From 7c68af6e32c73992bad24107311f3433c89016e2 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sat, 19 Sep 2009 09:40:22 +0300 Subject: [PATCH 01/84] core, x86: Add user return notifiers Add a general per-cpu notifier that is called whenever the kernel is about to return to userspace. The notifier uses a thread_info flag and existing checks, so there is no impact on user return or context switch fast paths. This will be used initially to speed up KVM task switching by lazily updating MSRs. Signed-off-by: Avi Kivity LKML-Reference: <1253342422-13811-1-git-send-email-avi@redhat.com> Signed-off-by: H. Peter Anvin --- arch/Kconfig | 10 ++++++ arch/x86/Kconfig | 1 + arch/x86/include/asm/thread_info.h | 7 +++-- arch/x86/kernel/process.c | 2 ++ arch/x86/kernel/signal.c | 3 ++ include/linux/user-return-notifier.h | 42 +++++++++++++++++++++++++ kernel/user-return-notifier.c | 46 ++++++++++++++++++++++++++++ 7 files changed, 109 insertions(+), 2 deletions(-) create mode 100644 include/linux/user-return-notifier.h create mode 100644 kernel/user-return-notifier.c diff --git a/arch/Kconfig b/arch/Kconfig index 7f418bbc261..4e312fffbfd 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -83,6 +83,13 @@ config KRETPROBES def_bool y depends on KPROBES && HAVE_KRETPROBES +config USER_RETURN_NOTIFIER + bool + depends on HAVE_USER_RETURN_NOTIFIER + help + Provide a kernel-internal notification when a cpu is about to + switch to user mode. + config HAVE_IOREMAP_PROT bool @@ -126,4 +133,7 @@ config HAVE_DMA_API_DEBUG config HAVE_DEFAULT_NO_SPIN_MUTEXES bool +config HAVE_USER_RETURN_NOTIFIER + bool + source "kernel/gcov/Kconfig" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8da93745c08..1df175d15aa 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -50,6 +50,7 @@ config X86 select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA select HAVE_ARCH_KMEMCHECK + select HAVE_USER_RETURN_NOTIFIER config OUTPUT_FORMAT string diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d27d0a2fec4..375c917c37d 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ +#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ @@ -107,6 +108,7 @@ struct thread_info { #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) +#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) @@ -142,13 +144,14 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME) + (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ + _TIF_USER_RETURN_NOTIFY) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC) -#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW +#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) #define PREEMPT_ACTIVE 0x10000000 diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 5284cd2b577..e51b056fc88 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -224,6 +225,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } + propagate_user_return_notify(prev_p, next_p); } int sys_fork(struct pt_regs *regs) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 6a44a76055a..c49f90f7957 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -872,6 +873,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (current->replacement_session_keyring) key_replace_session_keyring(); } + if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); diff --git a/include/linux/user-return-notifier.h b/include/linux/user-return-notifier.h new file mode 100644 index 00000000000..b6ac056291d --- /dev/null +++ b/include/linux/user-return-notifier.h @@ -0,0 +1,42 @@ +#ifndef _LINUX_USER_RETURN_NOTIFIER_H +#define _LINUX_USER_RETURN_NOTIFIER_H + +#ifdef CONFIG_USER_RETURN_NOTIFIER + +#include +#include + +struct user_return_notifier { + void (*on_user_return)(struct user_return_notifier *urn); + struct hlist_node link; +}; + + +void user_return_notifier_register(struct user_return_notifier *urn); +void user_return_notifier_unregister(struct user_return_notifier *urn); + +static inline void propagate_user_return_notify(struct task_struct *prev, + struct task_struct *next) +{ + if (test_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY)) { + clear_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY); + set_tsk_thread_flag(next, TIF_USER_RETURN_NOTIFY); + } +} + +void fire_user_return_notifiers(void); + +#else + +struct user_return_notifier {}; + +static inline void propagate_user_return_notify(struct task_struct *prev, + struct task_struct *next) +{ +} + +static inline void fire_user_return_notifiers(void) {} + +#endif + +#endif diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c new file mode 100644 index 00000000000..530ccb81651 --- /dev/null +++ b/kernel/user-return-notifier.c @@ -0,0 +1,46 @@ + +#include +#include +#include +#include + +static DEFINE_PER_CPU(struct hlist_head, return_notifier_list); + +#define URN_LIST_HEAD per_cpu(return_notifier_list, raw_smp_processor_id()) + +/* + * Request a notification when the current cpu returns to userspace. Must be + * called in atomic context. The notifier will also be called in atomic + * context. + */ +void user_return_notifier_register(struct user_return_notifier *urn) +{ + set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); + hlist_add_head(&urn->link, &URN_LIST_HEAD); +} +EXPORT_SYMBOL_GPL(user_return_notifier_register); + +/* + * Removes a registered user return notifier. Must be called from atomic + * context, and from the same cpu registration occured in. + */ +void user_return_notifier_unregister(struct user_return_notifier *urn) +{ + hlist_del(&urn->link); + if (hlist_empty(&URN_LIST_HEAD)) + clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY); +} +EXPORT_SYMBOL_GPL(user_return_notifier_unregister); + +/* Calls registered user return notifiers */ +void fire_user_return_notifiers(void) +{ + struct user_return_notifier *urn; + struct hlist_node *tmp1, *tmp2; + struct hlist_head *head; + + head = &get_cpu_var(return_notifier_list); + hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link) + urn->on_user_return(urn); + put_cpu_var(); +} From 7a041097518a120f92af631a83db4d41e07ee51b Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 25 Oct 2009 14:24:45 +0200 Subject: [PATCH 02/84] x86: Fix user return notifier build When CONFIG_USER_RETURN_NOTIFIER is set, we need to link kernel/user-return-notifier.o. Signed-off-by: Avi Kivity LKML-Reference: <1256473485-23109-1-git-send-email-avi@redhat.com> Signed-off-by: Ingo Molnar --- kernel/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/Makefile b/kernel/Makefile index b8d4cd8ac0b..0ae57a83d48 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -95,6 +95,7 @@ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_SLOW_WORK) += slow-work.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra , the -fno-omit-frame-pointer is From 3c912b6edaac56cb451e7571c95c15cbb6bd0c81 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 2 Nov 2009 16:17:22 +1100 Subject: [PATCH 03/84] x86: Fix user return notifier put_cpu_var() invocation Today's linux-next build (x86_64 allmodconfig) failed like this: kernel/user-return-notifier.c: In function 'fire_user_return_notifiers': kernel/user-return-notifier.c:45: error: expected expression before ')' token Introduced by commit 7c68af6e32c73992bad24107311f3433c89016e2 ("core, x86: Add user return notifiers") from the tip and kvm trees but revealed by commit e0fdb0e050eae331046385643618f12452aa7e73 ("percpu: add __percpu for sparse") from the percpu tree. Before that percpu tree commit, "put_cpu_var()" would compile without error (even though it really needs a parameter). Signed-off-by: Stephen Rothwell Cc: Avi Kivity Cc: Peter Zijlstra Cc: Tejun Heo Cc: Rusty Russell Cc: Christoph Lameter LKML-Reference: <20091102161722.eea4358d.sfr@canb.auug.org.au> Signed-off-by: Ingo Molnar --- kernel/user-return-notifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/user-return-notifier.c b/kernel/user-return-notifier.c index 530ccb81651..03e2d6fd9b1 100644 --- a/kernel/user-return-notifier.c +++ b/kernel/user-return-notifier.c @@ -42,5 +42,5 @@ void fire_user_return_notifiers(void) head = &get_cpu_var(return_notifier_list); hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link) urn->on_user_return(urn); - put_cpu_var(); + put_cpu_var(return_notifier_list); } From 8e7cac79808b62f242069a6ac88d364d35621371 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 29 Nov 2009 16:34:48 +0200 Subject: [PATCH 04/84] core: Fix user return notifier on fork() fork() clones all thread_info flags, including TIF_USER_RETURN_NOTIFY; if the new task is first scheduled on a cpu which doesn't have user return notifiers set, this causes user return notifiers to trigger without any way of clearing itself. This is easy to trigger with a forky workload on the host in parallel with kvm, resulting in a cpu in an endless loop on the verge of returning to userspace. Fix by dropping the TIF_USER_RETURN_NOTIFY immediately after fork. Signed-off-by: Avi Kivity LKML-Reference: <1259505288-16559-1-git-send-email-avi@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/user-return-notifier.h | 7 +++++++ kernel/fork.c | 2 ++ 2 files changed, 9 insertions(+) diff --git a/include/linux/user-return-notifier.h b/include/linux/user-return-notifier.h index b6ac056291d..9c4a445bb43 100644 --- a/include/linux/user-return-notifier.h +++ b/include/linux/user-return-notifier.h @@ -26,6 +26,11 @@ static inline void propagate_user_return_notify(struct task_struct *prev, void fire_user_return_notifiers(void); +static inline void clear_user_return_notifier(struct task_struct *p) +{ + clear_tsk_thread_flag(p, TIF_USER_RETURN_NOTIFY); +} + #else struct user_return_notifier {}; @@ -37,6 +42,8 @@ static inline void propagate_user_return_notify(struct task_struct *prev, static inline void fire_user_return_notifiers(void) {} +static inline void clear_user_return_notifier(struct task_struct *p) {} + #endif #endif diff --git a/kernel/fork.c b/kernel/fork.c index 266c6af6ef1..1b7512d5a64 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -64,6 +64,7 @@ #include #include #include +#include #include #include @@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) goto out; setup_thread_stack(tsk, orig); + clear_user_return_notifier(tsk); stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ From 45ec431c52f89218ac01d87663e54de30458edf0 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 23 Aug 2009 17:46:21 +0300 Subject: [PATCH 05/84] KVM: Don't wrap schedule() with vcpu_put()/vcpu_load() Preemption notifiers will do that for us automatically. Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 7495ce34734..22b520b5441 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1689,9 +1689,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) if (signal_pending(current)) break; - vcpu_put(vcpu); schedule(); - vcpu_load(vcpu); } finish_wait(&vcpu->wq, &wait); From 0934ac9d135021bec7f877340a039104af233bf3 Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Sun, 23 Aug 2009 14:24:24 +0300 Subject: [PATCH 06/84] KVM: x86 emulator: Add 'push/pop sreg' instructions [avi: avoid buffer overflow] Signed-off-by: Mohammed Gamal Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 107 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 101 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1be5cd640e9..1cdfec5231d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -92,19 +92,22 @@ static u32 opcode_table[256] = { /* 0x00 - 0x07 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack, ImplicitOps | Stack, /* 0x08 - 0x0F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + 0, 0, ImplicitOps | Stack, 0, /* 0x10 - 0x17 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack, ImplicitOps | Stack, /* 0x18 - 0x1F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack, ImplicitOps | Stack, /* 0x20 - 0x27 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, @@ -244,11 +247,13 @@ static u32 twobyte_table[256] = { /* 0x90 - 0x9F */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0xA0 - 0xA7 */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, + ImplicitOps | Stack, ImplicitOps | Stack, + 0, DstMem | SrcReg | ModRM | BitOp, DstMem | SrcReg | Src2ImmByte | ModRM, DstMem | SrcReg | Src2CL | ModRM, 0, 0, /* 0xA8 - 0xAF */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, + ImplicitOps | Stack, ImplicitOps | Stack, + 0, DstMem | SrcReg | ModRM | BitOp, DstMem | SrcReg | Src2ImmByte | ModRM, DstMem | SrcReg | Src2CL | ModRM, ModRM, 0, @@ -1186,6 +1191,32 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, return rc; } +static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +{ + struct decode_cache *c = &ctxt->decode; + struct kvm_segment segment; + + kvm_x86_ops->get_segment(ctxt->vcpu, &segment, seg); + + c->src.val = segment.selector; + emulate_push(ctxt); +} + +static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, int seg) +{ + struct decode_cache *c = &ctxt->decode; + unsigned long selector; + int rc; + + rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); + if (rc != 0) + return rc; + + rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, 1, seg); + return rc; +} + static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1707,18 +1738,66 @@ special_insn: add: /* add */ emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); break; + case 0x06: /* push es */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + emulate_push_sreg(ctxt, VCPU_SREG_ES); + break; + case 0x07: /* pop es */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); + if (rc != 0) + goto done; + break; case 0x08 ... 0x0d: or: /* or */ emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); break; + case 0x0e: /* push cs */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + emulate_push_sreg(ctxt, VCPU_SREG_CS); + break; case 0x10 ... 0x15: adc: /* adc */ emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); break; + case 0x16: /* push ss */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + emulate_push_sreg(ctxt, VCPU_SREG_SS); + break; + case 0x17: /* pop ss */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); + if (rc != 0) + goto done; + break; case 0x18 ... 0x1d: sbb: /* sbb */ emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); break; + case 0x1e: /* push ds */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + emulate_push_sreg(ctxt, VCPU_SREG_DS); + break; + case 0x1f: /* pop ds */ + if (ctxt->mode == X86EMUL_MODE_PROT64) + goto cannot_emulate; + + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); + if (rc != 0) + goto done; + break; case 0x20 ... 0x25: and: /* and */ emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags); @@ -2297,6 +2376,14 @@ twobyte_insn: jmp_rel(c, c->src.val); c->dst.type = OP_NONE; break; + case 0xa0: /* push fs */ + emulate_push_sreg(ctxt, VCPU_SREG_FS); + break; + case 0xa1: /* pop fs */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS); + if (rc != 0) + goto done; + break; case 0xa3: bt: /* bt */ c->dst.type = OP_NONE; @@ -2308,6 +2395,14 @@ twobyte_insn: case 0xa5: /* shld cl, r, r/m */ emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags); break; + case 0xa8: /* push gs */ + emulate_push_sreg(ctxt, VCPU_SREG_GS); + break; + case 0xa9: /* pop gs */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS); + if (rc != 0) + goto done; + break; case 0xab: bts: /* bts */ /* only subword offset */ From d8769fedd4e8323d8afea9a1b2bdebff4f1d2d37 Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Sun, 23 Aug 2009 14:24:25 +0300 Subject: [PATCH 07/84] KVM: x86 emulator: Introduce No64 decode option Introduces a new decode option "No64", which is used for instructions that are invalid in long mode. Signed-off-by: Mohammed Gamal Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 42 ++++++++++++++---------------------------- 1 file changed, 14 insertions(+), 28 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1cdfec5231d..1f0ff4afa73 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -75,6 +75,8 @@ #define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ #define GroupDual (1<<15) /* Alternate decoding of mod == 3 */ #define GroupMask 0xff /* Group number stored in bits 0:7 */ +/* Misc flags */ +#define No64 (1<<28) /* Source 2 operand type */ #define Src2None (0<<29) #define Src2CL (1<<29) @@ -93,21 +95,21 @@ static u32 opcode_table[256] = { ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, - ImplicitOps | Stack, ImplicitOps | Stack, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x08 - 0x0F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, ImplicitOps | Stack, 0, + 0, 0, ImplicitOps | Stack | No64, 0, /* 0x10 - 0x17 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, - ImplicitOps | Stack, ImplicitOps | Stack, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x18 - 0x1F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, - ImplicitOps | Stack, ImplicitOps | Stack, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x20 - 0x27 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, @@ -161,7 +163,7 @@ static u32 opcode_table[256] = { /* 0x90 - 0x97 */ DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, /* 0x98 - 0x9F */ - 0, 0, SrcImm | Src2Imm16, 0, + 0, 0, SrcImm | Src2Imm16 | No64, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0, /* 0xA0 - 0xA7 */ ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, @@ -188,7 +190,7 @@ static u32 opcode_table[256] = { ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, /* 0xC8 - 0xCF */ 0, 0, 0, ImplicitOps | Stack, - ImplicitOps, SrcImmByte, ImplicitOps, ImplicitOps, + ImplicitOps, SrcImmByte, ImplicitOps | No64, ImplicitOps, /* 0xD0 - 0xD7 */ ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, @@ -201,7 +203,7 @@ static u32 opcode_table[256] = { ByteOp | SrcImmUByte, SrcImmUByte, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps, + SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* 0xF0 - 0xF7 */ @@ -967,6 +969,11 @@ done_prefixes: } } + if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { + kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");; + return -1; + } + if (c->d & Group) { group = c->d & GroupMask; c->modrm = insn_fetch(u8, 1, c->eip); @@ -1739,15 +1746,9 @@ special_insn: emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); break; case 0x06: /* push es */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - emulate_push_sreg(ctxt, VCPU_SREG_ES); break; case 0x07: /* pop es */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); if (rc != 0) goto done; @@ -1757,9 +1758,6 @@ special_insn: emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); break; case 0x0e: /* push cs */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - emulate_push_sreg(ctxt, VCPU_SREG_CS); break; case 0x10 ... 0x15: @@ -1767,15 +1765,9 @@ special_insn: emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); break; case 0x16: /* push ss */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - emulate_push_sreg(ctxt, VCPU_SREG_SS); break; case 0x17: /* pop ss */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); if (rc != 0) goto done; @@ -1785,15 +1777,9 @@ special_insn: emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); break; case 0x1e: /* push ds */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - emulate_push_sreg(ctxt, VCPU_SREG_DS); break; case 0x1f: /* pop ds */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - goto cannot_emulate; - rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); if (rc != 0) goto done; From 851ba6922ac575b749f63dee0ae072808163ba6a Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 24 Aug 2009 11:10:17 +0300 Subject: [PATCH 08/84] KVM: Don't pass kvm_run arguments They're just copies of vcpu->run, which is readily accessible. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 10 +-- arch/x86/kvm/emulate.c | 6 +- arch/x86/kvm/mmu.c | 2 +- arch/x86/kvm/svm.c | 102 ++++++++++++++-------------- arch/x86/kvm/vmx.c | 113 +++++++++++++++----------------- arch/x86/kvm/x86.c | 50 +++++++------- 6 files changed, 141 insertions(+), 142 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d83892226f7..0b113f2b58c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -506,8 +506,8 @@ struct kvm_x86_ops { void (*tlb_flush)(struct kvm_vcpu *vcpu); - void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run); - int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); + void (*run)(struct kvm_vcpu *vcpu); + int (*handle_exit)(struct kvm_vcpu *vcpu); void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); @@ -568,7 +568,7 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run, +int emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, u16 error_code, int emulation_type); void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); @@ -585,9 +585,9 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); struct x86_emulate_ctxt; -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1f0ff4afa73..0644d3df621 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1826,7 +1826,7 @@ special_insn: break; case 0x6c: /* insb */ case 0x6d: /* insw/insd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + if (kvm_emulate_pio_string(ctxt->vcpu, 1, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? @@ -1842,7 +1842,7 @@ special_insn: return 0; case 0x6e: /* outsb */ case 0x6f: /* outsw/outsd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + if (kvm_emulate_pio_string(ctxt->vcpu, 0, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? @@ -2135,7 +2135,7 @@ special_insn: case 0xef: /* out (e/r)ax,dx */ port = c->regs[VCPU_REGS_RDX]; io_dir_in = 0; - do_io: if (kvm_emulate_pio(ctxt->vcpu, NULL, io_dir_in, + do_io: if (kvm_emulate_pio(ctxt->vcpu, io_dir_in, (c->d & ByteOp) ? 1 : c->op_bytes, port) != 0) { c->eip = saved_eip; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 818b92ad82c..a9024797b21 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2789,7 +2789,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) if (r) goto out; - er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0); + er = emulate_instruction(vcpu, cr2, error_code, 0); switch (er) { case EMULATE_DONE: diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c17404add91..92048a626d4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -286,7 +286,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (!svm->next_rip) { - if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) != + if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -1180,7 +1180,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, } } -static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int pf_interception(struct vcpu_svm *svm) { u64 fault_address; u32 error_code; @@ -1194,8 +1194,10 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } -static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int db_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && !svm->vcpu.arch.singlestep) { @@ -1223,25 +1225,27 @@ static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int bp_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = BP_VECTOR; return 0; } -static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int ud_interception(struct vcpu_svm *svm) { int er; - er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } -static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nm_interception(struct vcpu_svm *svm) { svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); if (!(svm->vcpu.arch.cr0 & X86_CR0_TS)) @@ -1251,7 +1255,7 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int mc_interception(struct vcpu_svm *svm) { /* * On an #MC intercept the MCE handler is not called automatically in @@ -1264,8 +1268,10 @@ static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int shutdown_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + /* * VMCB is undefined after a SHUTDOWN intercept * so reinitialize it. @@ -1277,7 +1283,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 0; } -static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int io_interception(struct vcpu_svm *svm) { u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ int size, in, string; @@ -1291,7 +1297,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) if (string) { if (emulate_instruction(&svm->vcpu, - kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } @@ -1301,33 +1307,33 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); + return kvm_emulate_pio(&svm->vcpu, in, size, port); } -static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nmi_interception(struct vcpu_svm *svm) { return 1; } -static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int intr_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.irq_exits; return 1; } -static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nop_on_interception(struct vcpu_svm *svm) { return 1; } -static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int halt_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } -static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -1837,7 +1843,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; } -static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -1857,7 +1863,7 @@ static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -1877,7 +1883,7 @@ static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmrun_interception(struct vcpu_svm *svm) { nsvm_printk("VMrun\n"); @@ -1907,7 +1913,7 @@ failed: return 1; } -static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int stgi_interception(struct vcpu_svm *svm) { if (nested_svm_check_permissions(svm)) return 1; @@ -1920,7 +1926,7 @@ static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int clgi_interception(struct vcpu_svm *svm) { if (nested_svm_check_permissions(svm)) return 1; @@ -1937,7 +1943,7 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; nsvm_printk("INVLPGA\n"); @@ -1950,15 +1956,13 @@ static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invalid_op_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int invalid_op_interception(struct vcpu_svm *svm) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } -static int task_switch_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; int reason; @@ -2008,14 +2012,14 @@ static int task_switch_interception(struct vcpu_svm *svm, return kvm_task_switch(&svm->vcpu, tss_selector, reason); } -static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int cpuid_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; kvm_emulate_cpuid(&svm->vcpu); return 1; } -static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int iret_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.nmi_window_exits; svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); @@ -2023,26 +2027,27 @@ static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int invlpg_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE) + if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } -static int emulate_on_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int emulate_on_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE) + if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } -static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int cr8_write_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ - emulate_instruction(&svm->vcpu, NULL, 0, 0, 0); + emulate_instruction(&svm->vcpu, 0, 0, 0); if (irqchip_in_kernel(svm->vcpu.kvm)) { svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; return 1; @@ -2128,7 +2133,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) return 0; } -static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int rdmsr_interception(struct vcpu_svm *svm) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data; @@ -2221,7 +2226,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) return 0; } -static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int wrmsr_interception(struct vcpu_svm *svm) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) @@ -2237,17 +2242,18 @@ static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int msr_interception(struct vcpu_svm *svm) { if (svm->vmcb->control.exit_info_1) - return wrmsr_interception(svm, kvm_run); + return wrmsr_interception(svm); else - return rdmsr_interception(svm, kvm_run); + return rdmsr_interception(svm); } -static int interrupt_window_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int interrupt_window_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; /* @@ -2265,8 +2271,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm, return 1; } -static int (*svm_exit_handlers[])(struct vcpu_svm *svm, - struct kvm_run *kvm_run) = { +static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = emulate_on_interception, [SVM_EXIT_READ_CR3] = emulate_on_interception, [SVM_EXIT_READ_CR4] = emulate_on_interception, @@ -2321,9 +2326,10 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_NPF] = pf_interception, }; -static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; trace_kvm_exit(exit_code, svm->vmcb->save.rip); @@ -2383,7 +2389,7 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) return 0; } - return svm_exit_handlers[exit_code](svm, kvm_run); + return svm_exit_handlers[exit_code](svm); } static void reload_tss(struct kvm_vcpu *vcpu) @@ -2588,7 +2594,7 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) #define R "e" #endif -static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); u16 fs_selector; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ed53b42caba..4635298d000 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2659,7 +2659,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) - if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE) + if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE) return 1; /* * Forward all other exceptions that are valid in real mode. @@ -2710,15 +2710,16 @@ static void kvm_machine_check(void) #endif } -static int handle_machine_check(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_machine_check(struct kvm_vcpu *vcpu) { /* already handled by vcpu_run */ return 1; } -static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_exception(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; unsigned long cr2, rip, dr6; u32 vect_info; @@ -2728,7 +2729,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) intr_info = vmcs_read32(VM_EXIT_INTR_INFO); if (is_machine_check(intr_info)) - return handle_machine_check(vcpu, kvm_run); + return handle_machine_check(vcpu); if ((vect_info & VECTORING_INFO_VALID_MASK) && !is_page_fault(intr_info)) @@ -2744,7 +2745,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } if (is_invalid_opcode(intr_info)) { - er = emulate_instruction(vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(vcpu, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); return 1; @@ -2803,20 +2804,19 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; } -static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_triple_fault(struct kvm_vcpu *vcpu) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; } -static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_io(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int size, in, string; @@ -2827,8 +2827,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) string = (exit_qualification & 16) != 0; if (string) { - if (emulate_instruction(vcpu, - kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } @@ -2838,7 +2837,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) port = exit_qualification >> 16; skip_emulated_instruction(vcpu); - return kvm_emulate_pio(vcpu, kvm_run, in, size, port); + return kvm_emulate_pio(vcpu, in, size, port); } static void @@ -2852,7 +2851,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } -static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; int cr; @@ -2887,7 +2886,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; if (cr8_prev <= cr8) return 1; - kvm_run->exit_reason = KVM_EXIT_SET_TPR; + vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } }; @@ -2922,13 +2921,13 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) default: break; } - kvm_run->exit_reason = 0; + vcpu->run->exit_reason = 0; pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } -static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; unsigned long val; @@ -2944,13 +2943,13 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - kvm_run->debug.arch.dr6 = vcpu->arch.dr6; - kvm_run->debug.arch.dr7 = dr; - kvm_run->debug.arch.pc = + vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; + vcpu->run->debug.arch.dr7 = dr; + vcpu->run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + vmcs_readl(GUEST_RIP); - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; + vcpu->run->debug.arch.exception = DB_VECTOR; + vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { vcpu->arch.dr7 &= ~DR7_GD; @@ -3016,13 +3015,13 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_cpuid(struct kvm_vcpu *vcpu) { kvm_emulate_cpuid(vcpu); return 1; } -static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data; @@ -3041,7 +3040,7 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_wrmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) @@ -3058,14 +3057,12 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { return 1; } -static int handle_interrupt_window(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_interrupt_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; @@ -3081,34 +3078,34 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu, * possible */ if (!irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && !kvm_cpu_has_interrupt(vcpu)) { - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; + vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; return 0; } return 1; } -static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_halt(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } -static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_vmcall(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } -static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_vmx_insn(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } -static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_invlpg(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -3117,14 +3114,14 @@ static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_wbinvd(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); /* TODO: Add support for VT-d/pass-through device */ return 1; } -static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_apic_access(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; enum emulation_result er; @@ -3133,7 +3130,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); offset = exit_qualification & 0xffful; - er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + er = emulate_instruction(vcpu, 0, 0, 0); if (er != EMULATE_DONE) { printk(KERN_ERR @@ -3144,7 +3141,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; @@ -3198,7 +3195,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; gpa_t gpa; @@ -3219,8 +3216,8 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vmcs_readl(GUEST_LINEAR_ADDRESS)); printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", (long unsigned int)exit_qualification); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; return 0; } @@ -3290,7 +3287,7 @@ static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, } } -static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { u64 sptes[4]; int nr_sptes, i; @@ -3306,13 +3303,13 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; return 0; } -static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; @@ -3325,8 +3322,7 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static void handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); enum emulation_result err = EMULATE_DONE; @@ -3335,7 +3331,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, preempt_enable(); while (!guest_state_valid(vcpu)) { - err = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + err = emulate_instruction(vcpu, 0, 0, 0); if (err == EMULATE_DO_MMIO) break; @@ -3362,8 +3358,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, * may resume. Otherwise they set the kvm_run parameter to indicate what needs * to be done to userspace and return 0. */ -static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) = { +static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EXCEPTION_NMI] = handle_exception, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, @@ -3403,7 +3398,7 @@ static const int kvm_vmx_max_exit_handlers = * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int vmx_handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; @@ -3425,8 +3420,8 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); if (unlikely(vmx->fail)) { - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - kvm_run->fail_entry.hardware_entry_failure_reason + vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; + vcpu->run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); return 0; } @@ -3459,10 +3454,10 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) - return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); + return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_reason; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = exit_reason; } return 0; } @@ -3600,7 +3595,7 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx) #define Q "l" #endif -static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3614,7 +3609,7 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) /* Handle invalid guest state instead of entering VMX */ if (vmx->emulation_required && emulate_invalid_guest_state) { - handle_invalid_guest_state(vcpu, kvm_run); + handle_invalid_guest_state(vcpu); return; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ae07d261527..1687d12b122 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2757,13 +2757,13 @@ static void cache_all_regs(struct kvm_vcpu *vcpu) } int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, unsigned long cr2, u16 error_code, int emulation_type) { int r, shadow_mask; struct decode_cache *c; + struct kvm_run *run = vcpu->run; kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; @@ -2969,8 +2969,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu) return r; } -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) { unsigned long val; @@ -2999,7 +2998,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, } EXPORT_SYMBOL_GPL(kvm_emulate_pio); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port) { @@ -3453,17 +3452,17 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); * * No need to exit to userspace if we already have an interrupt queued. */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && kvm_arch_interrupt_allowed(vcpu)); } -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static void post_kvm_run_save(struct kvm_vcpu *vcpu) { + struct kvm_run *kvm_run = vcpu->run; + kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); @@ -3525,7 +3524,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { @@ -3561,11 +3560,11 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } -static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window; + vcpu->run->request_interrupt_window; if (vcpu->requests) if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) @@ -3586,12 +3585,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_x86_ops->tlb_flush(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; + vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; r = 0; goto out; } @@ -3615,7 +3614,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - inject_pending_event(vcpu, kvm_run); + inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) @@ -3641,7 +3640,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } trace_kvm_entry(vcpu->vcpu_id); - kvm_x86_ops->run(vcpu, kvm_run); + kvm_x86_ops->run(vcpu); if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) { set_debugreg(current->thread.debugreg0, 0); @@ -3682,13 +3681,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); + r = kvm_x86_ops->handle_exit(vcpu); out: return r; } -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int __vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -3708,7 +3707,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) r = 1; while (r > 0) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) - r = vcpu_enter_guest(vcpu, kvm_run); + r = vcpu_enter_guest(vcpu); else { up_read(&vcpu->kvm->slots_lock); kvm_vcpu_block(vcpu); @@ -3736,14 +3735,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu, kvm_run)) { + if (dm_request_for_irq_injection(vcpu)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; } if (signal_pending(current)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } if (need_resched()) { @@ -3754,7 +3753,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } up_read(&vcpu->kvm->slots_lock); - post_kvm_run_save(vcpu, kvm_run); + post_kvm_run_save(vcpu); vapic_exit(vcpu); @@ -3794,8 +3793,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->mmio_needed = 0; down_read(&vcpu->kvm->slots_lock); - r = emulate_instruction(vcpu, kvm_run, - vcpu->arch.mmio_fault_cr2, 0, + r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, EMULTYPE_NO_DECODE); up_read(&vcpu->kvm->slots_lock); if (r == EMULATE_DO_MMIO) { @@ -3811,7 +3809,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_register_write(vcpu, VCPU_REGS_RAX, kvm_run->hypercall.ret); - r = __vcpu_run(vcpu, kvm_run); + r = __vcpu_run(vcpu); out: if (vcpu->sigset_active) From 79c727d4371aa9af47b0cdbcad53742b5a7919ea Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:18 +0300 Subject: [PATCH 09/84] KVM: Call pic_clear_isr() on pic reset to reuse logic there Also move call of ack notifiers after pic state change. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/i8259.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 01f15168280..ccc941af4ea 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -225,22 +225,11 @@ int kvm_pic_read_irq(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, irqbase, n; + int irq; struct kvm *kvm = s->pics_state->irq_request_opaque; struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu; + u8 irr = s->irr, isr = s->imr; - if (s == &s->pics_state->pics[0]) - irqbase = 0; - else - irqbase = 8; - - for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { - if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) - if (s->irr & (1 << irq) || s->isr & (1 << irq)) { - n = irq + irqbase; - kvm_notify_acked_irq(kvm, SELECT_PIC(n), n); - } - } s->last_irr = 0; s->irr = 0; s->imr = 0; @@ -256,6 +245,13 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->rotate_on_auto_eoi = 0; s->special_fully_nested_mode = 0; s->init4 = 0; + + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { + if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) + if (irr & (1 << irq) || isr & (1 << irq)) { + pic_clear_isr(s, irq); + } + } } static void pic_ioport_write(void *opaque, u32 addr, u32 val) From 1a6e4a8c276e122dbeb6f9c610f29735e4236bfd Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:19 +0300 Subject: [PATCH 10/84] KVM: Move irq sharing information to irqchip level 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: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/irq.h | 1 + include/linux/kvm_host.h | 2 +- virt/kvm/ioapic.h | 1 + virt/kvm/irq_comm.c | 59 ++++++++++++++++++++------------- 5 files changed, 39 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0b113f2b58c..35d3236c9de 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -410,7 +410,6 @@ struct kvm_arch{ gpa_t ept_identity_map_addr; unsigned long irq_sources_bitmap; - unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; u64 vm_init_tsc; }; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7d6058a2fd3..c025a2362aa 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -71,6 +71,7 @@ struct kvm_pic { int output; /* intr from master PIC */ struct kvm_io_device dev; void (*ack_notifier)(void *opaque, int irq); + unsigned long irq_states[16]; }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b7bbb5ddd7a..1c7f8c49e4e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -120,7 +120,7 @@ struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level); + struct kvm *kvm, int irq_source_id, int level); union { struct { unsigned irqchip; diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 7080b713c16..6e461ade636 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -41,6 +41,7 @@ struct kvm_ioapic { u32 irr; u32 pad; union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS]; + unsigned long irq_states[IOAPIC_NUM_PINS]; struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 001663ff401..9783f5c43da 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -31,20 +31,39 @@ #include "ioapic.h" +static inline int kvm_irq_line_state(unsigned long *irq_state, + int irq_source_id, int level) +{ + /* Logical OR for level trig interrupt */ + if (level) + set_bit(irq_source_id, irq_state); + else + clear_bit(irq_source_id, irq_state); + + return !!(*irq_state); +} + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { #ifdef CONFIG_X86 - return kvm_pic_set_irq(pic_irqchip(kvm), e->irqchip.pin, level); + struct kvm_pic *pic = pic_irqchip(kvm); + level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin], + irq_source_id, level); + return kvm_pic_set_irq(pic, e->irqchip.pin, level); #else return -1; #endif } static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { - return kvm_ioapic_set_irq(kvm->arch.vioapic, e->irqchip.pin, level); + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin], + irq_source_id, level); + + return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level); } inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) @@ -96,10 +115,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, } static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm, int level) + struct kvm *kvm, int irq_source_id, int level) { struct kvm_lapic_irq irq; + if (!level) + return -1; + trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); irq.dest_id = (e->msi.address_lo & @@ -125,34 +147,19 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) { struct kvm_kernel_irq_routing_entry *e; - unsigned long *irq_state, sig_level; int ret = -1; trace_kvm_set_irq(irq, level, irq_source_id); WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - if (irq < KVM_IOAPIC_NUM_PINS) { - irq_state = (unsigned long *)&kvm->arch.irq_states[irq]; - - /* Logical OR for level trig interrupt */ - if (level) - set_bit(irq_source_id, irq_state); - else - clear_bit(irq_source_id, irq_state); - sig_level = !!(*irq_state); - } else if (!level) - return ret; - else /* Deal with MSI/MSI-X */ - sig_level = 1; - /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ list_for_each_entry(e, &kvm->irq_routing, link) if (e->gsi == irq) { - int r = e->set(e, kvm, sig_level); + int r = e->set(e, kvm, irq_source_id, level); if (r < 0) continue; @@ -232,8 +239,14 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); return; } - for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) - clear_bit(irq_source_id, &kvm->arch.irq_states[i]); + for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { + clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); + if (i >= 16) + continue; +#ifdef CONFIG_X86 + clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]); +#endif + } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); mutex_unlock(&kvm->irq_lock); } From 46e624b95c36d729bdf24010fff11d16f6fe94fa Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:20 +0300 Subject: [PATCH 11/84] KVM: Change irq routing table to use gsi indexed array Use gsi indexed array instead of scanning all entries on each interrupt injection. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 21 ++++++++-- virt/kvm/irq_comm.c | 88 ++++++++++++++++++++++++---------------- virt/kvm/kvm_main.c | 1 - 3 files changed, 71 insertions(+), 39 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1c7f8c49e4e..f403e66557f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -128,7 +128,17 @@ struct kvm_kernel_irq_routing_entry { } irqchip; struct msi_msg msi; }; - struct list_head link; + struct hlist_node link; +}; + +struct kvm_irq_routing_table { + struct kvm_kernel_irq_routing_entry *rt_entries; + u32 nr_rt_entries; + /* + * Array indexed by gsi. Each entry contains list of irq chips + * the gsi is connected to. + */ + struct hlist_head map[0]; }; struct kvm { @@ -166,7 +176,7 @@ struct kvm { struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP - struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */ + struct kvm_irq_routing_table *irq_routing; struct hlist_head mask_notifier_list; #endif @@ -390,7 +400,12 @@ 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); -int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level); +#ifdef __KVM_HAVE_IOAPIC +void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, + union kvm_ioapic_redirect_entry *entry, + unsigned long *deliver_bitmask); +#endif +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, 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); diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 9783f5c43da..81950f6f6fd 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -144,10 +144,12 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, * = 0 Interrupt was coalesced (previous irq is still pending) * > 0 Number of CPUs interrupt was delivered to */ -int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) +int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) { struct kvm_kernel_irq_routing_entry *e; int ret = -1; + struct kvm_irq_routing_table *irq_rt; + struct hlist_node *n; trace_kvm_set_irq(irq, level, irq_source_id); @@ -157,8 +159,9 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - list_for_each_entry(e, &kvm->irq_routing, link) - if (e->gsi == irq) { + irq_rt = kvm->irq_routing; + if (irq < irq_rt->nr_rt_entries) + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { int r = e->set(e, kvm, irq_source_id, level); if (r < 0) continue; @@ -170,20 +173,23 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level) void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { - struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_ack_notifier *kian; struct hlist_node *n; unsigned gsi = pin; + int i; trace_kvm_ack_irq(irqchip, pin); - list_for_each_entry(e, &kvm->irq_routing, link) + for (i = 0; i < kvm->irq_routing->nr_rt_entries; i++) { + struct kvm_kernel_irq_routing_entry *e; + e = &kvm->irq_routing->rt_entries[i]; if (e->type == KVM_IRQ_ROUTING_IRQCHIP && e->irqchip.irqchip == irqchip && e->irqchip.pin == pin) { gsi = e->gsi; break; } + } hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) if (kian->gsi == gsi) @@ -280,26 +286,30 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) kimn->func(kimn, mask); } -static void __kvm_free_irq_routing(struct list_head *irq_routing) -{ - struct kvm_kernel_irq_routing_entry *e, *n; - - list_for_each_entry_safe(e, n, irq_routing, link) - kfree(e); -} - void kvm_free_irq_routing(struct kvm *kvm) { mutex_lock(&kvm->irq_lock); - __kvm_free_irq_routing(&kvm->irq_routing); + kfree(kvm->irq_routing); mutex_unlock(&kvm->irq_lock); } -static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, +static int setup_routing_entry(struct kvm_irq_routing_table *rt, + struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; int delta; + struct kvm_kernel_irq_routing_entry *ei; + struct hlist_node *n; + + /* + * Do not allow GSI to be mapped to the same irqchip more than once. + * Allow only one to one mapping between GSI and MSI. + */ + hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link) + if (ei->type == KVM_IRQ_ROUTING_MSI || + ue->u.irqchip.irqchip == ei->irqchip.irqchip) + return r; e->gsi = ue->gsi; e->type = ue->type; @@ -332,6 +342,8 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, default: goto out; } + + hlist_add_head(&e->link, &rt->map[e->gsi]); r = 0; out: return r; @@ -343,43 +355,49 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned nr, unsigned flags) { - struct list_head irq_list = LIST_HEAD_INIT(irq_list); - struct list_head tmp = LIST_HEAD_INIT(tmp); - struct kvm_kernel_irq_routing_entry *e = NULL; - unsigned i; + struct kvm_irq_routing_table *new, *old; + u32 i, nr_rt_entries = 0; int r; + for (i = 0; i < nr; ++i) { + if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) + return -EINVAL; + nr_rt_entries = max(nr_rt_entries, ue[i].gsi); + } + + nr_rt_entries += 1; + + new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head)) + + (nr * sizeof(struct kvm_kernel_irq_routing_entry)), + GFP_KERNEL); + + if (!new) + return -ENOMEM; + + new->rt_entries = (void *)&new->map[nr_rt_entries]; + + new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < nr; ++i) { r = -EINVAL; - if (ue->gsi >= KVM_MAX_IRQ_ROUTES) - goto out; if (ue->flags) goto out; - r = -ENOMEM; - e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - goto out; - r = setup_routing_entry(e, ue); + r = setup_routing_entry(new, &new->rt_entries[i], ue); if (r) goto out; ++ue; - list_add(&e->link, &irq_list); - e = NULL; } mutex_lock(&kvm->irq_lock); - list_splice(&kvm->irq_routing, &tmp); - INIT_LIST_HEAD(&kvm->irq_routing); - list_splice(&irq_list, &kvm->irq_routing); - INIT_LIST_HEAD(&irq_list); - list_splice(&tmp, &irq_list); + old = kvm->irq_routing; + kvm->irq_routing = new; mutex_unlock(&kvm->irq_lock); + new = old; r = 0; out: - kfree(e); - __kvm_free_irq_routing(&irq_list); + kfree(new); return r; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 22b520b5441..3bee9489277 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -957,7 +957,6 @@ static struct kvm *kvm_create_vm(void) if (IS_ERR(kvm)) goto out; #ifdef CONFIG_HAVE_KVM_IRQCHIP - INIT_LIST_HEAD(&kvm->irq_routing); INIT_HLIST_HEAD(&kvm->mask_notifier_list); #endif From 3e71f88bc90792a187703860cf22fbed7c12cbd9 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:21 +0300 Subject: [PATCH 12/84] KVM: Maintain back mapping from irqchip/pin to gsi Maintain back mapping from irqchip/pin to gsi to speedup interrupt acknowledgment notifications. [avi: build fix on non-x86/ia64] Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm.h | 1 + arch/x86/include/asm/kvm.h | 1 + include/linux/kvm_host.h | 9 +++++++++ virt/kvm/irq_comm.c | 31 ++++++++++++++----------------- 4 files changed, 25 insertions(+), 17 deletions(-) diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h index 18a7e49abbc..bc90c75adf6 100644 --- a/arch/ia64/include/asm/kvm.h +++ b/arch/ia64/include/asm/kvm.h @@ -60,6 +60,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 #define KVM_CONTEXT_SIZE 8*1024 diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 4a5fe914dc5..f02e87a5206 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -79,6 +79,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f403e66557f..cc2d7493598 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -131,7 +131,10 @@ struct kvm_kernel_irq_routing_entry { struct hlist_node link; }; +#ifdef __KVM_HAVE_IOAPIC + struct kvm_irq_routing_table { + int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS]; struct kvm_kernel_irq_routing_entry *rt_entries; u32 nr_rt_entries; /* @@ -141,6 +144,12 @@ struct kvm_irq_routing_table { struct hlist_head map[0]; }; +#else + +struct kvm_irq_routing_table {}; + +#endif + struct kvm { spinlock_t mmu_lock; spinlock_t requests_lock; diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 81950f6f6fd..59cf8dae006 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -175,25 +175,16 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_ack_notifier *kian; struct hlist_node *n; - unsigned gsi = pin; - int i; + int gsi; trace_kvm_ack_irq(irqchip, pin); - for (i = 0; i < kvm->irq_routing->nr_rt_entries; i++) { - struct kvm_kernel_irq_routing_entry *e; - e = &kvm->irq_routing->rt_entries[i]; - if (e->type == KVM_IRQ_ROUTING_IRQCHIP && - e->irqchip.irqchip == irqchip && - e->irqchip.pin == pin) { - gsi = e->gsi; - break; - } - } - - hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) - if (kian->gsi == gsi) - kian->irq_acked(kian); + gsi = kvm->irq_routing->chip[irqchip][pin]; + if (gsi != -1) + hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, + link) + if (kian->gsi == gsi) + kian->irq_acked(kian); } void kvm_register_irq_ack_notifier(struct kvm *kvm, @@ -332,6 +323,9 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt, } e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin + delta; + if (e->irqchip.pin >= KVM_IOAPIC_NUM_PINS) + goto out; + rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; @@ -356,7 +350,7 @@ int kvm_set_irq_routing(struct kvm *kvm, unsigned flags) { struct kvm_irq_routing_table *new, *old; - u32 i, nr_rt_entries = 0; + u32 i, j, nr_rt_entries = 0; int r; for (i = 0; i < nr; ++i) { @@ -377,6 +371,9 @@ int kvm_set_irq_routing(struct kvm *kvm, new->rt_entries = (void *)&new->map[nr_rt_entries]; new->nr_rt_entries = nr_rt_entries; + for (i = 0; i < 3; i++) + for (j = 0; j < KVM_IOAPIC_NUM_PINS; j++) + new->chip[i][j] = -1; for (i = 0; i < nr; ++i) { r = -EINVAL; From e42bba90bfe724e32fc66ab1b6cb283c51d064b1 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:22 +0300 Subject: [PATCH 13/84] KVM: Move irq routing data structure to rcu locking Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 59cf8dae006..fb861dd956f 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -159,7 +159,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ - irq_rt = kvm->irq_routing; + rcu_read_lock(); + irq_rt = rcu_dereference(kvm->irq_routing); if (irq < irq_rt->nr_rt_entries) hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { int r = e->set(e, kvm, irq_source_id, level); @@ -168,6 +169,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) ret = r + ((ret < 0) ? 0 : ret); } + rcu_read_unlock(); return ret; } @@ -179,7 +181,10 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) trace_kvm_ack_irq(irqchip, pin); - gsi = kvm->irq_routing->chip[irqchip][pin]; + rcu_read_lock(); + gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; + rcu_read_unlock(); + if (gsi != -1) hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, link) @@ -279,9 +284,9 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) void kvm_free_irq_routing(struct kvm *kvm) { - mutex_lock(&kvm->irq_lock); + /* Called only during vm destruction. Nobody can use the pointer + at this stage */ kfree(kvm->irq_routing); - mutex_unlock(&kvm->irq_lock); } static int setup_routing_entry(struct kvm_irq_routing_table *rt, @@ -387,8 +392,9 @@ int kvm_set_irq_routing(struct kvm *kvm, mutex_lock(&kvm->irq_lock); old = kvm->irq_routing; - kvm->irq_routing = new; + rcu_assign_pointer(kvm->irq_routing, new); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); new = old; r = 0; From 136bdfeee7b5bc986fc94af3a40d7d13ea37bb95 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:23 +0300 Subject: [PATCH 14/84] KVM: Move irq ack notifier list to arch independent code Mask irq notifier list is already there. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/include/asm/kvm_host.h | 1 - arch/x86/include/asm/kvm_host.h | 1 - include/linux/kvm_host.h | 1 + virt/kvm/irq_comm.c | 5 ++--- virt/kvm/kvm_main.c | 1 + 5 files changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h index d9b6325a932..a362e67e0ca 100644 --- a/arch/ia64/include/asm/kvm_host.h +++ b/arch/ia64/include/asm/kvm_host.h @@ -475,7 +475,6 @@ struct kvm_arch { struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; int iommu_flags; - struct hlist_head irq_ack_notifier_list; unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 35d3236c9de..a46e2dd9aca 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -397,7 +397,6 @@ struct kvm_arch{ struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; - struct hlist_head irq_ack_notifier_list; int vapics_in_nmi_mode; unsigned int tss_addr; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cc2d7493598..4aa5e1d9a79 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -187,6 +187,7 @@ struct kvm { #ifdef CONFIG_HAVE_KVM_IRQCHIP struct kvm_irq_routing_table *irq_routing; struct hlist_head mask_notifier_list; + struct hlist_head irq_ack_notifier_list; #endif #ifdef KVM_ARCH_WANT_MMU_NOTIFIER diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index fb861dd956f..f0197259593 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -186,8 +186,7 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) rcu_read_unlock(); if (gsi != -1) - hlist_for_each_entry(kian, n, &kvm->arch.irq_ack_notifier_list, - link) + hlist_for_each_entry(kian, n, &kvm->irq_ack_notifier_list, link) if (kian->gsi == gsi) kian->irq_acked(kian); } @@ -196,7 +195,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list); + hlist_add_head(&kian->link, &kvm->irq_ack_notifier_list); mutex_unlock(&kvm->irq_lock); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3bee9489277..6eca153e1a0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -958,6 +958,7 @@ static struct kvm *kvm_create_vm(void) goto out; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); + INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET From 280aa177dcd1edc718d8a92f17f235b783ec6307 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:24 +0300 Subject: [PATCH 15/84] KVM: Convert irq notifiers lists to RCU locking Use RCU locking for mask/ack notifiers lists. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index f0197259593..6c946141dbc 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -183,19 +183,19 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) rcu_read_lock(); gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin]; - rcu_read_unlock(); - if (gsi != -1) - hlist_for_each_entry(kian, n, &kvm->irq_ack_notifier_list, link) + hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list, + link) if (kian->gsi == gsi) kian->irq_acked(kian); + rcu_read_unlock(); } void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_add_head(&kian->link, &kvm->irq_ack_notifier_list); + hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list); mutex_unlock(&kvm->irq_lock); } @@ -203,8 +203,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian) { mutex_lock(&kvm->irq_lock); - hlist_del_init(&kian->link); + hlist_del_init_rcu(&kian->link); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); } int kvm_request_irq_source_id(struct kvm *kvm) @@ -257,7 +258,7 @@ void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, { mutex_lock(&kvm->irq_lock); kimn->irq = irq; - hlist_add_head(&kimn->link, &kvm->mask_notifier_list); + hlist_add_head_rcu(&kimn->link, &kvm->mask_notifier_list); mutex_unlock(&kvm->irq_lock); } @@ -265,8 +266,9 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn) { mutex_lock(&kvm->irq_lock); - hlist_del(&kimn->link); + hlist_del_rcu(&kimn->link); mutex_unlock(&kvm->irq_lock); + synchronize_rcu(); } void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) @@ -274,11 +276,11 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask) struct kvm_irq_mask_notifier *kimn; struct hlist_node *n; - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - - hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link) + rcu_read_lock(); + hlist_for_each_entry_rcu(kimn, n, &kvm->mask_notifier_list, link) if (kimn->irq == irq) kimn->func(kimn, mask); + rcu_read_unlock(); } void kvm_free_irq_routing(struct kvm *kvm) From eba0226bdfffe262e72b8360e4d0d12070e9a0f0 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:25 +0300 Subject: [PATCH 16/84] KVM: Move IO APIC to its own lock The allows removal of irq_lock from the injection path. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 7 +--- arch/x86/kvm/i8259.c | 22 ++++++++--- arch/x86/kvm/lapic.c | 5 +-- arch/x86/kvm/x86.c | 10 +---- virt/kvm/ioapic.c | 80 ++++++++++++++++++++++++++++++---------- virt/kvm/ioapic.h | 4 ++ virt/kvm/irq_comm.c | 23 +++++++----- 7 files changed, 100 insertions(+), 51 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 0ad09f05efa..4a983147f6e 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -851,8 +851,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -868,9 +867,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_IOAPIC: - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index ccc941af4ea..d057c0cbd24 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -38,7 +38,15 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) s->isr_ack |= (1 << irq); if (s != &s->pics_state->pics[0]) irq += 8; + /* + * We are dropping lock while calling ack notifiers since ack + * notifier callbacks for assigned devices call into PIC recursively. + * Other interrupt may be delivered to PIC while lock is dropped but + * it should be safe since PIC state is already updated at this stage. + */ + spin_unlock(&s->pics_state->lock); kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); + spin_lock(&s->pics_state->lock); } void kvm_pic_clear_isr_ack(struct kvm *kvm) @@ -176,16 +184,18 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) static inline void pic_intack(struct kvm_kpic_state *s, int irq) { s->isr |= 1 << irq; - if (s->auto_eoi) { - if (s->rotate_on_auto_eoi) - s->priority_add = (irq + 1) & 7; - pic_clear_isr(s, irq); - } /* * We don't clear a level sensitive interrupt here */ if (!(s->elcr & (1 << irq))) s->irr &= ~(1 << irq); + + if (s->auto_eoi) { + if (s->rotate_on_auto_eoi) + s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); + } + } int kvm_pic_read_irq(struct kvm *kvm) @@ -294,9 +304,9 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) priority = get_priority(s, s->isr); if (priority != 8) { irq = (priority + s->priority_add) & 7; - pic_clear_isr(s, irq); if (cmd == 5) s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); pic_update_irq(s->pics_state); } break; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 23c217692ea..df8bcb0f66d 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -471,11 +471,8 @@ static void apic_set_eoi(struct kvm_lapic *apic) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; - if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) { - mutex_lock(&apic->vcpu->kvm->irq_lock); + if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); - mutex_unlock(&apic->vcpu->kvm->irq_lock); - } } static void apic_send_ipi(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1687d12b122..fdf989f17a6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2038,9 +2038,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2070,11 +2068,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: - mutex_lock(&kvm->irq_lock); - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - mutex_unlock(&kvm->irq_lock); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 9fe140bb38e..38a2d20b89d 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -182,6 +182,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) union kvm_ioapic_redirect_entry entry; int ret = 1; + mutex_lock(&ioapic->lock); if (irq >= 0 && irq < IOAPIC_NUM_PINS) { entry = ioapic->redirtbl[irq]; level ^= entry.fields.polarity; @@ -198,34 +199,51 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) } trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0); } + mutex_unlock(&ioapic->lock); + return ret; } -static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin, - int trigger_mode) +static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector, + int trigger_mode) { - union kvm_ioapic_redirect_entry *ent; + int i; - ent = &ioapic->redirtbl[pin]; + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i]; - kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin); + if (ent->fields.vector != vector) + continue; + + /* + * We are dropping lock while calling ack notifiers because ack + * notifier callbacks for assigned devices call into IOAPIC + * recursively. Since remote_irr is cleared only after call + * to notifiers if the same vector will be delivered while lock + * is dropped it will be put into irr and will be delivered + * after ack notifier returns. + */ + mutex_unlock(&ioapic->lock); + kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i); + mutex_lock(&ioapic->lock); + + if (trigger_mode != IOAPIC_LEVEL_TRIG) + continue; - if (trigger_mode == IOAPIC_LEVEL_TRIG) { ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << pin))) - ioapic_service(ioapic, pin); + if (!ent->fields.mask && (ioapic->irr & (1 << i))) + ioapic_service(ioapic, i); } } void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; - int i; - for (i = 0; i < IOAPIC_NUM_PINS; i++) - if (ioapic->redirtbl[i].fields.vector == vector) - __kvm_ioapic_update_eoi(ioapic, i, trigger_mode); + mutex_lock(&ioapic->lock); + __kvm_ioapic_update_eoi(ioapic, vector, trigger_mode); + mutex_unlock(&ioapic->lock); } static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev) @@ -250,8 +268,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, ioapic_debug("addr %lx\n", (unsigned long)addr); ASSERT(!(addr & 0xf)); /* check alignment */ - mutex_lock(&ioapic->kvm->irq_lock); addr &= 0xff; + mutex_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: result = ioapic->ioregsel; @@ -265,6 +283,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, result = 0; break; } + mutex_unlock(&ioapic->lock); + switch (len) { case 8: *(u64 *) val = result; @@ -277,7 +297,6 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, default: printk(KERN_WARNING "ioapic: wrong length %d\n", len); } - mutex_unlock(&ioapic->kvm->irq_lock); return 0; } @@ -293,15 +312,15 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, (void*)addr, len, val); ASSERT(!(addr & 0xf)); /* check alignment */ - mutex_lock(&ioapic->kvm->irq_lock); if (len == 4 || len == 8) data = *(u32 *) val; else { printk(KERN_WARNING "ioapic: Unsupported size %d\n", len); - goto unlock; + return 0; } addr &= 0xff; + mutex_lock(&ioapic->lock); switch (addr) { case IOAPIC_REG_SELECT: ioapic->ioregsel = data; @@ -312,15 +331,14 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, break; #ifdef CONFIG_IA64 case IOAPIC_REG_EOI: - kvm_ioapic_update_eoi(ioapic->kvm, data, IOAPIC_LEVEL_TRIG); + __kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG); break; #endif default: break; } -unlock: - mutex_unlock(&ioapic->kvm->irq_lock); + mutex_unlock(&ioapic->lock); return 0; } @@ -349,6 +367,7 @@ int kvm_ioapic_init(struct kvm *kvm) ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); if (!ioapic) return -ENOMEM; + mutex_init(&ioapic->lock); kvm->arch.vioapic = ioapic; kvm_ioapic_reset(ioapic); kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops); @@ -360,3 +379,26 @@ int kvm_ioapic_init(struct kvm *kvm) return ret; } +int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +{ + struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + if (!ioapic) + return -EINVAL; + + mutex_lock(&ioapic->lock); + memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&ioapic->lock); + return 0; +} + +int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) +{ + struct kvm_ioapic *ioapic = ioapic_irqchip(kvm); + if (!ioapic) + return -EINVAL; + + mutex_lock(&ioapic->lock); + memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); + mutex_unlock(&ioapic->lock); + return 0; +} diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h index 6e461ade636..419c43b667a 100644 --- a/virt/kvm/ioapic.h +++ b/virt/kvm/ioapic.h @@ -45,6 +45,7 @@ struct kvm_ioapic { struct kvm_io_device dev; struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); + struct mutex lock; }; #ifdef DEBUG @@ -74,4 +75,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); void kvm_ioapic_reset(struct kvm_ioapic *ioapic); int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq); +int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); +int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); + #endif diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 6c946141dbc..fadf4408a82 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -146,8 +146,8 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, */ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) { - struct kvm_kernel_irq_routing_entry *e; - int ret = -1; + struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS]; + int ret = -1, i = 0; struct kvm_irq_routing_table *irq_rt; struct hlist_node *n; @@ -162,14 +162,19 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) rcu_read_lock(); irq_rt = rcu_dereference(kvm->irq_routing); if (irq < irq_rt->nr_rt_entries) - hlist_for_each_entry(e, n, &irq_rt->map[irq], link) { - int r = e->set(e, kvm, irq_source_id, level); - if (r < 0) - continue; - - ret = r + ((ret < 0) ? 0 : ret); - } + hlist_for_each_entry(e, n, &irq_rt->map[irq], link) + irq_set[i++] = *e; rcu_read_unlock(); + + while(i--) { + int r; + r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level); + if (r < 0) + continue; + + ret = r + ((ret < 0) ? 0 : ret); + } + return ret; } From 680b3648ba89c44ac8d0316f78a0d6e147b88809 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 24 Aug 2009 11:54:26 +0300 Subject: [PATCH 17/84] KVM: Drop kvm->irq_lock lock from irq injection path 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: Gleb Natapov Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 2 -- arch/x86/kvm/i8254.c | 2 -- arch/x86/kvm/lapic.c | 2 -- arch/x86/kvm/x86.c | 2 -- virt/kvm/eventfd.c | 2 -- virt/kvm/irq_comm.c | 6 +----- virt/kvm/kvm_main.c | 2 -- 7 files changed, 1 insertion(+), 17 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 4a983147f6e..f534e0f6bb0 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -982,10 +982,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 144e7f60b5e..fab7440c9bb 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -688,10 +688,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm) struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - mutex_unlock(&kvm->irq_lock); /* * Provides NMI watchdog support via Virtual Wire mode. diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index df8bcb0f66d..8787637b1a9 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -501,9 +501,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); - mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); - mutex_unlock(&apic->vcpu->kvm->irq_lock); } static u32 apic_get_tmcct(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fdf989f17a6..5beb4c16caa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2286,10 +2286,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index bb4ebd89b9f..30f70fd511c 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -61,10 +61,8 @@ irqfd_inject(struct work_struct *work) struct _irqfd *irqfd = container_of(work, struct _irqfd, inject); struct kvm *kvm = irqfd->kvm; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1); kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0); - mutex_unlock(&kvm->irq_lock); } /* diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index fadf4408a82..15a83b93566 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -82,8 +82,6 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, int i, r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - if (irq->dest_mode == 0 && irq->dest_id == 0xff && kvm_is_dm_lowest_prio(irq)) printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); @@ -138,7 +136,7 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq); } -/* This should be called with the kvm->irq_lock mutex held +/* * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) * = 0 Interrupt was coalesced (previous irq is still pending) @@ -153,8 +151,6 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level) trace_kvm_set_irq(irq, level, irq_source_id); - WARN_ON(!mutex_is_locked(&kvm->irq_lock)); - /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6eca153e1a0..c12c95b1b64 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -137,7 +137,6 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) interrupt_work); kvm = assigned_dev->kvm; - mutex_lock(&kvm->irq_lock); spin_lock_irq(&assigned_dev->assigned_dev_lock); if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { struct kvm_guest_msix_entry *guest_entries = @@ -156,7 +155,6 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) assigned_dev->guest_irq, 1); spin_unlock_irq(&assigned_dev->assigned_dev_lock); - mutex_unlock(&assigned_dev->kvm->irq_lock); } static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) From 367e1319b229110a27c53221c2fa32a6aa86d4a9 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 26 Aug 2009 14:57:07 +0300 Subject: [PATCH 18/84] KVM: Return -ENOTTY on unrecognized ioctls Not the incorrect -EINVAL. Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 2 +- arch/powerpc/kvm/powerpc.c | 2 +- arch/s390/kvm/kvm-s390.c | 2 +- arch/x86/kvm/x86.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index f534e0f6bb0..f6471c88266 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -941,7 +941,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; switch (ioctl) { case KVM_SET_MEMORY_REGION: { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 2a4551f78f6..95af62217b6 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -421,7 +421,7 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { default: - r = -EINVAL; + r = -ENOTTY; } return r; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 07ced89740d..00e2ce8e91f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -150,7 +150,7 @@ long kvm_arch_vm_ioctl(struct file *filp, break; } default: - r = -EINVAL; + r = -ENOTTY; } return r; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5beb4c16caa..829e3063e2a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2176,7 +2176,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; /* * This union makes it completely explicit to gcc-3.x * that these two variables' stack usage should be From bfd99ff5d483b11c32bca49fbff7a5ac59038b0a Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 26 Aug 2009 14:57:50 +0300 Subject: [PATCH 19/84] KVM: Move assigned device code to own file Signed-off-by: Avi Kivity --- arch/ia64/kvm/Makefile | 2 +- arch/x86/kvm/Makefile | 3 +- include/linux/kvm_host.h | 17 + virt/kvm/assigned-dev.c | 818 +++++++++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 798 +------------------------------------- 5 files changed, 840 insertions(+), 798 deletions(-) create mode 100644 virt/kvm/assigned-dev.c diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile index 0bb99b73290..1089b3e918a 100644 --- a/arch/ia64/kvm/Makefile +++ b/arch/ia64/kvm/Makefile @@ -49,7 +49,7 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/ EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o) + coalesced_mmio.o irq_comm.o assigned-dev.o) ifeq ($(CONFIG_IOMMU_API),y) common-objs += $(addprefix ../../../virt/kvm/, iommu.o) diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 0e7fe78d0f7..31a7035c4bd 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -6,7 +6,8 @@ CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o) + coalesced_mmio.o irq_comm.o eventfd.o \ + assigned-dev.o) kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4aa5e1d9a79..c0a1cc35f08 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -577,4 +577,21 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id; } #endif + +#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT + +long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg); + +#else + +static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg) +{ + return -ENOTTY; +} + #endif + +#endif + diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c new file mode 100644 index 00000000000..fd9c097b760 --- /dev/null +++ b/virt/kvm/assigned-dev.c @@ -0,0 +1,818 @@ +/* + * Kernel-based Virtual Machine - device assignment support + * + * Copyright (C) 2006-9 Red Hat, Inc + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "irq.h" + +static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, + int assigned_dev_id) +{ + struct list_head *ptr; + struct kvm_assigned_dev_kernel *match; + + list_for_each(ptr, head) { + match = list_entry(ptr, struct kvm_assigned_dev_kernel, list); + if (match->assigned_dev_id == assigned_dev_id) + return match; + } + return NULL; +} + +static int find_index_from_host_irq(struct kvm_assigned_dev_kernel + *assigned_dev, int irq) +{ + int i, index; + struct msix_entry *host_msix_entries; + + host_msix_entries = assigned_dev->host_msix_entries; + + index = -1; + for (i = 0; i < assigned_dev->entries_nr; i++) + if (irq == host_msix_entries[i].vector) { + index = i; + break; + } + if (index < 0) { + printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); + return 0; + } + + return index; +} + +static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) +{ + struct kvm_assigned_dev_kernel *assigned_dev; + struct kvm *kvm; + int i; + + assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, + interrupt_work); + kvm = assigned_dev->kvm; + + spin_lock_irq(&assigned_dev->assigned_dev_lock); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + struct kvm_guest_msix_entry *guest_entries = + assigned_dev->guest_msix_entries; + for (i = 0; i < assigned_dev->entries_nr; i++) { + if (!(guest_entries[i].flags & + KVM_ASSIGNED_MSIX_PENDING)) + continue; + guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; + kvm_set_irq(assigned_dev->kvm, + assigned_dev->irq_source_id, + guest_entries[i].vector, 1); + } + } else + kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, + assigned_dev->guest_irq, 1); + + spin_unlock_irq(&assigned_dev->assigned_dev_lock); +} + +static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) +{ + unsigned long flags; + struct kvm_assigned_dev_kernel *assigned_dev = + (struct kvm_assigned_dev_kernel *) dev_id; + + spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int index = find_index_from_host_irq(assigned_dev, irq); + if (index < 0) + goto out; + assigned_dev->guest_msix_entries[index].flags |= + KVM_ASSIGNED_MSIX_PENDING; + } + + schedule_work(&assigned_dev->interrupt_work); + + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { + disable_irq_nosync(irq); + assigned_dev->host_irq_disabled = true; + } + +out: + spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); + return IRQ_HANDLED; +} + +/* Ack the irq line for an assigned device */ +static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) +{ + struct kvm_assigned_dev_kernel *dev; + unsigned long flags; + + if (kian->gsi == -1) + return; + + dev = container_of(kian, struct kvm_assigned_dev_kernel, + ack_notifier); + + kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); + + /* The guest irq may be shared so this ack may be + * from another device. + */ + spin_lock_irqsave(&dev->assigned_dev_lock, flags); + if (dev->host_irq_disabled) { + enable_irq(dev->host_irq); + dev->host_irq_disabled = false; + } + spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); +} + +static void deassign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); + assigned_dev->ack_notifier.gsi = -1; + + if (assigned_dev->irq_source_id != -1) + kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); + assigned_dev->irq_source_id = -1; + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); +} + +/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ +static void deassign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + /* + * In kvm_free_device_irq, cancel_work_sync return true if: + * 1. work is scheduled, and then cancelled. + * 2. work callback is executed. + * + * The first one ensured that the irq is disabled and no more events + * would happen. But for the second one, the irq may be enabled (e.g. + * for MSI). So we disable irq here to prevent further events. + * + * Notice this maybe result in nested disable if the interrupt type is + * INTx, but it's OK for we are going to free it. + * + * If this function is a part of VM destroy, please ensure that till + * now, the kvm state is still legal for probably we also have to wait + * interrupt_work done. + */ + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { + int i; + for (i = 0; i < assigned_dev->entries_nr; i++) + disable_irq_nosync(assigned_dev-> + host_msix_entries[i].vector); + + cancel_work_sync(&assigned_dev->interrupt_work); + + for (i = 0; i < assigned_dev->entries_nr; i++) + free_irq(assigned_dev->host_msix_entries[i].vector, + (void *)assigned_dev); + + assigned_dev->entries_nr = 0; + kfree(assigned_dev->host_msix_entries); + kfree(assigned_dev->guest_msix_entries); + pci_disable_msix(assigned_dev->dev); + } else { + /* Deal with MSI and INTx */ + disable_irq_nosync(assigned_dev->host_irq); + cancel_work_sync(&assigned_dev->interrupt_work); + + free_irq(assigned_dev->host_irq, (void *)assigned_dev); + + if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) + pci_disable_msi(assigned_dev->dev); + } + + assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); +} + +static int kvm_deassign_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev, + unsigned long irq_requested_type) +{ + unsigned long guest_irq_type, host_irq_type; + + if (!irqchip_in_kernel(kvm)) + return -EINVAL; + /* no irq assignment to deassign */ + if (!assigned_dev->irq_requested_type) + return -ENXIO; + + host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; + guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; + + if (host_irq_type) + deassign_host_irq(kvm, assigned_dev); + if (guest_irq_type) + deassign_guest_irq(kvm, assigned_dev); + + return 0; +} + +static void kvm_free_assigned_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *assigned_dev) +{ + kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); +} + +static void kvm_free_assigned_device(struct kvm *kvm, + struct kvm_assigned_dev_kernel + *assigned_dev) +{ + kvm_free_assigned_irq(kvm, assigned_dev); + + pci_reset_function(assigned_dev->dev); + + pci_release_regions(assigned_dev->dev); + pci_disable_device(assigned_dev->dev); + pci_dev_put(assigned_dev->dev); + + list_del(&assigned_dev->list); + kfree(assigned_dev); +} + +void kvm_free_all_assigned_devices(struct kvm *kvm) +{ + struct list_head *ptr, *ptr2; + struct kvm_assigned_dev_kernel *assigned_dev; + + list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) { + assigned_dev = list_entry(ptr, + struct kvm_assigned_dev_kernel, + list); + + kvm_free_assigned_device(kvm, assigned_dev); + } +} + +static int assigned_device_enable_host_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + dev->host_irq = dev->dev->irq; + /* Even though this is PCI, we don't want to use shared + * interrupts. Sharing host devices with guest-assigned devices + * on the same interrupt line is not a happy situation: there + * are going to be long delays in accepting, acking, etc. + */ + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, + 0, "kvm_assigned_intx_device", (void *)dev)) + return -EIO; + return 0; +} + +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_host_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int r; + + if (!dev->dev->msi_enabled) { + r = pci_enable_msi(dev->dev); + if (r) + return r; + } + + dev->host_irq = dev->dev->irq; + if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, + "kvm_assigned_msi_device", (void *)dev)) { + pci_disable_msi(dev->dev); + return -EIO; + } + + return 0; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_host_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev) +{ + int i, r = -EINVAL; + + /* host_msix_entries and guest_msix_entries should have been + * initialized */ + if (dev->entries_nr == 0) + return r; + + r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); + if (r) + return r; + + for (i = 0; i < dev->entries_nr; i++) { + r = request_irq(dev->host_msix_entries[i].vector, + kvm_assigned_dev_intr, 0, + "kvm_assigned_msix_device", + (void *)dev); + /* FIXME: free requested_irq's on failure */ + if (r) + return r; + } + + return 0; +} + +#endif + +static int assigned_device_enable_guest_intx(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = irq->guest_irq; + return 0; +} + +#ifdef __KVM_HAVE_MSI +static int assigned_device_enable_guest_msi(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + dev->host_irq_disabled = false; + return 0; +} +#endif + +#ifdef __KVM_HAVE_MSIX +static int assigned_device_enable_guest_msix(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq) +{ + dev->guest_irq = irq->guest_irq; + dev->ack_notifier.gsi = -1; + dev->host_irq_disabled = false; + return 0; +} +#endif + +static int assign_host_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + __u32 host_irq_type) +{ + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) + return r; + + switch (host_irq_type) { + case KVM_DEV_IRQ_HOST_INTX: + r = assigned_device_enable_host_intx(kvm, dev); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_HOST_MSI: + r = assigned_device_enable_host_msi(kvm, dev); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_HOST_MSIX: + r = assigned_device_enable_host_msix(kvm, dev); + break; +#endif + default: + r = -EINVAL; + } + + if (!r) + dev->irq_requested_type |= host_irq_type; + + return r; +} + +static int assign_guest_irq(struct kvm *kvm, + struct kvm_assigned_dev_kernel *dev, + struct kvm_assigned_irq *irq, + unsigned long guest_irq_type) +{ + int id; + int r = -EEXIST; + + if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) + return r; + + id = kvm_request_irq_source_id(kvm); + if (id < 0) + return id; + + dev->irq_source_id = id; + + switch (guest_irq_type) { + case KVM_DEV_IRQ_GUEST_INTX: + r = assigned_device_enable_guest_intx(kvm, dev, irq); + break; +#ifdef __KVM_HAVE_MSI + case KVM_DEV_IRQ_GUEST_MSI: + r = assigned_device_enable_guest_msi(kvm, dev, irq); + break; +#endif +#ifdef __KVM_HAVE_MSIX + case KVM_DEV_IRQ_GUEST_MSIX: + r = assigned_device_enable_guest_msix(kvm, dev, irq); + break; +#endif + default: + r = -EINVAL; + } + + if (!r) { + dev->irq_requested_type |= guest_irq_type; + kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); + } else + kvm_free_irq_source_id(kvm, dev->irq_source_id); + + return r; +} + +/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ +static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, + struct kvm_assigned_irq *assigned_irq) +{ + int r = -EINVAL; + struct kvm_assigned_dev_kernel *match; + unsigned long host_irq_type, guest_irq_type; + + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + + if (!irqchip_in_kernel(kvm)) + return r; + + mutex_lock(&kvm->lock); + r = -ENODEV; + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); + guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); + + r = -EINVAL; + /* can only assign one type at a time */ + if (hweight_long(host_irq_type) > 1) + goto out; + if (hweight_long(guest_irq_type) > 1) + goto out; + if (host_irq_type == 0 && guest_irq_type == 0) + goto out; + + r = 0; + if (host_irq_type) + r = assign_host_irq(kvm, match, host_irq_type); + if (r) + goto out; + + if (guest_irq_type) + r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, + struct kvm_assigned_irq + *assigned_irq) +{ + int r = -ENODEV; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_irq->assigned_dev_id); + if (!match) + goto out; + + r = kvm_deassign_irq(kvm, match, assigned_irq->flags); +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_assign_device(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + struct pci_dev *dev; + + down_read(&kvm->slots_lock); + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (match) { + /* device already assigned */ + r = -EEXIST; + goto out; + } + + match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); + if (match == NULL) { + printk(KERN_INFO "%s: Couldn't allocate memory\n", + __func__); + r = -ENOMEM; + goto out; + } + dev = pci_get_bus_and_slot(assigned_dev->busnr, + assigned_dev->devfn); + if (!dev) { + printk(KERN_INFO "%s: host device not found\n", __func__); + r = -EINVAL; + goto out_free; + } + if (pci_enable_device(dev)) { + printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); + r = -EBUSY; + goto out_put; + } + r = pci_request_regions(dev, "kvm_assigned_device"); + if (r) { + printk(KERN_INFO "%s: Could not get access to device regions\n", + __func__); + goto out_disable; + } + + pci_reset_function(dev); + + match->assigned_dev_id = assigned_dev->assigned_dev_id; + match->host_busnr = assigned_dev->busnr; + match->host_devfn = assigned_dev->devfn; + match->flags = assigned_dev->flags; + match->dev = dev; + spin_lock_init(&match->assigned_dev_lock); + match->irq_source_id = -1; + match->kvm = kvm; + match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; + INIT_WORK(&match->interrupt_work, + kvm_assigned_dev_interrupt_work_handler); + + list_add(&match->list, &kvm->arch.assigned_dev_head); + + if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { + if (!kvm->arch.iommu_domain) { + r = kvm_iommu_map_guest(kvm); + if (r) + goto out_list_del; + } + r = kvm_assign_device(kvm, match); + if (r) + goto out_list_del; + } + +out: + mutex_unlock(&kvm->lock); + up_read(&kvm->slots_lock); + return r; +out_list_del: + list_del(&match->list); + pci_release_regions(dev); +out_disable: + pci_disable_device(dev); +out_put: + pci_dev_put(dev); +out_free: + kfree(match); + mutex_unlock(&kvm->lock); + up_read(&kvm->slots_lock); + return r; +} + +static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, + struct kvm_assigned_pci_dev *assigned_dev) +{ + int r = 0; + struct kvm_assigned_dev_kernel *match; + + mutex_lock(&kvm->lock); + + match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + assigned_dev->assigned_dev_id); + if (!match) { + printk(KERN_INFO "%s: device hasn't been assigned before, " + "so cannot be deassigned\n", __func__); + r = -EINVAL; + goto out; + } + + if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) + kvm_deassign_device(kvm, match); + + kvm_free_assigned_device(kvm, match); + +out: + mutex_unlock(&kvm->lock); + return r; +} + + +#ifdef __KVM_HAVE_MSIX +static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, + struct kvm_assigned_msix_nr *entry_nr) +{ + int r = 0; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry_nr->assigned_dev_id); + if (!adev) { + r = -EINVAL; + goto msix_nr_out; + } + + if (adev->entries_nr == 0) { + adev->entries_nr = entry_nr->entry_nr; + if (adev->entries_nr == 0 || + adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { + r = -EINVAL; + goto msix_nr_out; + } + + adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * + entry_nr->entry_nr, + GFP_KERNEL); + if (!adev->host_msix_entries) { + r = -ENOMEM; + goto msix_nr_out; + } + adev->guest_msix_entries = kzalloc( + sizeof(struct kvm_guest_msix_entry) * + entry_nr->entry_nr, GFP_KERNEL); + if (!adev->guest_msix_entries) { + kfree(adev->host_msix_entries); + r = -ENOMEM; + goto msix_nr_out; + } + } else /* Not allowed set MSI-X number twice */ + r = -EINVAL; +msix_nr_out: + mutex_unlock(&kvm->lock); + return r; +} + +static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, + struct kvm_assigned_msix_entry *entry) +{ + int r = 0, i; + struct kvm_assigned_dev_kernel *adev; + + mutex_lock(&kvm->lock); + + adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, + entry->assigned_dev_id); + + if (!adev) { + r = -EINVAL; + goto msix_entry_out; + } + + for (i = 0; i < adev->entries_nr; i++) + if (adev->guest_msix_entries[i].vector == 0 || + adev->guest_msix_entries[i].entry == entry->entry) { + adev->guest_msix_entries[i].entry = entry->entry; + adev->guest_msix_entries[i].vector = entry->gsi; + adev->host_msix_entries[i].entry = entry->entry; + break; + } + if (i == adev->entries_nr) { + r = -ENOSPC; + goto msix_entry_out; + } + +msix_entry_out: + mutex_unlock(&kvm->lock); + + return r; +} +#endif + +long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + int r = -ENOTTY; + + switch (ioctl) { + case KVM_ASSIGN_PCI_DEVICE: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); + if (r) + goto out; + break; + } + case KVM_ASSIGN_IRQ: { + r = -EOPNOTSUPP; + break; + } +#ifdef KVM_CAP_ASSIGN_DEV_IRQ + case KVM_ASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } + case KVM_DEASSIGN_DEV_IRQ: { + struct kvm_assigned_irq assigned_irq; + + r = -EFAULT; + if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) + goto out; + r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); + if (r) + goto out; + break; + } +#endif +#ifdef KVM_CAP_DEVICE_DEASSIGNMENT + case KVM_DEASSIGN_PCI_DEVICE: { + struct kvm_assigned_pci_dev assigned_dev; + + r = -EFAULT; + if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) + goto out; + r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); + if (r) + goto out; + break; + } +#endif +#ifdef KVM_CAP_IRQ_ROUTING + case KVM_SET_GSI_ROUTING: { + struct kvm_irq_routing routing; + struct kvm_irq_routing __user *urouting; + struct kvm_irq_routing_entry *entries; + + r = -EFAULT; + if (copy_from_user(&routing, argp, sizeof(routing))) + goto out; + r = -EINVAL; + if (routing.nr >= KVM_MAX_IRQ_ROUTES) + goto out; + if (routing.flags) + goto out; + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + r = kvm_set_irq_routing(kvm, entries, routing.nr, + routing.flags); + out_free_irq_routing: + vfree(entries); + break; + } +#endif /* KVM_CAP_IRQ_ROUTING */ +#ifdef __KVM_HAVE_MSIX + case KVM_ASSIGN_SET_MSIX_NR: { + struct kvm_assigned_msix_nr entry_nr; + r = -EFAULT; + if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) + goto out; + r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); + if (r) + goto out; + break; + } + case KVM_ASSIGN_SET_MSIX_ENTRY: { + struct kvm_assigned_msix_entry entry; + r = -EFAULT; + if (copy_from_user(&entry, argp, sizeof entry)) + goto out; + r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); + if (r) + goto out; + break; + } +#endif + } +out: + return r; +} + diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c12c95b1b64..38e4d2c34ac 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -53,12 +53,6 @@ #include "coalesced_mmio.h" #endif -#ifdef KVM_CAP_DEVICE_ASSIGNMENT -#include -#include -#include "irq.h" -#endif - #define CREATE_TRACE_POINTS #include @@ -90,608 +84,6 @@ static bool kvm_rebooting; static bool largepages_enabled = true; -#ifdef KVM_CAP_DEVICE_ASSIGNMENT -static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, - int assigned_dev_id) -{ - struct list_head *ptr; - struct kvm_assigned_dev_kernel *match; - - list_for_each(ptr, head) { - match = list_entry(ptr, struct kvm_assigned_dev_kernel, list); - if (match->assigned_dev_id == assigned_dev_id) - return match; - } - return NULL; -} - -static int find_index_from_host_irq(struct kvm_assigned_dev_kernel - *assigned_dev, int irq) -{ - int i, index; - struct msix_entry *host_msix_entries; - - host_msix_entries = assigned_dev->host_msix_entries; - - index = -1; - for (i = 0; i < assigned_dev->entries_nr; i++) - if (irq == host_msix_entries[i].vector) { - index = i; - break; - } - if (index < 0) { - printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n"); - return 0; - } - - return index; -} - -static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work) -{ - struct kvm_assigned_dev_kernel *assigned_dev; - struct kvm *kvm; - int i; - - assigned_dev = container_of(work, struct kvm_assigned_dev_kernel, - interrupt_work); - kvm = assigned_dev->kvm; - - spin_lock_irq(&assigned_dev->assigned_dev_lock); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - struct kvm_guest_msix_entry *guest_entries = - assigned_dev->guest_msix_entries; - for (i = 0; i < assigned_dev->entries_nr; i++) { - if (!(guest_entries[i].flags & - KVM_ASSIGNED_MSIX_PENDING)) - continue; - guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING; - kvm_set_irq(assigned_dev->kvm, - assigned_dev->irq_source_id, - guest_entries[i].vector, 1); - } - } else - kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id, - assigned_dev->guest_irq, 1); - - spin_unlock_irq(&assigned_dev->assigned_dev_lock); -} - -static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id) -{ - unsigned long flags; - struct kvm_assigned_dev_kernel *assigned_dev = - (struct kvm_assigned_dev_kernel *) dev_id; - - spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags); - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int index = find_index_from_host_irq(assigned_dev, irq); - if (index < 0) - goto out; - assigned_dev->guest_msix_entries[index].flags |= - KVM_ASSIGNED_MSIX_PENDING; - } - - schedule_work(&assigned_dev->interrupt_work); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) { - disable_irq_nosync(irq); - assigned_dev->host_irq_disabled = true; - } - -out: - spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags); - return IRQ_HANDLED; -} - -/* Ack the irq line for an assigned device */ -static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) -{ - struct kvm_assigned_dev_kernel *dev; - unsigned long flags; - - if (kian->gsi == -1) - return; - - dev = container_of(kian, struct kvm_assigned_dev_kernel, - ack_notifier); - - kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0); - - /* The guest irq may be shared so this ack may be - * from another device. - */ - spin_lock_irqsave(&dev->assigned_dev_lock, flags); - if (dev->host_irq_disabled) { - enable_irq(dev->host_irq); - dev->host_irq_disabled = false; - } - spin_unlock_irqrestore(&dev->assigned_dev_lock, flags); -} - -static void deassign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier); - assigned_dev->ack_notifier.gsi = -1; - - if (assigned_dev->irq_source_id != -1) - kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id); - assigned_dev->irq_source_id = -1; - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK); -} - -/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */ -static void deassign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - /* - * In kvm_free_device_irq, cancel_work_sync return true if: - * 1. work is scheduled, and then cancelled. - * 2. work callback is executed. - * - * The first one ensured that the irq is disabled and no more events - * would happen. But for the second one, the irq may be enabled (e.g. - * for MSI). So we disable irq here to prevent further events. - * - * Notice this maybe result in nested disable if the interrupt type is - * INTx, but it's OK for we are going to free it. - * - * If this function is a part of VM destroy, please ensure that till - * now, the kvm state is still legal for probably we also have to wait - * interrupt_work done. - */ - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) { - int i; - for (i = 0; i < assigned_dev->entries_nr; i++) - disable_irq_nosync(assigned_dev-> - host_msix_entries[i].vector); - - cancel_work_sync(&assigned_dev->interrupt_work); - - for (i = 0; i < assigned_dev->entries_nr; i++) - free_irq(assigned_dev->host_msix_entries[i].vector, - (void *)assigned_dev); - - assigned_dev->entries_nr = 0; - kfree(assigned_dev->host_msix_entries); - kfree(assigned_dev->guest_msix_entries); - pci_disable_msix(assigned_dev->dev); - } else { - /* Deal with MSI and INTx */ - disable_irq_nosync(assigned_dev->host_irq); - cancel_work_sync(&assigned_dev->interrupt_work); - - free_irq(assigned_dev->host_irq, (void *)assigned_dev); - - if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI) - pci_disable_msi(assigned_dev->dev); - } - - assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK); -} - -static int kvm_deassign_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev, - unsigned long irq_requested_type) -{ - unsigned long guest_irq_type, host_irq_type; - - if (!irqchip_in_kernel(kvm)) - return -EINVAL; - /* no irq assignment to deassign */ - if (!assigned_dev->irq_requested_type) - return -ENXIO; - - host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK; - guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK; - - if (host_irq_type) - deassign_host_irq(kvm, assigned_dev); - if (guest_irq_type) - deassign_guest_irq(kvm, assigned_dev); - - return 0; -} - -static void kvm_free_assigned_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *assigned_dev) -{ - kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type); -} - -static void kvm_free_assigned_device(struct kvm *kvm, - struct kvm_assigned_dev_kernel - *assigned_dev) -{ - kvm_free_assigned_irq(kvm, assigned_dev); - - pci_reset_function(assigned_dev->dev); - - pci_release_regions(assigned_dev->dev); - pci_disable_device(assigned_dev->dev); - pci_dev_put(assigned_dev->dev); - - list_del(&assigned_dev->list); - kfree(assigned_dev); -} - -void kvm_free_all_assigned_devices(struct kvm *kvm) -{ - struct list_head *ptr, *ptr2; - struct kvm_assigned_dev_kernel *assigned_dev; - - list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) { - assigned_dev = list_entry(ptr, - struct kvm_assigned_dev_kernel, - list); - - kvm_free_assigned_device(kvm, assigned_dev); - } -} - -static int assigned_device_enable_host_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - dev->host_irq = dev->dev->irq; - /* Even though this is PCI, we don't want to use shared - * interrupts. Sharing host devices with guest-assigned devices - * on the same interrupt line is not a happy situation: there - * are going to be long delays in accepting, acking, etc. - */ - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, - 0, "kvm_assigned_intx_device", (void *)dev)) - return -EIO; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_host_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int r; - - if (!dev->dev->msi_enabled) { - r = pci_enable_msi(dev->dev); - if (r) - return r; - } - - dev->host_irq = dev->dev->irq; - if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0, - "kvm_assigned_msi_device", (void *)dev)) { - pci_disable_msi(dev->dev); - return -EIO; - } - - return 0; -} -#endif - -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_host_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev) -{ - int i, r = -EINVAL; - - /* host_msix_entries and guest_msix_entries should have been - * initialized */ - if (dev->entries_nr == 0) - return r; - - r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr); - if (r) - return r; - - for (i = 0; i < dev->entries_nr; i++) { - r = request_irq(dev->host_msix_entries[i].vector, - kvm_assigned_dev_intr, 0, - "kvm_assigned_msix_device", - (void *)dev); - /* FIXME: free requested_irq's on failure */ - if (r) - return r; - } - - return 0; -} - -#endif - -static int assigned_device_enable_guest_intx(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = irq->guest_irq; - return 0; -} - -#ifdef __KVM_HAVE_MSI -static int assigned_device_enable_guest_msi(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; - return 0; -} -#endif -#ifdef __KVM_HAVE_MSIX -static int assigned_device_enable_guest_msix(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq) -{ - dev->guest_irq = irq->guest_irq; - dev->ack_notifier.gsi = -1; - dev->host_irq_disabled = false; - return 0; -} -#endif - -static int assign_host_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - __u32 host_irq_type) -{ - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK) - return r; - - switch (host_irq_type) { - case KVM_DEV_IRQ_HOST_INTX: - r = assigned_device_enable_host_intx(kvm, dev); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_HOST_MSI: - r = assigned_device_enable_host_msi(kvm, dev); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_HOST_MSIX: - r = assigned_device_enable_host_msix(kvm, dev); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) - dev->irq_requested_type |= host_irq_type; - - return r; -} - -static int assign_guest_irq(struct kvm *kvm, - struct kvm_assigned_dev_kernel *dev, - struct kvm_assigned_irq *irq, - unsigned long guest_irq_type) -{ - int id; - int r = -EEXIST; - - if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK) - return r; - - id = kvm_request_irq_source_id(kvm); - if (id < 0) - return id; - - dev->irq_source_id = id; - - switch (guest_irq_type) { - case KVM_DEV_IRQ_GUEST_INTX: - r = assigned_device_enable_guest_intx(kvm, dev, irq); - break; -#ifdef __KVM_HAVE_MSI - case KVM_DEV_IRQ_GUEST_MSI: - r = assigned_device_enable_guest_msi(kvm, dev, irq); - break; -#endif -#ifdef __KVM_HAVE_MSIX - case KVM_DEV_IRQ_GUEST_MSIX: - r = assigned_device_enable_guest_msix(kvm, dev, irq); - break; -#endif - default: - r = -EINVAL; - } - - if (!r) { - dev->irq_requested_type |= guest_irq_type; - kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier); - } else - kvm_free_irq_source_id(kvm, dev->irq_source_id); - - return r; -} - -/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */ -static int kvm_vm_ioctl_assign_irq(struct kvm *kvm, - struct kvm_assigned_irq *assigned_irq) -{ - int r = -EINVAL; - struct kvm_assigned_dev_kernel *match; - unsigned long host_irq_type, guest_irq_type; - - if (!capable(CAP_SYS_RAWIO)) - return -EPERM; - - if (!irqchip_in_kernel(kvm)) - return r; - - mutex_lock(&kvm->lock); - r = -ENODEV; - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK); - guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK); - - r = -EINVAL; - /* can only assign one type at a time */ - if (hweight_long(host_irq_type) > 1) - goto out; - if (hweight_long(guest_irq_type) > 1) - goto out; - if (host_irq_type == 0 && guest_irq_type == 0) - goto out; - - r = 0; - if (host_irq_type) - r = assign_host_irq(kvm, match, host_irq_type); - if (r) - goto out; - - if (guest_irq_type) - r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm, - struct kvm_assigned_irq - *assigned_irq) -{ - int r = -ENODEV; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_irq->assigned_dev_id); - if (!match) - goto out; - - r = kvm_deassign_irq(kvm, match, assigned_irq->flags); -out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_assign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - struct pci_dev *dev; - - down_read(&kvm->slots_lock); - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (match) { - /* device already assigned */ - r = -EEXIST; - goto out; - } - - match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL); - if (match == NULL) { - printk(KERN_INFO "%s: Couldn't allocate memory\n", - __func__); - r = -ENOMEM; - goto out; - } - dev = pci_get_bus_and_slot(assigned_dev->busnr, - assigned_dev->devfn); - if (!dev) { - printk(KERN_INFO "%s: host device not found\n", __func__); - r = -EINVAL; - goto out_free; - } - if (pci_enable_device(dev)) { - printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); - r = -EBUSY; - goto out_put; - } - r = pci_request_regions(dev, "kvm_assigned_device"); - if (r) { - printk(KERN_INFO "%s: Could not get access to device regions\n", - __func__); - goto out_disable; - } - - pci_reset_function(dev); - - match->assigned_dev_id = assigned_dev->assigned_dev_id; - match->host_busnr = assigned_dev->busnr; - match->host_devfn = assigned_dev->devfn; - match->flags = assigned_dev->flags; - match->dev = dev; - spin_lock_init(&match->assigned_dev_lock); - match->irq_source_id = -1; - match->kvm = kvm; - match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq; - INIT_WORK(&match->interrupt_work, - kvm_assigned_dev_interrupt_work_handler); - - list_add(&match->list, &kvm->arch.assigned_dev_head); - - if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match); - if (r) - goto out_list_del; - } - -out: - mutex_unlock(&kvm->lock); - up_read(&kvm->slots_lock); - return r; -out_list_del: - list_del(&match->list); - pci_release_regions(dev); -out_disable: - pci_disable_device(dev); -out_put: - pci_dev_put(dev); -out_free: - kfree(match); - mutex_unlock(&kvm->lock); - up_read(&kvm->slots_lock); - return r; -} -#endif - -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT -static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, - struct kvm_assigned_pci_dev *assigned_dev) -{ - int r = 0; - struct kvm_assigned_dev_kernel *match; - - mutex_lock(&kvm->lock); - - match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - assigned_dev->assigned_dev_id); - if (!match) { - printk(KERN_INFO "%s: device hasn't been assigned before, " - "so cannot be deassigned\n", __func__); - r = -EINVAL; - goto out; - } - - if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) - kvm_deassign_device(kvm, match); - - kvm_free_assigned_device(kvm, match); - -out: - mutex_unlock(&kvm->lock); - return r; -} -#endif - inline int kvm_is_mmio_pfn(pfn_t pfn) { if (pfn_valid(pfn)) { @@ -1824,88 +1216,6 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) return 0; } -#ifdef __KVM_HAVE_MSIX -static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, - struct kvm_assigned_msix_nr *entry_nr) -{ - int r = 0; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry_nr->assigned_dev_id); - if (!adev) { - r = -EINVAL; - goto msix_nr_out; - } - - if (adev->entries_nr == 0) { - adev->entries_nr = entry_nr->entry_nr; - if (adev->entries_nr == 0 || - adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) { - r = -EINVAL; - goto msix_nr_out; - } - - adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) * - entry_nr->entry_nr, - GFP_KERNEL); - if (!adev->host_msix_entries) { - r = -ENOMEM; - goto msix_nr_out; - } - adev->guest_msix_entries = kzalloc( - sizeof(struct kvm_guest_msix_entry) * - entry_nr->entry_nr, GFP_KERNEL); - if (!adev->guest_msix_entries) { - kfree(adev->host_msix_entries); - r = -ENOMEM; - goto msix_nr_out; - } - } else /* Not allowed set MSI-X number twice */ - r = -EINVAL; -msix_nr_out: - mutex_unlock(&kvm->lock); - return r; -} - -static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm, - struct kvm_assigned_msix_entry *entry) -{ - int r = 0, i; - struct kvm_assigned_dev_kernel *adev; - - mutex_lock(&kvm->lock); - - adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head, - entry->assigned_dev_id); - - if (!adev) { - r = -EINVAL; - goto msix_entry_out; - } - - for (i = 0; i < adev->entries_nr; i++) - if (adev->guest_msix_entries[i].vector == 0 || - adev->guest_msix_entries[i].entry == entry->entry) { - adev->guest_msix_entries[i].entry = entry->entry; - adev->guest_msix_entries[i].vector = entry->gsi; - adev->host_msix_entries[i].entry = entry->entry; - break; - } - if (i == adev->entries_nr) { - r = -ENOSPC; - goto msix_entry_out; - } - -msix_entry_out: - mutex_unlock(&kvm->lock); - - return r; -} -#endif - static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2163,112 +1473,6 @@ static long kvm_vm_ioctl(struct file *filp, r = 0; break; } -#endif -#ifdef KVM_CAP_DEVICE_ASSIGNMENT - case KVM_ASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } - case KVM_ASSIGN_IRQ: { - r = -EOPNOTSUPP; - break; - } -#ifdef KVM_CAP_ASSIGN_DEV_IRQ - case KVM_ASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } - case KVM_DEASSIGN_DEV_IRQ: { - struct kvm_assigned_irq assigned_irq; - - r = -EFAULT; - if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq)) - goto out; - r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq); - if (r) - goto out; - break; - } -#endif -#endif -#ifdef KVM_CAP_DEVICE_DEASSIGNMENT - case KVM_DEASSIGN_PCI_DEVICE: { - struct kvm_assigned_pci_dev assigned_dev; - - r = -EFAULT; - if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev)) - goto out; - r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev); - if (r) - goto out; - break; - } -#endif -#ifdef KVM_CAP_IRQ_ROUTING - case KVM_SET_GSI_ROUTING: { - struct kvm_irq_routing routing; - struct kvm_irq_routing __user *urouting; - struct kvm_irq_routing_entry *entries; - - r = -EFAULT; - if (copy_from_user(&routing, argp, sizeof(routing))) - goto out; - r = -EINVAL; - if (routing.nr >= KVM_MAX_IRQ_ROUTES) - goto out; - if (routing.flags) - goto out; - r = -ENOMEM; - entries = vmalloc(routing.nr * sizeof(*entries)); - if (!entries) - goto out; - r = -EFAULT; - urouting = argp; - if (copy_from_user(entries, urouting->entries, - routing.nr * sizeof(*entries))) - goto out_free_irq_routing; - r = kvm_set_irq_routing(kvm, entries, routing.nr, - routing.flags); - out_free_irq_routing: - vfree(entries); - break; - } -#endif /* KVM_CAP_IRQ_ROUTING */ -#ifdef __KVM_HAVE_MSIX - case KVM_ASSIGN_SET_MSIX_NR: { - struct kvm_assigned_msix_nr entry_nr; - r = -EFAULT; - if (copy_from_user(&entry_nr, argp, sizeof entry_nr)) - goto out; - r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr); - if (r) - goto out; - break; - } - case KVM_ASSIGN_SET_MSIX_ENTRY: { - struct kvm_assigned_msix_entry entry; - r = -EFAULT; - if (copy_from_user(&entry, argp, sizeof entry)) - goto out; - r = kvm_vm_ioctl_set_msix_entry(kvm, &entry); - if (r) - goto out; - break; - } #endif case KVM_IRQFD: { struct kvm_irqfd data; @@ -2301,6 +1505,8 @@ static long kvm_vm_ioctl(struct file *filp, #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); + if (r == -ENOTTY) + r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } out: return r; From 94677e61fdcf4cdae11a1b7c8974d7034ef9bd1b Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Fri, 28 Aug 2009 16:41:44 +0200 Subject: [PATCH 20/84] KVM: x86 emulator: Add missing decoder flags for 'or' instructions Add missing decoder flags for or instructions (0xc-0xd). Signed-off-by: Mohammed Gamal Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0644d3df621..db0820dfbff 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -99,7 +99,8 @@ static u32 opcode_table[256] = { /* 0x08 - 0x0F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, ImplicitOps | Stack | No64, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, 0, /* 0x10 - 0x17 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, From abcf14b560a4ba62c659e6f5aafc8f9934d8c130 Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Tue, 1 Sep 2009 15:28:11 +0200 Subject: [PATCH 21/84] KVM: x86 emulator: Add pusha and popa instructions This adds pusha and popa instructions (opcodes 0x60-0x61), this enables booting MINIX with invalid guest state emulation on. [marcelo: remove unused variable] Signed-off-by: Mohammed Gamal Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/emulate.c | 48 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index db0820dfbff..d226dff47d7 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -139,7 +139,8 @@ static u32 opcode_table[256] = { DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, /* 0x60 - 0x67 */ - 0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, + 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , 0, 0, 0, 0, /* 0x68 - 0x6F */ SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0, @@ -1225,6 +1226,43 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, return rc; } +static void emulate_pusha(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + unsigned long old_esp = c->regs[VCPU_REGS_RSP]; + int reg = VCPU_REGS_RAX; + + while (reg <= VCPU_REGS_RDI) { + (reg == VCPU_REGS_RSP) ? + (c->src.val = old_esp) : (c->src.val = c->regs[reg]); + + emulate_push(ctxt); + ++reg; + } +} + +static int emulate_popa(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc = 0; + int reg = VCPU_REGS_RDI; + + while (reg >= VCPU_REGS_RAX) { + if (reg == VCPU_REGS_RSP) { + register_address_increment(c, &c->regs[VCPU_REGS_RSP], + c->op_bytes); + --reg; + } + + rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); + if (rc != 0) + break; + --reg; + } + return rc; +} + static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1816,6 +1854,14 @@ special_insn: if (rc != 0) goto done; break; + case 0x60: /* pusha */ + emulate_pusha(ctxt); + break; + case 0x61: /* popa */ + rc = emulate_popa(ctxt, ops); + if (rc != 0) + goto done; + break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) goto cannot_emulate; From 80ced186d1761d2a66163d9eeb468ddb1f7e0697 Mon Sep 17 00:00:00 2001 From: Mohammed Gamal Date: Tue, 1 Sep 2009 12:48:18 +0200 Subject: [PATCH 22/84] KVM: VMX: Enhance invalid guest state emulation - Change returned handle_invalid_guest_state() to return relevant exit codes - Move triggering the emulation from vmx_vcpu_run() to vmx_handle_exit() - Return to userspace instead of repeatedly trying to emulate instructions that have already failed Signed-off-by: Mohammed Gamal Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/vmx.c | 44 ++++++++++++++++++++------------------------ 1 file changed, 20 insertions(+), 24 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4635298d000..73cb5dd960c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -107,7 +107,6 @@ struct vcpu_vmx { } rmode; int vpid; bool emulation_required; - enum emulation_result invalid_state_emulation_result; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; @@ -3322,35 +3321,37 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu) return 1; } -static void handle_invalid_guest_state(struct kvm_vcpu *vcpu) +static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); enum emulation_result err = EMULATE_DONE; - - local_irq_enable(); - preempt_enable(); + int ret = 1; while (!guest_state_valid(vcpu)) { err = emulate_instruction(vcpu, 0, 0, 0); - if (err == EMULATE_DO_MMIO) - break; + if (err == EMULATE_DO_MMIO) { + ret = 0; + goto out; + } if (err != EMULATE_DONE) { kvm_report_emulation_failure(vcpu, "emulation failure"); - break; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + ret = 0; + goto out; } if (signal_pending(current)) - break; + goto out; if (need_resched()) schedule(); } - preempt_disable(); - local_irq_disable(); - - vmx->invalid_state_emulation_result = err; + vmx->emulation_required = 0; +out: + return ret; } /* @@ -3406,13 +3407,9 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) trace_kvm_exit(exit_reason, kvm_rip_read(vcpu)); - /* If we need to emulate an MMIO from handle_invalid_guest_state - * we just return 0 */ - if (vmx->emulation_required && emulate_invalid_guest_state) { - if (guest_state_valid(vcpu)) - vmx->emulation_required = 0; - return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO; - } + /* If guest state is invalid, start emulating */ + if (vmx->emulation_required && emulate_invalid_guest_state) + return handle_invalid_guest_state(vcpu); /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ @@ -3607,11 +3604,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); - /* Handle invalid guest state instead of entering VMX */ - if (vmx->emulation_required && emulate_invalid_guest_state) { - handle_invalid_guest_state(vcpu); + /* Don't enter VMX if guest state is invalid, let the exit handler + start emulation until we arrive back to a valid state */ + if (vmx->emulation_required && emulate_invalid_guest_state) return; - } if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); From e8b3433a5c062e94e34cadb6144c10689a497bc3 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Tue, 8 Sep 2009 14:47:38 -0300 Subject: [PATCH 23/84] KVM: SVM: remove needless mmap_sem acquision from nested_svm_map nested_svm_map unnecessarily takes mmap_sem around gfn_to_page, since gfn_to_page / get_user_pages are responsible for it. Signed-off-by: Marcelo Tosatti Acked-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/x86/kvm/svm.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 92048a626d4..f54c4f9d286 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1396,10 +1396,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) { struct page *page; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); - if (is_error_page(page)) goto error; From 10474ae8945ce08622fd1f3464e55bd817bf2376 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Tue, 15 Sep 2009 11:37:46 +0200 Subject: [PATCH 24/84] KVM: Activate Virtualization On Demand 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: Alexander Graf Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/ia64/kvm/kvm-ia64.c | 8 +-- arch/powerpc/kvm/powerpc.c | 3 +- arch/s390/kvm/kvm-s390.c | 3 +- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm.c | 13 +++-- arch/x86/kvm/vmx.c | 11 ++-- arch/x86/kvm/x86.c | 4 +- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 90 ++++++++++++++++++++++++++++----- 9 files changed, 108 insertions(+), 28 deletions(-) diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index f6471c88266..5fdeec5fddc 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -124,7 +124,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler) static DEFINE_SPINLOCK(vp_lock); -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { long status; long tmp_base; @@ -137,7 +137,7 @@ void kvm_arch_hardware_enable(void *garbage) slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT); local_irq_restore(saved_psr); if (slot < 0) - return; + return -EINVAL; spin_lock(&vp_lock); status = ia64_pal_vp_init_env(kvm_vsa_base ? @@ -145,7 +145,7 @@ void kvm_arch_hardware_enable(void *garbage) __pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base); if (status != 0) { printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n"); - return ; + return -EINVAL; } if (!kvm_vsa_base) { @@ -154,6 +154,8 @@ void kvm_arch_hardware_enable(void *garbage) } spin_unlock(&vp_lock); ia64_ptr_entry(0x3, slot); + + return 0; } void kvm_arch_hardware_disable(void *garbage) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 95af62217b6..5902bbc2411 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -78,8 +78,9 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu) return r; } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { + return 0; } void kvm_arch_hardware_disable(void *garbage) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 00e2ce8e91f..544505893c9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -74,9 +74,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { static unsigned long long *facilities; /* Section: not file related */ -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { /* every s390 is virtualization enabled ;-) */ + return 0; } void kvm_arch_hardware_disable(void *garbage) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a46e2dd9aca..295c7c4d9c9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -459,7 +459,7 @@ struct descriptor_table { struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ - void (*hardware_enable)(void *dummy); /* __init */ + int (*hardware_enable)(void *dummy); void (*hardware_disable)(void *dummy); void (*check_processor_compatibility)(void *rtn); int (*hardware_setup)(void); /* __init */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f54c4f9d286..59fe4d54da1 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -316,7 +316,7 @@ static void svm_hardware_disable(void *garbage) cpu_svm_disable(); } -static void svm_hardware_enable(void *garbage) +static int svm_hardware_enable(void *garbage) { struct svm_cpu_data *svm_data; @@ -325,16 +325,20 @@ static void svm_hardware_enable(void *garbage) struct desc_struct *gdt; int me = raw_smp_processor_id(); + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) + return -EBUSY; + if (!has_svm()) { printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); - return; + return -EINVAL; } svm_data = per_cpu(svm_data, me); if (!svm_data) { printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", me); - return; + return -EINVAL; } svm_data->asid_generation = 1; @@ -345,11 +349,12 @@ static void svm_hardware_enable(void *garbage) gdt = (struct desc_struct *)gdt_descr.base; svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); - rdmsrl(MSR_EFER, efer); wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); + + return 0; } static void svm_cpu_uninit(int cpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 73cb5dd960c..a187570e483 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1138,12 +1138,15 @@ static __init int vmx_disabled_by_bios(void) /* locked but not enabled */ } -static void hardware_enable(void *garbage) +static int hardware_enable(void *garbage) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); u64 old; + if (read_cr4() & X86_CR4_VMXE) + return -EBUSY; + INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); if ((old & (FEATURE_CONTROL_LOCKED | @@ -1158,6 +1161,10 @@ static void hardware_enable(void *garbage) asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) : "memory", "cc"); + + ept_sync_global(); + + return 0; } static void vmclear_local_vcpus(void) @@ -4040,8 +4047,6 @@ static int __init vmx_init(void) if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); - ept_sync_global(); - return 0; out3: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 829e3063e2a..3d83de8bcbf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4691,9 +4691,9 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) return kvm_x86_ops->vcpu_reset(vcpu); } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { - kvm_x86_ops->hardware_enable(garbage); + return kvm_x86_ops->hardware_enable(garbage); } void kvm_arch_hardware_disable(void *garbage) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c0a1cc35f08..b985a29d817 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -345,7 +345,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu); -void kvm_arch_hardware_enable(void *garbage); +int kvm_arch_hardware_enable(void *garbage); void kvm_arch_hardware_disable(void *garbage); int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 38e4d2c34ac..70c8cbea0a9 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -69,6 +69,8 @@ DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; +static int kvm_usage_count = 0; +static atomic_t hardware_enable_failed; struct kmem_cache *kvm_vcpu_cache; EXPORT_SYMBOL_GPL(kvm_vcpu_cache); @@ -79,6 +81,8 @@ struct dentry *kvm_debugfs_dir; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); +static int hardware_enable_all(void); +static void hardware_disable_all(void); static bool kvm_rebooting; @@ -339,6 +343,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { static struct kvm *kvm_create_vm(void) { + int r = 0; struct kvm *kvm = kvm_arch_create_vm(); #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET struct page *page; @@ -346,6 +351,11 @@ static struct kvm *kvm_create_vm(void) if (IS_ERR(kvm)) goto out; + + r = hardware_enable_all(); + if (r) + goto out_err_nodisable; + #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); @@ -354,8 +364,8 @@ static struct kvm *kvm_create_vm(void) #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { - kfree(kvm); - return ERR_PTR(-ENOMEM); + r = -ENOMEM; + goto out_err; } kvm->coalesced_mmio_ring = (struct kvm_coalesced_mmio_ring *)page_address(page); @@ -363,15 +373,13 @@ static struct kvm *kvm_create_vm(void) #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) { - int err; kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; - err = mmu_notifier_register(&kvm->mmu_notifier, current->mm); - if (err) { + r = mmu_notifier_register(&kvm->mmu_notifier, current->mm); + if (r) { #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET put_page(page); #endif - kfree(kvm); - return ERR_PTR(err); + goto out_err; } } #endif @@ -395,6 +403,12 @@ static struct kvm *kvm_create_vm(void) #endif out: return kvm; + +out_err: + hardware_disable_all(); +out_err_nodisable: + kfree(kvm); + return ERR_PTR(r); } /* @@ -453,6 +467,7 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); + hardware_disable_all(); mmdrop(mm); } @@ -1644,11 +1659,21 @@ static struct miscdevice kvm_dev = { static void hardware_enable(void *junk) { int cpu = raw_smp_processor_id(); + int r; if (cpumask_test_cpu(cpu, cpus_hardware_enabled)) return; + cpumask_set_cpu(cpu, cpus_hardware_enabled); - kvm_arch_hardware_enable(NULL); + + r = kvm_arch_hardware_enable(NULL); + + if (r) { + cpumask_clear_cpu(cpu, cpus_hardware_enabled); + atomic_inc(&hardware_enable_failed); + printk(KERN_INFO "kvm: enabling virtualization on " + "CPU%d failed\n", cpu); + } } static void hardware_disable(void *junk) @@ -1661,11 +1686,52 @@ static void hardware_disable(void *junk) kvm_arch_hardware_disable(NULL); } +static void hardware_disable_all_nolock(void) +{ + BUG_ON(!kvm_usage_count); + + kvm_usage_count--; + if (!kvm_usage_count) + on_each_cpu(hardware_disable, NULL, 1); +} + +static void hardware_disable_all(void) +{ + spin_lock(&kvm_lock); + hardware_disable_all_nolock(); + spin_unlock(&kvm_lock); +} + +static int hardware_enable_all(void) +{ + int r = 0; + + spin_lock(&kvm_lock); + + kvm_usage_count++; + if (kvm_usage_count == 1) { + atomic_set(&hardware_enable_failed, 0); + on_each_cpu(hardware_enable, NULL, 1); + + if (atomic_read(&hardware_enable_failed)) { + hardware_disable_all_nolock(); + r = -EBUSY; + } + } + + spin_unlock(&kvm_lock); + + return r; +} + static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, void *v) { int cpu = (long)v; + if (!kvm_usage_count) + return NOTIFY_OK; + val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: @@ -1868,13 +1934,15 @@ static void kvm_exit_debug(void) static int kvm_suspend(struct sys_device *dev, pm_message_t state) { - hardware_disable(NULL); + if (kvm_usage_count) + hardware_disable(NULL); return 0; } static int kvm_resume(struct sys_device *dev) { - hardware_enable(NULL); + if (kvm_usage_count) + hardware_enable(NULL); return 0; } @@ -1949,7 +2017,6 @@ int kvm_init(void *opaque, unsigned int vcpu_size, goto out_free_1; } - on_each_cpu(hardware_enable, NULL, 1); r = register_cpu_notifier(&kvm_cpu_notifier); if (r) goto out_free_2; @@ -1999,7 +2066,6 @@ out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); out_free_2: - on_each_cpu(hardware_disable, NULL, 1); out_free_1: kvm_arch_hardware_unsetup(); out_free_0a: From bfc33beaed3ecf0f92612dc7fb7095029ae7722e Mon Sep 17 00:00:00 2001 From: Huang Weiyi Date: Wed, 16 Sep 2009 21:09:39 +0800 Subject: [PATCH 25/84] KVM: remove duplicated #include Remove duplicated #include('s) in arch/x86/kvm/lapic.c Signed-off-by: Huang Weiyi Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/lapic.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 8787637b1a9..cd60c0bd1b3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -32,7 +32,6 @@ #include #include #include -#include #include "kvm_cache_regs.h" #include "irq.h" #include "trace.h" From 7fcdb5103d10d2eb75876637a2efa9679cce14d3 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 16 Sep 2009 15:24:15 +0200 Subject: [PATCH 26/84] KVM: SVM: reorganize svm_interrupt_allowed This patch reorganizes the logic in svm_interrupt_allowed to make it better to read. This is important because the logic is a lot more complicated with Nested SVM. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 59fe4d54da1..3f3fe815c21 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2472,10 +2472,18 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - return (vmcb->save.rflags & X86_EFLAGS_IF) && - !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - gif_set(svm) && - !(is_nested(svm) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)); + int ret; + + if (!gif_set(svm) || + (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) + return 0; + + ret = !!(vmcb->save.rflags & X86_EFLAGS_IF); + + if (is_nested(svm)) + return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); + + return ret; } static void enable_irq_window(struct kvm_vcpu *vcpu) From 33527ad7e12a5cb50b39165945464600ab2f7632 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 16 Sep 2009 15:24:16 +0200 Subject: [PATCH 27/84] KVM: SVM: don't copy exit_int_info on nested vmrun The exit_int_info field is only written by the hardware and never read. So it does not need to be copied on a vmrun emulation. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3f3fe815c21..41c996ab87e 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1797,8 +1797,6 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->nested.intercept = nested_vmcb->control.intercept; force_new_asid(&svm->vcpu); - svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info; - svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err; svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; if (nested_vmcb->control.int_ctl & V_IRQ_MASK) { nsvm_printk("nSVM Injecting Interrupt: 0x%x\n", From e935d48e1b49451490218e1181d9834176200955 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 16 Sep 2009 15:24:19 +0200 Subject: [PATCH 28/84] KVM: SVM: Remove remaining occurences of rdtscll This patch replaces them with native_read_tsc() which can also be used in expressions and saves a variable on the stack in this case. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 41c996ab87e..9a4dacab6d8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -763,14 +763,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) int i; if (unlikely(cpu != vcpu->cpu)) { - u64 tsc_this, delta; + u64 delta; /* * Make sure that the guest sees a monotonically * increasing TSC. */ - rdtscll(tsc_this); - delta = vcpu->arch.host_tsc - tsc_this; + delta = vcpu->arch.host_tsc - native_read_tsc(); svm->vmcb->control.tsc_offset += delta; if (is_nested(svm)) svm->nested.hsave->control.tsc_offset += delta; @@ -792,7 +791,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - rdtscll(vcpu->arch.host_tsc); + vcpu->arch.host_tsc = native_read_tsc(); } static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) From 0c6ddcebd8303ada6faefa6f72ac18b6230320c4 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 25 Sep 2009 09:33:38 +0200 Subject: [PATCH 29/84] KVM: fix lock imbalance in kvm_*_irq_source_id() 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: Jiri Slaby Cc: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 15a83b93566..00c68d29857 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -220,11 +220,13 @@ int kvm_request_irq_source_id(struct kvm *kvm) if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); - return -EFAULT; + irq_source_id = -EFAULT; + goto unlock; } ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID); set_bit(irq_source_id, bitmap); +unlock: mutex_unlock(&kvm->irq_lock); return irq_source_id; @@ -240,7 +242,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) if (irq_source_id < 0 || irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); - return; + goto unlock; } for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); @@ -251,6 +253,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) #endif } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); +unlock: mutex_unlock(&kvm->irq_lock); } From b820cc0ca20fdcf8014d8e57421cf29095e39392 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Tue, 29 Sep 2009 11:38:34 -1000 Subject: [PATCH 30/84] KVM: Separate timer intialization into an indepedent function Signed-off-by: Zachary Amsden Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3d83de8bcbf..6a31dfb8849 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3118,9 +3118,22 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = { .notifier_call = kvmclock_cpufreq_notifier }; +static void kvm_timer_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + tsc_khz_ref = tsc_khz; + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + } +} + int kvm_arch_init(void *opaque) { - int r, cpu; + int r; struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; if (kvm_x86_ops) { @@ -3152,13 +3165,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); - for_each_possible_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { - tsc_khz_ref = tsc_khz; - cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); - } + kvm_timer_init(); return 0; From 0cca790753bf0cab4b070801a46df8e1297c17f6 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Tue, 29 Sep 2009 11:38:35 -1000 Subject: [PATCH 31/84] KVM: Kill the confusing tsc_ref_khz and ref_freq variables They are globals, not clearly protected by any ordering or locking, and vulnerable to various startup races. Instead, for variable TSC machines, register the cpufreq notifier and get the TSC frequency directly from the cpufreq machinery. Not only is it always right, it is also perfectly accurate, as no error prone measurement is required. On such machines, when a new CPU online is brought online, it isn't clear what frequency it will start with, and it may not correspond to the reference, thus in hardware_enable we clear the cpu_tsc_khz variable to zero and make sure it is set before running on a VCPU. Signed-off-by: Zachary Amsden Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6a31dfb8849..6f758567831 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1326,6 +1326,8 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); + if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) + per_cpu(cpu_tsc_khz, cpu) = cpufreq_quick_get(cpu); kvm_request_guest_time_update(vcpu); } @@ -3063,9 +3065,6 @@ static void bounce_off(void *info) /* nothing */ } -static unsigned int ref_freq; -static unsigned long tsc_khz_ref; - static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -3074,14 +3073,11 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va struct kvm_vcpu *vcpu; int i, send_ipi = 0; - if (!ref_freq) - ref_freq = freq->old; - if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) return 0; if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) return 0; - per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); + per_cpu(cpu_tsc_khz, freq->cpu) = freq->new; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { @@ -3122,12 +3118,14 @@ static void kvm_timer_init(void) { int cpu; - for_each_possible_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { - tsc_khz_ref = tsc_khz; cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); + for_each_online_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = cpufreq_get(cpu); + } else { + for_each_possible_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; } } @@ -4700,6 +4698,14 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) int kvm_arch_hardware_enable(void *garbage) { + /* + * Since this may be called from a hotplug notifcation, + * we can't get the CPU frequency directly. + */ + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + int cpu = raw_smp_processor_id(); + per_cpu(cpu_tsc_khz, cpu) = 0; + } return kvm_x86_ops->hardware_enable(garbage); } From e6732a5af9dfcc87078706a1598df0efe5010f73 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Tue, 29 Sep 2009 11:38:36 -1000 Subject: [PATCH 32/84] KVM: Fix printk name error in svm.c Signed-off-by: Zachary Amsden Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 9a4dacab6d8..d1036ce8917 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -330,13 +330,14 @@ static int svm_hardware_enable(void *garbage) return -EBUSY; if (!has_svm()) { - printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); + printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n", + me); return -EINVAL; } svm_data = per_cpu(svm_data, me); if (!svm_data) { - printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", + printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n", me); return -EINVAL; } From 3230bb4707278dba25e24cd0a11ea7b2337678ee Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Tue, 29 Sep 2009 11:38:37 -1000 Subject: [PATCH 33/84] KVM: Fix hotplug of CPUs Both VMX and SVM require per-cpu memory allocation, which is done at module init time, for only online cpus. Backend was not allocating enough structure for all possible CPUs, so new CPUs coming online could not be hardware enabled. Signed-off-by: Zachary Amsden Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 4 ++-- arch/x86/kvm/vmx.c | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d1036ce8917..02a4269be64 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -482,7 +482,7 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_SVME); } - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) goto err; @@ -516,7 +516,7 @@ static __exit void svm_hardware_unsetup(void) { int cpu; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a187570e483..97f4265cda3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1350,15 +1350,17 @@ static void free_kvm_area(void) { int cpu; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) { free_vmcs(per_cpu(vmxarea, cpu)); + per_cpu(vmxarea, cpu) = NULL; + } } static __init int alloc_kvm_area(void) { int cpu; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { struct vmcs *vmcs; vmcs = alloc_vmcs_cpu(cpu); From 201d945bcfb0d53e67c9c081f7c28532eb4669c7 Mon Sep 17 00:00:00 2001 From: Juan Quintela Date: Wed, 30 Sep 2009 17:39:07 +0200 Subject: [PATCH 34/84] KVM: remove pre_task_link setting in save_state_to_tss16 Now, also remove pre_task_link setting in save_state_to_tss16. commit b237ac37a149e8b56436fabf093532483bff13b0 Author: Gleb Natapov Date: Mon Mar 30 16:03:24 2009 +0300 KVM: Fix task switch back link handling. CC: Gleb Natapov Signed-off-by: Juan Quintela Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6f758567831..5f44d565cc9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4203,7 +4203,6 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); - tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR); } static int load_state_from_tss16(struct kvm_vcpu *vcpu, From 355be0b9300579e02275d7d19374806a974ce622 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sat, 3 Oct 2009 00:31:21 +0200 Subject: [PATCH 35/84] KVM: x86: Refactor guest debug IOCTL handling Much of so far vendor-specific code for setting up guest debug can actually be handled by the generic code. This also fixes a minor deficit in the SVM part /wrt processing KVM_GUESTDBG_ENABLE. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 4 ++-- arch/x86/kvm/svm.c | 14 ++------------ arch/x86/kvm/vmx.c | 18 +----------------- arch/x86/kvm/x86.c | 28 +++++++++++++++++++++------- 4 files changed, 26 insertions(+), 38 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 295c7c4d9c9..e7f87083260 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -475,8 +475,8 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); - int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg); + void (*set_guest_debug)(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 02a4269be64..279a2ae21b4 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1065,26 +1065,16 @@ static void update_db_intercept(struct kvm_vcpu *vcpu) vcpu->guest_debug = 0; } -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int old_debug = vcpu->guest_debug; struct vcpu_svm *svm = to_svm(vcpu); - vcpu->guest_debug = dbg->control; - - update_db_intercept(vcpu); - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) svm->vmcb->save.dr7 = dbg->arch.debugreg[7]; else svm->vmcb->save.dr7 = vcpu->arch.dr7; - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - - return 0; + update_db_intercept(vcpu); } static void load_host_msrs(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 97f4265cda3..70020e505c2 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1096,30 +1096,14 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int old_debug = vcpu->guest_debug; - unsigned long flags; - - vcpu->guest_debug = dbg->control; - if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) - vcpu->guest_debug = 0; - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]); else vmcs_writel(GUEST_DR7, vcpu->arch.dr7); - flags = vmcs_readl(GUEST_RFLAGS); - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - vmcs_writel(GUEST_RFLAGS, flags); - update_exception_bitmap(vcpu); - - return 0; } static __init int cpu_has_kvm_support(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5f44d565cc9..a06f88e66c8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4472,12 +4472,19 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int i, r; + unsigned long rflags; + int old_debug; + int i; vcpu_load(vcpu); - if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) { + old_debug = vcpu->guest_debug; + + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { for (i = 0; i < KVM_NR_DB_REGS; ++i) vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; vcpu->arch.switch_db_regs = @@ -4488,16 +4495,23 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + else if (old_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + kvm_x86_ops->set_rflags(vcpu, rflags); - if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_x86_ops->set_guest_debug(vcpu, dbg); + + if (vcpu->guest_debug & KVM_GUESTDBG_INJECT_DB) kvm_queue_exception(vcpu, DB_VECTOR); - else if (dbg->control & KVM_GUESTDBG_INJECT_BP) + else if (vcpu->guest_debug & KVM_GUESTDBG_INJECT_BP) kvm_queue_exception(vcpu, BP_VECTOR); vcpu_put(vcpu); - return r; + return 0; } /* From a68a6a7282373bedba8a2ed751b6384edb983a64 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 1 Oct 2009 19:28:39 -0300 Subject: [PATCH 36/84] KVM: x86: disable paravirt mmu reporting Disable paravirt MMU capability reporting, so that new (or rebooted) guests switch to native operation. Paravirt MMU is a burden to maintain and does not bring significant advantages compared to shadow anymore. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a06f88e66c8..4693f915f3b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1238,8 +1238,8 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_NR_MEMSLOTS: r = KVM_MEMORY_SLOTS; break; - case KVM_CAP_PV_MMU: - r = !tdp_enabled; + case KVM_CAP_PV_MMU: /* obsolete */ + r = 0; break; case KVM_CAP_IOMMU: r = iommu_found(); From 91586a3b7d79432772a3cdcb81473cd08a237c79 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 5 Oct 2009 13:07:21 +0200 Subject: [PATCH 37/84] KVM: x86: Rework guest single-step flag injection and filtering Push TF and RF injection and filtering on guest single-stepping into the vender get/set_rflags callbacks. This makes the whole mechanism more robust wrt user space IOCTL order and instruction emulations. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 3 ++ arch/x86/kvm/x86.c | 77 +++++++++++++++++++-------------- 2 files changed, 48 insertions(+), 32 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e7f87083260..179a919f53a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -614,6 +614,9 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); + void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4693f915f3b..385cd0a1e23 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -235,6 +235,25 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) } EXPORT_SYMBOL_GPL(kvm_require_cpl); +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_x86_ops->set_rflags(vcpu, rflags); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + /* * Load the pae pdptrs. Return true is they are all valid. */ @@ -2777,7 +2796,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); vcpu->arch.emulate_ctxt.mode = (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_REAL : cs_l @@ -2855,7 +2874,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); if (vcpu->mmio_is_write) { vcpu->mmio_needed = 0; @@ -3291,7 +3310,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long *rflags) { kvm_lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); } unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) @@ -3329,7 +3348,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, switch (cr) { case 0: kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); break; case 2: vcpu->arch.cr2 = val; @@ -3460,7 +3479,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) @@ -3840,13 +3859,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) #endif regs->rip = kvm_rip_read(vcpu); - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + regs->rflags = kvm_get_rflags(vcpu); vcpu_put(vcpu); @@ -3874,12 +3887,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); - #endif kvm_rip_write(vcpu, regs->rip); - kvm_x86_ops->set_rflags(vcpu, regs->rflags); - + kvm_set_rflags(vcpu, regs->rflags); vcpu->arch.exception.pending = false; @@ -4098,7 +4109,7 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) { return (seg != VCPU_SREG_LDTR) && (seg != VCPU_SREG_TR) && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM); + (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); } int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, @@ -4126,7 +4137,7 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu, { tss->cr3 = vcpu->arch.cr3; tss->eip = kvm_rip_read(vcpu); - tss->eflags = kvm_x86_ops->get_rflags(vcpu); + tss->eflags = kvm_get_rflags(vcpu); tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4150,7 +4161,7 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu, kvm_set_cr3(vcpu, tss->cr3); kvm_rip_write(vcpu, tss->eip); - kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2); + kvm_set_rflags(vcpu, tss->eflags | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); @@ -4188,7 +4199,7 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { tss->ip = kvm_rip_read(vcpu); - tss->flag = kvm_x86_ops->get_rflags(vcpu); + tss->flag = kvm_get_rflags(vcpu); tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4209,7 +4220,7 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { kvm_rip_write(vcpu, tss->ip); - kvm_x86_ops->set_rflags(vcpu, tss->flag | 2); + kvm_set_rflags(vcpu, tss->flag | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); @@ -4355,8 +4366,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); } /* set back link to prev task only if NT bit is set in eflags @@ -4377,8 +4388,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) old_tss_base, &nseg_desc); if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); } if (reason != TASK_SWITCH_IRET) { @@ -4473,12 +4484,15 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { unsigned long rflags; - int old_debug; int i; vcpu_load(vcpu); - old_debug = vcpu->guest_debug; + /* + * Read rflags as long as potentially injected trace flags are still + * filtered out. + */ + rflags = kvm_get_rflags(vcpu); vcpu->guest_debug = dbg->control; if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) @@ -4495,12 +4509,11 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - rflags = kvm_x86_ops->get_rflags(vcpu); - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - kvm_x86_ops->set_rflags(vcpu, rflags); + /* + * Trigger an rflags update that will inject or remove the trace + * flags. + */ + kvm_set_rflags(vcpu, rflags); kvm_x86_ops->set_guest_debug(vcpu, dbg); From e3267cbbbfbcbe9c18833e89b10beabb1117cb55 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Tue, 6 Oct 2009 13:24:50 -0400 Subject: [PATCH 38/84] KVM: x86: include pvclock MSRs in msrs_to_save For a while now, we are issuing a rdmsr instruction to find out which msrs in our save list are really supported by the underlying machine. However, it fails to account for kvm-specific msrs, such as the pvclock ones. This patch moves then to the beginning of the list, and skip testing them. Cc: stable@kernel.org Signed-off-by: Glauber Costa Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 385cd0a1e23..4de5bc0a8e8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -503,16 +503,19 @@ static inline u32 bit(int bitno) * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * * This list is modified at module load time to reflect the - * capabilities of the host cpu. + * capabilities of the host cpu. This capabilities test skips MSRs that are + * kvm-specific. Those are put in the beginning of the list. */ + +#define KVM_SAVE_MSRS_BEGIN 2 static u32 msrs_to_save[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_K6_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA + MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; static unsigned num_msrs_to_save; @@ -2446,7 +2449,8 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { + /* skip the first msrs in the list. KVM-specific */ + for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; if (j < i) From 8d23c4662427507f432c96ac4fa3b76f0a8360cd Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 9 Oct 2009 16:08:25 +0200 Subject: [PATCH 39/84] KVM: SVM: Notify nested hypervisor of lost event injections If event_inj is valid on a #vmexit the host CPU would write the contents to exit_int_info, so the hypervisor knows that the event wasn't injected. We don't do this in nested SVM by now which is a bug and fixed by this patch. Signed-off-by: Alexander Graf Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 279a2ae21b4..e37285446cb 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1615,6 +1615,22 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; + + /* + * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have + * to make sure that we do not lose injected events. So check event_inj + * here and copy it to exit_int_info if it is valid. + * Exit_int_info and event_inj can't be both valid because the case + * below only happens on a VMRUN instruction intercept which has + * no valid exit_int_info set. + */ + if (vmcb->control.event_inj & SVM_EVTINJ_VALID) { + struct vmcb_control_area *nc = &nested_vmcb->control; + + nc->exit_int_info = vmcb->control.event_inj; + nc->exit_int_info_err = vmcb->control.event_inj_err; + } + nested_vmcb->control.tlb_ctl = 0; nested_vmcb->control.event_inj = 0; nested_vmcb->control.event_inj_err = 0; From cd3ff653ae0b45bac7a19208e9c75034fcacc85f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:26 +0200 Subject: [PATCH 40/84] KVM: SVM: Move INTR vmexit out of atomic code The nested SVM code emulates a #vmexit caused by a request to open the irq window right in the request function. This is a bug because the request function runs with preemption and interrupts disabled but the #vmexit emulation might sleep. This can cause a schedule()-while-atomic bug and is fixed with this patch. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e37285446cb..884bffc70c7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -85,6 +85,9 @@ struct nested_state { /* gpa pointers to the real vectors */ u64 vmcb_msrpm; + /* A VMEXIT is required but not yet emulated */ + bool exit_required; + /* cache for intercepts of the guest */ u16 intercept_cr_read; u16 intercept_cr_write; @@ -1379,7 +1382,14 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) svm->vmcb->control.exit_code = SVM_EXIT_INTR; - if (nested_svm_exit_handled(svm)) { + if (svm->nested.intercept & 1ULL) { + /* + * The #vmexit can't be emulated here directly because this + * code path runs with irqs and preemtion disabled. A + * #vmexit emulation might sleep. Only signal request for + * the #vmexit here. + */ + svm->nested.exit_required = true; nsvm_printk("VMexit -> INTR\n"); return 1; } @@ -2340,6 +2350,13 @@ static int handle_exit(struct kvm_vcpu *vcpu) trace_kvm_exit(exit_code, svm->vmcb->save.rip); + if (unlikely(svm->nested.exit_required)) { + nested_svm_vmexit(svm); + svm->nested.exit_required = false; + + return 1; + } + if (is_nested(svm)) { int vmexit; @@ -2615,6 +2632,13 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) u16 gs_selector; u16 ldt_selector; + /* + * A vmexit emulation is required before the vcpu can be executed + * again. + */ + if (unlikely(svm->nested.exit_required)) + return; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; From 0ac406de8f3780c8e0801d5719e1ec531d4a6ec4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:27 +0200 Subject: [PATCH 41/84] KVM: SVM: Add tracepoint for nested vmrun This patch adds a dedicated kvm tracepoint for a nested vmrun. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 6 ++++++ arch/x86/kvm/trace.h | 33 +++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 40 insertions(+) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 884bffc70c7..907af3f3a7a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1726,6 +1726,12 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) /* nested_vmcb is our indicator if nested SVM is activated */ svm->nested.vmcb = svm->vmcb->save.rax; + trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb, + nested_vmcb->save.rip, + nested_vmcb->control.int_ctl, + nested_vmcb->control.event_inj, + nested_vmcb->control.nested_ctl); + /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 0d480e77eac..b5798e12182 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -349,6 +349,39 @@ TRACE_EVENT(kvm_apic_accept_irq, __entry->coalesced ? " (coalesced)" : "") ); +/* + * Tracepoint for nested VMRUN + */ +TRACE_EVENT(kvm_nested_vmrun, + TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl, + __u32 event_inj, bool npt), + TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u64, vmcb ) + __field( __u64, nested_rip ) + __field( __u32, int_ctl ) + __field( __u32, event_inj ) + __field( bool, npt ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->vmcb = vmcb; + __entry->nested_rip = nested_rip; + __entry->int_ctl = int_ctl; + __entry->event_inj = event_inj; + __entry->npt = npt; + ), + + TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " + "event_inj: 0x%08x npt: %s\n", + __entry->rip, __entry->vmcb, __entry->nested_rip, + __entry->int_ctl, __entry->event_inj, + __entry->npt ? "on" : "off") +); + #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4de5bc0a8e8..3ab2f9042dd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4984,3 +4984,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); From d8cabddf7e8fbdced2dd668c98d7762c7ef75245 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:28 +0200 Subject: [PATCH 42/84] KVM: SVM: Add tracepoint for nested #vmexit This patch adds a tracepoint for every #vmexit we get from a nested guest. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 6 ++++++ arch/x86/kvm/trace.h | 36 ++++++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 43 insertions(+) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 907af3f3a7a..edf6e8b2b84 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2366,6 +2366,12 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (is_nested(svm)) { int vmexit; + trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code, + svm->vmcb->control.exit_info_1, + svm->vmcb->control.exit_info_2, + svm->vmcb->control.exit_int_info, + svm->vmcb->control.exit_int_info_err); + nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n", exit_code, svm->vmcb->control.exit_info_1, svm->vmcb->control.exit_info_2, svm->vmcb->save.rip); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b5798e12182..a7eb6299a26 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -382,6 +382,42 @@ TRACE_EVENT(kvm_nested_vmrun, __entry->npt ? "on" : "off") ); +/* + * Tracepoint for #VMEXIT while nested + */ +TRACE_EVENT(kvm_nested_vmexit, + TP_PROTO(__u64 rip, __u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err), + TP_ARGS(rip, exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->exit_code = exit_code; + __entry->exit_info1 = exit_info1; + __entry->exit_info2 = exit_info2; + __entry->exit_int_info = exit_int_info; + __entry->exit_int_info_err = exit_int_info_err; + ), + TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + __entry->rip, + ftrace_print_symbols_seq(p, __entry->exit_code, + kvm_x86_ops->exit_reasons_str), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +); + #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3ab2f9042dd..192d58efc6d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4985,3 +4985,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); From 17897f366847a9ef8a13e3671a0eb1c15422abed Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:29 +0200 Subject: [PATCH 43/84] KVM: SVM: Add tracepoint for injected #vmexit This patch adds a tracepoint for a nested #vmexit that gets re-injected to the guest. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 6 ++++++ arch/x86/kvm/trace.h | 33 +++++++++++++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 40 insertions(+) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index edf6e8b2b84..369eeb86e87 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1592,6 +1592,12 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, + vmcb->control.exit_info_1, + vmcb->control.exit_info_2, + vmcb->control.exit_int_info, + vmcb->control.exit_int_info_err); + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); if (!nested_vmcb) return 1; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a7eb6299a26..4d6bb5ee39b 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -418,6 +418,39 @@ TRACE_EVENT(kvm_nested_vmexit, __entry->exit_int_info, __entry->exit_int_info_err) ); +/* + * Tracepoint for #VMEXIT reinjected to the guest + */ +TRACE_EVENT(kvm_nested_vmexit_inject, + TP_PROTO(__u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err), + TP_ARGS(exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err), + + TP_STRUCT__entry( + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + ), + + TP_fast_assign( + __entry->exit_code = exit_code; + __entry->exit_info1 = exit_info1; + __entry->exit_info2 = exit_info2; + __entry->exit_int_info = exit_int_info; + __entry->exit_int_info_err = exit_int_info_err; + ), + + TP_printk("reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + ftrace_print_symbols_seq(p, __entry->exit_code, + kvm_x86_ops->exit_reasons_str), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +); #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 192d58efc6d..a522d9ba81b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4986,3 +4986,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); From 236649de3360916ef85f95c82723af17a25b9179 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:30 +0200 Subject: [PATCH 44/84] KVM: SVM: Add tracepoint for #vmexit because intr pending This patch adds a special tracepoint for the event that a nested #vmexit is injected because kvm wants to inject an interrupt into the guest. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/trace.h | 18 ++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 20 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 369eeb86e87..78a391c60a7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1390,7 +1390,7 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) * the #vmexit here. */ svm->nested.exit_required = true; - nsvm_printk("VMexit -> INTR\n"); + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); return 1; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 4d6bb5ee39b..3cc8f444be1 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -451,6 +451,24 @@ TRACE_EVENT(kvm_nested_vmexit_inject, __entry->exit_info1, __entry->exit_info2, __entry->exit_int_info, __entry->exit_int_info_err) ); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_nested_intr_vmexit, + TP_PROTO(__u64 rip), + TP_ARGS(rip), + + TP_STRUCT__entry( + __field( __u64, rip ) + ), + + TP_fast_assign( + __entry->rip = rip + ), + + TP_printk("rip: 0x%016llx\n", __entry->rip) +); #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a522d9ba81b..2cf4146b425 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4987,3 +4987,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); From ec1ff79084fccdae0dca9b04b89dcdf3235bbfa1 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:31 +0200 Subject: [PATCH 45/84] KVM: SVM: Add tracepoint for invlpga instruction This patch adds a tracepoint for the event that the guest executed the INVLPGA instruction. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 3 +++ arch/x86/kvm/trace.h | 23 +++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 27 insertions(+) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 78a391c60a7..ba18fb7d365 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1976,6 +1976,9 @@ static int invlpga_interception(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; nsvm_printk("INVLPGA\n"); + trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], + vcpu->arch.regs[VCPU_REGS_RAX]); + /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 3cc8f444be1..7e1f08e959b 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -469,6 +469,29 @@ TRACE_EVENT(kvm_nested_intr_vmexit, TP_printk("rip: 0x%016llx\n", __entry->rip) ); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_invlpga, + TP_PROTO(__u64 rip, int asid, u64 address), + TP_ARGS(rip, asid, address), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( int, asid ) + __field( __u64, address ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->asid = asid; + __entry->address = address; + ), + + TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n", + __entry->rip, __entry->asid, __entry->address) +); #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2cf4146b425..86596fc7941 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4988,3 +4988,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); From 532a46b98963f110e9425a251e127d6537915dde Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:32 +0200 Subject: [PATCH 46/84] KVM: SVM: Add tracepoint for skinit instruction This patch adds a tracepoint for the event that the guest executed the SKINIT instruction. This information is important because SKINIT is an SVM extenstion not yet implemented by nested SVM and we may need this information for debugging hypervisors that do not yet run on nested SVM. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 10 +++++++++- arch/x86/kvm/trace.h | 22 ++++++++++++++++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 32 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ba18fb7d365..8b9f6fbba48 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1987,6 +1987,14 @@ static int invlpga_interception(struct vcpu_svm *svm) return 1; } +static int skinit_interception(struct vcpu_svm *svm) +{ + trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + static int invalid_op_interception(struct vcpu_svm *svm) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); @@ -2350,7 +2358,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_VMSAVE] = vmsave_interception, [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, - [SVM_EXIT_SKINIT] = invalid_op_interception, + [SVM_EXIT_SKINIT] = skinit_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, [SVM_EXIT_MWAIT] = invalid_op_interception, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 7e1f08e959b..816e0449db0 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -492,6 +492,28 @@ TRACE_EVENT(kvm_invlpga, TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n", __entry->rip, __entry->asid, __entry->address) ); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_skinit, + TP_PROTO(__u64 rip, __u32 slb), + TP_ARGS(rip, slb), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, slb ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->slb = slb; + ), + + TP_printk("rip: 0x%016llx slb: 0x%08x\n", + __entry->rip, __entry->slb) +); + #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 86596fc7941..098e7f88630 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4989,3 +4989,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); From d36f19e9ecd22dc035ef4cc6361b564be650f8e7 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 9 Oct 2009 16:08:33 +0200 Subject: [PATCH 47/84] KVM: SVM: Remove nsvm_printk debugging code With all important informations now delivered through tracepoints we can savely remove the nsvm_printk debugging code for nested svm. Signed-off-by: Joerg Roedel Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/svm.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 8b9f6fbba48..69610c5d6de 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -53,15 +53,6 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) -/* Turn on to get debugging output*/ -/* #define NESTED_DEBUG */ - -#ifdef NESTED_DEBUG -#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args) -#else -#define nsvm_printk(fmt, args...) do {} while(0) -#endif - static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, @@ -1540,14 +1531,12 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); - nsvm_printk("exit code: 0x%x\n", exit_code); if (svm->nested.intercept & exit_bits) vmexit = NESTED_EXIT_DONE; } } if (vmexit == NESTED_EXIT_DONE) { - nsvm_printk("#VMEXIT reason=%04x\n", exit_code); nested_svm_vmexit(svm); } @@ -1658,10 +1647,6 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(vmcb, hsave); - /* Kill any pending exceptions */ - if (svm->vcpu.arch.exception.pending == true) - nsvm_printk("WARNING: Pending Exception\n"); - kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -1826,25 +1811,14 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) force_new_asid(&svm->vcpu); svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; - if (nested_vmcb->control.int_ctl & V_IRQ_MASK) { - nsvm_printk("nSVM Injecting Interrupt: 0x%x\n", - nested_vmcb->control.int_ctl); - } if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; - nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n", - nested_vmcb->control.exit_int_info, - nested_vmcb->control.int_state); - svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; - if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID) - nsvm_printk("Injecting Event: 0x%x\n", - nested_vmcb->control.event_inj); svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; @@ -1913,8 +1887,6 @@ static int vmsave_interception(struct vcpu_svm *svm) static int vmrun_interception(struct vcpu_svm *svm) { - nsvm_printk("VMrun\n"); - if (nested_svm_check_permissions(svm)) return 1; @@ -1974,7 +1946,6 @@ static int clgi_interception(struct vcpu_svm *svm) static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - nsvm_printk("INVLPGA\n"); trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], vcpu->arch.regs[VCPU_REGS_RAX]); @@ -2389,10 +2360,6 @@ static int handle_exit(struct kvm_vcpu *vcpu) svm->vmcb->control.exit_int_info, svm->vmcb->control.exit_int_info_err); - nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n", - exit_code, svm->vmcb->control.exit_info_1, - svm->vmcb->control.exit_info_2, svm->vmcb->save.rip); - vmexit = nested_svm_exit_special(svm); if (vmexit == NESTED_EXIT_CONTINUE) @@ -2539,7 +2506,6 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nsvm_printk("Trying to open IRQ window\n"); nested_svm_intr(svm); From d255f4f2bac81eb798fcf76938147f1f6c756ae2 Mon Sep 17 00:00:00 2001 From: "Zhai, Edwin" Date: Fri, 9 Oct 2009 18:03:20 +0800 Subject: [PATCH 48/84] KVM: introduce kvm_vcpu_on_spin Introduce kvm_vcpu_on_spin, to be used by VMX/SVM to yield processing once the cpu detects pause-based looping. Signed-off-by: "Zhai, Edwin" Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b985a29d817..bd5a616d937 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -286,6 +286,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); +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); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 70c8cbea0a9..cac69c4415d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1108,6 +1108,21 @@ void kvm_resched(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_resched); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu) +{ + ktime_t expires; + DEFINE_WAIT(wait); + + prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + + /* Sleep for 100 us, and hope lock-holder got scheduled */ + expires = ktime_add_ns(ktime_get(), 100000UL); + schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); + + finish_wait(&vcpu->wq, &wait); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); + static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vma->vm_file->private_data; From 4b8d54f9726f1159330201c5ed2ea30bce7e63ea Mon Sep 17 00:00:00 2001 From: "Zhai, Edwin" Date: Fri, 9 Oct 2009 18:03:20 +0800 Subject: [PATCH 49/84] KVM: VMX: Add support for Pause-Loop Exiting New NHM processors will support Pause-Loop Exiting by adding 2 VM-execution control fields: PLE_Gap - upper bound on the amount of time between two successive executions of PAUSE in a loop. PLE_Window - upper bound on the amount of time a guest is allowed to execute in a PAUSE loop If the time, between this execution of PAUSE and previous one, exceeds the PLE_Gap, processor consider this PAUSE belongs to a new loop. Otherwise, processor determins the the total execution time of this loop(since 1st PAUSE in this loop), and triggers a VM exit if total time exceeds the PLE_Window. * Refer SDM volume 3b section 21.6.13 & 22.1.3. Pause-Loop Exiting can be used to detect Lock-Holder Preemption, where one VP is sched-out after hold a spinlock, then other VPs for same lock are sched-in to waste the CPU time. Our tests indicate that most spinlocks are held for less than 212 cycles. Performance tests show that with 2X LP over-commitment we can get +2% perf improvement for kernel build(Even more perf gain with more LPs). Signed-off-by: Zhai Edwin Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/vmx.h | 4 +++ arch/x86/kvm/vmx.c | 51 +++++++++++++++++++++++++++++++++++++- 2 files changed, 54 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 272514c2d45..2b4945419a8 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -56,6 +56,7 @@ #define SECONDARY_EXEC_ENABLE_VPID 0x00000020 #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 +#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -144,6 +145,8 @@ enum vmcs_field { VM_ENTRY_INSTRUCTION_LEN = 0x0000401a, TPR_THRESHOLD = 0x0000401c, SECONDARY_VM_EXEC_CONTROL = 0x0000401e, + PLE_GAP = 0x00004020, + PLE_WINDOW = 0x00004022, VM_INSTRUCTION_ERROR = 0x00004400, VM_EXIT_REASON = 0x00004402, VM_EXIT_INTR_INFO = 0x00004404, @@ -248,6 +251,7 @@ enum vmcs_field { #define EXIT_REASON_MSR_READ 31 #define EXIT_REASON_MSR_WRITE 32 #define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_PAUSE_INSTRUCTION 40 #define EXIT_REASON_MCE_DURING_VMENTRY 41 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 70020e505c2..a4580d65af5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -61,6 +61,25 @@ module_param_named(unrestricted_guest, static int __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); +/* + * These 2 parameters are used to config the controls for Pause-Loop Exiting: + * ple_gap: upper bound on the amount of time between two successive + * executions of PAUSE in a loop. Also indicate if ple enabled. + * According to test, this time is usually small than 41 cycles. + * ple_window: upper bound on the amount of time a guest is allowed to execute + * in a PAUSE loop. Tests indicate that most spinlocks are held for + * less than 2^12 cycles + * Time is measured based on a counter that runs at the same rate as the TSC, + * refer SDM volume 3b section 21.6.13 & 22.1.3. + */ +#define KVM_VMX_DEFAULT_PLE_GAP 41 +#define KVM_VMX_DEFAULT_PLE_WINDOW 4096 +static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP; +module_param(ple_gap, int, S_IRUGO); + +static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; +module_param(ple_window, int, S_IRUGO); + struct vmcs { u32 revision_id; u32 abort; @@ -319,6 +338,12 @@ static inline int cpu_has_vmx_unrestricted_guest(void) SECONDARY_EXEC_UNRESTRICTED_GUEST; } +static inline int cpu_has_vmx_ple(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_PAUSE_LOOP_EXITING; +} + static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) { return flexpriority_enabled && @@ -1240,7 +1265,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST; + SECONDARY_EXEC_UNRESTRICTED_GUEST | + SECONDARY_EXEC_PAUSE_LOOP_EXITING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -1386,6 +1412,9 @@ static __init int hardware_setup(void) if (enable_ept && !cpu_has_vmx_ept_2m_page()) kvm_disable_largepages(); + if (!cpu_has_vmx_ple()) + ple_gap = 0; + return alloc_kvm_area(); } @@ -2298,9 +2327,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; + if (!ple_gap) + exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } + if (ple_gap) { + vmcs_write32(PLE_GAP, ple_gap); + vmcs_write32(PLE_WINDOW, ple_window); + } + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ @@ -3347,6 +3383,18 @@ out: return ret; } +/* + * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE + * exiting, so only get here on cpu with PAUSE-Loop-Exiting. + */ +static int handle_pause(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + skip_emulated_instruction(vcpu); + kvm_vcpu_on_spin(vcpu); + + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -3383,6 +3431,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, + [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, }; static const int kvm_vmx_max_exit_handlers = From 565d0998ecac8373b9a9ecd5991abe74318cd235 Mon Sep 17 00:00:00 2001 From: Mark Langsdorf Date: Tue, 6 Oct 2009 14:25:02 -0500 Subject: [PATCH 50/84] KVM: SVM: Support Pause Filter in AMD processors New AMD processors (Family 0x10 models 8+) support the Pause Filter Feature. This feature creates a new field in the VMCB called Pause Filter Count. If Pause Filter Count is greater than 0 and intercepting PAUSEs is enabled, the processor will increment an internal counter when a PAUSE instruction occurs instead of intercepting. When the internal counter reaches the Pause Filter Count value, a PAUSE intercept will occur. This feature can be used to detect contended spinlocks, especially when the lock holding VCPU is not scheduled. Rescheduling another VCPU prevents the VCPU seeking the lock from wasting its quantum by spinning idly. Experimental results show that most spinlocks are held for less than 1000 PAUSE cycles or more than a few thousand. Default the Pause Filter Counter to 3000 to detect the contended spinlocks. Processor support for this feature is indicated by a CPUID bit. On a 24 core system running 4 guests each with 16 VCPUs, this patch improved overall performance of each guest's 32 job kernbench by approximately 3-5% when combined with a scheduler algorithm thati caused the VCPU to sleep for a brief period. Further performance improvement may be possible with a more sophisticated yield algorithm. Signed-off-by: Mark Langsdorf Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/svm.h | 3 ++- arch/x86/kvm/svm.c | 13 +++++++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 85574b7c1bc..1fecb7e6113 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -57,7 +57,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u16 intercept_dr_write; u32 intercept_exceptions; u64 intercept; - u8 reserved_1[44]; + u8 reserved_1[42]; + u16 pause_filter_count; u64 iopm_base_pa; u64 msrpm_base_pa; u64 tsc_offset; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 69610c5d6de..170b2d9c690 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -46,6 +46,7 @@ MODULE_LICENSE("GPL"); #define SVM_FEATURE_NPT (1 << 0) #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) +#define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ @@ -654,6 +655,11 @@ static void init_vmcb(struct vcpu_svm *svm) svm->nested.vmcb = 0; svm->vcpu.arch.hflags = 0; + if (svm_has(SVM_FEATURE_PAUSE_FILTER)) { + control->pause_filter_count = 3000; + control->intercept |= (1ULL << INTERCEPT_PAUSE); + } + enable_gif(svm); } @@ -2281,6 +2287,12 @@ static int interrupt_window_interception(struct vcpu_svm *svm) return 1; } +static int pause_interception(struct vcpu_svm *svm) +{ + kvm_vcpu_on_spin(&(svm->vcpu)); + return 1; +} + static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = emulate_on_interception, [SVM_EXIT_READ_CR3] = emulate_on_interception, @@ -2316,6 +2328,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, From 6b7d7e762b238f908fe4c3345c2c6eb5c3fdbd59 Mon Sep 17 00:00:00 2001 From: Zachary Amsden Date: Fri, 9 Oct 2009 16:26:08 -1000 Subject: [PATCH 51/84] KVM: x86: Harden against cpufreq If cpufreq can't determine the CPU khz, or cpufreq is not compiled in, we should fallback to the measured TSC khz. Signed-off-by: Zachary Amsden Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 098e7f88630..3cffa2cac70 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1348,8 +1348,12 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); - if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) - per_cpu(cpu_tsc_khz, cpu) = cpufreq_quick_get(cpu); + if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) { + unsigned long khz = cpufreq_quick_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } kvm_request_guest_time_update(vcpu); } @@ -3144,8 +3148,12 @@ static void kvm_timer_init(void) if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); - for_each_online_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = cpufreq_get(cpu); + for_each_online_cpu(cpu) { + unsigned long khz = cpufreq_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } } else { for_each_possible_cpu(cpu) per_cpu(cpu_tsc_khz, cpu) = tsc_khz; From 9fb41ba8962b18159e16cac81e7d57e897964038 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 12 Oct 2009 19:37:31 -0300 Subject: [PATCH 52/84] KVM: VMX: fix handle_pause declaration There's no kvm_run argument anymore. Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a4580d65af5..364263a25ff 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3387,7 +3387,7 @@ out: * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE * exiting, so only get here on cpu with PAUSE-Loop-Exiting. */ -static int handle_pause(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_pause(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); kvm_vcpu_on_spin(vcpu); From 94c30d9ca6fd00a69e367b91b6e13572c41938c5 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 12 Oct 2009 08:51:40 +0200 Subject: [PATCH 53/84] KVM: x86: Drop unneeded CONFIG_HAS_IOMEM check This (broken) check dates back to the days when this code was shared across architectures. x86 has IOMEM, so drop it. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3cffa2cac70..5d450cc6f84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3814,7 +3814,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (r) goto out; } -#if CONFIG_HAS_IOMEM if (vcpu->mmio_needed) { memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); vcpu->mmio_read_completed = 1; @@ -3832,7 +3831,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } } -#endif if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) kvm_register_write(vcpu, VCPU_REGS_RAX, kvm_run->hypercall.ret); From ffde22ac53b6d6b1d7206f1172176a667eead778 Mon Sep 17 00:00:00 2001 From: Ed Swierk Date: Thu, 15 Oct 2009 15:21:43 -0700 Subject: [PATCH 54/84] KVM: Xen PV-on-HVM guest support Support for Xen PV-on-HVM guests can be implemented almost entirely in userspace, except for handling one annoying MSR that maps a Xen hypercall blob into guest address space. A generic mechanism to delegate MSR writes to userspace seems overkill and risks encouraging similar MSR abuse in the future. Thus this patch adds special support for the Xen HVM MSR. I implemented a new ioctl, KVM_XEN_HVM_CONFIG, that lets userspace tell KVM which MSR the guest will write to, as well as the starting address and size of the hypercall blobs (one each for 32-bit and 64-bit) that userspace has loaded from files. When the guest writes to the MSR, KVM copies one page of the blob from userspace to the guest. I've tested this patch with a hacked-up version of Gerd's userspace code, booting a number of guests (CentOS 5.3 i386 and x86_64, and FreeBSD 8.0-RC1 amd64) and exercising PV network and block devices. [jan: fix i386 build warning] [avi: future proof abi with a flags field] Signed-off-by: Ed Swierk Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- Documentation/kvm/api.txt | 24 +++++++++++++++++ arch/x86/include/asm/kvm.h | 1 + arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/x86.c | 46 +++++++++++++++++++++++++++++++++ include/linux/kvm.h | 16 ++++++++++++ 5 files changed, 89 insertions(+) diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt index 5a4bc8cf6d0..3e8684e4850 100644 --- a/Documentation/kvm/api.txt +++ b/Documentation/kvm/api.txt @@ -593,6 +593,30 @@ struct kvm_irqchip { } chip; }; +4.27 KVM_XEN_HVM_CONFIG + +Capability: KVM_CAP_XEN_HVM +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_xen_hvm_config (in) +Returns: 0 on success, -1 on error + +Sets the MSR that the Xen HVM guest uses to initialize its hypercall +page, and provides the starting address and size of the hypercall +blobs in userspace. When the guest writes the MSR, kvm copies one +page of a blob (32- or 64-bit, depending on the vcpu mode) to guest +memory. + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index f02e87a5206..ef9b4b73cce 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -19,6 +19,7 @@ #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 +#define __KVM_HAVE_XEN_HVM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 179a919f53a..36f3b53f5c2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -410,6 +410,8 @@ struct kvm_arch{ unsigned long irq_sources_bitmap; u64 vm_init_tsc; + + struct kvm_xen_hvm_config xen_hvm_config; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5d450cc6f84..bb842db3ee7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -857,6 +857,38 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 0; } +static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + int lm = is_long_mode(vcpu); + u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 + : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + u8 *page; + int r; + + r = -E2BIG; + if (page_num >= blob_size) + goto out; + r = -ENOMEM; + page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!page) + goto out; + r = -EFAULT; + if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE)) + goto out_free; + if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + goto out_free; + r = 0; +out_free: + kfree(page); +out: + return r; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -972,6 +1004,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) "0x%x data 0x%llx\n", msr, data); break; default: + if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) + return xen_hvm_config(vcpu, data); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -1246,6 +1280,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: + case KVM_CAP_XEN_HVM: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2441,6 +2476,17 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_XEN_HVM_CONFIG: { + r = -EFAULT; + if (copy_from_user(&kvm->arch.xen_hvm_config, argp, + sizeof(struct kvm_xen_hvm_config))) + goto out; + r = -EINVAL; + if (kvm->arch.xen_hvm_config.flags) + goto out; + r = 0; + break; + } default: ; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index f8f8900fc5e..b694c1d2f91 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -436,6 +436,9 @@ struct kvm_ioeventfd { #endif #define KVM_CAP_IOEVENTFD 36 #define KVM_CAP_SET_IDENTITY_MAP_ADDR 37 +#ifdef __KVM_HAVE_XEN_HVM +#define KVM_CAP_XEN_HVM 38 +#endif #ifdef KVM_CAP_IRQ_ROUTING @@ -488,6 +491,18 @@ struct kvm_x86_mce { }; #endif +#ifdef KVM_CAP_XEN_HVM +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; +#endif + #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) struct kvm_irqfd { @@ -546,6 +561,7 @@ struct kvm_irqfd { #define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) #define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) #define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) +#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) /* * ioctls for vcpu fds From 94fe45da48f921d01d8ff02a0ad54ee9c326d7f0 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 18 Oct 2009 13:24:44 +0200 Subject: [PATCH 55/84] KVM: x86: Fix guest single-stepping while interruptible Commit 705c5323 opened the doors of hell by unconditionally injecting single-step flags as long as guest_debug signaled this. This doesn't work when the guest branches into some interrupt or exception handler and triggers a vmexit with flag reloading. Fix it by saving cs:rip when user space requests single-stepping and restricting the trace flag injection to this guest code position. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 4 +++ arch/x86/kvm/x86.c | 47 ++++++++++++++++++++------------- 2 files changed, 32 insertions(+), 19 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 36f3b53f5c2..2536fbd85b3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -371,6 +371,10 @@ struct kvm_vcpu_arch { u64 mcg_status; u64 mcg_ctl; u64 *mce_banks; + + /* used for guest single stepping over the given code position */ + u16 singlestep_cs; + unsigned long singlestep_rip; }; struct kvm_mem_alias { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bb842db3ee7..13f30aac460 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -235,25 +235,6 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) } EXPORT_SYMBOL_GPL(kvm_require_cpl); -unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) -{ - unsigned long rflags; - - rflags = kvm_x86_ops->get_rflags(vcpu); - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); - return rflags; -} -EXPORT_SYMBOL_GPL(kvm_get_rflags); - -void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) -{ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - kvm_x86_ops->set_rflags(vcpu, rflags); -} -EXPORT_SYMBOL_GPL(kvm_set_rflags); - /* * Load the pae pdptrs. Return true is they are all valid. */ @@ -4565,6 +4546,12 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + vcpu->arch.singlestep_cs = + get_segment_selector(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu); + } + /* * Trigger an rflags update that will inject or remove the trace * flags. @@ -5031,6 +5018,28 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + vcpu->arch.singlestep_cs == + get_segment_selector(vcpu, VCPU_SREG_CS) && + vcpu->arch.singlestep_rip == kvm_rip_read(vcpu)) + rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_x86_ops->set_rflags(vcpu, rflags); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); From 6be7d3062b59af891be7e40c6802350de5f78cef Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Sun, 18 Oct 2009 13:24:54 +0200 Subject: [PATCH 56/84] KVM: SVM: Cleanup NMI singlestep Push the NMI-related singlestep variable into vcpu_svm. It's dealing with an AMD-specific deficit, nothing generic for x86. Acked-by: Gleb Natapov Signed-off-by: Jan Kiszka arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/svm.c | 12 +++++++----- 2 files changed, 7 insertions(+), 6 deletions(-) Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/svm.c | 12 +++++++----- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2536fbd85b3..4d994ad5051 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -354,7 +354,6 @@ struct kvm_vcpu_arch { unsigned int time_offset; struct page *time_page; - bool singlestep; /* guest is single stepped by KVM */ bool nmi_pending; bool nmi_injected; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 170b2d9c690..ffa6ad216b7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -107,6 +107,8 @@ struct vcpu_svm { u32 *msrpm; struct nested_state nested; + + bool nmi_singlestep; }; /* enable NPT for AMD64 and X86 with PAE */ @@ -1050,7 +1052,7 @@ static void update_db_intercept(struct kvm_vcpu *vcpu) svm->vmcb->control.intercept_exceptions &= ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); - if (vcpu->arch.singlestep) + if (svm->nmi_singlestep) svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { @@ -1195,13 +1197,13 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && - !svm->vcpu.arch.singlestep) { + !svm->nmi_singlestep) { kvm_queue_exception(&svm->vcpu, DB_VECTOR); return 1; } - if (svm->vcpu.arch.singlestep) { - svm->vcpu.arch.singlestep = false; + if (svm->nmi_singlestep) { + svm->nmi_singlestep = false; if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); @@ -2543,7 +2545,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) /* Something prevents NMI from been injected. Single step over possible problem (IRET or exception injection or interrupt shadow) */ - vcpu->arch.singlestep = true; + svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_intercept(vcpu); } From cd5a2685de4a642fd0bd763e8c19711ef08dbe27 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Sat, 17 Oct 2009 22:47:23 -0300 Subject: [PATCH 57/84] KVM: fix irq_source_id size verification find_first_zero_bit works with bit numbers, not bytes. Fixes https://sourceforge.net/tracker/?func=detail&aid=2847560&group_id=180599&atid=893831 Reported-by: "Xu, Jiajun" Cc: stable@kernel.org Signed-off-by: Marcelo Tosatti --- virt/kvm/irq_comm.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 00c68d29857..0d454d35271 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -215,10 +215,9 @@ int kvm_request_irq_source_id(struct kvm *kvm) int irq_source_id; mutex_lock(&kvm->irq_lock); - irq_source_id = find_first_zero_bit(bitmap, - sizeof(kvm->arch.irq_sources_bitmap)); + irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); - if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + if (irq_source_id >= BITS_PER_LONG) { printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); irq_source_id = -EFAULT; goto unlock; @@ -240,7 +239,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || - irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) { + irq_source_id >= BITS_PER_LONG) { printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); goto unlock; } From afbcf7ab8d1bc8c2d04792f6d9e786e0adeb328d Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Fri, 16 Oct 2009 15:28:36 -0400 Subject: [PATCH 58/84] KVM: allow userspace to adjust kvmclock offset When we migrate a kvm guest that uses pvclock between two hosts, we may suffer a large skew. This is because there can be significant differences between the monotonic clock of the hosts involved. When a new host with a much larger monotonic time starts running the guest, the view of time will be significantly impacted. Situation is much worse when we do the opposite, and migrate to a host with a smaller monotonic clock. This proposed ioctl will allow userspace to inform us what is the monotonic clock value in the source host, so we can keep the time skew short, and more importantly, never goes backwards. Userspace may also need to trigger the current data, since from the first migration onwards, it won't be reflected by a simple call to clock_gettime() anymore. [marcelo: future-proof abi with a flags field] [jan: fix KVM_GET_CLOCK by clearing flags field instead of checking it] Signed-off-by: Glauber Costa Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- Documentation/kvm/api.txt | 36 ++++++++++++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 42 ++++++++++++++++++++++++++++++++- include/linux/kvm.h | 10 ++++++++ 4 files changed, 88 insertions(+), 1 deletion(-) diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt index 3e8684e4850..36594ba5772 100644 --- a/Documentation/kvm/api.txt +++ b/Documentation/kvm/api.txt @@ -617,6 +617,42 @@ struct kvm_xen_hvm_config { __u8 pad2[30]; }; +4.27 KVM_GET_CLOCK + +Capability: KVM_CAP_ADJUST_CLOCK +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_clock_data (out) +Returns: 0 on success, -1 on error + +Gets the current timestamp of kvmclock as seen by the current guest. In +conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios +such as migration. + +struct kvm_clock_data { + __u64 clock; /* kvmclock current value */ + __u32 flags; + __u32 pad[9]; +}; + +4.28 KVM_SET_CLOCK + +Capability: KVM_CAP_ADJUST_CLOCK +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_clock_data (in) +Returns: 0 on success, -1 on error + +Sets the current timestamp of kvmclock to the valued specific in its parameter. +In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios +such as migration. + +struct kvm_clock_data { + __u64 clock; /* kvmclock current value */ + __u32 flags; + __u32 pad[9]; +}; + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4d994ad5051..0558ff8c32a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -413,6 +413,7 @@ struct kvm_arch{ unsigned long irq_sources_bitmap; u64 vm_init_tsc; + s64 kvmclock_offset; struct kvm_xen_hvm_config xen_hvm_config; }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 13f30aac460..e16cdc9ec0c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -680,7 +680,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ vcpu->hv_clock.system_time = ts.tv_nsec + - (NSEC_PER_SEC * (u64)ts.tv_sec); + (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset; + /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -1262,6 +1263,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_XEN_HVM: + case KVM_CAP_ADJUST_CLOCK: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -2468,6 +2470,44 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_SET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + s64 delta; + + r = -EFAULT; + if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + goto out; + + r = -EINVAL; + if (user_ns.flags) + goto out; + + r = 0; + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + delta = user_ns.clock - now_ns; + kvm->arch.kvmclock_offset = delta; + break; + } + case KVM_GET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + user_ns.clock = kvm->arch.kvmclock_offset + now_ns; + user_ns.flags = 0; + + r = -EFAULT; + if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + goto out; + r = 0; + break; + } + default: ; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index b694c1d2f91..6ed1a12ed52 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -439,6 +439,7 @@ struct kvm_ioeventfd { #ifdef __KVM_HAVE_XEN_HVM #define KVM_CAP_XEN_HVM 38 #endif +#define KVM_CAP_ADJUST_CLOCK 39 #ifdef KVM_CAP_IRQ_ROUTING @@ -512,6 +513,12 @@ struct kvm_irqfd { __u8 pad[20]; }; +struct kvm_clock_data { + __u64 clock; + __u32 flags; + __u32 pad[9]; +}; + /* * ioctls for VM fds */ @@ -562,6 +569,9 @@ struct kvm_irqfd { #define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) #define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) #define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) +#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data) +#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data) + /* * ioctls for vcpu fds From 6ff5894cdfe7103083bd15b31002434ccd351039 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Oct 2009 14:19:27 +0200 Subject: [PATCH 59/84] KVM: Enable 32bit dirty log pointers on 64bit host 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: Arnd Bergmann Signed-off-by: Alexander Graf Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/kvm_main.c | 51 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cac69c4415d..bd44fb48ac4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -1542,6 +1543,52 @@ out: return r; } +#ifdef CONFIG_COMPAT +struct compat_kvm_dirty_log { + __u32 slot; + __u32 padding1; + union { + compat_uptr_t dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +static long kvm_vm_compat_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm *kvm = filp->private_data; + int r; + + if (kvm->mm != current->mm) + return -EIO; + switch (ioctl) { + case KVM_GET_DIRTY_LOG: { + struct compat_kvm_dirty_log compat_log; + struct kvm_dirty_log log; + + r = -EFAULT; + if (copy_from_user(&compat_log, (void __user *)arg, + sizeof(compat_log))) + goto out; + log.slot = compat_log.slot; + log.padding1 = compat_log.padding1; + log.padding2 = compat_log.padding2; + log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); + + r = kvm_vm_ioctl_get_dirty_log(kvm, &log); + if (r) + goto out; + break; + } + default: + r = kvm_vm_ioctl(filp, ioctl, arg); + } + +out: + return r; +} +#endif + static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page[1]; @@ -1576,7 +1623,9 @@ static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma) static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, - .compat_ioctl = kvm_vm_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = kvm_vm_compat_ioctl, +#endif .mmap = kvm_vm_mmap, }; From fa40052ca04bdbbeb20b839cc8ffe9fa7beefbe9 Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Sat, 24 Oct 2009 02:49:58 -0200 Subject: [PATCH 60/84] KVM: VMX: Use macros instead of hex value on cr0 initialization This should have no effect, it is just to make the code clearer. Signed-off-by: Eduardo Habkost Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 364263a25ff..17730175aa0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2538,7 +2538,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = 0x60000010; + vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */ vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); From 18fa000ae453767b59ab97477925895a3f0c46ea Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Sat, 24 Oct 2009 02:49:59 -0200 Subject: [PATCH 61/84] KVM: SVM: Reset cr0 properly on vcpu reset svm_vcpu_reset() was not properly resetting the contents of the guest-visible cr0 register, causing the following issue: https://bugzilla.redhat.com/show_bug.cgi?id=525699 Without resetting cr0 properly, the vcpu was running the SIPI bootstrap routine with paging enabled, making the vcpu get a pagefault exception while trying to run it. Instead of setting vmcb->save.cr0 directly, the new code just resets kvm->arch.cr0 and calls kvm_set_cr0(). The bits that were set/cleared on vmcb->save.cr0 (PG, WP, !CD, !NW) will be set properly by svm_set_cr0(). kvm_set_cr0() is used instead of calling svm_set_cr0() directly to make sure kvm_mmu_reset_context() is called to reset the mmu to nonpaging mode. Signed-off-by: Eduardo Habkost Signed-off-by: Avi Kivity --- arch/x86/kvm/svm.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ffa6ad216b7..c9ef6c0e1e9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -628,11 +628,12 @@ static void init_vmcb(struct vcpu_svm *svm) save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - /* - * cr0 val on cpu init should be 0x60000010, we enable cpu - * cache by default. the orderly way is to enable cache in bios. + /* This is the guest-visible cr0 value. + * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. */ - save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; + svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0); + save->cr4 = X86_CR4_PAE; /* rdx = ?? */ From 3ce672d48400e0112fec7a3cb6bb2120493c6e11 Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Sat, 24 Oct 2009 02:50:00 -0200 Subject: [PATCH 62/84] KVM: SVM: init_vmcb(): remove redundant save->cr0 initialization The svm_set_cr0() call will initialize save->cr0 properly even when npt is enabled, clearing the NW and CD bits as expected, so we don't need to initialize it manually for npt_enabled anymore. Signed-off-by: Eduardo Habkost Signed-off-by: Avi Kivity --- arch/x86/kvm/svm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c9ef6c0e1e9..34b700f9e49 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -648,8 +648,6 @@ static void init_vmcb(struct vcpu_svm *svm) control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| INTERCEPT_CR3_MASK); save->g_pat = 0x0007040600070406ULL; - /* enable caching because the QEMU Bios doesn't enable it */ - save->cr0 = X86_CR0_ET; save->cr3 = 0; save->cr4 = 0; } From 44ea2b1758d88ad822e65b1c4c21ca6164494e27 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 6 Sep 2009 15:55:37 +0300 Subject: [PATCH 63/84] KVM: VMX: Move MSR_KERNEL_GS_BASE out of the vmx autoload msr area Currently MSR_KERNEL_GS_BASE is saved and restored as part of the guest/host msr reloading. Since we wish to lazy-restore all the other msrs, save and reload MSR_KERNEL_GS_BASE explicitly instead of using the common code. Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 39 ++++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 17730175aa0..32512519e1a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -99,7 +99,8 @@ struct vcpu_vmx { int save_nmsrs; int msr_offset_efer; #ifdef CONFIG_X86_64 - int msr_offset_kernel_gs_base; + u64 msr_host_kernel_gs_base; + u64 msr_guest_kernel_gs_base; #endif struct vmcs *vmcs; struct { @@ -202,7 +203,7 @@ static void ept_save_pdptrs(struct kvm_vcpu *vcpu); */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_K6_STAR, }; @@ -674,10 +675,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) #endif #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) - save_msrs(vmx->host_msrs + - vmx->msr_offset_kernel_gs_base, 1); - + if (is_long_mode(&vmx->vcpu)) { + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + } #endif load_msrs(vmx->guest_msrs, vmx->save_nmsrs); load_transition_efer(vmx); @@ -711,6 +712,12 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) save_msrs(vmx->guest_msrs, vmx->save_nmsrs); load_msrs(vmx->host_msrs, vmx->save_nmsrs); reload_host_efer(vmx); +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) { + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + } +#endif } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -938,9 +945,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_CSTAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); /* @@ -954,10 +958,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) #endif vmx->save_nmsrs = save_nmsrs; -#ifdef CONFIG_X86_64 - vmx->msr_offset_kernel_gs_base = - __find_msr_index(vmx, MSR_KERNEL_GS_BASE); -#endif vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); if (cpu_has_vmx_msr_bitmap()) { @@ -1015,6 +1015,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) case MSR_GS_BASE: data = vmcs_readl(GUEST_GS_BASE); break; + case MSR_KERNEL_GS_BASE: + vmx_load_host_state(to_vmx(vcpu)); + data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + break; case MSR_EFER: return kvm_get_msr_common(vcpu, msr_index, pdata); #endif @@ -1068,6 +1072,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) case MSR_GS_BASE: vmcs_writel(GUEST_GS_BASE, data); break; + case MSR_KERNEL_GS_BASE: + vmx_load_host_state(vmx); + vmx->msr_guest_kernel_gs_base = data; + break; #endif case MSR_IA32_SYSENTER_CS: vmcs_write32(GUEST_SYSENTER_CS, data); @@ -1559,6 +1567,11 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) struct vcpu_vmx *vmx = to_vmx(vcpu); struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + /* + * Force kernel_gs_base reloading before EFER changes, as control + * of this msr depends on is_long_mode(). + */ + vmx_load_host_state(to_vmx(vcpu)); vcpu->arch.shadow_efer = efer; if (!msr) return; From 18863bdd60f895f3b3ba16b15e8331aee781e8ec Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 7 Sep 2009 11:12:18 +0300 Subject: [PATCH 64/84] KVM: x86 shared msr infrastructure The various syscall-related MSRs are fairly expensive to switch. Currently we switch them on every vcpu preemption, which is far too often: - if we're switching to a kernel thread (idle task, threaded interrupt, kernel-mode virtio server (vhost-net), for example) and back, then there's no need to switch those MSRs since kernel threasd won't be exiting to userspace. - if we're switching to another guest running an identical OS, most likely those MSRs will have the same value, so there's little point in reloading them. - if we're running the same OS on the guest and host, the MSRs will have identical values and reloading is unnecessary. This patch uses the new user return notifiers to implement last-minute switching, and checks the msr values to avoid unnecessary reloading. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 3 ++ arch/x86/kvm/Kconfig | 1 + arch/x86/kvm/x86.c | 81 +++++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0558ff8c32a..26a74b7bb6b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -809,4 +809,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); +void kvm_define_shared_msr(unsigned index, u32 msr); +void kvm_set_shared_msr(unsigned index, u64 val); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b84e571f417..4cd49833246 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select HAVE_KVM_IRQCHIP select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE + select USER_RETURN_NOTIFIER ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e16cdc9ec0c..58c5cddf363 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS @@ -87,6 +88,25 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); int ignore_msrs = 0; module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +#define KVM_NR_SHARED_MSRS 16 + +struct kvm_shared_msrs_global { + int nr; + struct kvm_shared_msr { + u32 msr; + u64 value; + } msrs[KVM_NR_SHARED_MSRS]; +}; + +struct kvm_shared_msrs { + struct user_return_notifier urn; + bool registered; + u64 current_value[KVM_NR_SHARED_MSRS]; +}; + +static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; +static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs); + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -123,6 +143,64 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +static void kvm_on_user_return(struct user_return_notifier *urn) +{ + unsigned slot; + struct kvm_shared_msr *global; + struct kvm_shared_msrs *locals + = container_of(urn, struct kvm_shared_msrs, urn); + + for (slot = 0; slot < shared_msrs_global.nr; ++slot) { + global = &shared_msrs_global.msrs[slot]; + if (global->value != locals->current_value[slot]) { + wrmsrl(global->msr, global->value); + locals->current_value[slot] = global->value; + } + } + locals->registered = false; + user_return_notifier_unregister(urn); +} + +void kvm_define_shared_msr(unsigned slot, u32 msr) +{ + int cpu; + u64 value; + + if (slot >= shared_msrs_global.nr) + shared_msrs_global.nr = slot + 1; + shared_msrs_global.msrs[slot].msr = msr; + rdmsrl_safe(msr, &value); + shared_msrs_global.msrs[slot].value = value; + for_each_online_cpu(cpu) + per_cpu(shared_msrs, cpu).current_value[slot] = value; +} +EXPORT_SYMBOL_GPL(kvm_define_shared_msr); + +static void kvm_shared_msr_cpu_online(void) +{ + unsigned i; + struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs); + + for (i = 0; i < shared_msrs_global.nr; ++i) + locals->current_value[i] = shared_msrs_global.msrs[i].value; +} + +void kvm_set_shared_msr(unsigned slot, u64 value) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (value == smsr->current_value[slot]) + return; + smsr->current_value[slot] = value; + wrmsrl(shared_msrs_global.msrs[slot].msr, value); + if (!smsr->registered) { + smsr->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&smsr->urn); + smsr->registered = true; + } +} +EXPORT_SYMBOL_GPL(kvm_set_shared_msr); + unsigned long segment_base(u16 selector) { struct descriptor_table gdt; @@ -4815,6 +4893,9 @@ int kvm_arch_hardware_enable(void *garbage) int cpu = raw_smp_processor_id(); per_cpu(cpu_tsc_khz, cpu) = 0; } + + kvm_shared_msr_cpu_online(); + return kvm_x86_ops->hardware_enable(garbage); } From 26bb0981b3ff00b9177d61fe55806db978862b3c Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Mon, 7 Sep 2009 11:14:12 +0300 Subject: [PATCH 65/84] KVM: VMX: Use shared msr infrastructure Instead of reloading syscall MSRs on every preemption, use the new shared msr infrastructure to reload them at the last possible minute (just before exit to userspace). Improves vcpu/idle/vcpu switches by about 2000 cycles (when EFER needs to be reloaded as well). [jan: fix slot index missing indirection] Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 112 +++++++++++++++++---------------------------- 1 file changed, 42 insertions(+), 70 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 32512519e1a..bf46253149c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -86,6 +86,11 @@ struct vmcs { char data[0]; }; +struct shared_msr_entry { + unsigned index; + u64 data; +}; + struct vcpu_vmx { struct kvm_vcpu vcpu; struct list_head local_vcpus_link; @@ -93,8 +98,7 @@ struct vcpu_vmx { int launched; u8 fail; u32 idt_vectoring_info; - struct kvm_msr_entry *guest_msrs; - struct kvm_msr_entry *host_msrs; + struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; int msr_offset_efer; @@ -108,7 +112,6 @@ struct vcpu_vmx { u16 fs_sel, gs_sel, ldt_sel; int gs_ldt_reload_needed; int fs_reload_needed; - int guest_efer_loaded; } host_state; struct { int vm86_active; @@ -195,6 +198,8 @@ static struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; +static u64 host_efer; + static void ept_save_pdptrs(struct kvm_vcpu *vcpu); /* @@ -209,22 +214,6 @@ static const u32 vmx_msr_index[] = { }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) -static void load_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - wrmsrl(e[i].index, e[i].data); -} - -static void save_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - rdmsrl(e[i].index, e[i].data); -} - static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | @@ -373,7 +362,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) int i; for (i = 0; i < vmx->nmsrs; ++i) - if (vmx->guest_msrs[i].index == msr) + if (vmx_msr_index[vmx->guest_msrs[i].index] == msr) return i; return -1; } @@ -404,7 +393,7 @@ static inline void __invept(int ext, u64 eptp, gpa_t gpa) : : "a" (&operand), "c" (ext) : "cc", "memory"); } -static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) +static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -595,17 +584,15 @@ static void reload_tss(void) load_TR_desc(); } -static void load_transition_efer(struct vcpu_vmx *vmx) +static bool update_transition_efer(struct vcpu_vmx *vmx) { int efer_offset = vmx->msr_offset_efer; - u64 host_efer; u64 guest_efer; u64 ignore_bits; if (efer_offset < 0) - return; - host_efer = vmx->host_msrs[efer_offset].data; - guest_efer = vmx->guest_msrs[efer_offset].data; + return false; + guest_efer = vmx->vcpu.arch.shadow_efer; /* * NX is emulated; LMA and LME handled by hardware; SCE meaninless @@ -619,26 +606,18 @@ static void load_transition_efer(struct vcpu_vmx *vmx) ignore_bits &= ~(u64)EFER_SCE; #endif if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits)) - return; + return false; - vmx->host_state.guest_efer_loaded = 1; guest_efer &= ~ignore_bits; guest_efer |= host_efer & ignore_bits; - wrmsrl(MSR_EFER, guest_efer); - vmx->vcpu.stat.efer_reload++; -} - -static void reload_host_efer(struct vcpu_vmx *vmx) -{ - if (vmx->host_state.guest_efer_loaded) { - vmx->host_state.guest_efer_loaded = 0; - load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1); - } + vmx->guest_msrs[efer_offset].data = guest_efer; + return true; } static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int i; if (vmx->host_state.loaded) return; @@ -680,8 +659,9 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); } #endif - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_transition_efer(vmx); + for (i = 0; i < vmx->save_nmsrs; ++i) + kvm_set_shared_msr(vmx->guest_msrs[i].index, + vmx->guest_msrs[i].data); } static void __vmx_load_host_state(struct vcpu_vmx *vmx) @@ -709,9 +689,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) local_irq_restore(flags); } reload_tss(); - save_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_msrs(vmx->host_msrs, vmx->save_nmsrs); - reload_host_efer(vmx); #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); @@ -908,19 +885,14 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, /* * Swap MSR entry in host/guest MSR entry array. */ -#ifdef CONFIG_X86_64 static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) { - struct kvm_msr_entry tmp; + struct shared_msr_entry tmp; tmp = vmx->guest_msrs[to]; vmx->guest_msrs[to] = vmx->guest_msrs[from]; vmx->guest_msrs[from] = tmp; - tmp = vmx->host_msrs[to]; - vmx->host_msrs[to] = vmx->host_msrs[from]; - vmx->host_msrs[from] = tmp; } -#endif /* * Set up the vmcs to automatically save and restore system @@ -929,15 +901,13 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) */ static void setup_msrs(struct vcpu_vmx *vmx) { - int save_nmsrs; + int save_nmsrs, index; unsigned long *msr_bitmap; vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { - int index; - index = __find_msr_index(vmx, MSR_SYSCALL_MASK); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); @@ -956,9 +926,11 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); } #endif - vmx->save_nmsrs = save_nmsrs; + vmx->msr_offset_efer = index = __find_msr_index(vmx, MSR_EFER); + if (index >= 0 && update_transition_efer(vmx)) + move_msr_up(vmx, index, save_nmsrs++); - vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); + vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) { if (is_long_mode(&vmx->vcpu)) @@ -1000,7 +972,7 @@ static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) { u64 data; - struct kvm_msr_entry *msr; + struct shared_msr_entry *msr; if (!pdata) { printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); @@ -1019,9 +991,9 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) vmx_load_host_state(to_vmx(vcpu)); data = to_vmx(vcpu)->msr_guest_kernel_gs_base; break; +#endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_index, pdata); -#endif case MSR_IA32_TSC: data = guest_read_tsc(); break; @@ -1035,6 +1007,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) data = vmcs_readl(GUEST_SYSENTER_ESP); break; default: + vmx_load_host_state(to_vmx(vcpu)); msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { vmx_load_host_state(to_vmx(vcpu)); @@ -1056,7 +1029,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr; + struct shared_msr_entry *msr; u64 host_tsc; int ret = 0; @@ -1565,7 +1538,10 @@ continue_rmode: static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + + if (!msr) + return; /* * Force kernel_gs_base reloading before EFER changes, as control @@ -2417,10 +2393,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) if (wrmsr_safe(index, data_low, data_high) < 0) continue; data = data_low | ((u64)data_high << 32); - vmx->host_msrs[j].index = index; - vmx->host_msrs[j].reserved = 0; - vmx->host_msrs[j].data = data; - vmx->guest_msrs[j] = vmx->host_msrs[j]; + vmx->guest_msrs[j].index = i; + vmx->guest_msrs[j].data = 0; ++vmx->nmsrs; } @@ -3821,7 +3795,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) __clear_bit(vmx->vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); vmx_free_vmcs(vcpu); - kfree(vmx->host_msrs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); @@ -3848,10 +3821,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto uninit_vcpu; } - vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!vmx->host_msrs) - goto free_guest_msrs; - vmx->vmcs = alloc_vmcs(); if (!vmx->vmcs) goto free_msrs; @@ -3882,8 +3851,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) free_vmcs: free_vmcs(vmx->vmcs); free_msrs: - kfree(vmx->host_msrs); -free_guest_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); @@ -4033,7 +4000,12 @@ static struct kvm_x86_ops vmx_x86_ops = { static int __init vmx_init(void) { - int r; + int r, i; + + rdmsrl_safe(MSR_EFER, &host_efer); + + for (i = 0; i < NR_VMX_MSR; ++i) + kvm_define_shared_msr(i, vmx_msr_index[i]); vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_io_bitmap_a) From c0a187e12d48235cb8af4cdeff283117ab42bbb2 Mon Sep 17 00:00:00 2001 From: Hollis Blanchard Date: Fri, 23 Oct 2009 00:35:30 +0000 Subject: [PATCH 66/84] KVM: powerpc: Fix BUILD_BUG_ON condition The old BUILD_BUG_ON implementation didn't work with __builtin_constant_p(). Fixing that revealed this test had been inverted for a long time without anybody noticing... Signed-off-by: Hollis Blanchard Signed-off-by: Avi Kivity --- arch/powerpc/kvm/timing.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index 806ef67868b..8167d42a776 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -51,7 +51,7 @@ static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type) /* The BUILD_BUG_ON below breaks in funny ways, commented out * for now ... -BenH - BUILD_BUG_ON(__builtin_constant_p(type)); + BUILD_BUG_ON(!__builtin_constant_p(type)); */ switch (type) { case EXT_INTR_EXITS: From 1655e3a3dc16e21b60d9950e201b38a9894f1bcf Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 25 Oct 2009 17:45:07 +0200 Subject: [PATCH 67/84] KVM: remove duplicated task_switch check Probably introduced by a bad merge. Signed-off-by: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 58c5cddf363..dbddcc2d2c9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4525,11 +4525,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); } - /* set back link to prev task only if NT bit is set in eflags - note that old_tss_sel is not used afetr this point */ - if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) - old_tss_sel = 0xffff; - /* set back link to prev task only if NT bit is set in eflags note that old_tss_sel is not used afetr this point */ if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) From 7c93be44a4790b0fd9dddf29c5503cf86c105304 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 26 Oct 2009 16:48:33 -0200 Subject: [PATCH 68/84] KVM: VMX: move CR3/PDPTR update to vmx_set_cr3 GUEST_CR3 is updated via kvm_set_cr3 whenever CR3 is modified from outside guest context. Similarly pdptrs are updated via load_pdptrs. Let kvm_set_cr3 perform the update, removing it from the vcpu_run fast path. Signed-off-by: Marcelo Tosatti Acked-by: Acked-by: Sheng Yang Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 5 +---- arch/x86/kvm/x86.c | 4 +++- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bf46253149c..a5f3f3ec69e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1737,6 +1737,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vmcs_write64(EPT_POINTER, eptp); guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 : vcpu->kvm->arch.ept_identity_map_addr; + ept_load_pdptrs(vcpu); } vmx_flush_tlb(vcpu); @@ -3625,10 +3626,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (enable_ept && is_paging(vcpu)) { - vmcs_writel(GUEST_CR3, vcpu->arch.cr3); - ept_load_pdptrs(vcpu); - } /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index dbddcc2d2c9..719f31eecd3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4591,8 +4591,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) + if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.cr3); + mmu_reset_needed = 1; + } if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); From 5f5c35aad5ccaa8f1bd5d9e12f9f5251f3180093 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Mon, 26 Oct 2009 16:50:14 -0200 Subject: [PATCH 69/84] KVM: MMU: update invlpg handler comment Large page translations are always synchronized (either in level 3 or level 2), so its not necessary to properly deal with them in the invlpg handler. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/paging_tmpl.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 72558f8ff3f..a6017132fba 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -467,7 +467,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) level = iterator.level; sptep = iterator.sptep; - /* FIXME: properly handle invlpg on large guest pages */ if (level == PT_PAGE_TABLE_LEVEL || ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) { From 92c0d900159a4fa582e1c8ebcc1c4a8020defff5 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 29 Oct 2009 11:00:16 +0200 Subject: [PATCH 70/84] KVM: VMX: Remove vmx->msr_offset_efer This variable is used to communicate between a caller and a callee; switch to a function argument instead. Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a5f3f3ec69e..c9cc9596e1a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -101,7 +101,6 @@ struct vcpu_vmx { struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; - int msr_offset_efer; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; u64 msr_guest_kernel_gs_base; @@ -584,14 +583,11 @@ static void reload_tss(void) load_TR_desc(); } -static bool update_transition_efer(struct vcpu_vmx *vmx) +static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - int efer_offset = vmx->msr_offset_efer; u64 guest_efer; u64 ignore_bits; - if (efer_offset < 0) - return false; guest_efer = vmx->vcpu.arch.shadow_efer; /* @@ -926,8 +922,8 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); } #endif - vmx->msr_offset_efer = index = __find_msr_index(vmx, MSR_EFER); - if (index >= 0 && update_transition_efer(vmx)) + index = __find_msr_index(vmx, MSR_EFER); + if (index >= 0 && update_transition_efer(vmx, index)) move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; From 3ddea128ad75bd33e88780fe44f44c3717369b98 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 29 Oct 2009 13:44:15 -0200 Subject: [PATCH 71/84] KVM: x86: disallow multiple KVM_CREATE_IRQCHIP Otherwise kvm will leak memory on multiple KVM_CREATE_IRQCHIP. Also serialize multiple accesses with kvm->lock. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/irq.h | 6 +++++- arch/x86/kvm/x86.c | 30 ++++++++++++++++++++++-------- 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index c025a2362aa..be399e207d5 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -86,7 +86,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) static inline int irqchip_in_kernel(struct kvm *kvm) { - return pic_irqchip(kvm) != NULL; + int ret; + + ret = (pic_irqchip(kvm) != NULL); + smp_rmb(); + return ret; } void kvm_pic_reset(struct kvm_kpic_state *s); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 719f31eecd3..97f6f9565ac 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2362,25 +2362,39 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) goto out; break; - case KVM_CREATE_IRQCHIP: + case KVM_CREATE_IRQCHIP: { + struct kvm_pic *vpic; + + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpic) + goto create_irqchip_unlock; r = -ENOMEM; - kvm->arch.vpic = kvm_create_pic(kvm); - if (kvm->arch.vpic) { + vpic = kvm_create_pic(kvm); + if (vpic) { r = kvm_ioapic_init(kvm); if (r) { - kfree(kvm->arch.vpic); - kvm->arch.vpic = NULL; - goto out; + kfree(vpic); + goto create_irqchip_unlock; } } else - goto out; + goto create_irqchip_unlock; + smp_wmb(); + kvm->arch.vpic = vpic; + smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { + mutex_lock(&kvm->irq_lock); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); - goto out; + kvm->arch.vpic = NULL; + kvm->arch.vioapic = NULL; + mutex_unlock(&kvm->irq_lock); } + create_irqchip_unlock: + mutex_unlock(&kvm->lock); break; + } case KVM_CREATE_PIT: u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; From 2204ae3c96e9a1fed50f7ee19ce092e69d7dfe82 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 29 Oct 2009 13:44:16 -0200 Subject: [PATCH 72/84] KVM: x86: disallow KVM_{SET,GET}_LAPIC without allocated in-kernel lapic Otherwise kvm might attempt to dereference a NULL pointer. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97f6f9565ac..cd6fe0a5797 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1893,6 +1893,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_GET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; @@ -1908,6 +1911,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; if (!lapic) From e50212bb51356f0df48d6cce0aae5acf41df336d Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 29 Oct 2009 13:44:17 -0200 Subject: [PATCH 73/84] KVM: only clear irq_source_id if irqchip is present Otherwise kvm might attempt to dereference a NULL pointer. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- virt/kvm/irq_comm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index 0d454d35271..9b077342ab5 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -243,6 +243,10 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); goto unlock; } + clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); + if (!irqchip_in_kernel(kvm)) + goto unlock; + for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) { clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]); if (i >= 16) @@ -251,7 +255,6 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]); #endif } - clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); unlock: mutex_unlock(&kvm->irq_lock); } From 4f926bf291863c237188bd2e27222ed801f12094 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 30 Oct 2009 12:46:59 +0100 Subject: [PATCH 74/84] KVM: x86: Polish exception injection via KVM_SET_GUEST_DEBUG Decouple KVM_GUESTDBG_INJECT_DB and KVM_GUESTDBG_INJECT_BP from KVM_GUESTDBG_ENABLE, their are actually orthogonal. At this chance, avoid triggering the WARN_ON in kvm_queue_exception if there is already an exception pending and reject such invalid requests. Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd6fe0a5797..ba8958dca3c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4656,10 +4656,20 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { unsigned long rflags; - int i; + int i, r; vcpu_load(vcpu); + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { + r = -EBUSY; + if (vcpu->arch.exception.pending) + goto unlock_out; + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else + kvm_queue_exception(vcpu, BP_VECTOR); + } + /* * Read rflags as long as potentially injected trace flags are still * filtered out. @@ -4695,14 +4705,12 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, kvm_x86_ops->set_guest_debug(vcpu, dbg); - if (vcpu->guest_debug & KVM_GUESTDBG_INJECT_DB) - kvm_queue_exception(vcpu, DB_VECTOR); - else if (vcpu->guest_debug & KVM_GUESTDBG_INJECT_BP) - kvm_queue_exception(vcpu, BP_VECTOR); + r = 0; +unlock_out: vcpu_put(vcpu); - return 0; + return r; } /* From c54d2aba27f0c505d61700d656c5943e96982e60 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Mon, 2 Nov 2009 17:20:28 +0100 Subject: [PATCH 75/84] KVM: Reorder IOCTLs in main kvm.h Obviously, people tend to extend this header at the bottom - more or less blindly. Ensure that deprecated stuff gets its own corner again by moving things to the top. Also add some comments and reindent IOCTLs to make them more readable and reduce the risk of number collisions. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm.h | 235 ++++++++++++++++++++++---------------------- 1 file changed, 117 insertions(+), 118 deletions(-) diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 6ed1a12ed52..ca62b8e056f 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -14,12 +14,76 @@ #define KVM_API_VERSION 12 -/* for KVM_TRACE_ENABLE, deprecated */ +/* *** Deprecated interfaces *** */ + +#define KVM_TRC_SHIFT 16 + +#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) +#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) + +#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) +#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) +#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) + +#define KVM_TRC_HEAD_SIZE 12 +#define KVM_TRC_CYCLE_SIZE 8 +#define KVM_TRC_EXTRA_MAX 7 + +#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) +#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) +#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) +#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) +#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) +#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) +#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) +#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) +#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) +#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) +#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) +#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) +#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) +#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) +#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) +#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) +#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) +#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) +#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) +#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) +#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) +#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) +#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) +#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) + struct kvm_user_trace_setup { - __u32 buf_size; /* sub_buffer size of each per-cpu */ - __u32 buf_nr; /* the number of sub_buffers of each per-cpu */ + __u32 buf_size; + __u32 buf_nr; }; +#define __KVM_DEPRECATED_MAIN_W_0x06 \ + _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) +#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07) +#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08) + +#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq) + +struct kvm_breakpoint { + __u32 enabled; + __u32 padding; + __u64 address; +}; + +struct kvm_debug_guest { + __u32 enabled; + __u32 pad; + struct kvm_breakpoint breakpoints[4]; + __u32 singlestep; +}; + +#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest) + +/* *** End of deprecated interfaces *** */ + + /* for KVM_CREATE_MEMORY_REGION */ struct kvm_memory_region { __u32 slot; @@ -329,24 +393,6 @@ struct kvm_ioeventfd { __u8 pad[36]; }; -#define KVM_TRC_SHIFT 16 -/* - * kvm trace categories - */ -#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT) -#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1)) /* only 12 bits */ - -/* - * kvm trace action - */ -#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01) -#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02) -#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01) - -#define KVM_TRC_HEAD_SIZE 12 -#define KVM_TRC_CYCLE_SIZE 8 -#define KVM_TRC_EXTRA_MAX 7 - #define KVMIO 0xAE /* @@ -367,12 +413,10 @@ struct kvm_ioeventfd { */ #define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ #define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) -/* - * ioctls for kvm trace - */ -#define KVM_TRACE_ENABLE _IOW(KVMIO, 0x06, struct kvm_user_trace_setup) -#define KVM_TRACE_PAUSE _IO(KVMIO, 0x07) -#define KVM_TRACE_DISABLE _IO(KVMIO, 0x08) +#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06 +#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 +#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 + /* * Extension capability list. */ @@ -522,56 +566,57 @@ struct kvm_clock_data { /* * ioctls for VM fds */ -#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) +#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. */ -#define KVM_CREATE_VCPU _IO(KVMIO, 0x41) -#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) -#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) -#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\ +#define KVM_CREATE_VCPU _IO(KVMIO, 0x41) +#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) +#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) +#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ struct kvm_userspace_memory_region) -#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) -#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) +#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) +#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) /* Device model IOC */ -#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) -#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) -#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) -#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) -#define KVM_CREATE_PIT _IO(KVMIO, 0x64) -#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) -#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) -#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) +#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) +#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) +#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) +#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) +#define KVM_CREATE_PIT _IO(KVMIO, 0x64) +#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) +#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) +#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) #define KVM_REGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) #define KVM_UNREGISTER_COALESCED_MMIO \ _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) -#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ - struct kvm_assigned_pci_dev) -#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) +#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \ + struct kvm_assigned_pci_dev) +#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) /* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */ -#define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \ - struct kvm_assigned_irq) -#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) -#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) -#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ - struct kvm_assigned_pci_dev) -#define KVM_ASSIGN_SET_MSIX_NR \ - _IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr) -#define KVM_ASSIGN_SET_MSIX_ENTRY \ - _IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry) -#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) -#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) -#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) -#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) -#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) -#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) -#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data) -#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data) - +#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70 +#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq) +#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) +#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \ + struct kvm_assigned_pci_dev) +#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \ + struct kvm_assigned_msix_nr) +#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \ + struct kvm_assigned_msix_entry) +#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq) +#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) +#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) +#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) +#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) +#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) +#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data) +#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data) +/* Available with KVM_CAP_PIT_STATE2 */ +#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2) +#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* * ioctls for vcpu fds @@ -584,7 +629,7 @@ struct kvm_clock_data { #define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) #define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) /* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */ -#define KVM_DEBUG_GUEST __KVM_DEPRECATED_DEBUG_GUEST +#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87 #define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) #define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) #define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) @@ -596,7 +641,7 @@ struct kvm_clock_data { #define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2) #define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) /* Available with KVM_CAP_VAPIC */ -#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) +#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) /* Available with KVM_CAP_VAPIC */ #define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr) /* valid for virtual machine (for floating interrupt)_and_ vcpu */ @@ -608,67 +653,21 @@ struct kvm_clock_data { /* initial ipl psw for s390 */ #define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw) /* initial reset for s390 */ -#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) +#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) #define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state) #define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) /* Available with KVM_CAP_NMI */ -#define KVM_NMI _IO(KVMIO, 0x9a) +#define KVM_NMI _IO(KVMIO, 0x9a) /* Available with KVM_CAP_SET_GUEST_DEBUG */ #define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug) /* MCE for x86 */ #define KVM_X86_SETUP_MCE _IOW(KVMIO, 0x9c, __u64) #define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO, 0x9d, __u64) #define KVM_X86_SET_MCE _IOW(KVMIO, 0x9e, struct kvm_x86_mce) - -/* - * Deprecated interfaces - */ -struct kvm_breakpoint { - __u32 enabled; - __u32 padding; - __u64 address; -}; - -struct kvm_debug_guest { - __u32 enabled; - __u32 pad; - struct kvm_breakpoint breakpoints[4]; - __u32 singlestep; -}; - -#define __KVM_DEPRECATED_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest) - +/* IA64 stack access */ #define KVM_IA64_VCPU_GET_STACK _IOR(KVMIO, 0x9a, void *) #define KVM_IA64_VCPU_SET_STACK _IOW(KVMIO, 0x9b, void *) -#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2) -#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) - -#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02) -#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03) -#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04) -#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05) -#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06) -#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07) -#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08) -#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09) -#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A) -#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B) -#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C) -#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D) -#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E) -#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F) -#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10) -#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11) -#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12) -#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13) -#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14) -#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15) -#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16) -#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17) -#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18) -#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19) - #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) struct kvm_assigned_pci_dev { @@ -722,4 +721,4 @@ struct kvm_assigned_msix_entry { __u16 padding[3]; }; -#endif +#endif /* __LINUX_KVM_H */ From a9c7399d6cda0a092b347f8ee49bbe44f6e1fe66 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 4 Nov 2009 11:54:59 +0200 Subject: [PATCH 76/84] KVM: Allow internal errors reported to userspace to carry extra data 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: Avi Kivity --- arch/x86/kvm/mmu.c | 1 + arch/x86/kvm/vmx.c | 1 + include/linux/kvm.h | 4 ++++ virt/kvm/kvm_main.c | 1 + 4 files changed, 7 insertions(+) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a9024797b21..4c3e5b2314c 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2800,6 +2800,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) case EMULATE_FAIL: vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; default: BUG(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c9cc9596e1a..c0e66dd58a4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3352,6 +3352,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) kvm_report_emulation_failure(vcpu, "emulation failure"); vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; ret = 0; goto out; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index ca62b8e056f..172639e9439 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -251,6 +251,9 @@ struct kvm_run { } dcr; struct { __u32 suberror; + /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */ + __u32 ndata; + __u64 data[16]; } internal; /* Fix the size of the union. */ char padding[256]; @@ -484,6 +487,7 @@ struct kvm_ioeventfd { #define KVM_CAP_XEN_HVM 38 #endif #define KVM_CAP_ADJUST_CLOCK 39 +#define KVM_CAP_INTERNAL_ERROR_DATA 40 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index bd44fb48ac4..f92ba138007 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1653,6 +1653,7 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) #ifdef CONFIG_KVM_APIC_ARCHITECTURE case KVM_CAP_SET_BOOT_CPU_ID: #endif + case KVM_CAP_INTERNAL_ERROR_DATA: return 1; #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQ_ROUTING: From 65ac7264043740572ba804edca03c374d70427c9 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 4 Nov 2009 11:59:01 +0200 Subject: [PATCH 77/84] KVM: VMX: Report unexpected simultaneous exceptions as internal errors These happen when we trap an exception when another exception is being delivered; we only expect these with MCEs and page faults. If something unexpected happens, things probably went south and we're better off reporting an internal error and freezing. Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 11 ++++++++--- include/linux/kvm.h | 1 + 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c0e66dd58a4..22fcd27a0b5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2744,9 +2744,14 @@ static int handle_exception(struct kvm_vcpu *vcpu) return handle_machine_check(vcpu); if ((vect_info & VECTORING_INFO_VALID_MASK) && - !is_page_fault(intr_info)) - printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " - "intr info 0x%x\n", __func__, vect_info, intr_info); + !is_page_fault(intr_info)) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = vect_info; + vcpu->run->internal.data[1] = intr_info; + return 0; + } if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR) return 1; /* already handled by vmx_vcpu_run() */ diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 172639e9439..976f4d18185 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -163,6 +163,7 @@ struct kvm_pit_config { /* For KVM_EXIT_INTERNAL_ERROR */ #define KVM_INTERNAL_ERROR_EMULATION 1 +#define KVM_INTERNAL_ERROR_SIMUL_EX 2 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { From 3cfc3092f40bc37c57ba556cfd8de4218f2135ab Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Thu, 12 Nov 2009 01:04:25 +0100 Subject: [PATCH 78/84] KVM: x86: Add KVM_GET/SET_VCPU_EVENTS This new IOCTL exports all yet user-invisible states related to exceptions, interrupts, and NMIs. Together with appropriate user space changes, this fixes sporadic problems of vmsave/restore, live migration and system reset. [avi: future-proof abi by adding a flags field] Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- Documentation/kvm/api.txt | 49 +++++++++++++++++++++ arch/x86/include/asm/kvm.h | 28 ++++++++++++ arch/x86/include/asm/kvm_host.h | 2 + arch/x86/kvm/svm.c | 22 ++++++++++ arch/x86/kvm/vmx.c | 30 +++++++++++++ arch/x86/kvm/x86.c | 77 +++++++++++++++++++++++++++++++++ include/linux/kvm.h | 6 +++ 7 files changed, 214 insertions(+) diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt index 36594ba5772..e1a11416102 100644 --- a/Documentation/kvm/api.txt +++ b/Documentation/kvm/api.txt @@ -653,6 +653,55 @@ struct kvm_clock_data { __u32 pad[9]; }; +4.29 KVM_GET_VCPU_EVENTS + +Capability: KVM_CAP_VCPU_EVENTS +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_vcpu_event (out) +Returns: 0 on success, -1 on error + +Gets currently pending exceptions, interrupts, and NMIs as well as related +states of the vcpu. + +struct kvm_vcpu_events { + struct { + __u8 injected; + __u8 nr; + __u8 has_error_code; + __u8 pad; + __u32 error_code; + } exception; + struct { + __u8 injected; + __u8 nr; + __u8 soft; + __u8 pad; + } interrupt; + struct { + __u8 injected; + __u8 pending; + __u8 masked; + __u8 pad; + } nmi; + __u32 sipi_vector; + __u32 flags; /* must be zero */ +}; + +4.30 KVM_SET_VCPU_EVENTS + +Capability: KVM_CAP_VCPU_EVENTS +Architectures: x86 +Type: vm ioctl +Parameters: struct kvm_vcpu_event (in) +Returns: 0 on success, -1 on error + +Set pending exceptions, interrupts, and NMIs as well as related states of the +vcpu. + +See KVM_GET_VCPU_EVENTS for the data structure. + + 5. The kvm_run structure Application code obtains a pointer to the kvm_run structure by diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index ef9b4b73cce..950df434763 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -20,6 +20,7 @@ #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 #define __KVM_HAVE_XEN_HVM +#define __KVM_HAVE_VCPU_EVENTS /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -252,4 +253,31 @@ struct kvm_reinject_control { __u8 pit_reinject; __u8 reserved[31]; }; + +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 injected; + __u8 nr; + __u8 has_error_code; + __u8 pad; + __u32 error_code; + } exception; + struct { + __u8 injected; + __u8 nr; + __u8 soft; + __u8 pad; + } interrupt; + struct { + __u8 injected; + __u8 pending; + __u8 masked; + __u8 pad; + } nmi; + __u32 sipi_vector; + __u32 flags; + __u32 reserved[10]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 26a74b7bb6b..06e085614da 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -523,6 +523,8 @@ struct kvm_x86_ops { bool has_error_code, u32 error_code); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); + bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); + void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 34b700f9e49..3de0b37ec03 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2499,6 +2499,26 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu) !(svm->vcpu.arch.hflags & HF_NMI_MASK); } +static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return !!(svm->vcpu.arch.hflags & HF_NMI_MASK); +} + +static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (masked) { + svm->vcpu.arch.hflags |= HF_NMI_MASK; + svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET); + } else { + svm->vcpu.arch.hflags &= ~HF_NMI_MASK; + svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); + } +} + static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2946,6 +2966,8 @@ static struct kvm_x86_ops svm_x86_ops = { .queue_exception = svm_queue_exception, .interrupt_allowed = svm_interrupt_allowed, .nmi_allowed = svm_nmi_allowed, + .get_nmi_mask = svm_get_nmi_mask, + .set_nmi_mask = svm_set_nmi_mask, .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 22fcd27a0b5..778f059ae42 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2639,6 +2639,34 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } +static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + if (!cpu_has_virtual_nmis()) + return to_vmx(vcpu)->soft_vnmi_blocked; + else + return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + GUEST_INTR_STATE_NMI); +} + +static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!cpu_has_virtual_nmis()) { + if (vmx->soft_vnmi_blocked != masked) { + vmx->soft_vnmi_blocked = masked; + vmx->vnmi_blocked_time = 0; + } + } else { + if (masked) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + else + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + } +} + static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && @@ -3985,6 +4013,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .queue_exception = vmx_queue_exception, .interrupt_allowed = vmx_interrupt_allowed, .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ba8958dca3c..35eea30821d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1342,6 +1342,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_XEN_HVM: case KVM_CAP_ADJUST_CLOCK: + case KVM_CAP_VCPU_EVENTS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1883,6 +1884,61 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; } +static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_load(vcpu); + + events->exception.injected = vcpu->arch.exception.pending; + events->exception.nr = vcpu->arch.exception.nr; + events->exception.has_error_code = vcpu->arch.exception.has_error_code; + events->exception.error_code = vcpu->arch.exception.error_code; + + events->interrupt.injected = vcpu->arch.interrupt.pending; + events->interrupt.nr = vcpu->arch.interrupt.nr; + events->interrupt.soft = vcpu->arch.interrupt.soft; + + events->nmi.injected = vcpu->arch.nmi_injected; + events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + + events->sipi_vector = vcpu->arch.sipi_vector; + + events->flags = 0; + + vcpu_put(vcpu); +} + +static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + if (events->flags) + return -EINVAL; + + vcpu_load(vcpu); + + vcpu->arch.exception.pending = events->exception.injected; + vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.has_error_code = events->exception.has_error_code; + vcpu->arch.exception.error_code = events->exception.error_code; + + vcpu->arch.interrupt.pending = events->interrupt.injected; + vcpu->arch.interrupt.nr = events->interrupt.nr; + vcpu->arch.interrupt.soft = events->interrupt.soft; + if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) + kvm_pic_clear_isr_ack(vcpu->kvm); + + vcpu->arch.nmi_injected = events->nmi.injected; + vcpu->arch.nmi_pending = events->nmi.pending; + kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + + vcpu->arch.sipi_vector = events->sipi_vector; + + vcpu_put(vcpu); + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2040,6 +2096,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); break; } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); + + r = -EFAULT; + if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) + break; + r = 0; + break; + } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + r = -EFAULT; + if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) + break; + + r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + break; + } default: r = -EINVAL; } diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 976f4d18185..92045a92d71 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -489,6 +489,9 @@ struct kvm_ioeventfd { #endif #define KVM_CAP_ADJUST_CLOCK 39 #define KVM_CAP_INTERNAL_ERROR_DATA 40 +#ifdef __KVM_HAVE_VCPU_EVENTS +#define KVM_CAP_VCPU_EVENTS 41 +#endif #ifdef KVM_CAP_IRQ_ROUTING @@ -672,6 +675,9 @@ struct kvm_clock_data { /* IA64 stack access */ #define KVM_IA64_VCPU_GET_STACK _IOR(KVMIO, 0x9a, void *) #define KVM_IA64_VCPU_SET_STACK _IOW(KVMIO, 0x9b, void *) +/* 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) #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) From d7b0b5eb3000c6fb902f08c619fcd673a23d8fab Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Thu, 19 Nov 2009 14:21:16 +0100 Subject: [PATCH 79/84] KVM: s390: Make psw available on all exits, not just a subset This patch moves s390 processor status word into the base kvm_run struct and keeps it up-to date on all userspace exits. The userspace ABI is broken by this, however there are no applications in the wild using this. A capability check is provided so users can verify the updated API exists. Cc: stable@kernel.org Signed-off-by: Carsten Otte Signed-off-by: Avi Kivity --- arch/s390/include/asm/kvm.h | 3 ++- arch/s390/kvm/kvm-s390.c | 25 +++++++++++++++++-------- include/linux/kvm.h | 8 ++++++-- 3 files changed, 25 insertions(+), 11 deletions(-) diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h index 3dfcaeb5d7f..82b32a100c7 100644 --- a/arch/s390/include/asm/kvm.h +++ b/arch/s390/include/asm/kvm.h @@ -1,6 +1,5 @@ #ifndef __LINUX_KVM_S390_H #define __LINUX_KVM_S390_H - /* * asm-s390/kvm.h - KVM s390 specific structures and definitions * @@ -15,6 +14,8 @@ */ #include +#define __KVM_S390 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 544505893c9..f8bcaefd7d3 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -117,10 +117,16 @@ long kvm_arch_dev_ioctl(struct file *filp, int kvm_dev_ioctl_check_extension(long ext) { + int r; + switch (ext) { + case KVM_CAP_S390_PSW: + r = 1; + break; default: - return 0; + r = 0; } + return r; } /* Section: vm related */ @@ -420,8 +426,10 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw) vcpu_load(vcpu); if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING) rc = -EBUSY; - else - vcpu->arch.sie_block->gpsw = psw; + else { + vcpu->run->psw_mask = psw.mask; + vcpu->run->psw_addr = psw.addr; + } vcpu_put(vcpu); return rc; } @@ -509,9 +517,6 @@ rerun_vcpu: switch (kvm_run->exit_reason) { case KVM_EXIT_S390_SIEIC: - vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask; - vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr; - break; case KVM_EXIT_UNKNOWN: case KVM_EXIT_INTR: case KVM_EXIT_S390_RESET: @@ -520,6 +525,9 @@ rerun_vcpu: BUG(); } + vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask; + vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr; + might_fault(); do { @@ -539,8 +547,6 @@ rerun_vcpu: /* intercept cannot be handled in-kernel, prepare kvm-run */ kvm_run->exit_reason = KVM_EXIT_S390_SIEIC; kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; - kvm_run->s390_sieic.mask = vcpu->arch.sie_block->gpsw.mask; - kvm_run->s390_sieic.addr = vcpu->arch.sie_block->gpsw.addr; kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; rc = 0; @@ -552,6 +558,9 @@ rerun_vcpu: rc = 0; } + kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask; + kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr; + if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 92045a92d71..2d241da0723 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -181,6 +181,11 @@ struct kvm_run { __u64 cr8; __u64 apic_base; +#ifdef __KVM_S390 + /* the processor status word for s390 */ + __u64 psw_mask; /* psw upper half */ + __u64 psw_addr; /* psw lower half */ +#endif union { /* KVM_EXIT_UNKNOWN */ struct { @@ -232,8 +237,6 @@ struct kvm_run { /* KVM_EXIT_S390_SIEIC */ struct { __u8 icptcode; - __u64 mask; /* psw upper half */ - __u64 addr; /* psw lower half */ __u16 ipa; __u32 ipb; } s390_sieic; @@ -492,6 +495,7 @@ struct kvm_ioeventfd { #ifdef __KVM_HAVE_VCPU_EVENTS #define KVM_CAP_VCPU_EVENTS 41 #endif +#define KVM_CAP_S390_PSW 42 #ifdef KVM_CAP_IRQ_ROUTING From eb3c79e64a70fb8f7473e30fa07e89c1ecc2c9bb Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Tue, 24 Nov 2009 15:20:15 +0200 Subject: [PATCH 80/84] KVM: x86 emulator: limit instructions to 15 bytes While we are never normally passed an instruction that exceeds 15 bytes, smp games can cause us to attempt to interpret one, which will cause large latencies in non-preempt hosts. Cc: stable@kernel.org Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_emulate.h | 2 +- arch/x86/kvm/emulate.c | 5 ++++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index b7ed2c42311..7c18e1230f5 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -129,7 +129,7 @@ struct decode_cache { u8 seg_override; unsigned int d; unsigned long regs[NR_VCPU_REGS]; - unsigned long eip; + unsigned long eip, eip_orig; /* modrm */ u8 modrm; u8 modrm_mod; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d226dff47d7..7e8faea4651 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -622,6 +622,9 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, { int rc = 0; + /* x86 instructions are limited to 15 bytes. */ + if (eip + size - ctxt->decode.eip_orig > 15) + return X86EMUL_UNHANDLEABLE; eip += ctxt->cs_base; while (size--) { rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); @@ -880,7 +883,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) /* Shadow copy of register state. Committed on successful emulation. */ memset(c, 0, sizeof(struct decode_cache)); - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu); ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); From 046d87103addc117f0d397196e85189722d4d7de Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Fri, 27 Nov 2009 16:46:26 +0800 Subject: [PATCH 81/84] KVM: VMX: Disable unrestricted guest when EPT disabled Otherwise would cause VMEntry failure when using ept=0 on unrestricted guest supported processors. Signed-off-by: Sheng Yang Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/vmx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 778f059ae42..ed97c6c7e64 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2309,8 +2309,10 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; - if (!enable_ept) + if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + enable_unrestricted_guest = 0; + } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) From 3548bab501887a698a887639b54d5ecaf35c387b Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sat, 28 Nov 2009 14:18:47 +0200 Subject: [PATCH 82/84] KVM: Drop user return notifier when disabling virtualization on a cpu This way, we don't leave a dangling notifier on cpu hotunplug or module unload. In particular, module unload leaves the notifier pointing into freed memory. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 35eea30821d..106f9f1f78c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -201,6 +201,14 @@ void kvm_set_shared_msr(unsigned slot, u64 value) } EXPORT_SYMBOL_GPL(kvm_set_shared_msr); +static void drop_user_return_notifiers(void *ignore) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (smsr->registered) + kvm_on_user_return(&smsr->urn); +} + unsigned long segment_base(u16 selector) { struct descriptor_table gdt; @@ -5004,6 +5012,7 @@ int kvm_arch_hardware_enable(void *garbage) void kvm_arch_hardware_disable(void *garbage) { kvm_x86_ops->hardware_disable(garbage); + drop_user_return_notifiers(garbage); } int kvm_arch_hardware_setup(void) From f50146bd7bdb75435638e60d4960edd9bcdf88b8 Mon Sep 17 00:00:00 2001 From: Carsten Otte Date: Mon, 30 Nov 2009 17:14:41 +0100 Subject: [PATCH 83/84] KVM: s390: Fix prefix register checking in arch/s390/kvm/sigp.c This patch corrects the checking of the new address for the prefix register. On s390, the prefix register is used to address the cpu's lowcore (address 0...8k). This check is supposed to verify that the memory is readable and present. copy_from_guest is a helper function, that can be used to read from guest memory. It applies prefixing, adds the start address of the guest memory in user, and then calls copy_from_user. Previous code was obviously broken for two reasons: - prefixing should not be applied here. The current prefix register is going to be updated soon, and the address we're looking for will be 0..8k after we've updated the register - we're adding the guest origin (gmsor) twice: once in subject code and once in copy_from_guest With kuli, we did not hit this problem because (a) we were lucky with previous prefix register content, and (b) our guest memory was mmaped very low into user address space. Cc: stable@kernel.org Signed-off-by: Carsten Otte Reported-by: Alexander Graf Signed-off-by: Avi Kivity --- arch/s390/kvm/sigp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 40c8c6748cf..15ee1111de5 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -188,9 +188,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, /* make sure that the new value is valid memory */ address = address & 0x7fffe000u; - if ((copy_from_guest(vcpu, &tmp, - (u64) (address + vcpu->arch.sie_block->gmsor) , 1)) || - (copy_from_guest(vcpu, &tmp, (u64) (address + + if ((copy_from_user(&tmp, (void __user *) + (address + vcpu->arch.sie_block->gmsor) , 1)) || + (copy_from_user(&tmp, (void __user *)(address + vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) { *reg |= SIGP_STAT_INVALID_PARAMETER; return 1; /* invalid parameter */ From d5696725b2a4c59503f5e0bc33adeee7f30cd45b Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 2 Dec 2009 12:28:47 +0200 Subject: [PATCH 84/84] KVM: VMX: Fix comparison of guest efer with stale host value update_transition_efer() masks out some efer bits when deciding whether to switch the msr during guest entry; for example, NX is emulated using the mmu so we don't need to disable it, and LMA/LME are handled by the hardware. However, with shared msrs, the comparison is made against a stale value; at the time of the guest switch we may be running with another guest's efer. Fix by deferring the mask/compare to the actual point of guest entry. Noted by Marcelo. Signed-off-by: Avi Kivity --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/vmx.c | 9 +++++---- arch/x86/kvm/x86.c | 4 ++-- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 06e085614da..4f865e8b854 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -812,6 +812,6 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_define_shared_msr(unsigned index, u32 msr); -void kvm_set_shared_msr(unsigned index, u64 val); +void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ed97c6c7e64..d4918d6fc92 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -89,6 +89,7 @@ struct vmcs { struct shared_msr_entry { unsigned index; u64 data; + u64 mask; }; struct vcpu_vmx { @@ -601,12 +602,10 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits)) - return false; - guest_efer &= ~ignore_bits; guest_efer |= host_efer & ignore_bits; vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; return true; } @@ -657,7 +656,8 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) #endif for (i = 0; i < vmx->save_nmsrs; ++i) kvm_set_shared_msr(vmx->guest_msrs[i].index, - vmx->guest_msrs[i].data); + vmx->guest_msrs[i].data, + vmx->guest_msrs[i].mask); } static void __vmx_load_host_state(struct vcpu_vmx *vmx) @@ -2394,6 +2394,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) data = data_low | ((u64)data_high << 32); vmx->guest_msrs[j].index = i; vmx->guest_msrs[j].data = 0; + vmx->guest_msrs[j].mask = -1ull; ++vmx->nmsrs; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 106f9f1f78c..ce677b20bf8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -185,11 +185,11 @@ static void kvm_shared_msr_cpu_online(void) locals->current_value[i] = shared_msrs_global.msrs[i].value; } -void kvm_set_shared_msr(unsigned slot, u64 value) +void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) { struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); - if (value == smsr->current_value[slot]) + if (((value ^ smsr->current_value[slot]) & mask) == 0) return; smsr->current_value[slot] = value; wrmsrl(shared_msrs_global.msrs[slot].msr, value);