Re: [RFC][PATCH] dax: Do not try to clear poison for partial pages

2020-01-30 Thread Christoph Hellwig
On Wed, Jan 29, 2020 at 04:03:37PM -0500, Vivek Goyal wrote: > I am looking into getting rid of dependency on block device in dax > path. One such place is __dax_zero_page_range() which checks if > range being zeroed is aligned to block device logical size, then > it calls bdev_issue_zeroout()

Re: [RFC] dax,pmem: Provide a dax operation to zero range of memory

2020-01-30 Thread Christoph Hellwig
On Thu, Jan 23, 2020 at 11:52:49AM -0500, Vivek Goyal wrote: > Hi, > > This is an RFC patch to provide a dax operation to zero a range of memory. > It will also clear poison in the process. This is primarily compile tested > patch. I don't have real hardware to test the poison logic. I am posting

Re: [PATCH 1/5] mm/memremap_pages: Kill unused __devm_memremap_pages()

2020-01-30 Thread Christoph Hellwig
On Thu, Jan 30, 2020 at 12:06:01PM -0800, Dan Williams wrote: > Kill this definition that was introduced in commit 41e94a851304 ("add > devm_memremap_pages") add never used. > > Cc: Christoph Hellwig > Signed-off-by: Dan Williams Looks good, Reviewed-by: Christoph Hellwig

Re: [PATCH 09/10] powerpc: Enable OpenCAPI Storage Class Memory driver on bare metal

2020-01-30 Thread Dan Williams
On Thu, Jan 30, 2020 at 8:57 PM Alastair D'Silva wrote: > > On Fri, 2019-11-08 at 08:10 +0100, Frederic Barrat wrote: > > > > Le 25/10/2019 à 06:47, Alastair D'Silva a écrit : > > > From: Alastair D'Silva > > > > > > Enable OpenCAPI Storage Class Memory driver on bare metal > > > > > >

Re: [PATCH 09/10] powerpc: Enable OpenCAPI Storage Class Memory driver on bare metal

2020-01-30 Thread Alastair D'Silva
On Fri, 2019-11-08 at 08:10 +0100, Frederic Barrat wrote: > > Le 25/10/2019 à 06:47, Alastair D'Silva a écrit : > > From: Alastair D'Silva > > > > Enable OpenCAPI Storage Class Memory driver on bare metal > > > > Signed-off-by: Alastair D'Silva > > --- > >

Re: [PATCH v6] mm/pgmap: Use correct alignment when looking at first pfn from a region

2020-01-30 Thread Andrew Morton
On Tue, 3 Dec 2019 15:42:28 +0530 "Aneesh Kumar K.V" wrote: > On 12/3/19 6:20 AM, Dan Williams wrote: > > On Sat, Nov 30, 2019 at 3:13 PM Andrew Morton > > wrote: > >> > >> On Wed, 25 Sep 2019 09:21:02 +0530 "Aneesh Kumar K.V" > >> wrote: > >> > >>> Andrew Morton writes: > >>> > On

Re: [ndctl PATCH v2] ndctl/lib: fix symbol redefinitions reported by GCC10

2020-01-30 Thread Dan Williams
On Thu, Jan 30, 2020 at 4:40 PM Vishal Verma wrote: > > A toolchain update in Fedora 32 caused new compile errors due to > multiple definitions of dimm_ops structures. The declarations in > 'private.h' for the various NFIT families are present so that libndctl > can find all the per-family

[ndctl PATCH v2] ndctl/lib: fix symbol redefinitions reported by GCC10

2020-01-30 Thread Vishal Verma
A toolchain update in Fedora 32 caused new compile errors due to multiple definitions of dimm_ops structures. The declarations in 'private.h' for the various NFIT families are present so that libndctl can find all the per-family dimm-ops. However they need to be declared as extern because the

[ndctl PATCH 0/2] ndctl: Cross-arch compatible namespace alignment

2020-01-30 Thread Dan Williams
A follow-up to the region-align kernel enabling, [1], update ndctl to enumerate region alignment, and update the unit tests to account for the kernel's default compatible alignment. Given that changing the default is a surefire way to create incompatible namespaces I do not think it makes sense

[ndctl PATCH 2/2] ndctl/namespace: Improve namespace action failure messages

2020-01-30 Thread Dan Williams
With the new kernel updates to enforce wider alignment constraints by default, it is increasingly important to report why provisioning failed. Move some debug messages to error messages when they indicate a hard failure, and drop the generic message when something more precise has been emitted.

[ndctl PATCH 1/2] ndctl/region: Support ndctl_region_{get, set}_align()

2020-01-30 Thread Dan Williams
Add support for the new kernel facility to set space alignment constraints at the region level. Update the unit tests to bypass the default 16MiB alignment constraint. Add the new parameter to the default region listing given how central it is to understanding the valid values for

Re: Re: SOA - 23-12-19 - QIHUA MANUFACTURERS SOA linux-nvdimm@lists.01.org

2020-01-30 Thread Purchase Service
Greetings, Please find the revised attached statement of account for your kind confirmation. We will be remitting payment this week before the Chinese new year . Feel free to contact me for any further clarification. --- Kind regards, Khac Lee Chun Purchase

[PATCH 4/5] libnvdimm/region: Introduce NDD_LABELING

2020-01-30 Thread Dan Williams
The NDD_ALIASING flag is used to indicate where pmem capacity might alias with blk capacity and require labeling. It is also used to indicate whether the DIMM supports labeling. Separate this latter capability into its own flag so that the NDD_ALIASING flag is scoped to true aliased

[PATCH 5/5] libnvdimm/region: Introduce an 'align' attribute

2020-01-30 Thread Dan Williams
The align attribute applies an alignment constraint for namespace creation in a region. Whereas the 'align' attribute of a namespace applied alignment padding via an info block, the 'align' attribute applies alignment constraints to the free space allocation. The default for 'align' is the

[PATCH 3/5] libnvdimm/namespace: Enforce memremap_compat_align()

2020-01-30 Thread Dan Williams
The pmem driver on PowerPC crashes with the following signature when instantiating misaligned namespaces that map their capacity via memremap_pages(). BUG: Unable to handle kernel data access at 0xc00100040600 Faulting instruction address: 0xc0090790 NIP [c0090790]

[PATCH 2/5] mm/memremap_pages: Introduce memremap_compat_align()

2020-01-30 Thread Dan Williams
The "sub-section memory hotplug" facility allows memremap_pages() users like libnvdimm to compensate for hardware platforms like x86 that have a section size larger than their hardware memory mapping granularity. The compensation that sub-section support affords is being tolerant of physical

[PATCH 1/5] mm/memremap_pages: Kill unused __devm_memremap_pages()

2020-01-30 Thread Dan Williams
Kill this definition that was introduced in commit 41e94a851304 ("add devm_memremap_pages") add never used. Cc: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/io.h |2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/io.h b/include/linux/io.h index

[PATCH 0/5] libnvdimm: Cross-arch compatible namespace alignment

2020-01-30 Thread Dan Williams
Aneesh reports that PowerPC requires 16MiB alignment for the address range passed to devm_memremap_pages(), and Jeff reports that it is possible to create a misaligned namespace which blocks future namespace creation in that region. Both of these issues require namespace alignment to be managed at

Re: [ndctl PATCH] ndctl/lib: make dimm_ops in private.h extern

2020-01-30 Thread Verma, Vishal L
On Thu, 2020-01-30 at 11:03 -0800, Dan Williams wrote: > On Thu, Jan 30, 2020 at 10:56 AM Vishal Verma > wrote: > > A toolchain update in Fedora 32 caused new compile errors due to > > multiple definitions of dimm_ops structures. The declarations in > > 'private.h' for the various NFIT families

Re: [ndctl PATCH] ndctl/lib: make dimm_ops in private.h extern

2020-01-30 Thread Dan Williams
On Thu, Jan 30, 2020 at 10:56 AM Vishal Verma wrote: > > A toolchain update in Fedora 32 caused new compile errors due to > multiple definitions of dimm_ops structures. The declarations in > 'private.h' for the various NFIT families are present so that libndctl > can find all the per-family

[ndctl PATCH] ndctl/lib: make dimm_ops in private.h extern

2020-01-30 Thread Vishal Verma
A toolchain update in Fedora 32 caused new compile errors due to multiple definitions of dimm_ops structures. The declarations in 'private.h' for the various NFIT families are present so that libndctl can find all the per-family dimm-ops. However they need to be declared as extern because the

NEW BUSINESS PURCHASE ORDER

2020-01-30 Thread Kalit
___ Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org To unsubscribe send an email to linux-nvdimm-le...@lists.01.org