aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/x86/kvm/emulate.c38
-rw-r--r--arch/x86/kvm/lapic.c42
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--include/linux/kvm_host.h28
-rw-r--r--virt/kvm/kvm_main.c68
5 files changed, 119 insertions, 59 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6a57157675ad..38173343153f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -123,6 +123,7 @@
#define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */
#define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */
#define Escape (5<<15) /* Escape to coprocessor instruction */
+#define InstrDual (6<<15) /* Alternate instruction decoding of mod == 3 */
#define Sse (1<<18) /* SSE Vector instruction */
/* Generic ModRM decode. */
#define ModRM (1<<19)
@@ -211,6 +212,7 @@ struct opcode {
const struct group_dual *gdual;
const struct gprefix *gprefix;
const struct escape *esc;
+ const struct instr_dual *idual;
void (*fastop)(struct fastop *fake);
} u;
int (*check_perm)(struct x86_emulate_ctxt *ctxt);
@@ -233,6 +235,11 @@ struct escape {
struct opcode high[64];
};
+struct instr_dual {
+ struct opcode mod012;
+ struct opcode mod3;
+};
+
/* EFLAGS bit definitions. */
#define EFLG_ID (1<<21)
#define EFLG_VIP (1<<20)
@@ -3679,6 +3686,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
#define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
#define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
+#define ID(_f, _i) { .flags = ((_f) | InstrDual | ModRM), .u.idual = (_i) }
#define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
#define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
@@ -3840,8 +3848,12 @@ static const struct gprefix pfx_0f_6f_0f_7f = {
I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
};
+static const struct instr_dual instr_dual_0f_2b = {
+ I(0, em_mov), N
+};
+
static const struct gprefix pfx_0f_2b = {
- I(0, em_mov), I(0, em_mov), N, N,
+ ID(0, &instr_dual_0f_2b), ID(0, &instr_dual_0f_2b), N, N,
};
static const struct gprefix pfx_0f_28_0f_29 = {
@@ -3915,6 +3927,10 @@ static const struct escape escape_dd = { {
N, N, N, N, N, N, N, N,
} };
+static const struct instr_dual instr_dual_0f_c3 = {
+ I(DstMem | SrcReg | ModRM | No16 | Mov, em_mov), N
+};
+
static const struct opcode opcode_table[256] = {
/* 0x00 - 0x07 */
F6ALU(Lock, em_add),
@@ -4117,7 +4133,7 @@ static const struct opcode twobyte_table[256] = {
D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
/* 0xC0 - 0xC7 */
F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd),
- N, I(DstMem | SrcReg | ModRM | No16 | Mov, em_mov),
+ N, ID(0, &instr_dual_0f_c3),
N, N, N, GD(0, &group9),
/* 0xC8 - 0xCF */
X8(I(DstReg, em_bswap)),
@@ -4130,12 +4146,20 @@ static const struct opcode twobyte_table[256] = {
N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N
};
+static const struct instr_dual instr_dual_0f_38_f0 = {
+ I(DstReg | SrcMem | Mov, em_movbe), N
+};
+
+static const struct instr_dual instr_dual_0f_38_f1 = {
+ I(DstMem | SrcReg | Mov, em_movbe), N
+};
+
static const struct gprefix three_byte_0f_38_f0 = {
- I(DstReg | SrcMem | Mov, em_movbe), N, N, N
+ ID(0, &instr_dual_0f_38_f0), N, N, N
};
static const struct gprefix three_byte_0f_38_f1 = {
- I(DstMem | SrcReg | Mov, em_movbe), N, N, N
+ ID(0, &instr_dual_0f_38_f1), N, N, N
};
/*
@@ -4536,6 +4560,12 @@ done_prefixes:
else
opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
break;
+ case InstrDual:
+ if ((ctxt->modrm >> 6) == 3)
+ opcode = opcode.u.idual->mod3;
+ else
+ opcode = opcode.u.idual->mod012;
+ break;
default:
return EMULATION_FAILED;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index f739f804b3a2..4f0c0b954686 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -132,8 +132,6 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
}
-#define KVM_X2APIC_CID_BITS 0
-
static void recalculate_apic_map(struct kvm *kvm)
{
struct kvm_apic_map *new, *old = NULL;
@@ -163,8 +161,7 @@ static void recalculate_apic_map(struct kvm *kvm)
if (apic_x2apic_mode(apic)) {
new->ldr_bits = 32;
new->cid_shift = 16;
- new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
- new->lid_mask = 0xffff;
+ 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) ==
@@ -193,15 +190,16 @@ static void recalculate_apic_map(struct kvm *kvm)
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvm_lapic *apic = vcpu->arch.apic;
u16 cid, lid;
- u32 ldr;
-
- new->phys_map[kvm_apic_id(apic)] = apic;
+ u32 ldr, aid;
+ 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 (lid)
+ if (aid < ARRAY_SIZE(new->phys_map))
+ new->phys_map[aid] = apic;
+ if (lid && cid < ARRAY_SIZE(new->logical_map))
new->logical_map[cid][ffs(lid) - 1] = apic;
}
out:
@@ -690,14 +688,21 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
if (irq->dest_id == map->broadcast)
goto out;
+ ret = true;
+
if (irq->dest_mode == 0) { /* physical mode */
- if (irq->delivery_mode == APIC_DM_LOWEST)
+ if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
goto out;
- dst = &map->phys_map[irq->dest_id & 0xff];
+
+ dst = &map->phys_map[irq->dest_id];
} else {
u32 mda = irq->dest_id << (32 - map->ldr_bits);
+ u16 cid = apic_cluster_id(map, mda);
+
+ if (cid >= ARRAY_SIZE(map->logical_map))
+ goto out;
- dst = map->logical_map[apic_cluster_id(map, mda)];
+ dst = map->logical_map[cid];
bitmap = apic_logical_id(map, mda);
@@ -723,8 +728,6 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
*r = 0;
*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
}
-
- ret = true;
out:
rcu_read_unlock();
return ret;
@@ -1883,8 +1886,11 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
return 1;
+ if (reg == APIC_ICR2)
+ return 1;
+
/* if this is ICR write vector before command */
- if (msr == 0x830)
+ if (reg == APIC_ICR)
apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
return apic_reg_write(apic, reg, (u32)data);
}
@@ -1897,9 +1903,15 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
return 1;
+ if (reg == APIC_DFR || reg == APIC_ICR2) {
+ apic_debug("KVM_APIC_READ: read x2apic reserved register %x\n",
+ reg);
+ return 1;
+ }
+
if (apic_reg_read(apic, reg, 4, &low))
return 1;
- if (msr == 0x830)
+ if (reg == APIC_ICR)
apic_reg_read(apic, APIC_ICR2, 4, &high);
*data = (((u64)high) << 32) | low;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index d4365f21ea2e..c674fce53cf9 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -154,8 +154,6 @@ static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
ldr >>= 32 - map->ldr_bits;
cid = (ldr >> map->cid_shift) & map->cid_mask;
- BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
-
return cid;
}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 231dd9472226..193bca68372d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -353,6 +353,8 @@ struct kvm_memslots {
struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM];
/* The mapping table from slot id to the index in memslots[]. */
short id_to_index[KVM_MEM_SLOTS_NUM];
+ atomic_t lru_slot;
+ int used_slots;
};
struct kvm {
@@ -790,12 +792,28 @@ static inline void kvm_guest_exit(void)
static inline struct kvm_memory_slot *
search_memslots(struct kvm_memslots *slots, gfn_t gfn)
{
- struct kvm_memory_slot *memslot;
+ int start = 0, end = slots->used_slots;
+ int slot = atomic_read(&slots->lru_slot);
+ struct kvm_memory_slot *memslots = slots->memslots;
- kvm_for_each_memslot(memslot, slots)
- if (gfn >= memslot->base_gfn &&
- gfn < memslot->base_gfn + memslot->npages)
- return memslot;
+ if (gfn >= memslots[slot].base_gfn &&
+ gfn < memslots[slot].base_gfn + memslots[slot].npages)
+ return &memslots[slot];
+
+ while (start < end) {
+ slot = start + (end - start) / 2;
+
+ if (gfn >= memslots[slot].base_gfn)
+ end = slot;
+ else
+ start = slot + 1;
+ }
+
+ if (gfn >= memslots[start].base_gfn &&
+ gfn < memslots[start].base_gfn + memslots[start].npages) {
+ atomic_set(&slots->lru_slot, start);
+ return &memslots[start];
+ }
return NULL;
}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5b4533079eaa..c5c186af823b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -124,15 +124,6 @@ int vcpu_load(struct kvm_vcpu *vcpu)
if (mutex_lock_killable(&vcpu->mutex))
return -EINTR;
- if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
- /* The thread running this VCPU changed. */
- struct pid *oldpid = vcpu->pid;
- struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
- rcu_assign_pointer(vcpu->pid, newpid);
- if (oldpid)
- synchronize_rcu();
- put_pid(oldpid);
- }
cpu = get_cpu();
preempt_notifier_register(&vcpu->preempt_notifier);
kvm_arch_vcpu_load(vcpu, cpu);
@@ -666,10 +657,10 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
}
/*
- * Insert memslot and re-sort memslots based on their size,
- * so the larger slots will get better fit. Sorting algorithm
- * takes advantage of having initially sorted array and
- * known changed memslot position.
+ * Insert memslot and re-sort memslots based on their GFN,
+ * so binary search could be used to lookup GFN.
+ * Sorting algorithm takes advantage of having initially
+ * sorted array and known changed memslot position.
*/
static void update_memslots(struct kvm_memslots *slots,
struct kvm_memory_slot *new)
@@ -679,22 +670,28 @@ static void update_memslots(struct kvm_memslots *slots,
struct kvm_memory_slot *mslots = slots->memslots;
WARN_ON(mslots[i].id != id);
- if (new->npages != mslots[i].npages) {
- if (new->npages < mslots[i].npages) {
- while (i < KVM_MEM_SLOTS_NUM - 1 &&
- new->npages < mslots[i + 1].npages) {
- mslots[i] = mslots[i + 1];
- slots->id_to_index[mslots[i].id] = i;
- i++;
- }
- } else {
- while (i > 0 &&
- new->npages > mslots[i - 1].npages) {
- mslots[i] = mslots[i - 1];
- slots->id_to_index[mslots[i].id] = i;
- i--;
- }
- }
+ if (!new->npages) {
+ new->base_gfn = 0;
+ if (mslots[i].npages)
+ slots->used_slots--;
+ } else {
+ if (!mslots[i].npages)
+ slots->used_slots++;
+ }
+
+ while (i < KVM_MEM_SLOTS_NUM - 1 &&
+ new->base_gfn <= mslots[i + 1].base_gfn) {
+ if (!mslots[i + 1].npages)
+ break;
+ mslots[i] = mslots[i + 1];
+ slots->id_to_index[mslots[i].id] = i;
+ i++;
+ }
+ while (i > 0 &&
+ new->base_gfn > mslots[i - 1].base_gfn) {
+ mslots[i] = mslots[i - 1];
+ slots->id_to_index[mslots[i].id] = i;
+ i--;
}
mslots[i] = *new;
@@ -1782,10 +1779,6 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target)
rcu_read_unlock();
if (!task)
return ret;
- if (task->flags & PF_VCPU) {
- put_task_struct(task);
- return ret;
- }
ret = yield_to(task, 1);
put_task_struct(task);
@@ -2048,6 +2041,15 @@ static long kvm_vcpu_ioctl(struct file *filp,
r = -EINVAL;
if (arg)
goto out;
+ if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
+ /* The thread running this VCPU changed. */
+ struct pid *oldpid = vcpu->pid;
+ struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
+ rcu_assign_pointer(vcpu->pid, newpid);
+ if (oldpid)
+ synchronize_rcu();
+ put_pid(oldpid);
+ }
r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
break;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.