From c10207fe86b1761c3ad135eb922fdb41bbde3025 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 19 Feb 2010 11:00:45 +0100 Subject: KVM: PPC: Add capability for paired singles We need to tell userspace that we can emulate paired single instructions. So let's add a capability export. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 60df9c84ecae..360f85e8c435 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -501,6 +501,7 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV_VAPIC 45 #define KVM_CAP_HYPERV_SPIN 46 #define KVM_CAP_PCI_SEGMENT 47 +#define KVM_CAP_PPC_PAIRED_SINGLES 48 #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING -- cgit From 48005f64d0ea965d454e38b5181af4aba9bdef5b Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 19 Feb 2010 19:38:07 +0100 Subject: KVM: x86: Save&restore interrupt shadow mask The interrupt shadow created by STI or MOV-SS-like operations is part of the VCPU state and must be preserved across migration. Transfer it in the spare padding field of kvm_vcpu_events.interrupt. As a side effect we now have to make vmx_set_interrupt_shadow robust against both shadow types being set. Give MOV SS a higher priority and skip STI in that case to avoid that VMX throws a fault on next entry. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 360f85e8c435..48516a2a0b84 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -502,6 +502,7 @@ struct kvm_ioeventfd { #define KVM_CAP_HYPERV_SPIN 46 #define KVM_CAP_PCI_SEGMENT 47 #define KVM_CAP_PPC_PAIRED_SINGLES 48 +#define KVM_CAP_INTR_SHADOW 49 #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING -- cgit From a1efbe77c1fd7c34a97a76a61520bf23fb3663f6 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 15 Feb 2010 10:45:43 +0100 Subject: KVM: x86: Add support for saving&restoring debug registers So far user space was not able to save and restore debug registers for migration or after reset. Plug this hole. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 48516a2a0b84..ce2876717a8b 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -503,6 +503,9 @@ struct kvm_ioeventfd { #define KVM_CAP_PCI_SEGMENT 47 #define KVM_CAP_PPC_PAIRED_SINGLES 48 #define KVM_CAP_INTR_SHADOW 49 +#ifdef __KVM_HAVE_DEBUGREGS +#define KVM_CAP_DEBUGREGS 50 +#endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #ifdef KVM_CAP_IRQ_ROUTING @@ -690,6 +693,9 @@ struct kvm_clock_data { /* Available with KVM_CAP_VCPU_EVENTS */ #define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events) #define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events) +/* Available with KVM_CAP_DEBUGREGS */ +#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) +#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit From 2ed152afc7ed61830b848b32936e1541a1a57799 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Wed, 10 Mar 2010 19:00:43 +0800 Subject: KVM: cleanup kvm trace This patch does: - no need call tracepoint_synchronize_unregister() when kvm module is unloaded since ftrace can handle it - cleanup ftrace's macro Signed-off-by: Xiao Guangrong Signed-off-by: Avi Kivity --- include/trace/events/kvm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index b17d49dfc3ef..6dd3a51ab1cb 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -5,7 +5,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm -#define TRACE_INCLUDE_FILE kvm #if defined(__KVM_HAVE_IOAPIC) TRACE_EVENT(kvm_set_irq, -- cgit From 18978768d89f638165646718c50ced19f2a10164 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 24 Mar 2010 21:48:18 +0100 Subject: KVM: PPC: Allow userspace to unset the IRQ line Userspace can tell us that it wants to trigger an interrupt. But so far it can't tell us that it wants to stop triggering one. So let's interpret the parameter to the ioctl that we have anyways to tell us if we want to raise or lower the interrupt line. Signed-off-by: Alexander Graf v2 -> v3: - Add CAP for unset irq Signed-off-by: Avi Kivity --- include/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ce2876717a8b..c36d093e9806 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -507,6 +507,7 @@ struct kvm_ioeventfd { #define KVM_CAP_DEBUGREGS 50 #endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_UNSET_IRQ 53 #ifdef KVM_CAP_IRQ_ROUTING -- cgit From 71fbfd5f38f73515f1516a68fbe04dba198b70f0 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 24 Mar 2010 21:48:29 +0100 Subject: KVM: Add support for enabling capabilities per-vcpu Some times we don't want all capabilities to be available to all our vcpus. One example for that is the OSI interface, implemented in the next patch. In order to have a generic mechanism in how to enable capabilities individually, this patch introduces a new ioctl that can be used for this purpose. That way features we don't want in all guests or userspace configurations can just not be enabled and we're good. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index c36d093e9806..ecb68e433558 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -400,6 +400,15 @@ struct kvm_ioeventfd { __u8 pad[36]; }; +/* for KVM_ENABLE_CAP */ +struct kvm_enable_cap { + /* in */ + __u32 cap; + __u32 flags; + __u64 args[4]; + __u8 pad[64]; +}; + #define KVMIO 0xAE /* @@ -508,6 +517,7 @@ struct kvm_ioeventfd { #endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 #define KVM_CAP_PPC_UNSET_IRQ 53 +#define KVM_CAP_ENABLE_CAP 54 #ifdef KVM_CAP_IRQ_ROUTING @@ -697,6 +707,7 @@ struct kvm_clock_data { /* Available with KVM_CAP_DEBUGREGS */ #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) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -- cgit From ad0a048b096ac819f28667602285453468a8d8f9 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Wed, 24 Mar 2010 21:48:30 +0100 Subject: KVM: PPC: Add OSI hypercall interface MOL uses its own hypercall interface to call back into userspace when the guest wants to do something. So let's implement that as an exit reason, specify it with a CAP and only really use it when userspace wants us to. The only user of it so far is MOL. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ecb68e433558..23ea02253900 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -160,6 +160,7 @@ struct kvm_pit_config { #define KVM_EXIT_DCR 15 #define KVM_EXIT_NMI 16 #define KVM_EXIT_INTERNAL_ERROR 17 +#define KVM_EXIT_OSI 18 /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 @@ -259,6 +260,10 @@ struct kvm_run { __u32 ndata; __u64 data[16]; } internal; + /* KVM_EXIT_OSI */ + struct { + __u64 gprs[32]; + } osi; /* Fix the size of the union. */ char padding[256]; }; @@ -516,6 +521,7 @@ struct kvm_enable_cap { #define KVM_CAP_DEBUGREGS 50 #endif #define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_OSI 52 #define KVM_CAP_PPC_UNSET_IRQ 53 #define KVM_CAP_ENABLE_CAP 54 -- cgit From 660c22c425cbe14badfb3b0a0206862577701ab7 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 13 Apr 2010 22:47:24 +0900 Subject: KVM: limit the number of pages per memory slot This patch limits the number of pages per memory slot to make us free from extra care about type issues. Signed-off-by: Takuya Yoshikawa Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 169d07758ee5..55830638aeb1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -105,6 +105,12 @@ struct kvm_vcpu { struct kvm_vcpu_arch arch; }; +/* + * Some of the bitops functions do not support too long bitmaps. + * This number must be determined not to exceed such limits. + */ +#define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) + struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; -- cgit From 90d83dc3d49f5101addae962ccc1b4aff66b68d8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Mon, 19 Apr 2010 17:41:23 +0800 Subject: KVM: use the correct RCU API for PROVE_RCU=y The RCU/SRCU API have already changed for proving RCU usage. I got the following dmesg when PROVE_RCU=y because we used incorrect API. This patch coverts rcu_deference() to srcu_dereference() or family API. =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- arch/x86/kvm/mmu.c:3020 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 0 2 locks held by qemu-system-x86/8550: #0: (&kvm->slots_lock){+.+.+.}, at: [] kvm_set_memory_region+0x29/0x50 [kvm] #1: (&(&kvm->mmu_lock)->rlock){+.+...}, at: [] kvm_arch_commit_memory_region+0xa6/0xe2 [kvm] stack backtrace: Pid: 8550, comm: qemu-system-x86 Not tainted 2.6.34-rc4-tip-01028-g939eab1 #27 Call Trace: [] lockdep_rcu_dereference+0xaa/0xb3 [] kvm_mmu_calculate_mmu_pages+0x44/0x7d [kvm] [] kvm_arch_commit_memory_region+0xb7/0xe2 [kvm] [] __kvm_set_memory_region+0x636/0x6e2 [kvm] [] kvm_set_memory_region+0x37/0x50 [kvm] [] vmx_set_tss_addr+0x46/0x5a [kvm_intel] [] kvm_arch_vm_ioctl+0x17a/0xcf8 [kvm] [] ? unlock_page+0x27/0x2c [] ? __do_fault+0x3a9/0x3e1 [] kvm_vm_ioctl+0x364/0x38d [kvm] [] ? up_read+0x23/0x3d [] vfs_ioctl+0x32/0xa6 [] do_vfs_ioctl+0x495/0x4db [] ? fget_light+0xc2/0x241 [] ? do_sys_open+0x104/0x116 [] ? retint_swapgs+0xe/0x13 [] sys_ioctl+0x47/0x6a [] system_call_fastpath+0x16/0x1b Signed-off-by: Lai Jiangshan Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 55830638aeb1..1ed030bad59e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -250,6 +250,13 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) +{ + return rcu_dereference_check(kvm->memslots, + srcu_read_lock_held(&kvm->srcu) + || lockdep_is_held(&kvm->slots_lock)); +} + #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } -- cgit From 2a059bf444dd7758ccf48f217cd981570132be85 Mon Sep 17 00:00:00 2001 From: Gui Jianfeng Date: Fri, 16 Apr 2010 17:19:48 +0800 Subject: KVM: Get rid of dead function gva_to_page() Nobody use gva_to_page() anymore, get rid of it. Signed-off-by: Gui Jianfeng Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1ed030bad59e..ce027d518096 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -260,7 +260,6 @@ static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm) #define HPA_MSB ((sizeof(hpa_t) * 8) - 1) #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva); extern struct page *bad_page; extern pfn_t bad_pfn; -- cgit From 0ee75bead83da4791e5cbf659806c54d8ee40f12 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 28 Apr 2010 15:39:01 +0300 Subject: KVM: Let vcpu structure alignment be determined at runtime vmx and svm vcpus have different contents and therefore may have different alignmment requirements. Let each specify its required alignment. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ce027d518096..7cb116afa1cd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -243,7 +243,7 @@ void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); -int kvm_init(void *opaque, unsigned int vcpu_size, +int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); -- cgit From cafd66595d92591e4bd25c3904e004fc6f897e2d Mon Sep 17 00:00:00 2001 From: Shane Wang Date: Thu, 29 Apr 2010 12:09:01 -0400 Subject: KVM: VMX: enable VMXON check with SMX enabled (Intel TXT) Per document, for feature control MSR: Bit 1 enables VMXON in SMX operation. If the bit is clear, execution of VMXON in SMX operation causes a general-protection exception. Bit 2 enables VMXON outside SMX operation. If the bit is clear, execution of VMXON outside SMX operation causes a general-protection exception. This patch is to enable this kind of check with SMX for VMXON in KVM. Signed-off-by: Shane Wang Signed-off-by: Avi Kivity --- include/linux/tboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/tboot.h b/include/linux/tboot.h index bf2a0c748878..1dba6ee55203 100644 --- a/include/linux/tboot.h +++ b/include/linux/tboot.h @@ -150,6 +150,7 @@ extern int tboot_force_iommu(void); #else +#define tboot_enabled() 0 #define tboot_probe() do { } while (0) #define tboot_shutdown(shutdown_type) do { } while (0) #define tboot_sleep(sleep_state, pm1a_control, pm1b_control) \ -- cgit