- 01 3月, 2010 14 次提交
-
-
由 Avi Kivity 提交于
When the guest acknowledges an interrupt, it sends an EOI message to the local apic, which broadcasts it to the ioapic. To handle the EOI, we need to take the ioapic mutex. On large guests, this causes a lot of contention on this mutex. Since large guests usually don't route interrupts via the ioapic (they use msi instead), this is completely unnecessary. Avoid taking the mutex by introducing a handled_vectors bitmap. Before taking the mutex, check if the ioapic was actually responsible for the acked vector. If not, we can return early. Signed-off-by: NAvi Kivity <avi@redhat.com> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Using a similar two-step procedure as for memslots. Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Use two steps for memslot deletion: mark the slot invalid (which stops instantiation of new shadow pages for that slot, but allows destruction), then instantiate the new empty slot. Also simplifies kvm_handle_hva locking. Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
So its possible to iommu map a memslot before making it visible to kvm. Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Which takes a memslot pointer instead of using kvm->memslots. To be used by SRCU convertion later. Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Required for SRCU convertion later. Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Marcelo Tosatti 提交于
Have a pointer to an allocated region inside struct kvm. [alex: fix ppc book 3s] Signed-off-by: NAlexander Graf <agraf@suse.de> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Avi Kivity 提交于
- add destructor function - move related allocation into constructor - add stubs for !CONFIG_KVM_MMIO Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Avi Kivity 提交于
s390 doesn't have mmio, this will simplify ifdefing it out. Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Avi Kivity 提交于
Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Avi Kivity 提交于
Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Avi Kivity 提交于
They aren't related. Signed-off-by: NAvi Kivity <avi@redhat.com>
-
- 25 1月, 2010 3 次提交
-
-
由 Michael S. Tsirkin 提交于
kvm didn't clear irqfd counter on deassign, as a result we could get a spurious interrupt when irqfd is assigned back. this leads to poor performance and, in theory, guest crash. Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Marcelo Tosatti 提交于
Otherwise memory beyond irq_states[16] might be accessed. Noticed by Juan Quintela. Cc: stable@kernel.org Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com> Acked-by: NJuan Quintela <quintela@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Michael S. Tsirkin 提交于
Looks like repeatedly binding same fd to multiple gsi's with irqfd can use up a ton of kernel memory for irqfd structures. A simple fix is to allow each fd to only trigger one gsi: triggering a storm of interrupts in guest is likely useless anyway, and we can do it by binding a single gsi to many interrupts if we really want to. Cc: stable@kernel.org Signed-off-by: NMichael S. Tsirkin <mst@redhat.com> Acked-by: NAcked-by: Gregory Haskins <ghaskins@novell.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
- 27 12月, 2009 2 次提交
-
-
由 Heiko Carstens 提交于
arch/s390/kvm/../../../virt/kvm/kvm_main.c: In function 'kvm_create_vm': arch/s390/kvm/../../../virt/kvm/kvm_main.c:409: warning: label 'out_err' defined but not used Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Sheng Yang 提交于
One possible order is: KVM_CREATE_IRQCHIP ioctl(took kvm->lock) -> kvm_iobus_register_dev() -> down_write(kvm->slots_lock). The other one is in kvm_vm_ioctl_assign_device(), which take kvm->slots_lock first, then kvm->lock. Update the comment of lock order as well. Observe it due to kernel locking debug warnings. Cc: stable@kernel.org Signed-off-by: NSheng Yang <sheng@linux.intel.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
- 23 12月, 2009 1 次提交
-
-
由 Roland Dreier 提交于
It seems a couple places such as arch/ia64/kernel/perfmon.c and drivers/infiniband/core/uverbs_main.c could use anon_inode_getfile() instead of a private pseudo-fs + alloc_file(), if only there were a way to get a read-only file. So provide this by having anon_inode_getfile() create a read-only file if we pass O_RDONLY in flags. Signed-off-by: NRoland Dreier <rolandd@cisco.com> Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
-
- 03 12月, 2009 17 次提交
-
-
由 Avi Kivity 提交于
Usually userspace will freeze the guest so we can inspect it, but some internal state is not available. Add extra data to internal error reporting so we can expose it to the debugger. Extra data is specific to the suberror. Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Marcelo Tosatti 提交于
Otherwise kvm might attempt to dereference a NULL pointer. Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Arnd Bergmann 提交于
With big endian userspace, we can't quite figure out if a pointer is 32 bit (shifted >> 32) or 64 bit when we read a 64 bit pointer. This is what happens with dirty logging. To get the pointer interpreted correctly, we thus need Arnd's patch to implement a compat layer for the ioctl: A better way to do this is to add a separate compat_ioctl() method that converts this for you. Based on initial patch from Arnd Bergmann. Signed-off-by: NArnd Bergmann <arnd@arndb.de> Signed-off-by: NAlexander Graf <agraf@suse.de> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Marcelo Tosatti 提交于
find_first_zero_bit works with bit numbers, not bytes. Fixes https://sourceforge.net/tracker/?func=detail&aid=2847560&group_id=180599&atid=893831Reported-by: N"Xu, Jiajun" <jiajun.xu@intel.com> Cc: stable@kernel.org Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Zhai, Edwin 提交于
Introduce kvm_vcpu_on_spin, to be used by VMX/SVM to yield processing once the cpu detects pause-based looping. Signed-off-by: N"Zhai, Edwin" <edwin.zhai@intel.com> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
由 Jiri Slaby 提交于
Stanse found 2 lock imbalances in kvm_request_irq_source_id and kvm_free_irq_source_id. They omit to unlock kvm->irq_lock on fail paths. Fix that by adding unlock labels at the end of the functions and jump there from the fail paths. Signed-off-by: NJiri Slaby <jirislaby@gmail.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Alexander Graf 提交于
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: NAlexander Graf <agraf@suse.de> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Avi Kivity 提交于
Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
The only thing it protects now is interrupt injection into lapic and this can work lockless. Even now with kvm->irq_lock in place access to lapic is not entirely serialized since vcpu access doesn't take kvm->irq_lock. Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
The allows removal of irq_lock from the injection path. Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
Use RCU locking for mask/ack notifiers lists. Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
Mask irq notifier list is already there. Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
Maintain back mapping from irqchip/pin to gsi to speedup interrupt acknowledgment notifications. [avi: build fix on non-x86/ia64] Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
Use gsi indexed array instead of scanning all entries on each interrupt injection. Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Gleb Natapov 提交于
This removes assumptions that max GSIs is smaller than number of pins. Sharing is tracked on pin level not GSI level. [avi: no PIC on ia64] Signed-off-by: NGleb Natapov <gleb@redhat.com> Signed-off-by: NAvi Kivity <avi@redhat.com>
-
由 Avi Kivity 提交于
Preemption notifiers will do that for us automatically. Signed-off-by: NAvi Kivity <avi@redhat.com>
-
- 05 11月, 2009 1 次提交
-
-
由 Alexander Graf 提交于
We currently use host endian long types to store information in the dirty bitmap. This works reasonably well on Little Endian targets, because the u32 after the first contains the next 32 bits. On Big Endian this breaks completely though, forcing us to be inventive here. So Ben suggested to always use Little Endian, which looks reasonable. We only have dirty bitmap implemented in Little Endian targets so far and since PowerPC would be the first Big Endian platform, we can just as well switch to Little Endian always with little effort without breaking existing targets. Signed-off-by: NAlexander Graf <agraf@suse.de> Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
-
- 16 10月, 2009 1 次提交
-
-
由 Darrick J. Wong 提交于
I'm seeing an oops condition when kvm-intel and kvm-amd are modprobe'd during boot (say on an Intel system) and then rmmod'd: # modprobe kvm-intel kvm_init() kvm_init_debug() kvm_arch_init() <-- stores debugfs dentries internally (success, etc) # modprobe kvm-amd kvm_init() kvm_init_debug() <-- second initialization clobbers kvm's internal pointers to dentries kvm_arch_init() kvm_exit_debug() <-- and frees them # rmmod kvm-intel kvm_exit() kvm_exit_debug() <-- double free of debugfs files! *BOOM* If execution gets to the end of kvm_init(), then the calling module has been established as the kvm provider. Move the debugfs initialization to the end of the function, and remove the now-unnecessary call to kvm_exit_debug() from the error path. That way we avoid trampling on the debugfs entries and freeing them twice. Cc: stable@kernel.org Signed-off-by: NDarrick J. Wong <djwong@us.ibm.com> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-
- 04 10月, 2009 1 次提交
-
-
由 Izik Eidus 提交于
this is needed for kvm if it want ksm to directly map pages into its shadow page tables. [marcelo: cast pfn assignment to u64] Signed-off-by: NIzik Eidus <ieidus@redhat.com> Signed-off-by: NMarcelo Tosatti <mtosatti@redhat.com>
-