Commit Graph
9315 Commits
Author SHA1 Message Date
kaf24@firebug.cl.cam.ac.uk ed87d736e9 merge with xen-ia64-unstable.hg 2006-03-18 10:59:11 +01:00
cl349@firebug.cl.cam.ac.uk ce0bcf0e64 Update to Linux 2.6.16-rc6.
Signed-off-by: Christian Limpach <Christian.Limpach@cl.cam.ac.uk>


--HG--
rename : patches/linux-2.6.16-rc5/i386-mach-io-check-nmi.patch => patches/linux-2.6.16-rc6/i386-mach-io-check-nmi.patch
rename : patches/linux-2.6.16-rc5/net-csum.patch => patches/linux-2.6.16-rc6/net-csum.patch
rename : patches/linux-2.6.16-rc5/pmd-shared.patch => patches/linux-2.6.16-rc6/pmd-shared.patch
rename : patches/linux-2.6.16-rc5/smp-alts.patch => patches/linux-2.6.16-rc6/smp-alts.patch
2006-03-18 00:12:26 +00:00
awilliam@xenbuild.aw b6144da6bb merge 2006-03-17 15:37:28 -07:00
awilliam@xenbuild.aw 9dc734c3ad [IA64] VT-i Domains should use same hvm builder as VT-x
Signed-off-by: Fred Yang <fred.yang@intel.com>
2006-03-17 14:26:24 -07:00
awilliam@xenbuild.aw b7c7a62b6d [IA64] -mconstant-gp gcc/as option added.
Thus gp is not saved/restored before calls, saving memory and bundles.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-17 14:23:43 -07:00
awilliam@xenbuild.aw e14a1fda82 [IA64] zero_page_memmap_ptr removed (was unused).
Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-17 14:21:56 -07:00
awilliam@xenbuild.aw 7d408ed38f [IA64] fixed a vcpu_translate bug
There are some below code segments in guest OS
1.     Rsm psr.dt
       ...
2.     itc.d r18
       ...
3.     rfi

After executing instruction 1, domain is in metaphysical mode.
When executing instruction 2, VMM gets control to emulate this
instruction. Firstly VMM will try to get opcode, which may
trigger a tlb miss. At this time domain is in metaphysical mode
and the fault address is in region 5. vcpu_translate handles this
as normal guest metaphysical mode.

It's not correct; sometimes this will make dom0 hang.

cpu_translate should handle this situation as if
guest is not in metaphysical mode.

Signed-off-by: Anthony Xu <anthony.xu@intel.com>
2006-03-17 14:06:20 -07:00
awilliam@xenbuild.aw 2ed2802aa7 [IA64] setting rr0 is not correctly emulated
When guest is not at metaphysical mode, VMM should
set machine rr0.

Signed-off-by: Anthony Xu <anthony.xu@intel.com>
2006-03-17 13:44:48 -07:00
awilliam@xenbuild.aw af8e297826 [IA64] Remove "#define page_info page"
This patch removed "#define page_info page" in asm-ia64/config.h.
We tested compilation, booting dom0, and creation/destruction domU.

This patch is "step3" which we showed by the following mail.
http://lists.xensource.com/archives/html/xen-ia64-devel/2006-03/msg00305.html

Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
Signed-off-by: Masaki Kanno <kanno.masaki@jp.fujitsu.com>
2006-03-17 13:23:59 -07:00
awilliam@xenbuild.aw 07a4baeb2a [IA64] Remove header files where "page" is used
This patch is "step2" which we showed by the following mail.
http://lists.xensource.com/archives/html/xen-ia64-devel/2006-03/msg00305.html

Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
Signed-off-by: Masaki Kanno <kanno.masaki@jp.fujitsu.com>
2006-03-17 13:23:01 -07:00
kaf24@firebug.cl.cam.ac.uk ba05fb571e Fix VMX cpuid handling when EAX == 4.
When eax == 4, ecx should contain cache level.

Signed-off-by: Xin Li <xin.b.li@intel.com>
2006-03-17 16:25:04 +01:00
kaf24@firebug.cl.cam.ac.uk a431b2fa06 Allows the hypervisor to build without warnings (wisely considered
errors with/-Werror) when perfc_arrays are enabled in xen/Rules.mk.

Signed-off-by: David Lively <dlively@virtualiron.com>
2006-03-17 11:45:46 +01:00
kaf24@firebug.cl.cam.ac.uk 13134a9fdd Fix the gzip size extraction in xc_inflate_buffer(). Extract
bytes as unsigned quantities.

Signed-off-by: David Lively <dlively@virtualiron.com>
2006-03-17 11:44:55 +01:00
kaf24@firebug.cl.cam.ac.uk e21b3a393e Fix sched_sedf adjdom to properly clamp the period max value.
Remove temporary debug tracing.

Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-17 11:00:46 +01:00
kaf24@firebug.cl.cam.ac.uk fceb225f85 Declare inline function as 'static inline', not 'extern inline'.
Fixes the ioemu build which was broken on some systems.

Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-17 10:57:28 +01:00
vhanquez@kneesa.uk.xensource.com 18b6341b93 Reinitialize producer and consumer index to 0 if indexes corruption are detected
in XenBus.
Prevent a kernel infinite loop and add more recovering ability.

Signed-off-by: Vincent Hanquez <vincent@xensource.com>
2006-03-17 10:03:37 +00:00
vhanquez@kneesa.uk.xensource.com 6ac4acde21 Substitute kmalloc+memset by kzalloc where possible
Signed-off-by: Vincent Hanquez <vincent@xensource.com>
2006-03-17 09:52:05 +00:00
awilliam@xenbuild.aw 311e7e309d [IA64] disable handling of legacy privified insns
Disable handling of privified insns into another instructions.
This is controled by a static constant.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-16 12:22:37 -07:00
awilliam@xenbuild.aw 824bd8fc88 [IA64] remaining privified insns removed
Privified insns replaced by hyperprivops.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-16 12:20:59 -07:00
awilliam@xenbuild.aw e84241ca48 [IA64] new hyperprivop
Missing hyperprivop added.
These were privified insn without hyperprivop.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-16 12:19:08 -07:00
awilliam@xenbuild.aw c5f10fc9a6 [IA64] postat tool
Small utility to display and clear privop statistics.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-16 12:13:23 -07:00
awilliam@xenbuild.aw f4792216d0 [IA64] Changed from page to page_info
This patch changed from "struct page" to "struct page_info" in the below files.
 - xen/arch/ia64/xen/domain.c
 - xen/arch/ia64/xen/mm_init.c
 - xen/arch/ia64/xen/xenmem.c
 - xen/arch/ia64/xen/xenmisc.c
 - xen/include/asm-ia64/config.h
 - xen/include/asm-ia64/mm.h

This patch is "step1" which we showed by the following mail.
http://lists.xensource.com/archives/html/xen-ia64-devel/2006-03/msg00305.html

Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
Signed-off-by: Masaki Kanno <kanno.masaki@jp.fujitsu.com>
2006-03-16 12:10:22 -07:00
awilliam@xenbuild.aw 3402cbc5bc [IA64] use of max_addr= & command line
Use 'max_addr' option to limit the amount of physical memory.  The
default is 4G (the same as the previous hard limit).  The hard-coded
limit is removed.  dom0_command_line now contains the cmdline for
dom0 linux.  saved_command_line now contains the cmdline for Xen (it
is used in Xen).

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-16 12:06:48 -07:00
awilliam@xenbuild.aw 24ea66b731 [IA64] fix AFLAGS in Rules.mk
Signed-off-by: Tsunehisa Doi <doi.tsunehisa@jp.fujitsu.com>
Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
2006-03-16 12:02:39 -07:00
kaf24@firebug.cl.cam.ac.uk bae56b0ac6 Clean up HVM relinquish_guest_resources interface and implementation.
Ensure we only unmap the shared I/O page after killing all timers
whose handlers may reference that page.

Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-16 19:36:28 +01:00
kaf24@firebug.cl.cam.ac.uk 7d258cc98e Add Summagraphics Tablet emulation for VNC users. The current PS/2 emulation
is unusable under VNC since a PS/2 mouse provides deltas while VNC only
provides absolute coordinates.  Fortunately, the Summagraphics Tablet provides
absolute coordinates and works perfectly with VNC.

Signed-off-by: Don Dugger <donald.d.dugger@intel.com>
2006-03-16 18:57:54 +01:00
kaf24@firebug.cl.cam.ac.uk 1409287078 Change the VNC main input loop delay from 1 second down to 10
msec.  The 1 second delay was causing significant latency problems
with the mouse while there is no measurable overhead in lowering the
delay down to 10 msec.

Signed-off-by: Don Dugger <donald.d.dugger@intel.com>
2006-03-16 18:43:07 +01:00
kaf24@firebug.cl.cam.ac.uk 3fd07d7995 Add a shadow VRAM to track changes to the real VRAM. When the guest
OS was given write access to the VRAM the device model tracked all
VRAM changes by updating the entire screen on every output loop,
causing significant overhead (a CPU bound loop in a guest slows down
by about 35%) and significant mouse latency (VNC uses the same data
path for mouse events and video updates).  With the shadow VRAM only
modified pages need to be updated and the comparison of the shadow
VRAM to the real VRAM only adds ~4% overhead while eliminating the
mouse latencies.

Signed-off-by: Don Dugger <donald.d.dugger@intel.com>
2006-03-16 18:41:01 +01:00
kaf24@firebug.cl.cam.ac.uk abed9e6eea Explicitly include time.h to get gettimeofday declaration.
Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-16 12:34:27 +01:00
kaf24@firebug.cl.cam.ac.uk 7d2b8840b8 pcifront poll loop now checks gettimeofday rather than jiffies,
as the latter does not increase while interrupts are disabled.

Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-16 12:31:16 +01:00
kaf24@firebug.cl.cam.ac.uk a54b2baac2 Implement console for Mini-os and also fix 2 bugs:
a) in initialising new page table frames
b) in initialising idle thread.

Signed-off-by: Grzegorz Milos <gm281@cam.ac.uk>
2006-03-15 20:25:50 +01:00
kaf24@firebug.cl.cam.ac.uk 7999d90426 Make asm macros use the generally accepted comma-separated arg-passing style.
Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-15 20:22:31 +01:00
kaf24@firebug.cl.cam.ac.uk d7282c3e44 Update interface documentation to include sched_op_new hypercall
and clean up the style a bit. Also clean up the sched_op_new
description in the sched.h public header.

Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-15 19:19:22 +01:00
awilliam@xenbuild.aw e62073aba7 [IA64] cleanup in dom_fw.c
Unused code removed.
A few 'static' added.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-15 08:33:23 -07:00
awilliam@xenbuild.aw ce93231c1e [IA64] LID virtualization
Virtualize lid for domU.
LSAPIC table cleaned for SMP-g.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-15 08:28:23 -07:00
awilliam@xenbuild.aw dd5693a038 [IA64] dummy IO memmap entry
Create a dummy IO ports memmap entry for domU, so that
IO accesses are trapped by Xen.  Otherwise, they could
pollute memory.

Signed-off-by: Tristan Gingold <tristan.gingold@bull.net>
2006-03-15 08:22:03 -07:00
awilliam@xenbuild.aw 499341ff62 [IA64] remove warning of xen_init()
Signed-off-by: Akio Takebe <takebe_akio@jp.fujitsu.com>
2006-03-15 08:20:28 -07:00
kaf24@firebug.cl.cam.ac.uk 7ed3b9e46c Remove unnecessary cr4 handling in vmx_set_cr0.
1) on x86_32, PAE should never be enabled in guest cr4, since we only
support pure IA32 VMX guest.
2) on x86_32p or x86_64, PAE should always be enabled in guest cr4,
since even pure IA32 guest uses PAE paging mode actually.

Signed-off-by: Xin Li <xin.b.li@intel.com>
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
2006-03-15 13:35:43 +01:00
vhanquez@kneesa.uk.xensource.com be7c672575 merge 2006-03-15 12:24:59 +00:00
vhanquez@kneesa.uk.xensource.com 3645dec056 fix buffer overflow in print XS_DEBUG command
Signed-off-by: Vincent Hanquez <vincent@xensource.com>
2006-03-15 12:24:34 +00:00
vhanquez@kneesa.uk.xensource.com 9d34613c4e move XS_DEBUG code into a proper function
Signed-off-by: Vincent Hanquez <vincent@xensource.com>
2006-03-15 12:08:10 +00:00
kaf24@firebug.cl.cam.ac.uk 3b9ba71177 Make MTU rx check in netfront more permissive to allow for 8021q vlan tagging.
Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-15 12:52:33 +01:00
kaf24@firebug.cl.cam.ac.uk 5ad9b84e65 Remove unused macro VMX_CPU_STATE_PG_ENABLED.
Use vmx_paging_enabled() instead.

Signed-off-by: Xin Li <xin.b.li@intel.com>
2006-03-15 12:41:58 +01:00
kaf24@firebug.cl.cam.ac.uk 2cc7ae652d Fix 64-bit build.
Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-15 12:40:42 +01:00
vhanquez@kneesa.uk.xensource.com ba07c577c6 Do not BUG when receiving unexpected message type from xenbus
print a warning and discard the query

Signed-off-by: Vincent Hanquez <vincent@xensource.com>
2006-03-15 11:09:45 +00:00
Ian.Campbell@xensource.com 65749e4633 There is no need to pin page tables when XENFEAT_writable_page_tables
is enabled.

Signed-off-by: Ian Campbell <ian.campbell@xensource.com>
2006-03-15 10:33:43 +00:00
kaf24@firebug.cl.cam.ac.uk 40caad2490 Fix x86/64 HVM assertion failure.
Signed-off-by: Xin Li <xin.b.li@intel.com>
2006-03-15 11:09:20 +01:00
kaf24@firebug.cl.cam.ac.uk 2c8dbad938 I've found it useful to display the panic message *before* dropping into the
debugger. Once there it may be very difficult to find the original message, 
and often a debugger isn't even needed if you can see what panicked.

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
2006-03-15 11:07:26 +01:00
kaf24@firebug.cl.cam.ac.uk 72e3f22324 Unlike x86 and apparently ia64, PowerPC delivers timer interrupts as a
different exception than device interrupts. For PowerPC Xen, we emulate this 
exception rather than delivering timer events as virtual IRQs. This patch 
introduces no functional changes for x86 and ia64, but is a required change 
for xen/arch/ppc.

Signed-off-by: Hollis Blanchard <hollisb@us.ibm.com>
2006-03-15 11:06:45 +01:00
kaf24@firebug.cl.cam.ac.uk 92d6391152 Add extra tracing near a commonly-failing scheduler assertion.
Signed-off-by: Keir Fraser <keir@xensource.com>
2006-03-15 10:32:34 +01:00