- 08 Apr, 2015 18 commits
-
-
Wanpeng Li authored
Dirty logging tracks sptes in 4k granularity, meaning that large sptes have to be split. If live migration is successful, the guest in the source machine will be destroyed and large sptes will be created in the destination. However, the guest continues to run in the source machine (for example if live migration fails), small sptes will remain around and cause bad performance. This patch introduce lazy collapsing of small sptes into large sptes. The rmap will be scanned in ioctl context when dirty logging is stopped, dropping those sptes which can be collapsed into a single large-page spte. Later page faults will create the large-page sptes. Reviewed-by:
Xiao Guangrong <guangrong.xiao@linux.intel.com> Signed-off-by:
Wanpeng Li <wanpeng.li@linux.intel.com> Message-Id: <1428046825-6905-1-git-send-email-wanpeng.li@linux.intel.com> Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com>
-
Nadav Amit authored
CR2 is not cleared as it should after reset. See Intel SDM table named "IA-32 Processor States Following Power-up, Reset, or INIT". Signed-off-by:
Nadav Amit <namit@cs.technion.ac.il> Message-Id: <1427933438-12782-5-git-send-email-namit@cs.technion.ac.il> Signed-off-by:
-
Nadav Amit authored
DR0-DR3 are not cleared as they should during reset and when they are set from userspace. It appears to be caused by c77fb5fe ("KVM: x86: Allow the guest to run with dirty debug registers"). Force their reload on these situations. Signed-off-by:
-
Nadav Amit authored
After reset, the CPU can change the BSP, which will be used upon INIT. Reset should return the BSP which QEMU asked for, and therefore handled accordingly. To quote: "If the MP protocol has completed and a BSP is chosen, subsequent INITs (either to a specific processor or system wide) do not cause the MP protocol to be repeated." [Intel SDM 8.4.2: MP Initialization Protocol Requirements and Restrictions] Signed-off-by:
-
Radim Krčmář authored
recalculate_apic_map() uses two passes over all VCPUs. This is a relic from time when we selected a global mode in the first pass and set up the optimized table in the second pass (to have a consistent mode). Recent changes made mixed mode unoptimized and we can do it in one pass. Format of logical MDA is a function of the mode, so we encode it in apic_logical_id() and drop obsoleted variables from the struct. Signed-off-by:
Radim Krčmář <rkrcmar@redhat.com> Message-Id: <1423766494-26150-5-git-send-email-rkrcmar@redhat.com> [Add lid_bits temporary in apic_logical_id. - Paolo] Signed-off-by:
-
Radim Krčmář authored
We want to support mixed modes and the easiest solution is to avoid optimizing those weird and unlikely scenarios. Signed-off-by:
-
Radim Krčmář authored
Broadcast allowed only one global APIC mode, but mixed modes are theoretically possible. x2APIC IPI doesn't mean 0xff as broadcast, the rest does. x2APIC broadcasts are accepted by xAPIC. If we take SDM to be logical, even addreses beginning with 0xff should be accepted, but real hardware disagrees. This patch aims for simple code by considering most of real behavior as undefined. Signed-off-by:
-
Radim Krčmář authored
In mixed modes, we musn't deliver xAPIC IPIs like x2APIC and vice versa. Instead of preserving the information in apic_send_ipi(), we regain it by converting all destinations into correct MDA in the slow path. This allows easier reasoning about subsequent matching. Our kvm_apic_broadcast() had an interesting design decision: it didn't consider IOxAPIC 0xff as broadcast in x2APIC mode ... everything worked because IOxAPIC can't set that in physical mode and logical mode considered it as a message for first 8 VCPUs. This patch interprets IOxAPIC 0xff as x2APIC broadcast. Signed-off-by:
-
Arseny Solokha authored
Drop unused static procedure which doesn't have callers within its translation unit. It had been already removed independently in QEMU[1] from the OpenPIC implementation borrowed from the kernel. [1] https://lists.gnu.org/archive/html/qemu-devel/2014-06/msg01812.htmlSigned-off-by:
Arseny Solokha <asolokha@kb.kras.ru> Cc: Alexander Graf <agraf@suse.de> Cc: Gleb Natapov <gleb@kernel.org> Cc: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <1424768706-23150-3-git-send-email-asolokha@kb.kras.ru> Signed-off-by:
-
Eugene Korenevsky authored
After speed-up of cpuid_maxphyaddr() it can be called frequently: instead of heavyweight enumeration of CPUID entries it returns a cached pre-computed value. It is also inlined now. So caching its result became unnecessary and can be removed. Signed-off-by:
Eugene Korenevsky <ekorenevsky@gmail.com> Message-Id: <20150329205644.GA1258@gnote> Signed-off-by:
-
Eugene Korenevsky authored
On each VM-entry CPU should check the following VMCS fields for zero bits beyond physical address width: - APIC-access address - virtual-APIC address - posted-interrupt descriptor address This patch adds these checks required by Intel SDM. Signed-off-by:
-
Eugene Korenevsky authored
cpuid_maxphyaddr(), which performs lot of memory accesses is called extensively across KVM, especially in nVMX code. This patch adds a cached value of maxphyaddr to vcpu.arch to reduce the pressure onto CPU cache and simplify the code of cpuid_maxphyaddr() callers. The cached value is initialized in kvm_arch_vcpu_init() and reloaded every time CPUID is updated by usermode. It is obvious that these reloads occur infrequently. Signed-off-by:
-
Radim Krčmář authored
Exposing the on-stack error code with internal error is cheap and potentially useful. Signed-off-by:
-
Radim Krčmář authored
If we were migrated right after __getcpu, but before reading the migration_count, we wouldn't notice that we read TSC of a different VCPU, nor that KVM's bug made pvti invalid, as only migration_count on source VCPU is increased. Change vdso instead of updating migration_count on destination. Cc: stable@vger.kernel.org Signed-off-by:
-
Paolo Bonzini authored
The corresponding write functions just use __copy_to_user. Do the same on the read side. This reverts what's left of commit 86ab8cff (KVM: introduce gfn_to_hva_read/kvm_read_hva/kvm_read_hva_atomic, 2012-08-21) Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com> Signed-off-by:
-
Paolo Bonzini authored
The newly-added tracepoint shows the following results on the tscdeadline_latency test: qemu-kvm-8387 [002] 6425.558974: kvm_vcpu_wakeup: poll time 10407 ns qemu-kvm-8387 [002] 6425.558984: kvm_vcpu_wakeup: poll time 0 ns qemu-kvm-8387 [002] 6425.561242: kvm_vcpu_wakeup: poll time 10477 ns qemu-kvm-8387 [002] 6425.561251: kvm_vcpu_wakeup: poll time 0 ns and so on. This is because we need to go through kvm_vcpu_block again after the timer IRQ is injected. Avoid it by polling once before entering kvm_vcpu_block. On my machine (Xeon E5 Sandy Bridge) this removes about 500 cycles (7%) from the latency of the TSC deadline timer. Signed-off-by: -
Paolo Bonzini authored
Rename the old __vcpu_run to vcpu_run, and extract part of it to a new function vcpu_block. The next patch will add a new condition in vcpu_block, avoid extra indentation. Reviewed-by:
David Matlack <dmatlack@google.com> Signed-off-by:
-
Wanpeng Li authored
Guest can't be booted w/ ept=0, there is a message dumped as below: If you're running a guest on an Intel machine without unrestricted mode support, the failure can be most likely due to the guest entering an invalid state for Intel VT. For example, the guest maybe running in big real mode which is not supported on less recent Intel processors. EAX=00000011 EBX=f000d2f6 ECX=00006cac EDX=000f8956 ESI=bffbdf62 EDI=00000000 EBP=00006c68 ESP=00006c68 EIP=0000d187 EFL=00000004 [-----P-] CPL=0 II=0 A20=1 SMM=0 HLT=0 ES =e000 000e0000 ffffffff 00809300 DPL=0 DS16 [-WA] CS =f000 000f0000 ffffffff 00809b00 DPL=0 CS16 [-RA] SS =0000 00000000 ffffffff 00809300 DPL=0 DS16 [-WA] DS =0000 00000000 ffffffff 00809300 DPL=0 DS16 [-WA] FS =0000 00000000 ffffffff 00809300 DPL=0 DS16 [-WA] GS =0000 00000000 ffffffff 00809300 DPL=0 DS16 [-WA] LDT=0000 00000000 0000ffff 00008200 DPL=0 LDT TR =0000 00000000 0000ffff 00008b00 DPL=0 TSS32-busy GDT= 000f6a80 00000037 IDT= 000f6abe 00000000 CR0=00000011 CR2=00000000 CR3=00000000 CR4=00000000 DR0=0000000000000000 DR1=0000000000000000 DR2=0000000000000000 DR3=0000000000000000 DR6=00000000ffff0ff0 DR7=0000000000000400 EFER=0000000000000000 Code=01 1e b8 6a 2e 0f 01 16 74 6a 0f 20 c0 66 83 c8 01 0f 22 c0 <66> ea 8f d1 0f 00 08 00 b8 10 00 00 00 8e d8 8e c0 8e d0 8e e0 8e e8 89 c8 ff e2 89 c1 b8X X86 eflags bit 1 is fixed set, which means that 1 << 1 is set instead of 1, this patch fix it. Signed-off-by:
-
- 07 Apr, 2015 3 commits
-
-
Paolo Bonzini authored
Merge tag 'kvm-s390-next-20150331' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD Features and fixes for 4.1 (kvm/next) 1. Assorted changes 1.1 allow more feature bits for the guest 1.2 Store breaking event address on program interrupts 2. Interrupt handling rework 2.1 Fix copy_to_user while holding a spinlock (cc stable) 2.2 Rework floating interrupts to follow the priorities 2.3 Allow to inject all local interrupts via new ioctl 2.4 allow to get/set the full local irq state, e.g. for migration and introspection
-
Paolo Bonzini authored
Merge tag 'kvm-arm-for-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into 'kvm-next' KVM/ARM changes for v4.1: - fixes for live migration - irqfd support - kvm-io-bus & vgic rework to enable ioeventfd - page ageing for stage-2 translation - various cleanups
-
Paolo Bonzini authored
Merge tag 'kvm-arm-fixes-4.0-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into 'kvm-next' Fixes for KVM/ARM for 4.0-rc5. Fixes page refcounting issues in our Stage-2 page table management code, fixes a missing unlock in a gicv3 error path, and fixes a race that can cause lost interrupts if signals are pending just prior to entering the guest.
-
- 31 Mar, 2015 9 commits
-
-
Jens Freimann authored
This patch adds support to migrate vcpu interrupts. Two new vcpu ioctls are added which get/set the complete status of pending interrupts in one go. The ioctls are marked as available with the new capability KVM_CAP_S390_IRQ_STATE. We can not use a ONEREG, as the number of pending local interrupts is not constant and depends on the number of CPUs. To retrieve the interrupt state we add an ioctl KVM_S390_GET_IRQ_STATE. Its input parameter is a pointer to a struct kvm_s390_irq_state which has a buffer and length. For all currently pending interrupts, we copy a struct kvm_s390_irq into the buffer and pass it to userspace. To store interrupt state into a buffer provided by userspace, we add an ioctl KVM_S390_SET_IRQ_STATE. It passes a struct kvm_s390_irq_state into the kernel and injects all interrupts contained in the buffer. Signed-off-by:
Jens Freimann <jfrei@linux.vnet.ibm.com> Signed-off-by:
Christian Borntraeger <borntraeger@de.ibm.com> Acked-by:
Cornelia Huck <cornelia.huck@de.ibm.com>
-
Jens Freimann authored
Let's provide a version of kvm_s390_inject_vcpu() that does not acquire the local-interrupt lock and skips waking up the vcpu. To be used in a later patch for vcpu-local interrupt migration, where we are already holding the lock. Reviewed-by:
David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by:
-
Jens Freimann authored
We have introduced struct kvm_s390_irq a while ago which allows to inject all kinds of interrupts as defined in the Principles of Operation. Add ioctl to inject interrupts with the extended struct kvm_s390_irq Signed-off-by:
-
David Hildenbrand authored
We now have a mechanism for delivering interrupts according to their priority. Let's inject them using our new infrastructure (instead of letting only hardware handle them), so we can be sure that the irq priorities are satisfied. For s390, the cpu timer and the clock comparator are to be checked for common code kvm_cpu_has_pending_timer(), although the cpu timer is only stepped when the guest is being executed. Reviewed-by:
-
Jens Freimann authored
This patch makes interrupt handling compliant to the z/Architecture Principles of Operation with regard to interrupt priorities. Add a bitmap for pending floating interrupts. Each bit relates to a interrupt type and its list. A turned on bit indicates that a list contains items (interrupts) which need to be delivered. When delivering interrupts on a cpu we can merge the existing bitmap for cpu-local interrupts and floating interrupts and have a single mechanism for delivery. Currently we have one list for all kinds of floating interrupts and a corresponding spin lock. This patch adds a separate list per interrupt type. An exception to this are service signal and machine check interrupts, as there can be only one pending interrupt at a time. Signed-off-by:
-
Jens Freimann authored
This fixes a bug introduced with commit c05c4186 ("KVM: s390: add floating irq controller"). get_all_floating_irqs() does copy_to_user() while holding a spin lock. Let's fix this by filling a temporary buffer first and copy it to userspace after giving up the lock. Cc: <stable@vger.kernel.org> # 3.18+: 69a8d456 KVM: s390: no need to hold... Reviewed-by:
-
Joe Perches authored
Use the normal return values for bool functions Signed-off-by:
Joe Perches <joe@perches.com> Message-Id: <9f593eb2f43b456851cd73f7ed09654ca58fb570.1427759009.git.joe@perches.com> Signed-off-by:
-
Christian Borntraeger authored
After some review about what these facilities do, the following facilities will work under KVM and can, therefore, be reported to the guest if the cpu model and the host cpu provide this bit. There are plans underway to make the whole bit thing more readable, but its not yet finished. So here are some last bit changes and we enhance the KVM mask with: 9 The sense-running-status facility is installed in the z/Architecture architectural mode. ---> handled by SIE or KVM 10 The conditional-SSKE facility is installed in the z/Architecture architectural mode. ---> handled by SIE. KVM will retry SIE 13 The IPTE-range facility is installed in the z/Architecture architectural mode. ---> handled by SIE. KVM will retry SIE 36 The enhanced-monitor facility is installed in the z/Architecture architectural mode. ---> handled by SIE 47 The CMPSC-enhancement facility is installed in the z/Architecture architectural mode. ---> handled by SIE 48 The decimal-floating-point zoned-conversion facility is installed in the z/Architecture architectural mode. ---> handled by SIE 49 The execution-hint, load-and-trap, miscellaneous- instruction-extensions and processor-assist ---> handled by SIE 51 The local-TLB-clearing facility is installed in the z/Architecture architectural mode. ---> handled by SIE 52 The interlocked-access facility 2 is installed. ---> handled by SIE 53 The load/store-on-condition facility 2 and load-and- zero-rightmost-byte facility are installed in the z/Architecture architectural mode. ---> handled by SIE 57 The message-security-assist-extension-5 facility is installed in the z/Architecture architectural mode. ---> handled by SIE 66 The reset-reference-bits-multiple facility is installed in the z/Architecture architectural mode. ---> handled by SIE. KVM will retry SIE 80 The decimal-floating-point packed-conversion facility is installed in the z/Architecture architectural mode. ---> handled by SIE Signed-off-by:
Michael Mueller <mimu@linux.vnet.ibm.com> Acked-by:
-
David Hildenbrand authored
If the PER-3 facility is installed, the breaking-event address is to be stored in the low core. There is no facility bit for PER-3 in stfl(e) and Linux always uses the value at address 272 no matter if PER-3 is available or not. We can't hide its existence from the guest. All program interrupts injected via the SIE automatically store this information if the PER-3 facility is available in the hypervisor. Also the itdb contains the address automatically. As there is no switch to turn this mechanism off, let's simply make it consistent and also store the breaking event address in case of manual program interrupt injection. Reviewed-by:
-
- 30 Mar, 2015 10 commits
-
-
Nikolay Nikolaev authored
As the infrastructure for eventfd has now been merged, report the ioeventfd capability as being supported. Signed-off-by:
Nikolay Nikolaev <n.nikolaev@virtualopensystems.com> [maz: grouped the case entry with the others, fixed commit log] Signed-off-by:
Marc Zyngier <marc.zyngier@arm.com>
-
Andre Przywara authored
Currently we have struct kvm_exit_mmio for encapsulating MMIO abort data to be passed on from syndrome decoding all the way down to the VGIC register handlers. Now as we switch the MMIO handling to be routed through the KVM MMIO bus, it does not make sense anymore to use that structure already from the beginning. So we keep the data in local variables until we put them into the kvm_io_bus framework. Then we fill kvm_exit_mmio in the VGIC only, making it a VGIC private structure. On that way we replace the data buffer in that structure with a pointer pointing to a single location in a local variable, so we get rid of some copying on the way. With all of the virtual GIC emulation code now being registered with the kvm_io_bus, we can remove all of the old MMIO handling code and its dispatching functionality. I didn't bother to rename kvm_exit_mmio (to vgic_mmio or something), because that touches a lot of code lines without any good reason. This is based on an original patch by Nikolay. Signed-off-by:
Andre Przywara <andre.przywara@arm.com> Cc: Nikolay Nikolaev <n.nikolaev@virtualopensystems.com> Reviewed-by:
-
Andre Przywara authored
Using the framework provided by the recent vgic.c changes, we register a kvm_io_bus device on mapping the virtual GICv3 resources. The distributor mapping is pretty straight forward, but the redistributors need some more love, since they need to be tagged with the respective redistributor (read: VCPU) they are connected with. We use the kvm_io_bus framework to register one devices per VCPU. Signed-off-by:
-
Andre Przywara authored
Currently we handle the redistributor registers in two separate MMIO regions, one for the overall behaviour and SPIs and one for the SGIs/PPIs. That latter forces the creation of _two_ KVM I/O bus devices for each redistributor. Since the spec mandates those two pages to be contigious, we could as well merge them and save the churn with the second KVM I/O bus device. Signed-off-by:
-
Eugene Korenevsky authored
A trivial code cleanup. This `if` is redundant. Signed-off-by:
-
Nadav Amit authored
Some constants are redfined in emulate.c. Avoid it. s/SELECTOR_RPL_MASK/SEGMENT_RPL_MASK s/SELECTOR_TI_MASK/SEGMENT_TI_MASK No functional change. Signed-off-by:
-
Nadav Amit authored
The eflags are redefined (using other defines) in emulate.c. Use the definition from processor-flags.h as some mess already started. No functional change. Signed-off-by:
-
Nadav Amit authored
If the source of BSF and BSR is zero, the destination register should not change. That is how real hardware behaves. If we set the destination even with the same value that we had before, we may clear bits [63:32] unnecassarily. Signed-off-by:
-
Nadav Amit authored
POPA should assign the values to the registers as usual registers are assigned. In other words, 32-bits register assignments should clear bits [63:32] of the register. Split the code of register assignments that will be used by future changes as well. Signed-off-by:
-
Nadav Amit authored
On legacy mode CMOV emulation should still clear bits [63:32] even if the assignment is not done. The previous fix 140bad89 ("KVM: x86: emulation of dword cmov on long-mode should clear [63:32]") was incomplete. Signed-off-by:
-
