summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/emulate.c63
-rw-r--r--arch/x86/kvm/mmu.c6
-rw-r--r--arch/x86/kvm/mmutrace.h4
-rw-r--r--arch/x86/kvm/vmx.c6
4 files changed, 58 insertions, 21 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 749f9fa38254..9f8a2faf5040 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -574,12 +574,14 @@ static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
case 4:
ctxt->_eip = (u32)dst;
break;
+#ifdef CONFIG_X86_64
case 8:
if ((cs_l && is_noncanonical_address(dst)) ||
- (!cs_l && (dst & ~(u32)-1)))
+ (!cs_l && (dst >> 32) != 0))
return emulate_gp(ctxt, 0);
ctxt->_eip = dst;
break;
+#endif
default:
WARN(1, "unsupported eip assignment size\n");
}
@@ -641,7 +643,8 @@ static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
static int __linearize(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
- unsigned size, bool write, bool fetch,
+ unsigned *max_size, unsigned size,
+ bool write, bool fetch,
ulong *linear)
{
struct desc_struct desc;
@@ -652,10 +655,15 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
unsigned cpl;
la = seg_base(ctxt, addr.seg) + addr.ea;
+ *max_size = 0;
switch (ctxt->mode) {
case X86EMUL_MODE_PROT64:
if (((signed long)la << 16) >> 16 != la)
return emulate_gp(ctxt, 0);
+
+ *max_size = min_t(u64, ~0u, (1ull << 48) - la);
+ if (size > *max_size)
+ goto bad;
break;
default:
usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
@@ -673,20 +681,25 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
if ((ctxt->mode == X86EMUL_MODE_REAL) && !fetch &&
(ctxt->d & NoBigReal)) {
/* la is between zero and 0xffff */
- if (la > 0xffff || (u32)(la + size - 1) > 0xffff)
+ if (la > 0xffff)
goto bad;
+ *max_size = 0x10000 - la;
} else if ((desc.type & 8) || !(desc.type & 4)) {
/* expand-up segment */
- if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
+ if (addr.ea > lim)
goto bad;
+ *max_size = min_t(u64, ~0u, (u64)lim + 1 - addr.ea);
} else {
/* expand-down segment */
- if (addr.ea <= lim || (u32)(addr.ea + size - 1) <= lim)
+ if (addr.ea <= lim)
goto bad;
lim = desc.d ? 0xffffffff : 0xffff;
- if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
+ if (addr.ea > lim)
goto bad;
+ *max_size = min_t(u64, ~0u, (u64)lim + 1 - addr.ea);
}
+ if (size > *max_size)
+ goto bad;
cpl = ctxt->ops->cpl(ctxt);
if (!(desc.type & 8)) {
/* data segment */
@@ -711,9 +724,9 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
return X86EMUL_CONTINUE;
bad:
if (addr.seg == VCPU_SREG_SS)
- return emulate_ss(ctxt, sel);
+ return emulate_ss(ctxt, 0);
else
- return emulate_gp(ctxt, sel);
+ return emulate_gp(ctxt, 0);
}
static int linearize(struct x86_emulate_ctxt *ctxt,
@@ -721,7 +734,8 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
unsigned size, bool write,
ulong *linear)
{
- return __linearize(ctxt, addr, size, write, false, linear);
+ unsigned max_size;
+ return __linearize(ctxt, addr, &max_size, size, write, false, linear);
}
@@ -746,17 +760,27 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
{
int rc;
- unsigned size;
+ unsigned size, max_size;
unsigned long linear;
int cur_size = ctxt->fetch.end - ctxt->fetch.data;
struct segmented_address addr = { .seg = VCPU_SREG_CS,
.ea = ctxt->eip + cur_size };
- size = 15UL ^ cur_size;
- rc = __linearize(ctxt, addr, size, false, true, &linear);
+ /*
+ * We do not know exactly how many bytes will be needed, and
+ * __linearize is expensive, so fetch as much as possible. We
+ * just have to avoid going beyond the 15 byte limit, the end
+ * of the segment, or the end of the page.
+ *
+ * __linearize is called with size 0 so that it does not do any
+ * boundary check itself. Instead, we use max_size to check
+ * against op_size.
+ */
+ rc = __linearize(ctxt, addr, &max_size, 0, false, true, &linear);
if (unlikely(rc != X86EMUL_CONTINUE))
return rc;
+ size = min_t(unsigned, 15UL ^ cur_size, max_size);
size = min_t(unsigned, size, PAGE_SIZE - offset_in_page(linear));
/*
@@ -766,7 +790,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
* still, we must have hit the 15-byte boundary.
*/
if (unlikely(size < op_size))
- return X86EMUL_UNHANDLEABLE;
+ return emulate_gp(ctxt, 0);
+
rc = ctxt->ops->fetch(ctxt, linear, ctxt->fetch.end,
size, &ctxt->exception);
if (unlikely(rc != X86EMUL_CONTINUE))
@@ -2012,7 +2037,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
rc = assign_eip_far(ctxt, ctxt->src.val, new_desc.l);
if (rc != X86EMUL_CONTINUE) {
- WARN_ON(!ctxt->mode != X86EMUL_MODE_PROT64);
+ WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
/* assigning eip failed; restore the old cs */
ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
return rc;
@@ -2109,7 +2134,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
return rc;
rc = assign_eip_far(ctxt, eip, new_desc.l);
if (rc != X86EMUL_CONTINUE) {
- WARN_ON(!ctxt->mode != X86EMUL_MODE_PROT64);
+ WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
}
return rc;
@@ -4262,6 +4287,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
fetch_register_operand(op);
break;
case OpCL:
+ op->type = OP_IMM;
op->bytes = 1;
op->val = reg_read(ctxt, VCPU_REGS_RCX) & 0xff;
break;
@@ -4269,6 +4295,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
rc = decode_imm(ctxt, op, 1, true);
break;
case OpOne:
+ op->type = OP_IMM;
op->bytes = 1;
op->val = 1;
break;
@@ -4327,21 +4354,27 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
ctxt->memop.bytes = ctxt->op_bytes + 2;
goto mem_common;
case OpES:
+ op->type = OP_IMM;
op->val = VCPU_SREG_ES;
break;
case OpCS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_CS;
break;
case OpSS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_SS;
break;
case OpDS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_DS;
break;
case OpFS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_FS;
break;
case OpGS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_GS;
break;
case OpImplicit:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ac1c4de3a484..978f402006ee 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -630,7 +630,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
* kvm mmu, before reclaiming the page, we should
* unmap it from mmu first.
*/
- WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+ WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));
if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
kvm_set_pfn_accessed(pfn);
@@ -2461,7 +2461,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
spte |= PT_PAGE_SIZE_MASK;
if (tdp_enabled)
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
- kvm_is_mmio_pfn(pfn));
+ kvm_is_reserved_pfn(pfn));
if (host_writable)
spte |= SPTE_HOST_WRITEABLE;
@@ -2737,7 +2737,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
* PT_PAGE_TABLE_LEVEL and there would be no adjustment done
* here.
*/
- if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
+ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
PageTransCompound(pfn_to_page(pfn)) &&
!has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 5aaf35641768..ce463a9cc8fb 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -22,7 +22,7 @@
__entry->unsync = sp->unsync;
#define KVM_MMU_PAGE_PRINTK() ({ \
- const u32 saved_len = p->len; \
+ const char *saved_ptr = trace_seq_buffer_ptr(p); \
static const char *access_str[] = { \
"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" \
}; \
@@ -41,7 +41,7 @@
role.nxe ? "" : "!", \
__entry->root_count, \
__entry->unsync ? "unsync" : "sync", 0); \
- p->buffer + saved_len; \
+ saved_ptr; \
})
#define kvm_mmu_trace_pferr_flags \
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a8b76c4c95e2..3e556c68351b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4579,7 +4579,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write32(TPR_THRESHOLD, 0);
}
- kvm_vcpu_reload_apic_access_page(vcpu);
+ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
if (vmx_vm_has_apicv(vcpu->kvm))
memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
@@ -6426,6 +6426,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
const unsigned long *fields = shadow_read_write_fields;
const int num_fields = max_shadow_read_write_fields;
+ preempt_disable();
+
vmcs_load(shadow_vmcs);
for (i = 0; i < num_fields; i++) {
@@ -6449,6 +6451,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
vmcs_clear(shadow_vmcs);
vmcs_load(vmx->loaded_vmcs->vmcs);
+
+ preempt_enable();
}
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
generated by cgit v1.2.3 (git 2.25.1) at 2026-01-03 18:29:09 +0000