This patch introduces two ioctls for virtual cpus, that are only
valid for kernel virtual machines that are controlled by userspace.
Each virtual cpu has its individual address space in this mode of
operation, and each address space is backed by the gmap
implementation just like the address space for regular KVM guests.
KVM_S390_UCAS_MAP allows to map a part of the user's virtual address
space to the vcpu. Starting offset and length in both the user and
the vcpu address space need to be aligned to 1M.
KVM_S390_UCAS_UNMAP can be used to unmap a range of memory from a
virtual cpu in a similar way.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch introduces a new config option for user controlled kernel
virtual machines. It introduces a parameter to KVM_CREATE_VM that
allows to set bits that alter the capabilities of the newly created
virtual machine.
The parameter is passed to kvm_arch_init_vm for all architectures.
The only valid modifier bit for now is KVM_VM_S390_UCONTROL.
This requires CAP_SYS_ADMIN privileges and creates a user controlled
virtual machine on s390 architectures.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
KVM on s390 always had a sync mmu. Any mapping change in userspace
mapping was always reflected immediately in the guest mapping.
- In older code the guest mapping was just an offset
- In newer code the last level page table is shared
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
There is a potential host deadlock in the tprot intercept handling.
We must not hold the mmap semaphore while resolving the guest
address. If userspace is remapping, then the memory detection in
the guest is broken anyway so we can safely separate the
address translation from walking the vmas.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
SIGP sense running may cause an intercept on higher level
virtualization, so handle it by checking the CPUSTAT_RUNNING flag.
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
CPUSTAT_RUNNING was implemented signifying that a vcpu is not stopped.
This is not, however, what the architecture says: RUNNING should be
set when the host is acting on the behalf of the guest operating
system.
CPUSTAT_RUNNING has been changed to be set in kvm_arch_vcpu_load()
and to be unset in kvm_arch_vcpu_put().
For signifying stopped state of a vcpu, a host-controlled bit has
been used and is set/unset basically on the reverse as the old
CPUSTAT_RUNNING bit (including pushing it down into stop handling
proper in handle_stop()).
Cc: stable@kernel.org
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Linux on System z uses a ballooner based on diagnose 0x10. (aka as
collaborative memory management). This patch implements diagnose
0x10 on the guest address space.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Implement sigp external call, which might be required for guests that
issue an external call instead of an emergency signal for IPI.
This fixes an issue with "KVM: unknown SIGP: 0x02" when booting
such an SMP guest.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
KVM common code does vcpu_load prior to calling our arch ioctls and
vcpu_put after we're done here. Via the kvm_arch_vcpu_load/put
callbacks we do load the fpu and access register state into the
processor, which saves us moving the state on every SIE exit the
kernel handles. However this breaks register setting from userspace,
because of the following sequence:
1a. vcpu load stores userspace register content
1b. vcpu load loads guest register content
2. kvm_arch_vcpu_ioctl_set_fpu/sregs updates saved guest register content
3a. vcpu put stores the guest registers and overwrites the new content
3b. vcpu put loads the userspace register set again
This patch loads the new guest register state into the cpu, so that the correct
(new) set of guest registers will be stored in step 3a.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This patch fixes the return value of kvm_arch_init_vm in case a memory
allocation goes wrong.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
We use the cpu id provided by userspace as array index here. Thus we
clearly need to check it first. Ooops.
CC: <stable@vger.kernel.org>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
598841ca99 ([S390] use gmap address
spaces for kvm guest images) changed kvm on s390 to use a separate
address space for kvm guests. We can now put KVM guests anywhere
in the user address mode with a size up to 8PB - as long as the
memory is 1MB-aligned. This change was done without KVM extension
capability bit.
The change was added after 3.0, but we still have a chance to add
a feature bit before 3.1 (keeping the releases in a sane state).
We use number 71 to avoid collisions with other pending kvm patches
as requested by Alexander Graf.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Avi Kivity <avi@redhat.com>
Cc: Alexander Graf <agraf@suse.de>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
598841ca99 ([S390] use gmap address
spaces for kvm guest images) changed kvm to use a separate address
space for kvm guests. This address space was switched in __vcpu_run
In some cases (preemption, page fault) there is the possibility that
this address space switch is lost.
The typical symptom was a huge amount of validity intercepts or
random guest addressing exceptions.
Fix this by doing the switch in sie_loop and sie_exit and saving the
address space in the gmap structure itself. Also use the preempt
notifier.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
SIGP emerg needs to pass the source vpu adress into __LC_CPU_ADDRESS of the
target guest.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch removes the mmu reload logic for kvm on s390. Via Martin's
new gmap interface, we can safely add or remove memory slots while
guest CPUs are in-flight. Thus, the mmu reload logic is not needed
anymore.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch removes kvm-s390 internal assumption of a linear mapping
of guest address space to user space. Previously, guest memory was
translated to user addresses using a fixed offset (gmsor). The new
code uses gmap_fault to resolve guest addresses.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch switches kvm from using (Qemu's) user address space to
Martin's gmap address space. This way QEMU does not have to use a
linker script in order to fit large guests at low addresses in its
address space.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
The entry to / exit from sie has subtle dependencies to the first level
interrupt handler. Move the sie assembler code to entry64.S and replace
the SIE_HOOK callback with a test and the new _TIF_SIE bit.
In addition this patch fixes several problems in regard to the check for
the_TIF_EXIT_SIE bits. The old code checked the TIF bits before executing
the interrupt handler and it only modified the instruction address if it
pointed directly to the sie instruction. In both cases it could miss
a TIF bit that normally would cause an exit from the guest and would
reenter the guest context.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
When running a kvm guest we can get intercepts for tprot, if the host
page table is read-only or not populated. This patch implements the
most common case (linux memory detection).
This also allows host copy on write for guest memory on newer systems.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
virtio has been so far used only in the context of virtualization,
and the virtio Kconfig was sourced directly by the relevant arch
Kconfigs when VIRTUALIZATION was selected.
Now that we start using virtio for inter-processor communications,
we need to source the virtio Kconfig outside of the virtualization
scope too.
Moreover, some architectures might use virtio for both virtualization
and inter-processor communications, so directly sourcing virtio
might yield unexpected results due to conflicting selections.
The simple solution offered by this patch is to always source virtio's
Kconfig in drivers/Kconfig, and remove it from the appropriate arch
Kconfigs. Additionally, a virtio menu entry has been added so virtio
drivers don't show up in the general drivers menu.
This way anyone can use virtio, though it's arguably less accessible
(and neat!) for virtualization users now.
Note: some architectures (mips and sh) seem to have a VIRTUALIZATION
menu merely for sourcing virtio's Kconfig, so that menu is removed too.
Signed-off-by: Ohad Ben-Cohen <ohad@wizery.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
commit 9ff4cfb3fc ([S390] kvm-390: Let
kernel exit SIE instruction on work) fixed a problem of commit
commit cd3b70f5d4 ([S390] virtualization
aware cpu measurement) but uncovered another one.
If a kvm guest accesses guest real memory that doesnt exist, the
page fault handler calls the sie hook, which then rewrites
the return psw from sie_inst to either sie_exit or sie_reenter.
On return, the page fault handler will then detect the wrong access
as a kernel fault causing a kernel oops in sie_reenter or sie_exit.
We have to add these two addresses to the exception table to allow
graceful exits.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
From: Christian Borntraeger <borntraeger@de.ibm.com>
This patch fixes the sie exit on interrupts. The low level
interrupt handler returns to the PSW address in pt_regs and not
to the PSW address in the lowcore.
Without this fix a cpu bound guest might never leave guest state
since the host interrupt handler would blindly return to the
SIE instruction, even on need_resched and friends.
Cc: stable@kernel.org
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Replace EXTRA_CFLAGS with ccflags-y.
Signed-off-by: matt mooney <mfm@muteddisk.com>
Acked-by: WANG Cong <xiyou.wangcong@gmail.com>
Signed-off-by: Michal Marek <mmarek@suse.cz>
* 'kvm-updates/2.6.38' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (142 commits)
KVM: Initialize fpu state in preemptible context
KVM: VMX: when entering real mode align segment base to 16 bytes
KVM: MMU: handle 'map_writable' in set_spte() function
KVM: MMU: audit: allow audit more guests at the same time
KVM: Fetch guest cr3 from hardware on demand
KVM: Replace reads of vcpu->arch.cr3 by an accessor
KVM: MMU: only write protect mappings at pagetable level
KVM: VMX: Correct asm constraint in vmcs_load()/vmcs_clear()
KVM: MMU: Initialize base_role for tdp mmus
KVM: VMX: Optimize atomic EFER load
KVM: VMX: Add definitions for more vm entry/exit control bits
KVM: SVM: copy instruction bytes from VMCB
KVM: SVM: implement enhanced INVLPG intercept
KVM: SVM: enhance mov DR intercept handler
KVM: SVM: enhance MOV CR intercept handler
KVM: SVM: add new SVM feature bit names
KVM: cleanup emulate_instruction
KVM: move complete_insn_gp() into x86.c
KVM: x86: fix CR8 handling
KVM guest: Fix kvm clock initialization when it's configured out
...
IA64 support forces us to abstract the allocation of the kvm structure.
But instead of mixing this up with arch-specific initialization and
doing the same on destruction, split both steps. This allows to move
generic destruction calls into generic code.
It also fixes error clean-up on failures of kvm_create_vm for IA64.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Make use of def_bool and def_tristate where possible and add sensible
defaults to the config symbols where applicable. This shortens the
defconfig file by another ~40 lines.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Store the facility list once at system startup with stfl/stfle and
reuse the result for all facility tests.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Enable PFPO, floating point extension, distinct-operands,
fast-BCR-serialization, high-word, interlocked-access, load/store-
on-condition, and population-count facilities for guests.
(bits 37, 44 and 45).
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
As advertised in feature-removal-schedule.txt. Equivalent support is provided
by overlapping memory regions.
Signed-off-by: Avi Kivity <avi@redhat.com>
Newer (guest) kernels use sigp sense running in their spinlock
implementation to check if the other cpu is running before yielding
the processor. This revealed some wrong guest settings, causing
unnecessary exits for every sigp sense running.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Now that all arch specific ioctls have centralized locking, it is easy to
move it to the central dispatcher.
Signed-off-by: Avi Kivity <avi@redhat.com>
All vcpu ioctls need to be locked, so instead of locking each one specifically
we lock at the generic dispatcher.
This patch only updates generic ioctls and leaves arch specific ioctls alone.
Signed-off-by: Avi Kivity <avi@redhat.com>
The containing function is called from several places. At one of them, in
the function __sigp_stop, the spin lock &fi->lock is held.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@gfp exists@
identifier fn;
position p;
@@
fn(...) {
... when != spin_unlock
when any
GFP_KERNEL@p
... when any
}
@locked@
identifier gfp.fn;
@@
spin_lock(...)
... when != spin_unlock
fn(...)
@depends on locked@
position gfp.p;
@@
- GFP_KERNEL@p
+ GFP_ATOMIC
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Add missing GFP flag to memory allocations. The part in cio only
changes a comment.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This config option enables or disables three single instructions
which aren't expensive. This is too fine grained.
Besided that everybody who uses kvm would enable it anyway in order
to debug performance problems.
Just remove it.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
* 'kvm-updates/2.6.35' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (269 commits)
KVM: x86: Add missing locking to arch specific vcpu ioctls
KVM: PPC: Add missing vcpu_load()/vcpu_put() in vcpu ioctls
KVM: MMU: Segregate shadow pages with different cr0.wp
KVM: x86: Check LMA bit before set_efer
KVM: Don't allow lmsw to clear cr0.pe
KVM: Add cpuid.txt file
KVM: x86: Tell the guest we'll warn it about tsc stability
x86, paravirt: don't compute pvclock adjustments if we trust the tsc
x86: KVM guest: Try using new kvm clock msrs
KVM: x86: export paravirtual cpuid flags in KVM_GET_SUPPORTED_CPUID
KVM: x86: add new KVMCLOCK cpuid feature
KVM: x86: change msr numbers for kvmclock
x86, paravirt: Add a global synchronization point for pvclock
x86, paravirt: Enable pvclock flags in vcpu_time_info structure
KVM: x86: Inject #GP with the right rip on efer writes
KVM: SVM: Don't allow nested guest to VMMCALL into host
KVM: x86: Fix exception reinjection forced to true
KVM: Fix wallclock version writing race
KVM: MMU: Don't read pdptrs with mmu spinlock held in mmu_alloc_roots
KVM: VMX: enable VMXON check with SMX enabled (Intel TXT)
...
vmx and svm vcpus have different contents and therefore may have different
alignmment requirements. Let each specify its required alignment.
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch fixed possible memory leak in kvm_arch_vcpu_create()
under s390, which would happen when kvm_arch_vcpu_create() fails.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Cc: stable@kernel.org
Signed-off-by: Avi Kivity <avi@redhat.com>
Use the SPP instruction to set a tag on entry to / exit of the virtual
machine context. This allows the cpu measurement facility to distinguish
the samples from the host and the different guests.
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Use asm offsets to make sure the offset defines to struct _lowcore and
its layout don't get out of sync.
Also add a BUILD_BUG_ON() which checks that the size of the structure
is sane.
And while being at it change those sites which use odd casts to access
the current lowcore. These should use S390_lowcore instead.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
ENOTSUPP is not supposed to leak to userspace so lets just use
EOPNOTSUPP everywhere.
Doesn't fix a bug, but makes future reviews easier.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Remove support to be able to dump 31 bit systems with a 64 bit dumper.
This is mostly useless since no distro ships 31 bit kernels together
with a 64 bit dumper.
We also get rid of a bit of hacky code.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
kvm_handle_sie_intercept uses a jump table to get the intercept handler
for a SIE intercept. Static code analysis revealed a potential problem:
the intercept_funcs jump table was defined to contain (0x48 >> 2) entries,
but we only checked for code > 0x48 which would cause an off-by-one
array overflow if code == 0x48.
Use the compiler and ARRAY_SIZE to automatically set the limits.
Cc: stable@kernel.org
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
(Includes fixes by Alan Cox <alan@linux.intel.com>,
David L Stevens <dlstevens@us.ibm.com>,
Chris Wright <chrisw@redhat.com>)
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce user_mode to replace the two variables switch_amode and
s390_noexec. There are three valid combinations of the old values:
1) switch_amode == 0 && s390_noexec == 0
2) switch_amode == 1 && s390_noexec == 0
3) switch_amode == 1 && s390_noexec == 1
They get replaced by
1) user_mode == HOME_SPACE_MODE
2) user_mode == PRIMARY_SPACE_MODE
3) user_mode == SECONDARY_SPACE_MODE
The new kernel parameter user_mode=[primary,secondary,home] lets
you choose the address space mode the user space processes should
use. In addition the CONFIG_S390_SWITCH_AMODE config option
is removed.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch corrects the checking of the new address for the prefix register.
On s390, the prefix register is used to address the cpu's lowcore (address
0...8k). This check is supposed to verify that the memory is readable and
present.
copy_from_guest is a helper function, that can be used to read from guest
memory. It applies prefixing, adds the start address of the guest memory in
user, and then calls copy_from_user. Previous code was obviously broken for
two reasons:
- prefixing should not be applied here. The current prefix register is
going to be updated soon, and the address we're looking for will be
0..8k after we've updated the register
- we're adding the guest origin (gmsor) twice: once in subject code
and once in copy_from_guest
With kuli, we did not hit this problem because (a) we were lucky with
previous prefix register content, and (b) our guest memory was mmaped
very low into user address space.
Cc: stable@kernel.org
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Reported-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch moves s390 processor status word into the base kvm_run
struct and keeps it up-to date on all userspace exits.
The userspace ABI is broken by this, however there are no applications
in the wild using this. A capability check is provided so users can
verify the updated API exists.
Cc: stable@kernel.org
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
X86 CPUs need to have some magic happening to enable the virtualization
extensions on them. This magic can result in unpleasant results for
users, like blocking other VMMs from working (vmx) or using invalid TLB
entries (svm).
Currently KVM activates virtualization when the respective kernel module
is loaded. This blocks us from autoloading KVM modules without breaking
other VMMs.
To circumvent this problem at least a bit, this patch introduces on
demand activation of virtualization. This means, that instead
virtualization is enabled on creation of the first virtual machine
and disabled on destruction of the last one.
So using this, KVM can be easily autoloaded, while keeping other
hypervisors usable.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
commit 628eb9b8a8
KVM: s390: streamline memslot handling
introduced kvm_s390_vcpu_get_memsize. This broke guests >=4G, since this
function returned an int.
This patch changes the return value to a long.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Remove kvm_cpu_has_interrupt() and kvm_arch_interrupt_allowed() from
interface between general code and arch code. kvm_arch_vcpu_runnable()
checks for interrupts instead.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch relocates the variables kvm-s390 uses to track guest mem addr/size.
As discussed dropping the variables at struct kvm_arch level allows to use the
common vcpu->request based mechanism to reload guest memory if e.g. changes
via set_memory_region.
The kick mechanism introduced in this series is used to ensure running vcpus
leave guest state to catch the update.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
If signal pending is true we exit without updating kvm_run, userspace
currently just does nothing and jumps to kvm_run again.
Since we did not set an exit_reason we might end up with a random one
(whatever was the last exit). Therefore it was possible to e.g. jump to
the psw position the last real interruption set.
Setting the INTR exit reason ensures that no old psw data is swapped
in on reentry.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
To ensure vcpu's come out of guest context in certain cases this patch adds a
s390 specific way to kick them out of guest context. Currently it kicks them
out to rerun the vcpu_run path in the s390 code, but the mechanism itself is
expandable and with a new flag we could also add e.g. kicks to userspace etc.
Signed-off-by: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
* 'kvm-updates/2.6.31' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: Avoid redelivery of edge interrupt before next edge
KVM: MMU: limit rmap chain length
KVM: ia64: fix build failures due to ia64/unsigned long mismatches
KVM: Make KVM_HPAGES_PER_HPAGE unsigned long to avoid build error on powerpc
KVM: fix ack not being delivered when msi present
KVM: s390: fix wait_queue handling
KVM: VMX: Fix locking imbalance on emulation failure
KVM: VMX: Fix locking order in handle_invalid_guest_state
KVM: MMU: handle n_free_mmu_pages > n_alloc_mmu_pages in kvm_mmu_change_mmu_pages
KVM: SVM: force new asid on vcpu migration
KVM: x86: verify MTRR/PAT validity
KVM: PIT: fix kpit_elapsed division by zero
KVM: Fix KVM_GET_MSR_INDEX_LIST
Check whether index is within bounds before testing the element.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
There are two waitqueues in kvm for wait handling:
vcpu->wq for virt/kvm/kvm_main.c and
vpcu->arch.local_int.wq for the s390 specific wait code.
the wait handling in kvm_s390_handle_wait was broken by using different
wait_queues for add_wait queue and remove_wait_queue.
There are two options to fix the problem:
o move all the s390 specific code to vcpu->wq and remove
vcpu->arch.local_int.wq
o move all the s390 specific code to vcpu->arch.local_int.wq
This patch chooses the 2nd variant for two reasons:
o s390 does not use kvm_vcpu_block but implements its own enabled wait
handling.
Having a separate wait_queue make it clear, that our wait mechanism is
different
o the patch is much smaller
Report-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
2.6.31-rc introduced an architecture level set checker based on facility
bits. e.g. if the kernel is compiled to run only on z9, several facility
bits are checked very early and the kernel refuses to boot if a z9 specific
facility is missing.
Until now kvm on s390 did not implement the store facility extended (STFLE)
instruction. A 2.6.31-rc kernel that was compiled for z9 or higher did not
boot in kvm. This patch implements stfle.
This patch should go in before 2.6.31.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Adds more checking in case lockdep is turned on.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This check verifies that the guest we're trying to run in KVM_RUN
has some memory assigned to it. It enters an endless exception
loop if this is not the case.
Reported-by: Mijo Safradin <mijo@linux.vnet.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch adds a sanity check for the content of the guest
prefix register content before faulting in the cpu lowcore
that it refers to. The guest might end up in an endless loop
where SIE complains about missing lowcore with incorrect
content of the prefix register without this fix.
Reported-by: Mijo Safradin <mijo@linux.vnet.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch makes sure we do unlink a vcpu's sie control block
from the system control area in kvm_arch_vcpu_destroy. This
prevents illegal accesses to the sie control block from other
virtual cpus after free.
Reported-by: Mijo Safradin <mijo@linux.vnet.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The floating interrupt lock is only taken in process context. We can
replace all spin_lock_bh with standard spin_lock calls.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch reworks the s390 clock comparator wakeup to hrtimer. The clock
comparator is a per-cpu value that is compared against the TOD clock. If
ckc <= TOD an external interrupt 1004 is triggered. Since the clock comparator
and the TOD clock have a much higher resolution than jiffies we should use
hrtimers to trigger the wakeup. This speeds up guest nanosleep for small
values.
Since hrtimers callbacks run in hard-irq context, I added a tasklet to do
the actual work with enabled interrupts.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch fixes an incorrectness in the kvm backend for s390.
In case virtual cpus are being created before the corresponding
memory slot is being registered, we need to update the sie
control blocks for the virtual cpus.
*updates in v3*
In consideration of the s390 memslot constraints locking was changed
to trylock. These locks should never be held, as vcpu's can't run without
the single memslot we just assign when running this code. To ensure this
never deadlocks in case other code changes the code uses trylocks and bail
out if it can't get all locks.
Additionally most of the discussed special conditions for s390 like
only one memslot and no user_alloc are now checked for validity in
kvm_arch_set_memory_region.
Reported-by: Mijo Safradin <mijo@linux.vnet.ibm.com>
Signed-off-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Ehrhardt <ehrhardt@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
kvm_vcpu_block() unhalts vpu on an interrupt/timer without checking
if interrupt window is actually opened.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (81 commits)
[S390] remove duplicated #includes
[S390] cpumask: use mm_cpumask() wrapper
[S390] cpumask: Use accessors code.
[S390] cpumask: prepare for iterators to only go to nr_cpu_ids/nr_cpumask_bits.
[S390] cpumask: remove cpu_coregroup_map
[S390] fix clock comparator save area usage
[S390] Add hwcap flag for the etf3 enhancement facility
[S390] Ensure that ipl panic notifier is called late.
[S390] fix dfp elf hwcap/facility bit detection
[S390] smp: perform initial cpu reset before starting a cpu
[S390] smp: fix memory leak on __cpu_up
[S390] ipl: Improve checking logic and remove switch defaults.
[S390] s390dbf: Remove needless check for NULL pointer.
[S390] s390dbf: Remove redundant initilizations.
[S390] use kzfree()
[S390] BUG to BUG_ON changes
[S390] zfcpdump: Prevent zcore from beeing built as a kernel module.
[S390] Use csum_partial in checksum.h
[S390] cleanup lowcore.h
[S390] eliminate ipl_device from lowcore
...
Split machine check handler code and move it to cio and kernel code
where it belongs to. No functional change.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Currently we use the cpuid (via STIDP instruction) to recognize LPAR,
z/VM and KVM.
The architecture states, that bit 0-7 of STIDP returns all zero, and
if STIDP is executed in a virtual machine, the VM operating system
will replace bits 0-7 with FF.
KVM should not use FE to distinguish z/VM from KVM for interested
guests. The proper way to detect the hypervisor is the STSI (Store
System Information) instruction, which return information about the
hypervisors via function code 3, selector1=2, selector2=2.
This patch changes the detection routine of Linux to use STSI instead
of STIDP. This detection is earlier than bootmem, we have to use a
static buffer. Since STSI expects a 4kb block (4kb aligned) this
patch also changes the init.data alignment for s390. As this section
will be freed during boot, this should be no problem.
Patch is tested with LPAR, z/VM, KVM on LPAR, and KVM under z/VM.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch fixes the SET PREFIX interrupt if triggered by userspace.
Until now, it was not necessary, but life migration will need it. In
addition, it helped me creating SMP support for my kvm_crashme tool
(lets kvm execute random guest memory content).
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The kernel handles some priviledged instruction exits. While I was
unable to trigger such an exit from guest userspace, the code should
check for supervisor state before emulating a priviledged instruction.
I also renamed kvm_s390_handle_priv to kvm_s390_handle_b2. After all
there are non priviledged b2 instructions like stck (store clock).
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
KVM on s390 does not support the ESA/390 architecture. We refuse to
change the architecture mode and print a warning. This patch removes
the printk for several reasons:
o A malicious guest can flood host dmesg
o The old message had no newline
o there is no connection between the message and the failing guest
This patch simply removes the printk. We already set the condition
code to 3 - the guest knows that something went wrong.
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Two KVM archs support irqchips and two don't. Add a Kconfig item to
make selecting between the two models easier.
Signed-off-by: Avi Kivity <avi@redhat.com>
This rips out the support for KVM_DEBUG_GUEST and introduces a new IOCTL
instead: KVM_SET_GUEST_DEBUG. The IOCTL payload consists of a generic
part, controlling the "main switch" and the single-step feature. The
arch specific part adds an x86 interface for intercepting both types of
debug exceptions separately and re-injecting them when the host was not
interested. Moveover, the foundation for guest debugging via debug
registers is layed.
To signal breakpoint events properly back to userland, an arch-specific
data block is now returned along KVM_EXIT_DEBUG. For x86, the arch block
contains the PC, the debug exception, and relevant debug registers to
tell debug events properly apart.
The availability of this new interface is signaled by
KVM_CAP_SET_GUEST_DEBUG. Empty stubs for not yet supported archs are
provided.
Note that both SVM and VTX are supported, but only the latter was tested
yet. Based on the experience with all those VTX corner case, I would be
fairly surprised if SVM will work out of the box.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
kvm_arch_sync_events is introduced to quiet down all other events may happen
contemporary with VM destroy process, like IRQ handler and work struct for
assigned device.
For kvm_arch_sync_events is called at the very beginning of kvm_destroy_vm(), so
the state of KVM here is legal and can provide a environment to quiet down other
events.
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
As requested by Andrew. Same as what sparc did.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
The s390 backend of kvm never calls kvm_vcpu_uninit. This causes
a memory leak of vcpu->run pages.
Lets call kvm_vcpu_uninit in kvm_arch_vcpu_destroy to free
the vcpu->run.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Currently it is impossible to unload the kvm module on s390.
This patch fixes kvm_arch_destroy_vm to release all cpus.
This make it possible to unload the module.
In addition we stop messing with the module refcount in arch code.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
We can get an exit for instructions starting with 0xae, even if the guest is
in userspace. Lets make sure, that the signal processor handler is only called
in guest supervisor mode. Otherwise, send a program check.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Heiko Carstens pointed out, that its safer to activate working facilities
instead of disabling problematic facilities. The new code uses the host
facility bits and masks it with known good ones.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
The z10 system supports large pages, kvm-s390 doesnt.
Make sure that we dont advertise large pages to avoid the guest crashing as
soon as the guest kernel activates DAT.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
Carsten Otte