- 29 Aug, 2014 8 commits
-
-
Alex Williamson authored
Windows 8.1 guest with NVIDIA driver and GPU fails to boot with an emulation failure. The KVM spew suggests the fault is with lack of movntdq emulation (courtesy of Paolo): Code=02 00 00 b8 08 00 00 00 f3 0f 6f 44 0a f0 f3 0f 6f 4c 0a e0 <66> 0f e7 41 f0 66 0f e7 49 e0 48 83 e9 40 f3 0f 6f 44 0a 10 f3 0f 6f 0c 0a 66 0f e7 41 10 $ as -o a.out .section .text .byte 0x66, 0x0f, 0xe7, 0x41, 0xf0 .byte 0x66, 0x0f, 0xe7, 0x49, 0xe0 $ objdump -d a.out 0: 66 0f e7 41 f0 movntdq %xmm0,-0x10(%rcx) 5: 66 0f e7 49 e0 movntdq %xmm1,-0x20(%rcx) Add the necessary emulation. Signed-off-by:Alex Williamson <alex.williamson@redhat.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com>
-
Nadav Amit authored
Unlike VMCALL, the instructions VMXOFF, VMLAUNCH and VMRESUME should cause a UD exception in real-mode or vm86. However, the emulator considers all these instructions the same for the matter of mode checks, and emulation upon exit due to #UD exception. As a result, the hypervisor behaves incorrectly on vm86 mode. VMXOFF, VMLAUNCH or VMRESUME cause on vm86 exit due to #UD. The hypervisor then emulates these instruction and inject #GP to the guest instead of #UD. This patch creates a new group for these instructions and mark only VMCALL as an instruction which can be emulated. Signed-off-by:
Nadav Amit <namit@cs.technion.ac.il> Signed-off-by:
-
Paolo Bonzini authored
Sparse reports the following easily fixed warnings: arch/x86/kvm/vmx.c:8795:48: sparse: Using plain integer as NULL pointer arch/x86/kvm/vmx.c:2138:5: sparse: symbol vmx_read_l1_tsc was not declared. Should it be static? arch/x86/kvm/vmx.c:6151:48: sparse: Using plain integer as NULL pointer arch/x86/kvm/vmx.c:8851:6: sparse: symbol vmx_sched_in was not declared. Should it be static? arch/x86/kvm/svm.c:2162:5: sparse: symbol svm_read_l1_tsc was not declared. Should it be static? Cc: Radim Krčmář <rkrcmar@redhat.com> Signed-off-by:
Fengguang Wu <fengguang.wu@intel.com> Signed-off-by:
-
Wanpeng Li authored
This patch fix bug https://bugzilla.kernel.org/show_bug.cgi?id=61411 TPR shadow/threshold feature is important to speed up the Windows guest. Besides, it is a must feature for certain VMM. We map virtual APIC page address and TPR threshold from L1 VMCS. If TPR_BELOW_THRESHOLD VM exit is triggered by L2 guest and L1 interested in, we inject it into L1 VMM for handling. Reviewed-by:
Wanpeng Li <wanpeng.li@linux.intel.com> [Add PAGE_ALIGNED check, do not write useless virtual APIC page address if TPR shadowing is disabled. - Paolo] Signed-off-by:
-
Wanpeng Li authored
Introduce function nested_get_vmcs12_pages() to check the valid of nested apic access page and virtual apic page earlier. Signed-off-by:
-
Christoffer Dall authored
The idea between capabilities and the KVM_CHECK_EXTENSION ioctl is that userspace can, at run-time, determine if a feature is supported or not. This allows KVM to being supporting a new feature with a new kernel version without any need to update user space. Unfortunately, since the definition of KVM_CAP_USER_NMI was guarded by #ifdef __KVM_HAVE_USER_NMI, such discovery still required a user space update. Therefore, unconditionally export KVM_CAP_USER_NMI and change the the typo in the comment for the IOCTL number definition as well. Signed-off-by:
Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by:
-
Christoffer Dall authored
The idea between capabilities and the KVM_CHECK_EXTENSION ioctl is that userspace can, at run-time, determine if a feature is supported or not. This allows KVM to being supporting a new feature with a new kernel version without any need to update user space. Unfortunately, since the definition of KVM_CAP_READONLY_MEM was guarded by #ifdef __KVM_HAVE_READONLY_MEM, such discovery still required a user space update. Therefore, unconditionally export KVM_CAP_READONLY_MEM and change the in-kernel conditional to rely on __KVM_HAVE_READONLY_MEM. Signed-off-by:
-
Christian Borntraeger authored
commit ab3f285f ("KVM: s390/mm: try a cow on read only pages for key ops")' misaligned a code block. Let's fixup the indentation. Reported-by:
Ben Hutchings <ben@decadent.org.uk> Signed-off-by:
Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by:
-
- 26 Aug, 2014 4 commits
-
-
Paolo Bonzini authored
Merge tag 'kvm-s390-next-20140825' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD KVM: s390: Fixes and features for 3.18 part 1 1. The usual cleanups: get rid of duplicate code, use defines, factor out the sync_reg handling, additional docs for sync_regs, better error handling on interrupt injection 2. We use KVM_REQ_TLB_FLUSH instead of open coding tlb flushes 3. Additional registers for kvm_run sync regs. This is usually not needed in the fast path due to eventfd/irqfd, but kvm stat claims that we reduced the overhead of console output by ~50% on my system 4. A rework of the gmap infrastructure. This is the 2nd step towards host large page support (after getting rid of the storage key dependency). We introduces two radix trees to store the guest-to-host and host-to-guest translations. This gets us rid of most of the page-table walks in the gmap code. Only one in __gmap_link is left, this one is required to link the shadow page table to the process page table. Finally this contains the plumbing to support gmap page tables with less than 5 levels.
-
Martin Schwidefsky authored
The radix tree rework removed all code that uses the gmap_rmap and gmap_pgtable data structures. Remove these outdated definitions. Signed-off-by:
Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by:
-
Martin Schwidefsky authored
Add an addressing limit to the gmap address spaces and only allocate the page table levels that are needed for the given limit. The limit is fixed and can not be changed after a gmap has been created. Signed-off-by:
-
Martin Schwidefsky authored
Store the target address for the gmap segments in a radix tree instead of using invalid segment table entries. gmap_translate becomes a simple radix_tree_lookup, gmap_fault is split into the address translation with gmap_translate and the part that does the linking of the gmap shadow page table with the process page table. A second radix tree is used to keep the pointers to the segment table entries for segments that are mapped in the guest address space. On unmap of a segment the pointer is retrieved from the radix tree and is used to carry out the segment invalidation in the gmap shadow page table. As the radix tree can only store one pointer, each host segment may only be mapped to exactly one guest location. Signed-off-by:
-
- 25 Aug, 2014 16 commits
-
-
Paolo Bonzini authored
Fix commit 7b46268d, which mistakenly included the new tracepoint under #ifdef CONFIG_X86_64. Reported-by:
Sabrina Dubroca <sd@queasysnail.net> Signed-off-by:
-
Paolo Bonzini authored
Merge tag 'kvm-s390-20140825' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD Here are two fixes for s390 KVM code that prevent: 1. a malicious user to trigger a kernel BUG 2. a malicious user to change the storage key of read-only pages
-
Martin Schwidefsky authored
Make the order of arguments for the gmap calls more consistent, if the gmap pointer is passed it is always the first argument. In addition distinguish between guest address and user address by naming the variables gaddr for a guest address and vmaddr for a user address. Signed-off-by:
Cornelia Huck <cornelia.huck@de.ibm.com> Signed-off-by:
-
Martin Schwidefsky authored
Revert git commit c3a23b9874c1 ("remove unnecessary parameter from gmap_do_ipte_notify"). Signed-off-by: -
Martin Schwidefsky authored
Revert git commit 1b7fd6952063 ("remove unecessary parameter from pgste_ipte_notify") Signed-off-by: -
Jens Freimann authored
The kvm lock protects us against vcpus going away, but they only go away when the virtual machine is shut down. We don't need this mutex here, so let's get rid of it. Signed-off-by:
Jens Freimann <jfrei@linux.vnet.ibm.com> Reviewed-by:
David Hildenbrand <dahi@linux.vnet.ibm.com> Reviewed-by:
-
Jens Freimann authored
Currently we just kill the userspace process and exit the thread immediatly without making sure that we don't hold any locks etc. Improve this by making KVM_RUN return -EFAULT if the lowcore is not mapped during interrupt delivery. To achieve this we need to pass the return code of guest memory access routines used in interrupt delivery all the way back to the KVM_RUN ioctl. Signed-off-by:
-
David Hildenbrand authored
Use the KVM_REQ_TLB_FLUSH request in order to trigger tlb flushes instead of manipulating the SIE control block whenever we need it. Also trigger it for a control register sync directly instead of (ab)using kvm_s390_set_prefix(). Signed-off-by:
-
David Hildenbrand authored
In order to reduce the number of syscalls when dropping to user space, this patch enables the synchronization of the following "registers" with kvm_run: - ARCH0: CPU timer, clock comparator, TOD programmable register, guest breaking-event register, program parameter - PFAULT: pfault parameters (token, select, compare) The registers are grouped to reduce the overhead when syncing. As this grows the number of sync registers quite a bit, let's move the code synchronizing registers with kvm_run from kvm_arch_vcpu_ioctl_run() into separate helper routines. Signed-off-by: -
Christian Borntraeger authored
The load PSW handler does not have to inject pending machine checks. This can wait until the CPU runs the generic interrupt injection code. Signed-off-by:
-
David Hildenbrand authored
We should make sure that all kvm_dirty_regs bits are cleared before dropping to user space. Until now, some would remain pending. Signed-off-by:
-
David Hildenbrand authored
This patch clarifies that kvm_dirty_regs are just a hint to the kernel and that the kernel might just ignore some flags and sync the values (like done for acrs and gprs now). Signed-off-by:
-
Jens Freimann authored
Let's make this a reusable function. Signed-off-by:
-
Christian Borntraeger authored
The PFMF instruction handler blindly wrote the storage key even if the page was mapped R/O in the host. Lets try a COW before continuing and bail out in case of errors. Signed-off-by:
Dominik Dingel <dingel@linux.vnet.ibm.com> Cc: stable@vger.kernel.org
-
Jens Freimann authored
Get rid of open coded values for pfault init. Signed-off-by:
-
Christian Borntraeger authored
In the early days, we had some special handling for the KVM_EXIT_S390_SIEIC exit, but this was gone in 2009 with commit d7b0b5eb (KVM: s390: Make psw available on all exits, not just a subset). Now this switch statement is just a sanity check for userspace not messing with the kvm_run structure. Unfortunately, this allows userspace to trigger a kernel BUG. Let's just remove this switch statement. Signed-off-by:
-
- 21 Aug, 2014 7 commits
-
-
Radim Krčmář authored
Tracepoint for dynamic PLE window, fired on every potential change. Signed-off-by:
Radim Krčmář <rkrcmar@redhat.com> Signed-off-by:
-
Radim Krčmář authored
Window is increased on every PLE exit and decreased on every sched_in. The idea is that we don't want to PLE exit if there is no preemption going on. We do this with sched_in() because it does not hold rq lock. There are two new kernel parameters for changing the window: ple_window_grow and ple_window_shrink ple_window_grow affects the window on PLE exit and ple_window_shrink does it on sched_in; depending on their value, the window is modifier like this: (ple_window is kvm_intel's global) ple_window_shrink/ | ple_window_grow | PLE exit | sched_in -------------------+--------------------+--------------------- < 1 | = ple_window | = ple_window < ple_window | *= ple_window_grow | /= ple_window_shrink otherwise | += ple_window_grow | -= ple_window_shrink A third new parameter, ple_window_max, controls the maximal ple_window; it is internally rounded down to a closest multiple of ple_window_grow. VCPU's PLE window is never allowed below ple_window. Signed-off-by:
-
Radim Krčmář authored
Change PLE window into per-VCPU variable, seeded from module parameter, to allow greater flexibility. Brings in a small overhead on every vmentry. Signed-off-by:
-
Radim Krčmář authored
sched_in preempt notifier is available for x86, allow its use in specific virtualization technlogies as well. Signed-off-by:
-
Radim Krčmář authored
Introduce preempt notifiers for architecture specific code. Advantage over creating a new notifier in every arch is slightly simpler code and guaranteed call order with respect to kvm_sched_in. Signed-off-by:
-
Nadav Amit authored
Replace reference to X86_FEATURE_NX using bit shift with the defined X86_FEATURE_NX. Signed-off-by:
-
Christian Borntraeger authored
We dont have to wait for a grace period if there is no oldpid that we are going to free. putpid also checks for NULL, so this patch only fences synchronize_rcu. Signed-off-by:
-
- 20 Aug, 2014 4 commits
-
-
Paolo Bonzini authored
These were reported when running Jailhouse on AMD processors. Initialize ctxt->exception.vector with an invalid exception number, and warn if it remained invalid even though the emulator got an X86EMUL_PROPAGATE_FAULT return code. Signed-off-by: -
Paolo Bonzini authored
Always get it through emulate_exception or emulate_ts. This ensures that the ctxt->exception fields have been populated. Signed-off-by: -
Nadav Amit authored
kvm_pmu_cpuid_update makes a lot of bit manuiplation operations, when in fact there are already unions that can be used instead. Changing the bit manipulation to the union for clarity. This patch does not change the functionality. Signed-off-by:
-
Wanpeng Li authored
EPT misconfig handler in kvm will check which reason lead to EPT misconfiguration after vmexit. One of the reasons is that an EPT paging-structure entry is configured with settings reserved for future functionality. However, the handler can't identify if paging-structure entry of reserved bits for 1-GByte page are configured, since PDPTE which point to 1-GByte page will reserve bits 29:12 instead of bits 7:3 which are reserved for PDPTE that references an EPT Page Directory. This patch fix it by reserve bits 29:12 for 1-GByte page. Signed-off-by:
-
- 19 Aug, 2014 1 commit
-
-
Nadav Amit authored
Currently, recalculate_apic_map ignores vcpus whose lapic is software disabled through the spurious interrupt vector. However, once it is re-enabled, the map is not recalculated. Therefore, if the guest OS configured DFR while lapic is software-disabled, the map may be incorrect. This patch recalculates apic map after software enabling the lapic. Signed-off-by:
-
