From 8ab2d2e231062814bd89bba2d6d92563190aa2bb Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 15 Dec 2008 13:52:10 +0100
Subject: KVM: VMX: Support for injecting software exceptions
VMX differentiates between processor and software generated exceptions
when injecting them into the guest. Extend vmx_queue_exception
accordingly (and refactor related constants) so that we can use this
service reliably for the new guest debugging framework.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 35 ++++++++++++++++++++---------------
1 file changed, 20 insertions(+), 15 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7611af576829..1d974c1eaa7d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -189,21 +189,21 @@ static inline int is_page_fault(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+ (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
}
static inline int is_no_device(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+ (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
}
static inline int is_invalid_opcode(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
- (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+ (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
}
static inline int is_external_interrupt(u32 intr_info)
@@ -747,29 +747,33 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
bool has_error_code, u32 error_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 intr_info = nr | INTR_INFO_VALID_MASK;
- if (has_error_code)
+ if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+ intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+ }
if (vcpu->arch.rmode.active) {
vmx->rmode.irq.pending = true;
vmx->rmode.irq.vector = nr;
vmx->rmode.irq.rip = kvm_rip_read(vcpu);
- if (nr == BP_VECTOR)
+ if (nr == BP_VECTOR || nr == OF_VECTOR)
vmx->rmode.irq.rip++;
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
- nr | INTR_TYPE_SOFT_INTR
- | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
- | INTR_INFO_VALID_MASK);
+ intr_info |= INTR_TYPE_SOFT_INTR;
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
return;
}
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
- nr | INTR_TYPE_EXCEPTION
- | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
- | INTR_INFO_VALID_MASK);
+ if (nr == BP_VECTOR || nr == OF_VECTOR) {
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
+ intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+ } else
+ intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
}
static bool vmx_exception_injected(struct kvm_vcpu *vcpu)
@@ -2650,7 +2654,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) ==
- (INTR_TYPE_EXCEPTION | 1)) {
+ (INTR_TYPE_HARD_EXCEPTION | 1)) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
return 0;
}
@@ -3238,7 +3242,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
vmx->vcpu.arch.nmi_injected = false;
}
kvm_clear_exception_queue(&vmx->vcpu);
- if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) {
+ if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION ||
+ type == INTR_TYPE_SOFT_EXCEPTION)) {
if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
error = vmcs_read32(IDT_VECTORING_ERROR_CODE);
kvm_queue_exception_e(&vmx->vcpu, vector, error);
--
cgit v1.2.3
From d0bfb940ecabf0b44fb1fd80d8d60594e569e5ec Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 15 Dec 2008 13:52:10 +0100
Subject: KVM: New guest debug interface
This rips out the support for KVM_DEBUG_GUEST and introduces a new IOCTL
instead: KVM_SET_GUEST_DEBUG. The IOCTL payload consists of a generic
part, controlling the "main switch" and the single-step feature. The
arch specific part adds an x86 interface for intercepting both types of
debug exceptions separately and re-injecting them when the host was not
interested. Moveover, the foundation for guest debugging via debug
registers is layed.
To signal breakpoint events properly back to userland, an arch-specific
data block is now returned along KVM_EXIT_DEBUG. For x86, the arch block
contains the PC, the debug exception, and relevant debug registers to
tell debug events properly apart.
The availability of this new interface is signaled by
KVM_CAP_SET_GUEST_DEBUG. Empty stubs for not yet supported archs are
provided.
Note that both SVM and VTX are supported, but only the latter was tested
yet. Based on the experience with all those VTX corner case, I would be
fairly surprised if SVM will work out of the box.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/ia64/include/asm/kvm.h | 7 ++++
arch/ia64/kvm/kvm-ia64.c | 4 +-
arch/powerpc/include/asm/kvm.h | 7 ++++
arch/powerpc/kvm/powerpc.c | 4 +-
arch/s390/include/asm/kvm.h | 7 ++++
arch/s390/kvm/kvm-s390.c | 4 +-
arch/x86/include/asm/kvm.h | 18 ++++++++
arch/x86/include/asm/kvm_host.h | 9 +---
arch/x86/kvm/svm.c | 50 +++++++++++++++++++++-
arch/x86/kvm/vmx.c | 93 ++++++++++++++++-------------------------
arch/x86/kvm/x86.c | 14 ++++---
include/linux/kvm.h | 51 +++++++++++++++-------
include/linux/kvm_host.h | 6 +--
virt/kvm/kvm_main.c | 6 +--
14 files changed, 179 insertions(+), 101 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index bfa86b6af7cd..be3fdb891214 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -214,4 +214,11 @@ struct kvm_sregs {
struct kvm_fpu {
};
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
#endif
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 28f982045f29..de47467a0e61 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1303,8 +1303,8 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
return -EINVAL;
}
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *dbg)
{
return -EINVAL;
}
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f993e4198d5c..755f1b1948c5 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -52,4 +52,11 @@ struct kvm_fpu {
__u64 fpr[32];
};
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 5f81256287f5..7c2ad4017d6a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -240,8 +240,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvmppc_core_vcpu_put(vcpu);
}
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *dbg)
{
int i;
diff --git a/arch/s390/include/asm/kvm.h b/arch/s390/include/asm/kvm.h
index e1f54654e3ae..0b2f829f6d50 100644
--- a/arch/s390/include/asm/kvm.h
+++ b/arch/s390/include/asm/kvm.h
@@ -42,4 +42,11 @@ struct kvm_fpu {
__u64 fprs[16];
};
+struct kvm_debug_exit_arch {
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
#endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0d33893e1e89..cbfe91e10120 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -422,8 +422,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
return -EINVAL; /* not implemented yet */
}
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *dbg)
{
return -EINVAL; /* not implemented yet */
}
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 886c9402ec45..32eb96c7ca27 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -212,6 +212,24 @@ struct kvm_pit_channel_state {
__s64 count_load_time;
};
+struct kvm_debug_exit_arch {
+ __u32 exception;
+ __u32 pad;
+ __u64 pc;
+ __u64 dr6;
+ __u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP 0x00010000
+#define KVM_GUESTDBG_USE_HW_BP 0x00020000
+#define KVM_GUESTDBG_INJECT_DB 0x00040000
+#define KVM_GUESTDBG_INJECT_BP 0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+ __u64 debugreg[8];
+};
+
struct kvm_pit_state {
struct kvm_pit_channel_state channels[3];
};
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 53779309514a..c430cd580ee2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -135,12 +135,6 @@ enum {
#define KVM_NR_MEM_OBJS 40
-struct kvm_guest_debug {
- int enabled;
- unsigned long bp[4];
- int singlestep;
-};
-
/*
* We don't want allocation failures within the mmu code, so we preallocate
* enough memory for a single page fault in a cache.
@@ -448,8 +442,7 @@ struct kvm_x86_ops {
void (*vcpu_put)(struct kvm_vcpu *vcpu);
int (*set_guest_debug)(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg);
- void (*guest_debug_pre)(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 0fbbde54ecae..88d9062f4545 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -968,9 +968,32 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
}
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
{
- return -EOPNOTSUPP;
+ int old_debug = vcpu->guest_debug;
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ vcpu->guest_debug = dbg->control;
+
+ svm->vmcb->control.intercept_exceptions &=
+ ~((1 << DB_VECTOR) | (1 << BP_VECTOR));
+ if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+ if (vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+ svm->vmcb->control.intercept_exceptions |=
+ 1 << DB_VECTOR;
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+ svm->vmcb->control.intercept_exceptions |=
+ 1 << BP_VECTOR;
+ } else
+ vcpu->guest_debug = 0;
+
+ 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;
}
static int svm_get_irq(struct kvm_vcpu *vcpu)
@@ -1094,6 +1117,27 @@ 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)
+{
+ if (!(svm->vcpu.guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+ kvm_queue_exception(&svm->vcpu, DB_VECTOR);
+ return 1;
+ }
+ 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 = DB_VECTOR;
+ return 0;
+}
+
+static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_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)
{
int er;
@@ -2050,6 +2094,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
[SVM_EXIT_WRITE_DR3] = emulate_on_interception,
[SVM_EXIT_WRITE_DR5] = emulate_on_interception,
[SVM_EXIT_WRITE_DR7] = emulate_on_interception,
+ [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception,
+ [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
[SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
[SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1d974c1eaa7d..f55690ddb3ac 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -480,8 +480,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
eb = (1u << PF_VECTOR) | (1u << UD_VECTOR);
if (!vcpu->fpu_active)
eb |= 1u << NM_VECTOR;
- if (vcpu->guest_debug.enabled)
- eb |= 1u << DB_VECTOR;
+ if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+ if (vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+ eb |= 1u << DB_VECTOR;
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+ eb |= 1u << BP_VECTOR;
+ }
if (vcpu->arch.rmode.active)
eb = ~0;
if (vm_need_ept())
@@ -1003,40 +1008,23 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
}
}
-static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
{
- unsigned long dr7 = 0x400;
- int old_singlestep;
-
- old_singlestep = vcpu->guest_debug.singlestep;
-
- vcpu->guest_debug.enabled = dbg->enabled;
- if (vcpu->guest_debug.enabled) {
- int i;
-
- dr7 |= 0x200; /* exact */
- for (i = 0; i < 4; ++i) {
- if (!dbg->breakpoints[i].enabled)
- continue;
- vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
- dr7 |= 2 << (i*2); /* global enable */
- dr7 |= 0 << (i*4+16); /* execution breakpoint */
- }
-
- vcpu->guest_debug.singlestep = dbg->singlestep;
- } else
- vcpu->guest_debug.singlestep = 0;
+ int old_debug = vcpu->guest_debug;
+ unsigned long flags;
- if (old_singlestep && !vcpu->guest_debug.singlestep) {
- unsigned long flags;
+ vcpu->guest_debug = dbg->control;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
+ vcpu->guest_debug = 0;
- flags = vmcs_readl(GUEST_RFLAGS);
+ 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);
- }
+ vmcs_writel(GUEST_RFLAGS, flags);
update_exception_bitmap(vcpu);
- vmcs_writel(GUEST_DR7, dr7);
return 0;
}
@@ -2540,24 +2528,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
return 0;
}
-static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
-{
- struct kvm_guest_debug *dbg = &vcpu->guest_debug;
-
- set_debugreg(dbg->bp[0], 0);
- set_debugreg(dbg->bp[1], 1);
- set_debugreg(dbg->bp[2], 2);
- set_debugreg(dbg->bp[3], 3);
-
- if (dbg->singlestep) {
- unsigned long flags;
-
- flags = vmcs_readl(GUEST_RFLAGS);
- flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
- vmcs_writel(GUEST_RFLAGS, flags);
- }
-}
-
static int handle_rmode_exception(struct kvm_vcpu *vcpu,
int vec, u32 err_code)
{
@@ -2574,9 +2544,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
* the required debugging infrastructure rework.
*/
switch (vec) {
- case DE_VECTOR:
case DB_VECTOR:
+ if (vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+ return 0;
+ kvm_queue_exception(vcpu, vec);
+ return 1;
case BP_VECTOR:
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+ return 0;
+ /* fall through */
+ case DE_VECTOR:
case OF_VECTOR:
case BR_VECTOR:
case UD_VECTOR:
@@ -2593,7 +2571,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 intr_info, error_code;
+ u32 intr_info, ex_no, error_code;
unsigned long cr2, rip;
u32 vect_info;
enum emulation_result er;
@@ -2653,14 +2631,16 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
- if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) ==
- (INTR_TYPE_HARD_EXCEPTION | 1)) {
+ ex_no = intr_info & INTR_INFO_VECTOR_MASK;
+ if (ex_no == DB_VECTOR || ex_no == BP_VECTOR) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
- return 0;
+ kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+ kvm_run->debug.arch.exception = ex_no;
+ } else {
+ kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
+ kvm_run->ex.exception = ex_no;
+ kvm_run->ex.error_code = error_code;
}
- kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
- kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK;
- kvm_run->ex.error_code = error_code;
return 0;
}
@@ -3600,7 +3580,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
.vcpu_put = vmx_vcpu_put,
.set_guest_debug = set_guest_debug,
- .guest_debug_pre = kvm_guest_debug_pre,
.get_msr = vmx_get_msr,
.set_msr = vmx_set_msr,
.get_segment_base = vmx_get_segment_base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b5e9932e0f62..e990d164b56d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3005,9 +3005,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
goto out;
}
- if (vcpu->guest_debug.enabled)
- kvm_x86_ops->guest_debug_pre(vcpu);
-
vcpu->guest_mode = 1;
/*
* Make sure that guest_mode assignment won't happen after
@@ -3218,7 +3215,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
/*
* Don't leak debug flags in case they were set for guest debugging
*/
- if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep)
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
vcpu_put(vcpu);
@@ -3837,8 +3834,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
return 0;
}
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *dbg)
{
int r;
@@ -3846,6 +3843,11 @@ int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
+ if (dbg->control & KVM_GUESTDBG_INJECT_DB)
+ kvm_queue_exception(vcpu, DB_VECTOR);
+ else if (dbg->control & KVM_GUESTDBG_INJECT_BP)
+ kvm_queue_exception(vcpu, BP_VECTOR);
+
vcpu_put(vcpu);
return r;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 0424326f1679..429a2ce202f9 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -126,6 +126,7 @@ struct kvm_run {
__u64 data_offset; /* relative to kvm_run start */
} io;
struct {
+ struct kvm_debug_exit_arch arch;
} debug;
/* KVM_EXIT_MMIO */
struct {
@@ -217,21 +218,6 @@ struct kvm_interrupt {
__u32 irq;
};
-struct kvm_breakpoint {
- __u32 enabled;
- __u32 padding;
- __u64 address;
-};
-
-/* for KVM_DEBUG_GUEST */
-struct kvm_debug_guest {
- /* int */
- __u32 enabled;
- __u32 pad;
- struct kvm_breakpoint breakpoints[4];
- __u32 singlestep;
-};
-
/* for KVM_GET_DIRTY_LOG */
struct kvm_dirty_log {
__u32 slot;
@@ -292,6 +278,17 @@ struct kvm_s390_interrupt {
__u64 parm64;
};
+/* for KVM_SET_GUEST_DEBUG */
+
+#define KVM_GUESTDBG_ENABLE 0x00000001
+#define KVM_GUESTDBG_SINGLESTEP 0x00000002
+
+struct kvm_guest_debug {
+ __u32 control;
+ __u32 pad;
+ struct kvm_guest_debug_arch arch;
+};
+
#define KVM_TRC_SHIFT 16
/*
* kvm trace categories
@@ -396,6 +393,7 @@ struct kvm_trace_rec {
#ifdef __KVM_HAVE_USER_NMI
#define KVM_CAP_USER_NMI 22
#endif
+#define KVM_CAP_SET_GUEST_DEBUG 23
/*
* ioctls for VM fds
@@ -440,7 +438,8 @@ struct kvm_trace_rec {
#define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs)
#define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation)
#define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt)
-#define KVM_DEBUG_GUEST _IOW(KVMIO, 0x87, struct kvm_debug_guest)
+/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
+#define KVM_DEBUG_GUEST __KVM_DEPRECATED_DEBUG_GUEST
#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)
@@ -469,6 +468,26 @@ struct kvm_trace_rec {
#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state)
/* Available with KVM_CAP_NMI */
#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)
+
+/*
+ * 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)
#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02)
#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bf6f703642fc..e92212f970db 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -73,7 +73,7 @@ struct kvm_vcpu {
struct kvm_run *run;
int guest_mode;
unsigned long requests;
- struct kvm_guest_debug guest_debug;
+ unsigned long guest_debug;
int fpu_active;
int guest_fpu_loaded;
wait_queue_head_t wq;
@@ -255,8 +255,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state);
int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state);
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg);
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *dbg);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
int kvm_arch_init(void *opaque);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 29a667ce35b0..f83ef9c7e89b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1755,13 +1755,13 @@ out_free2:
r = 0;
break;
}
- case KVM_DEBUG_GUEST: {
- struct kvm_debug_guest dbg;
+ case KVM_SET_GUEST_DEBUG: {
+ struct kvm_guest_debug dbg;
r = -EFAULT;
if (copy_from_user(&dbg, argp, sizeof dbg))
goto out;
- r = kvm_arch_vcpu_ioctl_debug_guest(vcpu, &dbg);
+ r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
if (r)
goto out;
r = 0;
--
cgit v1.2.3
From 55934c0bd3bb232a9cf902820dd63ad18ed65e49 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 15 Dec 2008 13:52:10 +0100
Subject: KVM: VMX: Allow single-stepping when uninterruptible
When single-stepping over STI and MOV SS, we must clear the
corresponding interruptibility bits in the guest state. Otherwise
vmentry fails as it then expects bit 14 (BS) in pending debug exceptions
being set, but that's not correct for the guest debugging case.
Note that clearing those bits is safe as we check for interruptibility
based on the original state and do not inject interrupts or NMIs if
guest interruptibility was blocked.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 10 ++++++++++
1 file changed, 10 insertions(+)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f55690ddb3ac..c776868ffe41 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2478,6 +2478,11 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
{
vmx_update_window_states(vcpu);
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+ vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_STI |
+ GUEST_INTR_STATE_MOV_SS);
+
if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
if (vcpu->arch.interrupt.pending) {
enable_nmi_window(vcpu);
@@ -3244,6 +3249,11 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
vmx_update_window_states(vcpu);
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+ vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+ GUEST_INTR_STATE_STI |
+ GUEST_INTR_STATE_MOV_SS);
+
if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
if (vcpu->arch.interrupt.pending) {
enable_nmi_window(vcpu);
--
cgit v1.2.3
From 42dbaa5a057736bf8b5c22aa42dbe975bf1080e5 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 15 Dec 2008 13:52:10 +0100
Subject: KVM: x86: Virtualize debug registers
So far KVM only had basic x86 debug register support, once introduced to
realize guest debugging that way. The guest itself was not able to use
those registers.
This patch now adds (almost) full support for guest self-debugging via
hardware registers. It refactors the code, moving generic parts out of
SVM (VMX was already cleaned up by the KVM_SET_GUEST_DEBUG patches), and
it ensures that the registers are properly switched between host and
guest.
This patch also prepares debug register usage by the host. The latter
will (once wired-up by the following patch) allow for hardware
breakpoints/watchpoints in guest code. If this is enabled, the guest
will only see faked debug registers without functionality, but with
content reflecting the guest's modifications.
Tested on Intel only, but SVM /should/ work as well, but who knows...
Known limitations: Trapping on tss switch won't work - most probably on
Intel.
Credits also go to Joerg Roedel - I used his once posted debugging
series as platform for this patch.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 22 ++++++++
arch/x86/include/asm/vmx.h | 2 +-
arch/x86/kvm/kvm_svm.h | 6 ---
arch/x86/kvm/svm.c | 116 +++++++++++++++-------------------------
arch/x86/kvm/vmx.c | 114 +++++++++++++++++++++++++++++++++------
arch/x86/kvm/x86.c | 29 ++++++++++
6 files changed, 193 insertions(+), 96 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c430cd580ee2..0a4dab25a919 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -135,6 +135,19 @@ enum {
#define KVM_NR_MEM_OBJS 40
+#define KVM_NR_DB_REGS 4
+
+#define DR6_BD (1 << 13)
+#define DR6_BS (1 << 14)
+#define DR6_FIXED_1 0xffff0ff0
+#define DR6_VOLATILE 0x0000e00f
+
+#define DR7_BP_EN_MASK 0x000000ff
+#define DR7_GE (1 << 9)
+#define DR7_GD (1 << 13)
+#define DR7_FIXED_1 0x00000400
+#define DR7_VOLATILE 0xffff23ff
+
/*
* We don't want allocation failures within the mmu code, so we preallocate
* enough memory for a single page fault in a cache.
@@ -334,6 +347,15 @@ struct kvm_vcpu_arch {
struct mtrr_state_type mtrr_state;
u32 pat;
+
+ int switch_db_regs;
+ unsigned long host_db[KVM_NR_DB_REGS];
+ unsigned long host_dr6;
+ unsigned long host_dr7;
+ unsigned long db[KVM_NR_DB_REGS];
+ unsigned long dr6;
+ unsigned long dr7;
+ unsigned long eff_db[KVM_NR_DB_REGS];
};
struct kvm_mem_alias {
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 32159f034efc..498f944010b9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -312,7 +312,7 @@ enum vmcs_field {
#define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */
#define TYPE_MOV_TO_DR (0 << 4)
#define TYPE_MOV_FROM_DR (1 << 4)
-#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose reg. */
+#define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */
/* segment AR */
diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h
index 91673413d8f7..ed66e4c078dc 100644
--- a/arch/x86/kvm/kvm_svm.h
+++ b/arch/x86/kvm/kvm_svm.h
@@ -18,7 +18,6 @@ static const u32 host_save_user_msrs[] = {
};
#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
-#define NUM_DB_REGS 4
struct kvm_vcpu;
@@ -29,16 +28,11 @@ struct vcpu_svm {
struct svm_cpu_data *svm_data;
uint64_t asid_generation;
- unsigned long db_regs[NUM_DB_REGS];
-
u64 next_rip;
u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
u64 host_gs_base;
unsigned long host_cr2;
- unsigned long host_db_regs[NUM_DB_REGS];
- unsigned long host_dr6;
- unsigned long host_dr7;
u32 *msrpm;
struct vmcb *hsave;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 88d9062f4545..815f50e425ac 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -38,9 +38,6 @@ MODULE_LICENSE("GPL");
#define IOPM_ALLOC_ORDER 2
#define MSRPM_ALLOC_ORDER 1
-#define DR7_GD_MASK (1 << 13)
-#define DR6_BD_MASK (1 << 13)
-
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
@@ -181,32 +178,6 @@ static inline void kvm_write_cr2(unsigned long val)
asm volatile ("mov %0, %%cr2" :: "r" (val));
}
-static inline unsigned long read_dr6(void)
-{
- unsigned long dr6;
-
- asm volatile ("mov %%dr6, %0" : "=r" (dr6));
- return dr6;
-}
-
-static inline void write_dr6(unsigned long val)
-{
- asm volatile ("mov %0, %%dr6" :: "r" (val));
-}
-
-static inline unsigned long read_dr7(void)
-{
- unsigned long dr7;
-
- asm volatile ("mov %%dr7, %0" : "=r" (dr7));
- return dr7;
-}
-
-static inline void write_dr7(unsigned long val)
-{
- asm volatile ("mov %0, %%dr7" :: "r" (val));
-}
-
static inline void force_new_asid(struct kvm_vcpu *vcpu)
{
to_svm(vcpu)->asid_generation--;
@@ -695,7 +666,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
clear_page(svm->vmcb);
svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
svm->asid_generation = 0;
- memset(svm->db_regs, 0, sizeof(svm->db_regs));
init_vmcb(svm);
fx_init(&svm->vcpu);
@@ -1035,7 +1005,29 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
{
- unsigned long val = to_svm(vcpu)->db_regs[dr];
+ struct vcpu_svm *svm = to_svm(vcpu);
+ unsigned long val;
+
+ switch (dr) {
+ case 0 ... 3:
+ val = vcpu->arch.db[dr];
+ break;
+ case 6:
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+ val = vcpu->arch.dr6;
+ else
+ val = svm->vmcb->save.dr6;
+ break;
+ case 7:
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+ val = vcpu->arch.dr7;
+ else
+ val = svm->vmcb->save.dr7;
+ break;
+ default:
+ val = 0;
+ }
+
KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
return val;
}
@@ -1045,33 +1037,40 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
{
struct vcpu_svm *svm = to_svm(vcpu);
- *exception = 0;
+ KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)value, handler);
- if (svm->vmcb->save.dr7 & DR7_GD_MASK) {
- svm->vmcb->save.dr7 &= ~DR7_GD_MASK;
- svm->vmcb->save.dr6 |= DR6_BD_MASK;
- *exception = DB_VECTOR;
- return;
- }
+ *exception = 0;
switch (dr) {
case 0 ... 3:
- svm->db_regs[dr] = value;
+ vcpu->arch.db[dr] = value;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+ vcpu->arch.eff_db[dr] = value;
return;
case 4 ... 5:
- if (vcpu->arch.cr4 & X86_CR4_DE) {
+ if (vcpu->arch.cr4 & X86_CR4_DE)
*exception = UD_VECTOR;
+ return;
+ case 6:
+ if (value & 0xffffffff00000000ULL) {
+ *exception = GP_VECTOR;
return;
}
- case 7: {
- if (value & ~((1ULL << 32) - 1)) {
+ vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
+ return;
+ case 7:
+ if (value & 0xffffffff00000000ULL) {
*exception = GP_VECTOR;
return;
}
- svm->vmcb->save.dr7 = value;
+ vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+ svm->vmcb->save.dr7 = vcpu->arch.dr7;
+ vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
+ }
return;
- }
default:
+ /* FIXME: Possible case? */
printk(KERN_DEBUG "%s: unexpected dr %u\n",
__func__, dr);
*exception = UD_VECTOR;
@@ -2365,22 +2364,6 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
return 0;
}
-static void save_db_regs(unsigned long *db_regs)
-{
- asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0]));
- asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1]));
- asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2]));
- asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3]));
-}
-
-static void load_db_regs(unsigned long *db_regs)
-{
- asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0]));
- asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1]));
- asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2]));
- asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3]));
-}
-
static void svm_flush_tlb(struct kvm_vcpu *vcpu)
{
force_new_asid(vcpu);
@@ -2439,20 +2422,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
gs_selector = kvm_read_gs();
ldt_selector = kvm_read_ldt();
svm->host_cr2 = kvm_read_cr2();
- svm->host_dr6 = read_dr6();
- svm->host_dr7 = read_dr7();
if (!is_nested(svm))
svm->vmcb->save.cr2 = vcpu->arch.cr2;
/* required for live migration with NPT */
if (npt_enabled)
svm->vmcb->save.cr3 = vcpu->arch.cr3;
- if (svm->vmcb->save.dr7 & 0xff) {
- write_dr7(0);
- save_db_regs(svm->host_db_regs);
- load_db_regs(svm->db_regs);
- }
-
clgi();
local_irq_enable();
@@ -2528,16 +2503,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
#endif
);
- if ((svm->vmcb->save.dr7 & 0xff))
- load_db_regs(svm->host_db_regs);
-
vcpu->arch.cr2 = svm->vmcb->save.cr2;
vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax;
vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
- write_dr6(svm->host_dr6);
- write_dr7(svm->host_dr7);
kvm_write_cr2(svm->host_cr2);
kvm_load_fs(fs_selector);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c776868ffe41..0989776ee7b0 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2311,7 +2311,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
kvm_rip_write(vcpu, 0);
kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
- /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */
vmcs_writel(GUEST_DR7, 0x400);
vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -2577,7 +2576,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info, ex_no, error_code;
- unsigned long cr2, rip;
+ unsigned long cr2, rip, dr6;
u32 vect_info;
enum emulation_result er;
@@ -2637,14 +2636,28 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
ex_no = intr_info & INTR_INFO_VECTOR_MASK;
- if (ex_no == DB_VECTOR || ex_no == BP_VECTOR) {
+ switch (ex_no) {
+ case DB_VECTOR:
+ dr6 = vmcs_readl(EXIT_QUALIFICATION);
+ if (!(vcpu->guest_debug &
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+ vcpu->arch.dr6 = dr6 | DR6_FIXED_1;
+ kvm_queue_exception(vcpu, DB_VECTOR);
+ return 1;
+ }
+ kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+ kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
+ /* fall through */
+ case BP_VECTOR:
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
kvm_run->debug.arch.exception = ex_no;
- } else {
+ break;
+ default:
kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
kvm_run->ex.exception = ex_no;
kvm_run->ex.error_code = error_code;
+ break;
}
return 0;
}
@@ -2784,21 +2797,44 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
unsigned long val;
int dr, reg;
- /*
- * FIXME: this code assumes the host is debugging the guest.
- * need to deal with guest debugging itself too.
- */
+ dr = vmcs_readl(GUEST_DR7);
+ if (dr & DR7_GD) {
+ /*
+ * As the vm-exit takes precedence over the debug trap, we
+ * need to emulate the latter, either for the host or the
+ * 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 =
+ vmcs_readl(GUEST_CS_BASE) +
+ vmcs_readl(GUEST_RIP);
+ kvm_run->debug.arch.exception = DB_VECTOR;
+ kvm_run->exit_reason = KVM_EXIT_DEBUG;
+ return 0;
+ } else {
+ vcpu->arch.dr7 &= ~DR7_GD;
+ vcpu->arch.dr6 |= DR6_BD;
+ vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
+ kvm_queue_exception(vcpu, DB_VECTOR);
+ return 1;
+ }
+ }
+
exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- dr = exit_qualification & 7;
- reg = (exit_qualification >> 8) & 15;
- if (exit_qualification & 16) {
- /* mov from dr */
+ dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
+ reg = DEBUG_REG_ACCESS_REG(exit_qualification);
+ if (exit_qualification & TYPE_MOV_FROM_DR) {
switch (dr) {
+ case 0 ... 3:
+ val = vcpu->arch.db[dr];
+ break;
case 6:
- val = 0xffff0ff0;
+ val = vcpu->arch.dr6;
break;
case 7:
- val = 0x400;
+ val = vcpu->arch.dr7;
break;
default:
val = 0;
@@ -2806,7 +2842,38 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_register_write(vcpu, reg, val);
KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
} else {
- /* mov to dr */
+ val = vcpu->arch.regs[reg];
+ switch (dr) {
+ case 0 ... 3:
+ vcpu->arch.db[dr] = val;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+ vcpu->arch.eff_db[dr] = val;
+ break;
+ case 4 ... 5:
+ if (vcpu->arch.cr4 & X86_CR4_DE)
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ break;
+ case 6:
+ if (val & 0xffffffff00000000ULL) {
+ kvm_queue_exception(vcpu, GP_VECTOR);
+ break;
+ }
+ vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+ break;
+ case 7:
+ if (val & 0xffffffff00000000ULL) {
+ kvm_queue_exception(vcpu, GP_VECTOR);
+ break;
+ }
+ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+ vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
+ vcpu->arch.switch_db_regs =
+ (val & DR7_BP_EN_MASK);
+ }
+ break;
+ }
+ KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler);
}
skip_emulated_instruction(vcpu);
return 1;
@@ -2957,7 +3024,18 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
tss_selector = exit_qualification;
- return kvm_task_switch(vcpu, tss_selector, reason);
+ if (!kvm_task_switch(vcpu, tss_selector, reason))
+ return 0;
+
+ /* clear all local breakpoint enable flags */
+ vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
+
+ /*
+ * TODO: What about debug traps on tss switch?
+ * Are we supposed to inject them and update dr6?
+ */
+
+ return 1;
}
static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -3342,6 +3420,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
*/
vmcs_writel(HOST_CR0, read_cr0());
+ set_debugreg(vcpu->arch.dr6, 6);
+
asm(
/* Store host registers */
"push %%"R"dx; push %%"R"bp;"
@@ -3436,6 +3516,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
vcpu->arch.regs_dirty = 0;
+ get_debugreg(vcpu->arch.dr6, 6);
+
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
if (vmx->rmode.irq.pending)
fixup_rmode_irq(vmx);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e990d164b56d..300bc4d42abc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3025,10 +3025,34 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
kvm_guest_enter();
+ get_debugreg(vcpu->arch.host_dr6, 6);
+ get_debugreg(vcpu->arch.host_dr7, 7);
+ if (unlikely(vcpu->arch.switch_db_regs)) {
+ get_debugreg(vcpu->arch.host_db[0], 0);
+ get_debugreg(vcpu->arch.host_db[1], 1);
+ get_debugreg(vcpu->arch.host_db[2], 2);
+ get_debugreg(vcpu->arch.host_db[3], 3);
+
+ set_debugreg(0, 7);
+ set_debugreg(vcpu->arch.eff_db[0], 0);
+ set_debugreg(vcpu->arch.eff_db[1], 1);
+ set_debugreg(vcpu->arch.eff_db[2], 2);
+ set_debugreg(vcpu->arch.eff_db[3], 3);
+ }
KVMTRACE_0D(VMENTRY, vcpu, entryexit);
kvm_x86_ops->run(vcpu, kvm_run);
+ if (unlikely(vcpu->arch.switch_db_regs)) {
+ set_debugreg(0, 7);
+ set_debugreg(vcpu->arch.host_db[0], 0);
+ set_debugreg(vcpu->arch.host_db[1], 1);
+ set_debugreg(vcpu->arch.host_db[2], 2);
+ set_debugreg(vcpu->arch.host_db[3], 3);
+ }
+ set_debugreg(vcpu->arch.host_dr6, 6);
+ set_debugreg(vcpu->arch.host_dr7, 7);
+
vcpu->guest_mode = 0;
local_irq_enable();
@@ -4035,6 +4059,11 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
vcpu->arch.nmi_pending = false;
vcpu->arch.nmi_injected = false;
+ vcpu->arch.switch_db_regs = 0;
+ memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
+ vcpu->arch.dr6 = DR6_FIXED_1;
+ vcpu->arch.dr7 = DR7_FIXED_1;
+
return kvm_x86_ops->vcpu_reset(vcpu);
}
--
cgit v1.2.3
From ae675ef01cd86014acf8da5dee87876b71122495 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 15 Dec 2008 13:52:10 +0100
Subject: KVM: x86: Wire-up hardware breakpoints for guest debugging
Add the remaining bits to make use of debug registers also for guest
debugging, thus enabling the use of hardware breakpoints and
watchpoints.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/svm.c | 5 +++++
arch/x86/kvm/vmx.c | 5 +++++
arch/x86/kvm/x86.c | 14 +++++++++++++-
3 files changed, 23 insertions(+), 1 deletion(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 815f50e425ac..b3a7a314d55c 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -958,6 +958,11 @@ static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
} else
vcpu->guest_debug = 0;
+ 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)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0989776ee7b0..cee81c9a6653 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1017,6 +1017,11 @@ static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
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;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 300bc4d42abc..2477e87b2f84 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3861,10 +3861,22 @@ 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 r;
+ int i, r;
vcpu_load(vcpu);
+ if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) ==
+ (KVM_GUESTDBG_ENABLE | 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 =
+ (dbg->arch.debugreg[7] & DR7_BP_EN_MASK);
+ } else {
+ for (i = 0; i < KVM_NR_DB_REGS; i++)
+ vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
+ }
+
r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
if (dbg->control & KVM_GUESTDBG_INJECT_DB)
--
cgit v1.2.3
From 53f658b3c33616a4997ee254311b335e59063289 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Thu, 11 Dec 2008 20:45:05 +0100
Subject: KVM: VMX: initialize TSC offset relative to vm creation time
VMX initializes the TSC offset for each vcpu at different times, and
also reinitializes it for vcpus other than 0 on APIC SIPI message.
This bug causes the TSC's to appear unsynchronized in the guest, even if
the host is good.
Older Linux kernels don't handle the situation very well, so
gettimeofday is likely to go backwards in time:
http://www.mail-archive.com/kvm@vger.kernel.org/msg02955.html
http://sourceforge.net/tracker/index.php?func=detail&aid=2025534&group_id=180599&atid=893831
Fix it by initializating the offset of each vcpu relative to vm creation
time, and moving it from vmx_vcpu_reset to vmx_vcpu_setup, out of the
APIC MP init path.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/vmx.c | 19 +++++++++++--------
arch/x86/kvm/x86.c | 2 ++
3 files changed, 14 insertions(+), 8 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c2a01d0513f5..9efc446b5ac6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -398,6 +398,7 @@ struct kvm_arch{
unsigned long irq_sources_bitmap;
unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
+ u64 vm_init_tsc;
};
struct kvm_vm_stat {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cee81c9a6653..3312047664a4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -865,11 +865,8 @@ static u64 guest_read_tsc(void)
* writes 'guest_tsc' into guest's timestamp counter "register"
* guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc
*/
-static void guest_write_tsc(u64 guest_tsc)
+static void guest_write_tsc(u64 guest_tsc, u64 host_tsc)
{
- u64 host_tsc;
-
- rdtscll(host_tsc);
vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc);
}
@@ -934,6 +931,7 @@ 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;
+ u64 host_tsc;
int ret = 0;
switch (msr_index) {
@@ -959,7 +957,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_TIME_STAMP_COUNTER:
- guest_write_tsc(data);
+ rdtscll(host_tsc);
+ guest_write_tsc(data, host_tsc);
break;
case MSR_P6_PERFCTR0:
case MSR_P6_PERFCTR1:
@@ -2109,7 +2108,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
{
u32 host_sysenter_cs, msr_low, msr_high;
u32 junk;
- u64 host_pat;
+ u64 host_pat, tsc_this, tsc_base;
unsigned long a;
struct descriptor_table dt;
int i;
@@ -2237,6 +2236,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
+ tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
+ rdtscll(tsc_this);
+ if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc)
+ tsc_base = tsc_this;
+
+ guest_write_tsc(0, tsc_base);
return 0;
}
@@ -2328,8 +2333,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
- guest_write_tsc(0);
-
/* Special registers */
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 873602b5edfd..3b2acfd72d7f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4170,6 +4170,8 @@ struct kvm *kvm_arch_create_vm(void)
/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
+ rdtscll(kvm->arch.vm_init_tsc);
+
return kvm;
}
--
cgit v1.2.3
From 1872a3f411ffe95c8e92300e0986a3532db55ce9 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Sun, 4 Jan 2009 23:26:52 +0200
Subject: KVM: VMX: Fix guest state validity checks
The vmx guest state validity checks are full of bugs. Make them
conform to the manual.
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3312047664a4..be9441056ff2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1784,14 +1784,16 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
cs_rpl = cs.selector & SELECTOR_RPL_MASK;
+ if (cs.unusable)
+ return false;
if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
return false;
if (!cs.s)
return false;
- if (!(~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK))) {
+ if (cs.type & AR_TYPE_WRITEABLE_MASK) {
if (cs.dpl > cs_rpl)
return false;
- } else if (cs.type & AR_TYPE_CODE_MASK) {
+ } else {
if (cs.dpl != cs_rpl)
return false;
}
@@ -1810,7 +1812,9 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu)
vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
ss_rpl = ss.selector & SELECTOR_RPL_MASK;
- if ((ss.type != 3) || (ss.type != 7))
+ if (ss.unusable)
+ return true;
+ if (ss.type != 3 && ss.type != 7)
return false;
if (!ss.s)
return false;
@@ -1830,6 +1834,8 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
vmx_get_segment(vcpu, &var, seg);
rpl = var.selector & SELECTOR_RPL_MASK;
+ if (var.unusable)
+ return true;
if (!var.s)
return false;
if (!var.present)
@@ -1851,9 +1857,11 @@ static bool tr_valid(struct kvm_vcpu *vcpu)
vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);
+ if (tr.unusable)
+ return false;
if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */
return false;
- if ((tr.type != 3) || (tr.type != 11)) /* TODO: Check if guest is in IA32e mode */
+ if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
return false;
if (!tr.present)
return false;
@@ -1867,6 +1875,8 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu)
vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);
+ if (ldtr.unusable)
+ return true;
if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */
return false;
if (ldtr.type != 2)
--
cgit v1.2.3
From 9fd4a3b7a412f983696b23121413a79d2132fed6 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Sun, 4 Jan 2009 23:43:42 +0200
Subject: KVM: VMX: don't clobber segment AR if emulating invalid state
The ususable bit is important for determining state validity; don't
clobber it.
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index be9441056ff2..a6598cbaa001 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1649,7 +1649,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
var->limit = vmcs_read32(sf->limit);
var->selector = vmcs_read16(sf->selector);
ar = vmcs_read32(sf->ar_bytes);
- if (ar & AR_UNUSABLE_MASK)
+ if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
ar = 0;
var->type = ar & 15;
var->s = (ar >> 4) & 1;
--
cgit v1.2.3
From 10f32d84c750ccf8c0afb3a4ea9d4059aa3e9ffc Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 5 Jan 2009 00:53:19 +0200
Subject: KVM: VMX: Prevent exit handler from running if emulating due to
invalid state
If we've just emulated an instruction, we won't have any valid exit
reason and associated information.
Fix by moving the clearing of the emulation_required flag to the exit handler.
This way the exit handler can notice that we've been emulating and abort
early.
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a6598cbaa001..a309be6788e7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3130,7 +3130,6 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
int err;
preempt_enable();
@@ -3155,11 +3154,6 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
local_irq_disable();
preempt_disable();
-
- /* Guest state should be valid now except if we need to
- * emulate an MMIO */
- if (guest_state_valid(vcpu))
- vmx->emulation_required = 0;
}
/*
@@ -3208,8 +3202,11 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *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 (vmx->emulation_required && emulate_invalid_guest_state) {
+ if (guest_state_valid(vcpu))
+ vmx->emulation_required = 0;
return 0;
+ }
/* Access CR3 don't cause VMExit in paging mode, so we need
* to sync with guest real CR3. */
--
cgit v1.2.3
From 8b3079a5c0c031de07c8390aa160a4229088274f Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 5 Jan 2009 12:10:54 +0200
Subject: KVM: VMX: When emulating on invalid vmx state, don't return to
userspace unnecessarily
If we aren't doing mmio there's no need to exit to userspace (which will
just be confused).
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a309be6788e7..df454de8acfa 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -91,6 +91,7 @@ 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;
@@ -3130,7 +3131,8 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
- int err;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ enum emulation_result err = EMULATE_DONE;
preempt_enable();
local_irq_enable();
@@ -3154,6 +3156,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
local_irq_disable();
preempt_disable();
+
+ vmx->invalid_state_emulation_result = err;
}
/*
@@ -3205,7 +3209,7 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
if (vmx->emulation_required && emulate_invalid_guest_state) {
if (guest_state_valid(vcpu))
vmx->emulation_required = 0;
- return 0;
+ return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO;
}
/* Access CR3 don't cause VMExit in paging mode, so we need
--
cgit v1.2.3
From 34c33d163fe509da8414a736c6328855f8c164e5 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@web.de>
Date: Sun, 8 Feb 2009 13:28:15 +0100
Subject: KVM: Drop unused evaluations from string pio handlers
Looks like neither the direction nor the rep prefix are used anymore.
Drop related evaluations from SVM's and VMX's I/O exit handlers.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/svm.c | 4 +---
arch/x86/kvm/vmx.c | 4 +---
2 files changed, 2 insertions(+), 6 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1c4a018bf4bb..22e88a4a51c7 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1194,7 +1194,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
{
u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
- int size, down, in, string, rep;
+ int size, in, string;
unsigned port;
++svm->vcpu.stat.io_exits;
@@ -1213,8 +1213,6 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
port = io_info >> 16;
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
- rep = (io_info & SVM_IOIO_REP_MASK) != 0;
- down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0;
skip_emulated_instruction(&svm->vcpu);
return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index df454de8acfa..509b35305402 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2698,7 +2698,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
unsigned long exit_qualification;
- int size, down, in, string, rep;
+ int size, in, string;
unsigned port;
++vcpu->stat.io_exits;
@@ -2714,8 +2714,6 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
size = (exit_qualification & 7) + 1;
in = (exit_qualification & 8) != 0;
- down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0;
- rep = (exit_qualification & 32) != 0;
port = exit_qualification >> 16;
skip_emulated_instruction(vcpu);
--
cgit v1.2.3
From 49cd7d2238e44f7ee4269481cd8a1261cc8f93a5 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Wed, 11 Feb 2009 13:50:40 +0800
Subject: KVM: VMX: Use kvm_mmu_page_fault() handle EPT violation mmio
Removed duplicated code.
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 30 +-----------------------------
1 file changed, 1 insertion(+), 29 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 509b35305402..cb27ffccf466 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3058,11 +3058,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
u64 exit_qualification;
- enum emulation_result er;
gpa_t gpa;
- unsigned long hva;
int gla_validity;
- int r;
exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
@@ -3085,32 +3082,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
- hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT);
- if (!kvm_is_error_hva(hva)) {
- r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
- if (r < 0) {
- printk(KERN_ERR "EPT: Not enough memory!\n");
- return -ENOMEM;
- }
- return 1;
- } else {
- /* must be MMIO */
- er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
-
- if (er == EMULATE_FAIL) {
- printk(KERN_ERR
- "EPT: Fail to handle EPT violation vmexit!er is %d\n",
- er);
- printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
- (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
- (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS));
- printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
- (long unsigned int)exit_qualification);
- return -ENOTSUPP;
- } else if (er == EMULATE_DO_MMIO)
- return 0;
- }
- return 1;
+ return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
}
static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
--
cgit v1.2.3
From 401d10dee083bda281f2fdcdf654080313ba30ec Mon Sep 17 00:00:00 2001
From: Amit Shah <amit.shah@redhat.com>
Date: Fri, 20 Feb 2009 22:53:37 +0530
Subject: KVM: VMX: Update necessary state when guest enters long mode
setup_msrs() should be called when entering long mode to save the
shadow state for the 64-bit guest state.
Using vmx_set_efer() in enter_lmode() removes some duplicated code
and also ensures we call setup_msrs(). We can safely pass the value
of shadow_efer to vmx_set_efer() as no other bits in the efer change
while enabling long mode (guest first sets EFER.LME, then sets CR0.PG
which causes a vmexit where we activate long mode).
With this fix, is_long_mode() can check for EFER.LMA set instead of
EFER.LME and 5e23049e86dd298b72e206b420513dbc3a240cd9 can be reverted.
Signed-off-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 54 ++++++++++++++++++++++++------------------------------
1 file changed, 24 insertions(+), 30 deletions(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cb27ffccf466..48063a0aa243 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1430,6 +1430,29 @@ continue_rmode:
init_rmode(vcpu->kvm);
}
+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);
+
+ vcpu->arch.shadow_efer = efer;
+ if (!msr)
+ return;
+ if (efer & EFER_LMA) {
+ vmcs_write32(VM_ENTRY_CONTROLS,
+ vmcs_read32(VM_ENTRY_CONTROLS) |
+ VM_ENTRY_IA32E_MODE);
+ msr->data = efer;
+ } else {
+ vmcs_write32(VM_ENTRY_CONTROLS,
+ vmcs_read32(VM_ENTRY_CONTROLS) &
+ ~VM_ENTRY_IA32E_MODE);
+
+ msr->data = efer & ~EFER_LME;
+ }
+ setup_msrs(vmx);
+}
+
#ifdef CONFIG_X86_64
static void enter_lmode(struct kvm_vcpu *vcpu)
@@ -1444,13 +1467,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
(guest_tr_ar & ~AR_TYPE_MASK)
| AR_TYPE_BUSY_64_TSS);
}
-
vcpu->arch.shadow_efer |= EFER_LMA;
-
- find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME;
- vmcs_write32(VM_ENTRY_CONTROLS,
- vmcs_read32(VM_ENTRY_CONTROLS)
- | VM_ENTRY_IA32E_MODE);
+ vmx_set_efer(vcpu, vcpu->arch.shadow_efer);
}
static void exit_lmode(struct kvm_vcpu *vcpu)
@@ -1609,30 +1627,6 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
vmcs_writel(GUEST_CR4, hw_cr4);
}
-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);
-
- vcpu->arch.shadow_efer = efer;
- if (!msr)
- return;
- if (efer & EFER_LMA) {
- vmcs_write32(VM_ENTRY_CONTROLS,
- vmcs_read32(VM_ENTRY_CONTROLS) |
- VM_ENTRY_IA32E_MODE);
- msr->data = efer;
-
- } else {
- vmcs_write32(VM_ENTRY_CONTROLS,
- vmcs_read32(VM_ENTRY_CONTROLS) &
- ~VM_ENTRY_IA32E_MODE);
-
- msr->data = efer & ~EFER_LME;
- }
- setup_msrs(vmx);
-}
-
static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
--
cgit v1.2.3
From 16175a796d061833aacfbd9672235f2d2725df65 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Mon, 23 Mar 2009 22:13:44 +0200
Subject: KVM: VMX: Don't allow uninhibited access to EFER on i386
vmx_set_msr() does not allow i386 guests to touch EFER, but they can still
do so through the default: label in the switch. If they set EFER_LME, they
can oops the host.
Fix by having EFER access through the normal channel (which will check for
EFER_LME) even on i386.
Reported-and-tested-by: Benjamin Gilbert <bgilbert@cs.cmu.edu>
Cc: stable@kernel.org
Signed-off-by: Avi Kivity <avi@redhat.com>
---
arch/x86/kvm/vmx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch/x86/kvm/vmx.c')
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 48063a0aa243..bb481330716f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -936,11 +936,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
int ret = 0;
switch (msr_index) {
-#ifdef CONFIG_X86_64
case MSR_EFER:
vmx_load_host_state(vmx);
ret = kvm_set_msr_common(vcpu, msr_index, data);
break;
+#ifdef CONFIG_X86_64
case MSR_FS_BASE:
vmcs_writel(GUEST_FS_BASE, data);
break;
--
cgit v1.2.3