search for: m2p_override

On 27/02/14 15:55, Zoltan Kiss wrote: > (This is a continuation of "[PATCH v9] xen/grant-table: Avoid m2p_override > during mapping") > > The grant mapping API does m2p_override unnecessarily: only gntdev needs it, > for blkback and future netback patches it just cause a lock contention, as > those pages never go to userspace. Therefore this series does the following: > - the bulk of the...

(This is a continuation of "[PATCH v9] xen/grant-table: Avoid m2p_override during mapping") The grant mapping API does m2p_override unnecessarily: only gntdev needs it, for blkback and future netback patches it just cause a lock contention, as those pages never go to userspace. Therefore this series does the following: - the bulk of the original function (everything...

(This is a continuation of "[PATCH v9] xen/grant-table: Avoid m2p_override during mapping") The grant mapping API does m2p_override unnecessarily: only gntdev needs it, for blkback and future netback patches it just cause a lock contention, as those pages never go to userspace. Therefore this series does the following: - the bulk of the original function (everything...

This patch is a significant performance improvement for the m2p_override: about 6% using the gntdev device. Each m2p_add/remove_override call issues a MULTI_grant_table_op and a __flush_tlb_single if kmap_op != NULL. Batching all the calls together is a great performance benefit because it means issuing one hypercall total rather than two hypercall per page. If paravi...

Since when we are using the m2p_override it is not true anymore that the mmap''ed area doesn''t have corresponsing struct pages. Removing the VM_PFNMAP flag makes get_user_pages work on the mmap''ed user vma. An example test case would be using a Xen userspace block backend (QDISK) on a file on NFS using O_DIRECT....

...mplement io apic read with hypercall xen: implement IRQ_WORK_VECTOR handler Marek Marczykowski (1): xen: do not disable netfront in dom0 Srivatsa Vaddagiri (1): debugfs: Add support to print u32 array in debugfs Stefano Stabellini (3): xen: enter/exit lazy_mmu_mode around m2p_override calls xen: do not map the same GSI twice in PVHVM guests. xen: mark local pages as FOREIGN in the m2p_override Zhang, Yang Z (1): xen/pci: Check for PCI bridge before using it.

...it a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 1b267e7..a4d35d4 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -807,23 +807,18 @@ EXPORT_SYMBOL_GPL(m2p_remove_override); struct page *m2p_find_override(unsigned long mfn) { - unsigned long flags; struct list_head *bucket = &m2p_overrides[mfn_hash(mfn)]; - struct page *p, *ret; + struct page *p, *t, *ret; ret = NULL; - spin_lock_irqsave(&m2p_override_lock, flags); - - list_for_each_entry(p, bucket, lru) { + list_for_each_entry_safe(p, t, bucket, lru) { if (page_private(p) == mfn) { ret = p; break; } } -...

Since we are using the m2p_override we do have struct pages corresponding to the user vma mmap''ed by gntdev. Removing the VM_PFNMAP flag makes get_user_pages work on that vma. An example test case would be using a Xen userspace block backend (QDISK) on a file on NFS using O_DIRECT. The patch should be backported back to 2....

Hi all, this patch series enables xen-swiotlb on arm and arm64. It has been heavily reworked compared to the previous versions in order to achieve better performances and to address review comments. We are not using dma_mark_clean to ensure coherency anymore. We call the platform implementation of map_page and unmap_page. We assume that dom0 has been mapped 1:1 (physical address == machine

Hello, Jeremy: See the included patch. If it''s OK it''d be nice to get it into xen/stable-2.6.32.x branch. Thanks Nathanael! -- Pasi ----- Forwarded message from Nathanael Rensen <nathanael@polymorpheus.com> ----- From: Nathanael Rensen <nathanael@polymorpheus.com> To: Pasi Kärkkäinen <pasik@iki.fi> Cc: n_iwamatsu@jp.fujitsu.com Date: Mon, 3 Jan 2011