From af585b921e5d1e919947c4b1164b59507fe7cd7b Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 14 Oct 2010 11:22:46 +0200 Subject: KVM: Halt vcpu if page it tries to access is swapped out If a guest accesses swapped out memory do not swap it in from vcpu thread context. Schedule work to do swapping and put vcpu into halted state instead. Interrupts will still be delivered to the guest and if interrupt will cause reschedule guest will continue to run another task. [avi: remove call to get_user_pages_noio(), nacked by Linus; this makes everything synchrnous again] Acked-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 31 ++++++++++++++++ include/trace/events/kvm.h | 90 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 121 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a0557422715e..e56acc7857e2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -40,6 +40,7 @@ #define KVM_REQ_KICK 9 #define KVM_REQ_DEACTIVATE_FPU 10 #define KVM_REQ_EVENT 11 +#define KVM_REQ_APF_HALT 12 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 @@ -74,6 +75,26 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); +#ifdef CONFIG_KVM_ASYNC_PF +struct kvm_async_pf { + struct work_struct work; + struct list_head link; + struct list_head queue; + struct kvm_vcpu *vcpu; + struct mm_struct *mm; + gva_t gva; + unsigned long addr; + struct kvm_arch_async_pf arch; + struct page *page; + bool done; +}; + +void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); +void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, + struct kvm_arch_async_pf *arch); +#endif + struct kvm_vcpu { struct kvm *kvm; #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -104,6 +125,15 @@ struct kvm_vcpu { gpa_t mmio_phys_addr; #endif +#ifdef CONFIG_KVM_ASYNC_PF + struct { + u32 queued; + struct list_head queue; + struct list_head done; + spinlock_t lock; + } async_pf; +#endif + struct kvm_vcpu_arch arch; }; @@ -302,6 +332,7 @@ void kvm_set_page_accessed(struct page *page); pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); +pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 6dd3a51ab1cb..a78a5e574632 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -185,6 +185,96 @@ TRACE_EVENT(kvm_age_page, __entry->referenced ? "YOUNG" : "OLD") ); +#ifdef CONFIG_KVM_ASYNC_PF +TRACE_EVENT( + kvm_try_async_get_page, + TP_PROTO(bool async, u64 pfn), + TP_ARGS(async, pfn), + + TP_STRUCT__entry( + __field(__u64, pfn) + ), + + TP_fast_assign( + __entry->pfn = (!async) ? pfn : (u64)-1; + ), + + TP_printk("pfn %#llx", __entry->pfn) +); + +TRACE_EVENT( + kvm_async_pf_not_present, + TP_PROTO(u64 gva), + TP_ARGS(gva), + + TP_STRUCT__entry( + __field(__u64, gva) + ), + + TP_fast_assign( + __entry->gva = gva; + ), + + TP_printk("gva %#llx not present", __entry->gva) +); + +TRACE_EVENT( + kvm_async_pf_ready, + TP_PROTO(u64 gva), + TP_ARGS(gva), + + TP_STRUCT__entry( + __field(__u64, gva) + ), + + TP_fast_assign( + __entry->gva = gva; + ), + + TP_printk("gva %#llx ready", __entry->gva) +); + +TRACE_EVENT( + kvm_async_pf_completed, + TP_PROTO(unsigned long address, struct page *page, u64 gva), + TP_ARGS(address, page, gva), + + TP_STRUCT__entry( + __field(unsigned long, address) + __field(pfn_t, pfn) + __field(u64, gva) + ), + + TP_fast_assign( + __entry->address = address; + __entry->pfn = page ? page_to_pfn(page) : 0; + __entry->gva = gva; + ), + + TP_printk("gva %#llx address %#lx pfn %#llx", __entry->gva, + __entry->address, __entry->pfn) +); + +TRACE_EVENT( + kvm_async_pf_doublefault, + TP_PROTO(u64 gva, u64 gfn), + TP_ARGS(gva, gfn), + + TP_STRUCT__entry( + __field(u64, gva) + __field(u64, gfn) + ), + + TP_fast_assign( + __entry->gva = gva; + __entry->gfn = gfn; + ), + + TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) +); + +#endif + #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 49c7754ce57063b819b01eb8a4290841ad0886c4 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 18 Oct 2010 15:22:23 +0200 Subject: KVM: Add memory slot versioning and use it to provide fast guest write interface Keep track of memslots changes by keeping generation number in memslots structure. Provide kvm_write_guest_cached() function that skips gfn_to_hva() translation if memslots was not changed since previous invocation. Acked-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 7 +++++++ include/linux/kvm_types.h | 7 +++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e56acc7857e2..e6748204cd56 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -199,6 +199,7 @@ struct kvm_irq_routing_table {}; struct kvm_memslots { int nmemslots; + u64 generation; struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS]; }; @@ -352,12 +353,18 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); +int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len); +int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + gpa_t gpa); int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, + gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 7ac0d4eee430..fa7cc7244cbd 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -67,4 +67,11 @@ struct kvm_lapic_irq { u32 dest_id; }; +struct gfn_to_hva_cache { + u64 generation; + gpa_t gpa; + unsigned long hva; + struct kvm_memory_slot *memslot; +}; + #endif /* __KVM_TYPES_H__ */ -- cgit v1.2.3 From 344d9588a9df06182684168be4f1408b55c7da3e Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 14 Oct 2010 11:22:50 +0200 Subject: KVM: Add PV MSR to enable asynchronous page faults delivery. Guest enables async PF vcpu functionality using this MSR. Reviewed-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm.h | 1 + include/linux/kvm_host.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 919ae53adc5c..ea2dc1a2e13d 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -540,6 +540,7 @@ struct kvm_ppc_pvinfo { #endif #define KVM_CAP_PPC_GET_PVINFO 57 #define KVM_CAP_PPC_IRQ_LEVEL 58 +#define KVM_CAP_ASYNC_PF 59 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e6748204cd56..ee4314e15ead 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -93,6 +93,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, struct kvm_arch_async_pf *arch); +int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif struct kvm_vcpu { -- cgit v1.2.3 From 7c90705bf2a373aa238661bdb6446f27299ef489 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 14 Oct 2010 11:22:53 +0200 Subject: KVM: Inject asynchronous page fault into a PV guest if page is swapped out. Send async page fault to a PV guest if it accesses swapped out memory. Guest will choose another task to run upon receiving the fault. Allow async page fault injection only when guest is in user mode since otherwise guest may be in non-sleepable context and will not be able to reschedule. Vcpu will be halted if guest will fault on the same page again or if vcpu executes kernel code. Acked-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index a78a5e574632..9c2cc6a96e82 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -204,34 +204,39 @@ TRACE_EVENT( TRACE_EVENT( kvm_async_pf_not_present, - TP_PROTO(u64 gva), - TP_ARGS(gva), + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( + __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( + __entry->token = token; __entry->gva = gva; ), - TP_printk("gva %#llx not present", __entry->gva) + TP_printk("token %#llx gva %#llx not present", __entry->token, + __entry->gva) ); TRACE_EVENT( kvm_async_pf_ready, - TP_PROTO(u64 gva), - TP_ARGS(gva), + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( + __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( + __entry->token = token; __entry->gva = gva; ), - TP_printk("gva %#llx ready", __entry->gva) + TP_printk("token %#llx gva %#llx ready", __entry->token, __entry->gva) ); TRACE_EVENT( -- cgit v1.2.3 From 612819c3c6e67bac8fceaa7cc402f13b1b63f7e4 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Fri, 22 Oct 2010 14:18:18 -0200 Subject: KVM: propagate fault r/w information to gup(), allow read-only memory As suggested by Andrea, pass r/w error code to gup(), upgrading read fault to writable if host pte allows it. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ee4314e15ead..462b982fedfb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -334,8 +334,11 @@ void kvm_set_page_accessed(struct page *page); pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async); +pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, + bool write_fault, bool *writable); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, + bool *writable); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); int memslot_id(struct kvm *kvm, gfn_t gfn); -- cgit v1.2.3 From 64be5007066173d11a4635eedd57d41a3b3a7027 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 24 Oct 2010 16:49:08 +0200 Subject: KVM: x86: trace "exit to userspace" event Add tracepoint for userspace exit. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 9c2cc6a96e82..c86f4e8e0bc9 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -6,6 +6,36 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm +#define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x } + +#define kvm_trace_exit_reason \ + ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL), \ + ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN), \ + ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \ + ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\ + ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI) + +TRACE_EVENT(kvm_userspace_exit, + TP_PROTO(__u32 reason, int errno), + TP_ARGS(reason, errno), + + TP_STRUCT__entry( + __field( __u32, reason ) + __field( int, errno ) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->errno = errno; + ), + + TP_printk("reason %s (%d)", + __entry->errno < 0 ? + (__entry->errno == -EINTR ? "restart" : "error") : + __print_symbolic(__entry->reason, kvm_trace_exit_reason), + __entry->errno < 0 ? -__entry->errno : __entry->reason) +); + #if defined(__KVM_HAVE_IOAPIC) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), -- cgit v1.2.3 From 515a01279a187415322a80736800a7d6325876ab Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Oct 2010 18:23:54 +0900 Subject: KVM: pre-allocate one more dirty bitmap to avoid vmalloc() Currently x86's kvm_vm_ioctl_get_dirty_log() needs to allocate a bitmap by vmalloc() which will be used in the next logging and this has been causing bad effect to VGA and live-migration: vmalloc() consumes extra systime, triggers tlb flush, etc. This patch resolves this issue by pre-allocating one more bitmap and switching between two bitmaps during dirty logging. Performance improvement: I measured performance for the case of VGA update by trace-cmd. The result was 1.5 times faster than the original one. In the case of live migration, the improvement ratio depends on the workload and the guest memory size. In general, the larger the memory size is the more benefits we get. Note: This does not change other architectures's logic but the allocation size becomes twice. This will increase the actual memory consumption only when the new size changes the number of pages allocated by vmalloc(). Signed-off-by: Takuya Yoshikawa Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 462b982fedfb..bcf71c7730f0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,6 +150,7 @@ struct kvm_memory_slot { unsigned long flags; unsigned long *rmap; unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_head; struct { unsigned long rmap_pde; int write_count; -- cgit v1.2.3 From c9b263d2be9c535b410f6617710534f798bf0ff0 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 1 Nov 2010 16:58:43 +0800 Subject: KVM: fix tracing kvm_try_async_get_page Tracing 'async' and *pfn is useless, since 'async' is always true, and '*pfn' is always "fault_pfn' We can trace 'gva' and 'gfn' instead, it can help us to see the life-cycle of an async_pf Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index c86f4e8e0bc9..d94d6c312ca1 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -218,18 +218,20 @@ TRACE_EVENT(kvm_age_page, #ifdef CONFIG_KVM_ASYNC_PF TRACE_EVENT( kvm_try_async_get_page, - TP_PROTO(bool async, u64 pfn), - TP_ARGS(async, pfn), + TP_PROTO(u64 gva, u64 gfn), + TP_ARGS(gva, gfn), TP_STRUCT__entry( - __field(__u64, pfn) + __field(u64, gva) + __field(u64, gfn) ), TP_fast_assign( - __entry->pfn = (!async) ? pfn : (u64)-1; + __entry->gva = gva; + __entry->gfn = gfn; ), - TP_printk("pfn %#llx", __entry->pfn) + TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) ); TRACE_EVENT( -- cgit v1.2.3 From 0730388b97d20cc568c25b42b9a23b28959b481f Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 1 Nov 2010 16:59:39 +0800 Subject: KVM: cleanup async_pf tracepoints Use 'DECLARE_EVENT_CLASS' to cleanup async_pf tracepoints Acked-by: Gleb Natapov Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 76 +++++++++++++++++++++------------------------- 1 file changed, 35 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index d94d6c312ca1..46e3cd8e197a 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -216,59 +216,71 @@ TRACE_EVENT(kvm_age_page, ); #ifdef CONFIG_KVM_ASYNC_PF -TRACE_EVENT( - kvm_try_async_get_page, +DECLARE_EVENT_CLASS(kvm_async_get_page_class, + TP_PROTO(u64 gva, u64 gfn), + TP_ARGS(gva, gfn), TP_STRUCT__entry( - __field(u64, gva) + __field(__u64, gva) __field(u64, gfn) - ), + ), TP_fast_assign( __entry->gva = gva; __entry->gfn = gfn; - ), + ), TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) ); -TRACE_EVENT( - kvm_async_pf_not_present, +DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page, + + TP_PROTO(u64 gva, u64 gfn), + + TP_ARGS(gva, gfn) +); + +DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_doublefault, + + TP_PROTO(u64 gva, u64 gfn), + + TP_ARGS(gva, gfn) +); + +DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready, + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( __field(__u64, token) __field(__u64, gva) - ), + ), TP_fast_assign( __entry->token = token; __entry->gva = gva; - ), + ), + + TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva) - TP_printk("token %#llx gva %#llx not present", __entry->token, - __entry->gva) ); -TRACE_EVENT( - kvm_async_pf_ready, +DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present, + TP_PROTO(u64 token, u64 gva), - TP_ARGS(token, gva), - TP_STRUCT__entry( - __field(__u64, token) - __field(__u64, gva) - ), + TP_ARGS(token, gva) +); - TP_fast_assign( - __entry->token = token; - __entry->gva = gva; - ), +DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready, + + TP_PROTO(u64 token, u64 gva), - TP_printk("token %#llx gva %#llx ready", __entry->token, __entry->gva) + TP_ARGS(token, gva) ); TRACE_EVENT( @@ -292,24 +304,6 @@ TRACE_EVENT( __entry->address, __entry->pfn) ); -TRACE_EVENT( - kvm_async_pf_doublefault, - TP_PROTO(u64 gva, u64 gfn), - TP_ARGS(gva, gfn), - - TP_STRUCT__entry( - __field(u64, gva) - __field(u64, gfn) - ), - - TP_fast_assign( - __entry->gva = gva; - __entry->gfn = gfn; - ), - - TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) -); - #endif #endif /* _TRACE_KVM_MAIN_H */ -- cgit v1.2.3 From d89f5eff70a31237ffa1e21c51d23ca532110aea Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 9 Nov 2010 17:02:49 +0100 Subject: KVM: Clean up vm creation and release IA64 support forces us to abstract the allocation of the kvm structure. But instead of mixing this up with arch-specific initialization and doing the same on destruction, split both steps. This allows to move generic destruction calls into generic code. It also fixes error clean-up on failures of kvm_create_vm for IA64. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bcf71c7730f0..2d63f2c0137c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -441,7 +442,19 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); void kvm_free_physmem(struct kvm *kvm); -struct kvm *kvm_arch_create_vm(void); +#ifndef __KVM_HAVE_ARCH_VM_ALLOC +static inline struct kvm *kvm_arch_alloc_vm(void) +{ + return kzalloc(sizeof(struct kvm), GFP_KERNEL); +} + +static inline void kvm_arch_free_vm(struct kvm *kvm) +{ + kfree(kvm); +} +#endif + +int kvm_arch_init_vm(struct kvm *kvm); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_free_all_assigned_devices(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); -- cgit v1.2.3 From 0645211c43df0b96c51e12980066b3227e10b164 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 16 Nov 2010 22:30:03 +0100 Subject: KVM: Switch assigned device IRQ forwarding to threaded handler This improves the IRQ forwarding for assigned devices: By using the kernel's threaded IRQ scheme, we can get rid of the latency-prone work queue and simplify the code in the same run. Moreover, we no longer have to hold assigned_dev_lock while raising the guest IRQ, which can be a lenghty operation as we may have to iterate over all VCPUs. The lock is now only used for synchronizing masking vs. unmasking of INTx-type IRQs, thus is renames to intx_lock. Acked-by: Alex Williamson Acked-by: Michael S. Tsirkin Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2d63f2c0137c..9fe7fefe76b1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -470,16 +470,8 @@ struct kvm_irq_ack_notifier { void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; -#define KVM_ASSIGNED_MSIX_PENDING 0x1 -struct kvm_guest_msix_entry { - u32 vector; - u16 entry; - u16 flags; -}; - struct kvm_assigned_dev_kernel { struct kvm_irq_ack_notifier ack_notifier; - struct work_struct interrupt_work; struct list_head list; int assigned_dev_id; int host_segnr; @@ -490,13 +482,13 @@ struct kvm_assigned_dev_kernel { bool host_irq_disabled; struct msix_entry *host_msix_entries; int guest_irq; - struct kvm_guest_msix_entry *guest_msix_entries; + struct msix_entry *guest_msix_entries; unsigned long irq_requested_type; int irq_source_id; int flags; struct pci_dev *dev; struct kvm *kvm; - spinlock_t assigned_dev_lock; + spinlock_t intx_lock; }; struct kvm_irq_mask_notifier { -- cgit v1.2.3 From 1e001d49f9f9a0e3eb72939ad49d9a2c7754e9c1 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 16 Nov 2010 22:30:04 +0100 Subject: KVM: Refactor IRQ names of assigned devices Cosmetic change, but it helps to correlate IRQs with PCI devices. Acked-by: Alex Williamson Acked-by: Michael S. Tsirkin Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9fe7fefe76b1..4bd663d6443d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -489,6 +489,7 @@ struct kvm_assigned_dev_kernel { struct pci_dev *dev; struct kvm *kvm; spinlock_t intx_lock; + char irq_name[32]; }; struct kvm_irq_mask_notifier { -- cgit v1.2.3 From bd2b53b20fcd0d6c4c815b54e6d464e34429d3a4 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 18 Nov 2010 19:09:08 +0200 Subject: KVM: fast-path msi injection with irqfd Store irq routing table pointer in the irqfd object, and use that to inject MSI directly without bouncing out to a kernel thread. While we touch this structure, rearrange irqfd fields to make fastpath better packed for better cache utilization. This also adds some comments about locking rules and rcu usage in code. Some notes on the design: - Use pointer into the rt instead of copying an entry, to make it possible to use rcu, thus side-stepping locking complexities. We also save some memory this way. - Old workqueue code is still used for level irqs. I don't think we DTRT with level anyway, however, it seems easier to keep the code around as it has been thought through and debugged, and fix level later than rip out and re-instate it later. Signed-off-by: Michael S. Tsirkin Acked-by: Marcelo Tosatti Acked-by: Gregory Haskins Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4bd663d6443d..f17beae3cca0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -240,6 +241,10 @@ struct kvm { struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP + /* + * Update side is protected by irq_lock and, + * if configured, irqfds.lock. + */ struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head mask_notifier_list; struct hlist_head irq_ack_notifier_list; @@ -511,6 +516,8 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, unsigned long *deliver_bitmask); #endif int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, + int irq_source_id, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); @@ -652,17 +659,26 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {} void kvm_eventfd_init(struct kvm *kvm); int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags); void kvm_irqfd_release(struct kvm *kvm); +void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #else static inline void kvm_eventfd_init(struct kvm *kvm) {} + static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags) { return -EINVAL; } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline void kvm_irq_routing_update(struct kvm *kvm, + struct kvm_irq_routing_table *irq_rt) +{ + rcu_assign_pointer(kvm->irq_routing, irq_rt); +} + static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { return -ENOSYS; -- cgit v1.2.3 From 27923eb19c5d1197bd9d1472abdc2e749f21387a Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Thu, 25 Nov 2010 10:25:44 +0100 Subject: KVM: PPC: Fix compile warning KVM compilation fails with the following warning: include/linux/kvm_host.h: In function 'kvm_irq_routing_update': include/linux/kvm_host.h:679:2: error: 'struct kvm' has no member named 'irq_routing' That function is only used and reasonable to have on systems that implement an in-kernel interrupt chip. PPC doesn't. Fix by #ifdef'ing it out when no irqchip is available. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f17beae3cca0..da0794f707f6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -673,11 +673,13 @@ static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags) static inline void kvm_irqfd_release(struct kvm *kvm) {} +#ifdef CONFIG_HAVE_KVM_IRQCHIP static inline void kvm_irq_routing_update(struct kvm *kvm, struct kvm_irq_routing_table *irq_rt) { rcu_assign_pointer(kvm->irq_routing, irq_rt); } +#endif static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { -- cgit v1.2.3 From a4ee1ca4a36e7857d90ae8c2b85f1bde9a042c10 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Tue, 23 Nov 2010 11:13:00 +0800 Subject: KVM: MMU: delay flush all tlbs on sync_page path Quote from Avi: | I don't think we need to flush immediately; set a "tlb dirty" bit somewhere | that is cleareded when we flush the tlb. kvm_mmu_notifier_invalidate_page() | can consult the bit and force a flush if set. Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index da0794f707f6..ac4e83a1a10d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -254,6 +254,7 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; + long tlbs_dirty; #endif }; @@ -382,6 +383,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); + void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); -- cgit v1.2.3 From d4dbf470096c51cb4785167ea59fdbdea87ccbe4 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 7 Dec 2010 12:59:07 +0900 Subject: KVM: MMU: Make the way of accessing lpage_info more generic Large page information has two elements but one of them, write_count, alone is accessed by a helper function. This patch replaces this helper function with more generic one which returns newly named kvm_lpage_info structure and use it to access the other element rmap_pde. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ac4e83a1a10d..bd0da8f12500 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -146,6 +146,11 @@ struct kvm_vcpu { */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +struct kvm_lpage_info { + unsigned long rmap_pde; + int write_count; +}; + struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; @@ -153,10 +158,7 @@ struct kvm_memory_slot { unsigned long *rmap; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_head; - struct { - unsigned long rmap_pde; - int write_count; - } *lpage_info[KVM_NR_PAGE_SIZES - 1]; + struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned long userspace_addr; int user_alloc; int id; -- cgit v1.2.3 From 5c663a1534d27d817e17eed06a83d08f497f9f4f Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 8 Dec 2010 18:04:51 +0200 Subject: KVM: Fix build error on s390 due to missing tlbs_dirty Make it available for all archs. 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 bd0da8f12500..b5021db21858 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -256,8 +256,8 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; - long tlbs_dirty; #endif + long tlbs_dirty; }; /* The guest did something we don't support. */ -- cgit v1.2.3