
managing these objects stored in host memory.
Add the functions and data structures to manage the allocation
of backing pages used by the HMC for the various objects
Link: https://lore.kernel.org/r/20210602205138.889-5-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The driver posts privileged commands to the HW
Admin Queue (Control QP or CQP) to request administrative
actions from the HW. Implement create/destroy of CQP
and the supporting functions, data structures and headers
to handle the different CQP commands
Link: https://lore.kernel.org/r/20210602205138.889-4-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Register auxiliary drivers which can attach to auxiliary RDMA
devices from Intel PCI netdev drivers i40e and ice. Implement the private
channel ops, and register net notifiers.
Link: https://lore.kernel.org/r/20210602205138.889-2-shiraz.saleem@intel.com
[flexible array transformation]
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Because this happens at high thread counts on high IOPS devices
doing mixed read/write AIO-DIO to a single file at about a million
iops:
64.09% 0.21% [kernel] [k] io_submit_one
- 63.87% io_submit_one
- 44.33% aio_write
- 42.70% xfs_file_write_iter
- 41.32% xfs_file_dio_write_aligned
- 25.51% xfs_file_write_checks
- 21.60% _raw_spin_lock
- 21.59% do_raw_spin_lock
- 19.70% __pv_queued_spin_lock_slowpath
This also happens of the IO completion IO path:
22.89% 0.69% [kernel] [k] xfs_dio_write_end_io
- 22.49% xfs_dio_write_end_io
- 21.79% _raw_spin_lock
- 20.97% do_raw_spin_lock
- 20.10% __pv_queued_spin_lock_slowpath
IOWs, fio is burning ~14 whole CPUs on this spin lock.
So, do an unlocked check against inode size first, then if we are
at/beyond EOF, take the spinlock and recheck. This makes the
spinlock disappear from the overwrite fastpath.
I'd like to report that fixing this makes things go faster. It
doesn't - it just exposes the the XFS_ILOCK as the next severe
contention point doing extent mapping lookups, and that now burns
all the 14 CPUs this spinlock was burning.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
xfs_bmap_set_attrforkoff is only used inside of xfs_bmap.c, so mark it
static.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>