- 01 Aug, 2010 40 commits
-
-
Xiao Guangrong authored
If the sync-sp just sync transient, don't mark its pte notrap Signed-off-by:
Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Signed-off-by:
Marcelo Tosatti <mtosatti@redhat.com>
-
Xiao Guangrong authored
The sync page is already write protected in mmu_sync_children(), don't write protected it again Signed-off-by:
-
Xiao Guangrong authored
Using wrap function to cleanup page dirty judgment Signed-off-by:
-
Xiao Guangrong authored
Rename 'page' and 'shadow_page' to 'sp' to better fit the context Signed-off-by:
-
Sheng Yang authored
This patch enable save/restore of xsave state. Signed-off-by:
Sheng Yang <sheng@linux.intel.com> Signed-off-by:
-
Denis Kirjanov authored
Fix compile warning: CC [M] arch/powerpc/kvm/powerpc.o arch/powerpc/kvm/powerpc.c: In function 'kvm_arch_vcpu_ioctl_run': arch/powerpc/kvm/powerpc.c:290: warning: 'gpr' may be used uninitialized in this function arch/powerpc/kvm/powerpc.c:290: note: 'gpr' was declared here Signed-off-by:
Denis Kirjanov <dkirjanov@kernel.org> Signed-off-by:
-
Avi Kivity authored
On Intel, we call skip_emulated_instruction() even if we injected a #GP, resulting in the #GP pointing at the wrong address. Fix by injecting the exception and skipping the instruction at the same place, so we can do just one or the other. Signed-off-by:
Avi Kivity <avi@redhat.com> Signed-off-by:
-
Avi Kivity authored
On Intel, we call skip_emulated_instruction() even if we injected a #GP, resulting in the #GP pointing at the wrong address. Fix by injecting the exception and skipping the instruction at the same place, so we can do just one or the other. Signed-off-by:
-
Avi Kivity authored
On Intel, we call skip_emulated_instruction() even if we injected a #GP, resulting in the #GP pointing at the wrong address. Fix by injecting the exception and skipping the instruction at the same place, so we can do just one or the other. Signed-off-by:
-
Dexuan Cui authored
This patch enable guest to use XSAVE/XRSTOR instructions. We assume that host_xcr0 would use all possible bits that OS supported. And we loaded xcr0 in the same way we handled fpu - do it as late as we can. Signed-off-by:
Dexuan Cui <dexuan.cui@intel.com> Signed-off-by:
-
Avi Kivity authored
Signed-off-by: -
Andi Kleen authored
No real bugs in this one. Signed-off-by:
Andi Kleen <ak@linux.intel.com> Signed-off-by:
-
Andi Kleen authored
When the user passed in a NULL mask pass this on from the ioctl handler. Found by gcc 4.6's new warnings. Signed-off-by:
-
Xiao Guangrong authored
delay local tlb flush until enter guest moden, it can reduce vpid flush frequency and reduce remote tlb flush IPI(if KVM_REQ_TLB_FLUSH bit is already set, IPI is not sent) Signed-off-by:
-
Xiao Guangrong authored
Use kvm_mmu_flush_tlb() function instead of calling kvm_x86_ops->tlb_flush(vcpu) directly. Signed-off-by:
-
Xiao Guangrong authored
This remote tlb flush is no necessary since we have synced while sp is zapped Signed-off-by:
-
Xiao Guangrong authored
fix: [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- include/linux/kvm_host.h:258 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 1 1 lock held by qemu-system-x86/3796: #0: (&vcpu->mutex){+.+.+.}, at: [<ffffffffa0217fd8>] vcpu_load+0x1a/0x66 [kvm] stack backtrace: Pid: 3796, comm: qemu-system-x86 Not tainted 2.6.34 #25 Call Trace: [<ffffffff81070ed1>] lockdep_rcu_dereference+0x9d/0xa5 [<ffffffffa0214fdf>] gfn_to_memslot_unaliased+0x65/0xa0 [kvm] [<ffffffffa0216139>] gfn_to_hva+0x22/0x4c [kvm] [<ffffffffa0216217>] kvm_write_guest_page+0x2a/0x7f [kvm] [<ffffffffa0216286>] kvm_clear_guest_page+0x1a/0x1c [kvm] [<ffffffffa0278239>] init_rmode+0x3b/0x180 [kvm_intel] [<ffffffffa02786ce>] vmx_set_cr0+0x350/0x4d3 [kvm_intel] [<ffffffffa02274ff>] kvm_arch_vcpu_ioctl_set_sregs+0x122/0x31a [kvm] [<ffffffffa021859c>] kvm_vcpu_ioctl+0x578/0xa3d [kvm] [<ffffffff8106624c>] ? cpu_clock+0x2d/0x40 [<ffffffff810f7d86>] ? fget_light+0x244/0x28e [<ffffffff810709b9>] ? trace_hardirqs_off_caller+0x1f/0x10e [<ffffffff8110501b>] vfs_ioctl+0x32/0xa6 [<ffffffff81105597>] do_vfs_ioctl+0x47f/0x4b8 [<ffffffff813ae654>] ? sub_preempt_count+0xa3/0xb7 [<ffffffff810f7da8>] ? fget_light+0x266/0x28e [<ffffffff810f7c53>] ? fget_light+0x111/0x28e [<ffffffff81105617>] sys_ioctl+0x47/0x6a [<ffffffff81002c1b>] system_call_fastpath+0x16/0x1b Signed-off-by: -
Gui Jianfeng authored
The name "pid_sync_vcpu_all" isn't appropriate since it just affect a single vpid, so rename it to vpid_sync_vcpu_single(). Signed-off-by:
Gui Jianfeng <guijianfeng@cn.fujitsu.com> Signed-off-by:
-
Gui Jianfeng authored
Add all-context INVVPID type support. Signed-off-by:
-
Xiao Guangrong authored
collect remote tlb flush in kvm_mmu_pte_write() path Signed-off-by:
-
Xiao Guangrong authored
Now, we can safely to traverse sp hlish Signed-off-by:
-
Xiao Guangrong authored
Using kvm_mmu_prepare_zap_page() and kvm_mmu_zap_page() instead of kvm_mmu_zap_page() that can reduce remote tlb flush IPI Signed-off-by:
-
Xiao Guangrong authored
In the later patch, we will modify sp's zapping way like below: kvm_mmu_prepare_zap_page A kvm_mmu_prepare_zap_page B kvm_mmu_prepare_zap_page C .... kvm_mmu_commit_zap_page [ zaped multiple sps only need to call kvm_mmu_commit_zap_page once ] In __kvm_mmu_free_some_pages() function, the free page number is getted form 'vcpu->kvm->arch.n_free_mmu_pages' in loop, it will hinders us to apply kvm_mmu_prepare_zap_page() and kvm_mmu_commit_zap_page() since kvm_mmu_prepare_zap_page() not free sp. Signed-off-by:
-
Xiao Guangrong authored
Using kvm_mmu_prepare_zap_page() and kvm_mmu_commit_zap_page() to split kvm_mmu_zap_page() function, then we can: - traverse hlist safely - easily to gather remote tlb flush which occurs during page zapped Those feature can be used in the later patches Signed-off-by:
-
Xiao Guangrong authored
Introduce for_each_gfn_sp() and for_each_gfn_indirect_valid_sp() to cleanup hlist traverseing Signed-off-by:
-
Xiao Guangrong authored
In kvm_mmu_unprotect_page(), the invalid sp can be skipped Signed-off-by:
-
Gui Jianfeng authored
According to SDM, we need check whether single-context INVVPID type is supported before issuing invvpid instruction. Signed-off-by:
-
Lai Jiangshan authored
Should use linux/uaccess.h instead of asm/uaccess.h Signed-off-by:
Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by:
-
Lai Jiangshan authored
The type of '*new.rmap' is not 'struct page *', fix it Signed-off-by:
-
Sheng Yang authored
We only support 4 levels EPT pagetable now. Signed-off-by:
-
Glauber Costa authored
This patch adds a file that documents the usage of KVM-specific MSRs. Signed-off-by:
Glauber Costa <glommer@redhat.com> Reviewed-by:
Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by:
-
Andreas Schwab authored
Instead of instantiating a whole thread_struct on the stack use only the required parts of it. Signed-off-by:
Andreas Schwab <schwab@linux-m68k.org> Tested-by:
Alexander Graf <agraf@suse.de> Signed-off-by:
-
Mohammed Gamal authored
The vmexit handler returns KVM_EXIT_UNKNOWN since there is no handler for vmentry failures. This intercepts vmentry failures and returns KVM_FAIL_ENTRY to userspace instead. Signed-off-by:
Mohammed Gamal <m.gamal005@gmail.com> Signed-off-by:
-
Gui Jianfeng authored
There's no need to calculate quadrant if tdp is enabled. Signed-off-by:
-
Avi Kivity authored
Signed-off-by:
-
Avi Kivity authored
Signed-off-by: -
Avi Kivity authored
When tdp is enabled, the guest's cr0.wp shouldn't have any effect on spte permissions. Signed-off-by: -
Jan Kiszka authored
Memory allocation may fail. Propagate such errors. Signed-off-by:
Jan Kiszka <jan.kiszka@siemens.com> Reviewed-by:
-
Zachary Amsden authored
Must set VCPU register to be the guest notion of EFER even if that setting is not valid on hardware. This was masked by the set in set_efer until 7657fd5ace88e8092f5f3a84117e093d7b893f26 broke that. Fix is simply to set the VCPU register before stripping bits. Signed-off-by:
Zachary Amsden <zamsden@redhat.com> Signed-off-by:
-
Gui Jianfeng authored
Since we have is_writable_pte(), make use of it. Signed-off-by:
-
