Invitation to Bid

2020-04-14 Thread Frank Bakker
Good day, The municipality would like to extend an invitation to your company to supply the attached product(s). Some of the product(s) that we may request may fall out of your scope of work, Therefore we would like you to outsource for the product(s) and supply the Municipality as we are

[PATCH v3] mm/memory_hotplug: refrain from adding memory into an impossible node

2020-04-14 Thread Vishal Verma
A misbehaving qemu created a situation where the ACPI SRAT table advertised one fewer proximity domains than intended. The NFIT table did describe all the expected proximity domains. This caused the device dax driver to assign an impossible target_node to the device, and when hotplugged as system

Re: [PATCH v2] mm/memory_hotplug: refrain from adding memory into an impossible node

2020-04-14 Thread Dan Williams
On Tue, Apr 14, 2020 at 3:50 PM Vishal Verma wrote: > > A misbehaving qemu created a situation where the ACPI SRAT table > advertised one fewer proximity domains than intended. The NFIT table did > describe all the expected proximity domains. This caused the device dax > driver to assign an

[PATCH v2] mm/memory_hotplug: refrain from adding memory into an impossible node

2020-04-14 Thread Vishal Verma
A misbehaving qemu created a situation where the ACPI SRAT table advertised one fewer proximity domains than intended. The NFIT table did describe all the expected proximity domains. This caused the device dax driver to assign an impossible target_node to the device, and when hotplugged as system

Re: [PATCH 20/20] fuse,virtiofs: Add logic to free up a memory range

2020-04-14 Thread Vivek Goyal
On Sat, Mar 28, 2020 at 06:06:06AM +0800, Liu Bo wrote: > On Fri, Mar 27, 2020 at 10:01:14AM -0400, Vivek Goyal wrote: > > On Thu, Mar 26, 2020 at 08:09:05AM +0800, Liu Bo wrote: > > > > [..] > > > > +/* > > > > + * Find first mapping in the tree and free it and return it. Do not add > > > > + *

Re: [PATCH] dax/kmem: refrain from adding memory into an impossible node

2020-04-14 Thread David Hildenbrand
On 14.04.20 19:58, Dan Williams wrote: > On Tue, Apr 14, 2020 at 4:51 AM David Hildenbrand wrote: >> >> On 11.04.20 02:09, Vishal Verma wrote: >>> A misbehaving qemu created a situation where the ACPI SRAT table >>> advertised one fewer proximity domains than intended. The NFIT table did >>>

Re: [PATCH] dax/kmem: refrain from adding memory into an impossible node

2020-04-14 Thread Dan Williams
On Tue, Apr 14, 2020 at 4:51 AM David Hildenbrand wrote: > > On 11.04.20 02:09, Vishal Verma wrote: > > A misbehaving qemu created a situation where the ACPI SRAT table > > advertised one fewer proximity domains than intended. The NFIT table did > > describe all the expected proximity domains.

Re: [ndctl PATCH] Skip region filtering if numa_node attribute is not present

2020-04-14 Thread Dan Williams
On Tue, Apr 14, 2020 at 4:39 AM Santosh Sivaraj wrote: > > For kernel versions older than 5.4, the numa_node attribute is not > present for regions; due to which `ndctl list -U 1` fails to list > namespaces. > > Signed-off-by: Santosh Sivaraj > --- > ndctl/lib/libndctl.c | 11 +++ >

Re: [PATCH 13/20] fuse, dax: Implement dax read/write operations

2020-04-14 Thread Vivek Goyal
On Sat, Apr 04, 2020 at 08:25:21AM +0800, Liu Bo wrote: [..] > > +static int iomap_begin_upgrade_mapping(struct inode *inode, loff_t pos, > > +loff_t length, unsigned flags, > > +struct iomap *iomap) > > +{ > > + struct

Re: [PATCH] dax/kmem: refrain from adding memory into an impossible node

2020-04-14 Thread David Hildenbrand
On 11.04.20 02:09, Vishal Verma wrote: > A misbehaving qemu created a situation where the ACPI SRAT table > advertised one fewer proximity domains than intended. The NFIT table did > describe all the expected proximity domains. This caused the device dax > driver to assign an impossible

[ndctl PATCH] Skip region filtering if numa_node attribute is not present

2020-04-14 Thread Santosh Sivaraj
For kernel versions older than 5.4, the numa_node attribute is not present for regions; due to which `ndctl list -U 1` fails to list namespaces. Signed-off-by: Santosh Sivaraj --- ndctl/lib/libndctl.c | 11 +++ ndctl/lib/libndctl.sym | 1 + ndctl/libndctl.h | 1 +