On Thu, Oct 12, 2017 at 10:41:39AM -0700, Dan Williams wrote:
> So, you're jumping into this review at v9 where I've split the patches
> that take an initial MAP_DIRECT lease out from the patches that take
> FL_LAYOUT leases at memory registration time. You can see a previous
> attempt in "[PATCH v
On Thu, Oct 12, 2017 at 01:10:33PM -0700, Dan Williams wrote:
> On Thu, Oct 12, 2017 at 11:27 AM, Jason Gunthorpe
> wrote:
> > On Tue, Oct 10, 2017 at 01:17:26PM -0700, Dan Williams wrote:
> >
> >> Also keep in mind that what triggers the lease break is another
> >> application trying to write or
Let's use the same logging scheme as libndctl where we have 'struct
log_ctx' and the the log function can be set to a custom routine. That
way we can redirect log messages to syslog or structured json output
simply by changing log_ctx.log_fn.
Thinking further about this, using log_ctx is probably
On Thu, Oct 12, 2017 at 08:10:10AM +1100, Dave Chinner wrote:
> On Wed, Oct 11, 2017 at 09:54:15PM +0800, Xiong Zhou wrote:
> > On Mon, Sep 25, 2017 at 10:49:03AM +0200, Carlos Maiolino wrote:
> > > On Mon, Sep 25, 2017 at 01:40:06AM +, Xiong Zhou wrote:
> > > > Hi,
> > > >
> > > > ffsb test w
The new error injection command allows us to inject errors that persist
through changing the mode of a BTT namespace to 'raw' and back. This
allows us to test error clearing with a BTT by adding a selective error
block to the raw namespace, enabling the BTT, and then clearing it via a
write.
Cc: D
Add a new unit test to test all the features of the inject-error
command.
Cc: Dan Williams
Signed-off-by: Vishal Verma
---
test/Makefile.am | 3 +-
test/inject-error.sh | 120 +++
2 files changed, 122 insertions(+), 1 deletion(-)
create mod
Until now, various unit tests related to error handling used to expect
'canned' errors to be present in the middle of every nfit_test
namespace. With the ACPI error injection patches for nfit_test, this is
no longer the case. Update the existing unit tests it inject any errors
they need for testing
v2:
patch 1:
- use poll() instead of a sleep loop when waiting for a scrub. (Dan)
patch 2 (new):
- move the acpi nfit specific routines into generic wrappers exported
by the library. (Dan)
patch 3:
- rename 'clear' to 'uninject' use 'block' instead of 'sector' (Dan)
- cleanup th
Add an inject-error command to ndctl. This uses the error injection DSMs
in ACPI6.2 to provide a generic error injection and management
interface. Once can inject errors, and view as well as clear injected
errors using these commands.
Cc: Dan Williams
Signed-off-by: Vishal Verma
---
Documentati
Add interfaces to enable error injection commands. Add nfit specific
error injection helpers in ndctl/lib/nfit.c, and generic wrappers for
them in libndctl.
Cc: Dan Williams
Signed-off-by: Vishal Verma
---
ndctl/lib/Makefile.am | 1 +
ndctl/lib/inject.c | 391
The kernel uses sysfs to notify userspace of the number of completed
Address Range Scrubs, as well as any ongoing scrubs. Add libndctl
helpers to get the scrub count, and to wait for an in-progress scrub to
complete.
Cc: Dan Williams
Signed-off-by: Vishal Verma
---
ndctl/lib/libndctl.c | 100
linux-nvdimm
您好!课题内容在附件,请查收
___
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
> > Dan,
> >
> > I have a query regarding below patch [*]. My assumption is its halted
> > because of memory hotplug restructuring work? Anything I am missing
> > here?
> >
> > [*] https://www.mail-archive.com/linux-nvdimm@lists.01.org/msg02978.html
>
> It's fallen to the back of my queue since t
On Thu, Oct 12, 2017 at 3:52 PM, Pankaj Gupta wrote:
> Dan,
>
> I have a query regarding below patch [*]. My assumption is its halted
> because of memory hotplug restructuring work? Anything I am missing
> here?
>
> [*] https://www.mail-archive.com/linux-nvdimm@lists.01.org/msg02978.html
It's fal
> > > wrote:
> > > >
> > > > > > This patch adds virtio-pmem driver for KVM guest.
> > > > > > Guest reads the persistent memory range information
> > > > > > over virtio bus from Qemu and reserves the range
> > > > > > as persistent memory. Guest also allocates a block
> > > > > > devi
> > > >
> > > > > > This patch adds virtio-pmem driver for KVM guest.
> > > > > > Guest reads the persistent memory range information
> > > > > > over virtio bus from Qemu and reserves the range
> > > > > > as persistent memory. Guest also allocates a block
> > > > > > device correspondi
On Thu, 2017-10-12 at 18:18 -0400, Pankaj Gupta wrote:
> >
> > On Thu, Oct 12, 2017 at 2:25 PM, Pankaj Gupta
> > wrote:
> > >
> > > > > This patch adds virtio-pmem driver for KVM guest.
> > > > > Guest reads the persistent memory range information
> > > > > over virtio bus from Qemu and re
>
> On Thu, Oct 12, 2017 at 2:25 PM, Pankaj Gupta wrote:
> >
> >> > This patch adds virtio-pmem driver for KVM guest.
> >> > Guest reads the persistent memory range information
> >> > over virtio bus from Qemu and reserves the range
> >> > as persistent memory. Guest also allocates a blo
linux-nvdimm
亲,附 件 详 细 内 容 请 您 查 阅
___
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
On Thu, Oct 12, 2017 at 2:25 PM, Pankaj Gupta wrote:
>
>> > This patch adds virtio-pmem driver for KVM guest.
>> > Guest reads the persistent memory range information
>> > over virtio bus from Qemu and reserves the range
>> > as persistent memory. Guest also allocates a block
>> > device
>
> On Thu, Oct 12, 2017 at 8:50 AM, Pankaj Gupta wrote:
> > This patch moves common code to base header files
> > so that it can be used for both ACPI pmem and VIRTIO pmem
> > drivers. More common code needs to be moved out in future
> > based on functionality required for virtio_pmem drive
> > This patch adds virtio-pmem driver for KVM guest.
> > Guest reads the persistent memory range information
> > over virtio bus from Qemu and reserves the range
> > as persistent memory. Guest also allocates a block
> > device corresponding to the pmem range which later
> > can be ac
On Thu, Oct 12, 2017 at 8:50 AM, Pankaj Gupta wrote:
> This patch adds virtio-pmem driver for KVM guest.
> Guest reads the persistent memory range information
> over virtio bus from Qemu and reserves the range
> as persistent memory. Guest also allocates a block
> device corresponding to
On Thu, Oct 12, 2017 at 8:50 AM, Pankaj Gupta wrote:
> This patch moves common code to base header files
> so that it can be used for both ACPI pmem and VIRTIO pmem
> drivers. More common code needs to be moved out in future
> based on functionality required for virtio_pmem driver and
> coupl
On Thu, Oct 12, 2017 at 11:27 AM, Jason Gunthorpe
wrote:
> On Tue, Oct 10, 2017 at 01:17:26PM -0700, Dan Williams wrote:
>
>> Also keep in mind that what triggers the lease break is another
>> application trying to write or punch holes in a file that is mapped
>> for RDMA. So, if the hardware can'
On Tue, Oct 10, 2017 at 01:17:26PM -0700, Dan Williams wrote:
> Also keep in mind that what triggers the lease break is another
> application trying to write or punch holes in a file that is mapped
> for RDMA. So, if the hardware can't handle the iommu mapping getting
> invalidated asynchronously
On Thu, Oct 12, 2017 at 7:23 AM, Christoph Hellwig wrote:
> Sorry for chiming in so late, been extremely busy lately.
>
> From quickly glacing over what the now finally described use case is
> (which contradicts the subject btw - it's not about flushing, it's
> about not removing block mapping und
On Thu, Oct 12, 2017 at 6:51 AM, Jan Kara wrote:
>
> When thinking a bit more about this I've realized one problem: Currently
> user can call mmap() with MAP_SHARED type and MAP_SYNC or MAP_DIRECT flags
> and he will get the new semantics (if the kernel happens to support it). I
> think that is u
On Mon, Sep 11, 2017 at 11:05:26PM -0600, Ross Zwisler wrote:
> The following commit:
>
> commit 9b7365fc1c82 ("ext4: add FS_IOC_FSSETXATTR/FS_IOC_FSGETXATTR
> interface support")
>
> added several defines related to extended attributes to ext4.h. They were
> added within an #ifndef FS_IOC_FSGET
On Tue, Sep 12, 2017 at 08:46:12AM +0200, Jan Kara wrote:
> On Mon 11-09-17 23:05:25, Ross Zwisler wrote:
> > This helper, in the spirit of ext4_should_dioread_nolock() et al., replaces
> > the complex conditional in ext4_set_inode_flags().
> >
> > Signed-off-by: Ross Zwisler
>
> Yeah, makes sen
On Mon, Sep 11, 2017 at 11:05:23PM -0600, Ross Zwisler wrote:
> The current code has the potential for data corruption when changing an
> inode's journaling mode, as that can result in a subsequent unsafe change
> in S_DAX.
>
> I've captured an instance of this data corruption in the following fst
On Mon, Sep 11, 2017 at 11:05:22PM -0600, Ross Zwisler wrote:
> If an inode has inline data it is currently prevented from using DAX by a
> check in ext4_set_inode_flags(). When the inode grows inline data via
> ext4_create_inline_data() or removes its inline data via
> ext4_destroy_inline_data_no
This patch adds virtio-pmem Qemu device.
This device configures memory address range information with file
backend type. It acts like persistent memory device for KVM guest.
It presents the memory address range to virtio-pmem driver over
virtio channel and does the block flush whenever there
This patch adds virtio-pmem driver for KVM guest.
Guest reads the persistent memory range information
over virtio bus from Qemu and reserves the range
as persistent memory. Guest also allocates a block
device corresponding to the pmem range which later
can be accessed with DAX compatibl
This patch moves common code to base header files
so that it can be used for both ACPI pmem and VIRTIO pmem
drivers. More common code needs to be moved out in future
based on functionality required for virtio_pmem driver and
coupling of code with existing ACPI pmem driver.
Signed-off-by: Pan
We are sharing the prototype version of 'fake DAX' flushing
interface for the initial feedback. This is still work in progress
and not yet ready for merging.
Prototype right now just implements basic functionality without advanced
features with two major parts:
- Qemu virtio-pmem device
It expo
Sorry for chiming in so late, been extremely busy lately.
>From quickly glacing over what the now finally described use case is
(which contradicts the subject btw - it's not about flushing, it's
about not removing block mapping under a MR) and the previous comments
I think that mmap is simply the
Hi,
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 680506faceae..2649c00581a0 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -1389,6 +1389,18 @@ unsigned long do_mmap(struct file *file, unsigned long
> addr,
> struct inode *inode = file_inode(file);
>
> switch (flags
> On Thu, Oct 12, 2017 at 12:21:46AM +0530, Pankaj Gupta wrote:
> > We are sharing the prototype version of 'fake DAX' flushing
> > interface for the initial feedback. This is still work in progress
> > and not yet ready for merging.
> >
> > Protoype right now just implements basic functionality
On Thu, Oct 12, 2017 at 12:21:46AM +0530, Pankaj Gupta wrote:
> We are sharing the prototype version of 'fake DAX' flushing
> interface for the initial feedback. This is still work in progress
> and not yet ready for merging.
>
> Protoype right now just implements basic functionality without advan
40 matches
Mail list logo