#define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
-#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
+#define _HYP_PAGE_DEFAULT _PAGE_DEFAULT
-#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
-#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
+#define PAGE_KERNEL __pgprot(PROT_NORMAL)
+#define PAGE_KERNEL_RO __pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
+#define PAGE_KERNEL_ROX __pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
+#define PAGE_KERNEL_EXEC __pgprot(PROT_NORMAL & ~PTE_PXN)
+#define PAGE_KERNEL_EXEC_CONT __pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
-#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
-#define PAGE_HYP_EXEC __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
-#define PAGE_HYP_RO __pgprot(_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
+#define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
+#define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
+#define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
- #define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
- #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
-#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
-#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
++#define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN)
++#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
-#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
+#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
void hyperv_setup_mmu_ops(void);
void hyper_alloc_mmu(void);
void hyperv_report_panic(struct pt_regs *regs, long err);
-bool hv_is_hypercall_page_setup(void);
+bool hv_is_hyperv_initialized(void);
void hyperv_cleanup(void);
+
+ void hyperv_reenlightenment_intr(struct pt_regs *regs);
+ void set_hv_tscchange_cb(void (*cb)(void));
+ void clear_hv_tscchange_cb(void);
+ void hyperv_stop_tsc_emulation(void);
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
-static inline bool hv_is_hypercall_page_setup(void) { return false; }
+static inline bool hv_is_hyperv_initialized(void) { return false; }
static inline void hyperv_cleanup(void) {}
static inline void hyperv_setup_mmu_ops(void) {}
+ static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
+ static inline void clear_hv_tscchange_cb(void) {}
+ static inline void hyperv_stop_tsc_emulation(void) {};
#endif /* CONFIG_HYPERV */
#ifdef CONFIG_HYPERV_TSCPAGE
static inline short vmcs_field_to_offset(unsigned long field)
{
+ const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table);
+ unsigned short offset;
+ unsigned index;
+
+ if (field >> 15)
+ return -ENOENT;
- BUILD_BUG_ON(size > SHRT_MAX);
- if (field >= size)
+ index = ROL16(field, 6);
- if (index >= ARRAY_SIZE(vmcs_field_to_offset_table))
++ if (index >= size)
return -ENOENT;
- field = array_index_nospec(field, size);
- offset = vmcs_field_to_offset_table[field];
- /*
- * FIXME: Mitigation for CVE-2017-5753. To be replaced with a
- * generic mechanism.
- */
- asm("lfence");
-
- if (vmcs_field_to_offset_table[index] == 0)
++ index = array_index_nospec(index, size);
++ offset = vmcs_field_to_offset_table[index];
+ if (offset == 0)
return -ENOENT;
-
- return vmcs_field_to_offset_table[index];
+ return offset;
}
static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
struct page *page;
unsigned long *msr_bitmap_l1;
unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
+ /*
+ * pred_cmd & spec_ctrl are trying to verify two things:
+ *
+ * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
+ * ensures that we do not accidentally generate an L02 MSR bitmap
+ * from the L12 MSR bitmap that is too permissive.
+ * 2. That L1 or L2s have actually used the MSR. This avoids
+ * unnecessarily merging of the bitmap if the MSR is unused. This
+ * works properly because we only update the L01 MSR bitmap lazily.
+ * So even if L0 should pass L1 these MSRs, the L01 bitmap is only
+ * updated to reflect this when L1 (or its L2s) actually write to
+ * the MSR.
+ */
+ bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+ bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
- /* This shortcut is ok because we support only x2APIC MSRs so far. */
- if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
+ /* Nothing to do if the MSR bitmap is not in use. */
+ if (!cpu_has_vmx_msr_bitmap() ||
+ !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+ return false;
+
+ if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+ !pred_cmd && !spec_ctrl)
return false;
page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
if (is_error_page(page))
return false;
- msr_bitmap_l1 = (unsigned long *)kmap(page);
- memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+ msr_bitmap_l1 = (unsigned long *)kmap(page);
+ if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+ /*
+ * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
+ * just lets the processor take the value from the virtual-APIC page;
+ * take those 256 bits directly from the L1 bitmap.
+ */
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+ msr_bitmap_l0[word] = msr_bitmap_l1[word];
+ msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
+ }
+ } else {
+ for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+ unsigned word = msr / BITS_PER_LONG;
+ msr_bitmap_l0[word] = ~0;
+ msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
+ }
+ }
- if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
- if (nested_cpu_has_apic_reg_virt(vmcs12))
- for (msr = 0x800; msr <= 0x8ff; msr++)
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- msr, MSR_TYPE_R);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_TASKPRI),
+ MSR_TYPE_W);
+ if (nested_cpu_has_vid(vmcs12)) {
nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- APIC_BASE_MSR + (APIC_TASKPRI >> 4),
- MSR_TYPE_R | MSR_TYPE_W);
-
- if (nested_cpu_has_vid(vmcs12)) {
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- APIC_BASE_MSR + (APIC_EOI >> 4),
- MSR_TYPE_W);
- nested_vmx_disable_intercept_for_msr(
- msr_bitmap_l1, msr_bitmap_l0,
- APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
- MSR_TYPE_W);
- }
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_EOI),
+ MSR_TYPE_W);
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ X2APIC_MSR(APIC_SELF_IPI),
+ MSR_TYPE_W);
}
+
+ if (spec_ctrl)
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_SPEC_CTRL,
+ MSR_TYPE_R | MSR_TYPE_W);
+
+ if (pred_cmd)
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_PRED_CMD,
+ MSR_TYPE_W);
+
kunmap(page);
kvm_release_page_clean(page);
projects / linux-2.6-block.git / commitdiff