[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20171027022524.22589-1-haozhong.zhang@intel.com>
Date: Fri, 27 Oct 2017 10:25:21 +0800
From: Haozhong Zhang <haozhong.zhang@...el.com>
To: kvm@...r.kernel.org, x86@...nel.org
Cc: linux-kernel@...r.kernel.org, Paolo Bonzini <pbonzini@...hat.com>,
rkrcmar@...hat.com, Xiao Guangrong <xiaoguangrong.eric@...il.com>,
Dan Williams <dan.j.williams@...el.com>,
ivan.d.cuevas.escareno@...el.com, karthik.kumar@...el.com,
Haozhong Zhang <haozhong.zhang@...el.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>, Borislav Petkov <bp@...e.de>,
Mikulas Patocka <mpatocka@...hat.com>,
Tom Lendacky <thomas.lendacky@....com>
Subject: [PATCH 0/3] KVM: MMU: fix kvm_is_mmio_pfn()
[I just copy the commit message from patch 3]
By default, KVM treats a reserved page as for MMIO purpose, and maps
it to guest with UC memory type. However, some reserved pages are not
for MMIO, such as pages of DAX device (e.g., /dev/daxX.Y). Mapping
them with UC memory type will harm the performance. In order to
exclude those cases, we check the host cache mode in addition and only
treat UC/UC- pages as MMIO.
Haozhong Zhang (3):
x86/mm: expose track_pfn_insert()
KVM: add converters between pfn_t and kvm_pfn_t
KVM: MMU: consider host cache type in MMIO pfn check
arch/x86/kvm/mmu.c | 32 +++++++++++++++++++++++++++++---
arch/x86/mm/pat.c | 1 +
include/linux/kvm_host.h | 3 +++
3 files changed, 33 insertions(+), 3 deletions(-)
--
2.14.1
Powered by blists - more mailing lists