summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/Makefile2
-rw-r--r--arch/x86/kvm/assigned-dev.c2
-rw-r--r--arch/x86/kvm/cpuid.c33
-rw-r--r--arch/x86/kvm/cpuid.h8
-rw-r--r--arch/x86/kvm/emulate.c196
-rw-r--r--arch/x86/kvm/i8254.c14
-rw-r--r--arch/x86/kvm/i8254.h2
-rw-r--r--arch/x86/kvm/i8259.c13
-rw-r--r--arch/x86/kvm/ioapic.c26
-rw-r--r--arch/x86/kvm/ioapic.h11
-rw-r--r--arch/x86/kvm/irq.h2
-rw-r--r--arch/x86/kvm/lapic.c163
-rw-r--r--arch/x86/kvm/lapic.h17
-rw-r--r--arch/x86/kvm/mmu.c67
-rw-r--r--arch/x86/kvm/pmu.c2
-rw-r--r--arch/x86/kvm/svm.c49
-rw-r--r--arch/x86/kvm/vmx.c199
-rw-r--r--arch/x86/kvm/x86.c215
18 files changed, 616 insertions, 405 deletions
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 08f790dfadc9..16e8f962eaad 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -1,5 +1,5 @@
-ccflags-y += -Ivirt/kvm -Iarch/x86/kvm
+ccflags-y += -Iarch/x86/kvm
CFLAGS_x86.o := -I.
CFLAGS_svm.o := -I.
diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c
index 6eb5c20ee373..d090ecf08809 100644
--- a/arch/x86/kvm/assigned-dev.c
+++ b/arch/x86/kvm/assigned-dev.c
@@ -666,7 +666,7 @@ static int probe_sysfs_permissions(struct pci_dev *dev)
if (r)
return r;
- inode = path.dentry->d_inode;
+ inode = d_backing_inode(path.dentry);
r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
path_put(&path);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8a80737ee6e6..59b69f6a2844 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -104,6 +104,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
((best->eax & 0xff00) >> 8) != 0)
return -EINVAL;
+ /* Update physical-address width */
+ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+
kvm_pmu_cpuid_update(vcpu);
return 0;
}
@@ -135,6 +138,21 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
}
}
+int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
+ if (!best || best->eax < 0x80000008)
+ goto not_found;
+ best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+ if (best)
+ return best->eax & 0xff;
+not_found:
+ return 36;
+}
+EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr);
+
/* when an old userspace process fills a new kernel module */
int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
struct kvm_cpuid *cpuid,
@@ -757,21 +775,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
}
EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
-int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
- if (!best || best->eax < 0x80000008)
- goto not_found;
- best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
- if (best)
- return best->eax & 0xff;
-not_found:
- return 36;
-}
-EXPORT_SYMBOL_GPL(cpuid_maxphyaddr);
-
/*
* If no match is found, check whether we exceed the vCPU's limit
* and return the content of the highest valid _standard_ leaf instead.
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 4452eedfaedd..c3b1ad9fca81 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -20,13 +20,19 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
struct kvm_cpuid_entry2 __user *entries);
void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
+
+static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.maxphyaddr;
+}
static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
if (!static_cpu_has(X86_FEATURE_XSAVE))
- return 0;
+ return false;
best = kvm_find_cpuid_entry(vcpu, 1, 0);
return best && (best->ecx & bit(X86_FEATURE_XSAVE));
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e0b794a84c35..630bcb0d7a04 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -248,27 +248,7 @@ struct mode_dual {
struct opcode mode64;
};
-/* EFLAGS bit definitions. */
-#define EFLG_ID (1<<21)
-#define EFLG_VIP (1<<20)
-#define EFLG_VIF (1<<19)
-#define EFLG_AC (1<<18)
-#define EFLG_VM (1<<17)
-#define EFLG_RF (1<<16)
-#define EFLG_IOPL (3<<12)
-#define EFLG_NT (1<<14)
-#define EFLG_OF (1<<11)
-#define EFLG_DF (1<<10)
-#define EFLG_IF (1<<9)
-#define EFLG_TF (1<<8)
-#define EFLG_SF (1<<7)
-#define EFLG_ZF (1<<6)
-#define EFLG_AF (1<<4)
-#define EFLG_PF (1<<2)
-#define EFLG_CF (1<<0)
-
#define EFLG_RESERVED_ZEROS_MASK 0xffc0802a
-#define EFLG_RESERVED_ONE_MASK 2
enum x86_transfer_type {
X86_TRANSFER_NONE,
@@ -317,7 +297,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
* These EFLAGS bits are restored from saved value during emulation, and
* any changes are written back to the saved value after emulation.
*/
-#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF)
+#define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\
+ X86_EFLAGS_PF|X86_EFLAGS_CF)
#ifdef CONFIG_X86_64
#define ON64(x) x
@@ -478,6 +459,25 @@ static void assign_masked(ulong *dest, ulong src, ulong mask)
*dest = (*dest & ~mask) | (src & mask);
}
+static void assign_register(unsigned long *reg, u64 val, int bytes)
+{
+ /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
+ switch (bytes) {
+ case 1:
+ *(u8 *)reg = (u8)val;
+ break;
+ case 2:
+ *(u16 *)reg = (u16)val;
+ break;
+ case 4:
+ *reg = (u32)val;
+ break; /* 64b: zero-extend */
+ case 8:
+ *reg = val;
+ break;
+ }
+}
+
static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt)
{
return (1UL << (ctxt->ad_bytes << 3)) - 1;
@@ -943,6 +943,22 @@ FASTOP2(xadd);
FASTOP2R(cmp, cmp_r);
+static int em_bsf_c(struct x86_emulate_ctxt *ctxt)
+{
+ /* If src is zero, do not writeback, but update flags */
+ if (ctxt->src.val == 0)
+ ctxt->dst.type = OP_NONE;
+ return fastop(ctxt, em_bsf);
+}
+
+static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
+{
+ /* If src is zero, do not writeback, but update flags */
+ if (ctxt->src.val == 0)
+ ctxt->dst.type = OP_NONE;
+ return fastop(ctxt, em_bsr);
+}
+
static u8 test_cc(unsigned int condition, unsigned long flags)
{
u8 rc;
@@ -1399,7 +1415,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
unsigned int in_page, n;
unsigned int count = ctxt->rep_prefix ?
address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1;
- in_page = (ctxt->eflags & EFLG_DF) ?
+ in_page = (ctxt->eflags & X86_EFLAGS_DF) ?
offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) :
PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI));
n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count);
@@ -1412,7 +1428,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
}
if (ctxt->rep_prefix && (ctxt->d & String) &&
- !(ctxt->eflags & EFLG_DF)) {
+ !(ctxt->eflags & X86_EFLAGS_DF)) {
ctxt->dst.data = rc->data + rc->pos;
ctxt->dst.type = OP_MEM_STR;
ctxt->dst.count = (rc->end - rc->pos) / size;
@@ -1691,21 +1707,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
static void write_register_operand(struct operand *op)
{
- /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
- switch (op->bytes) {
- case 1:
- *(u8 *)op->addr.reg = (u8)op->val;
- break;
- case 2:
- *(u16 *)op->addr.reg = (u16)op->val;
- break;
- case 4:
- *op->addr.reg = (u32)op->val;
- break; /* 64b: zero-extend */
- case 8:
- *op->addr.reg = op->val;
- break;
- }
+ return assign_register(op->addr.reg, op->val, op->bytes);
}
static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
@@ -1792,32 +1794,34 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt,
{
int rc;
unsigned long val, change_mask;
- int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+ int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT;
int cpl = ctxt->ops->cpl(ctxt);
rc = emulate_pop(ctxt, &val, len);
if (rc != X86EMUL_CONTINUE)
return rc;
- change_mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_OF
- | EFLG_TF | EFLG_DF | EFLG_NT | EFLG_AC | EFLG_ID;
+ change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+ X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF |
+ X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT |
+ X86_EFLAGS_AC | X86_EFLAGS_ID;
switch(ctxt->mode) {
case X86EMUL_MODE_PROT64:
case X86EMUL_MODE_PROT32:
case X86EMUL_MODE_PROT16:
if (cpl == 0)
- change_mask |= EFLG_IOPL;
+ change_mask |= X86_EFLAGS_IOPL;
if (cpl <= iopl)
- change_mask |= EFLG_IF;
+ change_mask |= X86_EFLAGS_IF;
break;
case X86EMUL_MODE_VM86:
if (iopl < 3)
return emulate_gp(ctxt, 0);
- change_mask |= EFLG_IF;
+ change_mask |= X86_EFLAGS_IF;
break;
default: /* real mode */
- change_mask |= (EFLG_IOPL | EFLG_IF);
+ change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF);
break;
}
@@ -1918,7 +1922,7 @@ static int em_pusha(struct x86_emulate_ctxt *ctxt)
static int em_pushf(struct x86_emulate_ctxt *ctxt)
{
- ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM;
+ ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM;
return em_push(ctxt);
}
@@ -1926,6 +1930,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
{
int rc = X86EMUL_CONTINUE;
int reg = VCPU_REGS_RDI;
+ u32 val;
while (reg >= VCPU_REGS_RAX) {
if (reg == VCPU_REGS_RSP) {
@@ -1933,9 +1938,10 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
--reg;
}
- rc = emulate_pop(ctxt, reg_rmw(ctxt, reg), ctxt->op_bytes);
+ rc = emulate_pop(ctxt, &val, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
break;
+ assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes);
--reg;
}
return rc;
@@ -1956,7 +1962,7 @@ static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
if (rc != X86EMUL_CONTINUE)
return rc;
- ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC);
+ ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC);
ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS);
rc = em_push(ctxt);
@@ -2022,10 +2028,14 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt)
unsigned long temp_eip = 0;
unsigned long temp_eflags = 0;
unsigned long cs = 0;
- unsigned long mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_TF |
- EFLG_IF | EFLG_DF | EFLG_OF | EFLG_IOPL | EFLG_NT | EFLG_RF |
- EFLG_AC | EFLG_ID | (1 << 1); /* Last one is the reserved bit */
- unsigned long vm86_mask = EFLG_VM | EFLG_VIF | EFLG_VIP;
+ unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+ X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF |
+ X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF |
+ X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF |
+ X86_EFLAGS_AC | X86_EFLAGS_ID |
+ X86_EFLAGS_FIXED;
+ unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF |
+ X86_EFLAGS_VIP;
/* TODO: Add stack limit check */
@@ -2054,7 +2064,6 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt)
ctxt->_eip = temp_eip;
-
if (ctxt->op_bytes == 4)
ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask));
else if (ctxt->op_bytes == 2) {
@@ -2063,7 +2072,7 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt)
}
ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */
- ctxt->eflags |= EFLG_RESERVED_ONE_MASK;
+ ctxt->eflags |= X86_EFLAGS_FIXED;
ctxt->ops->set_nmi_mask(ctxt, false);
return rc;
@@ -2145,12 +2154,12 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) {
*reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0);
*reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32);
- ctxt->eflags &= ~EFLG_ZF;
+ ctxt->eflags &= ~X86_EFLAGS_ZF;
} else {
ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) |
(u32) reg_read(ctxt, VCPU_REGS_RBX);
- ctxt->eflags |= EFLG_ZF;
+ ctxt->eflags |= X86_EFLAGS_ZF;
}
return X86EMUL_CONTINUE;
}
@@ -2222,7 +2231,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
ctxt->src.val = ctxt->dst.orig_val;
fastop(ctxt, em_cmp);
- if (ctxt->eflags & EFLG_ZF) {
+ if (ctxt->eflags & X86_EFLAGS_ZF) {
/* Success: write back to memory; no update of EAX */
ctxt->src.type = OP_NONE;
ctxt->dst.val = ctxt->src.orig_val;
@@ -2381,14 +2390,14 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data);
ctxt->eflags &= ~msr_data;
- ctxt->eflags |= EFLG_RESERVED_ONE_MASK;
+ ctxt->eflags |= X86_EFLAGS_FIXED;
#endif
} else {
/* legacy mode */
ops->get_msr(ctxt, MSR_STAR, &msr_data);
ctxt->_eip = (u32)msr_data;
- ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
+ ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
}
return X86EMUL_CONTINUE;
@@ -2425,8 +2434,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
if ((msr_data & 0xfffc) == 0x0)
return emulate_gp(ctxt, 0);
- ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
- cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK;
+ ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
+ cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK;
ss_sel = cs_sel + 8;
if (efer & EFER_LMA) {
cs.d = 0;
@@ -2493,8 +2502,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
return emulate_gp(ctxt, 0);
break;
}
- cs_sel |= SELECTOR_RPL_MASK;
- ss_sel |= SELECTOR_RPL_MASK;
+ cs_sel |= SEGMENT_RPL_MASK;
+ ss_sel |= SEGMENT_RPL_MASK;
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
@@ -2512,7 +2521,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
return false;
if (ctxt->mode == X86EMUL_MODE_VM86)
return true;
- iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+ iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT;
return ctxt->ops->cpl(ctxt) > iopl;
}
@@ -2782,10 +2791,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
return ret;
ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
- if (ret != X86EMUL_CONTINUE)
- return ret;
- return X86EMUL_CONTINUE;
+ return ret;
}
static int task_switch_32(struct x86_emulate_ctxt *ctxt,
@@ -2954,7 +2961,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg,
struct operand *op)
{
- int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count;
+ int df = (ctxt->eflags & X86_EFLAGS_DF) ? -op->count : op->count;
register_address_increment(ctxt, reg, df * op->bytes);
op->addr.mem.ea = register_address(ctxt, reg);
@@ -3323,7 +3330,7 @@ static int em_clts(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
-static int em_vmcall(struct x86_emulate_ctxt *ctxt)
+static int em_hypercall(struct x86_emulate_ctxt *ctxt)
{
int rc = ctxt->ops->fix_hypercall(ctxt);
@@ -3395,17 +3402,6 @@ static int em_lgdt(struct x86_emulate_ctxt *ctxt)
return em_lgdt_lidt(ctxt, true);
}
-static int em_vmmcall(struct x86_emulate_ctxt *ctxt)
-{
- int rc;
-
- rc = ctxt->ops->fix_hypercall(ctxt);
-
- /* Disable writeback. */
- ctxt->dst.type = OP_NONE;
- return rc;
-}
-
static int em_lidt(struct x86_emulate_ctxt *ctxt)
{
return em_lgdt_lidt(ctxt, false);
@@ -3504,7 +3500,8 @@ static int em_sahf(struct x86_emulate_ctxt *ctxt)
{
u32 flags;
- flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF;
+ flags = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
+ X86_EFLAGS_SF;
flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8;
ctxt->eflags &= ~0xffUL;
@@ -3769,7 +3766,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
static const struct opcode group7_rm0[] = {
N,
- I(SrcNone | Priv | EmulateOnUD, em_vmcall),
+ I(SrcNone | Priv | EmulateOnUD, em_hypercall),
N, N, N, N, N, N,
};
@@ -3781,7 +3778,7 @@ static const struct opcode group7_rm1[] = {
static const struct opcode group7_rm3[] = {
DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa),
- II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall),
+ II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall),
DIP(SrcNone | Prot | Priv, vmload, check_svme_pa),
DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa),
DIP(SrcNone | Prot | Priv, stgi, check_svme),
@@ -4192,7 +4189,8 @@ static const struct opcode twobyte_table[256] = {
N, N,
G(BitOp, group8),
F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc),
- F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr),
+ I(DstReg | SrcMem | ModRM, em_bsf_c),
+ I(DstReg | SrcMem | ModRM, em_bsr_c),
D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
/* 0xC0 - 0xC7 */
F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd),
@@ -4759,9 +4757,9 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
if (((ctxt->b == 0xa6) || (ctxt->b == 0xa7) ||
(ctxt->b == 0xae) || (ctxt->b == 0xaf))
&& (((ctxt->rep_prefix == REPE_PREFIX) &&
- ((ctxt->eflags & EFLG_ZF) == 0))
+ ((ctxt->eflags & X86_EFLAGS_ZF) == 0))
|| ((ctxt->rep_prefix == REPNE_PREFIX) &&
- ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))))
+ ((ctxt->eflags & X86_EFLAGS_ZF) == X86_EFLAGS_ZF))))
return true;
return false;
@@ -4913,7 +4911,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
/* All REP prefixes have the same first termination condition */
if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
ctxt->eip = ctxt->_eip;
- ctxt->eflags &= ~EFLG_RF;
+ ctxt->eflags &= ~X86_EFLAGS_RF;
goto done;
}
}
@@ -4950,7 +4948,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
goto done;
}
}
- ctxt->dst.orig_val = ctxt->dst.val;
+ /* Copy full 64-bit value for CMPXCHG8B. */
+ ctxt->dst.orig_val64 = ctxt->dst.val64;
special_insn:
@@ -4962,9 +4961,9 @@ special_insn:
}
if (ctxt->rep_prefix && (ctxt->d & String))
- ctxt->eflags |= EFLG_RF;
+ ctxt->eflags |= X86_EFLAGS_RF;
else
- ctxt->eflags &= ~EFLG_RF;
+ ctxt->eflags &= ~X86_EFLAGS_RF;
if (ctxt->execute) {
if (ctxt->d & Fastop) {
@@ -5013,7 +5012,7 @@ special_insn:
rc = emulate_int(ctxt, ctxt->src.val);
break;
case 0xce: /* into */
- if (ctxt->eflags & EFLG_OF)
+ if (ctxt->eflags & X86_EFLAGS_OF)
rc = emulate_int(ctxt, 4);
break;
case 0xe9: /* jmp rel */
@@ -5026,19 +5025,19 @@ special_insn:
break;
case 0xf5: /* cmc */
/* complement carry flag from eflags reg */
- ctxt->eflags ^= EFLG_CF;
+ ctxt->eflags ^= X86_EFLAGS_CF;
break;
case 0xf8: /* clc */
- ctxt->eflags &= ~EFLG_CF;
+ ctxt->eflags &= ~X86_EFLAGS_CF;
break;
case 0xf9: /* stc */
- ctxt->eflags |= EFLG_CF;
+ ctxt->eflags |= X86_EFLAGS_CF;
break;
case 0xfc: /* cld */
- ctxt->eflags &= ~EFLG_DF;
+ ctxt->eflags &= ~X86_EFLAGS_DF;
break;
case 0xfd: /* std */
- ctxt->eflags |= EFLG_DF;
+ ctxt->eflags |= X86_EFLAGS_DF;
break;
default:
goto cannot_emulate;
@@ -5099,7 +5098,7 @@ writeback:
}
goto done; /* skip rip writeback */
}
- ctxt->eflags &= ~EFLG_RF;
+ ctxt->eflags &= ~X86_EFLAGS_RF;
}
ctxt->eip = ctxt->_eip;
@@ -5136,8 +5135,7 @@ twobyte_insn:
case 0x40 ... 0x4f: /* cmov */
if (test_cc(ctxt->b, ctxt->eflags))
ctxt->dst.val = ctxt->src.val;
- else if (ctxt->mode != X86EMUL_MODE_PROT64 ||
- ctxt->op_bytes != 4)
+ else if (ctxt->op_bytes != 4)
ctxt->dst.type = OP_NONE; /* no writeback */
break;
case 0x80 ... 0x8f: /* jnz rel, etc*/
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 298781d4cfb4..4dce6f8b6129 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -443,7 +443,8 @@ static inline int pit_in_range(gpa_t addr)
(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
}
-static int pit_ioport_write(struct kvm_io_device *this,
+static int pit_ioport_write(struct kvm_vcpu *vcpu,
+ struct kvm_io_device *this,
gpa_t addr, int len, const void *data)
{
struct kvm_pit *pit = dev_to_pit(this);
@@ -519,7 +520,8 @@ static int pit_ioport_write(struct kvm_io_device *this,
return 0;
}
-static int pit_ioport_read(struct kvm_io_device *this,
+static int pit_ioport_read(struct kvm_vcpu *vcpu,
+ struct kvm_io_device *this,
gpa_t addr, int len, void *data)
{
struct kvm_pit *pit = dev_to_pit(this);
@@ -589,7 +591,8 @@ static int pit_ioport_read(struct kvm_io_device *this,
return 0;
}
-static int speaker_ioport_write(struct kvm_io_device *this,
+static int speaker_ioport_write(struct kvm_vcpu *vcpu,
+ struct kvm_io_device *this,
gpa_t addr, int len, const void *data)
{
struct kvm_pit *pit = speaker_to_pit(this);
@@ -606,8 +609,9 @@ static int speaker_ioport_write(struct kvm_io_device *this,
return 0;
}
-static int speaker_ioport_read(struct kvm_io_device *this,
- gpa_t addr, int len, void *data)
+static int speaker_ioport_read(struct kvm_vcpu *vcpu,
+ struct kvm_io_device *this,
+ gpa_t addr, int len, void *data)
{
struct kvm_pit *pit = speaker_to_pit(this);
struct kvm_kpit_state *pit_state = &pit->pit_state;
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index dd1b16b611b0..c84990b42b5b 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -3,7 +3,7 @@
#include <linux/kthread.h>
-#include "iodev.h"
+#include <kvm/iodev.h>
struct kvm_kpit_channel_state {
u32 count; /* can be 65536 */
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index cc31f7c06d3d..fef922ff2635 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -507,6 +507,7 @@ static int picdev_read(struct kvm_pic *s,
return -EOPNOTSUPP;
if (len != 1) {
+ memset(val, 0, len);
pr_pic_unimpl("non byte read\n");
return 0;
}
@@ -528,42 +529,42 @@ static int picdev_read(struct kvm_pic *s,
return 0;
}
-static int picdev_master_write(struct kvm_io_device *dev,
+static int picdev_master_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, const void *val)
{
return picdev_write(container_of(dev, struct kvm_pic, dev_master),
addr, len, val);
}
-static int picdev_master_read(struct kvm_io_device *dev,
+static int picdev_master_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, void *val)
{
return picdev_read(container_of(dev, struct kvm_pic, dev_master),
addr, len, val);
}
-static int picdev_slave_write(struct kvm_io_device *dev,
+static int picdev_slave_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, const void *val)
{
return picdev_write(container_of(dev, struct kvm_pic, dev_slave),
addr, len, val);
}
-static int picdev_slave_read(struct kvm_io_device *dev,
+static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, void *val)
{
return picdev_read(container_of(dev, struct kvm_pic, dev_slave),
addr, len, val);
}
-static int picdev_eclr_write(struct kvm_io_device *dev,
+static int picdev_eclr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, const void *val)
{
return picdev_write(container_of(dev, struct kvm_pic, dev_eclr),
addr, len, val);
}
-static int picdev_eclr_read(struct kvm_io_device *dev,
+static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
gpa_t addr, int len, void *val)
{
return picdev_read(container_of(dev, struct kvm_pic, dev_eclr),
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index b1947e0f3e10..28146f03c514 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -206,6 +206,8 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
old_irr = ioapic->irr;
ioapic->irr |= mask;
+ if (edge)
+ ioapic->irr_delivered &= ~mask;
if ((edge && old_irr == ioapic->irr) ||
(!edge && entry.fields.remote_irr)) {
ret = 0;
@@ -349,7 +351,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
irqe.shorthand = 0;
if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
- ioapic->irr &= ~(1 << irq);
+ ioapic->irr_delivered |= 1 << irq;
if (irq == RTC_GSI && line_status) {
/*
@@ -422,6 +424,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
struct kvm_ioapic *ioapic, int vector, int trigger_mode)
{
int i;
+ struct kvm_lapic *apic = vcpu->arch.apic;
for (i = 0; i < IOAPIC_NUM_PINS; i++) {
union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -443,7 +446,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
spin_lock(&ioapic->lock);
- if (trigger_mode != IOAPIC_LEVEL_TRIG)
+ if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+ kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
continue;
ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
@@ -471,13 +475,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
}
}
-bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
-{
- struct kvm_ioapic *ioapic = kvm->arch.vioapic;
- smp_rmb();
- return test_bit(vector, ioapic->handled_vectors);
-}
-
void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode)
{
struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
@@ -498,8 +495,8 @@ static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr)
(addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
}
-static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
- void *val)
+static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
+ gpa_t addr, int len, void *val)
{
struct kvm_ioapic *ioapic = to_ioapic(this);
u32 result;
@@ -541,8 +538,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
return 0;
}
-static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
- const void *val)
+static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
+ gpa_t addr, int len, const void *val)
{
struct kvm_ioapic *ioapic = to_ioapic(this);
u32 data;
@@ -597,6 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
ioapic->ioregsel = 0;
ioapic->irr = 0;
+ ioapic->irr_delivered = 0;
ioapic->id = 0;
memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
rtc_irq_eoi_tracking_reset(ioapic);
@@ -654,6 +652,7 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
spin_lock(&ioapic->lock);
memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
+ state->irr &= ~ioapic->irr_delivered;
spin_unlock(&ioapic->lock);
return 0;
}
@@ -667,6 +666,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
spin_lock(&ioapic->lock);
memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
ioapic->irr = 0;
+ ioapic->irr_delivered = 0;
update_handled_vectors(ioapic);
kvm_vcpu_request_scan_ioapic(kvm);
kvm_ioapic_inject_all(ioapic, state->irr);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index c2e36d934af4..ca0b0b4e6256 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -3,7 +3,7 @@
#include <linux/kvm_host.h>
-#include "iodev.h"
+#include <kvm/iodev.h>
struct kvm;
struct kvm_vcpu;
@@ -77,6 +77,7 @@ struct kvm_ioapic {
struct rtc_status rtc_status;
struct delayed_work eoi_inject;
u32 irq_eoi[IOAPIC_NUM_PINS];
+ u32 irr_delivered;
};
#ifdef DEBUG
@@ -97,13 +98,19 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
return kvm->arch.vioapic;
}
+static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ smp_rmb();
+ return test_bit(vector, ioapic->handled_vectors);
+}
+
void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, unsigned int dest, int dest_mode);
int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
int trigger_mode);
-bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
int kvm_ioapic_init(struct kvm *kvm);
void kvm_ioapic_destroy(struct kvm *kvm);
int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2d03568e9498..ad68c73008c5 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -27,7 +27,7 @@
#include <linux/kvm_host.h>
#include <linux/spinlock.h>
-#include "iodev.h"
+#include <kvm/iodev.h>
#include "ioapic.h"
#include "lapic.h"
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e55b5fc344eb..629af0f1c5c4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -133,6 +133,28 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
}
+/* The logical map is definitely wrong if we have multiple
+ * modes at the same time. (Physical map is always right.)
+ */
+static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map)
+{
+ return !(map->mode & (map->mode - 1));
+}
+
+static inline void
+apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid)
+{
+ unsigned lid_bits;
+
+ BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4);
+ BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8);
+ BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16);
+ lid_bits = map->mode;
+
+ *cid = dest_id >> lid_bits;
+ *lid = dest_id & ((1 << lid_bits) - 1);
+}
+
static void recalculate_apic_map(struct kvm *kvm)
{
struct kvm_apic_map *new, *old = NULL;
@@ -146,48 +168,6 @@ static void recalculate_apic_map(struct kvm *kvm)
if (!new)
goto out;
- new->ldr_bits = 8;
- /* flat mode is default */
- new->cid_shift = 8;
- new->cid_mask = 0;
- new->lid_mask = 0xff;
- new->broadcast = APIC_BROADCAST;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- struct kvm_lapic *apic = vcpu->arch.apic;
-
- if (!kvm_apic_present(vcpu))
- continue;
-
- if (apic_x2apic_mode(apic)) {
- new->ldr_bits = 32;
- new->cid_shift = 16;
- new->cid_mask = new->lid_mask = 0xffff;
- new->broadcast = X2APIC_BROADCAST;
- } else if (kvm_apic_get_reg(apic, APIC_LDR)) {
- if (kvm_apic_get_reg(apic, APIC_DFR) ==
- APIC_DFR_CLUSTER) {
- new->cid_shift = 4;
- new->cid_mask = 0xf;
- new->lid_mask = 0xf;
- } else {
- new->cid_shift = 8;
- new->cid_mask = 0;
- new->lid_mask = 0xff;
- }
- }
-
- /*
- * All APICs have to be configured in the same mode by an OS.
- * We take advatage of this while building logical id loockup
- * table. After reset APICs are in software disabled mode, so if
- * we find apic with different setting we assume this is the mode
- * OS wants all apics to be in; build lookup table accordingly.
- */
- if (kvm_apic_sw_enabled(apic))
- break;
- }
-
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvm_lapic *apic = vcpu->arch.apic;
u16 cid, lid;
@@ -198,11 +178,25 @@ static void recalculate_apic_map(struct kvm *kvm)
aid = kvm_apic_id(apic);
ldr = kvm_apic_get_reg(apic, APIC_LDR);
- cid = apic_cluster_id(new, ldr);
- lid = apic_logical_id(new, ldr);
if (aid < ARRAY_SIZE(new->phys_map))
new->phys_map[aid] = apic;
+
+ if (apic_x2apic_mode(apic)) {
+ new->mode |= KVM_APIC_MODE_X2APIC;
+ } else if (ldr) {
+ ldr = GET_APIC_LOGICAL_ID(ldr);
+ if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT)
+ new->mode |= KVM_APIC_MODE_XAPIC_FLAT;
+ else
+ new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER;
+ }
+
+ if (!kvm_apic_logical_map_valid(new))
+ continue;
+
+ apic_logical_id(new, ldr, &cid, &lid);
+
if (lid && cid < ARRAY_SIZE(new->logical_map))
new->logical_map[cid][ffs(lid) - 1] = apic;
}
@@ -588,15 +582,23 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
apic_update_ppr(apic);
}
-static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest)
+static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda)
{
- return dest == (apic_x2apic_mode(apic) ?
- X2APIC_BROADCAST : APIC_BROADCAST);
+ if (apic_x2apic_mode(apic))
+ return mda == X2APIC_BROADCAST;
+
+ return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST;
}
-static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest)
+static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda)
{
- return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest);
+ if (kvm_apic_broadcast(apic, mda))
+ return true;
+
+ if (apic_x2apic_mode(apic))
+ return mda == kvm_apic_id(apic);
+
+ return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic));
}
static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
@@ -613,6 +615,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
&& (logical_id & mda & 0xffff) != 0;
logical_id = GET_APIC_LOGICAL_ID(logical_id);
+ mda = GET_APIC_DEST_FIELD(mda);
switch (kvm_apic_get_reg(apic, APIC_DFR)) {
case APIC_DFR_FLAT:
@@ -627,10 +630,27 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
}
}
+/* KVM APIC implementation has two quirks
+ * - dest always begins at 0 while xAPIC MDA has offset 24,
+ * - IOxAPIC messages have to be delivered (directly) to x2APIC.
+ */
+static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source,
+ struct kvm_lapic *target)
+{
+ bool ipi = source != NULL;
+ bool x2apic_mda = apic_x2apic_mode(ipi ? source : target);
+
+ if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda)
+ return X2APIC_BROADCAST;
+
+ return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id);
+}
+
bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int short_hand, unsigned int dest, int dest_mode)
{
struct kvm_lapic *target = vcpu->arch.apic;
+ u32 mda = kvm_apic_mda(dest, source, target);
apic_debug("target %p, source %p, dest 0x%x, "
"dest_mode 0x%x, short_hand 0x%x\n",
@@ -640,9 +660,9 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
switch (short_hand) {
case APIC_DEST_NOSHORT:
if (dest_mode == APIC_DEST_PHYSICAL)
- return kvm_apic_match_physical_addr(target, dest);
+ return kvm_apic_match_physical_addr(target, mda);
else
- return kvm_apic_match_logical_addr(target, dest);
+ return kvm_apic_match_logical_addr(target, mda);
case APIC_DEST_SELF:
return target == source;
case APIC_DEST_ALLINC:
@@ -663,7 +683,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
unsigned long bitmap = 1;
struct kvm_lapic **dst;
int i;
- bool ret = false;
+ bool ret, x2apic_ipi;
*r = -1;
@@ -675,16 +695,18 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
if (irq->shorthand)
return false;
+ x2apic_ipi = src && apic_x2apic_mode(src);
+ if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST))
+ return false;
+
+ ret = true;
rcu_read_lock();
map = rcu_dereference(kvm->arch.apic_map);
- if (!map)
+ if (!map) {
+ ret = false;
goto out;
-
- if (irq->dest_id == map->broadcast)
- goto out;
-
- ret = true;
+ }
if (irq->dest_mode == APIC_DEST_PHYSICAL) {
if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
@@ -692,16 +714,20 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
dst = &map->phys_map[irq->dest_id];
} else {
- u32 mda = irq->dest_id << (32 - map->ldr_bits);
- u16 cid = apic_cluster_id(map, mda);
+ u16 cid;
+
+ if (!kvm_apic_logical_map_valid(map)) {
+ ret = false;
+ goto out;
+ }
+
+ apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap);
if (cid >= ARRAY_SIZE(map->logical_map))
goto out;
dst = map->logical_map[cid];
- bitmap = apic_logical_id(map, mda);
-
if (irq->delivery_mode == APIC_DM_LOWEST) {
int l = -1;
for_each_set_bit(i, &bitmap, 16) {
@@ -833,8 +859,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
{
- if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
- kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+ if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
int trigger_mode;
if (apic_test_vector(vector, apic->regs + APIC_TMR))
trigger_mode = IOAPIC_LEVEL_TRIG;
@@ -1038,7 +1063,7 @@ static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
addr < apic->base_address + LAPIC_MMIO_LENGTH;
}
-static int apic_mmio_read(struct kvm_io_device *this,
+static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
gpa_t address, int len, void *data)
{
struct kvm_lapic *apic = to_lapic(this);
@@ -1358,7 +1383,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
return ret;
}
-static int apic_mmio_write(struct kvm_io_device *this,
+static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this,
gpa_t address, int len, const void *data)
{
struct kvm_lapic *apic = to_lapic(this);
@@ -1498,8 +1523,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
return;
}
- if (!kvm_vcpu_is_bsp(apic->vcpu))
- value &= ~MSR_IA32_APICBASE_BSP;
vcpu->arch.apic_base = value;
/* update jump label if enable bit changes */
@@ -1572,7 +1595,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
}
apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
- apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
+ apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0;
apic->highest_isr_cache = -1;
update_divide_count(apic);
atomic_set(&apic->lapic_timer.pending, 0);
@@ -1782,7 +1805,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
update_divide_count(apic);
start_apic_timer(apic);
apic->irr_pending = true;
- apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+ apic->isr_count = kvm_x86_ops->hwapic_isr_update ?
1 : count_vectors(apic->regs + APIC_ISR);
apic->highest_isr_cache = -1;
if (kvm_x86_ops->hwapic_irr_update)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 0bc6c656625b..9d28383fc1e7 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -1,7 +1,7 @@
#ifndef __KVM_X86_LAPIC_H
#define __KVM_X86_LAPIC_H
-#include "iodev.h"
+#include <kvm/iodev.h>
#include <linux/kvm_host.h>
@@ -148,21 +148,6 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
return kvm_x86_ops->vm_has_apicv(kvm);
}
-static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
-{
- u16 cid;
- ldr >>= 32 - map->ldr_bits;
- cid = (ldr >> map->cid_shift) & map->cid_mask;
-
- return cid;
-}
-
-static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
-{
- ldr >>= (32 - map->ldr_bits);
- return ldr & map->lid_mask;
-}
-
static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
{
return vcpu->arch.apic->pending_events;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index cee759299a35..d43867c33bc4 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4465,6 +4465,73 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
kvm_flush_remote_tlbs(kvm);
}
+static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
+ unsigned long *rmapp)
+{
+ u64 *sptep;
+ struct rmap_iterator iter;
+ int need_tlb_flush = 0;
+ pfn_t pfn;
+ struct kvm_mmu_page *sp;
+
+ for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
+ BUG_ON(!(*sptep & PT_PRESENT_MASK));
+
+ sp = page_header(__pa(sptep));
+ pfn = spte_to_pfn(*sptep);
+
+ /*
+ * We cannot do huge page mapping for indirect shadow pages,
+ * which are found on the last rmap (level = 1) when not using
+ * tdp; such shadow pages are synced with the page table in
+ * the guest, and the guest page table is using 4K page size
+ * mapping if the indirect sp has level = 1.
+ */
+ if (sp->role.direct &&
+ !kvm_is_reserved_pfn(pfn) &&
+ PageTransCompound(pfn_to_page(pfn))) {
+ drop_spte(kvm, sptep);
+ sptep = rmap_get_first(*rmapp, &iter);
+ need_tlb_flush = 1;
+ } else
+ sptep = rmap_get_next(&iter);
+ }
+
+ return need_tlb_flush;
+}
+
+void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
+ struct kvm_memory_slot *memslot)
+{
+ bool flush = false;
+ unsigned long *rmapp;
+ unsigned long last_index, index;
+
+ spin_lock(&kvm->mmu_lock);
+
+ rmapp = memslot->arch.rmap[0];
+ last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1,
+ memslot->base_gfn, PT_PAGE_TABLE_LEVEL);
+
+ for (index = 0; index <= last_index; ++index, ++rmapp) {
+ if (*rmapp)
+ flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp);
+
+ if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+ if (flush) {
+ kvm_flush_remote_tlbs(kvm);
+ flush = false;
+ }
+ cond_resched_lock(&kvm->mmu_lock);
+ }
+ }
+
+ if (flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+}
+
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 8e6b7d869d2f..29fbf9dfdc54 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -38,7 +38,7 @@ static struct kvm_arch_event_perf_mapping {
};
/* mapping between fixed pmc index and arch_events array */
-int fixed_pmc_events[] = {1, 0, 7};
+static int fixed_pmc_events[] = {1, 0, 7};
static bool pmc_is_gp(struct kvm_pmc *pmc)
{
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d319e0c24758..ce741b8650f6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1261,7 +1261,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
MSR_IA32_APICBASE_ENABLE;
- if (kvm_vcpu_is_bsp(&svm->vcpu))
+ if (kvm_vcpu_is_reset_bsp(&svm->vcpu))
svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
svm_init_osvw(&svm->vcpu);
@@ -1929,14 +1929,12 @@ static int nop_on_interception(struct vcpu_svm *svm)
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)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
- skip_emulated_instruction(&svm->vcpu);
kvm_emulate_hypercall(&svm->vcpu);
return 1;
}
@@ -2757,11 +2755,11 @@ static int invlpga_interception(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
- trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX],
- vcpu->arch.regs[VCPU_REGS_RAX]);
+ trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX),
+ kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
- kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
+ kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
@@ -2770,12 +2768,18 @@ static int invlpga_interception(struct vcpu_svm *svm)
static int skinit_interception(struct vcpu_svm *svm)
{
- trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]);
+ trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
}
+static int wbinvd_interception(struct vcpu_svm *svm)
+{
+ kvm_emulate_wbinvd(&svm->vcpu);
+ return 1;
+}
+
static int xsetbv_interception(struct vcpu_svm *svm)
{
u64 new_bv = kvm_read_edx_eax(&svm->vcpu);
@@ -2902,7 +2906,8 @@ static int rdpmc_interception(struct vcpu_svm *svm)
return 1;
}
-bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val)
+static bool check_selective_cr0_intercepted(struct vcpu_svm *svm,
+ unsigned long val)
{
unsigned long cr0 = svm->vcpu.arch.cr0;
bool ret = false;
@@ -2940,7 +2945,10 @@ static int cr_interception(struct vcpu_svm *svm)
return emulate_on_interception(svm);
reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK;
- cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0;
+ if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE)
+ cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0;
+ else
+ cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0;
err = 0;
if (cr >= 16) { /* mov to cr */
@@ -3133,7 +3141,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
static int rdmsr_interception(struct vcpu_svm *svm)
{
- u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+ u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
u64 data;
if (svm_get_msr(&svm->vcpu, ecx, &data)) {
@@ -3142,8 +3150,8 @@ static int rdmsr_interception(struct vcpu_svm *svm)
} else {
trace_kvm_msr_read(ecx, data);
- svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff;
- svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32;
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff);
+ kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32);
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
skip_emulated_instruction(&svm->vcpu);
}
@@ -3246,9 +3254,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
static int wrmsr_interception(struct vcpu_svm *svm)
{
struct msr_data msr;
- u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
- u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u)
- | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32);
+ u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX);
+ u64 data = kvm_read_edx_eax(&svm->vcpu);
msr.data = data;
msr.index = ecx;
@@ -3325,7 +3332,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_READ_CR3] = cr_interception,
[SVM_EXIT_READ_CR4] = cr_interception,
[SVM_EXIT_READ_CR8] = cr_interception,
- [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception,
+ [SVM_EXIT_CR0_SEL_WRITE] = cr_interception,
[SVM_EXIT_WRITE_CR0] = cr_interception,
[SVM_EXIT_WRITE_CR3] = cr_interception,
[SVM_EXIT_WRITE_CR4] = cr_interception,
@@ -3376,7 +3383,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_STGI] = stgi_interception,
[SVM_EXIT_CLGI] = clgi_interception,
[SVM_EXIT_SKINIT] = skinit_interception,
- [SVM_EXIT_WBINVD] = emulate_on_interception,
+ [SVM_EXIT_WBINVD] = wbinvd_interception,
[SVM_EXIT_MONITOR] = monitor_interception,
[SVM_EXIT_MWAIT] = mwait_interception,
[SVM_EXIT_XSETBV] = xsetbv_interception,
@@ -3555,7 +3562,7 @@ static int handle_exit(struct kvm_vcpu *vcpu)
if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
|| !svm_exit_handlers[exit_code]) {
- WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+ WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
@@ -3649,11 +3656,6 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
return;
}
-static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
-{
- return;
-}
-
static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu)
{
return;
@@ -4403,7 +4405,6 @@ static struct kvm_x86_ops svm_x86_ops = {
.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
.vm_has_apicv = svm_vm_has_apicv,
.load_eoi_exitmap = svm_load_eoi_exitmap,
- .hwapic_isr_update = svm_hwapic_isr_update,
.sync_pir_to_irr = svm_sync_pir_to_irr,
.set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14c1a18d206a..f7b61687bd79 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2168,7 +2168,10 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
{
unsigned long *msr_bitmap;
- if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+ if (is_guest_mode(vcpu))
+ msr_bitmap = vmx_msr_bitmap_nested;
+ else if (irqchip_in_kernel(vcpu->kvm) &&
+ apic_x2apic_mode(vcpu->arch.apic)) {
if (is_long_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
else
@@ -2467,6 +2470,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
vmx->nested.nested_vmx_secondary_ctls_low = 0;
vmx->nested.nested_vmx_secondary_ctls_high &=
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
@@ -2476,8 +2480,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
if (enable_ept) {
/* nested EPT: emulate EPT also to L1 */
vmx->nested.nested_vmx_secondary_ctls_high |=
- SECONDARY_EXEC_ENABLE_EPT |
- SECONDARY_EXEC_UNRESTRICTED_GUEST;
+ SECONDARY_EXEC_ENABLE_EPT;
vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
VMX_EPT_INVEPT_BIT;
@@ -2491,6 +2494,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
} else
vmx->nested.nested_vmx_ept_caps = 0;
+ if (enable_unrestricted_guest)
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
/* miscellaneous data */
rdmsr(MSR_IA32_VMX_MISC,
vmx->nested.nested_vmx_misc_low,
@@ -3262,8 +3269,8 @@ static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg,
* default value.
*/
if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS)
- save->selector &= ~SELECTOR_RPL_MASK;
- save->dpl = save->selector & SELECTOR_RPL_MASK;
+ save->selector &= ~SEGMENT_RPL_MASK;
+ save->dpl = save->selector & SEGMENT_RPL_MASK;
save->s = 1;
}
vmx_set_segment(vcpu, save, seg);
@@ -3615,8 +3622,16 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
- unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ?
- KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+ /*
+ * Pass through host's Machine Check Enable value to hw_cr4, which
+ * is in force while we are in guest mode. Do not let guests control
+ * this bit, even if host CR4.MCE == 0.
+ */
+ unsigned long hw_cr4 =
+ (cr4_read_shadow() & X86_CR4_MCE) |
+ (cr4 & ~X86_CR4_MCE) |
+ (to_vmx(vcpu)->rmode.vm86_active ?
+ KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
if (cr4 & X86_CR4_VMXE) {
/*
@@ -3836,7 +3851,7 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
unsigned int cs_rpl;
vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
- cs_rpl = cs.selector & SELECTOR_RPL_MASK;
+ cs_rpl = cs.selector & SEGMENT_RPL_MASK;
if (cs.unusable)
return false;
@@ -3864,7 +3879,7 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu)
unsigned int ss_rpl;
vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
- ss_rpl = ss.selector & SELECTOR_RPL_MASK;
+ ss_rpl = ss.selector & SEGMENT_RPL_MASK;
if (ss.unusable)
return true;
@@ -3886,7 +3901,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
unsigned int rpl;
vmx_get_segment(vcpu, &var, seg);
- rpl = var.selector & SELECTOR_RPL_MASK;
+ rpl = var.selector & SEGMENT_RPL_MASK;
if (var.unusable)
return true;
@@ -3913,7 +3928,7 @@ static bool tr_valid(struct kvm_vcpu *vcpu)
if (tr.unusable)
return false;
- if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */
+ if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */
return false;
if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
return false;
@@ -3931,7 +3946,7 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu)
if (ldtr.unusable)
return true;
- if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */
+ if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */
return false;
if (ldtr.type != 2)
return false;
@@ -3948,8 +3963,8 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
- return ((cs.selector & SELECTOR_RPL_MASK) ==
- (ss.selector & SELECTOR_RPL_MASK));
+ return ((cs.selector & SEGMENT_RPL_MASK) ==
+ (ss.selector & SEGMENT_RPL_MASK));
}
/*
@@ -4367,6 +4382,18 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
return 0;
}
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_SMP
+ if (vcpu->mode == IN_GUEST_MODE) {
+ apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
+ POSTED_INTR_VECTOR);
+ return true;
+ }
+#endif
+ return false;
+}
+
static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
int vector)
{
@@ -4375,9 +4402,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
if (is_guest_mode(vcpu) &&
vector == vmx->nested.posted_intr_nv) {
/* the PIR and ON have been set by L1. */
- if (vcpu->mode == IN_GUEST_MODE)
- apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
- POSTED_INTR_VECTOR);
+ kvm_vcpu_trigger_posted_interrupt(vcpu);
/*
* If a posted intr is not recognized by hardware,
* we will accomplish it in the next vmentry.
@@ -4409,12 +4434,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
r = pi_test_and_set_on(&vmx->pi_desc);
kvm_make_request(KVM_REQ_EVENT, vcpu);
-#ifdef CONFIG_SMP
- if (!r && (vcpu->mode == IN_GUEST_MODE))
- apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
- POSTED_INTR_VECTOR);
- else
-#endif
+ if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu))
kvm_vcpu_kick(vcpu);
}
@@ -4700,7 +4720,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(&vmx->vcpu, 0);
apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
- if (kvm_vcpu_is_bsp(&vmx->vcpu))
+ if (kvm_vcpu_is_reset_bsp(&vmx->vcpu))
apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
apic_base_msr.host_initiated = true;
kvm_set_apic_base(&vmx->vcpu, &apic_base_msr);
@@ -4995,7 +5015,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
if (emulate_instruction(vcpu, 0) == EMULATE_DONE) {
if (vcpu->arch.halt_request) {
vcpu->arch.halt_request = 0;
- return kvm_emulate_halt(vcpu);
+ return kvm_vcpu_halt(vcpu);
}
return 1;
}
@@ -5060,6 +5080,10 @@ static int handle_exception(struct kvm_vcpu *vcpu)
}
if (is_invalid_opcode(intr_info)) {
+ if (is_guest_mode(vcpu)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
@@ -5079,9 +5103,10 @@ static int handle_exception(struct kvm_vcpu *vcpu)
!(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) {
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.ndata = 3;
vcpu->run->internal.data[0] = vect_info;
vcpu->run->internal.data[1] = intr_info;
+ vcpu->run->internal.data[2] = error_code;
return 0;
}
@@ -5522,13 +5547,11 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu)
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)
{
- skip_emulated_instruction(vcpu);
kvm_emulate_hypercall(vcpu);
return 1;
}
@@ -5559,7 +5582,6 @@ static int handle_rdpmc(struct kvm_vcpu *vcpu)
static int handle_wbinvd(struct kvm_vcpu *vcpu)
{
- skip_emulated_instruction(vcpu);
kvm_emulate_wbinvd(vcpu);
return 1;
}
@@ -5817,7 +5839,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
gpa_t gpa;
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
- if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+ if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
skip_emulated_instruction(vcpu);
return 1;
}
@@ -5898,7 +5920,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
if (vcpu->arch.halt_request) {
vcpu->arch.halt_request = 0;
- ret = kvm_emulate_halt(vcpu);
+ ret = kvm_vcpu_halt(vcpu);
goto out;
}
@@ -7307,21 +7329,21 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
else if (port < 0x10000)
bitmap = vmcs12->io_bitmap_b;
else
- return 1;
+ return true;
bitmap += (port & 0x7fff) / 8;
if (last_bitmap != bitmap)
if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1))
- return 1;
+ return true;
if (b & (1 << (port & 7)))
- return 1;
+ return true;
port++;
size--;
last_bitmap = bitmap;
}
- return 0;
+ return false;
}
/*
@@ -7337,7 +7359,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
gpa_t bitmap;
if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
- return 1;
+ return true;
/*
* The MSR_BITMAP page is divided into four 1024-byte bitmaps,
@@ -7356,10 +7378,10 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
if (msr_index < 1024*8) {
unsigned char b;
if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1))
- return 1;
+ return true;
return 1 & (b >> (msr_index & 7));
} else
- return 1; /* let L1 handle the wrong parameter */
+ return true; /* let L1 handle the wrong parameter */
}
/*
@@ -7381,7 +7403,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
case 0:
if (vmcs12->cr0_guest_host_mask &
(val ^ vmcs12->cr0_read_shadow))
- return 1;
+ return true;
break;
case 3:
if ((vmcs12->cr3_target_count >= 1 &&
@@ -7392,37 +7414,37 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
vmcs12->cr3_target_value2 == val) ||
(vmcs12->cr3_target_count >= 4 &&
vmcs12->cr3_target_value3 == val))
- return 0;
+ return false;
if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING))
- return 1;
+ return true;
break;
case 4:
if (vmcs12->cr4_guest_host_mask &
(vmcs12->cr4_read_shadow ^ val))
- return 1;
+ return true;
break;
case 8:
if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING))
- return 1;
+ return true;
break;
}
break;
case 2: /* clts */
if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) &&
(vmcs12->cr0_read_shadow & X86_CR0_TS))
- return 1;
+ return true;
break;
case 1: /* mov from cr */
switch (cr) {
case 3:
if (vmcs12->cpu_based_vm_exec_control &
CPU_BASED_CR3_STORE_EXITING)
- return 1;
+ return true;
break;
case 8:
if (vmcs12->cpu_based_vm_exec_control &
CPU_BASED_CR8_STORE_EXITING)
- return 1;
+ return true;
break;
}
break;
@@ -7433,14 +7455,14 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
*/
if (vmcs12->cr0_guest_host_mask & 0xe &
(val ^ vmcs12->cr0_read_shadow))
- return 1;
+ return true;
if ((vmcs12->cr0_guest_host_mask & 0x1) &&
!(vmcs12->cr0_read_shadow & 0x1) &&
(val & 0x1))
- return 1;
+ return true;
break;
}
- return 0;
+ return false;
}
/*
@@ -7463,48 +7485,48 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
KVM_ISA_VMX);
if (vmx->nested.nested_run_pending)
- return 0;
+ return false;
if (unlikely(vmx->fail)) {
pr_info_ratelimited("%s failed vm entry %x\n", __func__,
vmcs_read32(VM_INSTRUCTION_ERROR));
- return 1;
+ return true;
}
switch (exit_reason) {
case EXIT_REASON_EXCEPTION_NMI:
if (!is_exception(intr_info))
- return 0;
+ return false;
else if (is_page_fault(intr_info))
return enable_ept;
else if (is_no_device(intr_info) &&
!(vmcs12->guest_cr0 & X86_CR0_TS))
- return 0;
+ return false;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
case EXIT_REASON_EXTERNAL_INTERRUPT:
- return 0;
+ return false;
case EXIT_REASON_TRIPLE_FAULT:
- return 1;
+ return true;
case EXIT_REASON_PENDING_INTERRUPT:
return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING);
case EXIT_REASON_NMI_WINDOW:
return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING);
case EXIT_REASON_TASK_SWITCH:
- return 1;
+ return true;
case EXIT_REASON_CPUID:
if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa)
- return 0;
- return 1;
+ return false;
+ return true;
case EXIT_REASON_HLT:
return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
case EXIT_REASON_INVD:
- return 1;
+ return true;
case EXIT_REASON_INVLPG:
return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING);
case EXIT_REASON_RDPMC:
return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING);
- case EXIT_REASON_RDTSC:
+ case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP:
return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING);
case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR:
case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD:
@@ -7516,7 +7538,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
* VMX instructions trap unconditionally. This allows L1 to
* emulate them for its L2 guest, i.e., allows 3-level nesting!
*/
- return 1;
+ return true;
case EXIT_REASON_CR_ACCESS:
return nested_vmx_exit_handled_cr(vcpu, vmcs12);
case EXIT_REASON_DR_ACCESS:
@@ -7527,7 +7549,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_MSR_WRITE:
return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
case EXIT_REASON_INVALID_STATE:
- return 1;
+ return true;
case EXIT_REASON_MWAIT_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
case EXIT_REASON_MONITOR_INSTRUCTION:
@@ -7537,7 +7559,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
nested_cpu_has2(vmcs12,
SECONDARY_EXEC_PAUSE_LOOP_EXITING);
case EXIT_REASON_MCE_DURING_VMENTRY:
- return 0;
+ return false;
case EXIT_REASON_TPR_BELOW_THRESHOLD:
return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
case EXIT_REASON_APIC_ACCESS:
@@ -7546,7 +7568,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_APIC_WRITE:
case EXIT_REASON_EOI_INDUCED:
/* apic_write and eoi_induced should exit unconditionally. */
- return 1;
+ return true;
case EXIT_REASON_EPT_VIOLATION:
/*
* L0 always deals with the EPT violation. If nested EPT is
@@ -7554,7 +7576,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
* missing in the guest EPT table (EPT12), the EPT violation
* will be injected with nested_ept_inject_page_fault()
*/
- return 0;
+ return false;
case EXIT_REASON_EPT_MISCONFIG:
/*
* L2 never uses directly L1's EPT, but rather L0's own EPT
@@ -7562,11 +7584,11 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
* (EPT on EPT). So any problems with the structure of the
* table is L0's fault.
*/
- return 0;
+ return false;
case EXIT_REASON_WBINVD:
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
case EXIT_REASON_XSETBV:
- return 1;
+ return true;
case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS:
/*
* This should never happen, since it is not possible to
@@ -7576,7 +7598,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
*/
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
default:
- return 1;
+ return true;
}
}
@@ -8511,6 +8533,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
exec_control);
}
}
+ if (nested && !vmx->rdtscp_enabled)
+ vmx->nested.nested_vmx_secondary_ctls_high &=
+ ~SECONDARY_EXEC_RDTSCP;
}
/* Exposing INVPCID only when PCID is exposed */
@@ -8611,10 +8636,11 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- /* TODO: Also verify bits beyond physical address width are 0 */
- if (!PAGE_ALIGNED(vmcs12->apic_access_addr))
+ if (!PAGE_ALIGNED(vmcs12->apic_access_addr) ||
+ vmcs12->apic_access_addr >> maxphyaddr)
return false;
/*
@@ -8630,8 +8656,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
}
if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
- /* TODO: Also verify bits beyond physical address width are 0 */
- if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr))
+ if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) ||
+ vmcs12->virtual_apic_page_addr >> maxphyaddr)
return false;
if (vmx->nested.virtual_apic_page) /* shouldn't happen */
@@ -8654,7 +8680,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
}
if (nested_cpu_has_posted_intr(vmcs12)) {
- if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64))
+ if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) ||
+ vmcs12->posted_intr_desc_addr >> maxphyaddr)
return false;
if (vmx->nested.pi_desc_page) { /* shouldn't happen */
@@ -8853,9 +8880,9 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
unsigned long count_field,
- unsigned long addr_field,
- int maxphyaddr)
+ unsigned long addr_field)
{
+ int maxphyaddr;
u64 count, addr;
if (vmcs12_read_any(vcpu, count_field, &count) ||
@@ -8865,6 +8892,7 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
}
if (count == 0)
return 0;
+ maxphyaddr = cpuid_maxphyaddr(vcpu);
if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
(addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) {
pr_warn_ratelimited(
@@ -8878,19 +8906,16 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- int maxphyaddr;
-
if (vmcs12->vm_exit_msr_load_count == 0 &&
vmcs12->vm_exit_msr_store_count == 0 &&
vmcs12->vm_entry_msr_load_count == 0)
return 0; /* Fast path */
- maxphyaddr = cpuid_maxphyaddr(vcpu);
if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT,
- VM_EXIT_MSR_LOAD_ADDR, maxphyaddr) ||
+ VM_EXIT_MSR_LOAD_ADDR) ||
nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT,
- VM_EXIT_MSR_STORE_ADDR, maxphyaddr) ||
+ VM_EXIT_MSR_STORE_ADDR) ||
nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT,
- VM_ENTRY_MSR_LOAD_ADDR, maxphyaddr))
+ VM_ENTRY_MSR_LOAD_ADDR))
return -EINVAL;
return 0;
}
@@ -9140,8 +9165,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
exec_control &= ~SECONDARY_EXEC_RDTSCP;
/* Take the following fields only from vmcs12 */
exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_APIC_REGISTER_VIRT);
+ SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
exec_control |= vmcs12->secondary_vm_exec_control;
@@ -9213,9 +9239,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
}
if (cpu_has_vmx_msr_bitmap() &&
- exec_control & CPU_BASED_USE_MSR_BITMAPS &&
- nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) {
- vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested));
+ exec_control & CPU_BASED_USE_MSR_BITMAPS) {
+ nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
+ /* MSR_BITMAP will be set by following vmx_set_efer. */
} else
exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
@@ -9374,7 +9400,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
}
if (!nested_get_vmcs12_pages(vcpu, vmcs12)) {
- /*TODO: Also verify bits beyond physical address width are 0*/
nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
return 1;
}
@@ -9513,7 +9538,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
vmcs12->launch_state = 1;
if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT)
- return kvm_emulate_halt(vcpu);
+ return kvm_vcpu_halt(vcpu);
vmx->nested.nested_run_pending = 1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd7a70be41b3..c73efcd03e29 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -801,6 +801,17 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);
+static void kvm_update_dr0123(struct kvm_vcpu *vcpu)
+{
+ int i;
+
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+ for (i = 0; i < KVM_NR_DB_REGS; i++)
+ vcpu->arch.eff_db[i] = vcpu->arch.db[i];
+ vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
+ }
+}
+
static void kvm_update_dr6(struct kvm_vcpu *vcpu)
{
if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
@@ -1070,19 +1081,19 @@ static void update_pvclock_gtod(struct timekeeper *tk)
struct pvclock_gtod_data *vdata = &pvclock_gtod_data;
u64 boot_ns;
- boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot));
+ boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot));
write_seqcount_begin(&vdata->seq);
/* copy pvclock gtod data */
- vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode;
- vdata->clock.cycle_last = tk->tkr.cycle_last;
- vdata->clock.mask = tk->tkr.mask;
- vdata->clock.mult = tk->tkr.mult;
- vdata->clock.shift = tk->tkr.shift;
+ vdata->clock.vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+ vdata->clock.cycle_last = tk->tkr_mono.cycle_last;
+ vdata->clock.mask = tk->tkr_mono.mask;
+ vdata->clock.mult = tk->tkr_mono.mult;
+ vdata->clock.shift = tk->tkr_mono.shift;
vdata->boot_ns = boot_ns;
- vdata->nsec_base = tk->tkr.xtime_nsec;
+ vdata->nsec_base = tk->tkr_mono.xtime_nsec;
write_seqcount_end(&vdata->seq);
}
@@ -1658,12 +1669,28 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
&guest_hv_clock, sizeof(guest_hv_clock))))
return 0;
- /*
- * The interface expects us to write an even number signaling that the
- * update is finished. Since the guest won't see the intermediate
- * state, we just increase by 2 at the end.
+ /* This VCPU is paused, but it's legal for a guest to read another
+ * VCPU's kvmclock, so we really have to follow the specification where
+ * it says that version is odd if data is being modified, and even after
+ * it is consistent.
+ *
+ * Version field updates must be kept separate. This is because
+ * kvm_write_guest_cached might use a "rep movs" instruction, and
+ * writes within a string instruction are weakly ordered. So there
+ * are three writes overall.
+ *
+ * As a small optimization, only write the version field in the first
+ * and third write. The vcpu->pv_time cache is still valid, because the
+ * version field is the first in the struct.
*/
- vcpu->hv_clock.version = guest_hv_clock.version + 2;
+ BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+
+ vcpu->hv_clock.version = guest_hv_clock.version + 1;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
+
+ smp_wmb();
/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
@@ -1684,6 +1711,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
&vcpu->hv_clock,
sizeof(vcpu->hv_clock));
+
+ smp_wmb();
+
+ vcpu->hv_clock.version++;
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
return 0;
}
@@ -2744,7 +2778,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_USER_NMI:
case KVM_CAP_REINJECT_CONTROL:
case KVM_CAP_IRQ_INJECT_STATUS:
- case KVM_CAP_IRQFD:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_IOEVENTFD_NO_LENGTH:
case KVM_CAP_PIT2:
@@ -3150,6 +3183,7 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
return -EINVAL;
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
+ kvm_update_dr0123(vcpu);
vcpu->arch.dr6 = dbgregs->dr6;
kvm_update_dr6(vcpu);
vcpu->arch.dr7 = dbgregs->dr7;
@@ -4115,8 +4149,8 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
do {
n = min(len, 8);
if (!(vcpu->arch.apic &&
- !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v))
- && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v))
+ !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v))
+ && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
handled += n;
addr += n;
@@ -4135,8 +4169,9 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
do {
n = min(len, 8);
if (!(vcpu->arch.apic &&
- !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v))
- && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v))
+ !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev,
+ addr, n, v))
+ && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v);
handled += n;
@@ -4476,7 +4511,8 @@ mmio:
return X86EMUL_CONTINUE;
}
-int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
+static int emulator_read_write(struct x86_emulate_ctxt *ctxt,
+ unsigned long addr,
void *val, unsigned int bytes,
struct x86_exception *exception,
const struct read_write_emulator_ops *ops)
@@ -4539,7 +4575,7 @@ static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
exception, &read_emultor);
}
-int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
+static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
unsigned long addr,
const void *val,
unsigned int bytes,
@@ -4630,10 +4666,10 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
int r;
if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
+ r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
vcpu->arch.pio.size, pd);
else
- r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
+ r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
vcpu->arch.pio.port, vcpu->arch.pio.size,
pd);
return r;
@@ -4706,7 +4742,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address)
kvm_mmu_invlpg(emul_to_vcpu(ctxt), address);
}
-int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
+int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
{
if (!need_emulate_wbinvd(vcpu))
return X86EMUL_CONTINUE;
@@ -4723,19 +4759,29 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
wbinvd();
return X86EMUL_CONTINUE;
}
+
+int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops->skip_emulated_instruction(vcpu);
+ return kvm_emulate_wbinvd_noskip(vcpu);
+}
EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
+
+
static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt)
{
- kvm_emulate_wbinvd(emul_to_vcpu(ctxt));
+ kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt));
}
-int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
+static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
+ unsigned long *dest)
{
return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest);
}
-int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
+static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
+ unsigned long value)
{
return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value);
@@ -5776,7 +5822,6 @@ int kvm_arch_init(void *opaque)
kvm_set_mmio_spte_mask();
kvm_x86_ops = ops;
- kvm_init_msr_list();
kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
PT_DIRTY_MASK, PT64_NX_MASK, 0);
@@ -5817,7 +5862,7 @@ void kvm_arch_exit(void)
free_percpu(shared_msrs);
}
-int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+int kvm_vcpu_halt(struct kvm_vcpu *vcpu)
{
++vcpu->stat.halt_exits;
if (irqchip_in_kernel(vcpu->kvm)) {
@@ -5828,6 +5873,13 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
return 0;
}
}
+EXPORT_SYMBOL_GPL(kvm_vcpu_halt);
+
+int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops->skip_emulated_instruction(vcpu);
+ return kvm_vcpu_halt(vcpu);
+}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
@@ -5904,7 +5956,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
lapic_irq.dest_id = apicid;
lapic_irq.delivery_mode = APIC_DM_REMRD;
- kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL);
+ kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
}
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
@@ -5912,6 +5964,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
unsigned long nr, a0, a1, a2, a3, ret;
int op_64_bit, r = 1;
+ kvm_x86_ops->skip_emulated_instruction(vcpu);
+
if (kvm_hv_hypercall_enabled(vcpu->kvm))
return kvm_hv_hypercall(vcpu);
@@ -6165,7 +6219,7 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
}
/*
- * Returns 1 to let __vcpu_run() continue the guest execution loop without
+ * Returns 1 to let vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
* userspace.
*/
@@ -6302,6 +6356,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
set_debugreg(vcpu->arch.eff_db[2], 2);
set_debugreg(vcpu->arch.eff_db[3], 3);
set_debugreg(vcpu->arch.dr6, 6);
+ vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
}
trace_kvm_entry(vcpu->vcpu_id);
@@ -6383,42 +6438,47 @@ out:
return r;
}
+static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
+{
+ if (!kvm_arch_vcpu_runnable(vcpu)) {
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+ kvm_vcpu_block(vcpu);
+ vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+ if (!kvm_check_request(KVM_REQ_UNHALT, vcpu))
+ return 1;
+ }
-static int __vcpu_run(struct kvm_vcpu *vcpu)
+ kvm_apic_accept_events(vcpu);
+ switch(vcpu->arch.mp_state) {
+ case KVM_MP_STATE_HALTED:
+ vcpu->arch.pv.pv_unhalted = false;
+ vcpu->arch.mp_state =
+ KVM_MP_STATE_RUNNABLE;
+ case KVM_MP_STATE_RUNNABLE:
+ vcpu->arch.apf.halted = false;
+ break;
+ case KVM_MP_STATE_INIT_RECEIVED:
+ break;
+ default:
+ return -EINTR;
+ break;
+ }
+ return 1;
+}
+
+static int vcpu_run(struct kvm_vcpu *vcpu)
{
int r;
struct kvm *kvm = vcpu->kvm;
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- r = 1;
- while (r > 0) {
+ for (;;) {
if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
!vcpu->arch.apf.halted)
r = vcpu_enter_guest(vcpu);
- else {
- srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- kvm_vcpu_block(vcpu);
- vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) {
- kvm_apic_accept_events(vcpu);
- switch(vcpu->arch.mp_state) {
- case KVM_MP_STATE_HALTED:
- vcpu->arch.pv.pv_unhalted = false;
- vcpu->arch.mp_state =
- KVM_MP_STATE_RUNNABLE;
- case KVM_MP_STATE_RUNNABLE:
- vcpu->arch.apf.halted = false;
- break;
- case KVM_MP_STATE_INIT_RECEIVED:
- break;
- default:
- r = -EINTR;
- break;
- }
- }
- }
-
+ else
+ r = vcpu_block(kvm, vcpu);
if (r <= 0)
break;
@@ -6430,6 +6490,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
r = -EINTR;
vcpu->run->exit_reason = KVM_EXIT_INTR;
++vcpu->stat.request_irq_exits;
+ break;
}
kvm_check_async_pf_completion(vcpu);
@@ -6438,6 +6499,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
r = -EINTR;
vcpu->run->exit_reason = KVM_EXIT_INTR;
++vcpu->stat.signal_exits;
+ break;
}
if (need_resched()) {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
@@ -6569,7 +6631,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
} else
WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
- r = __vcpu_run(vcpu);
+ r = vcpu_run(vcpu);
out:
post_kvm_run_save(vcpu);
@@ -7076,11 +7138,14 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
kvm_clear_exception_queue(vcpu);
memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
+ kvm_update_dr0123(vcpu);
vcpu->arch.dr6 = DR6_INIT;
kvm_update_dr6(vcpu);
vcpu->arch.dr7 = DR7_FIXED_1;
kvm_update_dr7(vcpu);
+ vcpu->arch.cr2 = 0;
+
kvm_make_request(KVM_REQ_EVENT, vcpu);
vcpu->arch.apf.msr_val = 0;
vcpu->arch.st.msr_val = 0;
@@ -7210,7 +7275,14 @@ void kvm_arch_hardware_disable(void)
int kvm_arch_hardware_setup(void)
{
- return kvm_x86_ops->hardware_setup();
+ int r;
+
+ r = kvm_x86_ops->hardware_setup();
+ if (r != 0)
+ return r;
+
+ kvm_init_msr_list();
+ return 0;
}
void kvm_arch_hardware_unsetup(void)
@@ -7241,7 +7313,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.emulate_ctxt.ops = &emulate_ops;
- if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
+ if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
@@ -7289,6 +7361,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
vcpu->arch.guest_supported_xcr0 = 0;
vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+
kvm_async_pf_hash_reset(vcpu);
kvm_pmu_init(vcpu);
@@ -7429,7 +7503,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) {
- kvm_kvfree(free->arch.rmap[i]);
+ kvfree(free->arch.rmap[i]);
free->arch.rmap[i] = NULL;
}
if (i == 0)
@@ -7437,7 +7511,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
if (!dont || free->arch.lpage_info[i - 1] !=
dont->arch.lpage_info[i - 1]) {
- kvm_kvfree(free->arch.lpage_info[i - 1]);
+ kvfree(free->arch.lpage_info[i - 1]);
free->arch.lpage_info[i - 1] = NULL;
}
}
@@ -7491,12 +7565,12 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
out_free:
for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
- kvm_kvfree(slot->arch.rmap[i]);
+ kvfree(slot->arch.rmap[i]);
slot->arch.rmap[i] = NULL;
if (i == 0)
continue;
- kvm_kvfree(slot->arch.lpage_info[i - 1]);
+ kvfree(slot->arch.lpage_info[i - 1]);
slot->arch.lpage_info[i - 1] = NULL;
}
return -ENOMEM;
@@ -7619,6 +7693,23 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
new = id_to_memslot(kvm->memslots, mem->slot);
/*
+ * Dirty logging tracks sptes in 4k granularity, meaning that large
+ * sptes have to be split. If live migration is successful, the guest
+ * in the source machine will be destroyed and large sptes will be
+ * created in the destination. However, if the guest continues to run
+ * in the source machine (for example if live migration fails), small
+ * sptes will remain around and cause bad performance.
+ *
+ * Scan sptes if dirty logging has been stopped, dropping those
+ * which can be collapsed into a single large-page spte. Later
+ * page faults will create the large-page sptes.
+ */
+ if ((change != KVM_MR_DELETE) &&
+ (old->flags & KVM_MEM_LOG_DIRTY_PAGES) &&
+ !(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
+ kvm_mmu_zap_collapsible_sptes(kvm, new);
+
+ /*
* Set up write protection and/or dirty logging for the new slot.
*
* For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of old slot have
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-28 23:20:57 +0300