From bf998156d24bcb127318ad5bf531ac3bdfcd6449 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 31 May 2010 14:28:19 +0800 Subject: KVM: Avoid killing userspace through guest SRAO MCE on unmapped pages In common cases, guest SRAO MCE will cause corresponding poisoned page be un-mapped and SIGBUS be sent to QEMU-KVM, then QEMU-KVM will relay the MCE to guest OS. But it is reported that if the poisoned page is accessed in guest after unmapping and before MCE is relayed to guest OS, userspace will be killed. The reason is as follows. Because poisoned page has been un-mapped, guest access will cause guest exit and kvm_mmu_page_fault will be called. kvm_mmu_page_fault can not get the poisoned page for fault address, so kernel and user space MMIO processing is tried in turn. In user MMIO processing, poisoned page is accessed again, then userspace is killed by force_sig_info. To fix the bug, kvm_mmu_page_fault send HWPOISON signal to QEMU-KVM and do not try kernel and user space MMIO processing for poisoned page. [xiao: fix warning introduced by avi] Reported-by: Max Asbock Signed-off-by: Huang Ying Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + include/linux/mm.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7cb116afa1cd..a0e019769f5d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,6 +266,7 @@ extern pfn_t bad_pfn; int is_error_page(struct page *page); int is_error_pfn(pfn_t pfn); +int is_hwpoison_pfn(pfn_t pfn); int kvm_is_error_hva(unsigned long addr); int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, diff --git a/include/linux/mm.h b/include/linux/mm.h index a2b48041b910..7a9ab7db1975 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1465,6 +1465,14 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t mce_bad_pages; extern int soft_offline_page(struct page *page, int flags); +#ifdef CONFIG_MEMORY_FAILURE +int is_hwpoison_address(unsigned long addr); +#else +static inline int is_hwpoison_address(unsigned long addr) +{ + return 0; +} +#endif extern void dump_page(struct page *page); -- cgit v1.2.3 From d94e1dc9af60e3431a586c3edfbe42d8a0d3932b Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 3 May 2010 16:54:48 +0300 Subject: KVM: Get rid of KVM_REQ_KICK KVM_REQ_KICK poisons vcpu->requests by having a bit set during normal operation. This causes the fast path check for a clear vcpu->requests to fail all the time, triggering tons of atomic operations. Fix by replacing KVM_REQ_KICK with a vcpu->guest_mode atomic. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a0e019769f5d..2c62319727ef 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -81,6 +81,7 @@ struct kvm_vcpu { int vcpu_id; struct mutex mutex; int cpu; + atomic_t guest_mode; struct kvm_run *run; unsigned long requests; unsigned long guest_debug; -- cgit v1.2.3 From 2acf923e38fb6a4ce0c57115decbb38d334902ac Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 10 Jun 2010 11:27:12 +0800 Subject: KVM: VMX: Enable XSAVE/XRSTOR for guest 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 Signed-off-by: Sheng Yang Reviewed-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2c62319727ef..2d96555cd4ed 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -88,7 +88,7 @@ struct kvm_vcpu { int srcu_idx; int fpu_active; - int guest_fpu_loaded; + int guest_fpu_loaded, guest_xcr0_loaded; wait_queue_head_t wq; int sigset_active; sigset_t sigset; -- cgit v1.2.3 From 2d5b5a665508c60577c1088e0405850a965b6795 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Sun, 13 Jun 2010 17:29:39 +0800 Subject: KVM: x86: XSAVE/XRSTOR live migration support This patch enable save/restore of xsave state. Signed-off-by: Sheng Yang Signed-off-by: Marcelo Tosatti --- include/linux/kvm.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 23ea02253900..6fd40f540a8e 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -524,6 +524,12 @@ struct kvm_enable_cap { #define KVM_CAP_PPC_OSI 52 #define KVM_CAP_PPC_UNSET_IRQ 53 #define KVM_CAP_ENABLE_CAP 54 +#ifdef __KVM_HAVE_XSAVE +#define KVM_CAP_XSAVE 55 +#endif +#ifdef __KVM_HAVE_XCRS +#define KVM_CAP_XCRS 56 +#endif #ifdef KVM_CAP_IRQ_ROUTING @@ -714,6 +720,12 @@ struct kvm_clock_data { #define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) #define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) #define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap) +/* Available with KVM_CAP_XSAVE */ +#define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave) +#define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave) +/* Available with KVM_CAP_XCRS */ +#define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) +#define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit v1.2.3 From a1f4d39500ad8ed61825eff061debff42386ab5b Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 21 Jun 2010 11:44:20 +0300 Subject: KVM: Remove memory alias support As advertised in feature-removal-schedule.txt. Equivalent support is provided by overlapping memory regions. Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + include/linux/kvm_host.h | 6 ------ 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 6fd40f540a8e..636fc381c897 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -619,6 +619,7 @@ struct kvm_clock_data { */ #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) +/* KVM_SET_MEMORY_ALIAS is obsolete: */ #define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) #define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2d96555cd4ed..240e460777bc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -286,8 +286,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, int user_alloc); void kvm_disable_largepages(void); void kvm_arch_flush_shadow(struct kvm *kvm); -gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn); -gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn); struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); @@ -564,10 +562,6 @@ static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_se } #endif -#ifndef KVM_ARCH_HAS_UNALIAS_INSTANTIATION -#define unalias_gfn_instantiation unalias_gfn -#endif - #ifdef CONFIG_HAVE_KVM_IRQCHIP #define KVM_MAX_IRQ_ROUTES 1024 -- cgit v1.2.3 From a8eeb04a44dd6dc4c8158953d9bae48849c9a188 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 10 May 2010 12:34:53 +0300 Subject: KVM: Add mini-API for vcpu->requests Makes it a little more readable and hackable. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 240e460777bc..c8a9d628898e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -624,5 +624,20 @@ static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, #endif +static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +{ + set_bit(req, &vcpu->requests); +} + +static inline bool kvm_make_check_request(int req, struct kvm_vcpu *vcpu) +{ + return test_and_set_bit(req, &vcpu->requests); +} + +static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) +{ + return test_and_clear_bit(req, &vcpu->requests); +} + #endif -- cgit v1.2.3 From 0719837c0832a7b305e42327caa7d330462360ea Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 10 May 2010 13:08:26 +0300 Subject: KVM: Reduce atomic operations on vcpu->requests Usually the vcpu->requests bitmap is sparse, so a test_and_clear_bit() for each request generates a large number of unneeded atomics if a bit is set. Replace with a separate test/clear sequence. This is safe since there is no clear_bit() outside the vcpu thread. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c8a9d628898e..e820eb579108 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -636,7 +636,12 @@ static inline bool kvm_make_check_request(int req, struct kvm_vcpu *vcpu) static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) { - return test_and_clear_bit(req, &vcpu->requests); + if (test_bit(req, &vcpu->requests)) { + clear_bit(req, &vcpu->requests); + return true; + } else { + return false; + } } #endif -- cgit v1.2.3 From e36d96f7cfaa71870c407131eb4fbd38ea285c01 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 21 Jun 2010 10:56:36 +0300 Subject: KVM: Keep slot ID in memory slot structure May be used for distinguishing between internal and user slots, or for sorting slots in size order. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e820eb579108..e796326f3646 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -124,6 +124,7 @@ struct kvm_memory_slot { } *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned long userspace_addr; int user_alloc; + int id; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) -- cgit v1.2.3 From 5689cc53fa9d09b5bf41b1b1a7c90bd6c112ab40 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 1 Jul 2010 16:00:12 +0200 Subject: KVM: Use u64 for frame data types For 32bit machines where the physical address width is larger than the virtual address width the frame number types in KVM may overflow. Fix this by changing them to u64. [sfr: fix build on 32-bit ppc] Signed-off-by: Joerg Roedel Signed-off-by: Stephen Rothwell Signed-off-by: Marcelo Tosatti --- include/linux/kvm_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index fb46efbeabec..7ac0d4eee430 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -32,11 +32,11 @@ typedef unsigned long gva_t; typedef u64 gpa_t; -typedef unsigned long gfn_t; +typedef u64 gfn_t; typedef unsigned long hva_t; typedef u64 hpa_t; -typedef unsigned long hfn_t; +typedef u64 hfn_t; typedef hfn_t pfn_t; -- cgit v1.2.3 From edba23e51578f7cb6781461568489fc1825db4ac Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 7 Jul 2010 20:16:45 +0300 Subject: KVM: Return EFAULT from kvm ioctl when guest accesses bad area Currently if guest access address that belongs to memory slot but is not backed up by page or page is read only KVM treats it like MMIO access. Remove that capability. It was never part of the interface and should not be relied upon. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e796326f3646..8055067b6bec 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -269,6 +269,7 @@ extern pfn_t bad_pfn; int is_error_page(struct page *page); int is_error_pfn(pfn_t pfn); int is_hwpoison_pfn(pfn_t pfn); +int is_fault_pfn(pfn_t pfn); int kvm_is_error_hva(unsigned long addr); int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, -- cgit v1.2.3 From 4a994358b919c3b14de61be5e30d9edc9089ba3f Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 11 Jul 2010 15:32:23 +0300 Subject: KVM: Convert mask notifiers to use irqchip/pin instead of gsi Devices register mask notifier using gsi, but irqchip knows about irqchip/pin, so conversion from irqchip/pin to gsi should be done before looking for mask notifier to call. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8055067b6bec..c13cc48697aa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -447,7 +447,8 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); -void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask); +void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, + bool mask); #ifdef __KVM_HAVE_IOAPIC void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, -- cgit v1.2.3