The stripe cache has two goals:
1. cache data, so next time if data can be found in stripe cache, disk access
can be avoided.
2. stable data. data is copied from bio to stripe cache and calculated parity.
data written to disk is from stripe cache, so if upper layer changes bio data,
data written to disk isn't impacted.
In my environment, I can guarantee 2 will not happen. And BDI_CAP_STABLE_WRITES
can guarantee 2 too. For 1, it's not common too. block plug mechanism will
dispatch a bunch of sequentail small requests together. And since I'm using
SSD, I'm using small chunk size. It's rare case stripe cache is really useful.
So I'd like to avoid the copy from bio to stripe cache and it's very helpful
for performance. In my 1M randwrite tests, avoid the copy can increase the
performance more than 30%.
Of course, this shouldn't be enabled by default. It's reported enabling
BDI_CAP_STABLE_WRITES can harm some workloads before, so I added an option to
control it.
Neilb:
changed BUG_ON to WARN_ON
Removed some assignments from raid5_build_block which are now not needed.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
file_page_index(store, 0) is *always* 0.
This is because the bitmap sb, at 256 bytes, is *always* less than
one page.
So subtracting it has no effect and the code should be removed.
Reported-by: Goldwyn Rodrigues <rgoldwyn@suse.de>
Signed-off-by: NeilBrown <neilb@suse.de>
The (lockless) release_list reduces lock contention, but there is excessive
queueing and dequeuing of stripes on this list. A stripe will currently be
queued on the release_list with a stripe reference count > 1. This can cause
the raid5 kernel thread(s) to dequeue the stripe and decrement the refcount
without doing any other useful processing of the stripe. The are two cases
when the stripe can be put on the release_list multiple times before it is
actually handled by the kernel thread(s).
1) make_request() activates the stripe processing in 4k increments. When a
write request is large enough to span multiple chunks of a stripe_head, the
first 4k chunk adds the stripe to the plug list. The next 4k chunk that is
processed for the same stripe puts the stripe on the release_list with a
refcount=2. This can cause the kernel thread to process and decrement the
stripe before the stripe us unplugged, which again will put it back on the
release_list.
2) Whenever IO is scheduled on a stripe (pre-read and/or write), the stripe
refcount is set to the number of active IO (for each chunk). The stripe is
released as each IO complete, and can be queued and dequeued multiple times
on the release_list, until its refcount finally reached zero.
This simple patch will ensure a stripe is only queued on the release_list when
its refcount=1 and is ready to be handled by the kernel thread(s). I added some
instrumentation to raid5 and counted the number of times striped were queued on
the release_list for a variety of write IO sizes. Without this patch the number
of times stripes got queued on the release_list was 100-500% higher than with
the patch. The excess queuing will increase with the IO size. The patch also
improved throughput by 5-10%.
Signed-off-by: Eivind Sarto <esarto@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Julia Lawall and coccinelle report that md_clear_badblocks always
returns 0, despite appearing to have an error path.
The error path really should return an error code. ENOSPC is
reasonably appropriate.
Reported-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: NeilBrown <neilb@suse.de>
If it is found that we need to pre-read some blocks before a write
can succeed, we normally set STRIPE_DELAYED and don't actually perform
the read until STRIPE_PREREAD_ACTIVE subsequently gets set.
However for a degraded RAID6 we currently perform the reads as soon
as we see that a write is pending. This significantly hurts
throughput.
So:
- when handle_stripe_dirtying find a block that it wants on a device
that is failed, set STRIPE_DELAY, instead of doing nothing, and
- when fetch_block detects that a read might be required to satisfy a
write, only perform the read if STRIPE_PREREAD_ACTIVE is set,
and if we would actually need to read something to complete the write.
This also helps RAID5, though less often as RAID5 supports a
read-modify-write cycle. For RAID5 the read is performed too early
only if the write is not a full 4K aligned write (i.e. no an
R5_OVERWRITE).
Also clean up a couple of horrible bits of formatting.
Reported-by: Patrik Horník <patrik@dsl.sk>
Signed-off-by: NeilBrown <neilb@suse.de>
read-only arrays should not be changed. This includes changing
the level, layout, size, or number of devices.
So reject those changes for readonly arrays.
Signed-off-by: NeilBrown <neilb@suse.de>
Commit 8313b8e57f
md: fix problem when adding device to read-only array with bitmap.
added a called to md_reap_sync_thread() which cause a reshape thread
to be interrupted (in particular, it could cause md_thread() to never even
call md_do_sync()).
However it didn't set MD_RECOVERY_INTR so ->finish_reshape() would not
know that the reshape didn't complete.
This only happens when mddev->ro is set and normally reshape threads
don't run in that situation. But raid5 and raid10 can start a reshape
thread during "run" is the array is in the middle of a reshape.
They do this even if ->ro is set.
So it is best to set MD_RECOVERY_INTR before abortingg the
sync thread, just in case.
Though it rare for this to trigger a problem it can cause data corruption
because the reshape isn't finished properly.
So it is suitable for any stable which the offending commit was applied to.
(3.2 or later)
Fixes: 8313b8e57f
Cc: stable@vger.kernel.org (3.2+)
Signed-off-by: NeilBrown <neilb@suse.de>
Let's switch the driver to use managed resources, this will simplify
error handling and driver unbinding logic.
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Let's switch the driver to use managed resources, this will simplify
error handling and driver unbinding logic.
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Let's switch the driver to use managed resources, this will simplify error
handling and allows us to get rid of da9034_touch_remove().
Signed-off-by: Himangi Saraogi <himangi774@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Let's switch the driver to use managed resources, this will simplify
error handling and driver unbinding logic.
Signed-off-by: Beomho Seo <beomho.seo@samsung.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
This patch fix a typo error in MELFAS MCS-5000 controller driver.
Signed-off-by: Beomho Seo <beomho.seo@samsung.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
This patch fix a typo error in mms114 touchscreen driver.
Signed-off-by: Beomho Seo <beomho.seo@samsung.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
This patch fix a typo error in MELFAS 5000/5080 controller driver.
Signed-off-by: Beomho Seo <beomho.seo@samsung.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Check for NULL before using the acl in the access type switch
statement. This seems to be consistent with what is done in the JFFS
and ext4 filesystems and with the behaviour of JFS in the 3.13 kernel.
The bug seemed to be introduced in commit 2cc6a5a0.
The bug results in a kernel Oops, NULL dereference could not be handled
when accessing a JFS filesystem. The rdiff-backup process seemed to
trigger the bug. See also reported bug #75341:
https://bugzilla.kernel.org/show_bug.cgi?id=75341
Signed-off-by: William Burrow <wbkernel@gmail.com>
Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Handling calls to ->target_index() has got complex over time and might become
more complex. So, its better to take target_index() bits out in another routine
__target_index() for better code readability. Shouldn't have any functional
impact.
Tested-by: Stephen Warren <swarren@nvidia.com>
Reviewed-by: Doug Anderson <dianders@chromium.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
In "-n" mode, reserved tables (RSDP/RSDT/XSDT/DSDT/FACS) are dumped
multiple times due a missing instance check in osl_get_bios_table().
This patch fixes this issue.
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
The gpmi's IP for imx6sx is nearly the same as the gpmi's IP for imx6q,
except the following two new features:
(1) the new BCH contoller has 62-BIT correcting ECC strength
(The BCH for imx6q only has 40-BIT ECC strength).
(2) add the hardware Randomizer support.
This patch does the follow changes:
(1) add a new macro GPMI_IS_MX6SX to represent the imx6sx's gpmi.
(2) add a new macro GPMI_IS_MX6.
We use this macro to initialize the same registers for both
imx6sx and imx6q, and so on.
(3) add a new gpmi_devdata instance, the gpmi_devdata_imx6sx, for
imx6sx.
Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
These functions are almost identical on both the read and write side.
FLUSH_COND_STABLE will never be set for the read path, so leaving it in
the generic code won't hurt anything.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
At this point, the read and write versions of this function look
identical so both should use the same function.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Write adds a little bit of code dealing with flush flags, but since
"how" will always be 0 when reading we can share the code.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
The read and write paths set up this struct in exactly the same way, so
create a single shared struct.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Combining these functions will let me make a single nfs_rw_common_ops
struct (see the next patch).
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
The read and write paths do exactly the same thing for the rpc_prepare
rpc_op. This patch combines them together into a single function.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
I create a new struct nfs_rw_ops to decide the differences between reads
and writes. This struct will be set when initializing a new
nfs_pgio_descriptor, and then passed on to the nfs_rw_header when a new
header is allocated.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
These functions are identical for the read and write paths so they can
be combined.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
The header had a pointer to the verifier that was set from the old write
data struct. We don't need to keep the pointer around now that we have
shared structures.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
* pci/misc:
PCI: Fix return value from pci_user_{read,write}_config_*()
PCI: Turn pcibios_penalize_isa_irq() into a weak function
PCI: Test for std config alias when testing extended config space
* pci/hotplug:
PCI: cpqphp: Fix possible null pointer dereference
NVMe: Implement PCIe reset notification callback
PCI: Notify driver before and after device reset
* pci/pci_is_bridge:
pcmcia: Use pci_is_bridge() to simplify code
PCI: pciehp: Use pci_is_bridge() to simplify code
PCI: acpiphp: Use pci_is_bridge() to simplify code
PCI: cpcihp: Use pci_is_bridge() to simplify code
PCI: shpchp: Use pci_is_bridge() to simplify code
PCI: rpaphp: Use pci_is_bridge() to simplify code
sparc/PCI: Use pci_is_bridge() to simplify code
powerpc/PCI: Use pci_is_bridge() to simplify code
ia64/PCI: Use pci_is_bridge() to simplify code
x86/PCI: Use pci_is_bridge() to simplify code
PCI: Use pci_is_bridge() to simplify code
PCI: Add new pci_is_bridge() interface
PCI: Rename pci_is_bridge() to pci_has_subordinate()
* pci/virtualization:
PCI: Introduce new device binding path using pci_dev.driver_override
Conflicts:
drivers/pci/pci-sysfs.c
* pci/host-exynos:
PCI: exynos: Remove unnecessary OOM messages
* pci/host-rcar:
PCI: rcar: Add gen2 device tree support
PCI: rcar: Add R-Car PCIe device tree bindings
PCI: rcar: Add MSI support for PCIe
PCI: rcar: Add Renesas R-Car PCIe driver
PCI: rcar: Use new OF interrupt mapping when possible
* pci/amd-numa:
x86/PCI: Clean up and mark early_root_info_init() as deprecated
x86/PCI: Work around AMD Fam15h BIOSes that fail to provide _PXM
x86/PCI: Warn if we have to "guess" host bridge node information
The only difference is the write verifier field, but we can keep that
for a little bit longer.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Since (a few releases before) v2.6.0 there have been checks for
CONFIG_MTD_SUPERH_RESERVE. One check is still present. But a Kconfig
symbol MTD_SUPERH_RESERVE has never been added. So a few lines of dead
code can be removed.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
At this point, the only difference between nfs_read_data and
nfs_write_data is the write verifier.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reads and writes have very similar results. This patch combines the two
structs together with comments to show where the differing fields are
used.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reads and writes have very similar arguments. This patch combines them
together and documents the few fields used only by write.
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
The driver_override field allows us to specify the driver for a device
rather than relying on the driver to provide a positive match of the
device. This shortcuts the existing process of looking up the vendor and
device ID, adding them to the driver new_id, binding the device, then
removing the ID, but it also provides a couple advantages.
First, the above existing process allows the driver to bind to any device
matching the new_id for the window where it's enabled. This is often not
desired, such as the case of trying to bind a single device to a meta
driver like pci-stub or vfio-pci. Using driver_override we can do this
deterministically using:
echo pci-stub > /sys/bus/pci/devices/0000:03:00.0/driver_override
echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind
echo 0000:03:00.0 > /sys/bus/pci/drivers_probe
Previously we could not invoke drivers_probe after adding a device to
new_id for a driver as we get non-deterministic behavior whether the driver
we intend or the standard driver will claim the device. Now it becomes a
deterministic process, only the driver matching driver_override will probe
the device.
To return the device to the standard driver, we simply clear the
driver_override and reprobe the device:
echo > /sys/bus/pci/devices/0000:03:00.0/driver_override
echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind
echo 0000:03:00.0 > /sys/bus/pci/drivers_probe
Another advantage to this approach is that we can specify a driver override
to force a specific binding or prevent any binding. For instance when an
IOMMU group is exposed to userspace through VFIO we require that all
devices within that group are owned by VFIO. However, devices can be
hot-added into an IOMMU group, in which case we want to prevent the device
from binding to any driver (override driver = "none") or perhaps have it
automatically bind to vfio-pci. With driver_override it's a simple matter
for this field to be set internally when the device is first discovered to
prevent driver matches.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Alexander Graf <agraf@suse.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Lists of endpoints are stored for bandwidth calculation for roothub ports.
Make sure we remove all endpoints from the list before the whole device,
containing its endpoints list_head stuctures, is freed.
This used to be done in the wrong order in xhci_mem_cleanup(),
and triggered an oops in resume from S4 (hibernate).
Cc: stable <stable@vger.kernel.org>
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The quirk is intended to be extremely generic, but we only apply it to
known offending devices.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=44881
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Several PCIe-to-PCI bridges fail to provide a PCIe capability, causing us
to handle them as conventional PCI devices when they really use the
requester ID of the secondary bus. We need to differentiate these from
PCIe-to-PCI bridges that actually use the conventional PCI ID when a PCIe
capability is not present, such as those found on the root complex of may
Intel chipsets. Add a dev_flag bit to identify devices to be handled as
standard PCIe-to-PCI bridges.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
The read_pageio_init method is just a very convoluted way to grab the
right nfs_pageio_ops vector. The vector to chose is not a choice of
protocol version, but just a pNFS vs MDS I/O choice that can simply be
done inside nfs_pageio_init_read based on the presence of a layout
driver, and a new force_mds flag to the special case of falling back
to MDS I/O on a pNFS-capable volume.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
The write_pageio_init method is just a very convoluted way to grab the
right nfs_pageio_ops vector. The vector to chose is not a choice of
protocol version, but just a pNFS vs MDS I/O choice that can simply be
done inside nfs_pageio_init_write based on the presence of a layout
driver, and a new force_mds flag to the special case of falling back
to MDS I/O on a pNFS-capable volume.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Several Marvell devices and a JMicron device have a similar DMA requester
ID problem to Ricoh, except they use function 1 as the PCIe requester ID.
Add a quirk for these to populate the DMA alias with the correct devfn.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=42679
Tested-by: George Spelvin <linux@horizon.com>
Tested-by: Andreas Schrägle <ajs124.ajs124@gmail.com>
Tested-by: Tobias N <qemu@suppser.de>
Tested-by: <daxcore@online.de>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
A sparse error fixup removed a htons() which is required for the driver
to function. This patch puts the htons() back and fixes the sparse
warning correctly by changing the left side cast.
Signed-off-by: Sean MacLennan <seanm@seanm.ca>
Cc: stable <stable@vger.kernel.org> # 3.14
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
"fdatasync() is similar to fsync(), but does not flush modified metadata
unless that metadata is needed in order to allow a subsequent data
retrieval to be correctly handled."
We absolutely need to commit the layouts to be able to retrieve the data
in case either the client, the server or the storage subsystem go down.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Casting value returned by k[cmz]alloc is useless.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Casting value returned by k[cmz]alloc is useless.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Casting value returned by k[cmz]alloc is useless.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
