search for: poppling

Device exclusive page table entries are used to prevent CPU access to a page whilst it is being accessed from a device. Typically this is used to implement atomic operations when the underlying bus does not support atomic access. When a CPU thread encounters a device exclusive entry it locks the page and restores the original entry after calling mmu notifiers to signal drivers that exclusive

Hi, Jean, thanks for your source code example. I like ask info about cpu consuption, in our example enabling echo removing cause the sound poppling with a celeron 1.7Ghz (taskman show cpu full, without echo is at 30%). Does exist a mode to lower the cpu consuption in echo removing? Because a large part of users base own still "old" CPU of 6-7 generation, as from 500-700 Mhz and lower too. Perhaps the code need be optimized? Or can...

Device exclusive page table entries are used to prevent CPU access to a page whilst it is being accessed from a device. Typically this is used to implement atomic operations when the underlying bus does not support atomic access. When a CPU thread encounters a device exclusive entry it locks the page and restores the original entry after calling mmu notifiers to signal drivers that exclusive

This is an initial series of patches to improve channel recovery on Turing GPUs with the goal of improving reliability enough to eventually enable SVM for Turing. It's likely follow up patches will be required to fully address problems with less trivial workloads than what I have been able to test thus far. This series primarily addresses a number of hardware changes to interrupt layout and

On 3/27/23 19:14, Alistair Popple wrote: > Device exclusive page table entries are used to prevent CPU access to > a page whilst it is being accessed from a device. Typically this is > used to implement atomic operations when the underlying bus does not > support atomic access. When a CPU thread encounters a device exclusive > entry it locks the page and restores the original entry

On Tue, Jan 24, 2023 at 04:42:31PM +1100, Alistair Popple wrote: > diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c > index ec32f78..a31dd53 100644 > --- a/drivers/vhost/vdpa.c > +++ b/drivers/vhost/vdpa.c ... > @@ -780,6 +780,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb, > u32 asid = iotlb_to_asid(iotlb); > int r = 0; >

On Tue, Mar 28, 2023 at 01:14:34PM +1100, Alistair Popple wrote: > +++ b/mm/memory.c > @@ -3623,8 +3623,19 @@ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) > struct vm_area_struct *vma = vmf->vma; > struct mmu_notifier_range range; > > - if (!folio_lock_or_retry(folio, vma->vm_mm, vmf->flags)) > + /* > + * We need a page reference to

John Hubbard <jhubbard at nvidia.com> writes: > On 3/28/23 20:16, Matthew Wilcox wrote: > ... >>> + if (!get_page_unless_zero(vmf->page)) >>> + return 0; >> From a folio point of view: what the hell are you doing here? Tail >> pages don't have individual refcounts; all the refcounts are actually I had stuck with using the page because none of

Hi, I have got a Powerware 5110 UPS which has a usb interface on it. I have downloaded and compiled nut-2.0.3-pre2 with the usb drivers enabled on RedHat Enterprise V3 however I have been unable to get nut to connect to the UPS. I have tried executing the driver directly (using bcmxcp_usb -DD -u root /proc/bus/usb/002/002) as well as using upsdrvctl with the port set to auto (am I correct in

"Zhou, Xianrong" <Xianrong.Zhou at amd.com> writes: > [AMD Official Use Only - General] > >> >>>>> The vmf_insert_pfn_prot could cause unnecessary double faults on a >> >>>>> device pfn. Because currently the vmf_insert_pfn_prot does not >> >>>>> make the pfn writable so the pte entry is normally read-only or

flight 17901 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/17901/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-i386-qemuu-rhel6hvm-intel 4 xen-install fail REGR. vs. 12557 test-amd64-i386-pv 4 xen-install fail REGR. vs. 12557 test-amd64-amd64-pv 4

flight 17916 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/17916/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-amd64-pv 4 xen-install fail REGR. vs. 12557 test-amd64-amd64-xl 4 xen-install fail REGR. vs. 12557 test-amd64-amd64-xl-win7-amd64 4

flight 18150 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/18150/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-i386-rhel6hvm-amd 7 redhat-install fail REGR. vs. 12557 test-amd64-i386-pair 17 guest-migrate/src_host/dst_host fail REGR. vs. 12557 Regressions which are regarded as

flight 18181 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/18181/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-i386-rhel6hvm-amd 7 redhat-install fail REGR. vs. 12557 test-amd64-i386-pair 17 guest-migrate/src_host/dst_host fail REGR. vs. 12557 Regressions which are regarded as

flight 18805 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/18805/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: test-amd64-i386-rhel6hvm-amd 7 redhat-install fail REGR. vs. 12557 test-amd64-i386-pair 17 guest-migrate/src_host/dst_host fail REGR. vs. 12557 Regressions which are regarded as

flight 18844 linux-linus real [real] http://www.chiark.greenend.org.uk/~xensrcts/logs/18844/ Regressions :-( Tests which did not succeed and are blocking, including tests which could not be run: build-i386 4 xen-build fail REGR. vs. 12557 Tests which did not succeed, but are not blocking: test-amd64-amd64-xl-pcipt-intel 9 guest-start fail

Christoph Hellwig <hch at infradead.org> writes: > s/page/folio/ in the entire commit log? I debated that but settled on leaving it as is because device exclusive entries only deal with non-compound pages for now and didn't want to give any other impression. Happy to change that though if people think it would be better/clearer.