<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel.git/arch/powerpc/kvm, branch linux-2.6.28.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.
</subtitle>
<id>https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-2.6.28.y</id>
<link rel='self' href='https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-2.6.28.y'/>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/'/>
<updated>2008-11-25T10:02:48Z</updated>
<entry>
<title>KVM: ppc: stop leaking host memory on VM exit</title>
<updated>2008-11-25T10:02:48Z</updated>
<author>
<name>Hollis Blanchard</name>
</author>
<published>2008-11-24T17:37:38Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=c30f8a6c6d74f67bc2107726cc61a1e7c71e9740'/>
<id>urn:sha1:c30f8a6c6d74f67bc2107726cc61a1e7c71e9740</id>
<content type='text'>
When the VM exits, we must call put_page() for every page referenced in the
shadow TLB.

Without this patch, we usually leak 30-50 host pages (120 - 200 KiB with 4 KiB
pages). The maximum number of pages leaked is the size of our shadow TLB, 64
pages.

Signed-off-by: Hollis Blanchard &lt;hollisb@us.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@redhat.com&gt;
</content>
</entry>
<entry>
<title>KVM: switch to get_user_pages_fast</title>
<updated>2008-10-15T12:25:06Z</updated>
<author>
<name>Marcelo Tosatti</name>
</author>
<published>2008-09-16T23:54:47Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=4c2155ce81c193788082d4b8cdbc26d79edebc58'/>
<id>urn:sha1:4c2155ce81c193788082d4b8cdbc26d79edebc58</id>
<content type='text'>
Convert gfn_to_pfn to use get_user_pages_fast, which can do lockless
pagetable lookups on x86. Kernel compilation on 4-way guest is 3.7%
faster on VMX.

Signed-off-by: Marcelo Tosatti &lt;mtosatti@redhat.com&gt;
Signed-off-by: Avi Kivity &lt;avi@redhat.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: kvmppc_44x_shadow_release() does not require mmap_sem to be locked</title>
<updated>2008-10-15T08:15:26Z</updated>
<author>
<name>Hollis Blanchard</name>
</author>
<published>2008-09-11T15:04:29Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=0bd595fc222583ca260f259698f72e9946c6e524'/>
<id>urn:sha1:0bd595fc222583ca260f259698f72e9946c6e524</id>
<content type='text'>
And it gets in the way of get_user_pages_fast().

Signed-off-by: Hollis Blanchard &lt;hollisb@us.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: powerpc: Map guest userspace with TID=0 mappings</title>
<updated>2008-10-15T08:15:16Z</updated>
<author>
<name>Hollis Blanchard</name>
</author>
<published>2008-07-25T18:54:53Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=49dd2c492895828a90ecdf889e7fe9cfb40a82a7'/>
<id>urn:sha1:49dd2c492895828a90ecdf889e7fe9cfb40a82a7</id>
<content type='text'>
When we use TID=N userspace mappings, we must ensure that kernel mappings have
been destroyed when entering userspace. Using TID=1/TID=0 for kernel/user
mappings and running userspace with PID=0 means that userspace can't access the
kernel mappings, but the kernel can directly access userspace.

The net is that we don't need to flush the TLB on privilege switches, but we do
on guest context switches (which are far more infrequent). Guest boot time
performance improvement: about 30%.

Signed-off-by: Hollis Blanchard &lt;hollisb@us.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: Write only modified shadow entries into the TLB on exit</title>
<updated>2008-10-15T08:15:16Z</updated>
<author>
<name>Hollis Blanchard</name>
</author>
<published>2008-07-25T18:54:52Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=83aae4a8098eb8a40a2e9dab3714354182143b4f'/>
<id>urn:sha1:83aae4a8098eb8a40a2e9dab3714354182143b4f</id>
<content type='text'>
Track which TLB entries need to be written, instead of overwriting everything
below the high water mark. Typically only a single guest TLB entry will be
modified in a single exit.

Guest boot time performance improvement: about 15%.

Signed-off-by: Hollis Blanchard &lt;hollisb@us.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: Stop saving host TLB state</title>
<updated>2008-10-15T08:15:16Z</updated>
<author>
<name>Hollis Blanchard</name>
</author>
<published>2008-07-25T18:54:51Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=20754c2495a791b5b429c0da63394c86ade978e7'/>
<id>urn:sha1:20754c2495a791b5b429c0da63394c86ade978e7</id>
<content type='text'>
We're saving the host TLB state to memory on every exit, but never using it.
Originally I had thought that we'd want to restore host TLB for heavyweight
exits, but that could actually hurt when context switching to an unrelated host
process (i.e. not qemu).

Since this decreases the performance penalty of all exits, this patch improves
guest boot time by about 15%.

Signed-off-by: Hollis Blanchard &lt;hollisb@us.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: guest breakpoint support</title>
<updated>2008-10-15T08:15:16Z</updated>
<author>
<name>Hollis Blanchard</name>
</author>
<published>2008-07-25T18:54:49Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=6a0ab738ef42d87951b3980f61b1f4cbb14d4171'/>
<id>urn:sha1:6a0ab738ef42d87951b3980f61b1f4cbb14d4171</id>
<content type='text'>
Allow host userspace to program hardware debug registers to set breakpoints
inside guests.

Signed-off-by: Jerone Young &lt;jyoung5@us.ibm.com&gt;
Signed-off-by: Hollis Blanchard &lt;hollisb@us.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: trace powerpc instruction emulation</title>
<updated>2008-10-15T08:15:15Z</updated>
<author>
<name>Christian Ehrhardt</name>
</author>
<published>2008-07-14T12:00:04Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=3b4bd7969f7b61a1ab455bff084ee4f0a2411055'/>
<id>urn:sha1:3b4bd7969f7b61a1ab455bff084ee4f0a2411055</id>
<content type='text'>
This patch adds a trace point for the instruction emulation on embedded powerpc
utilizing the KVM_TRACE interface.

Signed-off-by: Christian Ehrhardt &lt;ehrhardt@linux.vnet.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: adds trace points for ppc tlb activity</title>
<updated>2008-10-15T08:15:15Z</updated>
<author>
<name>Jerone Young</name>
</author>
<published>2008-07-14T12:00:03Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=31711f2294b38d8334efaf7dbac6da4781fd151e'/>
<id>urn:sha1:31711f2294b38d8334efaf7dbac6da4781fd151e</id>
<content type='text'>
This patch adds trace points to track powerpc TLB activities using the
KVM_TRACE infrastructure.

Signed-off-by: Jerone Young &lt;jyoung5@us.ibm.com&gt;
Signed-off-by: Christian Ehrhardt &lt;ehrhardt@linux.vnet.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
<entry>
<title>KVM: ppc: enable KVM_TRACE building for powerpc</title>
<updated>2008-10-15T08:15:15Z</updated>
<author>
<name>Jerone Young</name>
</author>
<published>2008-07-14T12:00:02Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=12f67556023389a6be929a56617142a8e8ab20fe'/>
<id>urn:sha1:12f67556023389a6be929a56617142a8e8ab20fe</id>
<content type='text'>
This patch enables KVM_TRACE to build for PowerPC arch. This means just
adding sections to Kconfig and Makefile.

Signed-off-by: Jerone Young &lt;jyoung5@us.ibm.com&gt;
Signed-off-by: Christian Ehrhardt &lt;ehrhardt@linux.vnet.ibm.com&gt;
Signed-off-by: Avi Kivity &lt;avi@qumranet.com&gt;
</content>
</entry>
</feed>
