aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/virtual/kvm/api.txt116
-rw-r--r--MAINTAINERS11
-rw-r--r--Makefile2
-rw-r--r--arch/arm/include/asm/kvm_arm.h3
-rw-r--r--arch/arm/include/asm/kvm_host.h13
-rw-r--r--arch/arm/include/asm/kvm_mmu.h15
-rw-r--r--arch/arm/include/asm/stage2_pgtable.h54
-rw-r--r--arch/arm64/include/asm/cpufeature.h20
-rw-r--r--arch/arm64/include/asm/kvm_arm.h155
-rw-r--r--arch/arm64/include/asm/kvm_asm.h3
-rw-r--r--arch/arm64/include/asm/kvm_host.h18
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h10
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h42
-rw-r--r--arch/arm64/include/asm/ptrace.h3
-rw-r--r--arch/arm64/include/asm/stage2_pgtable-nopmd.h42
-rw-r--r--arch/arm64/include/asm/stage2_pgtable-nopud.h39
-rw-r--r--arch/arm64/include/asm/stage2_pgtable.h236
-rw-r--r--arch/arm64/kvm/guest.c6
-rw-r--r--arch/arm64/kvm/handle_exit.c7
-rw-r--r--arch/arm64/kvm/hyp/Makefile1
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S16
-rw-r--r--arch/arm64/kvm/hyp/s2-setup.c90
-rw-r--r--arch/arm64/kvm/hyp/switch.c4
-rw-r--r--arch/arm64/kvm/hyp/sysreg-sr.c19
-rw-r--r--arch/arm64/kvm/hyp/tlb.c4
-rw-r--r--arch/arm64/kvm/reset.c108
-rw-r--r--arch/x86/include/asm/fixmap.h10
-rw-r--r--arch/x86/include/asm/kvm_host.h70
-rw-r--r--arch/x86/include/asm/mem_encrypt.h7
-rw-r--r--arch/x86/include/asm/pgtable_64.h3
-rw-r--r--arch/x86/include/asm/virtext.h2
-rw-r--r--arch/x86/include/asm/vmx.h13
-rw-r--r--arch/x86/include/uapi/asm/kvm.h8
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.h17
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c27
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c53
-rw-r--r--arch/x86/kernel/head64.c20
-rw-r--r--arch/x86/kernel/head_64.S16
-rw-r--r--arch/x86/kernel/kvmclock.c52
-rw-r--r--arch/x86/kernel/paravirt.c4
-rw-r--r--arch/x86/kernel/vmlinux.lds.S19
-rw-r--r--arch/x86/kvm/hyperv.c280
-rw-r--r--arch/x86/kvm/hyperv.h4
-rw-r--r--arch/x86/kvm/lapic.c45
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/kvm/mmu.c393
-rw-r--r--arch/x86/kvm/mmu.h13
-rw-r--r--arch/x86/kvm/mmu_audit.c12
-rw-r--r--arch/x86/kvm/paging_tmpl.h15
-rw-r--r--arch/x86/kvm/svm.c64
-rw-r--r--arch/x86/kvm/trace.h42
-rw-r--r--arch/x86/kvm/vmx.c2281
-rw-r--r--arch/x86/kvm/vmx_shadow_fields.h5
-rw-r--r--arch/x86/kvm/x86.c257
-rw-r--r--arch/x86/kvm/x86.h2
-rw-r--r--arch/x86/mm/init.c4
-rw-r--r--arch/x86/mm/mem_encrypt.c24
-rw-r--r--arch/x86/mm/pgtable.c9
-rw-r--r--arch/x86/xen/mmu_pv.c8
-rw-r--r--arch/x86/xen/pmu.c2
-rw-r--r--block/bio.c2
-rw-r--r--block/blk-core.c4
-rw-r--r--block/genhd.c6
-rw-r--r--block/partition-generic.c6
-rw-r--r--drivers/firmware/efi/Kconfig9
-rw-r--r--drivers/mfd/omap-usb-host.c11
-rw-r--r--drivers/pinctrl/intel/pinctrl-cannonlake.c2
-rw-r--r--drivers/pinctrl/intel/pinctrl-intel.c111
-rw-r--r--drivers/xen/grant-table.c27
-rw-r--r--include/linux/genhd.h5
-rw-r--r--include/linux/irqchip/arm-gic-v3.h5
-rw-r--r--include/linux/mfd/da9063/pdata.h16
-rw-r--r--include/uapi/linux/kvm.h24
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h10
-rw-r--r--tools/include/uapi/linux/kvm.h6
-rw-r--r--tools/lib/bpf/Build2
-rw-r--r--tools/lib/bpf/libbpf.c20
-rw-r--r--tools/lib/bpf/str_error.c18
-rw-r--r--tools/lib/bpf/str_error.h6
-rw-r--r--tools/perf/Documentation/Makefile2
-rw-r--r--tools/testing/selftests/kvm/.gitignore14
-rw-r--r--tools/testing/selftests/kvm/Makefile39
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c374
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h55
-rw-r--r--tools/testing/selftests/kvm/include/evmcs.h1098
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h169
-rw-r--r--tools/testing/selftests/kvm/include/sparsebit.h6
-rw-r--r--tools/testing/selftests/kvm/include/test_util.h6
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h (renamed from tools/testing/selftests/kvm/include/x86.h)28
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/vmx.h (renamed from tools/testing/selftests/kvm/include/vmx.h)35
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c311
-rw-r--r--tools/testing/selftests/kvm/lib/assert.c2
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c564
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h33
-rw-r--r--tools/testing/selftests/kvm/lib/ucall.c144
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c (renamed from tools/testing/selftests/kvm/lib/x86.c)263
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c (renamed from tools/testing/selftests/kvm/lib/vmx.c)55
-rw-r--r--tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c (renamed from tools/testing/selftests/kvm/cr4_cpuid_sync_test.c)14
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c160
-rw-r--r--tools/testing/selftests/kvm/x86_64/platform_info_test.c (renamed from tools/testing/selftests/kvm/platform_info_test.c)14
-rw-r--r--tools/testing/selftests/kvm/x86_64/set_sregs_test.c (renamed from tools/testing/selftests/kvm/set_sregs_test.c)2
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c (renamed from tools/testing/selftests/kvm/state_test.c)47
-rw-r--r--tools/testing/selftests/kvm/x86_64/sync_regs_test.c (renamed from tools/testing/selftests/kvm/sync_regs_test.c)2
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c (renamed from tools/testing/selftests/kvm/vmx_tsc_adjust_test.c)24
-rw-r--r--virt/kvm/arm/arm.c26
-rw-r--r--virt/kvm/arm/mmu.c128
-rw-r--r--virt/kvm/arm/vgic/vgic-its.c36
-rw-r--r--virt/kvm/arm/vgic/vgic-kvm-device.c2
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio-v3.c2
-rw-r--r--virt/kvm/coalesced_mmio.c12
-rw-r--r--virt/kvm/kvm_main.c39
111 files changed, 6437 insertions, 2379 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index df98b6304769..cd209f7730af 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -123,6 +123,37 @@ memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
flag KVM_VM_MIPS_VZ.
+On arm64, the physical address size for a VM (IPA Size limit) is limited
+to 40bits by default. The limit can be configured if the host supports the
+extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
+KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type
+identifier, where IPA_Bits is the maximum width of any physical
+address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
+machine type identifier.
+
+e.g, to configure a guest to use 48bit physical address size :
+
+ vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48));
+
+The requested size (IPA_Bits) must be :
+ 0 - Implies default size, 40bits (for backward compatibility)
+
+ or
+
+ N - Implies N bits, where N is a positive integer such that,
+ 32 <= N <= Host_IPA_Limit
+
+Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and
+is dependent on the CPU capability and the kernel configuration. The limit can
+be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
+ioctl() at run-time.
+
+Please note that configuring the IPA size does not affect the capability
+exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
+size of the address translated by the stage2 level (guest physical to
+host physical address translations).
+
+
4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
@@ -850,7 +881,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ __u8 pending;
__u32 error_code;
} exception;
struct {
@@ -873,15 +904,23 @@ struct kvm_vcpu_events {
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
+ __u8 reserved[27];
+ __u8 exception_has_payload;
+ __u64 exception_payload;
};
-Only two fields are defined in the flags field:
+The following bits are defined in the flags field:
-- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+- KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
interrupt.shadow contains a valid state.
-- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
- smi contains a valid state.
+- KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
+ valid state.
+
+- KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
+ exception_has_payload, exception_payload, and exception.pending
+ fields contain a valid state. This bit will be set whenever
+ KVM_CAP_EXCEPTION_PAYLOAD is enabled.
ARM/ARM64:
@@ -961,6 +1000,11 @@ shall be written into the VCPU.
KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
+If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD
+can be set in the flags field to signal that the
+exception_has_payload, exception_payload, and exception.pending fields
+contain a valid state and shall be written into the VCPU.
+
ARM/ARM64:
Set the pending SError exception state for this VCPU. It is not possible to
@@ -3681,6 +3725,34 @@ Returns: 0 on success, -1 on error
This copies the vcpu's kvm_nested_state struct from userspace to the kernel. For
the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
+4.116 KVM_(UN)REGISTER_COALESCED_MMIO
+
+Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
+ KVM_CAP_COALESCED_PIO (for coalesced pio)
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_coalesced_mmio_zone
+Returns: 0 on success, < 0 on error
+
+Coalesced I/O is a performance optimization that defers hardware
+register write emulation so that userspace exits are avoided. It is
+typically used to reduce the overhead of emulating frequently accessed
+hardware registers.
+
+When a hardware register is configured for coalesced I/O, write accesses
+do not exit to userspace and their value is recorded in a ring buffer
+that is shared between kernel and userspace.
+
+Coalesced I/O is used if one or more write accesses to a hardware
+register can be deferred until a read or a write to another hardware
+register on the same device. This last access will cause a vmexit and
+userspace will process accesses from the ring buffer before emulating
+it. That will avoid exiting to userspace on repeated writes.
+
+Coalesced pio is based on coalesced mmio. There is little difference
+between coalesced mmio and pio except that coalesced pio records accesses
+to I/O ports.
+
5. The kvm_run structure
------------------------
@@ -4527,7 +4599,7 @@ hpage module parameter is not set to 1, -EINVAL is returned.
While it is generally possible to create a huge page backed VM without
this capability, the VM will not be able to run.
-7.14 KVM_CAP_MSR_PLATFORM_INFO
+7.15 KVM_CAP_MSR_PLATFORM_INFO
Architectures: x86
Parameters: args[0] whether feature should be enabled or not
@@ -4550,6 +4622,31 @@ state). Enabling this capability on a VM depends on the CPU having
the necessary functionality and on the facility being enabled with a
kvm-hv module parameter.
+7.17 KVM_CAP_EXCEPTION_PAYLOAD
+
+Architectures: x86
+Parameters: args[0] whether feature should be enabled or not
+
+With this capability enabled, CR2 will not be modified prior to the
+emulated VM-exit when L1 intercepts a #PF exception that occurs in
+L2. Similarly, for kvm-intel only, DR6 will not be modified prior to
+the emulated VM-exit when L1 intercepts a #DB exception that occurs in
+L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or
+#DB) exception for L2, exception.has_payload will be set and the
+faulting address (or the new DR6 bits*) will be reported in the
+exception_payload field. Similarly, when userspace injects a #PF (or
+#DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set
+exception.has_payload and to put the faulting address (or the new DR6
+bits*) in the exception_payload field.
+
+This capability also enables exception.pending in struct
+kvm_vcpu_events, which allows userspace to distinguish between pending
+and injected exceptions.
+
+
+* For the new DR6 bits, note that bit 16 is set iff the #DB exception
+ will clear DR6.RTM.
+
8. Other capabilities.
----------------------
@@ -4791,3 +4888,10 @@ CPU when the exception is taken. If this virtual SError is taken to EL1 using
AArch64, this value will be reported in the ISS field of ESR_ELx.
See KVM_CAP_VCPU_EVENTS for more details.
+8.20 KVM_CAP_HYPERV_SEND_IPI
+
+Architectures: x86
+
+This capability indicates that KVM supports paravirtualized Hyper-V IPI send
+hypercalls:
+HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
diff --git a/MAINTAINERS b/MAINTAINERS
index 1610fb26bdac..86e019c7b0fa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12260,6 +12260,7 @@ F: Documentation/networking/rds.txt
RDT - RESOURCE ALLOCATION
M: Fenghua Yu <[email protected]>
+M: Reinette Chatre <[email protected]>
S: Supported
F: arch/x86/kernel/cpu/intel_rdt*
@@ -15924,6 +15925,7 @@ F: net/x25/
X86 ARCHITECTURE (32-BIT AND 64-BIT)
M: Thomas Gleixner <[email protected]>
M: Ingo Molnar <[email protected]>
+M: Borislav Petkov <[email protected]>
R: "H. Peter Anvin" <[email protected]>
@@ -15952,6 +15954,15 @@ M: Borislav Petkov <[email protected]>
S: Maintained
F: arch/x86/kernel/cpu/microcode/*
+X86 MM
+M: Dave Hansen <[email protected]>
+M: Andy Lutomirski <[email protected]>
+M: Peter Zijlstra <[email protected]>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm
+S: Maintained
+F: arch/x86/mm/
+
X86 PLATFORM DRIVERS
M: Darren Hart <[email protected]>
M: Andy Shevchenko <[email protected]>
diff --git a/Makefile b/Makefile
index f03a1e062503..0c90c4354979 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 4
PATCHLEVEL = 19
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
NAME = Merciless Moray
# *DOCUMENTATION*
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 3ab8b3781bfe..c3f1f9b304b7 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -133,8 +133,7 @@
* space.
*/
#define KVM_PHYS_SHIFT (40)
-#define KVM_PHYS_SIZE (_AC(1, ULL) << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK (KVM_PHYS_SIZE - _AC(1, ULL))
+
#define PTRS_PER_S2_PGD (_AC(1, ULL) << (KVM_PHYS_SHIFT - 30))
/* Virtualization Translation Control Register (VTCR) bits */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 3ad482d2f1eb..5ca5d9af0c26 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -273,7 +273,7 @@ static inline void __cpu_init_stage2(void)
kvm_call_hyp(__init_stage2_translation);
}
-static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
+static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
return 0;
}
@@ -354,4 +354,15 @@ static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {}
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);
+static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
+{
+ /*
+ * On 32bit ARM, VMs get a static 40bit IPA stage2 setup,
+ * so any non-zero value used as type is illegal.
+ */
+ if (type)
+ return -EINVAL;
+ return 0;
+}
+
#endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 265ea9cf7df7..5ad1a54f98dc 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -35,16 +35,12 @@
addr; \
})
-/*
- * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
- */
-#define KVM_MMU_CACHE_MIN_PAGES 2
-
#ifndef __ASSEMBLY__
#include <linux/highmem.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
+#include <asm/kvm_arm.h>
#include <asm/kvm_hyp.h>
#include <asm/pgalloc.h>
#include <asm/stage2_pgtable.h>
@@ -52,6 +48,13 @@
/* Ensure compatibility with arm64 */
#define VA_BITS 32
+#define kvm_phys_shift(kvm) KVM_PHYS_SHIFT
+#define kvm_phys_size(kvm) (1ULL << kvm_phys_shift(kvm))
+#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - 1ULL)
+#define kvm_vttbr_baddr_mask(kvm) VTTBR_BADDR_MASK
+
+#define stage2_pgd_size(kvm) (PTRS_PER_S2_PGD * sizeof(pgd_t))
+
int create_hyp_mappings(void *from, void *to, pgprot_t prot);
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
void __iomem **kaddr,
@@ -355,6 +358,8 @@ static inline int hyp_map_aux_data(void)
#define kvm_phys_to_vttbr(addr) (addr)
+static inline void kvm_set_ipa_limit(void) {}
+
#endif /* !__ASSEMBLY__ */
#endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
index 460d616bb2d6..f6a7ea805232 100644
--- a/arch/arm/include/asm/stage2_pgtable.h
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -19,43 +19,53 @@
#ifndef __ARM_S2_PGTABLE_H_
#define __ARM_S2_PGTABLE_H_
-#define stage2_pgd_none(pgd) pgd_none(pgd)
-#define stage2_pgd_clear(pgd) pgd_clear(pgd)
-#define stage2_pgd_present(pgd) pgd_present(pgd)
-#define stage2_pgd_populate(pgd, pud) pgd_populate(NULL, pgd, pud)
-#define stage2_pud_offset(pgd, address) pud_offset(pgd, address)
-#define stage2_pud_free(pud) pud_free(NULL, pud)
-
-#define stage2_pud_none(pud) pud_none(pud)
-#define stage2_pud_clear(pud) pud_clear(pud)
-#define stage2_pud_present(pud) pud_present(pud)
-#define stage2_pud_populate(pud, pmd) pud_populate(NULL, pud, pmd)
-#define stage2_pmd_offset(pud, address) pmd_offset(pud, address)
-#define stage2_pmd_free(pmd) pmd_free(NULL, pmd)
-
-#define stage2_pud_huge(pud) pud_huge(pud)
+/*
+ * kvm_mmu_cache_min_pages() is the number of pages required
+ * to install a stage-2 translation. We pre-allocate the entry
+ * level table at VM creation. Since we have a 3 level page-table,
+ * we need only two pages to add a new mapping.
+ */
+#define kvm_mmu_cache_min_pages(kvm) 2
+
+#define stage2_pgd_none(kvm, pgd) pgd_none(pgd)
+#define stage2_pgd_clear(kvm, pgd) pgd_clear(pgd)
+#define stage2_pgd_present(kvm, pgd) pgd_present(pgd)
+#define stage2_pgd_populate(kvm, pgd, pud) pgd_populate(NULL, pgd, pud)
+#define stage2_pud_offset(kvm, pgd, address) pud_offset(pgd, address)
+#define stage2_pud_free(kvm, pud) pud_free(NULL, pud)
+
+#define stage2_pud_none(kvm, pud) pud_none(pud)
+#define stage2_pud_clear(kvm, pud) pud_clear(pud)
+#define stage2_pud_present(kvm, pud) pud_present(pud)
+#define stage2_pud_populate(kvm, pud, pmd) pud_populate(NULL, pud, pmd)
+#define stage2_pmd_offset(kvm, pud, address) pmd_offset(pud, address)
+#define stage2_pmd_free(kvm, pmd) pmd_free(NULL, pmd)
+
+#define stage2_pud_huge(kvm, pud) pud_huge(pud)
/* Open coded p*d_addr_end that can deal with 64bit addresses */
-static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline phys_addr_t
+stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
{
phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK;
return (boundary - 1 < end - 1) ? boundary : end;
}
-#define stage2_pud_addr_end(addr, end) (end)
+#define stage2_pud_addr_end(kvm, addr, end) (end)
-static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline phys_addr_t
+stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
{
phys_addr_t boundary = (addr + PMD_SIZE) & PMD_MASK;
return (boundary - 1 < end - 1) ? boundary : end;
}
-#define stage2_pgd_index(addr) pgd_index(addr)
+#define stage2_pgd_index(kvm, addr) pgd_index(addr)
-#define stage2_pte_table_empty(ptep) kvm_page_empty(ptep)
-#define stage2_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
-#define stage2_pud_table_empty(pudp) false
+#define stage2_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)
+#define stage2_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp)
+#define stage2_pud_table_empty(kvm, pudp) false
#endif /* __ARM_S2_PGTABLE_H_ */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 1717ba1db35d..072cc1c970c2 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -530,6 +530,26 @@ void arm64_set_ssbd_mitigation(bool state);
static inline void arm64_set_ssbd_mitigation(bool state) {}
#endif
+static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
+{
+ switch (parange) {
+ case 0: return 32;
+ case 1: return 36;
+ case 2: return 40;
+ case 3: return 42;
+ case 4: return 44;
+ case 5: return 48;
+ case 6: return 52;
+ /*
+ * A future PE could use a value unknown to the kernel.
+ * However, by the "D10.1.4 Principles of the ID scheme
+ * for fields in ID registers", ARM DDI 0487C.a, any new
+ * value is guaranteed to be higher than what we know already.
+ * As a safe limit, we return the limit supported by the kernel.
+ */
+ default: return CONFIG_ARM64_PA_BITS;
+ }
+}
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index aa45df752a16..6e324d1f1231 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -107,6 +107,7 @@
#define VTCR_EL2_RES1 (1 << 31)
#define VTCR_EL2_HD (1 << 22)
#define VTCR_EL2_HA (1 << 21)
+#define VTCR_EL2_PS_SHIFT TCR_EL2_PS_SHIFT
#define VTCR_EL2_PS_MASK TCR_EL2_PS_MASK
#define VTCR_EL2_TG0_MASK TCR_TG0_MASK
#define VTCR_EL2_TG0_4K TCR_TG0_4K
@@ -120,62 +121,149 @@
#define VTCR_EL2_IRGN0_WBWA TCR_IRGN0_WBWA
#define VTCR_EL2_SL0_SHIFT 6
#define VTCR_EL2_SL0_MASK (3 << VTCR_EL2_SL0_SHIFT)
-#define VTCR_EL2_SL0_LVL1 (1 << VTCR_EL2_SL0_SHIFT)
#define VTCR_EL2_T0SZ_MASK 0x3f
-#define VTCR_EL2_T0SZ_40B 24
#define VTCR_EL2_VS_SHIFT 19
#define VTCR_EL2_VS_8BIT (0 << VTCR_EL2_VS_SHIFT)
#define VTCR_EL2_VS_16BIT (1 << VTCR_EL2_VS_SHIFT)
+#define VTCR_EL2_T0SZ(x) TCR_T0SZ(x)
+
/*
* We configure the Stage-2 page tables to always restrict the IPA space to be
* 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are
* not known to exist and will break with this configuration.
*
- * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time
- * (see hyp-init.S).
+ * The VTCR_EL2 is configured per VM and is initialised in kvm_arm_setup_stage2().
*
* Note that when using 4K pages, we concatenate two first level page tables
* together. With 16K pages, we concatenate 16 first level page tables.
*
- * The magic numbers used for VTTBR_X in this patch can be found in Tables
- * D4-23 and D4-25 in ARM DDI 0487A.b.
*/
-#define VTCR_EL2_T0SZ_IPA VTCR_EL2_T0SZ_40B
#define VTCR_EL2_COMMON_BITS (VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
VTCR_EL2_IRGN0_WBWA | VTCR_EL2_RES1)
-#ifdef CONFIG_ARM64_64K_PAGES
/*
- * Stage2 translation configuration:
- * 64kB pages (TG0 = 1)
- * 2 level page tables (SL = 1)
+ * VTCR_EL2:SL0 indicates the entry level for Stage2 translation.
+ * Interestingly, it depends on the page size.
+ * See D.10.2.121, VTCR_EL2, in ARM DDI 0487C.a
+ *
+ * -----------------------------------------
+ * | Entry level | 4K | 16K/64K |
+ * ------------------------------------------
+ * | Level: 0 | 2 | - |
+ * ------------------------------------------
+ * | Level: 1 | 1 | 2 |
+ * ------------------------------------------
+ * | Level: 2 | 0 | 1 |
+ * ------------------------------------------
+ * | Level: 3 | - | 0 |
+ * ------------------------------------------
+ *
+ * The table roughly translates to :
+ *
+ * SL0(PAGE_SIZE, Entry_level) = TGRAN_SL0_BASE - Entry_Level
+ *
+ * Where TGRAN_SL0_BASE is a magic number depending on the page size:
+ * TGRAN_SL0_BASE(4K) = 2
+ * TGRAN_SL0_BASE(16K) = 3
+ * TGRAN_SL0_BASE(64K) = 3
+ * provided we take care of ruling out the unsupported cases and
+ * Entry_Level = 4 - Number_of_levels.
+ *
*/
-#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_64K | VTCR_EL2_SL0_LVL1)
-#define VTTBR_X_TGRAN_MAGIC 38
+#ifdef CONFIG_ARM64_64K_PAGES
+
+#define VTCR_EL2_TGRAN VTCR_EL2_TG0_64K
+#define VTCR_EL2_TGRAN_SL0_BASE 3UL
+
#elif defined(CONFIG_ARM64_16K_PAGES)
-/*
- * Stage2 translation configuration:
- * 16kB pages (TG0 = 2)
- * 2 level page tables (SL = 1)
- */
-#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_16K | VTCR_EL2_SL0_LVL1)
-#define VTTBR_X_TGRAN_MAGIC 42
+
+#define VTCR_EL2_TGRAN VTCR_EL2_TG0_16K
+#define VTCR_EL2_TGRAN_SL0_BASE 3UL
+
#else /* 4K */
-/*
- * Stage2 translation configuration:
- * 4kB pages (TG0 = 0)
- * 3 level page tables (SL = 1)
- */
-#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SL0_LVL1)
-#define VTTBR_X_TGRAN_MAGIC 37
+
+#define VTCR_EL2_TGRAN VTCR_EL2_TG0_4K
+#define VTCR_EL2_TGRAN_SL0_BASE 2UL
+
#endif
-#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
-#define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
+#define VTCR_EL2_LVLS_TO_SL0(levels) \
+ ((VTCR_EL2_TGRAN_SL0_BASE - (4 - (levels))) << VTCR_EL2_SL0_SHIFT)
+#define VTCR_EL2_SL0_TO_LVLS(sl0) \
+ ((sl0) + 4 - VTCR_EL2_TGRAN_SL0_BASE)
+#define VTCR_EL2_LVLS(vtcr) \
+ VTCR_EL2_SL0_TO_LVLS(((vtcr) & VTCR_EL2_SL0_MASK) >> VTCR_EL2_SL0_SHIFT)
+
+#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN)
+#define VTCR_EL2_IPA(vtcr) (64 - ((vtcr) & VTCR_EL2_T0SZ_MASK))
+
+/*
+ * ARM VMSAv8-64 defines an algorithm for finding the translation table
+ * descriptors in section D4.2.8 in ARM DDI 0487C.a.
+ *
+ * The algorithm defines the expectations on the translation table
+ * addresses for each level, based on PAGE_SIZE, entry level
+ * and the translation table size (T0SZ). The variable "x" in the
+ * algorithm determines the alignment of a table base address at a given
+ * level and thus determines the alignment of VTTBR:BADDR for stage2
+ * page table entry level.
+ * Since the number of bits resolved at the entry level could vary
+ * depending on the T0SZ, the value of "x" is defined based on a
+ * Magic constant for a given PAGE_SIZE and Entry Level. The
+ * intermediate levels must be always aligned to the PAGE_SIZE (i.e,
+ * x = PAGE_SHIFT).
+ *
+ * The value of "x" for entry level is calculated as :
+ * x = Magic_N - T0SZ
+ *
+ * where Magic_N is an integer depending on the page size and the entry
+ * level of the page table as below:
+ *
+ * --------------------------------------------
+ * | Entry level | 4K 16K 64K |
+ * --------------------------------------------
+ * | Level: 0 (4 levels) | 28 | - | - |
+ * --------------------------------------------
+ * | Level: 1 (3 levels) | 37 | 31 | 25 |
+ * --------------------------------------------
+ * | Level: 2 (2 levels) | 46 | 42 | 38 |
+ * --------------------------------------------
+ * | Level: 3 (1 level) | - | 53 | 51 |
+ * --------------------------------------------
+ *
+ * We have a magic formula for the Magic_N below:
+ *
+ * Magic_N(PAGE_SIZE, Level) = 64 - ((PAGE_SHIFT - 3) * Number_of_levels)
+ *
+ * where Number_of_levels = (4 - Level). We are only interested in the
+ * value for Entry_Level for the stage2 page table.
+ *
+ * So, given that T0SZ = (64 - IPA_SHIFT), we can compute 'x' as follows:
+ *
+ * x = (64 - ((PAGE_SHIFT - 3) * Number_of_levels)) - (64 - IPA_SHIFT)
+ * = IPA_SHIFT - ((PAGE_SHIFT - 3) * Number of levels)
+ *
+ * Here is one way to explain the Magic Formula:
+ *
+ * x = log2(Size_of_Entry_Level_Table)
+ *
+ * Since, we can resolve (PAGE_SHIFT - 3) bits at each level, and another
+ * PAGE_SHIFT bits in the PTE, we have :
+ *
+ * Bits_Entry_level = IPA_SHIFT - ((PAGE_SHIFT - 3) * (n - 1) + PAGE_SHIFT)
+ * = IPA_SHIFT - (PAGE_SHIFT - 3) * n - 3
+ * where n = number of levels, and since each pointer is 8bytes, we have:
+ *
+ * x = Bits_Entry_Level + 3
+ * = IPA_SHIFT - (PAGE_SHIFT - 3) * n
+ *
+ * The only constraint here is that, we have to find the number of page table
+ * levels for a given IPA size (which we do, see stage2_pt_levels())
+ */
+#define ARM64_VTTBR_X(ipa, levels) ((ipa) - ((levels) * (PAGE_SHIFT - 3)))
-#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
#define VTTBR_VMID_SHIFT (UL(48))
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
@@ -223,6 +311,13 @@
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
+/*
+ * We have
+ * PAR [PA_Shift - 1 : 12] = PA [PA_Shift - 1 : 12]
+ * HPFAR [PA_Shift - 9 : 4] = FIPA [PA_Shift - 1 : 12]
+ */
+#define PAR_TO_HPFAR(par) \
+ (((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
#define kvm_arm_exception_type \
{0, "IRQ" }, \
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 102b5a5c47b6..aea01a09eb94 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -30,6 +30,7 @@
#define ARM_EXCEPTION_IRQ 0
#define ARM_EXCEPTION_EL1_SERROR 1
#define ARM_EXCEPTION_TRAP 2
+#define ARM_EXCEPTION_IL 3
/* The hyp-stub will return this for any kvm_call_hyp() call */
#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR
@@ -72,8 +73,6 @@ extern void __vgic_v3_init_lrs(void);
extern u32 __kvm_get_mdcr_el2(void);
-extern u32 __init_stage2_translation(void);
-
/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
#define __hyp_this_cpu_ptr(sym) \
({ \
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3d6d7336f871..f84052f306af 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -53,7 +53,7 @@ DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
-int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext);
+int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
struct kvm_arch {
@@ -61,11 +61,13 @@ struct kvm_arch {
u64 vmid_gen;
u32 vmid;
- /* 1-level 2nd stage table, protected by kvm->mmu_lock */
+ /* stage2 entry level table */
pgd_t *pgd;
/* VTTBR value associated with above pgd and vmid */
u64 vttbr;
+ /* VTCR_EL2 value for this VM */
+ u64 vtcr;
/* The last vcpu id that ran on each physical CPU */
int __percpu *last_vcpu_ran;
@@ -440,13 +442,7 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
-static inline void __cpu_init_stage2(void)
-{
- u32 parange = kvm_call_hyp(__init_stage2_translation);
-
- WARN_ONCE(parange < 40,
- "PARange is %d bits, unsupported configuration!", parange);
-}
+static inline void __cpu_init_stage2(void) {}
/* Guest/host FPSIMD coordination helpers */
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
@@ -509,8 +505,12 @@ static inline int kvm_arm_have_ssbd(void)
void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+void kvm_set_ipa_limit(void);
+
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);
+int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 384c34397619..23aca66767f9 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -155,5 +155,15 @@ void deactivate_traps_vhe_put(void);
u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
void __noreturn __hyp_do_panic(unsigned long, ...);
+/*
+ * Must be called from hyp code running at EL2 with an updated VTTBR
+ * and interrupts disabled.
+ */
+static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm)
+{
+ write_sysreg(kvm->arch.vtcr, vtcr_el2);
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+}
+
#endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index d6fff7de5539..77b1af9e64db 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -141,8 +141,16 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
* We currently only support a 40bit IPA.
*/
#define KVM_PHYS_SHIFT (40)
-#define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL)
+
+#define kvm_phys_shift(kvm) VTCR_EL2_IPA(kvm->arch.vtcr)
+#define kvm_phys_size(kvm) (_AC(1, ULL) << kvm_phys_shift(kvm))
+#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - _AC(1, ULL))
+
+static inline bool kvm_page_empty(void *ptr)
+{
+ struct page *ptr_page = virt_to_page(ptr);
+ return page_count(ptr_page) == 1;
+}
#include <asm/stage2_pgtable.h>
@@ -238,12 +246,6 @@ static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
}
-static inline bool kvm_page_empty(void *ptr)
-{
- struct page *ptr_page = virt_to_page(ptr);
- return page_count(ptr_page) == 1;
-}
-
#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
#ifdef __PAGETABLE_PMD_FOLDED
@@ -517,5 +519,29 @@ static inline int hyp_map_aux_data(void)
#define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
+/*
+ * Get the magic number 'x' for VTTBR:BADDR of this KVM instance.
+ * With v8.2 LVA extensions, 'x' should be a minimum of 6 with
+ * 52bit IPS.
+ */
+static inline int arm64_vttbr_x(u32 ipa_shift, u32 levels)
+{
+ int x = ARM64_VTTBR_X(ipa_shift, levels);
+
+ return (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && x < 6) ? 6 : x;
+}
+
+static inline u64 vttbr_baddr_mask(u32 ipa_shift, u32 levels)
+{
+ unsigned int x = arm64_vttbr_x(ipa_shift, levels);
+
+ return GENMASK_ULL(PHYS_MASK_SHIFT - 1, x);
+}
+
+static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
+{
+ return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 177b851ca6d9..ff35ac1258eb 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -25,6 +25,9 @@
#define CurrentEL_EL1 (1 << 2)
#define CurrentEL_EL2 (2 << 2)
+/* Additional SPSR bits not exposed in the UABI */
+#define PSR_IL_BIT (1 << 20)
+
/* AArch32-specific ptrace requests */
#define COMPAT_PTRACE_GETREGS 12
#define COMPAT_PTRACE_SETREGS 13
diff --git a/arch/arm64/include/asm/stage2_pgtable-nopmd.h b/arch/arm64/include/asm/stage2_pgtable-nopmd.h
deleted file mode 100644
index 2656a0fd05a6..000000000000
--- a/arch/arm64/include/asm/stage2_pgtable-nopmd.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Copyright (C) 2016 - ARM Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_S2_PGTABLE_NOPMD_H_
-#define __ARM64_S2_PGTABLE_NOPMD_H_
-
-#include <asm/stage2_pgtable-nopud.h>
-
-#define __S2_PGTABLE_PMD_FOLDED
-
-#define S2_PMD_SHIFT S2_PUD_SHIFT
-#define S2_PTRS_PER_PMD 1
-#define S2_PMD_SIZE (1UL << S2_PMD_SHIFT)
-#define S2_PMD_MASK (~(S2_PMD_SIZE-1))
-
-#define stage2_pud_none(pud) (0)
-#define stage2_pud_present(pud) (1)
-#define stage2_pud_clear(pud) do { } while (0)
-#define stage2_pud_populate(pud, pmd) do { } while (0)
-#define stage2_pmd_offset(pud, address) ((pmd_t *)(pud))
-
-#define stage2_pmd_free(pmd) do { } while (0)
-
-#define stage2_pmd_addr_end(addr, end) (end)
-
-#define stage2_pud_huge(pud) (0)
-#define stage2_pmd_table_empty(pmdp) (0)
-
-#endif
diff --git a/arch/arm64/include/asm/stage2_pgtable-nopud.h b/arch/arm64/include/asm/stage2_pgtable-nopud.h
deleted file mode 100644
index 5ee87b54ebf3..000000000000
--- a/arch/arm64/include/asm/stage2_pgtable-nopud.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Copyright (C) 2016 - ARM Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_S2_PGTABLE_NOPUD_H_
-#define __ARM64_S2_PGTABLE_NOPUD_H_
-
-#define __S2_PGTABLE_PUD_FOLDED
-
-#define S2_PUD_SHIFT S2_PGDIR_SHIFT
-#define S2_PTRS_PER_PUD 1
-#define S2_PUD_SIZE (_AC(1, UL) << S2_PUD_SHIFT)
-#define S2_PUD_MASK (~(S2_PUD_SIZE-1))
-
-#define stage2_pgd_none(pgd) (0)
-#define stage2_pgd_present(pgd) (1)
-#define stage2_pgd_clear(pgd) do { } while (0)
-#define stage2_pgd_populate(pgd, pud) do { } while (0)
-
-#define stage2_pud_offset(pgd, address) ((pud_t *)(pgd))
-
-#define stage2_pud_free(x) do { } while (0)
-
-#define stage2_pud_addr_end(addr, end) (end)
-#define stage2_pud_table_empty(pmdp) (0)
-
-#endif
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 8b68099348e5..d352f6df8d2c 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -19,9 +19,17 @@
#ifndef __ARM64_S2_PGTABLE_H_
#define __ARM64_S2_PGTABLE_H_
+#include <linux/hugetlb.h>
#include <asm/pgtable.h>
/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map
+ * and depends on the number of levels in the page table. Compute the
+ * PGDIR_SHIFT for a given number of levels.
+ */
+#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
+
+/*
* The hardware supports concatenation of up to 16 tables at stage2 entry level
* and we use the feature whenever possible.
*
@@ -29,112 +37,208 @@
* On arm64, the smallest PAGE_SIZE supported is 4k, which means
* (PAGE_SHIFT - 3) > 4 holds for all page sizes.
* This implies, the total number of page table levels at stage2 expected
- * by the hardware is actually the number of levels required for (KVM_PHYS_SHIFT - 4)
+ * by the hardware is actually the number of levels required for (IPA_SHIFT - 4)
* in normal translations(e.g, stage1), since we cannot have another level in
- * the range (KVM_PHYS_SHIFT, KVM_PHYS_SHIFT - 4).
+ * the range (IPA_SHIFT, IPA_SHIFT - 4).
*/
-#define STAGE2_PGTABLE_LEVELS ARM64_HW_PGTABLE_LEVELS(KVM_PHYS_SHIFT - 4)
+#define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
+#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr)
-/*
- * With all the supported VA_BITs and 40bit guest IPA, the following condition
- * is always true:
- *
- * STAGE2_PGTABLE_LEVELS <= CONFIG_PGTABLE_LEVELS
- *
- * We base our stage-2 page table walker helpers on this assumption and
- * fall back to using the host version of the helper wherever possible.
- * i.e, if a particular level is not folded (e.g, PUD) at stage2, we fall back
- * to using the host version, since it is guaranteed it is not folded at host.
- *
- * If the condition breaks in the future, we can rearrange the host level
- * definitions and reuse them for stage2. Till then...
- */
-#if STAGE2_PGTABLE_LEVELS > CONFIG_PGTABLE_LEVELS
-#error "Unsupported combination of guest IPA and host VA_BITS."
-#endif
-
-/* S2_PGDIR_SHIFT is the size mapped by top-level stage2 entry */
-#define S2_PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - STAGE2_PGTABLE_LEVELS)
-#define S2_PGDIR_SIZE (_AC(1, UL) << S2_PGDIR_SHIFT)
-#define S2_PGDIR_MASK (~(S2_PGDIR_SIZE - 1))
+/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */
+#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm))
+#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm))
+#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1)
/*
* The number of PTRS across all concatenated stage2 tables given by the
* number of bits resolved at the initial level.
+ * If we force more levels than necessary, we may have (stage2_pgdir_shift > IPA),
+ * in which case, stage2_pgd_ptrs will have one entry.
*/
-#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - S2_PGDIR_SHIFT))
+#define pgd_ptrs_shift(ipa, pgdir_shift) \
+ ((ipa) > (pgdir_shift) ? ((ipa) - (pgdir_shift)) : 0)
+#define __s2_pgd_ptrs(ipa, lvls) \
+ (1 << (pgd_ptrs_shift((ipa), pt_levels_pgdir_shift(lvls))))
+#define __s2_pgd_size(ipa, lvls) (__s2_pgd_ptrs((ipa), (lvls)) * sizeof(pgd_t))
+
+#define stage2_pgd_ptrs(kvm) __s2_pgd_ptrs(kvm_phys_shift(kvm), kvm_stage2_levels(kvm))
+#define stage2_pgd_size(kvm) __s2_pgd_size(kvm_phys_shift(kvm), kvm_stage2_levels(kvm))
/*
- * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
- * levels in addition to the PGD.
+ * kvm_mmmu_cache_min_pages() is the number of pages required to install
+ * a stage-2 translation. We pre-allocate the entry level page table at
+ * the VM creation.
*/
-#define KVM_MMU_CACHE_MIN_PAGES (STAGE2_PGTABLE_LEVELS - 1)
+#define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1)
-
-#if STAGE2_PGTABLE_LEVELS > 3
+/* Stage2 PUD definitions when the level is present */
+static inline bool kvm_stage2_has_pud(struct kvm *kvm)
+{
+ return (CONFIG_PGTABLE_LEVELS > 3) && (kvm_stage2_levels(kvm) > 3);
+}
#define S2_PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
-#define S2_PUD_SIZE (_AC(1, UL) << S2_PUD_SHIFT)
+#define S2_PUD_SIZE (1UL << S2_PUD_SHIFT)
#define S2_PUD_MASK (~(S2_PUD_SIZE - 1))
-#define stage2_pgd_none(pgd) pgd_none(pgd)
-#define stage2_pgd_clear(pgd) pgd_clear(pgd)
-#define stage2_pgd_present(pgd) pgd_present(pgd)
-#define stage2_pgd_populate(pgd, pud) pgd_populate(NULL, pgd, pud)
-#define stage2_pud_offset(pgd, address) pud_offset(pgd, address)
-#define stage2_pud_free(pud) pud_free(NULL, pud)
+static inline bool stage2_pgd_none(struct kvm *kvm, pgd_t pgd)
+{
+ if (kvm_stage2_has_pud(kvm))
+ return pgd_none(pgd);
+ else
+ return 0;
+}
-#define stage2_pud_table_empty(pudp) kvm_page_empty(pudp)
+static inline void stage2_pgd_clear(struct kvm *kvm, pgd_t *pgdp)
+{
+ if (kvm_stage2_has_pud(kvm))
+ pgd_clear(pgdp);
+}
-static inline phys_addr_t stage2_pud_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline bool stage2_pgd_present(struct kvm *kvm, pgd_t pgd)
{
- phys_addr_t boundary = (addr + S2_PUD_SIZE) & S2_PUD_MASK;
+ if (kvm_stage2_has_pud(kvm))
+ return pgd_present(pgd);
+ else
+ return 1;
+}
- return (boundary - 1 < end - 1) ? boundary : end;
+static inline void stage2_pgd_populate(struct kvm *kvm, pgd_t *pgd, pud_t *pud)
+{
+ if (kvm_stage2_has_pud(kvm))
+ pgd_populate(NULL, pgd, pud);
+}
+
+static inline pud_t *stage2_pud_offset(struct kvm *kvm,
+ pgd_t *pgd, unsigned long address)
+{
+ if (kvm_stage2_has_pud(kvm))
+ return pud_offset(pgd, address);
+ else
+ return (pud_t *)pgd;
}
-#endif /* STAGE2_PGTABLE_LEVELS > 3 */
+static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)
+{
+ if (kvm_stage2_has_pud(kvm))
+ pud_free(NULL, pud);
+}
+static inline bool stage2_pud_table_empty(struct kvm *kvm, pud_t *pudp)
+{
+ if (kvm_stage2_has_pud(kvm))
+ return kvm_page_empty(pudp);
+ else
+ return false;
+}
-#if STAGE2_PGTABLE_LEVELS > 2
+static inline phys_addr_t
+stage2_pud_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+{
+ if (kvm_stage2_has_pud(kvm)) {
+ phys_addr_t boundary = (addr + S2_PUD_SIZE) & S2_PUD_MASK;
+
+ return (boundary - 1 < end - 1) ? boundary : end;
+ } else {
+ return end;
+ }
+}
+
+/* Stage2 PMD definitions when the level is present */
+static inline bool kvm_stage2_has_pmd(struct kvm *kvm)
+{
+ return (CONFIG_PGTABLE_LEVELS > 2) && (kvm_stage2_levels(kvm) > 2);
+}
#define S2_PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
-#define S2_PMD_SIZE (_AC(1, UL) << S2_PMD_SHIFT)
+#define S2_PMD_SIZE (1UL << S2_PMD_SHIFT)
#define S2_PMD_MASK (~(S2_PMD_SIZE - 1))
-#define stage2_pud_none(pud) pud_none(pud)
-#define stage2_pud_clear(pud) pud_clear(pud)
-#define stage2_pud_present(pud) pud_present(pud)
-#define stage2_pud_populate(pud, pmd) pud_populate(NULL, pud, pmd)
-#define stage2_pmd_offset(pud, address) pmd_offset(pud, address)
-#define stage2_pmd_free(pmd) pmd_free(NULL, pmd)
+static inline bool stage2_pud_none(struct kvm *kvm, pud_t pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pud_none(pud);
+ else
+ return 0;
+}
+
+static inline void stage2_pud_clear(struct kvm *kvm, pud_t *pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ pud_clear(pud);
+}
-#define stage2_pud_huge(pud) pud_huge(pud)
-#define stage2_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+static inline bool stage2_pud_present(struct kvm *kvm, pud_t pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pud_present(pud);
+ else
+ return 1;
+}
-static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline void stage2_pud_populate(struct kvm *kvm, pud_t *pud, pmd_t *pmd)
{
- phys_addr_t boundary = (addr + S2_PMD_SIZE) & S2_PMD_MASK;
+ if (kvm_stage2_has_pmd(kvm))
+ pud_populate(NULL, pud, pmd);
+}
- return (boundary - 1 < end - 1) ? boundary : end;
+static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
+ pud_t *pud, unsigned long address)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pmd_offset(pud, address);
+ else
+ return (pmd_t *)pud;
}
-#endif /* STAGE2_PGTABLE_LEVELS > 2 */
+static inline void stage2_pmd_free(struct kvm *kvm, pmd_t *pmd)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ pmd_free(NULL, pmd);
+}
+
+static inline bool stage2_pud_huge(struct kvm *kvm, pud_t pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pud_huge(pud);
+ else
+ return 0;
+}
+
+static inline bool stage2_pmd_table_empty(struct kvm *kvm, pmd_t *pmdp)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return kvm_page_empty(pmdp);
+ else
+ return 0;
+}
-#define stage2_pte_table_empty(ptep) kvm_page_empty(ptep)
+static inline phys_addr_t
+stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+{
+ if (kvm_stage2_has_pmd(kvm)) {
+ phys_addr_t boundary = (addr + S2_PMD_SIZE) & S2_PMD_MASK;
-#if STAGE2_PGTABLE_LEVELS == 2
-#include <asm/stage2_pgtable-nopmd.h>
-#elif STAGE2_PGTABLE_LEVELS == 3
-#include <asm/stage2_pgtable-nopud.h>
-#endif
+ return (boundary - 1 < end - 1) ? boundary : end;
+ } else {
+ return end;
+ }
+}
+static inline bool stage2_pte_table_empty(struct kvm *kvm, pte_t *ptep)
+{
+ return kvm_page_empty(ptep);
+}
-#define stage2_pgd_index(addr) (((addr) >> S2_PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+static inline unsigned long stage2_pgd_index(struct kvm *kvm, phys_addr_t addr)
+{
+ return (((addr) >> stage2_pgdir_shift(kvm)) & (stage2_pgd_ptrs(kvm) - 1));
+}
-static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline phys_addr_t
+stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
{
- phys_addr_t boundary = (addr + S2_PGDIR_SIZE) & S2_PGDIR_MASK;
+ phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm);
return (boundary - 1 < end - 1) ? boundary : end;
}
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 07256b08226c..a74f84d09412 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -338,15 +338,15 @@ int __attribute_const__ kvm_target_cpu(void)
return KVM_ARM_TARGET_CORTEX_A53;
case ARM_CPU_PART_CORTEX_A57:
return KVM_ARM_TARGET_CORTEX_A57;
- };
+ }
break;
case ARM_CPU_IMP_APM:
switch (part_number) {
case APM_CPU_PART_POTENZA:
return KVM_ARM_TARGET_XGENE_POTENZA;
- };
+ }
break;
- };
+ }
/* Return a default generic target */
return KVM_ARM_TARGET_GENERIC_V8;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index e5e741bfffe1..35a81bebd02b 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -284,6 +284,13 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
*/
run->exit_reason = KVM_EXIT_FAIL_ENTRY;
return 0;
+ case ARM_EXCEPTION_IL:
+ /*
+ * We attempted an illegal exception return. Guest state must
+ * have been corrupted somehow. Give up.
+ */
+ run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ return -EINVAL;
default:
kvm_pr_unimpl("Unsupported exception type: %d",
exception_index);
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 2fabc2dc1966..82d1904328ad 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_KVM_ARM_HOST) += switch.o
obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o
obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
-obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
# KVM code is run at a different exception code with a different map, so
# compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 24b4fbafe3e4..b1f14f736962 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -162,6 +162,20 @@ el1_error:
mov x0, #ARM_EXCEPTION_EL1_SERROR
b __guest_exit
+el2_sync:
+ /* Check for illegal exception return, otherwise panic */
+ mrs x0, spsr_el2
+
+ /* if this was something else, then panic! */
+ tst x0, #PSR_IL_BIT
+ b.eq __hyp_panic
+
+ /* Let's attempt a recovery from the illegal exception return */
+ get_vcpu_ptr x1, x0
+ mov x0, #ARM_EXCEPTION_IL
+ b __guest_exit
+
+
el2_error:
ldp x0, x1, [sp], #16
@@ -240,7 +254,7 @@ ENTRY(__kvm_hyp_vector)
invalid_vect el2t_fiq_invalid // FIQ EL2t
invalid_vect el2t_error_invalid // Error EL2t
- invalid_vect el2h_sync_invalid // Synchronous EL2h
+ valid_vect el2_sync // Synchronous EL2h
invalid_vect el2h_irq_invalid // IRQ EL2h
invalid_vect el2h_fiq_invalid // FIQ EL2h
valid_vect el2_error // Error EL2h
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
deleted file mode 100644
index 603e1ee83e89..000000000000
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Copyright (C) 2016 - ARM Ltd
- * Author: Marc Zyngier <[email protected]>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/types.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_hyp.h>
-
-u32 __hyp_text __init_stage2_translation(void)
-{
- u64 val = VTCR_EL2_FLAGS;
- u64 parange;
- u64 tmp;
-
- /*
- * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS
- * bits in VTCR_EL2. Amusingly, the PARange is 4 bits, while
- * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
- */
- parange = read_sysreg(id_aa64mmfr0_el1) & 7;
- if (parange > ID_AA64MMFR0_PARANGE_MAX)
- parange = ID_AA64MMFR0_PARANGE_MAX;
- val |= parange << 16;
-
- /* Compute the actual PARange... */
- switch (parange) {
- case 0:
- parange = 32;
- break;
- case 1:
- parange = 36;
- break;
- case 2:
- parange = 40;
- break;
- case 3:
- parange = 42;
- break;
- case 4:
- parange = 44;
- break;
- case 5:
- default:
- parange = 48;
- break;
- }
-
- /*
- * ... and clamp it to 40 bits, unless we have some braindead
- * HW that implements less than that. In all cases, we'll
- * return that value for the rest of the kernel to decide what
- * to do.
- */
- val |= 64 - (parange > 40 ? 40 : parange);
-
- /*
- * Check the availability of Hardware Access Flag / Dirty Bit
- * Management in ID_AA64MMFR1_EL1 and enable the feature in VTCR_EL2.
- */
- tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_HADBS_SHIFT) & 0xf;
- if (tmp)
- val |= VTCR_EL2_HA;
-
- /*
- * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
- * bit in VTCR_EL2.
- */
- tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_VMIDBITS_SHIFT) & 0xf;
- val |= (tmp == ID_AA64MMFR1_VMIDBITS_16) ?
- VTCR_EL2_VS_16BIT :
- VTCR_EL2_VS_8BIT;
-
- write_sysreg(val, vtcr_el2);
-
- return parange;
-}
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index ca46153d7915..7cc175c88a37 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -198,7 +198,7 @@ void deactivate_traps_vhe_put(void)
static void __hyp_text __activate_vm(struct kvm *kvm)
{
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ __load_guest_stage2(kvm);
}
static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
@@ -263,7 +263,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
return false; /* Translation failed, back to guest */
/* Convert PAR to HPFAR format */
- *hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
+ *hpfar = PAR_TO_HPFAR(tmp);
return true;
}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 9ce223944983..8dc285318204 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -152,8 +152,25 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
static void __hyp_text
__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
{
+ u64 pstate = ctxt->gp_regs.regs.pstate;
+ u64 mode = pstate & PSR_AA32_MODE_MASK;
+
+ /*
+ * Safety check to ensure we're setting the CPU up to enter the guest
+ * in a less privileged mode.
+ *
+ * If we are attempting a return to EL2 or higher in AArch64 state,
+ * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that
+ * we'll take an illegal exception state exception immediately after
+ * the ERET to the guest. Attempts to return to AArch32 Hyp will
+ * result in an illegal exception return because EL2's execution state
+ * is determined by SCR_EL3.RW.
+ */
+ if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
+ pstate = PSR_MODE_EL2h | PSR_IL_BIT;
+
write_sysreg_el2(ctxt->gp_regs.regs.pc, elr);
- write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
+ write_sysreg_el2(pstate, spsr);
if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 131c7772703c..4dbd9c69a96d 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -30,7 +30,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
* bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
* let's flip TGE before executing the TLB operation.
*/
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ __load_guest_stage2(kvm);
val = read_sysreg(hcr_el2);
val &= ~HCR_TGE;
write_sysreg(val, hcr_el2);
@@ -39,7 +39,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
{
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ __load_guest_stage2(kvm);
isb();
}
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index e37c78bbe1ca..b72a3dd56204 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -26,6 +26,7 @@
#include <kvm/arm_arch_timer.h>
+#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/ptrace.h>
#include <asm/kvm_arm.h>
@@ -33,6 +34,9 @@
#include <asm/kvm_coproc.h>
#include <asm/kvm_mmu.h>
+/* Maximum phys_shift supported for any VM on this host */
+static u32 kvm_ipa_limit;
+
/*
* ARMv8 Reset Values
*/
@@ -55,12 +59,12 @@ static bool cpu_has_32bit_el1(void)
}
/**
- * kvm_arch_dev_ioctl_check_extension
+ * kvm_arch_vm_ioctl_check_extension
*
* We currently assume that the number of HW registers is uniform
* across all CPUs (see cpuinfo_sanity_check).
*/
-int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
+int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -82,9 +86,11 @@ int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_SET_GUEST_DEBUG:
case KVM_CAP_VCPU_ATTRIBUTES:
- case KVM_CAP_VCPU_EVENTS:
r = 1;
break;
+ case KVM_CAP_ARM_VM_IPA_SIZE:
+ r = kvm_ipa_limit;
+ break;
default:
r = 0;
}
@@ -133,3 +139,99 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
/* Reset timer */
return kvm_timer_vcpu_reset(vcpu);
}
+
+void kvm_set_ipa_limit(void)
+{
+ unsigned int ipa_max, pa_max, va_max, parange;
+
+ parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 0x7;
+ pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
+
+ /* Clamp the IPA limit to the PA size supported by the kernel */
+ ipa_max = (pa_max > PHYS_MASK_SHIFT) ? PHYS_MASK_SHIFT : pa_max;
+ /*
+ * Since our stage2 table is dependent on the stage1 page table code,
+ * we must always honor the following condition:
+ *
+ * Number of levels in Stage1 >= Number of levels in Stage2.
+ *
+ * So clamp the ipa limit further down to limit the number of levels.
+ * Since we can concatenate upto 16 tables at entry level, we could
+ * go upto 4bits above the maximum VA addressible with the current
+ * number of levels.
+ */
+ va_max = PGDIR_SHIFT + PAGE_SHIFT - 3;
+ va_max += 4;
+
+ if (va_max < ipa_max)
+ ipa_max = va_max;
+
+ /*
+ * If the final limit is lower than the real physical address
+ * limit of the CPUs, report the reason.
+ */
+ if (ipa_max < pa_max)
+ pr_info("kvm: Limiting the IPA size due to kernel %s Address limit\n",
+ (va_max < pa_max) ? "Virtual" : "Physical");
+
+ WARN(ipa_max < KVM_PHYS_SHIFT,
+ "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
+ kvm_ipa_limit = ipa_max;
+ kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
+}
+
+/*
+ * Configure the VTCR_EL2 for this VM. The VTCR value is common
+ * across all the physical CPUs on the system. We use system wide
+ * sanitised values to fill in different fields, except for Hardware
+ * Management of Access Flags. HA Flag is set unconditionally on
+ * all CPUs, as it is safe to run with or without the feature and
+ * the bit is RES0 on CPUs that don't support it.
+ */
+int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
+{
+ u64 vtcr = VTCR_EL2_FLAGS;
+ u32 parange, phys_shift;
+ u8 lvls;
+
+ if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+ return -EINVAL;
+
+ phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
+ if (phys_shift) {
+ if (phys_shift > kvm_ipa_limit ||
+ phys_shift < 32)
+ return -EINVAL;
+ } else {
+ phys_shift = KVM_PHYS_SHIFT;
+ }
+
+ parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 7;
+ if (parange > ID_AA64MMFR0_PARANGE_MAX)
+ parange = ID_AA64MMFR0_PARANGE_MAX;
+ vtcr |= parange << VTCR_EL2_PS_SHIFT;
+
+ vtcr |= VTCR_EL2_T0SZ(phys_shift);
+ /*
+ * Use a minimum 2 level page table to prevent splitting
+ * host PMD huge pages at stage2.
+ */
+ lvls = stage2_pgtable_levels(phys_shift);
+ if (lvls < 2)
+ lvls = 2;
+ vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
+
+ /*
+ * Enable the Hardware Access Flag management, unconditionally
+ * on all CPUs. The features is RES0 on CPUs without the support
+ * and must be ignored by the CPUs.
+ */
+ vtcr |= VTCR_EL2_HA;
+
+ /* Set the vmid bits */
+ vtcr |= (kvm_get_vmid_bits() == 16) ?
+ VTCR_EL2_VS_16BIT :
+ VTCR_EL2_VS_8BIT;
+ kvm->arch.vtcr = vtcr;
+ return 0;
+}
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index e203169931c7..6390bd8c141b 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -14,6 +14,16 @@
#ifndef _ASM_X86_FIXMAP_H
#define _ASM_X86_FIXMAP_H
+/*
+ * Exposed to assembly code for setting up initial page tables. Cannot be
+ * calculated in assembly code (fixmap entries are an enum), but is sanity
+ * checked in the actual fixmap C code to make sure that the fixmap is
+ * covered fully.
+ */
+#define FIXMAP_PMD_NUM 2
+/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
+#define FIXMAP_PMD_TOP 507
+
#ifndef __ASSEMBLY__
#include <linux/kernel.h>
#include <asm/acpi.h>
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 09b2e3e2cf1b..55e51ff7e421 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -102,7 +102,15 @@
#define UNMAPPED_GVA (~(gpa_t)0)
/* KVM Hugepage definitions for x86 */
-#define KVM_NR_PAGE_SIZES 3
+enum {
+ PT_PAGE_TABLE_LEVEL = 1,
+ PT_DIRECTORY_LEVEL = 2,
+ PT_PDPE_LEVEL = 3,
+ /* set max level to the biggest one */
+ PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL,
+};
+#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \
+ PT_PAGE_TABLE_LEVEL + 1)
#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9)
#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
@@ -177,6 +185,7 @@ enum {
#define DR6_BD (1 << 13)
#define DR6_BS (1 << 14)
+#define DR6_BT (1 << 15)
#define DR6_RTM (1 << 16)
#define DR6_FIXED_1 0xfffe0ff0
#define DR6_INIT 0xffff0ff0
@@ -247,7 +256,7 @@ struct kvm_mmu_memory_cache {
* @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
*/
union kvm_mmu_page_role {
- unsigned word;
+ u32 word;
struct {
unsigned level:4;
unsigned cr4_pae:1;
@@ -273,6 +282,34 @@ union kvm_mmu_page_role {
};
};
+union kvm_mmu_extended_role {
+/*
+ * This structure complements kvm_mmu_page_role caching everything needed for
+ * MMU configuration. If nothing in both these structures changed, MMU
+ * re-configuration can be skipped. @valid bit is set on first usage so we don't
+ * treat all-zero structure as valid data.
+ */
+ u32 word;
+ struct {
+ unsigned int valid:1;
+ unsigned int execonly:1;
+ unsigned int cr0_pg:1;
+ unsigned int cr4_pse:1;
+ unsigned int cr4_pke:1;
+ unsigned int cr4_smap:1;
+ unsigned int cr4_smep:1;
+ unsigned int cr4_la57:1;
+ };
+};
+
+union kvm_mmu_role {
+ u64 as_u64;
+ struct {
+ union kvm_mmu_page_role base;
+ union kvm_mmu_extended_role ext;
+ };
+};
+
struct kvm_rmap_head {
unsigned long val;
};
@@ -280,18 +317,18 @@ struct kvm_rmap_head {
struct kvm_mmu_page {
struct list_head link;
struct hlist_node hash_link;
+ bool unsync;
/*
* The following two entries are used to key the shadow page in the
* hash table.
*/
- gfn_t gfn;
union kvm_mmu_page_role role;
+ gfn_t gfn;
u64 *spt;
/* hold the gfn of each spte inside spt */
gfn_t *gfns;
- bool unsync;
int root_count; /* Currently serving as active root */
unsigned int unsync_children;
struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
@@ -360,7 +397,7 @@ struct kvm_mmu {
void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
u64 *spte, const void *pte);
hpa_t root_hpa;
- union kvm_mmu_page_role base_role;
+ union kvm_mmu_role mmu_role;
u8 root_level;
u8 shadow_root_level;
u8 ept_ad;
@@ -490,7 +527,7 @@ struct kvm_vcpu_hv {
struct kvm_hyperv_exit exit;
struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
- cpumask_t tlb_lush;
+ cpumask_t tlb_flush;
};
struct kvm_vcpu_arch {
@@ -534,7 +571,13 @@ struct kvm_vcpu_arch {
* the paging mode of the l1 guest. This context is always used to
* handle faults.
*/
- struct kvm_mmu mmu;
+ struct kvm_mmu *mmu;
+
+ /* Non-nested MMU for L1 */
+ struct kvm_mmu root_mmu;
+
+ /* L1 MMU when running nested */
+ struct kvm_mmu guest_mmu;
/*
* Paging state of an L2 guest (used for nested npt)
@@ -585,6 +628,8 @@ struct kvm_vcpu_arch {
bool has_error_code;
u8 nr;
u32 error_code;
+ unsigned long payload;
+ bool has_payload;
u8 nested_apf;
} exception;
@@ -781,6 +826,9 @@ struct kvm_hv {
u64 hv_reenlightenment_control;
u64 hv_tsc_emulation_control;
u64 hv_tsc_emulation_status;
+
+ /* How many vCPUs have VP index != vCPU index */
+ atomic_t num_mismatched_vp_indexes;
};
enum kvm_irqchip_mode {
@@ -871,6 +919,7 @@ struct kvm_arch {
bool x2apic_broadcast_quirk_disabled;
bool guest_can_read_msr_platform_info;
+ bool exception_payload_enabled;
};
struct kvm_vm_stat {
@@ -1133,6 +1182,9 @@ struct kvm_x86_ops {
int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*get_msr_feature)(struct kvm_msr_entry *entry);
+
+ int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version);
};
struct kvm_arch_async_pf {
@@ -1170,7 +1222,6 @@ void kvm_mmu_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_setup(struct kvm_vcpu *vcpu);
void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
@@ -1324,7 +1375,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free);
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ ulong roots_to_free);
gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index c0643831706e..616f8e637bc3 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void);
+void __init mem_encrypt_free_decrypted_mem(void);
bool sme_active(void);
bool sev_active(void);
+#define __bss_decrypted __attribute__((__section__(".bss..decrypted")))
+
#else /* !CONFIG_AMD_MEM_ENCRYPT */
#define sme_me_mask 0ULL
@@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0;
static inline int __init
early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
+#define __bss_decrypted
+
#endif /* CONFIG_AMD_MEM_ENCRYPT */
/*
@@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0;
#define __sme_pa(x) (__pa(x) | sme_me_mask)
#define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask)
+extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
+
#endif /* __ASSEMBLY__ */
#endif /* __X86_MEM_ENCRYPT_H__ */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index ce2b59047cb8..9c85b54bf03c 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -14,6 +14,7 @@
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
+#include <asm/fixmap.h>
extern p4d_t level4_kernel_pgt[512];
extern p4d_t level4_ident_pgt[512];
@@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pmd_t level2_fixmap_pgt[512];
extern pmd_t level2_ident_pgt[512];
-extern pte_t level1_fixmap_pgt[512];
+extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM];
extern pgd_t init_top_pgt[];
#define swapper_pg_dir init_top_pgt
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 0116b2ee9e64..449c92da2c91 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -40,7 +40,7 @@ static inline int cpu_has_vmx(void)
*/
static inline void cpu_vmxoff(void)
{
- asm volatile (ASM_VMX_VMXOFF : : : "cc");
+ asm volatile ("vmxoff");
cr4_clear_bits(X86_CR4_VMXE);
}
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9527ba5d62da..ade0f153947d 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -503,19 +503,6 @@ enum vmcs_field {
#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul
-
-#define ASM_VMX_VMCLEAR_RAX ".byte 0x66, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMLAUNCH ".byte 0x0f, 0x01, 0xc2"
-#define ASM_VMX_VMRESUME ".byte 0x0f, 0x01, 0xc3"
-#define ASM_VMX_VMPTRLD_RAX ".byte 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMREAD_RDX_RAX ".byte 0x0f, 0x78, 0xd0"
-#define ASM_VMX_VMWRITE_RAX_RDX ".byte 0x0f, 0x79, 0xd0"
-#define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4"
-#define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4"
-#define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_INVEPT ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
-#define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
-
struct vmx_msr_entry {
u32 index;
u32 reserved;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index fd23d5778ea1..dabfcf7c3941 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -299,7 +300,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ __u8 pending;
__u32 error_code;
} exception;
struct {
@@ -322,7 +323,9 @@ struct kvm_vcpu_events {
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
- __u32 reserved[9];
+ __u8 reserved[27];
+ __u8 exception_has_payload;
+ __u64 exception_payload;
};
/* for KVM_GET/SET_DEBUGREGS */
@@ -381,6 +384,7 @@ struct kvm_sync_regs {
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
+#define KVM_STATE_NESTED_EVMCS 0x00000004
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 4e588f36228f..285eb3ec4200 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e)
e <= QOS_L3_MBM_LOCAL_EVENT_ID);
}
+struct rdt_parse_data {
+ struct rdtgroup *rdtgrp;
+ char *buf;
+};
+
/**
* struct rdt_resource - attributes of an RDT resource
* @rid: The index of the resource
@@ -423,16 +428,19 @@ struct rdt_resource {
struct rdt_cache cache;
struct rdt_membw membw;
const char *format_str;
- int (*parse_ctrlval) (void *data, struct rdt_resource *r,
- struct rdt_domain *d);
+ int (*parse_ctrlval)(struct rdt_parse_data *data,
+ struct rdt_resource *r,
+ struct rdt_domain *d);
struct list_head evt_list;
int num_rmid;
unsigned int mon_scale;
unsigned long fflags;
};
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d);
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d);
extern struct mutex rdtgroup_mutex;
@@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
int update_domains(struct rdt_resource *r, int closid);
+int closids_supported(void);
void closid_free(int closid);
int alloc_rmid(void);
void free_rmid(u32 rmid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index af358ca05160..0f53049719cd 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
return true;
}
-int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
- unsigned long data;
- char *buf = _buf;
+ unsigned long bw_val;
if (d->have_new_ctrl) {
rdt_last_cmd_printf("duplicate domain %d\n", d->id);
return -EINVAL;
}
- if (!bw_validate(buf, &data, r))
+ if (!bw_validate(data->buf, &bw_val, r))
return -EINVAL;
- d->new_ctrl = data;
+ d->new_ctrl = bw_val;
d->have_new_ctrl = true;
return 0;
@@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
return true;
}
-struct rdt_cbm_parse_data {
- struct rdtgroup *rdtgrp;
- char *buf;
-};
-
/*
* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.
*/
-int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
+ struct rdt_domain *d)
{
- struct rdt_cbm_parse_data *data = _data;
struct rdtgroup *rdtgrp = data->rdtgrp;
u32 cbm_val;
@@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
static int parse_line(char *line, struct rdt_resource *r,
struct rdtgroup *rdtgrp)
{
- struct rdt_cbm_parse_data data;
+ struct rdt_parse_data data;
char *dom = NULL, *id;
struct rdt_domain *d;
unsigned long dom_id;
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+ r->rid == RDT_RESOURCE_MBA) {
+ rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
+ return -EINVAL;
+ }
+
next:
if (!line || line[0] == '\0')
return 0;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index b799c00bef09..1b8e86a5d5e1 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...)
* limited as the number of resources grows.
*/
static int closid_free_map;
+static int closid_free_map_len;
+
+int closids_supported(void)
+{
+ return closid_free_map_len;
+}
static void closid_init(void)
{
@@ -111,6 +117,7 @@ static void closid_init(void)
/* CLOSID 0 is always reserved for the default group */
closid_free_map &= ~1;
+ closid_free_map_len = rdt_min_closid;
}
static int closid_alloc(void)
@@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
sw_shareable = 0;
exclusive = 0;
seq_printf(seq, "%d=", dom->id);
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
if (!closid_allocated(i))
continue;
mode = rdtgroup_mode_by_closid(i);
@@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
/* Check for overlap with other resource groups */
ctrl = d->ctrl_val;
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
ctrl_b = (unsigned long *)ctrl;
mode = rdtgroup_mode_by_closid(i);
if (closid_allocated(i) && i != closid &&
@@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
{
int closid = rdtgrp->closid;
struct rdt_resource *r;
+ bool has_cache = false;
struct rdt_domain *d;
for_each_alloc_enabled_rdt_resource(r) {
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
+ has_cache = true;
list_for_each_entry(d, &r->domains, list) {
if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
- rdtgrp->closid, false))
+ rdtgrp->closid, false)) {
+ rdt_last_cmd_puts("schemata overlaps\n");
return false;
+ }
}
}
+ if (!has_cache) {
+ rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n");
+ return false;
+ }
+
return true;
}
@@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
rdtgrp->mode = RDT_MODE_SHAREABLE;
} else if (!strcmp(buf, "exclusive")) {
if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
- rdt_last_cmd_printf("schemata overlaps\n");
ret = -EINVAL;
goto out;
}
@@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
struct rdt_resource *r;
struct rdt_domain *d;
unsigned int size;
- bool sep = false;
- u32 cbm;
+ bool sep;
+ u32 ctrl;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
@@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
}
for_each_alloc_enabled_rdt_resource(r) {
+ sep = false;
seq_printf(s, "%*s:", max_name_width, r->name);
list_for_each_entry(d, &r->domains, list) {
if (sep)
@@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
size = 0;
} else {
- cbm = d->ctrl_val[rdtgrp->closid];
- size = rdtgroup_cbm_to_size(r, d, cbm);
+ ctrl = (!is_mba_sc(r) ?
+ d->ctrl_val[rdtgrp->closid] :
+ d->mbps_val[rdtgrp->closid]);
+ if (r->rid == RDT_RESOURCE_MBA)
+ size = ctrl;
+ else
+ size = rdtgroup_cbm_to_size(r, d, ctrl);
}
seq_printf(s, "%d=%u", d->id, size);
sep = true;
@@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
u32 *ctrl;
for_each_alloc_enabled_rdt_resource(r) {
+ /*
+ * Only initialize default allocations for CBM cache
+ * resources
+ */
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
list_for_each_entry(d, &r->domains, list) {
d->have_new_ctrl = false;
d->new_ctrl = r->cache.shareable_bits;
used_b = r->cache.shareable_bits;
ctrl = d->ctrl_val;
- for (i = 0; i < r->num_closid; i++, ctrl++) {
+ for (i = 0; i < closids_supported(); i++, ctrl++) {
if (closid_allocated(i) && i != closid) {
mode = rdtgroup_mode_by_closid(i);
if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
@@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
}
for_each_alloc_enabled_rdt_resource(r) {
+ /*
+ * Only initialize default allocations for CBM cache
+ * resources
+ */
+ if (r->rid == RDT_RESOURCE_MBA)
+ continue;
ret = update_domains(r, rdtgrp->closid);
if (ret < 0) {
rdt_last_cmd_puts("failed to initialize allocations\n");
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 8047379e575a..ddee1f0870c4 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -35,6 +35,7 @@
#include <asm/bootparam_utils.h>
#include <asm/microcode.h>
#include <asm/kasan.h>
+#include <asm/fixmap.h>
/*
* Manage page tables very early on.
@@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr)
unsigned long __head __startup_64(unsigned long physaddr,
struct boot_params *bp)
{
+ unsigned long vaddr, vaddr_end;
unsigned long load_delta, *p;
unsigned long pgtable_flags;
pgdval_t *pgd;
@@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr,
pud[511] += load_delta;
pmd = fixup_pointer(level2_fixmap_pgt, physaddr);
- pmd[506] += load_delta;
+ for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+ pmd[i] += load_delta;
/*
* Set up the identity mapping for the switchover. These
@@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr,
sme_encrypt_kernel(bp);
/*
+ * Clear the memory encryption mask from the .bss..decrypted section.
+ * The bss section will be memset to zero later in the initialization so
+ * there is no need to zero it after changing the memory encryption
+ * attribute.
+ */
+ if (mem_encrypt_active()) {
+ vaddr = (unsigned long)__start_bss_decrypted;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+ for (; vaddr < vaddr_end; vaddr += PMD_SIZE) {
+ i = pmd_index(vaddr);
+ pmd[i] -= sme_get_me_mask();
+ }
+ }
+
+ /*
* Return the SME encryption mask (if SME is active) to be used as a
* modifier for the initial pgdir entry programmed into CR3.
*/
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 15ebc2fc166e..a3618cf04cf6 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -24,6 +24,7 @@
#include "../entry/calling.h"
#include <asm/export.h>
#include <asm/nospec-branch.h>
+#include <asm/fixmap.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt)
KERNEL_IMAGE_SIZE/PMD_SIZE)
NEXT_PAGE(level2_fixmap_pgt)
- .fill 506,8,0
- .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
- /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */
- .fill 5,8,0
+ .fill (512 - 4 - FIXMAP_PMD_NUM),8,0
+ pgtno = 0
+ .rept (FIXMAP_PMD_NUM)
+ .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \
+ + _PAGE_TABLE_NOENC;
+ pgtno = pgtno + 1
+ .endr
+ /* 6 MB reserved space + a 2MB hole */
+ .fill 4,8,0
NEXT_PAGE(level1_fixmap_pgt)
+ .rept (FIXMAP_PMD_NUM)
.fill 512,8,0
+ .endr
#undef PMDS
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1e6764648af3..013fe3d21dbb 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -28,6 +28,7 @@
#include <linux/sched/clock.h>
#include <linux/mm.h>
#include <linux/slab.h>
+#include <linux/set_memory.h>
#include <asm/hypervisor.h>
#include <asm/mem_encrypt.h>
@@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
static struct pvclock_vsyscall_time_info
- hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
-static struct pvclock_wall_clock wall_clock;
+ hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
+static struct pvclock_wall_clock wall_clock __bss_decrypted;
static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+static struct pvclock_vsyscall_time_info *hvclock_mem;
static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
{
@@ -236,6 +238,45 @@ static void kvm_shutdown(void)
native_machine_shutdown();
}
+static void __init kvmclock_init_mem(void)
+{
+ unsigned long ncpus;
+ unsigned int order;
+ struct page *p;
+ int r;
+
+ if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus())
+ return;
+
+ ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE;
+ order = get_order(ncpus * sizeof(*hvclock_mem));
+
+ p = alloc_pages(GFP_KERNEL, order);
+ if (!p) {
+ pr_warn("%s: failed to alloc %d pages", __func__, (1U << order));
+ return;
+ }
+
+ hvclock_mem = page_address(p);
+
+ /*
+ * hvclock is shared between the guest and the hypervisor, must
+ * be mapped decrypted.
+ */
+ if (sev_active()) {
+ r = set_memory_decrypted((unsigned long) hvclock_mem,
+ 1UL << order);
+ if (r) {
+ __free_pages(p, order);
+ hvclock_mem = NULL;
+ pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n");
+ return;
+ }
+ }
+
+ memset(hvclock_mem, 0, PAGE_SIZE << order);
+}
+
static int __init kvm_setup_vsyscall_timeinfo(void)
{
#ifdef CONFIG_X86_64
@@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void)
kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
#endif
+
+ kvmclock_init_mem();
+
return 0;
}
early_initcall(kvm_setup_vsyscall_timeinfo);
@@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu)
/* Use the static page for the first CPUs, allocate otherwise */
if (cpu < HVC_BOOT_ARRAY_SIZE)
p = &hv_clock_boot[cpu];
+ else if (hvclock_mem)
+ p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE;
else
- p = kzalloc(sizeof(*p), GFP_KERNEL);
+ return -ENOMEM;
per_cpu(hv_clock_per_cpu, cpu) = p;
return p ? 0 : -ENOMEM;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index afdb303285f8..8dc69d82567e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf,
if (len < 5) {
#ifdef CONFIG_RETPOLINE
- WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+ WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr);
#endif
return len; /* call too long for patch site */
}
@@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
if (len < 5) {
#ifdef CONFIG_RETPOLINE
- WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+ WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
#endif
return len; /* call too long for patch site */
}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 8bde0a419f86..5dd3317d761f 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -65,6 +65,23 @@ jiffies_64 = jiffies;
#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+/*
+ * This section contains data which will be mapped as decrypted. Memory
+ * encryption operates on a page basis. Make this section PMD-aligned
+ * to avoid splitting the pages while mapping the section early.
+ *
+ * Note: We use a separate section so that only this section gets
+ * decrypted to avoid exposing more than we wish.
+ */
+#define BSS_DECRYPTED \
+ . = ALIGN(PMD_SIZE); \
+ __start_bss_decrypted = .; \
+ *(.bss..decrypted); \
+ . = ALIGN(PAGE_SIZE); \
+ __start_bss_decrypted_unused = .; \
+ . = ALIGN(PMD_SIZE); \
+ __end_bss_decrypted = .; \
+
#else
#define X86_ALIGN_RODATA_BEGIN
@@ -74,6 +91,7 @@ jiffies_64 = jiffies;
#define ALIGN_ENTRY_TEXT_BEGIN
#define ALIGN_ENTRY_TEXT_END
+#define BSS_DECRYPTED
#endif
@@ -355,6 +373,7 @@ SECTIONS
__bss_start = .;
*(.bss..page_aligned)
*(.bss)
+ BSS_DECRYPTED
. = ALIGN(PAGE_SIZE);
__bss_stop = .;
}
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 01d209ab5481..4e80080f277a 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -36,6 +36,8 @@
#include "trace.h"
+#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
+
static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint)
{
return atomic64_read(&synic->sint[sint]);
@@ -132,8 +134,10 @@ static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx)
struct kvm_vcpu *vcpu = NULL;
int i;
- if (vpidx < KVM_MAX_VCPUS)
- vcpu = kvm_get_vcpu(kvm, vpidx);
+ if (vpidx >= KVM_MAX_VCPUS)
+ return NULL;
+
+ vcpu = kvm_get_vcpu(kvm, vpidx);
if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
return vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
@@ -689,6 +693,24 @@ void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu)
stimer_cleanup(&hv_vcpu->stimer[i]);
}
+bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE))
+ return false;
+ return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED;
+}
+EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled);
+
+bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
+ struct hv_vp_assist_page *assist_page)
+{
+ if (!kvm_hv_assist_page_enabled(vcpu))
+ return false;
+ return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
+ assist_page, sizeof(*assist_page));
+}
+EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page);
+
static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer)
{
struct hv_message *msg = &stimer->msg;
@@ -1040,21 +1062,41 @@ static u64 current_task_runtime_100ns(void)
static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
{
- struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
switch (msr) {
- case HV_X64_MSR_VP_INDEX:
- if (!host)
+ case HV_X64_MSR_VP_INDEX: {
+ struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+ int vcpu_idx = kvm_vcpu_get_idx(vcpu);
+ u32 new_vp_index = (u32)data;
+
+ if (!host || new_vp_index >= KVM_MAX_VCPUS)
return 1;
- hv->vp_index = (u32)data;
+
+ if (new_vp_index == hv_vcpu->vp_index)
+ return 0;
+
+ /*
+ * The VP index is initialized to vcpu_index by
+ * kvm_hv_vcpu_postcreate so they initially match. Now the
+ * VP index is changing, adjust num_mismatched_vp_indexes if
+ * it now matches or no longer matches vcpu_idx.
+ */
+ if (hv_vcpu->vp_index == vcpu_idx)
+ atomic_inc(&hv->num_mismatched_vp_indexes);
+ else if (new_vp_index == vcpu_idx)
+ atomic_dec(&hv->num_mismatched_vp_indexes);
+
+ hv_vcpu->vp_index = new_vp_index;
break;
+ }
case HV_X64_MSR_VP_ASSIST_PAGE: {
u64 gfn;
unsigned long addr;
if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
- hv->hv_vapic = data;
- if (kvm_lapic_enable_pv_eoi(vcpu, 0))
+ hv_vcpu->hv_vapic = data;
+ if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0))
return 1;
break;
}
@@ -1062,12 +1104,19 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
if (kvm_is_error_hva(addr))
return 1;
- if (__clear_user((void __user *)addr, PAGE_SIZE))
+
+ /*
+ * Clear apic_assist portion of f(struct hv_vp_assist_page
+ * only, there can be valuable data in the rest which needs
+ * to be preserved e.g. on migration.
+ */
+ if (__clear_user((void __user *)addr, sizeof(u32)))
return 1;
- hv->hv_vapic = data;
+ hv_vcpu->hv_vapic = data;
kvm_vcpu_mark_page_dirty(vcpu, gfn);
if (kvm_lapic_enable_pv_eoi(vcpu,
- gfn_to_gpa(gfn) | KVM_MSR_ENABLED))
+ gfn_to_gpa(gfn) | KVM_MSR_ENABLED,
+ sizeof(struct hv_vp_assist_page)))
return 1;
break;
}
@@ -1080,7 +1129,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
case HV_X64_MSR_VP_RUNTIME:
if (!host)
return 1;
- hv->runtime_offset = data - current_task_runtime_100ns();
+ hv_vcpu->runtime_offset = data - current_task_runtime_100ns();
break;
case HV_X64_MSR_SCONTROL:
case HV_X64_MSR_SVERSION:
@@ -1172,11 +1221,11 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
bool host)
{
u64 data = 0;
- struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
switch (msr) {
case HV_X64_MSR_VP_INDEX:
- data = hv->vp_index;
+ data = hv_vcpu->vp_index;
break;
case HV_X64_MSR_EOI:
return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
@@ -1185,10 +1234,10 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
case HV_X64_MSR_TPR:
return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
case HV_X64_MSR_VP_ASSIST_PAGE:
- data = hv->hv_vapic;
+ data = hv_vcpu->hv_vapic;
break;
case HV_X64_MSR_VP_RUNTIME:
- data = current_task_runtime_100ns() + hv->runtime_offset;
+ data = current_task_runtime_100ns() + hv_vcpu->runtime_offset;
break;
case HV_X64_MSR_SCONTROL:
case HV_X64_MSR_SVERSION:
@@ -1255,32 +1304,47 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
return kvm_hv_get_msr(vcpu, msr, pdata, host);
}
-static __always_inline int get_sparse_bank_no(u64 valid_bank_mask, int bank_no)
+static __always_inline unsigned long *sparse_set_to_vcpu_mask(
+ struct kvm *kvm, u64 *sparse_banks, u64 valid_bank_mask,
+ u64 *vp_bitmap, unsigned long *vcpu_bitmap)
{
- int i = 0, j;
+ struct kvm_hv *hv = &kvm->arch.hyperv;
+ struct kvm_vcpu *vcpu;
+ int i, bank, sbank = 0;
- if (!(valid_bank_mask & BIT_ULL(bank_no)))
- return -1;
+ memset(vp_bitmap, 0,
+ KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap));
+ for_each_set_bit(bank, (unsigned long *)&valid_bank_mask,
+ KVM_HV_MAX_SPARSE_VCPU_SET_BITS)
+ vp_bitmap[bank] = sparse_banks[sbank++];
- for (j = 0; j < bank_no; j++)
- if (valid_bank_mask & BIT_ULL(j))
- i++;
+ if (likely(!atomic_read(&hv->num_mismatched_vp_indexes))) {
+ /* for all vcpus vp_index == vcpu_idx */
+ return (unsigned long *)vp_bitmap;
+ }
- return i;
+ bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (test_bit(vcpu_to_hv_vcpu(vcpu)->vp_index,
+ (unsigned long *)vp_bitmap))
+ __set_bit(i, vcpu_bitmap);
+ }
+ return vcpu_bitmap;
}
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
u16 rep_cnt, bool ex)
{
struct kvm *kvm = current_vcpu->kvm;
- struct kvm_vcpu_hv *hv_current = &current_vcpu->arch.hyperv;
+ struct kvm_vcpu_hv *hv_vcpu = &current_vcpu->arch.hyperv;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- struct kvm_vcpu *vcpu;
- unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] = {0};
- unsigned long valid_bank_mask = 0;
+ u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+ DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+ unsigned long *vcpu_mask;
+ u64 valid_bank_mask;
u64 sparse_banks[64];
- int sparse_banks_len, i;
+ int sparse_banks_len;
bool all_cpus;
if (!ex) {
@@ -1290,6 +1354,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
trace_kvm_hv_flush_tlb(flush.processor_mask,
flush.address_space, flush.flags);
+ valid_bank_mask = BIT_ULL(0);
sparse_banks[0] = flush.processor_mask;
all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
} else {
@@ -1306,7 +1371,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
all_cpus = flush_ex.hv_vp_set.format !=
HV_GENERIC_SET_SPARSE_4K;
- sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+ sparse_banks_len =
+ bitmap_weight((unsigned long *)&valid_bank_mask, 64) *
sizeof(sparse_banks[0]);
if (!sparse_banks_len && !all_cpus)
@@ -1321,48 +1387,19 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
return HV_STATUS_INVALID_HYPERCALL_INPUT;
}
- cpumask_clear(&hv_current->tlb_lush);
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
- int bank = hv->vp_index / 64, sbank = 0;
-
- if (!all_cpus) {
- /* Banks >64 can't be represented */
- if (bank >= 64)
- continue;
-
- /* Non-ex hypercalls can only address first 64 vCPUs */
- if (!ex && bank)
- continue;
-
- if (ex) {
- /*
- * Check is the bank of this vCPU is in sparse
- * set and get the sparse bank number.
- */
- sbank = get_sparse_bank_no(valid_bank_mask,
- bank);
-
- if (sbank < 0)
- continue;
- }
-
- if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64)))
- continue;
- }
+ cpumask_clear(&hv_vcpu->tlb_flush);
- /*
- * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we
- * can't analyze it here, flush TLB regardless of the specified
- * address space.
- */
- __set_bit(i, vcpu_bitmap);
- }
+ vcpu_mask = all_cpus ? NULL :
+ sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
+ vp_bitmap, vcpu_bitmap);
+ /*
+ * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
+ * analyze it here, flush TLB regardless of the specified address space.
+ */
kvm_make_vcpus_request_mask(kvm,
KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
- vcpu_bitmap, &hv_current->tlb_lush);
+ vcpu_mask, &hv_vcpu->tlb_flush);
ret_success:
/* We always do full TLB flush, set rep_done = rep_cnt. */
@@ -1370,6 +1407,99 @@ ret_success:
((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
}
+static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
+ unsigned long *vcpu_bitmap)
+{
+ struct kvm_lapic_irq irq = {
+ .delivery_mode = APIC_DM_FIXED,
+ .vector = vector
+ };
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+ continue;
+
+ /* We fail only when APIC is disabled */
+ kvm_apic_set_irq(vcpu, &irq, NULL);
+ }
+}
+
+static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa,
+ bool ex, bool fast)
+{
+ struct kvm *kvm = current_vcpu->kvm;
+ struct hv_send_ipi_ex send_ipi_ex;
+ struct hv_send_ipi send_ipi;
+ u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+ DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
+ unsigned long *vcpu_mask;
+ unsigned long valid_bank_mask;
+ u64 sparse_banks[64];
+ int sparse_banks_len;
+ u32 vector;
+ bool all_cpus;
+
+ if (!ex) {
+ if (!fast) {
+ if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi,
+ sizeof(send_ipi))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ sparse_banks[0] = send_ipi.cpu_mask;
+ vector = send_ipi.vector;
+ } else {
+ /* 'reserved' part of hv_send_ipi should be 0 */
+ if (unlikely(ingpa >> 32 != 0))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ sparse_banks[0] = outgpa;
+ vector = (u32)ingpa;
+ }
+ all_cpus = false;
+ valid_bank_mask = BIT_ULL(0);
+
+ trace_kvm_hv_send_ipi(vector, sparse_banks[0]);
+ } else {
+ if (unlikely(kvm_read_guest(kvm, ingpa, &send_ipi_ex,
+ sizeof(send_ipi_ex))))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector,
+ send_ipi_ex.vp_set.format,
+ send_ipi_ex.vp_set.valid_bank_mask);
+
+ vector = send_ipi_ex.vector;
+ valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask;
+ sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+ sizeof(sparse_banks[0]);
+
+ all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
+
+ if (!sparse_banks_len)
+ goto ret_success;
+
+ if (!all_cpus &&
+ kvm_read_guest(kvm,
+ ingpa + offsetof(struct hv_send_ipi_ex,
+ vp_set.bank_contents),
+ sparse_banks,
+ sparse_banks_len))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ }
+
+ if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+ vcpu_mask = all_cpus ? NULL :
+ sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask,
+ vp_bitmap, vcpu_bitmap);
+
+ kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
+
+ret_success:
+ return HV_STATUS_SUCCESS;
+}
+
bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
@@ -1539,6 +1669,20 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
}
ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
break;
+ case HVCALL_SEND_IPI:
+ if (unlikely(rep)) {
+ ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+ break;
+ }
+ ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, false, fast);
+ break;
+ case HVCALL_SEND_IPI_EX:
+ if (unlikely(fast || rep)) {
+ ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+ break;
+ }
+ ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false);
+ break;
default:
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
break;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index d6aa969e20f1..0e66c12ed2c3 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -62,6 +62,10 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
+bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
+bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
+ struct hv_vp_assist_page *assist_page);
+
static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu,
int timer_index)
{
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fbb0e6df121b..3cd227ff807f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,6 +70,11 @@
#define APIC_BROADCAST 0xFF
#define X2APIC_BROADCAST 0xFFFFFFFFul
+static bool lapic_timer_advance_adjust_done = false;
+#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
+/* step-by-step approximation to mitigate fluctuation */
+#define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+
static inline int apic_test_vector(int vec, void *bitmap)
{
return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -955,14 +960,14 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
map = rcu_dereference(kvm->arch.apic_map);
ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap);
- if (ret)
+ if (ret) {
+ *r = 0;
for_each_set_bit(i, &bitmap, 16) {
if (!dst[i])
continue;
- if (*r < 0)
- *r = 0;
*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
}
+ }
rcu_read_unlock();
return ret;
@@ -1472,7 +1477,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
void wait_lapic_expire(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- u64 guest_tsc, tsc_deadline;
+ u64 guest_tsc, tsc_deadline, ns;
if (!lapic_in_kernel(vcpu))
return;
@@ -1492,6 +1497,24 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
if (guest_tsc < tsc_deadline)
__delay(min(tsc_deadline - guest_tsc,
nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+
+ if (!lapic_timer_advance_adjust_done) {
+ /* too early */
+ if (guest_tsc < tsc_deadline) {
+ ns = (tsc_deadline - guest_tsc) * 1000000ULL;
+ do_div(ns, vcpu->arch.virtual_tsc_khz);
+ lapic_timer_advance_ns -= min((unsigned int)ns,
+ lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ } else {
+ /* too late */
+ ns = (guest_tsc - tsc_deadline) * 1000000ULL;
+ do_div(ns, vcpu->arch.virtual_tsc_khz);
+ lapic_timer_advance_ns += min((unsigned int)ns,
+ lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+ }
+ if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
+ lapic_timer_advance_adjust_done = true;
+ }
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
@@ -2621,17 +2644,25 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
return 0;
}
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
{
u64 addr = data & ~KVM_MSR_ENABLED;
+ struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data;
+ unsigned long new_len;
+
if (!IS_ALIGNED(addr, 4))
return 1;
vcpu->arch.pv_eoi.msr_val = data;
if (!pv_eoi_enabled(vcpu))
return 0;
- return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
- addr, sizeof(u8));
+
+ if (addr == ghc->gpa && len <= ghc->len)
+ new_len = ghc->len;
+ else
+ new_len = len;
+
+ return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
}
void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index ed0ed39abd36..ff6ef9c3d760 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -120,7 +120,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
}
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
+int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
void kvm_lapic_init(void);
void kvm_lapic_exit(void);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 51b953ad9d4e..4cf43ce42959 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -932,7 +932,7 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
obj = kmem_cache_zalloc(base_cache, GFP_KERNEL);
if (!obj)
- return -ENOMEM;
+ return cache->nobjs >= min ? 0 : -ENOMEM;
cache->objects[cache->nobjs++] = obj;
}
return 0;
@@ -960,7 +960,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
if (!page)
- return -ENOMEM;
+ return cache->nobjs >= min ? 0 : -ENOMEM;
cache->objects[cache->nobjs++] = page;
}
return 0;
@@ -1265,24 +1265,24 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
mmu_free_pte_list_desc(desc);
}
-static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
+static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
{
struct pte_list_desc *desc;
struct pte_list_desc *prev_desc;
int i;
if (!rmap_head->val) {
- printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte);
+ pr_err("%s: %p 0->BUG\n", __func__, spte);
BUG();
} else if (!(rmap_head->val & 1)) {
- rmap_printk("pte_list_remove: %p 1->0\n", spte);
+ rmap_printk("%s: %p 1->0\n", __func__, spte);
if ((u64 *)rmap_head->val != spte) {
- printk(KERN_ERR "pte_list_remove: %p 1->BUG\n", spte);
+ pr_err("%s: %p 1->BUG\n", __func__, spte);
BUG();
}
rmap_head->val = 0;
} else {
- rmap_printk("pte_list_remove: %p many->many\n", spte);
+ rmap_printk("%s: %p many->many\n", __func__, spte);
desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
prev_desc = NULL;
while (desc) {
@@ -1296,11 +1296,17 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head)
prev_desc = desc;
desc = desc->more;
}
- pr_err("pte_list_remove: %p many->many\n", spte);
+ pr_err("%s: %p many->many\n", __func__, spte);
BUG();
}
}
+static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep)
+{
+ mmu_spte_clear_track_bits(sptep);
+ __pte_list_remove(sptep, rmap_head);
+}
+
static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
struct kvm_memory_slot *slot)
{
@@ -1349,7 +1355,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
sp = page_header(__pa(spte));
gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt);
rmap_head = gfn_to_rmap(kvm, gfn, sp);
- pte_list_remove(spte, rmap_head);
+ __pte_list_remove(spte, rmap_head);
}
/*
@@ -1685,7 +1691,7 @@ static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
while ((sptep = rmap_get_first(rmap_head, &iter))) {
rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep);
- drop_spte(kvm, sptep);
+ pte_list_remove(rmap_head, sptep);
flush = true;
}
@@ -1721,7 +1727,7 @@ restart:
need_flush = 1;
if (pte_write(*ptep)) {
- drop_spte(kvm, sptep);
+ pte_list_remove(rmap_head, sptep);
goto restart;
} else {
new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
@@ -1988,7 +1994,7 @@ static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu,
static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
u64 *parent_pte)
{
- pte_list_remove(parent_pte, &sp->parent_ptes);
+ __pte_list_remove(parent_pte, &sp->parent_ptes);
}
static void drop_parent_pte(struct kvm_mmu_page *sp,
@@ -2181,7 +2187,7 @@ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
if (sp->role.cr4_pae != !!is_pae(vcpu)
- || vcpu->arch.mmu.sync_page(vcpu, sp) == 0) {
+ || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
return false;
}
@@ -2375,14 +2381,14 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
int collisions = 0;
LIST_HEAD(invalid_list);
- role = vcpu->arch.mmu.base_role;
+ role = vcpu->arch.mmu->mmu_role.base;
role.level = level;
role.direct = direct;
if (role.direct)
role.cr4_pae = 0;
role.access = access;
- if (!vcpu->arch.mmu.direct_map
- && vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
+ if (!vcpu->arch.mmu->direct_map
+ && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
role.quadrant = quadrant;
@@ -2457,11 +2463,11 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
{
iterator->addr = addr;
iterator->shadow_addr = root;
- iterator->level = vcpu->arch.mmu.shadow_root_level;
+ iterator->level = vcpu->arch.mmu->shadow_root_level;
if (iterator->level == PT64_ROOT_4LEVEL &&
- vcpu->arch.mmu.root_level < PT64_ROOT_4LEVEL &&
- !vcpu->arch.mmu.direct_map)
+ vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
+ !vcpu->arch.mmu->direct_map)
--iterator->level;
if (iterator->level == PT32E_ROOT_LEVEL) {
@@ -2469,10 +2475,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
* prev_root is currently only used for 64-bit hosts. So only
* the active root_hpa is valid here.
*/
- BUG_ON(root != vcpu->arch.mmu.root_hpa);
+ BUG_ON(root != vcpu->arch.mmu->root_hpa);
iterator->shadow_addr
- = vcpu->arch.mmu.pae_root[(addr >> 30) & 3];
+ = vcpu->arch.mmu->pae_root[(addr >> 30) & 3];
iterator->shadow_addr &= PT64_BASE_ADDR_MASK;
--iterator->level;
if (!iterator->shadow_addr)
@@ -2483,7 +2489,7 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator,
struct kvm_vcpu *vcpu, u64 addr)
{
- shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu.root_hpa,
+ shadow_walk_init_using_root(iterator, vcpu, vcpu->arch.mmu->root_hpa,
addr);
}
@@ -3095,7 +3101,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
int emulate = 0;
gfn_t pseudo_gfn;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return 0;
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
@@ -3310,7 +3316,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
u64 spte = 0ull;
uint retry_count = 0;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return false;
if (!page_fault_can_be_fast(error_code))
@@ -3480,11 +3486,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
}
/* roots_to_free must be some combination of the KVM_MMU_ROOT_* flags */
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free)
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ ulong roots_to_free)
{
int i;
LIST_HEAD(invalid_list);
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG);
@@ -3544,20 +3550,20 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
struct kvm_mmu_page *sp;
unsigned i;
- if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
+ if (vcpu->arch.mmu->shadow_root_level >= PT64_ROOT_4LEVEL) {
spin_lock(&vcpu->kvm->mmu_lock);
if(make_mmu_pages_available(vcpu) < 0) {
spin_unlock(&vcpu->kvm->mmu_lock);
return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, 0, 0,
- vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
+ vcpu->arch.mmu->shadow_root_level, 1, ACC_ALL);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.root_hpa = __pa(sp->spt);
- } else if (vcpu->arch.mmu.shadow_root_level == PT32E_ROOT_LEVEL) {
+ vcpu->arch.mmu->root_hpa = __pa(sp->spt);
+ } else if (vcpu->arch.mmu->shadow_root_level == PT32E_ROOT_LEVEL) {
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
MMU_WARN_ON(VALID_PAGE(root));
spin_lock(&vcpu->kvm->mmu_lock);
@@ -3570,9 +3576,9 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
+ vcpu->arch.mmu->pae_root[i] = root | PT_PRESENT_MASK;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
} else
BUG();
@@ -3586,7 +3592,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
gfn_t root_gfn;
int i;
- root_gfn = vcpu->arch.mmu.get_cr3(vcpu) >> PAGE_SHIFT;
+ root_gfn = vcpu->arch.mmu->get_cr3(vcpu) >> PAGE_SHIFT;
if (mmu_check_root(vcpu, root_gfn))
return 1;
@@ -3595,8 +3601,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* Do we shadow a long mode page table? If so we need to
* write-protect the guests page table root.
*/
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
MMU_WARN_ON(VALID_PAGE(root));
@@ -3606,11 +3612,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
return -ENOSPC;
}
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
- vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
+ vcpu->arch.mmu->shadow_root_level, 0, ACC_ALL);
root = __pa(sp->spt);
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.root_hpa = root;
+ vcpu->arch.mmu->root_hpa = root;
return 0;
}
@@ -3620,17 +3626,17 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
* the shadow page table may be a PAE or a long mode page table.
*/
pm_mask = PT_PRESENT_MASK;
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL)
+ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL)
pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK;
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
MMU_WARN_ON(VALID_PAGE(root));
- if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
- pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
+ if (vcpu->arch.mmu->root_level == PT32E_ROOT_LEVEL) {
+ pdptr = vcpu->arch.mmu->get_pdptr(vcpu, i);
if (!(pdptr & PT_PRESENT_MASK)) {
- vcpu->arch.mmu.pae_root[i] = 0;
+ vcpu->arch.mmu->pae_root[i] = 0;
continue;
}
root_gfn = pdptr >> PAGE_SHIFT;
@@ -3648,16 +3654,16 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
++sp->root_count;
spin_unlock(&vcpu->kvm->mmu_lock);
- vcpu->arch.mmu.pae_root[i] = root | pm_mask;
+ vcpu->arch.mmu->pae_root[i] = root | pm_mask;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
/*
* If we shadow a 32 bit page table with a long mode page
* table we enter this path.
*/
- if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL) {
- if (vcpu->arch.mmu.lm_root == NULL) {
+ if (vcpu->arch.mmu->shadow_root_level == PT64_ROOT_4LEVEL) {
+ if (vcpu->arch.mmu->lm_root == NULL) {
/*
* The additional page necessary for this is only
* allocated on demand.
@@ -3669,12 +3675,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
if (lm_root == NULL)
return 1;
- lm_root[0] = __pa(vcpu->arch.mmu.pae_root) | pm_mask;
+ lm_root[0] = __pa(vcpu->arch.mmu->pae_root) | pm_mask;
- vcpu->arch.mmu.lm_root = lm_root;
+ vcpu->arch.mmu->lm_root = lm_root;
}
- vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.lm_root);
+ vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
}
return 0;
@@ -3682,7 +3688,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
{
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return mmu_alloc_direct_roots(vcpu);
else
return mmu_alloc_shadow_roots(vcpu);
@@ -3693,17 +3699,16 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
int i;
struct kvm_mmu_page *sp;
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
-
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
sp = page_header(root);
/*
@@ -3734,7 +3739,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
@@ -3808,7 +3813,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
int root, leaf;
bool reserved = false;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
goto exit;
walk_shadow_page_lockless_begin(vcpu);
@@ -3825,7 +3830,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
if (!is_shadow_present_pte(spte))
break;
- reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
+ reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte,
iterator.level);
}
@@ -3904,7 +3909,7 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
struct kvm_shadow_walk_iterator iterator;
u64 spte;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
walk_shadow_page_lockless_begin(vcpu);
@@ -3931,7 +3936,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
if (r)
return r;
- MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
return nonpaging_map(vcpu, gva & PAGE_MASK,
@@ -3944,8 +3949,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
arch.gfn = gfn;
- arch.direct_map = vcpu->arch.mmu.direct_map;
- arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
+ arch.direct_map = vcpu->arch.mmu->direct_map;
+ arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
@@ -4051,7 +4056,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
int write = error_code & PFERR_WRITE_MASK;
bool map_writable;
- MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
if (page_fault_handle_page_track(vcpu, error_code, gfn))
return RET_PF_EMULATE;
@@ -4127,7 +4132,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3,
{
uint i;
struct kvm_mmu_root_info root;
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
root.cr3 = mmu->get_cr3(vcpu);
root.hpa = mmu->root_hpa;
@@ -4150,7 +4155,7 @@ static bool fast_cr3_switch(struct kvm_vcpu *vcpu, gpa_t new_cr3,
union kvm_mmu_page_role new_role,
bool skip_tlb_flush)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
/*
* For now, limit the fast switch to 64-bit hosts+VMs in order to avoid
@@ -4201,7 +4206,8 @@ static void __kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3,
bool skip_tlb_flush)
{
if (!fast_cr3_switch(vcpu, new_cr3, new_role, skip_tlb_flush))
- kvm_mmu_free_roots(vcpu, KVM_MMU_ROOT_CURRENT);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu,
+ KVM_MMU_ROOT_CURRENT);
}
void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush)
@@ -4219,7 +4225,7 @@ static unsigned long get_cr3(struct kvm_vcpu *vcpu)
static void inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
- vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+ vcpu->arch.mmu->inject_page_fault(vcpu, fault);
}
static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
@@ -4423,7 +4429,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
- bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+ bool uses_nx = context->nx ||
+ context->mmu_role.base.smep_andnot_wp;
struct rsvd_bits_validate *shadow_zero_check;
int i;
@@ -4562,7 +4569,7 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
* SMAP:kernel-mode data accesses from user-mode
* mappings should fault. A fault is considered
* as a SMAP violation if all of the following
- * conditions are ture:
+ * conditions are true:
* - X86_CR4_SMAP is set in CR4
* - A user page is accessed
* - The access is not a fetch
@@ -4723,27 +4730,65 @@ static void paging32E_init_context(struct kvm_vcpu *vcpu,
paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
}
-static union kvm_mmu_page_role
-kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu)
+static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
+{
+ union kvm_mmu_extended_role ext = {0};
+
+ ext.cr0_pg = !!is_paging(vcpu);
+ ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
+ ext.cr4_pse = !!is_pse(vcpu);
+ ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE);
+ ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
+
+ ext.valid = 1;
+
+ return ext;
+}
+
+static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
+ bool base_only)
+{
+ union kvm_mmu_role role = {0};
+
+ role.base.access = ACC_ALL;
+ role.base.nxe = !!is_nx(vcpu);
+ role.base.cr4_pae = !!is_pae(vcpu);
+ role.base.cr0_wp = is_write_protection(vcpu);
+ role.base.smm = is_smm(vcpu);
+ role.base.guest_mode = is_guest_mode(vcpu);
+
+ if (base_only)
+ return role;
+
+ role.ext = kvm_calc_mmu_role_ext(vcpu);
+
+ return role;
+}
+
+static union kvm_mmu_role
+kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
{
- union kvm_mmu_page_role role = {0};
+ union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
- role.guest_mode = is_guest_mode(vcpu);
- role.smm = is_smm(vcpu);
- role.ad_disabled = (shadow_accessed_mask == 0);
- role.level = kvm_x86_ops->get_tdp_level(vcpu);
- role.direct = true;
- role.access = ACC_ALL;
+ role.base.ad_disabled = (shadow_accessed_mask == 0);
+ role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
+ role.base.direct = true;
return role;
}
static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
+ union kvm_mmu_role new_role =
+ kvm_calc_tdp_mmu_root_page_role(vcpu, false);
- context->base_role.word = mmu_base_role_mask.word &
- kvm_calc_tdp_mmu_root_page_role(vcpu).word;
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == context->mmu_role.as_u64)
+ return;
+
+ context->mmu_role.as_u64 = new_role.as_u64;
context->page_fault = tdp_page_fault;
context->sync_page = nonpaging_sync_page;
context->invlpg = nonpaging_invlpg;
@@ -4783,36 +4828,36 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
reset_tdp_shadow_zero_bits_mask(vcpu, context);
}
-static union kvm_mmu_page_role
-kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu)
-{
- union kvm_mmu_page_role role = {0};
- bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
- bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
-
- role.nxe = is_nx(vcpu);
- role.cr4_pae = !!is_pae(vcpu);
- role.cr0_wp = is_write_protection(vcpu);
- role.smep_andnot_wp = smep && !is_write_protection(vcpu);
- role.smap_andnot_wp = smap && !is_write_protection(vcpu);
- role.guest_mode = is_guest_mode(vcpu);
- role.smm = is_smm(vcpu);
- role.direct = !is_paging(vcpu);
- role.access = ACC_ALL;
+static union kvm_mmu_role
+kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
+{
+ union kvm_mmu_role role = kvm_calc_mmu_role_common(vcpu, base_only);
+
+ role.base.smep_andnot_wp = role.ext.cr4_smep &&
+ !is_write_protection(vcpu);
+ role.base.smap_andnot_wp = role.ext.cr4_smap &&
+ !is_write_protection(vcpu);
+ role.base.direct = !is_paging(vcpu);
if (!is_long_mode(vcpu))
- role.level = PT32E_ROOT_LEVEL;
+ role.base.level = PT32E_ROOT_LEVEL;
else if (is_la57_mode(vcpu))
- role.level = PT64_ROOT_5LEVEL;
+ role.base.level = PT64_ROOT_5LEVEL;
else
- role.level = PT64_ROOT_4LEVEL;
+ role.base.level = PT64_ROOT_4LEVEL;
return role;
}
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
+ union kvm_mmu_role new_role =
+ kvm_calc_shadow_mmu_root_page_role(vcpu, false);
+
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == context->mmu_role.as_u64)
+ return;
if (!is_paging(vcpu))
nonpaging_init_context(vcpu, context);
@@ -4823,22 +4868,28 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
else
paging32_init_context(vcpu, context);
- context->base_role.word = mmu_base_role_mask.word &
- kvm_calc_shadow_mmu_root_page_role(vcpu).word;
+ context->mmu_role.as_u64 = new_role.as_u64;
reset_shadow_zero_bits_mask(vcpu, context);
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
-static union kvm_mmu_page_role
-kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
+static union kvm_mmu_role
+kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
+ bool execonly)
{
- union kvm_mmu_page_role role = vcpu->arch.mmu.base_role;
+ union kvm_mmu_role role;
+
+ /* Base role is inherited from root_mmu */
+ role.base.word = vcpu->arch.root_mmu.mmu_role.base.word;
+ role.ext = kvm_calc_mmu_role_ext(vcpu);
+
+ role.base.level = PT64_ROOT_4LEVEL;
+ role.base.direct = false;
+ role.base.ad_disabled = !accessed_dirty;
+ role.base.guest_mode = true;
+ role.base.access = ACC_ALL;
- role.level = PT64_ROOT_4LEVEL;
- role.direct = false;
- role.ad_disabled = !accessed_dirty;
- role.guest_mode = true;
- role.access = ACC_ALL;
+ role.ext.execonly = execonly;
return role;
}
@@ -4846,11 +4897,17 @@ kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty, gpa_t new_eptp)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
- union kvm_mmu_page_role root_page_role =
- kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty);
+ struct kvm_mmu *context = vcpu->arch.mmu;
+ union kvm_mmu_role new_role =
+ kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
+ execonly);
+
+ __kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);
+
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == context->mmu_role.as_u64)
+ return;
- __kvm_mmu_new_cr3(vcpu, new_eptp, root_page_role, false);
context->shadow_root_level = PT64_ROOT_4LEVEL;
context->nx = true;
@@ -4862,7 +4919,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
context->update_pte = ept_update_pte;
context->root_level = PT64_ROOT_4LEVEL;
context->direct_map = false;
- context->base_role.word = root_page_role.word & mmu_base_role_mask.word;
+ context->mmu_role.as_u64 = new_role.as_u64;
+
update_permission_bitmask(vcpu, context, true);
update_pkru_bitmask(vcpu, context, true);
update_last_nonleaf_level(vcpu, context);
@@ -4873,7 +4931,7 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
- struct kvm_mmu *context = &vcpu->arch.mmu;
+ struct kvm_mmu *context = vcpu->arch.mmu;
kvm_init_shadow_mmu(vcpu);
context->set_cr3 = kvm_x86_ops->set_cr3;
@@ -4884,14 +4942,20 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
{
+ union kvm_mmu_role new_role = kvm_calc_mmu_role_common(vcpu, false);
struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
+ new_role.base.word &= mmu_base_role_mask.word;
+ if (new_role.as_u64 == g_context->mmu_role.as_u64)
+ return;
+
+ g_context->mmu_role.as_u64 = new_role.as_u64;
g_context->get_cr3 = get_cr3;
g_context->get_pdptr = kvm_pdptr_read;
g_context->inject_page_fault = kvm_inject_page_fault;
/*
- * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using
+ * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using
* L1's nested page tables (e.g. EPT12). The nested translation
* of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using
* L2's page tables as the first level of translation and L1's
@@ -4930,10 +4994,10 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu, bool reset_roots)
if (reset_roots) {
uint i;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.mmu->root_hpa = INVALID_PAGE;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+ vcpu->arch.mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
}
if (mmu_is_nested(vcpu))
@@ -4948,10 +5012,14 @@ EXPORT_SYMBOL_GPL(kvm_init_mmu);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu)
{
+ union kvm_mmu_role role;
+
if (tdp_enabled)
- return kvm_calc_tdp_mmu_root_page_role(vcpu);
+ role = kvm_calc_tdp_mmu_root_page_role(vcpu, true);
else
- return kvm_calc_shadow_mmu_root_page_role(vcpu);
+ role = kvm_calc_shadow_mmu_root_page_role(vcpu, true);
+
+ return role.base;
}
void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -4981,8 +5049,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load);
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
- kvm_mmu_free_roots(vcpu, KVM_MMU_ROOTS_ALL);
- WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.root_mmu.root_hpa));
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+ WARN_ON(VALID_PAGE(vcpu->arch.guest_mmu.root_hpa));
}
EXPORT_SYMBOL_GPL(kvm_mmu_unload);
@@ -4996,7 +5066,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
}
++vcpu->kvm->stat.mmu_pte_updated;
- vcpu->arch.mmu.update_pte(vcpu, sp, spte, new);
+ vcpu->arch.mmu->update_pte(vcpu, sp, spte, new);
}
static bool need_remote_flush(u64 old, u64 new)
@@ -5173,10 +5243,12 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
local_flush = true;
while (npte--) {
+ u32 base_role = vcpu->arch.mmu->mmu_role.base.word;
+
entry = *spte;
mmu_page_zap_pte(vcpu->kvm, sp, spte);
if (gentry &&
- !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
+ !((sp->role.word ^ base_role)
& mmu_base_role_mask.word) && rmap_can_add(vcpu))
mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
if (need_remote_flush(entry, *spte))
@@ -5194,7 +5266,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
gpa_t gpa;
int r;
- if (vcpu->arch.mmu.direct_map)
+ if (vcpu->arch.mmu->direct_map)
return 0;
gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
@@ -5230,10 +5302,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
{
int r, emulation_type = 0;
enum emulation_result er;
- bool direct = vcpu->arch.mmu.direct_map;
+ bool direct = vcpu->arch.mmu->direct_map;
/* With shadow page tables, fault_address contains a GVA or nGPA. */
- if (vcpu->arch.mmu.direct_map) {
+ if (vcpu->arch.mmu->direct_map) {
vcpu->arch.gpa_available = true;
vcpu->arch.gpa_val = cr2;
}
@@ -5246,8 +5318,9 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
}
if (r == RET_PF_INVALID) {
- r = vcpu->arch.mmu.page_fault(vcpu, cr2, lower_32_bits(error_code),
- false);
+ r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+ lower_32_bits(error_code),
+ false);
WARN_ON(r == RET_PF_INVALID);
}
@@ -5263,7 +5336,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
* paging in both guests. If true, we simply unprotect the page
* and resume the guest.
*/
- if (vcpu->arch.mmu.direct_map &&
+ if (vcpu->arch.mmu->direct_map &&
(error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
return 1;
@@ -5311,7 +5384,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
int i;
/* INVLPG on a * non-canonical address is a NOP according to the SDM. */
@@ -5342,7 +5415,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid)
{
- struct kvm_mmu *mmu = &vcpu->arch.mmu;
+ struct kvm_mmu *mmu = vcpu->arch.mmu;
bool tlb_flush = false;
uint i;
@@ -5386,8 +5459,8 @@ EXPORT_SYMBOL_GPL(kvm_disable_tdp);
static void free_mmu_pages(struct kvm_vcpu *vcpu)
{
- free_page((unsigned long)vcpu->arch.mmu.pae_root);
- free_page((unsigned long)vcpu->arch.mmu.lm_root);
+ free_page((unsigned long)vcpu->arch.mmu->pae_root);
+ free_page((unsigned long)vcpu->arch.mmu->lm_root);
}
static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
@@ -5407,9 +5480,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
if (!page)
return -ENOMEM;
- vcpu->arch.mmu.pae_root = page_address(page);
+ vcpu->arch.mmu->pae_root = page_address(page);
for (i = 0; i < 4; ++i)
- vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
+ vcpu->arch.mmu->pae_root[i] = INVALID_PAGE;
return 0;
}
@@ -5418,27 +5491,21 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
{
uint i;
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
- vcpu->arch.mmu.translate_gpa = translate_gpa;
- vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.root_mmu.translate_gpa = translate_gpa;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- vcpu->arch.mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-
- return alloc_mmu_pages(vcpu);
-}
+ vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-void kvm_mmu_setup(struct kvm_vcpu *vcpu)
-{
- MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
+ vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
+ vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+ vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
- /*
- * kvm_mmu_setup() is called only on vCPU initialization.
- * Therefore, no need to reset mmu roots as they are not yet
- * initialized.
- */
- kvm_init_mmu(vcpu, false);
+ vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
+ return alloc_mmu_pages(vcpu);
}
static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
@@ -5621,7 +5688,7 @@ restart:
if (sp->role.direct &&
!kvm_is_reserved_pfn(pfn) &&
PageTransCompoundMap(pfn_to_page(pfn))) {
- drop_spte(kvm, sptep);
+ pte_list_remove(rmap_head, sptep);
need_tlb_flush = 1;
goto restart;
}
@@ -5878,6 +5945,16 @@ int kvm_mmu_module_init(void)
{
int ret = -ENOMEM;
+ /*
+ * MMU roles use union aliasing which is, generally speaking, an
+ * undefined behavior. However, we supposedly know how compilers behave
+ * and the current status quo is unlikely to change. Guardians below are
+ * supposed to let us know if the assumption becomes false.
+ */
+ BUILD_BUG_ON(sizeof(union kvm_mmu_page_role) != sizeof(u32));
+ BUILD_BUG_ON(sizeof(union kvm_mmu_extended_role) != sizeof(u32));
+ BUILD_BUG_ON(sizeof(union kvm_mmu_role) != sizeof(u64));
+
kvm_mmu_reset_all_pte_masks();
pte_list_desc_cache = kmem_cache_create("pte_list_desc",
@@ -5907,7 +5984,7 @@ out:
}
/*
- * Caculate mmu pages needed for kvm.
+ * Calculate mmu pages needed for kvm.
*/
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
{
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 1fab69c0b2f3..c7b333147c4a 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -43,11 +43,6 @@
#define PT32_ROOT_LEVEL 2
#define PT32E_ROOT_LEVEL 3
-#define PT_PDPE_LEVEL 3
-#define PT_DIRECTORY_LEVEL 2
-#define PT_PAGE_TABLE_LEVEL 1
-#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1)
-
static inline u64 rsvd_bits(int s, int e)
{
if (e < s)
@@ -80,7 +75,7 @@ static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
{
- if (likely(vcpu->arch.mmu.root_hpa != INVALID_PAGE))
+ if (likely(vcpu->arch.mmu->root_hpa != INVALID_PAGE))
return 0;
return kvm_mmu_load(vcpu);
@@ -102,9 +97,9 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
static inline void kvm_mmu_load_cr3(struct kvm_vcpu *vcpu)
{
- if (VALID_PAGE(vcpu->arch.mmu.root_hpa))
- vcpu->arch.mmu.set_cr3(vcpu, vcpu->arch.mmu.root_hpa |
- kvm_get_active_pcid(vcpu));
+ if (VALID_PAGE(vcpu->arch.mmu->root_hpa))
+ vcpu->arch.mmu->set_cr3(vcpu, vcpu->arch.mmu->root_hpa |
+ kvm_get_active_pcid(vcpu));
}
/*
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 1272861e77b9..abac7e208853 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -59,19 +59,19 @@ static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
int i;
struct kvm_mmu_page *sp;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
- hpa_t root = vcpu->arch.mmu.root_hpa;
+ if (vcpu->arch.mmu->root_level >= PT64_ROOT_4LEVEL) {
+ hpa_t root = vcpu->arch.mmu->root_hpa;
sp = page_header(root);
- __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu.root_level);
+ __mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu->root_level);
return;
}
for (i = 0; i < 4; ++i) {
- hpa_t root = vcpu->arch.mmu.pae_root[i];
+ hpa_t root = vcpu->arch.mmu->pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
@@ -122,7 +122,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
hpa = pfn << PAGE_SHIFT;
if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
audit_printk(vcpu->kvm, "levels %d pfn %llx hpa %llx "
- "ent %llxn", vcpu->arch.mmu.root_level, pfn,
+ "ent %llxn", vcpu->arch.mmu->root_level, pfn,
hpa, *sptep);
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 14ffd973df54..7cf2185b7eb5 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -158,14 +158,15 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp, u64 *spte,
u64 gpte)
{
- if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+ if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
goto no_present;
if (!FNAME(is_present_gpte)(gpte))
goto no_present;
/* if accessed bit is not supported prefetch non accessed gpte */
- if (PT_HAVE_ACCESSED_DIRTY(&vcpu->arch.mmu) && !(gpte & PT_GUEST_ACCESSED_MASK))
+ if (PT_HAVE_ACCESSED_DIRTY(vcpu->arch.mmu) &&
+ !(gpte & PT_GUEST_ACCESSED_MASK))
goto no_present;
return false;
@@ -480,7 +481,7 @@ error:
static int FNAME(walk_addr)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, gva_t addr, u32 access)
{
- return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.mmu, addr,
+ return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
access);
}
@@ -509,7 +510,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access & FNAME(gpte_access)(gpte);
- FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
no_dirty_log && (pte_access & ACC_WRITE_MASK));
if (is_error_pfn(pfn))
@@ -604,7 +605,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
direct_access = gw->pte_access;
- top_level = vcpu->arch.mmu.root_level;
+ top_level = vcpu->arch.mmu->root_level;
if (top_level == PT32E_ROOT_LEVEL)
top_level = PT32_ROOT_LEVEL;
/*
@@ -616,7 +617,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
if (FNAME(gpte_changed)(vcpu, gw, top_level))
goto out_gpte_changed;
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
goto out_gpte_changed;
for (shadow_walk_init(&it, vcpu, addr);
@@ -1004,7 +1005,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access;
pte_access &= FNAME(gpte_access)(gpte);
- FNAME(protect_clean_gpte)(&vcpu->arch.mmu, &pte_access, gpte);
+ FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte);
if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access,
&nr_present))
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d96092b35936..f416f5c7f2ae 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -805,6 +805,8 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu)
nested_svm_check_exception(svm, nr, has_error_code, error_code))
return;
+ kvm_deliver_exception_payload(&svm->vcpu);
+
if (nr == BP_VECTOR && !static_cpu_has(X86_FEATURE_NRIPS)) {
unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
@@ -2918,18 +2920,18 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
{
WARN_ON(mmu_is_nested(vcpu));
kvm_init_shadow_mmu(vcpu);
- vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3;
- vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3;
- vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr;
- vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
- vcpu->arch.mmu.shadow_root_level = get_npt_level(vcpu);
- reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
+ vcpu->arch.mmu->set_cr3 = nested_svm_set_tdp_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_svm_get_tdp_cr3;
+ vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr;
+ vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
+ vcpu->arch.mmu->shadow_root_level = get_npt_level(vcpu);
+ reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu);
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
}
static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static int nested_svm_check_permissions(struct vcpu_svm *svm)
@@ -2965,16 +2967,13 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
svm->vmcb->control.exit_info_1 = error_code;
/*
- * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception.
- * The fix is to add the ancillary datum (CR2 or DR6) to structs
- * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be
- * written only when inject_pending_event runs (DR6 would written here
- * too). This should be conditional on a new capability---if the
- * capability is disabled, kvm_multiple_exception would write the
- * ancillary information to CR2 or DR6, for backwards ABI-compatibility.
+ * EXITINFO2 is undefined for all exception intercepts other
+ * than #PF.
*/
if (svm->vcpu.arch.exception.nested_apf)
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
+ else if (svm->vcpu.arch.exception.has_payload)
+ svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
else
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
@@ -5638,26 +5637,24 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r13, %c[r13](%[svm]) \n\t"
"mov %%r14, %c[r14](%[svm]) \n\t"
"mov %%r15, %c[r15](%[svm]) \n\t"
-#endif
/*
* Clear host registers marked as clobbered to prevent
* speculative use.
*/
- "xor %%" _ASM_BX ", %%" _ASM_BX " \n\t"
- "xor %%" _ASM_CX ", %%" _ASM_CX " \n\t"
- "xor %%" _ASM_DX ", %%" _ASM_DX " \n\t"
- "xor %%" _ASM_SI ", %%" _ASM_SI " \n\t"
- "xor %%" _ASM_DI ", %%" _ASM_DI " \n\t"
-#ifdef CONFIG_X86_64
- "xor %%r8, %%r8 \n\t"
- "xor %%r9, %%r9 \n\t"
- "xor %%r10, %%r10 \n\t"
- "xor %%r11, %%r11 \n\t"
- "xor %%r12, %%r12 \n\t"
- "xor %%r13, %%r13 \n\t"
- "xor %%r14, %%r14 \n\t"
- "xor %%r15, %%r15 \n\t"
+ "xor %%r8d, %%r8d \n\t"
+ "xor %%r9d, %%r9d \n\t"
+ "xor %%r10d, %%r10d \n\t"
+ "xor %%r11d, %%r11d \n\t"
+ "xor %%r12d, %%r12d \n\t"
+ "xor %%r13d, %%r13d \n\t"
+ "xor %%r14d, %%r14d \n\t"
+ "xor %%r15d, %%r15d \n\t"
#endif
+ "xor %%ebx, %%ebx \n\t"
+ "xor %%ecx, %%ecx \n\t"
+ "xor %%edx, %%edx \n\t"
+ "xor %%esi, %%esi \n\t"
+ "xor %%edi, %%edi \n\t"
"pop %%" _ASM_BP
:
: [svm]"a"(svm),
@@ -7036,6 +7033,13 @@ failed:
return ret;
}
+static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version)
+{
+ /* Intel-only feature */
+ return -ENODEV;
+}
+
static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
@@ -7165,6 +7169,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.mem_enc_op = svm_mem_enc_op,
.mem_enc_reg_region = svm_register_enc_region,
.mem_enc_unreg_region = svm_unregister_enc_region,
+
+ .nested_enable_evmcs = nested_enable_evmcs,
};
static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 0f997683404f..0659465a745c 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1418,6 +1418,48 @@ TRACE_EVENT(kvm_hv_flush_tlb_ex,
__entry->valid_bank_mask, __entry->format,
__entry->address_space, __entry->flags)
);
+
+/*
+ * Tracepoints for kvm_hv_send_ipi.
+ */
+TRACE_EVENT(kvm_hv_send_ipi,
+ TP_PROTO(u32 vector, u64 processor_mask),
+ TP_ARGS(vector, processor_mask),
+
+ TP_STRUCT__entry(
+ __field(u32, vector)
+ __field(u64, processor_mask)
+ ),
+
+ TP_fast_assign(
+ __entry->vector = vector;
+ __entry->processor_mask = processor_mask;
+ ),
+
+ TP_printk("vector %x processor_mask 0x%llx",
+ __entry->vector, __entry->processor_mask)
+);
+
+TRACE_EVENT(kvm_hv_send_ipi_ex,
+ TP_PROTO(u32 vector, u64 format, u64 valid_bank_mask),
+ TP_ARGS(vector, format, valid_bank_mask),
+
+ TP_STRUCT__entry(
+ __field(u32, vector)
+ __field(u64, format)
+ __field(u64, valid_bank_mask)
+ ),
+
+ TP_fast_assign(
+ __entry->vector = vector;
+ __entry->format = format;
+ __entry->valid_bank_mask = valid_bank_mask;
+ ),
+
+ TP_printk("vector %x format %llx valid_bank_mask 0x%llx",
+ __entry->vector, __entry->format,
+ __entry->valid_bank_mask)
+);
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 612fd17be635..641a65b30685 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -20,6 +20,7 @@
#include "mmu.h"
#include "cpuid.h"
#include "lapic.h"
+#include "hyperv.h"
#include <linux/kvm_host.h>
#include <linux/module.h>
@@ -61,7 +62,7 @@
#define __ex(x) __kvm_handle_fault_on_reboot(x)
#define __ex_clear(x, reg) \
- ____kvm_handle_fault_on_reboot(x, "xor " reg " , " reg)
+ ____kvm_handle_fault_on_reboot(x, "xor " reg ", " reg)
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -107,9 +108,12 @@ module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
* VMX and be a hypervisor for its own guests. If nested=0, guests may not
* use VMX instructions.
*/
-static bool __read_mostly nested = 0;
+static bool __read_mostly nested = 1;
module_param(nested, bool, S_IRUGO);
+static bool __read_mostly nested_early_check = 0;
+module_param(nested_early_check, bool, S_IRUGO);
+
static u64 __read_mostly host_xss;
static bool __read_mostly enable_pml = 1;
@@ -131,7 +135,7 @@ static bool __read_mostly enable_preemption_timer = 1;
module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
#endif
-#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
+#define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE
#define KVM_VM_CR0_ALWAYS_ON \
(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \
@@ -187,6 +191,7 @@ static unsigned int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
module_param(ple_window_max, uint, 0444);
extern const ulong vmx_return;
+extern const ulong vmx_early_consistency_check_return;
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
@@ -827,14 +832,28 @@ struct nested_vmx {
*/
struct vmcs12 *cached_shadow_vmcs12;
/*
- * Indicates if the shadow vmcs must be updated with the
- * data hold by vmcs12
+ * Indicates if the shadow vmcs or enlightened vmcs must be updated
+ * with the data held by struct vmcs12.
*/
- bool sync_shadow_vmcs;
+ bool need_vmcs12_sync;
bool dirty_vmcs12;
+ /*
+ * vmcs02 has been initialized, i.e. state that is constant for
+ * vmcs02 has been written to the backing VMCS. Initialization
+ * is delayed until L1 actually attempts to run a nested VM.
+ */
+ bool vmcs02_initialized;
+
bool change_vmcs01_virtual_apic_mode;
+ /*
+ * Enlightened VMCS has been enabled. It does not mean that L1 has to
+ * use it. However, VMX features available to L1 will be limited based
+ * on what the enlightened VMCS supports.
+ */
+ bool enlightened_vmcs_enabled;
+
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
@@ -870,6 +889,10 @@ struct nested_vmx {
/* in guest mode on SMM entry? */
bool guest_mode;
} smm;
+
+ gpa_t hv_evmcs_vmptr;
+ struct page *hv_evmcs_page;
+ struct hv_enlightened_vmcs *hv_evmcs;
};
#define POSTED_INTR_ON 0
@@ -1381,6 +1404,49 @@ DEFINE_STATIC_KEY_FALSE(enable_evmcs);
#define KVM_EVMCS_VERSION 1
+/*
+ * Enlightened VMCSv1 doesn't support these:
+ *
+ * POSTED_INTR_NV = 0x00000002,
+ * GUEST_INTR_STATUS = 0x00000810,
+ * APIC_ACCESS_ADDR = 0x00002014,
+ * POSTED_INTR_DESC_ADDR = 0x00002016,
+ * EOI_EXIT_BITMAP0 = 0x0000201c,
+ * EOI_EXIT_BITMAP1 = 0x0000201e,
+ * EOI_EXIT_BITMAP2 = 0x00002020,
+ * EOI_EXIT_BITMAP3 = 0x00002022,
+ * GUEST_PML_INDEX = 0x00000812,
+ * PML_ADDRESS = 0x0000200e,
+ * VM_FUNCTION_CONTROL = 0x00002018,
+ * EPTP_LIST_ADDRESS = 0x00002024,
+ * VMREAD_BITMAP = 0x00002026,
+ * VMWRITE_BITMAP = 0x00002028,
+ *
+ * TSC_MULTIPLIER = 0x00002032,
+ * PLE_GAP = 0x00004020,
+ * PLE_WINDOW = 0x00004022,
+ * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
+ * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
+ * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
+ *
+ * Currently unsupported in KVM:
+ * GUEST_IA32_RTIT_CTL = 0x00002814,
+ */
+#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \
+ PIN_BASED_VMX_PREEMPTION_TIMER)
+#define EVMCS1_UNSUPPORTED_2NDEXEC \
+ (SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \
+ SECONDARY_EXEC_APIC_REGISTER_VIRT | \
+ SECONDARY_EXEC_ENABLE_PML | \
+ SECONDARY_EXEC_ENABLE_VMFUNC | \
+ SECONDARY_EXEC_SHADOW_VMCS | \
+ SECONDARY_EXEC_TSC_SCALING | \
+ SECONDARY_EXEC_PAUSE_LOOP_EXITING)
+#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)
+
#if IS_ENABLED(CONFIG_HYPERV)
static bool __read_mostly enlightened_vmcs = true;
module_param(enlightened_vmcs, bool, 0444);
@@ -1473,69 +1539,12 @@ static void evmcs_load(u64 phys_addr)
static void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
{
- /*
- * Enlightened VMCSv1 doesn't support these:
- *
- * POSTED_INTR_NV = 0x00000002,
- * GUEST_INTR_STATUS = 0x00000810,
- * APIC_ACCESS_ADDR = 0x00002014,
- * POSTED_INTR_DESC_ADDR = 0x00002016,
- * EOI_EXIT_BITMAP0 = 0x0000201c,
- * EOI_EXIT_BITMAP1 = 0x0000201e,
- * EOI_EXIT_BITMAP2 = 0x00002020,
- * EOI_EXIT_BITMAP3 = 0x00002022,
- */
- vmcs_conf->pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
- vmcs_conf->cpu_based_2nd_exec_ctrl &=
- ~SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
- vmcs_conf->cpu_based_2nd_exec_ctrl &=
- ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmcs_conf->cpu_based_2nd_exec_ctrl &=
- ~SECONDARY_EXEC_APIC_REGISTER_VIRT;
-
- /*
- * GUEST_PML_INDEX = 0x00000812,
- * PML_ADDRESS = 0x0000200e,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_ENABLE_PML;
-
- /* VM_FUNCTION_CONTROL = 0x00002018, */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_ENABLE_VMFUNC;
-
- /*
- * EPTP_LIST_ADDRESS = 0x00002024,
- * VMREAD_BITMAP = 0x00002026,
- * VMWRITE_BITMAP = 0x00002028,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_SHADOW_VMCS;
-
- /*
- * TSC_MULTIPLIER = 0x00002032,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_TSC_SCALING;
+ vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
- /*
- * PLE_GAP = 0x00004020,
- * PLE_WINDOW = 0x00004022,
- */
- vmcs_conf->cpu_based_2nd_exec_ctrl &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
-
- /*
- * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
- */
- vmcs_conf->pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
-
- /*
- * GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
- * HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
- */
- vmcs_conf->vmexit_ctrl &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
- vmcs_conf->vmentry_ctrl &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
- /*
- * Currently unsupported in KVM:
- * GUEST_IA32_RTIT_CTL = 0x00002814,
- */
}
/* check_ept_pointer() should be under protection of ept_pointer_lock. */
@@ -1560,7 +1569,8 @@ static void check_ept_pointer_match(struct kvm *kvm)
static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
{
- int ret;
+ struct kvm_vcpu *vcpu;
+ int ret = -ENOTSUPP, i;
spin_lock(&to_kvm_vmx(kvm)->ept_pointer_lock);
@@ -1568,14 +1578,14 @@ static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
check_ept_pointer_match(kvm);
if (to_kvm_vmx(kvm)->ept_pointers_match != EPT_POINTERS_MATCH) {
- ret = -ENOTSUPP;
- goto out;
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ ret |= hyperv_flush_guest_mapping(
+ to_vmx(kvm_get_vcpu(kvm, i))->ept_pointer);
+ } else {
+ ret = hyperv_flush_guest_mapping(
+ to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer);
}
- ret = hyperv_flush_guest_mapping(
- to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer);
-
-out:
spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
return ret;
}
@@ -1591,6 +1601,35 @@ static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
static inline void evmcs_touch_msr_bitmap(void) {}
#endif /* IS_ENABLED(CONFIG_HYPERV) */
+static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
+ uint16_t *vmcs_version)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /* We don't support disabling the feature for simplicity. */
+ if (vmx->nested.enlightened_vmcs_enabled)
+ return 0;
+
+ vmx->nested.enlightened_vmcs_enabled = true;
+
+ /*
+ * vmcs_version represents the range of supported Enlightened VMCS
+ * versions: lower 8 bits is the minimal version, higher 8 bits is the
+ * maximum supported version. KVM supports versions from 1 to
+ * KVM_EVMCS_VERSION.
+ */
+ if (vmcs_version)
+ *vmcs_version = (KVM_EVMCS_VERSION << 8) | 1;
+
+ vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
+ vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
+ vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
+ vmx->nested.msrs.secondary_ctls_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
+ vmx->nested.msrs.vmfunc_controls &= ~EVMCS1_UNSUPPORTED_VMFUNC;
+
+ return 0;
+}
+
static inline bool is_exception_n(u32 intr_info, u8 vector)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
@@ -1613,11 +1652,6 @@ static inline bool is_page_fault(u32 intr_info)
return is_exception_n(intr_info, PF_VECTOR);
}
-static inline bool is_no_device(u32 intr_info)
-{
- return is_exception_n(intr_info, NM_VECTOR);
-}
-
static inline bool is_invalid_opcode(u32 intr_info)
{
return is_exception_n(intr_info, UD_VECTOR);
@@ -1628,12 +1662,6 @@ static inline bool is_gp_fault(u32 intr_info)
return is_exception_n(intr_info, GP_VECTOR);
}
-static inline bool is_external_interrupt(u32 intr_info)
-{
- return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
- == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
-}
-
static inline bool is_machine_check(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
@@ -2059,9 +2087,6 @@ static inline bool is_nmi(u32 intr_info)
static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
u32 exit_intr_info,
unsigned long exit_qualification);
-static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12,
- u32 reason, unsigned long qualification);
static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
{
@@ -2073,7 +2098,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
return -1;
}
-static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva)
{
struct {
u64 vpid : 16;
@@ -2082,22 +2107,20 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva)
} operand = { vpid, 0, gva };
bool error;
- asm volatile (__ex(ASM_VMX_INVVPID) CC_SET(na)
- : CC_OUT(na) (error) : "a"(&operand), "c"(ext)
- : "memory");
+ asm volatile (__ex("invvpid %2, %1") CC_SET(na)
+ : CC_OUT(na) (error) : "r"(ext), "m"(operand));
BUG_ON(error);
}
-static inline void __invept(int ext, u64 eptp, gpa_t gpa)
+static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa)
{
struct {
u64 eptp, gpa;
} operand = {eptp, gpa};
bool error;
- asm volatile (__ex(ASM_VMX_INVEPT) CC_SET(na)
- : CC_OUT(na) (error) : "a" (&operand), "c" (ext)
- : "memory");
+ asm volatile (__ex("invept %2, %1") CC_SET(na)
+ : CC_OUT(na) (error) : "r"(ext), "m"(operand));
BUG_ON(error);
}
@@ -2116,9 +2139,8 @@ static void vmcs_clear(struct vmcs *vmcs)
u64 phys_addr = __pa(vmcs);
bool error;
- asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) CC_SET(na)
- : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr)
- : "memory");
+ asm volatile (__ex("vmclear %1") CC_SET(na)
+ : CC_OUT(na) (error) : "m"(phys_addr));
if (unlikely(error))
printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
vmcs, phys_addr);
@@ -2141,9 +2163,8 @@ static void vmcs_load(struct vmcs *vmcs)
if (static_branch_unlikely(&enable_evmcs))
return evmcs_load(phys_addr);
- asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) CC_SET(na)
- : CC_OUT(na) (error) : "a"(&phys_addr), "m"(phys_addr)
- : "memory");
+ asm volatile (__ex("vmptrld %1") CC_SET(na)
+ : CC_OUT(na) (error) : "m"(phys_addr));
if (unlikely(error))
printk(KERN_ERR "kvm: vmptrld %p/%llx failed\n",
vmcs, phys_addr);
@@ -2319,8 +2340,8 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field)
{
unsigned long value;
- asm volatile (__ex_clear(ASM_VMX_VMREAD_RDX_RAX, "%0")
- : "=a"(value) : "d"(field) : "cc");
+ asm volatile (__ex_clear("vmread %1, %0", "%k0")
+ : "=r"(value) : "r"(field));
return value;
}
@@ -2371,8 +2392,8 @@ static __always_inline void __vmcs_writel(unsigned long field, unsigned long val
{
bool error;
- asm volatile (__ex(ASM_VMX_VMWRITE_RAX_RDX) CC_SET(na)
- : CC_OUT(na) (error) : "a"(value), "d"(field));
+ asm volatile (__ex("vmwrite %2, %1") CC_SET(na)
+ : CC_OUT(na) (error) : "r"(field), "rm"(value));
if (unlikely(error))
vmwrite_error(field, value);
}
@@ -2703,7 +2724,8 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
u64 guest_val, u64 host_val)
{
vmcs_write64(guest_val_vmcs, guest_val);
- vmcs_write64(host_val_vmcs, host_val);
+ if (host_val_vmcs != HOST_IA32_EFER)
+ vmcs_write64(host_val_vmcs, host_val);
vm_entry_controls_setbit(vmx, entry);
vm_exit_controls_setbit(vmx, exit);
}
@@ -2801,8 +2823,6 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
ignore_bits &= ~(u64)EFER_SCE;
#endif
- clear_atomic_switch_msr(vmx, MSR_EFER);
-
/*
* On EPT, we can't emulate NX, so we must switch EFER atomically.
* On CPUs that support "load IA32_EFER", always switch EFER
@@ -2815,8 +2835,12 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
if (guest_efer != host_efer)
add_atomic_switch_msr(vmx, MSR_EFER,
guest_efer, host_efer, false);
+ else
+ clear_atomic_switch_msr(vmx, MSR_EFER);
return false;
} else {
+ clear_atomic_switch_msr(vmx, MSR_EFER);
+
guest_efer &= ~ignore_bits;
guest_efer |= host_efer & ignore_bits;
@@ -3268,34 +3292,30 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
unsigned int nr = vcpu->arch.exception.nr;
+ bool has_payload = vcpu->arch.exception.has_payload;
+ unsigned long payload = vcpu->arch.exception.payload;
if (nr == PF_VECTOR) {
if (vcpu->arch.exception.nested_apf) {
*exit_qual = vcpu->arch.apf.nested_apf_token;
return 1;
}
- /*
- * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
- * The fix is to add the ancillary datum (CR2 or DR6) to structs
- * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
- * can be written only when inject_pending_event runs. This should be
- * conditional on a new capability---if the capability is disabled,
- * kvm_multiple_exception would write the ancillary information to
- * CR2 or DR6, for backwards ABI-compatibility.
- */
if (nested_vmx_is_page_fault_vmexit(vmcs12,
vcpu->arch.exception.error_code)) {
- *exit_qual = vcpu->arch.cr2;
- return 1;
- }
- } else {
- if (vmcs12->exception_bitmap & (1u << nr)) {
- if (nr == DB_VECTOR)
- *exit_qual = vcpu->arch.dr6;
- else
- *exit_qual = 0;
+ *exit_qual = has_payload ? payload : vcpu->arch.cr2;
return 1;
}
+ } else if (vmcs12->exception_bitmap & (1u << nr)) {
+ if (nr == DB_VECTOR) {
+ if (!has_payload) {
+ payload = vcpu->arch.dr6;
+ payload &= ~(DR6_FIXED_1 | DR6_BT);
+ payload ^= DR6_RTM;
+ }
+ *exit_qual = payload;
+ } else
+ *exit_qual = 0;
+ return 1;
}
return 0;
@@ -3322,6 +3342,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
u32 error_code = vcpu->arch.exception.error_code;
u32 intr_info = nr | INTR_INFO_VALID_MASK;
+ kvm_deliver_exception_payload(vcpu);
+
if (has_error_code) {
vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
intr_info |= INTR_INFO_DELIVER_CODE_MASK;
@@ -4393,9 +4415,7 @@ static void kvm_cpu_vmxon(u64 addr)
cr4_set_bits(X86_CR4_VMXE);
intel_pt_handle_vmx(1);
- asm volatile (ASM_VMX_VMXON_RAX
- : : "a"(&addr), "m"(addr)
- : "memory", "cc");
+ asm volatile ("vmxon %0" : : "m"(addr));
}
static int hardware_enable(void)
@@ -4464,7 +4484,7 @@ static void vmclear_local_loaded_vmcss(void)
*/
static void kvm_cpu_vmxoff(void)
{
- asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
+ asm volatile (__ex("vmxoff"));
intel_pt_handle_vmx(0);
cr4_clear_bits(X86_CR4_VMXE);
@@ -5108,9 +5128,10 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid,
bool invalidate_gpa)
{
if (enable_ept && (invalidate_gpa || !enable_vpid)) {
- if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
return;
- ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa));
+ ept_sync_context(construct_eptp(vcpu,
+ vcpu->arch.mmu->root_hpa));
} else {
vpid_sync_context(vpid);
}
@@ -5260,7 +5281,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long hw_cr0;
- hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK);
+ hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF);
if (enable_unrestricted_guest)
hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
else {
@@ -6335,6 +6356,9 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
rdmsr(MSR_IA32_CR_PAT, low32, high32);
vmcs_write64(HOST_IA32_PAT, low32 | ((u64) high32 << 32));
}
+
+ if (cpu_has_load_ia32_efer)
+ vmcs_write64(HOST_IA32_EFER, host_efer);
}
static void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
@@ -6662,7 +6686,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
if (enable_pml) {
- ASSERT(vmx->pml_pg);
vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
}
@@ -8063,35 +8086,39 @@ static int handle_monitor(struct kvm_vcpu *vcpu)
/*
* The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
+ * set the success or error code of an emulated VMX instruction (as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
+ * instruction.
*/
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
+static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
{
vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+ return kvm_skip_emulated_instruction(vcpu);
}
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
{
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
| X86_EFLAGS_CF);
+ return kvm_skip_emulated_instruction(vcpu);
}
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
- u32 vm_instruction_error)
+static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
+ u32 vm_instruction_error)
{
- if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
- /*
- * failValid writes the error number to the current VMCS, which
- * can't be done there isn't a current VMCS.
- */
- nested_vmx_failInvalid(vcpu);
- return;
- }
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * failValid writes the error number to the current VMCS, which
+ * can't be done if there isn't a current VMCS.
+ */
+ if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
+ return nested_vmx_failInvalid(vcpu);
+
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
@@ -8101,6 +8128,7 @@ static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
* We don't need to force a shadow sync because
* VM_INSTRUCTION_ERROR is not shadowed
*/
+ return kvm_skip_emulated_instruction(vcpu);
}
static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
@@ -8288,6 +8316,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
vmx->nested.vpid02 = allocate_vpid();
+ vmx->nested.vmcs02_initialized = false;
vmx->nested.vmxon = true;
return 0;
@@ -8341,10 +8370,9 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
return 1;
}
- if (vmx->nested.vmxon) {
- nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmx->nested.vmxon)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
!= VMXON_NEEDED_FEATURES) {
@@ -8363,21 +8391,17 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
* Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
* which replaces physical address width with 32
*/
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failInvalid(vcpu);
page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
- if (is_error_page(page)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (is_error_page(page))
+ return nested_vmx_failInvalid(vcpu);
+
if (*(u32 *)kmap(page) != VMCS12_REVISION) {
kunmap(page);
kvm_release_page_clean(page);
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_failInvalid(vcpu);
}
kunmap(page);
kvm_release_page_clean(page);
@@ -8387,8 +8411,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
if (ret)
return ret;
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/*
@@ -8419,8 +8442,24 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
vmcs_write64(VMCS_LINK_POINTER, -1ull);
}
-static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
+static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (!vmx->nested.hv_evmcs)
+ return;
+
+ kunmap(vmx->nested.hv_evmcs_page);
+ kvm_release_page_dirty(vmx->nested.hv_evmcs_page);
+ vmx->nested.hv_evmcs_vmptr = -1ull;
+ vmx->nested.hv_evmcs_page = NULL;
+ vmx->nested.hv_evmcs = NULL;
+}
+
+static inline void nested_release_vmcs12(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (vmx->nested.current_vmptr == -1ull)
return;
@@ -8428,16 +8467,18 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
/* copy to memory all shadowed fields in case
they were modified */
copy_shadow_to_vmcs12(vmx);
- vmx->nested.sync_shadow_vmcs = false;
+ vmx->nested.need_vmcs12_sync = false;
vmx_disable_shadow_vmcs(vmx);
}
vmx->nested.posted_intr_nv = -1;
/* Flush VMCS12 to guest memory */
- kvm_vcpu_write_guest_page(&vmx->vcpu,
+ kvm_vcpu_write_guest_page(vcpu,
vmx->nested.current_vmptr >> PAGE_SHIFT,
vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
vmx->nested.current_vmptr = -1ull;
}
@@ -8445,8 +8486,10 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
* Free whatever needs to be freed from vmx->nested when L1 goes down, or
* just stops using VMX.
*/
-static void free_nested(struct vcpu_vmx *vmx)
+static void free_nested(struct kvm_vcpu *vcpu)
{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
@@ -8479,6 +8522,10 @@ static void free_nested(struct vcpu_vmx *vmx)
vmx->nested.pi_desc = NULL;
}
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
+ nested_release_evmcs(vcpu);
+
free_loaded_vmcs(&vmx->nested.vmcs02);
}
@@ -8487,9 +8534,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
{
if (!nested_vmx_check_permission(vcpu))
return 1;
- free_nested(to_vmx(vcpu));
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ free_nested(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the VMCLEAR instruction */
@@ -8505,25 +8551,28 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMCLEAR_INVALID_ADDRESS);
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmptr == vmx->nested.vmxon_ptr)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMCLEAR_VMXON_POINTER);
- if (vmptr == vmx->nested.current_vmptr)
- nested_release_vmcs12(vmx);
+ if (vmx->nested.hv_evmcs_page) {
+ if (vmptr == vmx->nested.hv_evmcs_vmptr)
+ nested_release_evmcs(vcpu);
+ } else {
+ if (vmptr == vmx->nested.current_vmptr)
+ nested_release_vmcs12(vcpu);
- kvm_vcpu_write_guest(vcpu,
- vmptr + offsetof(struct vmcs12, launch_state),
- &zero, sizeof(zero));
+ kvm_vcpu_write_guest(vcpu,
+ vmptr + offsetof(struct vmcs12,
+ launch_state),
+ &zero, sizeof(zero));
+ }
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
@@ -8606,6 +8655,395 @@ static inline int vmcs12_write_any(struct vmcs12 *vmcs12,
}
+static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
+{
+ struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
+ struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+ vmcs12->hdr.revision_id = evmcs->revision_id;
+
+ /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
+ vmcs12->tpr_threshold = evmcs->tpr_threshold;
+ vmcs12->guest_rip = evmcs->guest_rip;
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
+ vmcs12->guest_rsp = evmcs->guest_rsp;
+ vmcs12->guest_rflags = evmcs->guest_rflags;
+ vmcs12->guest_interruptibility_info =
+ evmcs->guest_interruptibility_info;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
+ vmcs12->cpu_based_vm_exec_control =
+ evmcs->cpu_based_vm_exec_control;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
+ vmcs12->exception_bitmap = evmcs->exception_bitmap;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) {
+ vmcs12->vm_entry_controls = evmcs->vm_entry_controls;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) {
+ vmcs12->vm_entry_intr_info_field =
+ evmcs->vm_entry_intr_info_field;
+ vmcs12->vm_entry_exception_error_code =
+ evmcs->vm_entry_exception_error_code;
+ vmcs12->vm_entry_instruction_len =
+ evmcs->vm_entry_instruction_len;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
+ vmcs12->host_ia32_pat = evmcs->host_ia32_pat;
+ vmcs12->host_ia32_efer = evmcs->host_ia32_efer;
+ vmcs12->host_cr0 = evmcs->host_cr0;
+ vmcs12->host_cr3 = evmcs->host_cr3;
+ vmcs12->host_cr4 = evmcs->host_cr4;
+ vmcs12->host_ia32_sysenter_esp = evmcs->host_ia32_sysenter_esp;
+ vmcs12->host_ia32_sysenter_eip = evmcs->host_ia32_sysenter_eip;
+ vmcs12->host_rip = evmcs->host_rip;
+ vmcs12->host_ia32_sysenter_cs = evmcs->host_ia32_sysenter_cs;
+ vmcs12->host_es_selector = evmcs->host_es_selector;
+ vmcs12->host_cs_selector = evmcs->host_cs_selector;
+ vmcs12->host_ss_selector = evmcs->host_ss_selector;
+ vmcs12->host_ds_selector = evmcs->host_ds_selector;
+ vmcs12->host_fs_selector = evmcs->host_fs_selector;
+ vmcs12->host_gs_selector = evmcs->host_gs_selector;
+ vmcs12->host_tr_selector = evmcs->host_tr_selector;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
+ vmcs12->pin_based_vm_exec_control =
+ evmcs->pin_based_vm_exec_control;
+ vmcs12->vm_exit_controls = evmcs->vm_exit_controls;
+ vmcs12->secondary_vm_exec_control =
+ evmcs->secondary_vm_exec_control;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) {
+ vmcs12->io_bitmap_a = evmcs->io_bitmap_a;
+ vmcs12->io_bitmap_b = evmcs->io_bitmap_b;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) {
+ vmcs12->msr_bitmap = evmcs->msr_bitmap;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) {
+ vmcs12->guest_es_base = evmcs->guest_es_base;
+ vmcs12->guest_cs_base = evmcs->guest_cs_base;
+ vmcs12->guest_ss_base = evmcs->guest_ss_base;
+ vmcs12->guest_ds_base = evmcs->guest_ds_base;
+ vmcs12->guest_fs_base = evmcs->guest_fs_base;
+ vmcs12->guest_gs_base = evmcs->guest_gs_base;
+ vmcs12->guest_ldtr_base = evmcs->guest_ldtr_base;
+ vmcs12->guest_tr_base = evmcs->guest_tr_base;
+ vmcs12->guest_gdtr_base = evmcs->guest_gdtr_base;
+ vmcs12->guest_idtr_base = evmcs->guest_idtr_base;
+ vmcs12->guest_es_limit = evmcs->guest_es_limit;
+ vmcs12->guest_cs_limit = evmcs->guest_cs_limit;
+ vmcs12->guest_ss_limit = evmcs->guest_ss_limit;
+ vmcs12->guest_ds_limit = evmcs->guest_ds_limit;
+ vmcs12->guest_fs_limit = evmcs->guest_fs_limit;
+ vmcs12->guest_gs_limit = evmcs->guest_gs_limit;
+ vmcs12->guest_ldtr_limit = evmcs->guest_ldtr_limit;
+ vmcs12->guest_tr_limit = evmcs->guest_tr_limit;
+ vmcs12->guest_gdtr_limit = evmcs->guest_gdtr_limit;
+ vmcs12->guest_idtr_limit = evmcs->guest_idtr_limit;
+ vmcs12->guest_es_ar_bytes = evmcs->guest_es_ar_bytes;
+ vmcs12->guest_cs_ar_bytes = evmcs->guest_cs_ar_bytes;
+ vmcs12->guest_ss_ar_bytes = evmcs->guest_ss_ar_bytes;
+ vmcs12->guest_ds_ar_bytes = evmcs->guest_ds_ar_bytes;
+ vmcs12->guest_fs_ar_bytes = evmcs->guest_fs_ar_bytes;
+ vmcs12->guest_gs_ar_bytes = evmcs->guest_gs_ar_bytes;
+ vmcs12->guest_ldtr_ar_bytes = evmcs->guest_ldtr_ar_bytes;
+ vmcs12->guest_tr_ar_bytes = evmcs->guest_tr_ar_bytes;
+ vmcs12->guest_es_selector = evmcs->guest_es_selector;
+ vmcs12->guest_cs_selector = evmcs->guest_cs_selector;
+ vmcs12->guest_ss_selector = evmcs->guest_ss_selector;
+ vmcs12->guest_ds_selector = evmcs->guest_ds_selector;
+ vmcs12->guest_fs_selector = evmcs->guest_fs_selector;
+ vmcs12->guest_gs_selector = evmcs->guest_gs_selector;
+ vmcs12->guest_ldtr_selector = evmcs->guest_ldtr_selector;
+ vmcs12->guest_tr_selector = evmcs->guest_tr_selector;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) {
+ vmcs12->tsc_offset = evmcs->tsc_offset;
+ vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
+ vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) {
+ vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask;
+ vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask;
+ vmcs12->cr0_read_shadow = evmcs->cr0_read_shadow;
+ vmcs12->cr4_read_shadow = evmcs->cr4_read_shadow;
+ vmcs12->guest_cr0 = evmcs->guest_cr0;
+ vmcs12->guest_cr3 = evmcs->guest_cr3;
+ vmcs12->guest_cr4 = evmcs->guest_cr4;
+ vmcs12->guest_dr7 = evmcs->guest_dr7;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) {
+ vmcs12->host_fs_base = evmcs->host_fs_base;
+ vmcs12->host_gs_base = evmcs->host_gs_base;
+ vmcs12->host_tr_base = evmcs->host_tr_base;
+ vmcs12->host_gdtr_base = evmcs->host_gdtr_base;
+ vmcs12->host_idtr_base = evmcs->host_idtr_base;
+ vmcs12->host_rsp = evmcs->host_rsp;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) {
+ vmcs12->ept_pointer = evmcs->ept_pointer;
+ vmcs12->virtual_processor_id = evmcs->virtual_processor_id;
+ }
+
+ if (unlikely(!(evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) {
+ vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer;
+ vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl;
+ vmcs12->guest_ia32_pat = evmcs->guest_ia32_pat;
+ vmcs12->guest_ia32_efer = evmcs->guest_ia32_efer;
+ vmcs12->guest_pdptr0 = evmcs->guest_pdptr0;
+ vmcs12->guest_pdptr1 = evmcs->guest_pdptr1;
+ vmcs12->guest_pdptr2 = evmcs->guest_pdptr2;
+ vmcs12->guest_pdptr3 = evmcs->guest_pdptr3;
+ vmcs12->guest_pending_dbg_exceptions =
+ evmcs->guest_pending_dbg_exceptions;
+ vmcs12->guest_sysenter_esp = evmcs->guest_sysenter_esp;
+ vmcs12->guest_sysenter_eip = evmcs->guest_sysenter_eip;
+ vmcs12->guest_bndcfgs = evmcs->guest_bndcfgs;
+ vmcs12->guest_activity_state = evmcs->guest_activity_state;
+ vmcs12->guest_sysenter_cs = evmcs->guest_sysenter_cs;
+ }
+
+ /*
+ * Not used?
+ * vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr;
+ * vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr;
+ * vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr;
+ * vmcs12->cr3_target_value0 = evmcs->cr3_target_value0;
+ * vmcs12->cr3_target_value1 = evmcs->cr3_target_value1;
+ * vmcs12->cr3_target_value2 = evmcs->cr3_target_value2;
+ * vmcs12->cr3_target_value3 = evmcs->cr3_target_value3;
+ * vmcs12->page_fault_error_code_mask =
+ * evmcs->page_fault_error_code_mask;
+ * vmcs12->page_fault_error_code_match =
+ * evmcs->page_fault_error_code_match;
+ * vmcs12->cr3_target_count = evmcs->cr3_target_count;
+ * vmcs12->vm_exit_msr_store_count = evmcs->vm_exit_msr_store_count;
+ * vmcs12->vm_exit_msr_load_count = evmcs->vm_exit_msr_load_count;
+ * vmcs12->vm_entry_msr_load_count = evmcs->vm_entry_msr_load_count;
+ */
+
+ /*
+ * Read only fields:
+ * vmcs12->guest_physical_address = evmcs->guest_physical_address;
+ * vmcs12->vm_instruction_error = evmcs->vm_instruction_error;
+ * vmcs12->vm_exit_reason = evmcs->vm_exit_reason;
+ * vmcs12->vm_exit_intr_info = evmcs->vm_exit_intr_info;
+ * vmcs12->vm_exit_intr_error_code = evmcs->vm_exit_intr_error_code;
+ * vmcs12->idt_vectoring_info_field = evmcs->idt_vectoring_info_field;
+ * vmcs12->idt_vectoring_error_code = evmcs->idt_vectoring_error_code;
+ * vmcs12->vm_exit_instruction_len = evmcs->vm_exit_instruction_len;
+ * vmcs12->vmx_instruction_info = evmcs->vmx_instruction_info;
+ * vmcs12->exit_qualification = evmcs->exit_qualification;
+ * vmcs12->guest_linear_address = evmcs->guest_linear_address;
+ *
+ * Not present in struct vmcs12:
+ * vmcs12->exit_io_instruction_ecx = evmcs->exit_io_instruction_ecx;
+ * vmcs12->exit_io_instruction_esi = evmcs->exit_io_instruction_esi;
+ * vmcs12->exit_io_instruction_edi = evmcs->exit_io_instruction_edi;
+ * vmcs12->exit_io_instruction_eip = evmcs->exit_io_instruction_eip;
+ */
+
+ return 0;
+}
+
+static int copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx)
+{
+ struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
+ struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+ /*
+ * Should not be changed by KVM:
+ *
+ * evmcs->host_es_selector = vmcs12->host_es_selector;
+ * evmcs->host_cs_selector = vmcs12->host_cs_selector;
+ * evmcs->host_ss_selector = vmcs12->host_ss_selector;
+ * evmcs->host_ds_selector = vmcs12->host_ds_selector;
+ * evmcs->host_fs_selector = vmcs12->host_fs_selector;
+ * evmcs->host_gs_selector = vmcs12->host_gs_selector;
+ * evmcs->host_tr_selector = vmcs12->host_tr_selector;
+ * evmcs->host_ia32_pat = vmcs12->host_ia32_pat;
+ * evmcs->host_ia32_efer = vmcs12->host_ia32_efer;
+ * evmcs->host_cr0 = vmcs12->host_cr0;
+ * evmcs->host_cr3 = vmcs12->host_cr3;
+ * evmcs->host_cr4 = vmcs12->host_cr4;
+ * evmcs->host_ia32_sysenter_esp = vmcs12->host_ia32_sysenter_esp;
+ * evmcs->host_ia32_sysenter_eip = vmcs12->host_ia32_sysenter_eip;
+ * evmcs->host_rip = vmcs12->host_rip;
+ * evmcs->host_ia32_sysenter_cs = vmcs12->host_ia32_sysenter_cs;
+ * evmcs->host_fs_base = vmcs12->host_fs_base;
+ * evmcs->host_gs_base = vmcs12->host_gs_base;
+ * evmcs->host_tr_base = vmcs12->host_tr_base;
+ * evmcs->host_gdtr_base = vmcs12->host_gdtr_base;
+ * evmcs->host_idtr_base = vmcs12->host_idtr_base;
+ * evmcs->host_rsp = vmcs12->host_rsp;
+ * sync_vmcs12() doesn't read these:
+ * evmcs->io_bitmap_a = vmcs12->io_bitmap_a;
+ * evmcs->io_bitmap_b = vmcs12->io_bitmap_b;
+ * evmcs->msr_bitmap = vmcs12->msr_bitmap;
+ * evmcs->ept_pointer = vmcs12->ept_pointer;
+ * evmcs->xss_exit_bitmap = vmcs12->xss_exit_bitmap;
+ * evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr;
+ * evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr;
+ * evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr;
+ * evmcs->cr3_target_value0 = vmcs12->cr3_target_value0;
+ * evmcs->cr3_target_value1 = vmcs12->cr3_target_value1;
+ * evmcs->cr3_target_value2 = vmcs12->cr3_target_value2;
+ * evmcs->cr3_target_value3 = vmcs12->cr3_target_value3;
+ * evmcs->tpr_threshold = vmcs12->tpr_threshold;
+ * evmcs->virtual_processor_id = vmcs12->virtual_processor_id;
+ * evmcs->exception_bitmap = vmcs12->exception_bitmap;
+ * evmcs->vmcs_link_pointer = vmcs12->vmcs_link_pointer;
+ * evmcs->pin_based_vm_exec_control = vmcs12->pin_based_vm_exec_control;
+ * evmcs->vm_exit_controls = vmcs12->vm_exit_controls;
+ * evmcs->secondary_vm_exec_control = vmcs12->secondary_vm_exec_control;
+ * evmcs->page_fault_error_code_mask =
+ * vmcs12->page_fault_error_code_mask;
+ * evmcs->page_fault_error_code_match =
+ * vmcs12->page_fault_error_code_match;
+ * evmcs->cr3_target_count = vmcs12->cr3_target_count;
+ * evmcs->virtual_apic_page_addr = vmcs12->virtual_apic_page_addr;
+ * evmcs->tsc_offset = vmcs12->tsc_offset;
+ * evmcs->guest_ia32_debugctl = vmcs12->guest_ia32_debugctl;
+ * evmcs->cr0_guest_host_mask = vmcs12->cr0_guest_host_mask;
+ * evmcs->cr4_guest_host_mask = vmcs12->cr4_guest_host_mask;
+ * evmcs->cr0_read_shadow = vmcs12->cr0_read_shadow;
+ * evmcs->cr4_read_shadow = vmcs12->cr4_read_shadow;
+ * evmcs->vm_exit_msr_store_count = vmcs12->vm_exit_msr_store_count;
+ * evmcs->vm_exit_msr_load_count = vmcs12->vm_exit_msr_load_count;
+ * evmcs->vm_entry_msr_load_count = vmcs12->vm_entry_msr_load_count;
+ *
+ * Not present in struct vmcs12:
+ * evmcs->exit_io_instruction_ecx = vmcs12->exit_io_instruction_ecx;
+ * evmcs->exit_io_instruction_esi = vmcs12->exit_io_instruction_esi;
+ * evmcs->exit_io_instruction_edi = vmcs12->exit_io_instruction_edi;
+ * evmcs->exit_io_instruction_eip = vmcs12->exit_io_instruction_eip;
+ */
+
+ evmcs->guest_es_selector = vmcs12->guest_es_selector;
+ evmcs->guest_cs_selector = vmcs12->guest_cs_selector;
+ evmcs->guest_ss_selector = vmcs12->guest_ss_selector;
+ evmcs->guest_ds_selector = vmcs12->guest_ds_selector;
+ evmcs->guest_fs_selector = vmcs12->guest_fs_selector;
+ evmcs->guest_gs_selector = vmcs12->guest_gs_selector;
+ evmcs->guest_ldtr_selector = vmcs12->guest_ldtr_selector;
+ evmcs->guest_tr_selector = vmcs12->guest_tr_selector;
+
+ evmcs->guest_es_limit = vmcs12->guest_es_limit;
+ evmcs->guest_cs_limit = vmcs12->guest_cs_limit;
+ evmcs->guest_ss_limit = vmcs12->guest_ss_limit;
+ evmcs->guest_ds_limit = vmcs12->guest_ds_limit;
+ evmcs->guest_fs_limit = vmcs12->guest_fs_limit;
+ evmcs->guest_gs_limit = vmcs12->guest_gs_limit;
+ evmcs->guest_ldtr_limit = vmcs12->guest_ldtr_limit;
+ evmcs->guest_tr_limit = vmcs12->guest_tr_limit;
+ evmcs->guest_gdtr_limit = vmcs12->guest_gdtr_limit;
+ evmcs->guest_idtr_limit = vmcs12->guest_idtr_limit;
+
+ evmcs->guest_es_ar_bytes = vmcs12->guest_es_ar_bytes;
+ evmcs->guest_cs_ar_bytes = vmcs12->guest_cs_ar_bytes;
+ evmcs->guest_ss_ar_bytes = vmcs12->guest_ss_ar_bytes;
+ evmcs->guest_ds_ar_bytes = vmcs12->guest_ds_ar_bytes;
+ evmcs->guest_fs_ar_bytes = vmcs12->guest_fs_ar_bytes;
+ evmcs->guest_gs_ar_bytes = vmcs12->guest_gs_ar_bytes;
+ evmcs->guest_ldtr_ar_bytes = vmcs12->guest_ldtr_ar_bytes;
+ evmcs->guest_tr_ar_bytes = vmcs12->guest_tr_ar_bytes;
+
+ evmcs->guest_es_base = vmcs12->guest_es_base;
+ evmcs->guest_cs_base = vmcs12->guest_cs_base;
+ evmcs->guest_ss_base = vmcs12->guest_ss_base;
+ evmcs->guest_ds_base = vmcs12->guest_ds_base;
+ evmcs->guest_fs_base = vmcs12->guest_fs_base;
+ evmcs->guest_gs_base = vmcs12->guest_gs_base;
+ evmcs->guest_ldtr_base = vmcs12->guest_ldtr_base;
+ evmcs->guest_tr_base = vmcs12->guest_tr_base;
+ evmcs->guest_gdtr_base = vmcs12->guest_gdtr_base;
+ evmcs->guest_idtr_base = vmcs12->guest_idtr_base;
+
+ evmcs->guest_ia32_pat = vmcs12->guest_ia32_pat;
+ evmcs->guest_ia32_efer = vmcs12->guest_ia32_efer;
+
+ evmcs->guest_pdptr0 = vmcs12->guest_pdptr0;
+ evmcs->guest_pdptr1 = vmcs12->guest_pdptr1;
+ evmcs->guest_pdptr2 = vmcs12->guest_pdptr2;
+ evmcs->guest_pdptr3 = vmcs12->guest_pdptr3;
+
+ evmcs->guest_pending_dbg_exceptions =
+ vmcs12->guest_pending_dbg_exceptions;
+ evmcs->guest_sysenter_esp = vmcs12->guest_sysenter_esp;
+ evmcs->guest_sysenter_eip = vmcs12->guest_sysenter_eip;
+
+ evmcs->guest_activity_state = vmcs12->guest_activity_state;
+ evmcs->guest_sysenter_cs = vmcs12->guest_sysenter_cs;
+
+ evmcs->guest_cr0 = vmcs12->guest_cr0;
+ evmcs->guest_cr3 = vmcs12->guest_cr3;
+ evmcs->guest_cr4 = vmcs12->guest_cr4;
+ evmcs->guest_dr7 = vmcs12->guest_dr7;
+
+ evmcs->guest_physical_address = vmcs12->guest_physical_address;
+
+ evmcs->vm_instruction_error = vmcs12->vm_instruction_error;
+ evmcs->vm_exit_reason = vmcs12->vm_exit_reason;
+ evmcs->vm_exit_intr_info = vmcs12->vm_exit_intr_info;
+ evmcs->vm_exit_intr_error_code = vmcs12->vm_exit_intr_error_code;
+ evmcs->idt_vectoring_info_field = vmcs12->idt_vectoring_info_field;
+ evmcs->idt_vectoring_error_code = vmcs12->idt_vectoring_error_code;
+ evmcs->vm_exit_instruction_len = vmcs12->vm_exit_instruction_len;
+ evmcs->vmx_instruction_info = vmcs12->vmx_instruction_info;
+
+ evmcs->exit_qualification = vmcs12->exit_qualification;
+
+ evmcs->guest_linear_address = vmcs12->guest_linear_address;
+ evmcs->guest_rsp = vmcs12->guest_rsp;
+ evmcs->guest_rflags = vmcs12->guest_rflags;
+
+ evmcs->guest_interruptibility_info =
+ vmcs12->guest_interruptibility_info;
+ evmcs->cpu_based_vm_exec_control = vmcs12->cpu_based_vm_exec_control;
+ evmcs->vm_entry_controls = vmcs12->vm_entry_controls;
+ evmcs->vm_entry_intr_info_field = vmcs12->vm_entry_intr_info_field;
+ evmcs->vm_entry_exception_error_code =
+ vmcs12->vm_entry_exception_error_code;
+ evmcs->vm_entry_instruction_len = vmcs12->vm_entry_instruction_len;
+
+ evmcs->guest_rip = vmcs12->guest_rip;
+
+ evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs;
+
+ return 0;
+}
+
/*
* Copy the writable VMCS shadow fields back to the VMCS12, in case
* they have been modified by the L1 guest. Note that the "read-only"
@@ -8679,20 +9117,6 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
vmcs_load(vmx->loaded_vmcs->vmcs);
}
-/*
- * VMX instructions which assume a current vmcs12 (i.e., that VMPTRLD was
- * used before) all generate the same failure when it is missing.
- */
-static int nested_vmx_check_vmcs12(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (vmx->nested.current_vmptr == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return 0;
- }
- return 1;
-}
-
static int handle_vmread(struct kvm_vcpu *vcpu)
{
unsigned long field;
@@ -8705,8 +9129,8 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- return kvm_skip_emulated_instruction(vcpu);
+ if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
if (!is_guest_mode(vcpu))
vmcs12 = get_vmcs12(vcpu);
@@ -8715,20 +9139,18 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
* When vmcs->vmcs_link_pointer is -1ull, any VMREAD
* to shadowed-field sets the ALU flags for VMfailInvalid.
*/
- if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_shadow_vmcs12(vcpu);
}
/* Decode instruction info and find the field to read */
field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
/* Read the field, zero-extended to a u64 field_value */
- if (vmcs12_read_any(vmcs12, field, &field_value) < 0) {
- nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmcs12_read_any(vmcs12, field, &field_value) < 0)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
/*
* Now copy part of this value to register or memory, as requested.
* Note that the number of bits actually copied is 32 or 64 depending
@@ -8746,8 +9168,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
(is_long_mode(vcpu) ? 8 : 4), NULL);
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
@@ -8772,8 +9193,8 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- return kvm_skip_emulated_instruction(vcpu);
+ if (vmx->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
if (vmx_instruction_info & (1u << 10))
field_value = kvm_register_readl(vcpu,
@@ -8796,11 +9217,9 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
* VMCS," then the "read-only" fields are actually read/write.
*/
if (vmcs_field_readonly(field) &&
- !nested_cpu_has_vmwrite_any_field(vcpu)) {
- nested_vmx_failValid(vcpu,
+ !nested_cpu_has_vmwrite_any_field(vcpu))
+ return nested_vmx_failValid(vcpu,
VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
if (!is_guest_mode(vcpu))
vmcs12 = get_vmcs12(vcpu);
@@ -8809,18 +9228,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
* When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
* to shadowed-field sets the ALU flags for VMfailInvalid.
*/
- if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_shadow_vmcs12(vcpu);
-
}
- if (vmcs12_write_any(vmcs12, field, field_value) < 0) {
- nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmcs12_write_any(vmcs12, field, field_value) < 0)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_UNSUPPORTED_VMCS_COMPONENT);
/*
* Do not track vmcs12 dirty-state if in guest-mode
@@ -8842,8 +9257,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
}
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
@@ -8854,7 +9268,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
SECONDARY_EXEC_SHADOW_VMCS);
vmcs_write64(VMCS_LINK_POINTER,
__pa(vmx->vmcs01.shadow_vmcs));
- vmx->nested.sync_shadow_vmcs = true;
+ vmx->nested.need_vmcs12_sync = true;
}
vmx->nested.dirty_vmcs12 = true;
}
@@ -8871,36 +9285,37 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
- nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu)))
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMPTRLD_INVALID_ADDRESS);
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (vmptr == vmx->nested.vmxon_ptr)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_VMPTRLD_VMXON_POINTER);
+
+ /* Forbid normal VMPTRLD if Enlightened version was used */
+ if (vmx->nested.hv_evmcs)
+ return 1;
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
page = kvm_vcpu_gpa_to_page(vcpu, vmptr);
- if (is_error_page(page)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ if (is_error_page(page))
+ return nested_vmx_failInvalid(vcpu);
+
new_vmcs12 = kmap(page);
if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
(new_vmcs12->hdr.shadow_vmcs &&
!nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
kunmap(page);
kvm_release_page_clean(page);
- nested_vmx_failValid(vcpu,
+ return nested_vmx_failValid(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
- return kvm_skip_emulated_instruction(vcpu);
}
- nested_release_vmcs12(vmx);
+ nested_release_vmcs12(vcpu);
+
/*
* Load VMCS12 from guest memory since it is not already
* cached.
@@ -8912,8 +9327,71 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
set_current_vmptr(vmx, vmptr);
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
+}
+
+/*
+ * This is an equivalent of the nested hypervisor executing the vmptrld
+ * instruction.
+ */
+static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
+ bool from_launch)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct hv_vp_assist_page assist_page;
+
+ if (likely(!vmx->nested.enlightened_vmcs_enabled))
+ return 1;
+
+ if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page)))
+ return 1;
+
+ if (unlikely(!assist_page.enlighten_vmentry))
+ return 1;
+
+ if (unlikely(assist_page.current_nested_vmcs !=
+ vmx->nested.hv_evmcs_vmptr)) {
+
+ if (!vmx->nested.hv_evmcs)
+ vmx->nested.current_vmptr = -1ull;
+
+ nested_release_evmcs(vcpu);
+
+ vmx->nested.hv_evmcs_page = kvm_vcpu_gpa_to_page(
+ vcpu, assist_page.current_nested_vmcs);
+
+ if (unlikely(is_error_page(vmx->nested.hv_evmcs_page)))
+ return 0;
+
+ vmx->nested.hv_evmcs = kmap(vmx->nested.hv_evmcs_page);
+
+ if (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION) {
+ nested_release_evmcs(vcpu);
+ return 0;
+ }
+
+ vmx->nested.dirty_vmcs12 = true;
+ /*
+ * As we keep L2 state for one guest only 'hv_clean_fields' mask
+ * can't be used when we switch between them. Reset it here for
+ * simplicity.
+ */
+ vmx->nested.hv_evmcs->hv_clean_fields &=
+ ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ vmx->nested.hv_evmcs_vmptr = assist_page.current_nested_vmcs;
+
+ /*
+ * Unlike normal vmcs12, enlightened vmcs12 is not fully
+ * reloaded from guest's memory (read only fields, fields not
+ * present in struct hv_enlightened_vmcs, ...). Make sure there
+ * are no leftovers.
+ */
+ if (from_launch)
+ memset(vmx->nested.cached_vmcs12, 0,
+ sizeof(*vmx->nested.cached_vmcs12));
+
+ }
+ return 1;
}
/* Emulate the VMPTRST instruction */
@@ -8928,6 +9406,9 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
+ if (unlikely(to_vmx(vcpu)->nested.hv_evmcs))
+ return 1;
+
if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
return 1;
/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
@@ -8936,8 +9417,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- nested_vmx_succeed(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
/* Emulate the INVEPT instruction */
@@ -8967,11 +9447,9 @@ static int handle_invept(struct kvm_vcpu *vcpu)
types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
- if (type >= 32 || !(types & (1 << type))) {
- nested_vmx_failValid(vcpu,
+ if (type >= 32 || !(types & (1 << type)))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
/* According to the Intel VMX instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
@@ -8993,14 +9471,20 @@ static int handle_invept(struct kvm_vcpu *vcpu)
case VMX_EPT_EXTENT_CONTEXT:
kvm_mmu_sync_roots(vcpu);
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- nested_vmx_succeed(vcpu);
break;
default:
BUG_ON(1);
break;
}
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
+}
+
+static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
}
static int handle_invvpid(struct kvm_vcpu *vcpu)
@@ -9014,6 +9498,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
u64 vpid;
u64 gla;
} operand;
+ u16 vpid02;
if (!(vmx->nested.msrs.secondary_ctls_high &
SECONDARY_EXEC_ENABLE_VPID) ||
@@ -9031,11 +9516,9 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
types = (vmx->nested.msrs.vpid_caps &
VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
- if (type >= 32 || !(types & (1 << type))) {
- nested_vmx_failValid(vcpu,
+ if (type >= 32 || !(types & (1 << type)))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
/* according to the intel vmx instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
@@ -9047,47 +9530,39 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- if (operand.vpid >> 16) {
- nested_vmx_failValid(vcpu,
+ if (operand.vpid >> 16)
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
+ vpid02 = nested_get_vpid02(vcpu);
switch (type) {
case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
if (!operand.vpid ||
- is_noncanonical_address(operand.gla, vcpu)) {
- nested_vmx_failValid(vcpu,
+ is_noncanonical_address(operand.gla, vcpu))
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
- if (cpu_has_vmx_invvpid_individual_addr() &&
- vmx->nested.vpid02) {
+ if (cpu_has_vmx_invvpid_individual_addr()) {
__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
- vmx->nested.vpid02, operand.gla);
+ vpid02, operand.gla);
} else
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vpid02, false);
break;
case VMX_VPID_EXTENT_SINGLE_CONTEXT:
case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
- if (!operand.vpid) {
- nested_vmx_failValid(vcpu,
+ if (!operand.vpid)
+ return nested_vmx_failValid(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- return kvm_skip_emulated_instruction(vcpu);
- }
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vpid02, false);
break;
case VMX_VPID_EXTENT_ALL_CONTEXT:
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, vpid02, false);
break;
default:
WARN_ON_ONCE(1);
return kvm_skip_emulated_instruction(vcpu);
}
- nested_vmx_succeed(vcpu);
-
- return kvm_skip_emulated_instruction(vcpu);
+ return nested_vmx_succeed(vcpu);
}
static int handle_invpcid(struct kvm_vcpu *vcpu)
@@ -9158,11 +9633,11 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
}
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
- if (kvm_get_pcid(vcpu, vcpu->arch.mmu.prev_roots[i].cr3)
+ if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].cr3)
== operand.pcid)
roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
- kvm_mmu_free_roots(vcpu, roots_to_free);
+ kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
/*
* If neither the current cr3 nor any of the prev_roots use the
* given PCID, then nothing needs to be done here because a
@@ -9289,7 +9764,7 @@ static int nested_vmx_eptp_switching(struct kvm_vcpu *vcpu,
kvm_mmu_unload(vcpu);
mmu->ept_ad = accessed_dirty;
- mmu->base_role.ad_disabled = !accessed_dirty;
+ mmu->mmu_role.base.ad_disabled = !accessed_dirty;
vmcs12->ept_pointer = address;
/*
* TODO: Check what's the correct approach in case
@@ -9648,9 +10123,6 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
return false;
else if (is_page_fault(intr_info))
return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
- else if (is_no_device(intr_info) &&
- !(vmcs12->guest_cr0 & X86_CR0_TS))
- return false;
else if (is_debug(intr_info) &&
vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
@@ -10672,9 +11144,25 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmcs_write32(PLE_WINDOW, vmx->ple_window);
}
- if (vmx->nested.sync_shadow_vmcs) {
- copy_vmcs12_to_shadow(vmx);
- vmx->nested.sync_shadow_vmcs = false;
+ if (vmx->nested.need_vmcs12_sync) {
+ /*
+ * hv_evmcs may end up being not mapped after migration (when
+ * L2 was running), map it here to make sure vmcs12 changes are
+ * properly reflected.
+ */
+ if (vmx->nested.enlightened_vmcs_enabled &&
+ !vmx->nested.hv_evmcs)
+ nested_vmx_handle_enlightened_vmptrld(vcpu, false);
+
+ if (vmx->nested.hv_evmcs) {
+ copy_vmcs12_to_enlightened(vmx);
+ /* All fields are clean */
+ vmx->nested.hv_evmcs->hv_clean_fields |=
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
+ } else {
+ copy_vmcs12_to_shadow(vmx);
+ }
+ vmx->nested.need_vmcs12_sync = false;
}
if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
@@ -10741,7 +11229,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%" _ASM_SP ", (%%" _ASM_SI ") \n\t"
"jmp 1f \n\t"
"2: \n\t"
- __ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
+ __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t"
"1: \n\t"
/* Reload cr2 if changed */
"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
@@ -10773,9 +11261,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
/* Enter guest mode */
"jne 1f \n\t"
- __ex(ASM_VMX_VMLAUNCH) "\n\t"
+ __ex("vmlaunch") "\n\t"
"jmp 2f \n\t"
- "1: " __ex(ASM_VMX_VMRESUME) "\n\t"
+ "1: " __ex("vmresume") "\n\t"
"2: "
/* Save guest registers, load host registers, keep flags */
"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
@@ -10797,6 +11285,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r13, %c[r13](%0) \n\t"
"mov %%r14, %c[r14](%0) \n\t"
"mov %%r15, %c[r15](%0) \n\t"
+ /*
+ * Clear host registers marked as clobbered to prevent
+ * speculative use.
+ */
"xor %%r8d, %%r8d \n\t"
"xor %%r9d, %%r9d \n\t"
"xor %%r10d, %%r10d \n\t"
@@ -10954,6 +11446,10 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
vmx->loaded_vmcs = vmcs;
vmx_vcpu_load(vcpu, cpu);
put_cpu();
+
+ vm_entry_controls_reset_shadow(vmx);
+ vm_exit_controls_reset_shadow(vmx);
+ vmx_segment_cache_clear(vmx);
}
/*
@@ -10962,12 +11458,10 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
*/
static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- vcpu_load(vcpu);
- vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- free_nested(vmx);
- vcpu_put(vcpu);
+ vcpu_load(vcpu);
+ vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
+ free_nested(vcpu);
+ vcpu_put(vcpu);
}
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
@@ -11330,28 +11824,28 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
return get_vmcs12(vcpu)->ept_pointer;
}
-static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
{
WARN_ON(mmu_is_nested(vcpu));
- if (!valid_ept_address(vcpu, nested_ept_get_cr3(vcpu)))
- return 1;
+ vcpu->arch.mmu = &vcpu->arch.guest_mmu;
kvm_init_shadow_ept_mmu(vcpu,
to_vmx(vcpu)->nested.msrs.ept_caps &
VMX_EPT_EXECUTE_ONLY_BIT,
nested_ept_ad_enabled(vcpu),
nested_ept_get_cr3(vcpu));
- vcpu->arch.mmu.set_cr3 = vmx_set_cr3;
- vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3;
- vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->set_cr3 = vmx_set_cr3;
+ vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3;
+ vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
+ vcpu->arch.mmu->get_pdptr = kvm_pdptr_read;
vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
- return 0;
}
static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+ vcpu->arch.mmu = &vcpu->arch.root_mmu;
+ vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}
static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
@@ -11768,15 +12262,12 @@ static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- u64 address = vmcs12->pml_address;
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
+ if (!nested_cpu_has_pml(vmcs12))
+ return 0;
- if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
- if (!nested_cpu_has_ept(vmcs12) ||
- !IS_ALIGNED(address, 4096) ||
- address >> maxphyaddr)
- return -EINVAL;
- }
+ if (!nested_cpu_has_ept(vmcs12) ||
+ !page_address_valid(vcpu, vmcs12->pml_address))
+ return -EINVAL;
return 0;
}
@@ -11956,112 +12447,87 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
return 0;
}
-static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
+/*
+ * Returns if KVM is able to config CPU to tag TLB entries
+ * populated by L2 differently than TLB entries populated
+ * by L1.
+ *
+ * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ *
+ * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
+ * with different VPID (L1 entries are tagged with vmx->vpid
+ * while L2 entries are tagged with vmx->nested.vpid02).
+ */
+static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
- vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
- vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
- vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
- vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
- vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
- vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
- vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
- vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
- vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
- vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
- vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
- vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
- vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
- vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
- vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
- vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
- vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
- vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
- vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
- vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
- vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
- vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
- vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
- vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
- vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
- vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
- vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
- vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
- vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
- vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
-
- vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
- vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
- vmcs12->guest_pending_dbg_exceptions);
- vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
- vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+ return nested_cpu_has_ept(vmcs12) ||
+ (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
+}
- if (nested_cpu_has_xsaves(vmcs12))
- vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
- vmcs_write64(VMCS_LINK_POINTER, -1ull);
+static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
+ return vmcs12->guest_ia32_efer;
+ else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
+ return vmx->vcpu.arch.efer | (EFER_LMA | EFER_LME);
+ else
+ return vmx->vcpu.arch.efer & ~(EFER_LMA | EFER_LME);
+}
- if (cpu_has_vmx_posted_intr())
- vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
+static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
+{
+ /*
+ * If vmcs02 hasn't been initialized, set the constant vmcs02 state
+ * according to L0's settings (vmcs12 is irrelevant here). Host
+ * fields that come from L0 and are not constant, e.g. HOST_CR3,
+ * will be set as needed prior to VMLAUNCH/VMRESUME.
+ */
+ if (vmx->nested.vmcs02_initialized)
+ return;
+ vmx->nested.vmcs02_initialized = true;
/*
- * Whether page-faults are trapped is determined by a combination of
- * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
- * If enable_ept, L0 doesn't care about page faults and we should
- * set all of these to L1's desires. However, if !enable_ept, L0 does
- * care about (at least some) page faults, and because it is not easy
- * (if at all possible?) to merge L0 and L1's desires, we simply ask
- * to exit on each and every L2 page fault. This is done by setting
- * MASK=MATCH=0 and (see below) EB.PF=1.
- * Note that below we don't need special code to set EB.PF beyond the
- * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
- * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
- * !enable_ept, EB.PF is 1, so the "or" will always be 1.
+ * We don't care what the EPTP value is we just need to guarantee
+ * it's valid so we don't get a false positive when doing early
+ * consistency checks.
*/
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
- enable_ept ? vmcs12->page_fault_error_code_mask : 0);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
- enable_ept ? vmcs12->page_fault_error_code_match : 0);
+ if (enable_ept && nested_early_check)
+ vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));
/* All VMFUNCs are currently emulated through L0 vmexits. */
if (cpu_has_vmx_vmfunc())
vmcs_write64(VM_FUNCTION_CONTROL, 0);
- if (cpu_has_vmx_apicv()) {
- vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
- vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
- vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
- vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
- }
+ if (cpu_has_vmx_posted_intr())
+ vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR);
- /*
- * Set host-state according to L0's settings (vmcs12 is irrelevant here)
- * Some constant fields are set here by vmx_set_constant_host_state().
- * Other fields are different per CPU, and will be set later when
- * vmx_vcpu_load() is called, and when vmx_prepare_switch_to_guest()
- * is called.
- */
- vmx_set_constant_host_state(vmx);
+ if (cpu_has_vmx_msr_bitmap())
+ vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
+
+ if (enable_pml)
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
/*
- * Set the MSR load/store lists to match L0's settings.
+ * Set the MSR load/store lists to match L0's settings. Only the
+ * addresses are constant (for vmcs02), the counts can change based
+ * on L2's behavior, e.g. switching to/from long mode.
*/
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
- set_cr4_guest_host_mask(vmx);
+ vmx_set_constant_host_state(vmx);
+}
- if (kvm_mpx_supported()) {
- if (vmx->nested.nested_run_pending &&
- (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
- vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
- else
- vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
- }
+static void prepare_vmcs02_early_full(struct vcpu_vmx *vmx,
+ struct vmcs12 *vmcs12)
+{
+ prepare_vmcs02_constant_state(vmx);
+
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
if (enable_vpid) {
if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
@@ -12069,78 +12535,30 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
else
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
}
-
- /*
- * L1 may access the L2's PDPTR, so save them to construct vmcs12
- */
- if (enable_ept) {
- vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
- vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
- vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
- vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
- }
-
- if (cpu_has_vmx_msr_bitmap())
- vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap));
}
-/*
- * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
- * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
- * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
- * guest in a way that will both be appropriate to L1's requests, and our
- * needs. In addition to modifying the active vmcs (which is vmcs02), this
- * function also has additional necessary side-effects, like setting various
- * vcpu->arch fields.
- * Returns 0 on success, 1 on failure. Invalid state exit qualification code
- * is assigned to entry_failure_code on failure.
- */
-static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- u32 *entry_failure_code)
+static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control, vmcs12_exec_ctrl;
+ u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12);
- if (vmx->nested.dirty_vmcs12) {
- prepare_vmcs02_full(vcpu, vmcs12);
- vmx->nested.dirty_vmcs12 = false;
- }
+ if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs)
+ prepare_vmcs02_early_full(vmx, vmcs12);
/*
- * First, the fields that are shadowed. This must be kept in sync
- * with vmx_shadow_fields.h.
+ * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
+ * entry, but only if the current (host) sp changed from the value
+ * we wrote last (vmx->host_rsp). This cache is no longer relevant
+ * if we switch vmcs, and rather than hold a separate cache per vmcs,
+ * here we just force the write to happen on entry. host_rsp will
+ * also be written unconditionally by nested_vmx_check_vmentry_hw()
+ * if we are doing early consistency checks via hardware.
*/
+ vmx->host_rsp = 0;
- vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
- vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
- vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
- vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
- vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
-
- if (vmx->nested.nested_run_pending &&
- (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
- kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
- } else {
- kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
- }
- if (vmx->nested.nested_run_pending) {
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
- vmcs12->vm_entry_intr_info_field);
- vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
- vmcs12->vm_entry_exception_error_code);
- vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
- vmcs12->vm_entry_instruction_len);
- vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
- vmcs12->guest_interruptibility_info);
- vmx->loaded_vmcs->nmi_known_unmasked =
- !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
- } else {
- vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
- }
- vmx_set_rflags(vcpu, vmcs12->guest_rflags);
-
+ /*
+ * PIN CONTROLS
+ */
exec_control = vmcs12->pin_based_vm_exec_control;
/* Preemption timer setting is computed directly in vmx_vcpu_run. */
@@ -12155,13 +12573,43 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
} else {
exec_control &= ~PIN_BASED_POSTED_INTR;
}
-
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
- vmx->nested.preemption_timer_expired = false;
- if (nested_cpu_has_preemption_timer(vmcs12))
- vmx_start_preemption_timer(vcpu);
+ /*
+ * EXEC CONTROLS
+ */
+ exec_control = vmx_exec_control(vmx); /* L0's desires */
+ exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+ exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
+ exec_control &= ~CPU_BASED_TPR_SHADOW;
+ exec_control |= vmcs12->cpu_based_vm_exec_control;
+ /*
+ * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if
+ * nested_get_vmcs12_pages can't fix it up, the illegal value
+ * will result in a VM entry failure.
+ */
+ if (exec_control & CPU_BASED_TPR_SHADOW) {
+ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
+ vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ } else {
+#ifdef CONFIG_X86_64
+ exec_control |= CPU_BASED_CR8_LOAD_EXITING |
+ CPU_BASED_CR8_STORE_EXITING;
+#endif
+ }
+
+ /*
+ * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
+ * for I/O port accesses.
+ */
+ exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
+ exec_control |= CPU_BASED_UNCOND_IO_EXITING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
+
+ /*
+ * SECONDARY EXEC CONTROLS
+ */
if (cpu_has_secondary_exec_ctrls()) {
exec_control = vmx->secondary_exec_control;
@@ -12202,43 +12650,214 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
}
/*
- * HOST_RSP is normally set correctly in vmx_vcpu_run() just before
- * entry, but only if the current (host) sp changed from the value
- * we wrote last (vmx->host_rsp). This cache is no longer relevant
- * if we switch vmcs, and rather than hold a separate cache per vmcs,
- * here we just force the write to happen on entry.
+ * ENTRY CONTROLS
+ *
+ * vmcs12's VM_{ENTRY,EXIT}_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE
+ * are emulated by vmx_set_efer() in prepare_vmcs02(), but speculate
+ * on the related bits (if supported by the CPU) in the hope that
+ * we can avoid VMWrites during vmx_set_efer().
+ */
+ exec_control = (vmcs12->vm_entry_controls | vmcs_config.vmentry_ctrl) &
+ ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER;
+ if (cpu_has_load_ia32_efer) {
+ if (guest_efer & EFER_LMA)
+ exec_control |= VM_ENTRY_IA32E_MODE;
+ if (guest_efer != host_efer)
+ exec_control |= VM_ENTRY_LOAD_IA32_EFER;
+ }
+ vm_entry_controls_init(vmx, exec_control);
+
+ /*
+ * EXIT CONTROLS
+ *
+ * L2->L1 exit controls are emulated - the hardware exit is to L0 so
+ * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
+ * bits may be modified by vmx_set_efer() in prepare_vmcs02().
*/
- vmx->host_rsp = 0;
+ exec_control = vmcs_config.vmexit_ctrl;
+ if (cpu_has_load_ia32_efer && guest_efer != host_efer)
+ exec_control |= VM_EXIT_LOAD_IA32_EFER;
+ vm_exit_controls_init(vmx, exec_control);
- exec_control = vmx_exec_control(vmx); /* L0's desires */
- exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
- exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
- exec_control &= ~CPU_BASED_TPR_SHADOW;
- exec_control |= vmcs12->cpu_based_vm_exec_control;
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit and never change
+ * the PML address (once set), this happens to be equivalent to
+ * simply resetting the index in vmcs02.
+ */
+ if (enable_pml)
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
/*
- * Write an illegal value to VIRTUAL_APIC_PAGE_ADDR. Later, if
- * nested_get_vmcs12_pages can't fix it up, the illegal value
- * will result in a VM entry failure.
+ * Interrupt/Exception Fields
*/
- if (exec_control & CPU_BASED_TPR_SHADOW) {
- vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, -1ull);
- vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ if (vmx->nested.nested_run_pending) {
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
+ vmcs12->vm_entry_intr_info_field);
+ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
+ vmcs12->vm_entry_exception_error_code);
+ vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
+ vmcs12->vm_entry_instruction_len);
+ vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
+ vmcs12->guest_interruptibility_info);
+ vmx->loaded_vmcs->nmi_known_unmasked =
+ !(vmcs12->guest_interruptibility_info & GUEST_INTR_STATE_NMI);
} else {
-#ifdef CONFIG_X86_64
- exec_control |= CPU_BASED_CR8_LOAD_EXITING |
- CPU_BASED_CR8_STORE_EXITING;
-#endif
+ vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
+ }
+}
+
+static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
+{
+ struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+
+ if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+ vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
+ vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
+ vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
+ vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
+ vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector);
+ vmcs_write16(GUEST_GS_SELECTOR, vmcs12->guest_gs_selector);
+ vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector);
+ vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector);
+ vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit);
+ vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
+ vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit);
+ vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit);
+ vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit);
+ vmcs_write32(GUEST_GS_LIMIT, vmcs12->guest_gs_limit);
+ vmcs_write32(GUEST_LDTR_LIMIT, vmcs12->guest_ldtr_limit);
+ vmcs_write32(GUEST_TR_LIMIT, vmcs12->guest_tr_limit);
+ vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit);
+ vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit);
+ vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes);
+ vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes);
+ vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes);
+ vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes);
+ vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes);
+ vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes);
+ vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
+ vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
+ vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base);
+ vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base);
+ vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base);
+ vmcs_writel(GUEST_GS_BASE, vmcs12->guest_gs_base);
+ vmcs_writel(GUEST_LDTR_BASE, vmcs12->guest_ldtr_base);
+ vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
+ vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
+ vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+ }
+
+ if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) {
+ vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+ vmcs12->guest_pending_dbg_exceptions);
+ vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
+ vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+
+ /*
+ * L1 may access the L2's PDPTR, so save them to construct
+ * vmcs12
+ */
+ if (enable_ept) {
+ vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+ vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+ vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+ vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ }
}
+ if (nested_cpu_has_xsaves(vmcs12))
+ vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
+
/*
- * A vmexit (to either L1 hypervisor or L0 userspace) is always needed
- * for I/O port accesses.
+ * Whether page-faults are trapped is determined by a combination of
+ * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
+ * If enable_ept, L0 doesn't care about page faults and we should
+ * set all of these to L1's desires. However, if !enable_ept, L0 does
+ * care about (at least some) page faults, and because it is not easy
+ * (if at all possible?) to merge L0 and L1's desires, we simply ask
+ * to exit on each and every L2 page fault. This is done by setting
+ * MASK=MATCH=0 and (see below) EB.PF=1.
+ * Note that below we don't need special code to set EB.PF beyond the
+ * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
+ * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
+ * !enable_ept, EB.PF is 1, so the "or" will always be 1.
*/
- exec_control &= ~CPU_BASED_USE_IO_BITMAPS;
- exec_control |= CPU_BASED_UNCOND_IO_EXITING;
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
+ enable_ept ? vmcs12->page_fault_error_code_mask : 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
+ enable_ept ? vmcs12->page_fault_error_code_match : 0);
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control);
+ if (cpu_has_vmx_apicv()) {
+ vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
+ vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
+ vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
+ vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
+ }
+
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+ set_cr4_guest_host_mask(vmx);
+
+ if (kvm_mpx_supported()) {
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+ vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+ else
+ vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+ }
+}
+
+/*
+ * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
+ * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
+ * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
+ * guest in a way that will both be appropriate to L1's requests, and our
+ * needs. In addition to modifying the active vmcs (which is vmcs02), this
+ * function also has additional necessary side-effects, like setting various
+ * vcpu->arch fields.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+ u32 *entry_failure_code)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+
+ if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) {
+ prepare_vmcs02_full(vmx, vmcs12);
+ vmx->nested.dirty_vmcs12 = false;
+ }
+
+ /*
+ * First, the fields that are shadowed. This must be kept in sync
+ * with vmx_shadow_fields.h.
+ */
+ if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
+ vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
+ vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes);
+ }
+
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
+ kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ } else {
+ kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
+ vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
+ }
+ vmx_set_rflags(vcpu, vmcs12->guest_rflags);
+
+ vmx->nested.preemption_timer_expired = false;
+ if (nested_cpu_has_preemption_timer(vmcs12))
+ vmx_start_preemption_timer(vcpu);
/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
* bitwise-or of what L1 wants to trap for L2, and what we want to
@@ -12248,20 +12867,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- /* L2->L1 exit controls are emulated - the hardware exit is to L0 so
- * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
- * bits are further modified by vmx_set_efer() below.
- */
- vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
-
- /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
- * emulated by vmx_set_efer(), below.
- */
- vm_entry_controls_init(vmx,
- (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
- ~VM_ENTRY_IA32E_MODE) |
- (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
-
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
@@ -12284,37 +12889,29 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
* influence global bitmap(for vpid01 and vpid02 allocation)
* even if spawn a lot of nested vCPUs.
*/
- if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
+ if (nested_cpu_has_vpid(vmcs12) && nested_has_guest_tlb_tag(vcpu)) {
if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
vmx->nested.last_vpid = vmcs12->virtual_processor_id;
- __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+ __vmx_flush_tlb(vcpu, nested_get_vpid02(vcpu), false);
}
} else {
- vmx_flush_tlb(vcpu, true);
+ /*
+ * If L1 use EPT, then L0 needs to execute INVEPT on
+ * EPTP02 instead of EPTP01. Therefore, delay TLB
+ * flush until vmcs02->eptp is fully updated by
+ * KVM_REQ_LOAD_CR3. Note that this assumes
+ * KVM_REQ_TLB_FLUSH is evaluated after
+ * KVM_REQ_LOAD_CR3 in vcpu_enter_guest().
+ */
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
}
- if (enable_pml) {
- /*
- * Conceptually we want to copy the PML address and index from
- * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
- * since we always flush the log on each vmexit, this happens
- * to be equivalent to simply resetting the fields in vmcs02.
- */
- ASSERT(vmx->pml_pg);
- vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
- vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
- }
-
- if (nested_cpu_has_ept(vmcs12)) {
- if (nested_ept_init_mmu_context(vcpu)) {
- *entry_failure_code = ENTRY_FAIL_DEFAULT;
- return 1;
- }
- } else if (nested_cpu_has2(vmcs12,
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ if (nested_cpu_has_ept(vmcs12))
+ nested_ept_init_mmu_context(vcpu);
+ else if (nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
vmx_flush_tlb(vcpu, true);
- }
/*
* This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
@@ -12330,14 +12927,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmx_set_cr4(vcpu, vmcs12->guest_cr4);
vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
- if (vmx->nested.nested_run_pending &&
- (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
- vcpu->arch.efer = vmcs12->guest_ia32_efer;
- else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
- vcpu->arch.efer |= (EFER_LMA | EFER_LME);
- else
- vcpu->arch.efer &= ~(EFER_LMA | EFER_LME);
- /* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
+ vcpu->arch.efer = nested_vmx_calc_efer(vmx, vmcs12);
+ /* Note: may modify VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */
vmx_set_efer(vcpu, vcpu->arch.efer);
/*
@@ -12379,6 +12970,7 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool ia32e;
if (vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
@@ -12453,6 +13045,21 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
/*
+ * If the load IA32_EFER VM-exit control is 1, bits reserved in the
+ * IA32_EFER MSR must be 0 in the field for that register. In addition,
+ * the values of the LMA and LME bits in the field must each be that of
+ * the host address-space size VM-exit control.
+ */
+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
+ ia32e = (vmcs12->vm_exit_controls &
+ VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;
+ if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
+ ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
+ ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
+ return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
+ }
+
+ /*
* From the Intel SDM, volume 3:
* Fields relevant to VM-entry event injection must be set properly.
* These fields are the VM-entry interruption-information field, the
@@ -12508,6 +13115,10 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
}
}
+ if (nested_cpu_has_ept(vmcs12) &&
+ !valid_ept_address(vcpu, vmcs12->ept_pointer))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
return 0;
}
@@ -12573,21 +13184,6 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
return 1;
}
- /*
- * If the load IA32_EFER VM-exit control is 1, bits reserved in the
- * IA32_EFER MSR must be 0 in the field for that register. In addition,
- * the values of the LMA and LME bits in the field must each be that of
- * the host address-space size VM-exit control.
- */
- if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) {
- ia32e = (vmcs12->vm_exit_controls &
- VM_EXIT_HOST_ADDR_SPACE_SIZE) != 0;
- if (!kvm_valid_efer(vcpu, vmcs12->host_ia32_efer) ||
- ia32e != !!(vmcs12->host_ia32_efer & EFER_LMA) ||
- ia32e != !!(vmcs12->host_ia32_efer & EFER_LME))
- return 1;
- }
-
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
(vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
@@ -12596,26 +13192,139 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
return 0;
}
+static int __noclone nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long cr3, cr4;
+
+ if (!nested_early_check)
+ return 0;
+
+ if (vmx->msr_autoload.host.nr)
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+ if (vmx->msr_autoload.guest.nr)
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+
+ preempt_disable();
+
+ vmx_prepare_switch_to_guest(vcpu);
+
+ /*
+ * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
+ * which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to
+ * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e.
+ * there is no need to preserve other bits or save/restore the field.
+ */
+ vmcs_writel(GUEST_RFLAGS, 0);
+
+ vmcs_writel(HOST_RIP, vmx_early_consistency_check_return);
+
+ cr3 = __get_current_cr3_fast();
+ if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+ vmcs_writel(HOST_CR3, cr3);
+ vmx->loaded_vmcs->host_state.cr3 = cr3;
+ }
+
+ cr4 = cr4_read_shadow();
+ if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->loaded_vmcs->host_state.cr4 = cr4;
+ }
+
+ vmx->__launched = vmx->loaded_vmcs->launched;
+
+ asm(
+ /* Set HOST_RSP */
+ __ex("vmwrite %%" _ASM_SP ", %%" _ASM_DX) "\n\t"
+ "mov %%" _ASM_SP ", %c[host_rsp](%0)\n\t"
+
+ /* Check if vmlaunch of vmresume is needed */
+ "cmpl $0, %c[launched](%0)\n\t"
+ "je 1f\n\t"
+ __ex("vmresume") "\n\t"
+ "jmp 2f\n\t"
+ "1: " __ex("vmlaunch") "\n\t"
+ "jmp 2f\n\t"
+ "2: "
+
+ /* Set vmx->fail accordingly */
+ "setbe %c[fail](%0)\n\t"
+
+ ".pushsection .rodata\n\t"
+ ".global vmx_early_consistency_check_return\n\t"
+ "vmx_early_consistency_check_return: " _ASM_PTR " 2b\n\t"
+ ".popsection"
+ :
+ : "c"(vmx), "d"((unsigned long)HOST_RSP),
+ [launched]"i"(offsetof(struct vcpu_vmx, __launched)),
+ [fail]"i"(offsetof(struct vcpu_vmx, fail)),
+ [host_rsp]"i"(offsetof(struct vcpu_vmx, host_rsp))
+ : "rax", "cc", "memory"
+ );
+
+ vmcs_writel(HOST_RIP, vmx_return);
+
+ preempt_enable();
+
+ if (vmx->msr_autoload.host.nr)
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+ if (vmx->msr_autoload.guest.nr)
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+
+ if (vmx->fail) {
+ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ vmx->fail = 0;
+ return 1;
+ }
+
+ /*
+ * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
+ */
+ local_irq_enable();
+ if (hw_breakpoint_active())
+ set_debugreg(__this_cpu_read(cpu_dr7), 7);
+
+ /*
+ * A non-failing VMEntry means we somehow entered guest mode with
+ * an illegal RIP, and that's just the tip of the iceberg. There
+ * is no telling what memory has been modified or what state has
+ * been exposed to unknown code. Hitting this all but guarantees
+ * a (very critical) hardware issue.
+ */
+ WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
+ VMX_EXIT_REASONS_FAILED_VMENTRY));
+
+ return 0;
+}
+STACK_FRAME_NON_STANDARD(nested_vmx_check_vmentry_hw);
+
+static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12);
+
/*
- * If exit_qual is NULL, this is being called from state restore (either RSM
+ * If from_vmentry is false, this is being called from state restore (either RSM
* or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume.
++ *
++ * Returns:
++ * 0 - success, i.e. proceed with actual VMEnter
++ * 1 - consistency check VMExit
++ * -1 - consistency check VMFail
*/
-static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
+static int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+ bool from_vmentry)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- bool from_vmentry = !!exit_qual;
- u32 dummy_exit_qual;
bool evaluate_pending_interrupts;
- int r = 0;
+ u32 exit_reason = EXIT_REASON_INVALID_STATE;
+ u32 exit_qual;
evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
- enter_guest_mode(vcpu);
-
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
if (kvm_mpx_supported() &&
@@ -12623,24 +13332,35 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
- vmx_segment_cache_clear(vmx);
+ prepare_vmcs02_early(vmx, vmcs12);
+
+ if (from_vmentry) {
+ nested_get_vmcs12_pages(vcpu);
+
+ if (nested_vmx_check_vmentry_hw(vcpu)) {
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+ return -1;
+ }
+
+ if (check_vmentry_postreqs(vcpu, vmcs12, &exit_qual))
+ goto vmentry_fail_vmexit;
+ }
+
+ enter_guest_mode(vcpu);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vcpu->arch.tsc_offset += vmcs12->tsc_offset;
- r = EXIT_REASON_INVALID_STATE;
- if (prepare_vmcs02(vcpu, vmcs12, from_vmentry ? exit_qual : &dummy_exit_qual))
- goto fail;
+ if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
+ goto vmentry_fail_vmexit_guest_mode;
if (from_vmentry) {
- nested_get_vmcs12_pages(vcpu);
-
- r = EXIT_REASON_MSR_LOAD_FAIL;
- *exit_qual = nested_vmx_load_msr(vcpu,
- vmcs12->vm_entry_msr_load_addr,
- vmcs12->vm_entry_msr_load_count);
- if (*exit_qual)
- goto fail;
+ exit_reason = EXIT_REASON_MSR_LOAD_FAIL;
+ exit_qual = nested_vmx_load_msr(vcpu,
+ vmcs12->vm_entry_msr_load_addr,
+ vmcs12->vm_entry_msr_load_count);
+ if (exit_qual)
+ goto vmentry_fail_vmexit_guest_mode;
} else {
/*
* The MMU is not initialized to point at the right entities yet and
@@ -12677,12 +13397,28 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
*/
return 0;
-fail:
+ /*
+ * A failed consistency check that leads to a VMExit during L1's
+ * VMEnter to L2 is a variation of a normal VMexit, as explained in
+ * 26.7 "VM-entry failures during or after loading guest state".
+ */
+vmentry_fail_vmexit_guest_mode:
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
leave_guest_mode(vcpu);
+
+vmentry_fail_vmexit:
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- return r;
+
+ if (!from_vmentry)
+ return 1;
+
+ load_vmcs12_host_state(vcpu, vmcs12);
+ vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
+ vmcs12->exit_qualification = exit_qual;
+ if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
+ vmx->nested.need_vmcs12_sync = true;
+ return 1;
}
/*
@@ -12694,14 +13430,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
struct vmcs12 *vmcs12;
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
- u32 exit_qual;
int ret;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_check_vmcs12(vcpu))
- goto out;
+ if (!nested_vmx_handle_enlightened_vmptrld(vcpu, true))
+ return 1;
+
+ if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)
+ return nested_vmx_failInvalid(vcpu);
vmcs12 = get_vmcs12(vcpu);
@@ -12711,13 +13449,16 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
* rather than RFLAGS.ZF, and no error number is stored to the
* VM-instruction error field.
*/
- if (vmcs12->hdr.shadow_vmcs) {
- nested_vmx_failInvalid(vcpu);
- goto out;
- }
+ if (vmcs12->hdr.shadow_vmcs)
+ return nested_vmx_failInvalid(vcpu);
- if (enable_shadow_vmcs)
+ if (vmx->nested.hv_evmcs) {
+ copy_enlightened_to_vmcs12(vmx);
+ /* Enlightened VMCS doesn't have launch state */
+ vmcs12->launch_state = !launch;
+ } else if (enable_shadow_vmcs) {
copy_shadow_to_vmcs12(vmx);
+ }
/*
* The nested entry process starts with enforcing various prerequisites
@@ -12729,59 +13470,37 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
* for misconfigurations which will anyway be caught by the processor
* when using the merged vmcs02.
*/
- if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS) {
- nested_vmx_failValid(vcpu,
- VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- goto out;
- }
+ if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- if (vmcs12->launch_state == launch) {
- nested_vmx_failValid(vcpu,
+ if (vmcs12->launch_state == launch)
+ return nested_vmx_failValid(vcpu,
launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
: VMXERR_VMRESUME_NONLAUNCHED_VMCS);
- goto out;
- }
ret = check_vmentry_prereqs(vcpu, vmcs12);
- if (ret) {
- nested_vmx_failValid(vcpu, ret);
- goto out;
- }
-
- /*
- * After this point, the trap flag no longer triggers a singlestep trap
- * on the vm entry instructions; don't call kvm_skip_emulated_instruction.
- * This is not 100% correct; for performance reasons, we delegate most
- * of the checks on host state to the processor. If those fail,
- * the singlestep trap is missed.
- */
- skip_emulated_instruction(vcpu);
-
- ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual);
- if (ret) {
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_INVALID_STATE, exit_qual);
- return 1;
- }
+ if (ret)
+ return nested_vmx_failValid(vcpu, ret);
/*
* We're finally done with prerequisite checking, and can start with
* the nested entry.
*/
-
vmx->nested.nested_run_pending = 1;
- ret = enter_vmx_non_root_mode(vcpu, &exit_qual);
- if (ret) {
- nested_vmx_entry_failure(vcpu, vmcs12, ret, exit_qual);
- vmx->nested.nested_run_pending = 0;
+ ret = nested_vmx_enter_non_root_mode(vcpu, true);
+ vmx->nested.nested_run_pending = !ret;
+ if (ret > 0)
return 1;
- }
+ else if (ret)
+ return nested_vmx_failValid(vcpu,
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/* Hide L1D cache contents from the nested guest. */
vmx->vcpu.arch.l1tf_flush_l1d = true;
/*
- * Must happen outside of enter_vmx_non_root_mode() as it will
+ * Must happen outside of nested_vmx_enter_non_root_mode() as it will
* also be used as part of restoring nVMX state for
* snapshot restore (migration).
*
@@ -12802,9 +13521,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
return kvm_vcpu_halt(vcpu);
}
return 1;
-
-out:
- return kvm_skip_emulated_instruction(vcpu);
}
/*
@@ -13118,24 +13834,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
kvm_clear_interrupt_queue(vcpu);
}
-static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12)
-{
- u32 entry_failure_code;
-
- nested_ept_uninit_mmu_context(vcpu);
-
- /*
- * Only PDPTE load can fail as the value of cr3 was checked on entry and
- * couldn't have changed.
- */
- if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
- nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
- if (!enable_ept)
- vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
-}
-
/*
* A part of what we need to when the nested L2 guest exits and we want to
* run its L1 parent, is to reset L1's guest state to the host state specified
@@ -13149,6 +13847,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
struct kvm_segment seg;
+ u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -13161,6 +13860,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
+ vmx_set_interrupt_shadow(vcpu, 0);
+
/*
* Note that calling vmx_set_cr0 is important, even if cr0 hasn't
* actually changed, because vmx_set_cr0 refers to efer set above.
@@ -13175,23 +13876,35 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
vmx_set_cr4(vcpu, vmcs12->host_cr4);
- load_vmcs12_mmu_host_state(vcpu, vmcs12);
+ nested_ept_uninit_mmu_context(vcpu);
+
+ /*
+ * Only PDPTE load can fail as the value of cr3 was checked on entry and
+ * couldn't have changed.
+ */
+ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+ if (!enable_ept)
+ vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
/*
- * If vmcs01 don't use VPID, CPU flushes TLB on every
+ * If vmcs01 doesn't use VPID, CPU flushes TLB on every
* VMEntry/VMExit. Thus, no need to flush TLB.
*
- * If vmcs12 uses VPID, TLB entries populated by L2 are
- * tagged with vmx->nested.vpid02 while L1 entries are tagged
- * with vmx->vpid. Thus, no need to flush TLB.
+ * If vmcs12 doesn't use VPID, L1 expects TLB to be
+ * flushed on every VMEntry/VMExit.
+ *
+ * Otherwise, we can preserve TLB entries as long as we are
+ * able to tag L1 TLB entries differently than L2 TLB entries.
*
- * Therefore, flush TLB only in case vmcs01 uses VPID and
- * vmcs12 don't use VPID as in this case L1 & L2 TLB entries
- * are both tagged with vmx->vpid.
+ * If vmcs12 uses EPT, we need to execute this flush on EPTP01
+ * and therefore we request the TLB flush to happen only after VMCS EPTP
+ * has been set by KVM_REQ_LOAD_CR3.
*/
if (enable_vpid &&
- !(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02)) {
- vmx_flush_tlb(vcpu, true);
+ (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) {
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
@@ -13271,6 +13984,140 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
}
+static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
+{
+ struct shared_msr_entry *efer_msr;
+ unsigned int i;
+
+ if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER)
+ return vmcs_read64(GUEST_IA32_EFER);
+
+ if (cpu_has_load_ia32_efer)
+ return host_efer;
+
+ for (i = 0; i < vmx->msr_autoload.guest.nr; ++i) {
+ if (vmx->msr_autoload.guest.val[i].index == MSR_EFER)
+ return vmx->msr_autoload.guest.val[i].value;
+ }
+
+ efer_msr = find_msr_entry(vmx, MSR_EFER);
+ if (efer_msr)
+ return efer_msr->data;
+
+ return host_efer;
+}
+
+static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmx_msr_entry g, h;
+ struct msr_data msr;
+ gpa_t gpa;
+ u32 i, j;
+
+ vcpu->arch.pat = vmcs_read64(GUEST_IA32_PAT);
+
+ if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+ /*
+ * L1's host DR7 is lost if KVM_GUESTDBG_USE_HW_BP is set
+ * as vmcs01.GUEST_DR7 contains a userspace defined value
+ * and vcpu->arch.dr7 is not squirreled away before the
+ * nested VMENTER (not worth adding a variable in nested_vmx).
+ */
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+ kvm_set_dr(vcpu, 7, DR7_FIXED_1);
+ else
+ WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
+ }
+
+ /*
+ * Note that calling vmx_set_{efer,cr0,cr4} is important as they
+ * handle a variety of side effects to KVM's software model.
+ */
+ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
+
+ vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
+
+ vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
+ vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
+
+ nested_ept_uninit_mmu_context(vcpu);
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
+ * from vmcs01 (if necessary). The PDPTRs are not loaded on
+ * VMFail, like everything else we just need to ensure our
+ * software model is up-to-date.
+ */
+ ept_save_pdptrs(vcpu);
+
+ kvm_mmu_reset_context(vcpu);
+
+ if (cpu_has_vmx_msr_bitmap())
+ vmx_update_msr_bitmap(vcpu);
+
+ /*
+ * This nasty bit of open coding is a compromise between blindly
+ * loading L1's MSRs using the exit load lists (incorrect emulation
+ * of VMFail), leaving the nested VM's MSRs in the software model
+ * (incorrect behavior) and snapshotting the modified MSRs (too
+ * expensive since the lists are unbound by hardware). For each
+ * MSR that was (prematurely) loaded from the nested VMEntry load
+ * list, reload it from the exit load list if it exists and differs
+ * from the guest value. The intent is to stuff host state as
+ * silently as possible, not to fully process the exit load list.
+ */
+ msr.host_initiated = false;
+ for (i = 0; i < vmcs12->vm_entry_msr_load_count; i++) {
+ gpa = vmcs12->vm_entry_msr_load_addr + (i * sizeof(g));
+ if (kvm_vcpu_read_guest(vcpu, gpa, &g, sizeof(g))) {
+ pr_debug_ratelimited(
+ "%s read MSR index failed (%u, 0x%08llx)\n",
+ __func__, i, gpa);
+ goto vmabort;
+ }
+
+ for (j = 0; j < vmcs12->vm_exit_msr_load_count; j++) {
+ gpa = vmcs12->vm_exit_msr_load_addr + (j * sizeof(h));
+ if (kvm_vcpu_read_guest(vcpu, gpa, &h, sizeof(h))) {
+ pr_debug_ratelimited(
+ "%s read MSR failed (%u, 0x%08llx)\n",
+ __func__, j, gpa);
+ goto vmabort;
+ }
+ if (h.index != g.index)
+ continue;
+ if (h.value == g.value)
+ break;
+
+ if (nested_vmx_load_msr_check(vcpu, &h)) {
+ pr_debug_ratelimited(
+ "%s check failed (%u, 0x%x, 0x%x)\n",
+ __func__, j, h.index, h.reserved);
+ goto vmabort;
+ }
+
+ msr.index = h.index;
+ msr.data = h.value;
+ if (kvm_set_msr(vcpu, &msr)) {
+ pr_debug_ratelimited(
+ "%s WRMSR failed (%u, 0x%x, 0x%llx)\n",
+ __func__, j, h.index, h.value);
+ goto vmabort;
+ }
+ }
+ }
+
+ return;
+
+vmabort:
+ nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
+}
+
/*
* Emulate an exit from nested guest (L2) to L1, i.e., prepare to run L1
* and modify vmcs12 to make it see what it would expect to see there if
@@ -13286,14 +14133,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
- /*
- * The only expected VM-instruction error is "VM entry with
- * invalid control field(s)." Anything else indicates a
- * problem with L0.
- */
- WARN_ON_ONCE(vmx->fail && (vmcs_read32(VM_INSTRUCTION_ERROR) !=
- VMXERR_ENTRY_INVALID_CONTROL_FIELD));
-
leave_guest_mode(vcpu);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
@@ -13320,12 +14159,19 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
if (nested_vmx_store_msr(vcpu, vmcs12->vm_exit_msr_store_addr,
vmcs12->vm_exit_msr_store_count))
nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL);
+ } else {
+ /*
+ * The only expected VM-instruction error is "VM entry with
+ * invalid control field(s)." Anything else indicates a
+ * problem with L0. And we should never get here with a
+ * VMFail of any type if early consistency checks are enabled.
+ */
+ WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
+ VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ WARN_ON_ONCE(nested_early_check);
}
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- vm_entry_controls_reset_shadow(vmx);
- vm_exit_controls_reset_shadow(vmx);
- vmx_segment_cache_clear(vmx);
/* Update any VMCS fields that might have changed while L2 ran */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
@@ -13369,8 +14215,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
*/
kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
- if (enable_shadow_vmcs && exit_reason != -1)
- vmx->nested.sync_shadow_vmcs = true;
+ if ((exit_reason != -1) && (enable_shadow_vmcs || vmx->nested.hv_evmcs))
+ vmx->nested.need_vmcs12_sync = true;
/* in case we halted in L2 */
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -13405,24 +14251,24 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
return;
}
-
+
/*
* After an early L2 VM-entry failure, we're now back
* in L1 which thinks it just finished a VMLAUNCH or
* VMRESUME instruction, so we need to set the failure
* flag and the VM-instruction error field of the VMCS
- * accordingly.
+ * accordingly, and skip the emulated instruction.
*/
- nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-
- load_vmcs12_mmu_host_state(vcpu, vmcs12);
+ (void)nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/*
- * The emulated instruction was already skipped in
- * nested_vmx_run, but the updated RIP was never
- * written back to the vmcs01.
+ * Restore L1's host state to KVM's software model. We're here
+ * because a consistency check was caught by hardware, which
+ * means some amount of guest state has been propagated to KVM's
+ * model and needs to be unwound to the host's state.
*/
- skip_emulated_instruction(vcpu);
+ nested_vmx_restore_host_state(vcpu);
+
vmx->fail = 0;
}
@@ -13435,26 +14281,7 @@ static void vmx_leave_nested(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
}
- free_nested(to_vmx(vcpu));
-}
-
-/*
- * L1's failure to enter L2 is a subset of a normal exit, as explained in
- * 23.7 "VM-entry failures during or after loading guest state" (this also
- * lists the acceptable exit-reason and exit-qualification parameters).
- * It should only be called before L2 actually succeeded to run, and when
- * vmcs01 is current (it doesn't leave_guest_mode() or switch vmcss).
- */
-static void nested_vmx_entry_failure(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12,
- u32 reason, unsigned long qualification)
-{
- load_vmcs12_host_state(vcpu, vmcs12);
- vmcs12->vm_exit_reason = reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
- vmcs12->exit_qualification = qualification;
- nested_vmx_succeed(vcpu);
- if (enable_shadow_vmcs)
- to_vmx(vcpu)->nested.sync_shadow_vmcs = true;
+ free_nested(vcpu);
}
static int vmx_check_intercept(struct kvm_vcpu *vcpu,
@@ -13880,7 +14707,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
if (vmx->nested.smm.guest_mode) {
vcpu->arch.hflags &= ~HF_SMM_MASK;
- ret = enter_vmx_non_root_mode(vcpu, NULL);
+ ret = nested_vmx_enter_non_root_mode(vcpu, false);
vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
@@ -13895,6 +14722,20 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
return 0;
}
+static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * In case we do two consecutive get/set_nested_state()s while L2 was
+ * running hv_evmcs may end up not being mapped (we map it from
+ * nested_vmx_run()/vmx_vcpu_run()). Check is_guest_mode() as we always
+ * have vmcs12 if it is true.
+ */
+ return is_guest_mode(vcpu) || vmx->nested.current_vmptr != -1ull ||
+ vmx->nested.hv_evmcs;
+}
+
static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
u32 user_data_size)
@@ -13914,12 +14755,16 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
vmx = to_vmx(vcpu);
vmcs12 = get_vmcs12(vcpu);
+
+ if (nested_vmx_allowed(vcpu) && vmx->nested.enlightened_vmcs_enabled)
+ kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
+
if (nested_vmx_allowed(vcpu) &&
(vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
kvm_state.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
kvm_state.vmx.vmcs_pa = vmx->nested.current_vmptr;
- if (vmx->nested.current_vmptr != -1ull) {
+ if (vmx_has_valid_vmcs12(vcpu)) {
kvm_state.size += VMCS12_SIZE;
if (is_guest_mode(vcpu) &&
@@ -13948,20 +14793,24 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
return -EFAULT;
- if (vmx->nested.current_vmptr == -1ull)
+ if (!vmx_has_valid_vmcs12(vcpu))
goto out;
/*
* When running L2, the authoritative vmcs12 state is in the
* vmcs02. When running L1, the authoritative vmcs12 state is
- * in the shadow vmcs linked to vmcs01, unless
- * sync_shadow_vmcs is set, in which case, the authoritative
+ * in the shadow or enlightened vmcs linked to vmcs01, unless
+ * need_vmcs12_sync is set, in which case, the authoritative
* vmcs12 state is in the vmcs12 already.
*/
- if (is_guest_mode(vcpu))
+ if (is_guest_mode(vcpu)) {
sync_vmcs12(vcpu, vmcs12);
- else if (enable_shadow_vmcs && !vmx->nested.sync_shadow_vmcs)
- copy_shadow_to_vmcs12(vmx);
+ } else if (!vmx->nested.need_vmcs12_sync) {
+ if (vmx->nested.hv_evmcs)
+ copy_enlightened_to_vmcs12(vmx);
+ else if (enable_shadow_vmcs)
+ copy_shadow_to_vmcs12(vmx);
+ }
if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12)))
return -EFAULT;
@@ -13989,6 +14838,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (kvm_state->format != 0)
return -EINVAL;
+ if (kvm_state->flags & KVM_STATE_NESTED_EVMCS)
+ nested_enable_evmcs(vcpu, NULL);
+
if (!nested_vmx_allowed(vcpu))
return kvm_state->vmx.vmxon_pa == -1ull ? 0 : -EINVAL;
@@ -14006,13 +14858,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (!page_address_valid(vcpu, kvm_state->vmx.vmxon_pa))
return -EINVAL;
- if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
- return -EINVAL;
-
- if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa ||
- !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa))
- return -EINVAL;
-
if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
return -EINVAL;
@@ -14042,7 +14887,25 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (ret)
return ret;
- set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa);
+ /* Empty 'VMXON' state is permitted */
+ if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+ return 0;
+
+ if (kvm_state->vmx.vmcs_pa != -1ull) {
+ if (kvm_state->vmx.vmcs_pa == kvm_state->vmx.vmxon_pa ||
+ !page_address_valid(vcpu, kvm_state->vmx.vmcs_pa))
+ return -EINVAL;
+
+ set_current_vmptr(vmx, kvm_state->vmx.vmcs_pa);
+ } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
+ /*
+ * Sync eVMCS upon entry as we may not have
+ * HV_X64_MSR_VP_ASSIST_PAGE set up yet.
+ */
+ vmx->nested.need_vmcs12_sync = true;
+ } else {
+ return -EINVAL;
+ }
if (kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON) {
vmx->nested.smm.vmxon = true;
@@ -14086,7 +14949,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
return -EINVAL;
vmx->nested.dirty_vmcs12 = true;
- ret = enter_vmx_non_root_mode(vcpu, NULL);
+ ret = nested_vmx_enter_non_root_mode(vcpu, false);
if (ret)
return -EINVAL;
@@ -14238,6 +15101,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.pre_enter_smm = vmx_pre_enter_smm,
.pre_leave_smm = vmx_pre_leave_smm,
.enable_smi_window = enable_smi_window,
+
+ .nested_enable_evmcs = nested_enable_evmcs,
};
static void vmx_cleanup_l1d_flush(void)
diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx_shadow_fields.h
index cd0c75f6d037..132432f375c2 100644
--- a/arch/x86/kvm/vmx_shadow_fields.h
+++ b/arch/x86/kvm/vmx_shadow_fields.h
@@ -28,7 +28,6 @@
*/
/* 16-bits */
-SHADOW_FIELD_RW(GUEST_CS_SELECTOR)
SHADOW_FIELD_RW(GUEST_INTR_STATUS)
SHADOW_FIELD_RW(GUEST_PML_INDEX)
SHADOW_FIELD_RW(HOST_FS_SELECTOR)
@@ -47,8 +46,8 @@ SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE)
SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD)
SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN)
SHADOW_FIELD_RW(TPR_THRESHOLD)
-SHADOW_FIELD_RW(GUEST_CS_LIMIT)
SHADOW_FIELD_RW(GUEST_CS_AR_BYTES)
+SHADOW_FIELD_RW(GUEST_SS_AR_BYTES)
SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO)
SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE)
@@ -61,8 +60,6 @@ SHADOW_FIELD_RW(GUEST_CR0)
SHADOW_FIELD_RW(GUEST_CR3)
SHADOW_FIELD_RW(GUEST_CR4)
SHADOW_FIELD_RW(GUEST_RFLAGS)
-SHADOW_FIELD_RW(GUEST_CS_BASE)
-SHADOW_FIELD_RW(GUEST_ES_BASE)
SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK)
SHADOW_FIELD_RW(CR0_READ_SHADOW)
SHADOW_FIELD_RW(CR4_READ_SHADOW)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ca717737347e..bdcb5babfb68 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 0;
+unsigned int __read_mostly lapic_timer_advance_ns = 1000;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
@@ -400,9 +400,51 @@ static int exception_type(int vector)
return EXCPT_FAULT;
}
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu)
+{
+ unsigned nr = vcpu->arch.exception.nr;
+ bool has_payload = vcpu->arch.exception.has_payload;
+ unsigned long payload = vcpu->arch.exception.payload;
+
+ if (!has_payload)
+ return;
+
+ switch (nr) {
+ case DB_VECTOR:
+ /*
+ * "Certain debug exceptions may clear bit 0-3. The
+ * remaining contents of the DR6 register are never
+ * cleared by the processor".
+ */
+ vcpu->arch.dr6 &= ~DR_TRAP_BITS;
+ /*
+ * DR6.RTM is set by all #DB exceptions that don't clear it.
+ */
+ vcpu->arch.dr6 |= DR6_RTM;
+ vcpu->arch.dr6 |= payload;
+ /*
+ * Bit 16 should be set in the payload whenever the #DB
+ * exception should clear DR6.RTM. This makes the payload
+ * compatible with the pending debug exceptions under VMX.
+ * Though not currently documented in the SDM, this also
+ * makes the payload compatible with the exit qualification
+ * for #DB exceptions under VMX.
+ */
+ vcpu->arch.dr6 ^= payload & DR6_RTM;
+ break;
+ case PF_VECTOR:
+ vcpu->arch.cr2 = payload;
+ break;
+ }
+
+ vcpu->arch.exception.has_payload = false;
+ vcpu->arch.exception.payload = 0;
+}
+EXPORT_SYMBOL_GPL(kvm_deliver_exception_payload);
+
static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
unsigned nr, bool has_error, u32 error_code,
- bool reinject)
+ bool has_payload, unsigned long payload, bool reinject)
{
u32 prev_nr;
int class1, class2;
@@ -424,6 +466,14 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
*/
WARN_ON_ONCE(vcpu->arch.exception.pending);
vcpu->arch.exception.injected = true;
+ if (WARN_ON_ONCE(has_payload)) {
+ /*
+ * A reinjected event has already
+ * delivered its payload.
+ */
+ has_payload = false;
+ payload = 0;
+ }
} else {
vcpu->arch.exception.pending = true;
vcpu->arch.exception.injected = false;
@@ -431,6 +481,22 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.has_error_code = has_error;
vcpu->arch.exception.nr = nr;
vcpu->arch.exception.error_code = error_code;
+ vcpu->arch.exception.has_payload = has_payload;
+ vcpu->arch.exception.payload = payload;
+ /*
+ * In guest mode, payload delivery should be deferred,
+ * so that the L1 hypervisor can intercept #PF before
+ * CR2 is modified (or intercept #DB before DR6 is
+ * modified under nVMX). However, for ABI
+ * compatibility with KVM_GET_VCPU_EVENTS and
+ * KVM_SET_VCPU_EVENTS, we can't delay payload
+ * delivery unless userspace has enabled this
+ * functionality via the per-VM capability,
+ * KVM_CAP_EXCEPTION_PAYLOAD.
+ */
+ if (!vcpu->kvm->arch.exception_payload_enabled ||
+ !is_guest_mode(vcpu))
+ kvm_deliver_exception_payload(vcpu);
return;
}
@@ -455,6 +521,8 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.has_error_code = true;
vcpu->arch.exception.nr = DF_VECTOR;
vcpu->arch.exception.error_code = 0;
+ vcpu->arch.exception.has_payload = false;
+ vcpu->arch.exception.payload = 0;
} else
/* replace previous exception with a new one in a hope
that instruction re-execution will regenerate lost
@@ -464,16 +532,29 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_multiple_exception(vcpu, nr, false, 0, false);
+ kvm_multiple_exception(vcpu, nr, false, 0, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);
void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_multiple_exception(vcpu, nr, false, 0, true);
+ kvm_multiple_exception(vcpu, nr, false, 0, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr,
+ unsigned long payload)
+{
+ kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false);
+}
+
+static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr,
+ u32 error_code, unsigned long payload)
+{
+ kvm_multiple_exception(vcpu, nr, true, error_code,
+ true, payload, false);
+}
+
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
if (err)
@@ -490,11 +571,13 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
++vcpu->stat.pf_guest;
vcpu->arch.exception.nested_apf =
is_guest_mode(vcpu) && fault->async_page_fault;
- if (vcpu->arch.exception.nested_apf)
+ if (vcpu->arch.exception.nested_apf) {
vcpu->arch.apf.nested_apf_token = fault->address;
- else
- vcpu->arch.cr2 = fault->address;
- kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
+ kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
+ } else {
+ kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code,
+ fault->address);
+ }
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
@@ -503,7 +586,7 @@ static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fau
if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
else
- vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+ vcpu->arch.mmu->inject_page_fault(vcpu, fault);
return fault->nested_page_fault;
}
@@ -517,13 +600,13 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- kvm_multiple_exception(vcpu, nr, true, error_code, false);
+ kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- kvm_multiple_exception(vcpu, nr, true, error_code, true);
+ kvm_multiple_exception(vcpu, nr, true, error_code, false, 0, true);
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
@@ -602,7 +685,7 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if ((pdpte[i] & PT_PRESENT_MASK) &&
(pdpte[i] &
- vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+ vcpu->arch.mmu->guest_rsvd_check.rsvd_bits_mask[0][2])) {
ret = 0;
goto out;
}
@@ -2477,7 +2560,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_KVM_PV_EOI_EN:
- if (kvm_lapic_enable_pv_eoi(vcpu, data))
+ if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8)))
return 1;
break;
@@ -2912,6 +2995,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_HYPERV_VP_INDEX:
case KVM_CAP_HYPERV_EVENTFD:
case KVM_CAP_HYPERV_TLBFLUSH:
+ case KVM_CAP_HYPERV_SEND_IPI:
+ case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
case KVM_CAP_PCI_SEGMENT:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -2930,6 +3015,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_IMMEDIATE_EXIT:
case KVM_CAP_GET_MSR_FEATURES:
case KVM_CAP_MSR_PLATFORM_INFO:
+ case KVM_CAP_EXCEPTION_PAYLOAD:
r = 1;
break;
case KVM_CAP_SYNC_REGS:
@@ -3185,11 +3271,16 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_x86_ops->vcpu_put(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
/*
- * If userspace has set any breakpoints or watchpoints, dr6 is restored
- * on every vmexit, but if not, we might have a stale dr6 from the
- * guest. do_debug expects dr6 to be cleared after it runs, do the same.
+ * Here dr6 is either zero or, if the guest has run and userspace
+ * has not set any breakpoints or watchpoints, it can be set to
+ * the guest dr6 (stored in vcpu->arch.dr6). do_debug expects dr6
+ * to be cleared after it runs, so clear the host register. However,
+ * MOV to DR can be expensive when running nested, omit it if
+ * vcpu->arch.dr6 is already zero: in that case, the host dr6 cannot
+ * currently be nonzero.
*/
- set_debugreg(0, 6);
+ if (vcpu->arch.dr6)
+ set_debugreg(0, 6);
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
@@ -3362,19 +3453,33 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
process_nmi(vcpu);
+
/*
- * FIXME: pass injected and pending separately. This is only
- * needed for nested virtualization, whose state cannot be
- * migrated yet. For now we can combine them.
+ * The API doesn't provide the instruction length for software
+ * exceptions, so don't report them. As long as the guest RIP
+ * isn't advanced, we should expect to encounter the exception
+ * again.
*/
- events->exception.injected =
- (vcpu->arch.exception.pending ||
- vcpu->arch.exception.injected) &&
- !kvm_exception_is_soft(vcpu->arch.exception.nr);
+ if (kvm_exception_is_soft(vcpu->arch.exception.nr)) {
+ events->exception.injected = 0;
+ events->exception.pending = 0;
+ } else {
+ events->exception.injected = vcpu->arch.exception.injected;
+ events->exception.pending = vcpu->arch.exception.pending;
+ /*
+ * For ABI compatibility, deliberately conflate
+ * pending and injected exceptions when
+ * KVM_CAP_EXCEPTION_PAYLOAD isn't enabled.
+ */
+ if (!vcpu->kvm->arch.exception_payload_enabled)
+ events->exception.injected |=
+ vcpu->arch.exception.pending;
+ }
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
- events->exception.pad = 0;
events->exception.error_code = vcpu->arch.exception.error_code;
+ events->exception_has_payload = vcpu->arch.exception.has_payload;
+ events->exception_payload = vcpu->arch.exception.payload;
events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -3398,6 +3503,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SHADOW
| KVM_VCPUEVENT_VALID_SMM);
+ if (vcpu->kvm->arch.exception_payload_enabled)
+ events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+
memset(&events->reserved, 0, sizeof(events->reserved));
}
@@ -3409,12 +3517,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW
- | KVM_VCPUEVENT_VALID_SMM))
+ | KVM_VCPUEVENT_VALID_SMM
+ | KVM_VCPUEVENT_VALID_PAYLOAD))
return -EINVAL;
- if (events->exception.injected &&
- (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR ||
- is_guest_mode(vcpu)))
+ if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
+ if (!vcpu->kvm->arch.exception_payload_enabled)
+ return -EINVAL;
+ if (events->exception.pending)
+ events->exception.injected = 0;
+ else
+ events->exception_has_payload = 0;
+ } else {
+ events->exception.pending = 0;
+ events->exception_has_payload = 0;
+ }
+
+ if ((events->exception.injected || events->exception.pending) &&
+ (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
return -EINVAL;
/* INITs are latched while in SMM */
@@ -3424,11 +3544,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return -EINVAL;
process_nmi(vcpu);
- vcpu->arch.exception.injected = false;
- vcpu->arch.exception.pending = events->exception.injected;
+ vcpu->arch.exception.injected = events->exception.injected;
+ vcpu->arch.exception.pending = events->exception.pending;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
vcpu->arch.exception.error_code = events->exception.error_code;
+ vcpu->arch.exception.has_payload = events->exception_has_payload;
+ vcpu->arch.exception.payload = events->exception_payload;
vcpu->arch.interrupt.injected = events->interrupt.injected;
vcpu->arch.interrupt.nr = events->interrupt.nr;
@@ -3694,6 +3816,10 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
struct kvm_enable_cap *cap)
{
+ int r;
+ uint16_t vmcs_version;
+ void __user *user_ptr;
+
if (cap->flags)
return -EINVAL;
@@ -3706,6 +3832,16 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
return -EINVAL;
return kvm_hv_activate_synic(vcpu, cap->cap ==
KVM_CAP_HYPERV_SYNIC2);
+ case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
+ r = kvm_x86_ops->nested_enable_evmcs(vcpu, &vmcs_version);
+ if (!r) {
+ user_ptr = (void __user *)(uintptr_t)cap->args[0];
+ if (copy_to_user(user_ptr, &vmcs_version,
+ sizeof(vmcs_version)))
+ r = -EFAULT;
+ }
+ return r;
+
default:
return -EINVAL;
}
@@ -4047,11 +4183,13 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
if (kvm_state.flags &
- ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE))
+ ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE
+ | KVM_STATE_NESTED_EVMCS))
break;
/* nested_run_pending implies guest_mode. */
- if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING)
+ if ((kvm_state.flags & KVM_STATE_NESTED_RUN_PENDING)
+ && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
break;
r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
@@ -4363,6 +4501,10 @@ split_irqchip_unlock:
kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
r = 0;
break;
+ case KVM_CAP_EXCEPTION_PAYLOAD:
+ kvm->arch.exception_payload_enabled = cap->args[0];
+ r = 0;
+ break;
default:
r = -EINVAL;
break;
@@ -4803,7 +4945,7 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
/* NPT walks are always user-walks */
access |= PFERR_USER_MASK;
- t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
+ t_gpa = vcpu->arch.mmu->gva_to_gpa(vcpu, gpa, access, exception);
return t_gpa;
}
@@ -5889,7 +6031,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
if (WARN_ON_ONCE(is_guest_mode(vcpu)))
return false;
- if (!vcpu->arch.mmu.direct_map) {
+ if (!vcpu->arch.mmu->direct_map) {
/*
* Write permission should be allowed since only
* write access need to be emulated.
@@ -5922,7 +6064,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
kvm_release_pfn_clean(pfn);
/* The instructions are well-emulated on direct mmu. */
- if (vcpu->arch.mmu.direct_map) {
+ if (vcpu->arch.mmu->direct_map) {
unsigned int indirect_shadow_pages;
spin_lock(&vcpu->kvm->mmu_lock);
@@ -5989,7 +6131,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
vcpu->arch.last_retry_eip = ctxt->eip;
vcpu->arch.last_retry_addr = cr2;
- if (!vcpu->arch.mmu.direct_map)
+ if (!vcpu->arch.mmu->direct_map)
gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
@@ -6049,14 +6191,7 @@ static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
kvm_run->exit_reason = KVM_EXIT_DEBUG;
*r = EMULATE_USER_EXIT;
} else {
- /*
- * "Certain debug exceptions may clear bit 0-3. The
- * remaining contents of the DR6 register are never
- * cleared by the processor".
- */
- vcpu->arch.dr6 &= ~15;
- vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
- kvm_queue_exception(vcpu, DB_VECTOR);
+ kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BS);
}
}
@@ -6995,10 +7130,22 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
X86_EFLAGS_RF);
- if (vcpu->arch.exception.nr == DB_VECTOR &&
- (vcpu->arch.dr7 & DR7_GD)) {
- vcpu->arch.dr7 &= ~DR7_GD;
- kvm_update_dr7(vcpu);
+ if (vcpu->arch.exception.nr == DB_VECTOR) {
+ /*
+ * This code assumes that nSVM doesn't use
+ * check_nested_events(). If it does, the
+ * DR6/DR7 changes should happen before L1
+ * gets a #VMEXIT for an intercepted #DB in
+ * L2. (Under VMX, on the other hand, the
+ * DR6/DR7 changes should not happen in the
+ * event of a VM-exit to L1 for an intercepted
+ * #DB in L2.)
+ */
+ kvm_deliver_exception_payload(vcpu);
+ if (vcpu->arch.dr7 & DR7_GD) {
+ vcpu->arch.dr7 &= ~DR7_GD;
+ kvm_update_dr7(vcpu);
+ }
}
kvm_x86_ops->queue_exception(vcpu);
@@ -8478,7 +8625,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
kvm_vcpu_mtrr_init(vcpu);
vcpu_load(vcpu);
kvm_vcpu_reset(vcpu, false);
- kvm_mmu_setup(vcpu);
+ kvm_init_mmu(vcpu, false);
vcpu_put(vcpu);
return 0;
}
@@ -9327,7 +9474,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
{
int r;
- if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
+ if ((vcpu->arch.mmu->direct_map != work->arch.direct_map) ||
work->wakeup_all)
return;
@@ -9335,11 +9482,11 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
if (unlikely(r))
return;
- if (!vcpu->arch.mmu.direct_map &&
- work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu))
+ if (!vcpu->arch.mmu->direct_map &&
+ work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
return;
- vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true);
+ vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
}
static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -9463,6 +9610,8 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
vcpu->arch.exception.nr = 0;
vcpu->arch.exception.has_error_code = false;
vcpu->arch.exception.error_code = 0;
+ vcpu->arch.exception.has_payload = false;
+ vcpu->arch.exception.payload = 0;
} else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
fault.vector = PF_VECTOR;
fault.error_code_valid = true;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 67b9568613f3..224cd0a47568 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -266,6 +266,8 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu,
int handle_ud(struct kvm_vcpu *vcpu);
+void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu);
+
void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu);
u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 7a8fc26c1115..faca978ebf9d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end)
set_memory_np_noalias(begin_ul, len_pages);
}
+void __weak mem_encrypt_free_decrypted_mem(void) { }
+
void __ref free_initmem(void)
{
e820__reallocate_tables();
+ mem_encrypt_free_decrypted_mem();
+
free_kernel_image_pages(&__init_begin, &__init_end);
}
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index b2de398d1fd3..006f373f54ab 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -348,6 +348,30 @@ bool sev_active(void)
EXPORT_SYMBOL(sev_active);
/* Architecture __weak replacement functions */
+void __init mem_encrypt_free_decrypted_mem(void)
+{
+ unsigned long vaddr, vaddr_end, npages;
+ int r;
+
+ vaddr = (unsigned long)__start_bss_decrypted_unused;
+ vaddr_end = (unsigned long)__end_bss_decrypted;
+ npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
+
+ /*
+ * The unused memory range was mapped decrypted, change the encryption
+ * attribute from decrypted to encrypted before freeing it.
+ */
+ if (mem_encrypt_active()) {
+ r = set_memory_encrypted(vaddr, npages);
+ if (r) {
+ pr_warn("failed to free unused decrypted pages\n");
+ return;
+ }
+ }
+
+ free_init_pages("unused decrypted", vaddr, vaddr_end);
+}
+
void __init mem_encrypt_init(void)
{
if (!sme_me_mask)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ae394552fb94..089e78c4effd 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
{
unsigned long address = __fix_to_virt(idx);
+#ifdef CONFIG_X86_64
+ /*
+ * Ensure that the static initial page tables are covering the
+ * fixmap completely.
+ */
+ BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
+ (FIXMAP_PMD_NUM * PTRS_PER_PTE));
+#endif
+
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2fe5c9b1816b..dd461c0167ef 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
/* L3_k[511] -> level2_fixmap_pgt */
convert_pfn_mfn(level3_kernel_pgt);
- /* L3_k[511][506] -> level1_fixmap_pgt */
+ /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */
convert_pfn_mfn(level2_fixmap_pgt);
/* We get [511][511] and have Xen's version of level2_kernel_pgt */
@@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
- set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+ for (i = 0; i < FIXMAP_PMD_NUM; i++) {
+ set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE,
+ PAGE_KERNEL_RO);
+ }
/* Pin down new L4 */
pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 7d00d4ad44d4..95997e6c0696 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs,
irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id)
{
int err, ret = IRQ_NONE;
- struct pt_regs regs;
+ struct pt_regs regs = {0};
const struct xen_pmu_data *xenpmu_data = get_xenpmu_data();
uint8_t xenpmu_flags = get_xenpmu_flags();
diff --git a/block/bio.c b/block/bio.c
index 8c680a776171..0093bed81c0e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op,
const int sgrp = op_stat_group(req_op);
int cpu = part_stat_lock();
- part_stat_add(cpu, part, ticks[sgrp], duration);
+ part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration));
part_round_stats(q, cpu, part);
part_dec_in_flight(q, part, op_is_write(req_op));
diff --git a/block/blk-core.c b/block/blk-core.c
index 4dbc93f43b38..cff0a60ee200 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2733,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now)
* containing request is enough.
*/
if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
- unsigned long duration;
const int sgrp = op_stat_group(req_op(req));
struct hd_struct *part;
int cpu;
- duration = nsecs_to_jiffies(now - req->start_time_ns);
cpu = part_stat_lock();
part = req->part;
part_stat_inc(cpu, part, ios[sgrp]);
- part_stat_add(cpu, part, ticks[sgrp], duration);
+ part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns);
part_round_stats(req->q, cpu, part);
part_dec_in_flight(req->q, part, rq_data_dir(req));
diff --git a/block/genhd.c b/block/genhd.c
index 8cc719a37b32..be5bab20b2ab 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v)
part_stat_read(hd, ios[STAT_READ]),
part_stat_read(hd, merges[STAT_READ]),
part_stat_read(hd, sectors[STAT_READ]),
- jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),
+ (unsigned int)part_stat_read_msecs(hd, STAT_READ),
part_stat_read(hd, ios[STAT_WRITE]),
part_stat_read(hd, merges[STAT_WRITE]),
part_stat_read(hd, sectors[STAT_WRITE]),
- jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
+ (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
inflight[0],
jiffies_to_msecs(part_stat_read(hd, io_ticks)),
jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
part_stat_read(hd, ios[STAT_DISCARD]),
part_stat_read(hd, merges[STAT_DISCARD]),
part_stat_read(hd, sectors[STAT_DISCARD]),
- jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))
+ (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
);
}
disk_part_iter_exit(&piter);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 5a8975a1201c..d3d14e81fb12 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev,
part_stat_read(p, ios[STAT_READ]),
part_stat_read(p, merges[STAT_READ]),
(unsigned long long)part_stat_read(p, sectors[STAT_READ]),
- jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),
+ (unsigned int)part_stat_read_msecs(p, STAT_READ),
part_stat_read(p, ios[STAT_WRITE]),
part_stat_read(p, merges[STAT_WRITE]),
(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
- jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
+ (unsigned int)part_stat_read_msecs(p, STAT_WRITE),
inflight[0],
jiffies_to_msecs(part_stat_read(p, io_ticks)),
jiffies_to_msecs(part_stat_read(p, time_in_queue)),
part_stat_read(p, ios[STAT_DISCARD]),
part_stat_read(p, merges[STAT_DISCARD]),
(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
- jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));
+ (unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
}
ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index d8e159feb573..89110dfc7127 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -90,14 +90,17 @@ config EFI_ARMSTUB
config EFI_ARMSTUB_DTB_LOADER
bool "Enable the DTB loader"
depends on EFI_ARMSTUB
+ default y
help
Select this config option to add support for the dtb= command
line parameter, allowing a device tree blob to be loaded into
memory from the EFI System Partition by the stub.
- The device tree is typically provided by the platform or by
- the bootloader, so this option is mostly for development
- purposes only.
+ If the device tree is provided by the platform or by
+ the bootloader this option may not be needed.
+ But, for various development reasons and to maintain existing
+ functionality for bootloaders that do not have such support
+ this option is necessary.
config EFI_BOOTLOADER_CONTROL
tristate "EFI Bootloader Control"
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index e11ab12fbdf2..800986a79704 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -528,8 +528,8 @@ static int usbhs_omap_get_dt_pdata(struct device *dev,
}
static const struct of_device_id usbhs_child_match_table[] = {
- { .compatible = "ti,omap-ehci", },
- { .compatible = "ti,omap-ohci", },
+ { .compatible = "ti,ehci-omap", },
+ { .compatible = "ti,ohci-omap3", },
{ }
};
@@ -855,6 +855,7 @@ static struct platform_driver usbhs_omap_driver = {
.pm = &usbhsomap_dev_pm_ops,
.of_match_table = usbhs_omap_dt_ids,
},
+ .probe = usbhs_omap_probe,
.remove = usbhs_omap_remove,
};
@@ -864,9 +865,9 @@ MODULE_ALIAS("platform:" USBHS_DRIVER_NAME);
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("usb host common core driver for omap EHCI and OHCI");
-static int __init omap_usbhs_drvinit(void)
+static int omap_usbhs_drvinit(void)
{
- return platform_driver_probe(&usbhs_omap_driver, usbhs_omap_probe);
+ return platform_driver_register(&usbhs_omap_driver);
}
/*
@@ -878,7 +879,7 @@ static int __init omap_usbhs_drvinit(void)
*/
fs_initcall_sync(omap_usbhs_drvinit);
-static void __exit omap_usbhs_drvexit(void)
+static void omap_usbhs_drvexit(void)
{
platform_driver_unregister(&usbhs_omap_driver);
}
diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index fb1afe55bf53..8d48371caaa2 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -379,7 +379,7 @@ static const struct intel_padgroup cnlh_community1_gpps[] = {
static const struct intel_padgroup cnlh_community3_gpps[] = {
CNL_GPP(0, 155, 178, 192), /* GPP_K */
CNL_GPP(1, 179, 202, 224), /* GPP_H */
- CNL_GPP(2, 203, 215, 258), /* GPP_E */
+ CNL_GPP(2, 203, 215, 256), /* GPP_E */
CNL_GPP(3, 216, 239, 288), /* GPP_F */
CNL_GPP(4, 240, 248, CNL_NO_GPIO), /* SPI */
};
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 62b009b27eda..ec8dafc94694 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -747,13 +747,63 @@ static const struct pinctrl_desc intel_pinctrl_desc = {
.owner = THIS_MODULE,
};
+/**
+ * intel_gpio_to_pin() - Translate from GPIO offset to pin number
+ * @pctrl: Pinctrl structure
+ * @offset: GPIO offset from gpiolib
+ * @commmunity: Community is filled here if not %NULL
+ * @padgrp: Pad group is filled here if not %NULL
+ *
+ * When coming through gpiolib irqchip, the GPIO offset is not
+ * automatically translated to pinctrl pin number. This function can be
+ * used to find out the corresponding pinctrl pin.
+ */
+static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset,
+ const struct intel_community **community,
+ const struct intel_padgroup **padgrp)
+{
+ int i;
+
+ for (i = 0; i < pctrl->ncommunities; i++) {
+ const struct intel_community *comm = &pctrl->communities[i];
+ int j;
+
+ for (j = 0; j < comm->ngpps; j++) {
+ const struct intel_padgroup *pgrp = &comm->gpps[j];
+
+ if (pgrp->gpio_base < 0)
+ continue;
+
+ if (offset >= pgrp->gpio_base &&
+ offset < pgrp->gpio_base + pgrp->size) {
+ int pin;
+
+ pin = pgrp->base + offset - pgrp->gpio_base;
+ if (community)
+ *community = comm;
+ if (padgrp)
+ *padgrp = pgrp;
+
+ return pin;
+ }
+ }
+ }
+
+ return -EINVAL;
+}
+
static int intel_gpio_get(struct gpio_chip *chip, unsigned offset)
{
struct intel_pinctrl *pctrl = gpiochip_get_data(chip);
void __iomem *reg;
u32 padcfg0;
+ int pin;
+
+ pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL);
+ if (pin < 0)
+ return -EINVAL;
- reg = intel_get_padcfg(pctrl, offset, PADCFG0);
+ reg = intel_get_padcfg(pctrl, pin, PADCFG0);
if (!reg)
return -EINVAL;
@@ -770,8 +820,13 @@ static void intel_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
unsigned long flags;
void __iomem *reg;
u32 padcfg0;
+ int pin;
+
+ pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL);
+ if (pin < 0)
+ return;
- reg = intel_get_padcfg(pctrl, offset, PADCFG0);
+ reg = intel_get_padcfg(pctrl, pin, PADCFG0);
if (!reg)
return;
@@ -790,8 +845,13 @@ static int intel_gpio_get_direction(struct gpio_chip *chip, unsigned int offset)
struct intel_pinctrl *pctrl = gpiochip_get_data(chip);
void __iomem *reg;
u32 padcfg0;
+ int pin;
- reg = intel_get_padcfg(pctrl, offset, PADCFG0);
+ pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL);
+ if (pin < 0)
+ return -EINVAL;
+
+ reg = intel_get_padcfg(pctrl, pin, PADCFG0);
if (!reg)
return -EINVAL;
@@ -827,51 +887,6 @@ static const struct gpio_chip intel_gpio_chip = {
.set_config = gpiochip_generic_config,
};
-/**
- * intel_gpio_to_pin() - Translate from GPIO offset to pin number
- * @pctrl: Pinctrl structure
- * @offset: GPIO offset from gpiolib
- * @commmunity: Community is filled here if not %NULL
- * @padgrp: Pad group is filled here if not %NULL
- *
- * When coming through gpiolib irqchip, the GPIO offset is not
- * automatically translated to pinctrl pin number. This function can be
- * used to find out the corresponding pinctrl pin.
- */
-static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset,
- const struct intel_community **community,
- const struct intel_padgroup **padgrp)
-{
- int i;
-
- for (i = 0; i < pctrl->ncommunities; i++) {
- const struct intel_community *comm = &pctrl->communities[i];
- int j;
-
- for (j = 0; j < comm->ngpps; j++) {
- const struct intel_padgroup *pgrp = &comm->gpps[j];
-
- if (pgrp->gpio_base < 0)
- continue;
-
- if (offset >= pgrp->gpio_base &&
- offset < pgrp->gpio_base + pgrp->size) {
- int pin;
-
- pin = pgrp->base + offset - pgrp->gpio_base;
- if (community)
- *community = comm;
- if (padgrp)
- *padgrp = pgrp;
-
- return pin;
- }
- }
- }
-
- return -EINVAL;
-}
-
static int intel_gpio_irq_reqres(struct irq_data *d)
{
struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 7bafa703a992..84575baceebc 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -1040,18 +1040,33 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
return ret;
for (i = 0; i < count; i++) {
- /* Retry eagain maps */
- if (map_ops[i].status == GNTST_eagain)
- gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
- &map_ops[i].status, __func__);
-
- if (map_ops[i].status == GNTST_okay) {
+ switch (map_ops[i].status) {
+ case GNTST_okay:
+ {
struct xen_page_foreign *foreign;
SetPageForeign(pages[i]);
foreign = xen_page_foreign(pages[i]);
foreign->domid = map_ops[i].dom;
foreign->gref = map_ops[i].ref;
+ break;
+ }
+
+ case GNTST_no_device_space:
+ pr_warn_ratelimited("maptrack limit reached, can't map all guest pages\n");
+ break;
+
+ case GNTST_eagain:
+ /* Retry eagain maps */
+ gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref,
+ map_ops + i,
+ &map_ops[i].status, __func__);
+ /* Test status in next loop iteration. */
+ i--;
+ break;
+
+ default:
+ break;
}
}
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 57864422a2c8..25c08c6c7f99 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -83,10 +83,10 @@ struct partition {
} __attribute__((packed));
struct disk_stats {
+ u64 nsecs[NR_STAT_GROUPS];
unsigned long sectors[NR_STAT_GROUPS];
unsigned long ios[NR_STAT_GROUPS];
unsigned long merges[NR_STAT_GROUPS];
- unsigned long ticks[NR_STAT_GROUPS];
unsigned long io_ticks;
unsigned long time_in_queue;
};
@@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part)
#endif /* CONFIG_SMP */
+#define part_stat_read_msecs(part, which) \
+ div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC)
+
#define part_stat_read_accum(part, field) \
(part_stat_read(part, field[STAT_READ]) + \
part_stat_read(part, field[STAT_WRITE]) + \
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 8bdbb5f29494..74b0aa9c7499 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -357,6 +357,8 @@
#define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt)
#define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb)
+#define GITS_CBASER_ADDRESS(cbaser) ((cbaser) & GENMASK_ULL(51, 12))
+
#define GITS_BASER_NR_REGS 8
#define GITS_BASER_VALID (1ULL << 63)
@@ -388,6 +390,9 @@
#define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48)
#define GITS_BASER_PHYS_52_to_48(phys) \
(((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12)
+#define GITS_BASER_ADDR_48_to_52(baser) \
+ (((baser) & GENMASK_ULL(47, 16)) | (((baser) >> 12) & 0xf) << 48)
+
#define GITS_BASER_SHAREABILITY_SHIFT (10)
#define GITS_BASER_InnerShareable \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h
index 8a125701ef7b..50bed4f89c1a 100644
--- a/include/linux/mfd/da9063/pdata.h
+++ b/include/linux/mfd/da9063/pdata.h
@@ -21,7 +21,7 @@
/*
* Regulator configuration
*/
-/* DA9063 regulator IDs */
+/* DA9063 and DA9063L regulator IDs */
enum {
/* BUCKs */
DA9063_ID_BCORE1,
@@ -37,18 +37,20 @@ enum {
DA9063_ID_BMEM_BIO_MERGED,
/* When two BUCKs are merged, they cannot be reused separately */
- /* LDOs */
+ /* LDOs on both DA9063 and DA9063L */
+ DA9063_ID_LDO3,
+ DA9063_ID_LDO7,
+ DA9063_ID_LDO8,
+ DA9063_ID_LDO9,
+ DA9063_ID_LDO11,
+
+ /* DA9063-only LDOs */
DA9063_ID_LDO1,
DA9063_ID_LDO2,
- DA9063_ID_LDO3,
DA9063_ID_LDO4,
DA9063_ID_LDO5,
DA9063_ID_LDO6,
- DA9063_ID_LDO7,
- DA9063_ID_LDO8,
- DA9063_ID_LDO9,
DA9063_ID_LDO10,
- DA9063_ID_LDO11,
};
/* Regulators platform data */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 7f2ff3a76995..2b7a652c9fa4 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -420,13 +420,19 @@ struct kvm_run {
struct kvm_coalesced_mmio_zone {
__u64 addr;
__u32 size;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
};
struct kvm_coalesced_mmio {
__u64 phys_addr;
__u32 len;
- __u32 pad;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
__u8 data[8];
};
@@ -752,6 +758,15 @@ struct kvm_ppc_resize_hpt {
#define KVM_S390_SIE_PAGE_OFFSET 1
/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK 0xffULL
+#define KVM_VM_TYPE_ARM_IPA_SIZE(x) \
+ ((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+/*
* ioctls for /dev/kvm fds:
*/
#define KVM_GET_API_VERSION _IO(KVMIO, 0x00)
@@ -955,6 +970,11 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
#define KVM_CAP_MSR_PLATFORM_INFO 159
#define KVM_CAP_PPC_NESTED_HV 160
+#define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
+#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 86299efa804a..b09875f580d5 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -288,6 +288,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -299,7 +300,10 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 has_error_code;
- __u8 pad;
+ union {
+ __u8 pad;
+ __u8 pending;
+ };
__u32 error_code;
} exception;
struct {
@@ -322,7 +326,9 @@ struct kvm_vcpu_events {
__u8 smm_inside_nmi;
__u8 latched_init;
} smi;
- __u32 reserved[9];
+ __u8 reserved[27];
+ __u8 exception_has_payload;
+ __u64 exception_payload;
};
/* for KVM_GET/SET_DEBUGREGS */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 07548de5c988..2875ce85b322 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -719,6 +719,7 @@ struct kvm_ppc_one_seg_page_size {
#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
#define KVM_PPC_1T_SEGMENTS 0x00000002
+#define KVM_PPC_NO_HASH 0x00000004
struct kvm_ppc_smmu_info {
__u64 flags;
@@ -952,6 +953,11 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_HPAGE_1M 156
#define KVM_CAP_NESTED_STATE 157
#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
+#define KVM_CAP_PPC_NESTED_HV 160
+#define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
+#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 13a861135127..6eb9bacd1948 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2abd0f112627..bdb94939fd60 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -50,6 +50,7 @@
#include "libbpf.h"
#include "bpf.h"
#include "btf.h"
+#include "str_error.h"
#ifndef EM_BPF
#define EM_BPF 247
@@ -469,7 +470,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
obj->efile.fd = open(obj->path, O_RDONLY);
if (obj->efile.fd < 0) {
char errmsg[STRERR_BUFSIZE];
- char *cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ char *cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("failed to open %s: %s\n", obj->path, cp);
return -errno;
@@ -810,8 +811,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
data->d_size, name, idx);
if (err) {
char errmsg[STRERR_BUFSIZE];
- char *cp = strerror_r(-err, errmsg,
- sizeof(errmsg));
+ char *cp = str_error(-err, errmsg, sizeof(errmsg));
pr_warning("failed to alloc program %s (%s): %s",
name, obj->path, cp);
@@ -1140,7 +1140,7 @@ bpf_object__create_maps(struct bpf_object *obj)
*pfd = bpf_create_map_xattr(&create_attr);
if (*pfd < 0 && create_attr.btf_key_type_id) {
- cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
map->name, cp, errno);
create_attr.btf_fd = 0;
@@ -1155,7 +1155,7 @@ bpf_object__create_maps(struct bpf_object *obj)
size_t j;
err = *pfd;
- cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("failed to create map (name: '%s'): %s\n",
map->name, cp);
for (j = 0; j < i; j++)
@@ -1339,7 +1339,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
}
ret = -LIBBPF_ERRNO__LOAD;
- cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("load bpf program failed: %s\n", cp);
if (log_buf && log_buf[0] != '\0') {
@@ -1654,7 +1654,7 @@ static int check_path(const char *path)
dir = dirname(dname);
if (statfs(dir, &st_fs)) {
- cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("failed to statfs %s: %s\n", dir, cp);
err = -errno;
}
@@ -1690,7 +1690,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
}
if (bpf_obj_pin(prog->instances.fds[instance], path)) {
- cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("failed to pin program: %s\n", cp);
return -errno;
}
@@ -1708,7 +1708,7 @@ static int make_dir(const char *path)
err = -errno;
if (err) {
- cp = strerror_r(-err, errmsg, sizeof(errmsg));
+ cp = str_error(-err, errmsg, sizeof(errmsg));
pr_warning("failed to mkdir %s: %s\n", path, cp);
}
return err;
@@ -1770,7 +1770,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
}
if (bpf_obj_pin(map->fd, path)) {
- cp = strerror_r(errno, errmsg, sizeof(errmsg));
+ cp = str_error(errno, errmsg, sizeof(errmsg));
pr_warning("failed to pin map: %s\n", cp);
return -errno;
}
diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c
new file mode 100644
index 000000000000..b8798114a357
--- /dev/null
+++ b/tools/lib/bpf/str_error.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: LGPL-2.1
+#undef _GNU_SOURCE
+#include <string.h>
+#include <stdio.h>
+#include "str_error.h"
+
+/*
+ * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl
+ * libc, while checking strerror_r() return to avoid having to check this in
+ * all places calling it.
+ */
+char *str_error(int err, char *dst, int len)
+{
+ int ret = strerror_r(err, dst, len);
+ if (ret)
+ snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret);
+ return dst;
+}
diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h
new file mode 100644
index 000000000000..355b1db571d1
--- /dev/null
+++ b/tools/lib/bpf/str_error.h
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: LGPL-2.1
+#ifndef BPF_STR_ERROR
+#define BPF_STR_ERROR
+
+char *str_error(int err, char *dst, int len);
+#endif // BPF_STR_ERROR
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 42261a9b280e..ac841bc5c35b 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -280,7 +280,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt
mv $@+ $@
ifdef USE_ASCIIDOCTOR
-$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt
$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
$(ASCIIDOC) -b manpage -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 5c34752e1cff..6210ba41c29e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,8 @@
-cr4_cpuid_sync_test
-platform_info_test
-set_sregs_test
-sync_regs_test
-vmx_tsc_adjust_test
-state_test
+/x86_64/cr4_cpuid_sync_test
+/x86_64/evmcs_test
+/x86_64/platform_info_test
+/x86_64/set_sregs_test
+/x86_64/sync_regs_test
+/x86_64/vmx_tsc_adjust_test
+/x86_64/state_test
+/dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ec32dad3c3f0..01a219229238 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,26 +1,30 @@
all:
-top_srcdir = ../../../../
+top_srcdir = ../../../..
UNAME_M := $(shell uname -m)
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c lib/vmx.c
-
-TEST_GEN_PROGS_x86_64 = platform_info_test
-TEST_GEN_PROGS_x86_64 += set_sregs_test
-TEST_GEN_PROGS_x86_64 += sync_regs_test
-TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
-TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test
-TEST_GEN_PROGS_x86_64 += state_test
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c
+LIBKVM_aarch64 = lib/aarch64/processor.c
+
+TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
+TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_aarch64 += dirty_log_test
+
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
LDFLAGS += -pthread
# After inclusion, $(OUTPUT) is defined and
@@ -29,7 +33,7 @@ include ../lib.mk
STATIC_LIBS := $(OUTPUT)/libkvm.a
LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS)
+EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
@@ -41,3 +45,12 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
all: $(STATIC_LIBS)
$(TEST_GEN_PROGS): $(STATIC_LIBS)
$(STATIC_LIBS):| khdr
+
+cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
+cscope:
+ $(RM) cscope.*
+ (find $(include_paths) -name '*.h' \
+ -exec realpath --relative-base=$(PWD) {} \;; \
+ find . -name '*.c' \
+ -exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files
+ cscope -b
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 0c2cdc105f96..d59820cc2d39 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -5,6 +5,8 @@
* Copyright (C) 2018, Red Hat, Inc.
*/
+#define _GNU_SOURCE /* for program_invocation_name */
+
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
@@ -15,76 +17,78 @@
#include "test_util.h"
#include "kvm_util.h"
+#include "processor.h"
+
+#define DEBUG printf
-#define DEBUG printf
+#define VCPU_ID 1
-#define VCPU_ID 1
/* The memory slot index to track dirty pages */
-#define TEST_MEM_SLOT_INDEX 1
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define TEST_MEM_OFFSET (1ULL << 30) /* 1G */
-/* Size of the testing memory slot */
-#define TEST_MEM_PAGES (1ULL << 18) /* 1G for 4K pages */
+#define TEST_MEM_SLOT_INDEX 1
+
+/* Default guest test memory offset, 1G */
+#define DEFAULT_GUEST_TEST_MEM 0x40000000
+
/* How many pages to dirty for each guest loop */
-#define TEST_PAGES_PER_LOOP 1024
+#define TEST_PAGES_PER_LOOP 1024
+
/* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define TEST_HOST_LOOP_N 32
+#define TEST_HOST_LOOP_N 32
+
/* Interval for each host loop (ms) */
-#define TEST_HOST_LOOP_INTERVAL 10
+#define TEST_HOST_LOOP_INTERVAL 10
+
+/*
+ * Guest/Host shared variables. Ensure addr_gva2hva() and/or
+ * sync_global_to/from_guest() are used when accessing from
+ * the host. READ/WRITE_ONCE() should also be used with anything
+ * that may change.
+ */
+static uint64_t host_page_size;
+static uint64_t guest_page_size;
+static uint64_t guest_num_pages;
+static uint64_t random_array[TEST_PAGES_PER_LOOP];
+static uint64_t iteration;
/*
- * Guest variables. We use these variables to share data between host
- * and guest. There are two copies of the variables, one in host memory
- * (which is unused) and one in guest memory. When the host wants to
- * access these variables, it needs to call addr_gva2hva() to access the
- * guest copy.
+ * GPA offset of the testing memory slot. Must be bigger than
+ * DEFAULT_GUEST_PHY_PAGES.
*/
-uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
-uint64_t guest_iteration;
-uint64_t guest_page_size;
+static uint64_t guest_test_mem = DEFAULT_GUEST_TEST_MEM;
/*
- * Writes to the first byte of a random page within the testing memory
- * region continuously.
+ * Continuously write to the first 8 bytes of a random pages within
+ * the testing memory region.
*/
-void guest_code(void)
+static void guest_code(void)
{
- int i = 0;
- uint64_t volatile *array = guest_random_array;
- uint64_t volatile *guest_addr;
+ int i;
while (true) {
for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
- /*
- * Write to the first 8 bytes of a random page
- * on the testing memory region.
- */
- guest_addr = (uint64_t *)
- (TEST_MEM_OFFSET +
- (array[i] % TEST_MEM_PAGES) * guest_page_size);
- *guest_addr = guest_iteration;
+ uint64_t addr = guest_test_mem;
+ addr += (READ_ONCE(random_array[i]) % guest_num_pages)
+ * guest_page_size;
+ addr &= ~(host_page_size - 1);
+ *(uint64_t *)addr = READ_ONCE(iteration);
}
+
/* Tell the host that we need more random numbers */
GUEST_SYNC(1);
}
}
-/*
- * Host variables. These variables should only be used by the host
- * rather than the guest.
- */
-bool host_quit;
+/* Host variables */
+static bool host_quit;
/* Points to the test VM memory region on which we track dirty logs */
-void *host_test_mem;
+static void *host_test_mem;
+static uint64_t host_num_pages;
/* For statistics only */
-uint64_t host_dirty_count;
-uint64_t host_clear_count;
-uint64_t host_track_next_count;
+static uint64_t host_dirty_count;
+static uint64_t host_clear_count;
+static uint64_t host_track_next_count;
/*
* We use this bitmap to track some pages that should have its dirty
@@ -93,40 +97,34 @@ uint64_t host_track_next_count;
* page bit is cleared in the latest bitmap, then the system must
* report that write in the next get dirty log call.
*/
-unsigned long *host_bmap_track;
+static unsigned long *host_bmap_track;
-void generate_random_array(uint64_t *guest_array, uint64_t size)
+static void generate_random_array(uint64_t *guest_array, uint64_t size)
{
uint64_t i;
- for (i = 0; i < size; i++) {
+ for (i = 0; i < size; i++)
guest_array[i] = random();
- }
}
-void *vcpu_worker(void *data)
+static void *vcpu_worker(void *data)
{
int ret;
- uint64_t loops, *guest_array, pages_count = 0;
struct kvm_vm *vm = data;
+ uint64_t *guest_array;
+ uint64_t pages_count = 0;
struct kvm_run *run;
- struct guest_args args;
+ struct ucall uc;
run = vcpu_state(vm, VCPU_ID);
- /* Retrieve the guest random array pointer and cache it */
- guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
-
- DEBUG("VCPU starts\n");
-
+ guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
while (!READ_ONCE(host_quit)) {
- /* Let the guest to dirty these random pages */
+ /* Let the guest dirty the random pages */
ret = _vcpu_run(vm, VCPU_ID);
- guest_args_read(vm, VCPU_ID, &args);
- if (run->exit_reason == KVM_EXIT_IO &&
- args.port == GUEST_PORT_SYNC) {
+ if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
pages_count += TEST_PAGES_PER_LOOP;
generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
} else {
@@ -137,18 +135,20 @@ void *vcpu_worker(void *data)
}
}
- DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
+ DEBUG("Dirtied %"PRIu64" pages\n", pages_count);
return NULL;
}
-void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
+static void vm_dirty_log_verify(unsigned long *bmap)
{
uint64_t page;
- uint64_t volatile *value_ptr;
+ uint64_t *value_ptr;
+ uint64_t step = host_page_size >= guest_page_size ? 1 :
+ guest_page_size / host_page_size;
- for (page = 0; page < TEST_MEM_PAGES; page++) {
- value_ptr = host_test_mem + page * getpagesize();
+ for (page = 0; page < host_num_pages; page += step) {
+ value_ptr = host_test_mem + page * host_page_size;
/* If this is a special page that we were tracking... */
if (test_and_clear_bit(page, host_bmap_track)) {
@@ -208,88 +208,117 @@ void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
}
}
-void help(char *name)
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
+ uint64_t extra_mem_pages, void *guest_code)
{
- puts("");
- printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
- puts("");
- printf(" -i: specify iteration counts (default: %"PRIu64")\n",
- TEST_HOST_LOOP_N);
- printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
- TEST_HOST_LOOP_INTERVAL);
- puts("");
- exit(0);
+ struct kvm_vm *vm;
+ uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+ vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+ vm_create_irqchip(vm);
+#endif
+ vm_vcpu_add_default(vm, vcpuid, guest_code);
+ return vm;
}
-int main(int argc, char *argv[])
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+ unsigned long interval, bool top_offset)
{
+ unsigned int guest_pa_bits, guest_page_shift;
pthread_t vcpu_thread;
struct kvm_vm *vm;
- uint64_t volatile *psize, *iteration;
- unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
- interval = TEST_HOST_LOOP_INTERVAL;
- int opt;
-
- while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
- switch (opt) {
- case 'i':
- iterations = strtol(optarg, NULL, 10);
- break;
- case 'I':
- interval = strtol(optarg, NULL, 10);
- break;
- case 'h':
- default:
- help(argv[0]);
- break;
- }
+ uint64_t max_gfn;
+ unsigned long *bmap;
+
+ switch (mode) {
+ case VM_MODE_P52V48_4K:
+ guest_pa_bits = 52;
+ guest_page_shift = 12;
+ break;
+ case VM_MODE_P52V48_64K:
+ guest_pa_bits = 52;
+ guest_page_shift = 16;
+ break;
+ case VM_MODE_P40V48_4K:
+ guest_pa_bits = 40;
+ guest_page_shift = 12;
+ break;
+ case VM_MODE_P40V48_64K:
+ guest_pa_bits = 40;
+ guest_page_shift = 16;
+ break;
+ default:
+ TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
}
- TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
- TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
+ DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
- DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
- iterations, interval);
+ max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
+ guest_page_size = (1ul << guest_page_shift);
+ /* 1G of guest page sized pages */
+ guest_num_pages = (1ul << (30 - guest_page_shift));
+ host_page_size = getpagesize();
+ host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
+ !!((guest_num_pages * guest_page_size) % host_page_size);
- srandom(time(0));
+ if (top_offset) {
+ guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size;
+ guest_test_mem &= ~(host_page_size - 1);
+ }
- bmap = bitmap_alloc(TEST_MEM_PAGES);
- host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
+ DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem);
- vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+ bmap = bitmap_alloc(host_num_pages);
+ host_bmap_track = bitmap_alloc(host_num_pages);
+
+ vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code);
/* Add an extra memory slot for testing dirty logging */
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
- TEST_MEM_OFFSET,
+ guest_test_mem,
TEST_MEM_SLOT_INDEX,
- TEST_MEM_PAGES,
+ guest_num_pages,
KVM_MEM_LOG_DIRTY_PAGES);
- /* Cache the HVA pointer of the region */
- host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
/* Do 1:1 mapping for the dirty track memory slot */
- virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
- TEST_MEM_PAGES * getpagesize(), 0);
+ virt_map(vm, guest_test_mem, guest_test_mem,
+ guest_num_pages * guest_page_size, 0);
+
+ /* Cache the HVA pointer of the region */
+ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem);
+#ifdef __x86_64__
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+#endif
+#ifdef __aarch64__
+ ucall_init(vm, UCALL_MMIO, NULL);
+#endif
- /* Tell the guest about the page size on the system */
- psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
- *psize = getpagesize();
+ /* Export the shared variables to the guest */
+ sync_global_to_guest(vm, host_page_size);
+ sync_global_to_guest(vm, guest_page_size);
+ sync_global_to_guest(vm, guest_test_mem);
+ sync_global_to_guest(vm, guest_num_pages);
/* Start the iterations */
- iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
- *iteration = 1;
+ iteration = 1;
+ sync_global_to_guest(vm, iteration);
+ host_quit = false;
+ host_dirty_count = 0;
+ host_clear_count = 0;
+ host_track_next_count = 0;
- /* Start dirtying pages */
pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
- while (*iteration < iterations) {
+ while (iteration < iterations) {
/* Give the vcpu thread some time to dirty some pages */
usleep(interval * 1000);
kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
- vm_dirty_log_verify(bmap, *iteration);
- (*iteration)++;
+ vm_dirty_log_verify(bmap);
+ iteration++;
+ sync_global_to_guest(vm, iteration);
}
/* Tell the vcpu thread to quit */
@@ -302,7 +331,118 @@ int main(int argc, char *argv[])
free(bmap);
free(host_bmap_track);
+ ucall_uninit(vm);
kvm_vm_free(vm);
+}
+
+static struct vm_guest_modes {
+ enum vm_guest_mode mode;
+ bool supported;
+ bool enabled;
+} vm_guest_modes[NUM_VM_MODES] = {
+#if defined(__x86_64__)
+ { VM_MODE_P52V48_4K, 1, 1, },
+ { VM_MODE_P52V48_64K, 0, 0, },
+ { VM_MODE_P40V48_4K, 0, 0, },
+ { VM_MODE_P40V48_64K, 0, 0, },
+#elif defined(__aarch64__)
+ { VM_MODE_P52V48_4K, 0, 0, },
+ { VM_MODE_P52V48_64K, 0, 0, },
+ { VM_MODE_P40V48_4K, 1, 1, },
+ { VM_MODE_P40V48_64K, 1, 1, },
+#endif
+};
+
+static void help(char *name)
+{
+ int i;
+
+ puts("");
+ printf("usage: %s [-h] [-i iterations] [-I interval] "
+ "[-o offset] [-t] [-m mode]\n", name);
+ puts("");
+ printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+ TEST_HOST_LOOP_N);
+ printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+ TEST_HOST_LOOP_INTERVAL);
+ printf(" -o: guest test memory offset (default: 0x%lx)\n",
+ DEFAULT_GUEST_TEST_MEM);
+ printf(" -t: map guest test memory at the top of the allowed "
+ "physical address range\n");
+ printf(" -m: specify the guest mode ID to test "
+ "(default: test all supported modes)\n"
+ " This option may be used multiple times.\n"
+ " Guest mode IDs:\n");
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ printf(" %d: %s%s\n",
+ vm_guest_modes[i].mode,
+ vm_guest_mode_string(vm_guest_modes[i].mode),
+ vm_guest_modes[i].supported ? " (supported)" : "");
+ }
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long iterations = TEST_HOST_LOOP_N;
+ unsigned long interval = TEST_HOST_LOOP_INTERVAL;
+ bool mode_selected = false;
+ bool top_offset = false;
+ unsigned int mode;
+ int opt, i;
+
+ while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) {
+ switch (opt) {
+ case 'i':
+ iterations = strtol(optarg, NULL, 10);
+ break;
+ case 'I':
+ interval = strtol(optarg, NULL, 10);
+ break;
+ case 'o':
+ guest_test_mem = strtoull(optarg, NULL, 0);
+ break;
+ case 't':
+ top_offset = true;
+ break;
+ case 'm':
+ if (!mode_selected) {
+ for (i = 0; i < NUM_VM_MODES; ++i)
+ vm_guest_modes[i].enabled = 0;
+ mode_selected = true;
+ }
+ mode = strtoul(optarg, NULL, 10);
+ TEST_ASSERT(mode < NUM_VM_MODES,
+ "Guest mode ID %d too big", mode);
+ vm_guest_modes[mode].enabled = 1;
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
+ TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+ TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM,
+ "Cannot use both -o [offset] and -t at the same time");
+
+ DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+ iterations, interval);
+
+ srandom(time(0));
+
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ if (!vm_guest_modes[i].enabled)
+ continue;
+ TEST_ASSERT(vm_guest_modes[i].supported,
+ "Guest mode ID %d (%s) not supported.",
+ vm_guest_modes[i].mode,
+ vm_guest_mode_string(vm_guest_modes[i].mode));
+ run_test(vm_guest_modes[i].mode, iterations, interval, top_offset);
+ }
return 0;
}
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
new file mode 100644
index 000000000000..9ef2ab1a0c08
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch64 processor specific defines
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+
+
+#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
+
+#define CPACR_EL1 3, 0, 1, 0, 2
+#define TCR_EL1 3, 0, 2, 0, 2
+#define MAIR_EL1 3, 0, 10, 2, 0
+#define TTBR0_EL1 3, 0, 2, 0, 0
+#define SCTLR_EL1 3, 0, 1, 0, 0
+
+/*
+ * Default MAIR
+ * index attribute
+ * DEVICE_nGnRnE 0 0000:0000
+ * DEVICE_nGnRE 1 0000:0100
+ * DEVICE_GRE 2 0000:1100
+ * NORMAL_NC 3 0100:0100
+ * NORMAL 4 1111:1111
+ * NORMAL_WT 5 1011:1011
+ */
+#define DEFAULT_MAIR_EL1 ((0x00ul << (0 * 8)) | \
+ (0x04ul << (1 * 8)) | \
+ (0x0cul << (2 * 8)) | \
+ (0x44ul << (3 * 8)) | \
+ (0xfful << (4 * 8)) | \
+ (0xbbul << (5 * 8)))
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
+{
+ struct kvm_one_reg reg;
+ reg.id = id;
+ reg.addr = (uint64_t)addr;
+ vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t val)
+{
+ struct kvm_one_reg reg;
+ reg.id = id;
+ reg.addr = (uint64_t)&val;
+ vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, &reg);
+}
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
new file mode 100644
index 000000000000..4059014d93ea
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -0,0 +1,1098 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ */
+
+#ifndef SELFTEST_KVM_EVMCS_H
+#define SELFTEST_KVM_EVMCS_H
+
+#include <stdint.h>
+#include "vmx.h"
+
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+extern bool enable_evmcs;
+
+struct hv_vp_assist_page {
+ __u32 apic_assist;
+ __u32 reserved;
+ __u64 vtl_control[2];
+ __u64 nested_enlightenments_control[2];
+ __u32 enlighten_vmentry;
+ __u64 current_nested_vmcs;
+};
+
+struct hv_enlightened_vmcs {
+ u32 revision_id;
+ u32 abort;
+
+ u16 host_es_selector;
+ u16 host_cs_selector;
+ u16 host_ss_selector;
+ u16 host_ds_selector;
+ u16 host_fs_selector;
+ u16 host_gs_selector;
+ u16 host_tr_selector;
+
+ u64 host_ia32_pat;
+ u64 host_ia32_efer;
+
+ u64 host_cr0;
+ u64 host_cr3;
+ u64 host_cr4;
+
+ u64 host_ia32_sysenter_esp;
+ u64 host_ia32_sysenter_eip;
+ u64 host_rip;
+ u32 host_ia32_sysenter_cs;
+
+ u32 pin_based_vm_exec_control;
+ u32 vm_exit_controls;
+ u32 secondary_vm_exec_control;
+
+ u64 io_bitmap_a;
+ u64 io_bitmap_b;
+ u64 msr_bitmap;
+
+ u16 guest_es_selector;
+ u16 guest_cs_selector;
+ u16 guest_ss_selector;
+ u16 guest_ds_selector;
+ u16 guest_fs_selector;
+ u16 guest_gs_selector;
+ u16 guest_ldtr_selector;
+ u16 guest_tr_selector;
+
+ u32 guest_es_limit;
+ u32 guest_cs_limit;
+ u32 guest_ss_limit;
+ u32 guest_ds_limit;
+ u32 guest_fs_limit;
+ u32 guest_gs_limit;
+ u32 guest_ldtr_limit;
+ u32 guest_tr_limit;
+ u32 guest_gdtr_limit;
+ u32 guest_idtr_limit;
+
+ u32 guest_es_ar_bytes;
+ u32 guest_cs_ar_bytes;
+ u32 guest_ss_ar_bytes;
+ u32 guest_ds_ar_bytes;
+ u32 guest_fs_ar_bytes;
+ u32 guest_gs_ar_bytes;
+ u32 guest_ldtr_ar_bytes;
+ u32 guest_tr_ar_bytes;
+
+ u64 guest_es_base;
+ u64 guest_cs_base;
+ u64 guest_ss_base;
+ u64 guest_ds_base;
+ u64 guest_fs_base;
+ u64 guest_gs_base;
+ u64 guest_ldtr_base;
+ u64 guest_tr_base;
+ u64 guest_gdtr_base;
+ u64 guest_idtr_base;
+
+ u64 padding64_1[3];
+
+ u64 vm_exit_msr_store_addr;
+ u64 vm_exit_msr_load_addr;
+ u64 vm_entry_msr_load_addr;
+
+ u64 cr3_target_value0;
+ u64 cr3_target_value1;
+ u64 cr3_target_value2;
+ u64 cr3_target_value3;
+
+ u32 page_fault_error_code_mask;
+ u32 page_fault_error_code_match;
+
+ u32 cr3_target_count;
+ u32 vm_exit_msr_store_count;
+ u32 vm_exit_msr_load_count;
+ u32 vm_entry_msr_load_count;
+
+ u64 tsc_offset;
+ u64 virtual_apic_page_addr;
+ u64 vmcs_link_pointer;
+
+ u64 guest_ia32_debugctl;
+ u64 guest_ia32_pat;
+ u64 guest_ia32_efer;
+
+ u64 guest_pdptr0;
+ u64 guest_pdptr1;
+ u64 guest_pdptr2;
+ u64 guest_pdptr3;
+
+ u64 guest_pending_dbg_exceptions;
+ u64 guest_sysenter_esp;
+ u64 guest_sysenter_eip;
+
+ u32 guest_activity_state;
+ u32 guest_sysenter_cs;
+
+ u64 cr0_guest_host_mask;
+ u64 cr4_guest_host_mask;
+ u64 cr0_read_shadow;
+ u64 cr4_read_shadow;
+ u64 guest_cr0;
+ u64 guest_cr3;
+ u64 guest_cr4;
+ u64 guest_dr7;
+
+ u64 host_fs_base;
+ u64 host_gs_base;
+ u64 host_tr_base;
+ u64 host_gdtr_base;
+ u64 host_idtr_base;
+ u64 host_rsp;
+
+ u64 ept_pointer;
+
+ u16 virtual_processor_id;
+ u16 padding16[3];
+
+ u64 padding64_2[5];
+ u64 guest_physical_address;
+
+ u32 vm_instruction_error;
+ u32 vm_exit_reason;
+ u32 vm_exit_intr_info;
+ u32 vm_exit_intr_error_code;
+ u32 idt_vectoring_info_field;
+ u32 idt_vectoring_error_code;
+ u32 vm_exit_instruction_len;
+ u32 vmx_instruction_info;
+
+ u64 exit_qualification;
+ u64 exit_io_instruction_ecx;
+ u64 exit_io_instruction_esi;
+ u64 exit_io_instruction_edi;
+ u64 exit_io_instruction_eip;
+
+ u64 guest_linear_address;
+ u64 guest_rsp;
+ u64 guest_rflags;
+
+ u32 guest_interruptibility_info;
+ u32 cpu_based_vm_exec_control;
+ u32 exception_bitmap;
+ u32 vm_entry_controls;
+ u32 vm_entry_intr_info_field;
+ u32 vm_entry_exception_error_code;
+ u32 vm_entry_instruction_len;
+ u32 tpr_threshold;
+
+ u64 guest_rip;
+
+ u32 hv_clean_fields;
+ u32 hv_padding_32;
+ u32 hv_synthetic_controls;
+ struct {
+ u32 nested_flush_hypercall:1;
+ u32 msr_bitmap:1;
+ u32 reserved:30;
+ } hv_enlightenments_control;
+ u32 hv_vp_id;
+
+ u64 hv_vm_id;
+ u64 partition_assist_page;
+ u64 padding64_4[4];
+ u64 guest_bndcfgs;
+ u64 padding64_5[7];
+ u64 xss_exit_bitmap;
+ u64 padding64_6[7];
+};
+
+#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
+#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
+ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+struct hv_enlightened_vmcs *current_evmcs;
+struct hv_vp_assist_page *current_vp_assist;
+
+static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist)
+{
+ u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
+ HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+ wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val);
+
+ current_vp_assist = vp_assist;
+
+ enable_evmcs = true;
+
+ return 0;
+}
+
+static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs)
+{
+ current_vp_assist->current_nested_vmcs = vmcs_pa;
+ current_vp_assist->enlighten_vmentry = 1;
+
+ current_evmcs = vmcs;
+
+ return 0;
+}
+
+static inline int evmcs_vmptrst(uint64_t *value)
+{
+ *value = current_vp_assist->current_nested_vmcs &
+ ~HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+ return 0;
+}
+
+static inline int evmcs_vmread(uint64_t encoding, uint64_t *value)
+{
+ switch (encoding) {
+ case GUEST_RIP:
+ *value = current_evmcs->guest_rip;
+ break;
+ case GUEST_RSP:
+ *value = current_evmcs->guest_rsp;
+ break;
+ case GUEST_RFLAGS:
+ *value = current_evmcs->guest_rflags;
+ break;
+ case HOST_IA32_PAT:
+ *value = current_evmcs->host_ia32_pat;
+ break;
+ case HOST_IA32_EFER:
+ *value = current_evmcs->host_ia32_efer;
+ break;
+ case HOST_CR0:
+ *value = current_evmcs->host_cr0;
+ break;
+ case HOST_CR3:
+ *value = current_evmcs->host_cr3;
+ break;
+ case HOST_CR4:
+ *value = current_evmcs->host_cr4;
+ break;
+ case HOST_IA32_SYSENTER_ESP:
+ *value = current_evmcs->host_ia32_sysenter_esp;
+ break;
+ case HOST_IA32_SYSENTER_EIP:
+ *value = current_evmcs->host_ia32_sysenter_eip;
+ break;
+ case HOST_RIP:
+ *value = current_evmcs->host_rip;
+ break;
+ case IO_BITMAP_A:
+ *value = current_evmcs->io_bitmap_a;
+ break;
+ case IO_BITMAP_B:
+ *value = current_evmcs->io_bitmap_b;
+ break;
+ case MSR_BITMAP:
+ *value = current_evmcs->msr_bitmap;
+ break;
+ case GUEST_ES_BASE:
+ *value = current_evmcs->guest_es_base;
+ break;
+ case GUEST_CS_BASE:
+ *value = current_evmcs->guest_cs_base;
+ break;
+ case GUEST_SS_BASE:
+ *value = current_evmcs->guest_ss_base;
+ break;
+ case GUEST_DS_BASE:
+ *value = current_evmcs->guest_ds_base;
+ break;
+ case GUEST_FS_BASE:
+ *value = current_evmcs->guest_fs_base;
+ break;
+ case GUEST_GS_BASE:
+ *value = current_evmcs->guest_gs_base;
+ break;
+ case GUEST_LDTR_BASE:
+ *value = current_evmcs->guest_ldtr_base;
+ break;
+ case GUEST_TR_BASE:
+ *value = current_evmcs->guest_tr_base;
+ break;
+ case GUEST_GDTR_BASE:
+ *value = current_evmcs->guest_gdtr_base;
+ break;
+ case GUEST_IDTR_BASE:
+ *value = current_evmcs->guest_idtr_base;
+ break;
+ case TSC_OFFSET:
+ *value = current_evmcs->tsc_offset;
+ break;
+ case VIRTUAL_APIC_PAGE_ADDR:
+ *value = current_evmcs->virtual_apic_page_addr;
+ break;
+ case VMCS_LINK_POINTER:
+ *value = current_evmcs->vmcs_link_pointer;
+ break;
+ case GUEST_IA32_DEBUGCTL:
+ *value = current_evmcs->guest_ia32_debugctl;
+ break;
+ case GUEST_IA32_PAT:
+ *value = current_evmcs->guest_ia32_pat;
+ break;
+ case GUEST_IA32_EFER:
+ *value = current_evmcs->guest_ia32_efer;
+ break;
+ case GUEST_PDPTR0:
+ *value = current_evmcs->guest_pdptr0;
+ break;
+ case GUEST_PDPTR1:
+ *value = current_evmcs->guest_pdptr1;
+ break;
+ case GUEST_PDPTR2:
+ *value = current_evmcs->guest_pdptr2;
+ break;
+ case GUEST_PDPTR3:
+ *value = current_evmcs->guest_pdptr3;
+ break;
+ case GUEST_PENDING_DBG_EXCEPTIONS:
+ *value = current_evmcs->guest_pending_dbg_exceptions;
+ break;
+ case GUEST_SYSENTER_ESP:
+ *value = current_evmcs->guest_sysenter_esp;
+ break;
+ case GUEST_SYSENTER_EIP:
+ *value = current_evmcs->guest_sysenter_eip;
+ break;
+ case CR0_GUEST_HOST_MASK:
+ *value = current_evmcs->cr0_guest_host_mask;
+ break;
+ case CR4_GUEST_HOST_MASK:
+ *value = current_evmcs->cr4_guest_host_mask;
+ break;
+ case CR0_READ_SHADOW:
+ *value = current_evmcs->cr0_read_shadow;
+ break;
+ case CR4_READ_SHADOW:
+ *value = current_evmcs->cr4_read_shadow;
+ break;
+ case GUEST_CR0:
+ *value = current_evmcs->guest_cr0;
+ break;
+ case GUEST_CR3:
+ *value = current_evmcs->guest_cr3;
+ break;
+ case GUEST_CR4:
+ *value = current_evmcs->guest_cr4;
+ break;
+ case GUEST_DR7:
+ *value = current_evmcs->guest_dr7;
+ break;
+ case HOST_FS_BASE:
+ *value = current_evmcs->host_fs_base;
+ break;
+ case HOST_GS_BASE:
+ *value = current_evmcs->host_gs_base;
+ break;
+ case HOST_TR_BASE:
+ *value = current_evmcs->host_tr_base;
+ break;
+ case HOST_GDTR_BASE:
+ *value = current_evmcs->host_gdtr_base;
+ break;
+ case HOST_IDTR_BASE:
+ *value = current_evmcs->host_idtr_base;
+ break;
+ case HOST_RSP:
+ *value = current_evmcs->host_rsp;
+ break;
+ case EPT_POINTER:
+ *value = current_evmcs->ept_pointer;
+ break;
+ case GUEST_BNDCFGS:
+ *value = current_evmcs->guest_bndcfgs;
+ break;
+ case XSS_EXIT_BITMAP:
+ *value = current_evmcs->xss_exit_bitmap;
+ break;
+ case GUEST_PHYSICAL_ADDRESS:
+ *value = current_evmcs->guest_physical_address;
+ break;
+ case EXIT_QUALIFICATION:
+ *value = current_evmcs->exit_qualification;
+ break;
+ case GUEST_LINEAR_ADDRESS:
+ *value = current_evmcs->guest_linear_address;
+ break;
+ case VM_EXIT_MSR_STORE_ADDR:
+ *value = current_evmcs->vm_exit_msr_store_addr;
+ break;
+ case VM_EXIT_MSR_LOAD_ADDR:
+ *value = current_evmcs->vm_exit_msr_load_addr;
+ break;
+ case VM_ENTRY_MSR_LOAD_ADDR:
+ *value = current_evmcs->vm_entry_msr_load_addr;
+ break;
+ case CR3_TARGET_VALUE0:
+ *value = current_evmcs->cr3_target_value0;
+ break;
+ case CR3_TARGET_VALUE1:
+ *value = current_evmcs->cr3_target_value1;
+ break;
+ case CR3_TARGET_VALUE2:
+ *value = current_evmcs->cr3_target_value2;
+ break;
+ case CR3_TARGET_VALUE3:
+ *value = current_evmcs->cr3_target_value3;
+ break;
+ case TPR_THRESHOLD:
+ *value = current_evmcs->tpr_threshold;
+ break;
+ case GUEST_INTERRUPTIBILITY_INFO:
+ *value = current_evmcs->guest_interruptibility_info;
+ break;
+ case CPU_BASED_VM_EXEC_CONTROL:
+ *value = current_evmcs->cpu_based_vm_exec_control;
+ break;
+ case EXCEPTION_BITMAP:
+ *value = current_evmcs->exception_bitmap;
+ break;
+ case VM_ENTRY_CONTROLS:
+ *value = current_evmcs->vm_entry_controls;
+ break;
+ case VM_ENTRY_INTR_INFO_FIELD:
+ *value = current_evmcs->vm_entry_intr_info_field;
+ break;
+ case VM_ENTRY_EXCEPTION_ERROR_CODE:
+ *value = current_evmcs->vm_entry_exception_error_code;
+ break;
+ case VM_ENTRY_INSTRUCTION_LEN:
+ *value = current_evmcs->vm_entry_instruction_len;
+ break;
+ case HOST_IA32_SYSENTER_CS:
+ *value = current_evmcs->host_ia32_sysenter_cs;
+ break;
+ case PIN_BASED_VM_EXEC_CONTROL:
+ *value = current_evmcs->pin_based_vm_exec_control;
+ break;
+ case VM_EXIT_CONTROLS:
+ *value = current_evmcs->vm_exit_controls;
+ break;
+ case SECONDARY_VM_EXEC_CONTROL:
+ *value = current_evmcs->secondary_vm_exec_control;
+ break;
+ case GUEST_ES_LIMIT:
+ *value = current_evmcs->guest_es_limit;
+ break;
+ case GUEST_CS_LIMIT:
+ *value = current_evmcs->guest_cs_limit;
+ break;
+ case GUEST_SS_LIMIT:
+ *value = current_evmcs->guest_ss_limit;
+ break;
+ case GUEST_DS_LIMIT:
+ *value = current_evmcs->guest_ds_limit;
+ break;
+ case GUEST_FS_LIMIT:
+ *value = current_evmcs->guest_fs_limit;
+ break;
+ case GUEST_GS_LIMIT:
+ *value = current_evmcs->guest_gs_limit;
+ break;
+ case GUEST_LDTR_LIMIT:
+ *value = current_evmcs->guest_ldtr_limit;
+ break;
+ case GUEST_TR_LIMIT:
+ *value = current_evmcs->guest_tr_limit;
+ break;
+ case GUEST_GDTR_LIMIT:
+ *value = current_evmcs->guest_gdtr_limit;
+ break;
+ case GUEST_IDTR_LIMIT:
+ *value = current_evmcs->guest_idtr_limit;
+ break;
+ case GUEST_ES_AR_BYTES:
+ *value = current_evmcs->guest_es_ar_bytes;
+ break;
+ case GUEST_CS_AR_BYTES:
+ *value = current_evmcs->guest_cs_ar_bytes;
+ break;
+ case GUEST_SS_AR_BYTES:
+ *value = current_evmcs->guest_ss_ar_bytes;
+ break;
+ case GUEST_DS_AR_BYTES:
+ *value = current_evmcs->guest_ds_ar_bytes;
+ break;
+ case GUEST_FS_AR_BYTES:
+ *value = current_evmcs->guest_fs_ar_bytes;
+ break;
+ case GUEST_GS_AR_BYTES:
+ *value = current_evmcs->guest_gs_ar_bytes;
+ break;
+ case GUEST_LDTR_AR_BYTES:
+ *value = current_evmcs->guest_ldtr_ar_bytes;
+ break;
+ case GUEST_TR_AR_BYTES:
+ *value = current_evmcs->guest_tr_ar_bytes;
+ break;
+ case GUEST_ACTIVITY_STATE:
+ *value = current_evmcs->guest_activity_state;
+ break;
+ case GUEST_SYSENTER_CS:
+ *value = current_evmcs->guest_sysenter_cs;
+ break;
+ case VM_INSTRUCTION_ERROR:
+ *value = current_evmcs->vm_instruction_error;
+ break;
+ case VM_EXIT_REASON:
+ *value = current_evmcs->vm_exit_reason;
+ break;
+ case VM_EXIT_INTR_INFO:
+ *value = current_evmcs->vm_exit_intr_info;
+ break;
+ case VM_EXIT_INTR_ERROR_CODE:
+ *value = current_evmcs->vm_exit_intr_error_code;
+ break;
+ case IDT_VECTORING_INFO_FIELD:
+ *value = current_evmcs->idt_vectoring_info_field;
+ break;
+ case IDT_VECTORING_ERROR_CODE:
+ *value = current_evmcs->idt_vectoring_error_code;
+ break;
+ case VM_EXIT_INSTRUCTION_LEN:
+ *value = current_evmcs->vm_exit_instruction_len;
+ break;
+ case VMX_INSTRUCTION_INFO:
+ *value = current_evmcs->vmx_instruction_info;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MASK:
+ *value = current_evmcs->page_fault_error_code_mask;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MATCH:
+ *value = current_evmcs->page_fault_error_code_match;
+ break;
+ case CR3_TARGET_COUNT:
+ *value = current_evmcs->cr3_target_count;
+ break;
+ case VM_EXIT_MSR_STORE_COUNT:
+ *value = current_evmcs->vm_exit_msr_store_count;
+ break;
+ case VM_EXIT_MSR_LOAD_COUNT:
+ *value = current_evmcs->vm_exit_msr_load_count;
+ break;
+ case VM_ENTRY_MSR_LOAD_COUNT:
+ *value = current_evmcs->vm_entry_msr_load_count;
+ break;
+ case HOST_ES_SELECTOR:
+ *value = current_evmcs->host_es_selector;
+ break;
+ case HOST_CS_SELECTOR:
+ *value = current_evmcs->host_cs_selector;
+ break;
+ case HOST_SS_SELECTOR:
+ *value = current_evmcs->host_ss_selector;
+ break;
+ case HOST_DS_SELECTOR:
+ *value = current_evmcs->host_ds_selector;
+ break;
+ case HOST_FS_SELECTOR:
+ *value = current_evmcs->host_fs_selector;
+ break;
+ case HOST_GS_SELECTOR:
+ *value = current_evmcs->host_gs_selector;
+ break;
+ case HOST_TR_SELECTOR:
+ *value = current_evmcs->host_tr_selector;
+ break;
+ case GUEST_ES_SELECTOR:
+ *value = current_evmcs->guest_es_selector;
+ break;
+ case GUEST_CS_SELECTOR:
+ *value = current_evmcs->guest_cs_selector;
+ break;
+ case GUEST_SS_SELECTOR:
+ *value = current_evmcs->guest_ss_selector;
+ break;
+ case GUEST_DS_SELECTOR:
+ *value = current_evmcs->guest_ds_selector;
+ break;
+ case GUEST_FS_SELECTOR:
+ *value = current_evmcs->guest_fs_selector;
+ break;
+ case GUEST_GS_SELECTOR:
+ *value = current_evmcs->guest_gs_selector;
+ break;
+ case GUEST_LDTR_SELECTOR:
+ *value = current_evmcs->guest_ldtr_selector;
+ break;
+ case GUEST_TR_SELECTOR:
+ *value = current_evmcs->guest_tr_selector;
+ break;
+ case VIRTUAL_PROCESSOR_ID:
+ *value = current_evmcs->virtual_processor_id;
+ break;
+ default: return 1;
+ }
+
+ return 0;
+}
+
+static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value)
+{
+ switch (encoding) {
+ case GUEST_RIP:
+ current_evmcs->guest_rip = value;
+ break;
+ case GUEST_RSP:
+ current_evmcs->guest_rsp = value;
+ break;
+ case GUEST_RFLAGS:
+ current_evmcs->guest_rflags = value;
+ break;
+ case HOST_IA32_PAT:
+ current_evmcs->host_ia32_pat = value;
+ break;
+ case HOST_IA32_EFER:
+ current_evmcs->host_ia32_efer = value;
+ break;
+ case HOST_CR0:
+ current_evmcs->host_cr0 = value;
+ break;
+ case HOST_CR3:
+ current_evmcs->host_cr3 = value;
+ break;
+ case HOST_CR4:
+ current_evmcs->host_cr4 = value;
+ break;
+ case HOST_IA32_SYSENTER_ESP:
+ current_evmcs->host_ia32_sysenter_esp = value;
+ break;
+ case HOST_IA32_SYSENTER_EIP:
+ current_evmcs->host_ia32_sysenter_eip = value;
+ break;
+ case HOST_RIP:
+ current_evmcs->host_rip = value;
+ break;
+ case IO_BITMAP_A:
+ current_evmcs->io_bitmap_a = value;
+ break;
+ case IO_BITMAP_B:
+ current_evmcs->io_bitmap_b = value;
+ break;
+ case MSR_BITMAP:
+ current_evmcs->msr_bitmap = value;
+ break;
+ case GUEST_ES_BASE:
+ current_evmcs->guest_es_base = value;
+ break;
+ case GUEST_CS_BASE:
+ current_evmcs->guest_cs_base = value;
+ break;
+ case GUEST_SS_BASE:
+ current_evmcs->guest_ss_base = value;
+ break;
+ case GUEST_DS_BASE:
+ current_evmcs->guest_ds_base = value;
+ break;
+ case GUEST_FS_BASE:
+ current_evmcs->guest_fs_base = value;
+ break;
+ case GUEST_GS_BASE:
+ current_evmcs->guest_gs_base = value;
+ break;
+ case GUEST_LDTR_BASE:
+ current_evmcs->guest_ldtr_base = value;
+ break;
+ case GUEST_TR_BASE:
+ current_evmcs->guest_tr_base = value;
+ break;
+ case GUEST_GDTR_BASE:
+ current_evmcs->guest_gdtr_base = value;
+ break;
+ case GUEST_IDTR_BASE:
+ current_evmcs->guest_idtr_base = value;
+ break;
+ case TSC_OFFSET:
+ current_evmcs->tsc_offset = value;
+ break;
+ case VIRTUAL_APIC_PAGE_ADDR:
+ current_evmcs->virtual_apic_page_addr = value;
+ break;
+ case VMCS_LINK_POINTER:
+ current_evmcs->vmcs_link_pointer = value;
+ break;
+ case GUEST_IA32_DEBUGCTL:
+ current_evmcs->guest_ia32_debugctl = value;
+ break;
+ case GUEST_IA32_PAT:
+ current_evmcs->guest_ia32_pat = value;
+ break;
+ case GUEST_IA32_EFER:
+ current_evmcs->guest_ia32_efer = value;
+ break;
+ case GUEST_PDPTR0:
+ current_evmcs->guest_pdptr0 = value;
+ break;
+ case GUEST_PDPTR1:
+ current_evmcs->guest_pdptr1 = value;
+ break;
+ case GUEST_PDPTR2:
+ current_evmcs->guest_pdptr2 = value;
+ break;
+ case GUEST_PDPTR3:
+ current_evmcs->guest_pdptr3 = value;
+ break;
+ case GUEST_PENDING_DBG_EXCEPTIONS:
+ current_evmcs->guest_pending_dbg_exceptions = value;
+ break;
+ case GUEST_SYSENTER_ESP:
+ current_evmcs->guest_sysenter_esp = value;
+ break;
+ case GUEST_SYSENTER_EIP:
+ current_evmcs->guest_sysenter_eip = value;
+ break;
+ case CR0_GUEST_HOST_MASK:
+ current_evmcs->cr0_guest_host_mask = value;
+ break;
+ case CR4_GUEST_HOST_MASK:
+ current_evmcs->cr4_guest_host_mask = value;
+ break;
+ case CR0_READ_SHADOW:
+ current_evmcs->cr0_read_shadow = value;
+ break;
+ case CR4_READ_SHADOW:
+ current_evmcs->cr4_read_shadow = value;
+ break;
+ case GUEST_CR0:
+ current_evmcs->guest_cr0 = value;
+ break;
+ case GUEST_CR3:
+ current_evmcs->guest_cr3 = value;
+ break;
+ case GUEST_CR4:
+ current_evmcs->guest_cr4 = value;
+ break;
+ case GUEST_DR7:
+ current_evmcs->guest_dr7 = value;
+ break;
+ case HOST_FS_BASE:
+ current_evmcs->host_fs_base = value;
+ break;
+ case HOST_GS_BASE:
+ current_evmcs->host_gs_base = value;
+ break;
+ case HOST_TR_BASE:
+ current_evmcs->host_tr_base = value;
+ break;
+ case HOST_GDTR_BASE:
+ current_evmcs->host_gdtr_base = value;
+ break;
+ case HOST_IDTR_BASE:
+ current_evmcs->host_idtr_base = value;
+ break;
+ case HOST_RSP:
+ current_evmcs->host_rsp = value;
+ break;
+ case EPT_POINTER:
+ current_evmcs->ept_pointer = value;
+ break;
+ case GUEST_BNDCFGS:
+ current_evmcs->guest_bndcfgs = value;
+ break;
+ case XSS_EXIT_BITMAP:
+ current_evmcs->xss_exit_bitmap = value;
+ break;
+ case GUEST_PHYSICAL_ADDRESS:
+ current_evmcs->guest_physical_address = value;
+ break;
+ case EXIT_QUALIFICATION:
+ current_evmcs->exit_qualification = value;
+ break;
+ case GUEST_LINEAR_ADDRESS:
+ current_evmcs->guest_linear_address = value;
+ break;
+ case VM_EXIT_MSR_STORE_ADDR:
+ current_evmcs->vm_exit_msr_store_addr = value;
+ break;
+ case VM_EXIT_MSR_LOAD_ADDR:
+ current_evmcs->vm_exit_msr_load_addr = value;
+ break;
+ case VM_ENTRY_MSR_LOAD_ADDR:
+ current_evmcs->vm_entry_msr_load_addr = value;
+ break;
+ case CR3_TARGET_VALUE0:
+ current_evmcs->cr3_target_value0 = value;
+ break;
+ case CR3_TARGET_VALUE1:
+ current_evmcs->cr3_target_value1 = value;
+ break;
+ case CR3_TARGET_VALUE2:
+ current_evmcs->cr3_target_value2 = value;
+ break;
+ case CR3_TARGET_VALUE3:
+ current_evmcs->cr3_target_value3 = value;
+ break;
+ case TPR_THRESHOLD:
+ current_evmcs->tpr_threshold = value;
+ break;
+ case GUEST_INTERRUPTIBILITY_INFO:
+ current_evmcs->guest_interruptibility_info = value;
+ break;
+ case CPU_BASED_VM_EXEC_CONTROL:
+ current_evmcs->cpu_based_vm_exec_control = value;
+ break;
+ case EXCEPTION_BITMAP:
+ current_evmcs->exception_bitmap = value;
+ break;
+ case VM_ENTRY_CONTROLS:
+ current_evmcs->vm_entry_controls = value;
+ break;
+ case VM_ENTRY_INTR_INFO_FIELD:
+ current_evmcs->vm_entry_intr_info_field = value;
+ break;
+ case VM_ENTRY_EXCEPTION_ERROR_CODE:
+ current_evmcs->vm_entry_exception_error_code = value;
+ break;
+ case VM_ENTRY_INSTRUCTION_LEN:
+ current_evmcs->vm_entry_instruction_len = value;
+ break;
+ case HOST_IA32_SYSENTER_CS:
+ current_evmcs->host_ia32_sysenter_cs = value;
+ break;
+ case PIN_BASED_VM_EXEC_CONTROL:
+ current_evmcs->pin_based_vm_exec_control = value;
+ break;
+ case VM_EXIT_CONTROLS:
+ current_evmcs->vm_exit_controls = value;
+ break;
+ case SECONDARY_VM_EXEC_CONTROL:
+ current_evmcs->secondary_vm_exec_control = value;
+ break;
+ case GUEST_ES_LIMIT:
+ current_evmcs->guest_es_limit = value;
+ break;
+ case GUEST_CS_LIMIT:
+ current_evmcs->guest_cs_limit = value;
+ break;
+ case GUEST_SS_LIMIT:
+ current_evmcs->guest_ss_limit = value;
+ break;
+ case GUEST_DS_LIMIT:
+ current_evmcs->guest_ds_limit = value;
+ break;
+ case GUEST_FS_LIMIT:
+ current_evmcs->guest_fs_limit = value;
+ break;
+ case GUEST_GS_LIMIT:
+ current_evmcs->guest_gs_limit = value;
+ break;
+ case GUEST_LDTR_LIMIT:
+ current_evmcs->guest_ldtr_limit = value;
+ break;
+ case GUEST_TR_LIMIT:
+ current_evmcs->guest_tr_limit = value;
+ break;
+ case GUEST_GDTR_LIMIT:
+ current_evmcs->guest_gdtr_limit = value;
+ break;
+ case GUEST_IDTR_LIMIT:
+ current_evmcs->guest_idtr_limit = value;
+ break;
+ case GUEST_ES_AR_BYTES:
+ current_evmcs->guest_es_ar_bytes = value;
+ break;
+ case GUEST_CS_AR_BYTES:
+ current_evmcs->guest_cs_ar_bytes = value;
+ break;
+ case GUEST_SS_AR_BYTES:
+ current_evmcs->guest_ss_ar_bytes = value;
+ break;
+ case GUEST_DS_AR_BYTES:
+ current_evmcs->guest_ds_ar_bytes = value;
+ break;
+ case GUEST_FS_AR_BYTES:
+ current_evmcs->guest_fs_ar_bytes = value;
+ break;
+ case GUEST_GS_AR_BYTES:
+ current_evmcs->guest_gs_ar_bytes = value;
+ break;
+ case GUEST_LDTR_AR_BYTES:
+ current_evmcs->guest_ldtr_ar_bytes = value;
+ break;
+ case GUEST_TR_AR_BYTES:
+ current_evmcs->guest_tr_ar_bytes = value;
+ break;
+ case GUEST_ACTIVITY_STATE:
+ current_evmcs->guest_activity_state = value;
+ break;
+ case GUEST_SYSENTER_CS:
+ current_evmcs->guest_sysenter_cs = value;
+ break;
+ case VM_INSTRUCTION_ERROR:
+ current_evmcs->vm_instruction_error = value;
+ break;
+ case VM_EXIT_REASON:
+ current_evmcs->vm_exit_reason = value;
+ break;
+ case VM_EXIT_INTR_INFO:
+ current_evmcs->vm_exit_intr_info = value;
+ break;
+ case VM_EXIT_INTR_ERROR_CODE:
+ current_evmcs->vm_exit_intr_error_code = value;
+ break;
+ case IDT_VECTORING_INFO_FIELD:
+ current_evmcs->idt_vectoring_info_field = value;
+ break;
+ case IDT_VECTORING_ERROR_CODE:
+ current_evmcs->idt_vectoring_error_code = value;
+ break;
+ case VM_EXIT_INSTRUCTION_LEN:
+ current_evmcs->vm_exit_instruction_len = value;
+ break;
+ case VMX_INSTRUCTION_INFO:
+ current_evmcs->vmx_instruction_info = value;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MASK:
+ current_evmcs->page_fault_error_code_mask = value;
+ break;
+ case PAGE_FAULT_ERROR_CODE_MATCH:
+ current_evmcs->page_fault_error_code_match = value;
+ break;
+ case CR3_TARGET_COUNT:
+ current_evmcs->cr3_target_count = value;
+ break;
+ case VM_EXIT_MSR_STORE_COUNT:
+ current_evmcs->vm_exit_msr_store_count = value;
+ break;
+ case VM_EXIT_MSR_LOAD_COUNT:
+ current_evmcs->vm_exit_msr_load_count = value;
+ break;
+ case VM_ENTRY_MSR_LOAD_COUNT:
+ current_evmcs->vm_entry_msr_load_count = value;
+ break;
+ case HOST_ES_SELECTOR:
+ current_evmcs->host_es_selector = value;
+ break;
+ case HOST_CS_SELECTOR:
+ current_evmcs->host_cs_selector = value;
+ break;
+ case HOST_SS_SELECTOR:
+ current_evmcs->host_ss_selector = value;
+ break;
+ case HOST_DS_SELECTOR:
+ current_evmcs->host_ds_selector = value;
+ break;
+ case HOST_FS_SELECTOR:
+ current_evmcs->host_fs_selector = value;
+ break;
+ case HOST_GS_SELECTOR:
+ current_evmcs->host_gs_selector = value;
+ break;
+ case HOST_TR_SELECTOR:
+ current_evmcs->host_tr_selector = value;
+ break;
+ case GUEST_ES_SELECTOR:
+ current_evmcs->guest_es_selector = value;
+ break;
+ case GUEST_CS_SELECTOR:
+ current_evmcs->guest_cs_selector = value;
+ break;
+ case GUEST_SS_SELECTOR:
+ current_evmcs->guest_ss_selector = value;
+ break;
+ case GUEST_DS_SELECTOR:
+ current_evmcs->guest_ds_selector = value;
+ break;
+ case GUEST_FS_SELECTOR:
+ current_evmcs->guest_fs_selector = value;
+ break;
+ case GUEST_GS_SELECTOR:
+ current_evmcs->guest_gs_selector = value;
+ break;
+ case GUEST_LDTR_SELECTOR:
+ current_evmcs->guest_ldtr_selector = value;
+ break;
+ case GUEST_TR_SELECTOR:
+ current_evmcs->guest_tr_selector = value;
+ break;
+ case VIRTUAL_PROCESSOR_ID:
+ current_evmcs->virtual_processor_id = value;
+ break;
+ default: return 1;
+ }
+
+ return 0;
+}
+
+static inline int evmcs_vmlaunch(void)
+{
+ int ret;
+
+ current_evmcs->hv_clean_fields = 0;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "mov %%rsp, (%[host_rsp]);"
+ "lea 1f(%%rip), %%rax;"
+ "mov %%rax, (%[host_rip]);"
+ "vmlaunch;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"
+ ((uint64_t)&current_evmcs->host_rsp),
+ [host_rip]"r"
+ ((uint64_t)&current_evmcs->host_rip)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int evmcs_vmresume(void)
+{
+ int ret;
+
+ current_evmcs->hv_clean_fields = 0;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "mov %%rsp, (%[host_rsp]);"
+ "lea 1f(%%rip), %%rax;"
+ "mov %%rax, (%[host_rip]);"
+ "vmresume;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"
+ ((uint64_t)&current_evmcs->host_rsp),
+ [host_rip]"r"
+ ((uint64_t)&current_evmcs->host_rip)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+#endif /* !SELFTEST_KVM_EVMCS_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 3acf9a91704c..a4e59e3b4826 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -7,7 +7,7 @@
*
*/
#ifndef SELFTEST_KVM_UTIL_H
-#define SELFTEST_KVM_UTIL_H 1
+#define SELFTEST_KVM_UTIL_H
#include "test_util.h"
@@ -17,12 +17,6 @@
#include "sparsebit.h"
-/*
- * Memslots can't cover the gfn starting at this gpa otherwise vCPUs can't be
- * created. Only applies to VMs using EPT.
- */
-#define KVM_DEFAULT_IDENTITY_MAP_ADDRESS 0xfffbc000ul
-
/* Callers of kvm_util only have an incomplete/opaque description of the
* structure kvm_util is using to maintain the state of a VM.
@@ -33,16 +27,23 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
/* Minimum allocated guest virtual and physical addresses */
-#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_UTIL_MIN_VADDR 0x2000
#define DEFAULT_GUEST_PHY_PAGES 512
#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
-#define DEFAULT_STACK_PGS 5
+#define DEFAULT_STACK_PGS 5
enum vm_guest_mode {
- VM_MODE_FLAT48PG,
+ VM_MODE_P52V48_4K,
+ VM_MODE_P52V48_64K,
+ VM_MODE_P40V48_4K,
+ VM_MODE_P40V48_64K,
+ NUM_VM_MODES,
};
+#define vm_guest_mode_string(m) vm_guest_mode_string[m]
+extern const char * const vm_guest_mode_string[];
+
enum vm_mem_backing_src_type {
VM_MEM_SRC_ANONYMOUS,
VM_MEM_SRC_ANONYMOUS_THP,
@@ -58,15 +59,15 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm);
void kvm_vm_release(struct kvm_vm *vmp);
void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
-int kvm_memcmp_hva_gva(void *hva,
- struct kvm_vm *vm, const vm_vaddr_t gva, size_t len);
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
+ size_t len);
void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
- uint32_t data_memslot, uint32_t pgd_memslot);
+ uint32_t data_memslot, uint32_t pgd_memslot);
void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-void vcpu_dump(FILE *stream, struct kvm_vm *vm,
- uint32_t vcpuid, uint8_t indent);
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
+ uint8_t indent);
void vm_create_irqchip(struct kvm_vm *vm);
@@ -75,13 +76,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
uint64_t guest_paddr, uint32_t slot, uint64_t npages,
uint32_t flags);
-void vcpu_ioctl(struct kvm_vm *vm,
- uint32_t vcpuid, unsigned long ioctl, void *arg);
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+ void *arg);
void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot);
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
+ int gdt_memslot);
vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
- uint32_t data_memslot, uint32_t pgd_memslot);
+ uint32_t data_memslot, uint32_t pgd_memslot);
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
size_t size, uint32_t pgd_memslot);
void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
@@ -93,56 +95,35 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_mp_state *mp_state);
-void vcpu_regs_get(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_regs *regs);
-void vcpu_regs_set(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_regs *regs);
+ struct kvm_mp_state *mp_state);
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
-void vcpu_sregs_get(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_sregs *sregs);
-void vcpu_sregs_set(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_sregs *sregs);
-int _vcpu_sregs_set(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_sregs *sregs);
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events);
+ struct kvm_vcpu_events *events);
void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events);
-uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
- uint64_t msr_value);
+ struct kvm_vcpu_events *events);
const char *exit_reason_str(unsigned int exit_reason);
void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- uint32_t pgd_memslot);
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
- vm_paddr_t paddr_min, uint32_t memslot);
-
-struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
-void vcpu_set_cpuid(
- struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
-
-struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
-
-static inline struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_entry(uint32_t function)
-{
- return kvm_get_supported_cpuid_index(function, 0);
-}
+ uint32_t pgd_memslot);
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+ uint32_t memslot);
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+ vm_paddr_t paddr_min, uint32_t memslot);
struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_size,
void *guest_code);
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
-typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
- vm_paddr_t vmxon_paddr,
- vm_vaddr_t vmcs_vaddr,
- vm_paddr_t vmcs_paddr);
-
struct kvm_userspace_memory_region *
kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
uint64_t end);
@@ -152,43 +133,49 @@ allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
-#define GUEST_PORT_SYNC 0x1000
-#define GUEST_PORT_ABORT 0x1001
-#define GUEST_PORT_DONE 0x1002
-
-static inline void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
-{
- __asm__ __volatile__("in %[port], %%al"
- :
- : [port]"d"(port), "D"(arg0), "S"(arg1)
- : "rax");
-}
-
-/*
- * Allows to pass three arguments to the host: port is 16bit wide,
- * arg0 & arg1 are 64bit wide
- */
-#define GUEST_SYNC_ARGS(_port, _arg0, _arg1) \
- __exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
-
-#define GUEST_ASSERT(_condition) do { \
- if (!(_condition)) \
- GUEST_SYNC_ARGS(GUEST_PORT_ABORT, \
- "Failed guest assert: " \
- #_condition, __LINE__); \
- } while (0)
-
-#define GUEST_SYNC(stage) GUEST_SYNC_ARGS(GUEST_PORT_SYNC, "hello", stage)
+#define sync_global_to_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(_p, &(g), sizeof(g)); \
+})
+
+#define sync_global_from_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(&(g), _p, sizeof(g)); \
+})
+
+/* ucall implementation types */
+typedef enum {
+ UCALL_PIO,
+ UCALL_MMIO,
+} ucall_type_t;
+
+/* Common ucalls */
+enum {
+ UCALL_NONE,
+ UCALL_SYNC,
+ UCALL_ABORT,
+ UCALL_DONE,
+};
-#define GUEST_DONE() GUEST_SYNC_ARGS(GUEST_PORT_DONE, 0, 0)
+#define UCALL_MAX_ARGS 6
-struct guest_args {
- uint64_t arg0;
- uint64_t arg1;
- uint16_t port;
-} __attribute__ ((packed));
+struct ucall {
+ uint64_t cmd;
+ uint64_t args[UCALL_MAX_ARGS];
+};
-void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
- struct guest_args *args);
+void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg);
+void ucall_uninit(struct kvm_vm *vm);
+void ucall(uint64_t cmd, int nargs, ...);
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
+
+#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_DONE() ucall(UCALL_DONE, 0)
+#define GUEST_ASSERT(_condition) do { \
+ if (!(_condition)) \
+ ucall(UCALL_ABORT, 2, \
+ "Failed guest assert: " \
+ #_condition, __LINE__); \
+} while (0)
#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h
index 54cfeb6568d3..31e030915c1f 100644
--- a/tools/testing/selftests/kvm/include/sparsebit.h
+++ b/tools/testing/selftests/kvm/include/sparsebit.h
@@ -15,8 +15,8 @@
* even in the case where most bits are set.
*/
-#ifndef _TEST_SPARSEBIT_H_
-#define _TEST_SPARSEBIT_H_
+#ifndef SELFTEST_KVM_SPARSEBIT_H
+#define SELFTEST_KVM_SPARSEBIT_H
#include <stdbool.h>
#include <stdint.h>
@@ -72,4 +72,4 @@ void sparsebit_validate_internal(struct sparsebit *sbit);
}
#endif
-#endif /* _TEST_SPARSEBIT_H_ */
+#endif /* SELFTEST_KVM_SPARSEBIT_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 73c3933436ec..c7dafe8bd02c 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -7,8 +7,8 @@
*
*/
-#ifndef TEST_UTIL_H
-#define TEST_UTIL_H 1
+#ifndef SELFTEST_KVM_TEST_UTIL_H
+#define SELFTEST_KVM_TEST_UTIL_H
#include <stdlib.h>
#include <stdarg.h>
@@ -41,4 +41,4 @@ void test_assert(bool exp, const char *exp_str,
#a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
} while (0)
-#endif /* TEST_UTIL_H */
+#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 42c3596815b8..e2884c2b81ff 100644
--- a/tools/testing/selftests/kvm/include/x86.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -1,5 +1,5 @@
/*
- * tools/testing/selftests/kvm/include/x86.h
+ * tools/testing/selftests/kvm/include/x86_64/processor.h
*
* Copyright (C) 2018, Google LLC.
*
@@ -7,8 +7,8 @@
*
*/
-#ifndef SELFTEST_KVM_X86_H
-#define SELFTEST_KVM_X86_H
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
#include <assert.h>
#include <stdint.h>
@@ -305,7 +305,25 @@ static inline unsigned long get_xmm(int n)
struct kvm_x86_state;
struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state);
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_x86_state *state);
+
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
+void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid);
+
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
+
+static inline struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_entry(uint32_t function)
+{
+ return kvm_get_supported_cpuid_index(function, 0);
+}
+
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index);
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+ uint64_t msr_value);
/*
* Basic CPU control in CR0
@@ -1044,4 +1062,4 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
#define MSR_VM_IGNNE 0xc0010115
#define MSR_VM_HSAVE_PA 0xc0010117
-#endif /* !SELFTEST_KVM_X86_H */
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index b9ffe1024d3a..c9bd935b939c 100644
--- a/tools/testing/selftests/kvm/include/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -1,5 +1,5 @@
/*
- * tools/testing/selftests/kvm/include/vmx.h
+ * tools/testing/selftests/kvm/include/x86_64/vmx.h
*
* Copyright (C) 2018, Google LLC.
*
@@ -11,7 +11,7 @@
#define SELFTEST_KVM_VMX_H
#include <stdint.h>
-#include "x86.h"
+#include "processor.h"
#define CPUID_VMX_BIT 5
@@ -339,6 +339,8 @@ struct vmx_msr_entry {
uint64_t value;
} __attribute__ ((aligned(16)));
+#include "evmcs.h"
+
static inline int vmxon(uint64_t phys)
{
uint8_t ret;
@@ -372,6 +374,9 @@ static inline int vmptrld(uint64_t vmcs_pa)
{
uint8_t ret;
+ if (enable_evmcs)
+ return -1;
+
__asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
: [ret]"=rm"(ret)
: [pa]"m"(vmcs_pa)
@@ -385,6 +390,9 @@ static inline int vmptrst(uint64_t *value)
uint64_t tmp;
uint8_t ret;
+ if (enable_evmcs)
+ return evmcs_vmptrst(value);
+
__asm__ __volatile__("vmptrst %[value]; setna %[ret]"
: [value]"=m"(tmp), [ret]"=rm"(ret)
: : "cc", "memory");
@@ -411,6 +419,9 @@ static inline int vmlaunch(void)
{
int ret;
+ if (enable_evmcs)
+ return evmcs_vmlaunch();
+
__asm__ __volatile__("push %%rbp;"
"push %%rcx;"
"push %%rdx;"
@@ -443,6 +454,9 @@ static inline int vmresume(void)
{
int ret;
+ if (enable_evmcs)
+ return evmcs_vmresume();
+
__asm__ __volatile__("push %%rbp;"
"push %%rcx;"
"push %%rdx;"
@@ -482,6 +496,9 @@ static inline int vmread(uint64_t encoding, uint64_t *value)
uint64_t tmp;
uint8_t ret;
+ if (enable_evmcs)
+ return evmcs_vmread(encoding, value);
+
__asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
: [value]"=rm"(tmp), [ret]"=rm"(ret)
: [encoding]"r"(encoding)
@@ -506,6 +523,9 @@ static inline int vmwrite(uint64_t encoding, uint64_t value)
{
uint8_t ret;
+ if (enable_evmcs)
+ return evmcs_vmwrite(encoding, value);
+
__asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
: [ret]"=rm"(ret)
: [value]"rm"(value), [encoding]"r"(encoding)
@@ -543,10 +563,19 @@ struct vmx_pages {
void *vmwrite_hva;
uint64_t vmwrite_gpa;
void *vmwrite;
+
+ void *vp_assist_hva;
+ uint64_t vp_assist_gpa;
+ void *vp_assist;
+
+ void *enlightened_vmcs_hva;
+ uint64_t enlightened_vmcs_gpa;
+ void *enlightened_vmcs;
};
struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
bool prepare_for_vmx_operation(struct vmx_pages *vmx);
void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
+bool load_vmcs(struct vmx_pages *vmx);
-#endif /* !SELFTEST_KVM_VMX_H */
+#endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
new file mode 100644
index 000000000000..b6022e2f116e
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AArch64 code
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+#define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000
+
+static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
+{
+ return (v + vm->page_size) & ~(vm->page_size - 1);
+}
+
+static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+ uint64_t mask = (1UL << (vm->va_bits - shift)) - 1;
+
+ return (gva >> shift) & mask;
+}
+
+static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift;
+ uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+ TEST_ASSERT(vm->pgtable_levels == 4,
+ "Mode %d does not have 4 page table levels", vm->mode);
+
+ return (gva >> shift) & mask;
+}
+
+static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ unsigned int shift = (vm->page_shift - 3) + vm->page_shift;
+ uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+ TEST_ASSERT(vm->pgtable_levels >= 3,
+ "Mode %d does not have >= 3 page table levels", vm->mode);
+
+ return (gva >> shift) & mask;
+}
+
+static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+ return (gva >> vm->page_shift) & mask;
+}
+
+static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
+{
+ uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift;
+ return entry & mask;
+}
+
+static uint64_t ptrs_per_pgd(struct kvm_vm *vm)
+{
+ unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+ return 1 << (vm->va_bits - shift);
+}
+
+static uint64_t ptrs_per_pte(struct kvm_vm *vm)
+{
+ return 1 << (vm->page_shift - 3);
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+ int rc;
+
+ if (!vm->pgd_created) {
+ vm_paddr_t paddr = vm_phy_pages_alloc(vm,
+ page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ vm->pgd = paddr;
+ vm->pgd_created = true;
+ }
+}
+
+void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint32_t pgd_memslot, uint64_t flags)
+{
+ uint8_t attr_idx = flags & 7;
+ uint64_t *ptep;
+
+ TEST_ASSERT((vaddr % vm->page_size) == 0,
+ "Virtual address not on page boundary,\n"
+ " vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size);
+ TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+ (vaddr >> vm->page_shift)),
+ "Invalid virtual address, vaddr: 0x%lx", vaddr);
+ TEST_ASSERT((paddr % vm->page_size) == 0,
+ "Physical address not on page boundary,\n"
+ " paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
+ if (!*ptep) {
+ *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ *ptep |= 3;
+ }
+
+ switch (vm->pgtable_levels) {
+ case 4:
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
+ if (!*ptep) {
+ *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ *ptep |= 3;
+ }
+ /* fall through */
+ case 3:
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
+ if (!*ptep) {
+ *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ *ptep |= 3;
+ }
+ /* fall through */
+ case 2:
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
+ break;
+ default:
+ TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+ }
+
+ *ptep = paddr | 3;
+ *ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */;
+}
+
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint32_t pgd_memslot)
+{
+ uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
+
+ _virt_pg_map(vm, vaddr, paddr, pgd_memslot, attr_idx);
+}
+
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ uint64_t *ptep;
+
+ if (!vm->pgd_created)
+ goto unmapped_gva;
+
+ ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+
+ switch (vm->pgtable_levels) {
+ case 4:
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ /* fall through */
+ case 3:
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ /* fall through */
+ case 2:
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ break;
+ default:
+ TEST_ASSERT(false, "Page table levels must be 2, 3, or 4");
+ }
+
+ return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+
+unmapped_gva:
+ TEST_ASSERT(false, "No mapping for vm virtual address, "
+ "gva: 0x%lx", gva);
+}
+
+static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
+{
+#ifdef DEBUG_VM
+ static const char * const type[] = { "", "pud", "pmd", "pte" };
+ uint64_t pte, *ptep;
+
+ if (level == 4)
+ return;
+
+ for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
+ ptep = addr_gpa2hva(vm, pte);
+ if (!*ptep)
+ continue;
+ printf("%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
+ pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1);
+ }
+#endif
+}
+
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ int level = 4 - (vm->pgtable_levels - 1);
+ uint64_t pgd, *ptep;
+
+ if (!vm->pgd_created)
+ return;
+
+ for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pgd(vm) * 8; pgd += 8) {
+ ptep = addr_gpa2hva(vm, pgd);
+ if (!*ptep)
+ continue;
+ printf("%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
+ pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
+ }
+}
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+ void *guest_code)
+{
+ uint64_t ptrs_per_4k_pte = 512;
+ uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2;
+ struct kvm_vm *vm;
+
+ vm = vm_create(VM_MODE_P52V48_4K, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+ vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+ return vm;
+}
+
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+ size_t stack_size = vm->page_size == 4096 ?
+ DEFAULT_STACK_PGS * vm->page_size :
+ vm->page_size;
+ uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+ DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0);
+
+ vm_vcpu_add(vm, vcpuid, 0, 0);
+
+ set_reg(vm, vcpuid, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
+ set_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+}
+
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+{
+ struct kvm_vcpu_init init;
+ uint64_t sctlr_el1, tcr_el1;
+
+ memset(&init, 0, sizeof(init));
+ init.target = KVM_ARM_TARGET_GENERIC_V8;
+ vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_INIT, &init);
+
+ /*
+ * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15
+ * registers, which the variable argument list macros do.
+ */
+ set_reg(vm, vcpuid, ARM64_SYS_REG(CPACR_EL1), 3 << 20);
+
+ get_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), &sctlr_el1);
+ get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1);
+
+ switch (vm->mode) {
+ case VM_MODE_P52V48_4K:
+ tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+ tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ break;
+ case VM_MODE_P52V48_64K:
+ tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+ tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ break;
+ case VM_MODE_P40V48_4K:
+ tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+ tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+ break;
+ case VM_MODE_P40V48_64K:
+ tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+ tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+ break;
+ default:
+ TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+
+ sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
+ /* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
+ tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
+ tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+
+ set_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), sctlr_el1);
+ set_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), tcr_el1);
+ set_reg(vm, vcpuid, ARM64_SYS_REG(MAIR_EL1), DEFAULT_MAIR_EL1);
+ set_reg(vm, vcpuid, ARM64_SYS_REG(TTBR0_EL1), vm->pgd);
+}
+
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+ uint64_t pstate, pc;
+
+ get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pstate), &pstate);
+ get_reg(vm, vcpuid, ARM64_CORE_REG(regs.pc), &pc);
+
+ fprintf(stream, "%*spstate: 0x%.16llx pc: 0x%.16llx\n",
+ indent, "", pstate, pc);
+
+}
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index cd01144d27c8..6398efe67885 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -13,7 +13,7 @@
#include <execinfo.h>
#include <sys/syscall.h>
-#include "../../kselftest.h"
+#include "kselftest.h"
/* Dumps the current stack trace to stderr. */
static void __attribute__((noinline)) test_dump_stack(void);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6fd8c089cafc..8c06da4f03db 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -16,10 +16,8 @@
#include <sys/stat.h>
#include <linux/kernel.h>
-#define KVM_DEV_PATH "/dev/kvm"
-
#define KVM_UTIL_PGS_PER_HUGEPG 512
-#define KVM_UTIL_MIN_PADDR 0x2000
+#define KVM_UTIL_MIN_PFN 2
/* Aligns x up to the next multiple of size. Size must be a power of 2. */
static void *align(void *x, size_t size)
@@ -30,7 +28,8 @@ static void *align(void *x, size_t size)
return (void *) (((size_t) x + mask) & ~mask);
}
-/* Capability
+/*
+ * Capability
*
* Input Args:
* cap - Capability
@@ -92,16 +91,23 @@ static void vm_open(struct kvm_vm *vm, int perm)
if (vm->kvm_fd < 0)
exit(KSFT_SKIP);
- /* Create VM. */
vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, NULL);
TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
"rc: %i errno: %i", vm->fd, errno);
}
-/* VM Create
+const char * const vm_guest_mode_string[] = {
+ "PA-bits:52, VA-bits:48, 4K pages",
+ "PA-bits:52, VA-bits:48, 64K pages",
+ "PA-bits:40, VA-bits:48, 4K pages",
+ "PA-bits:40, VA-bits:48, 64K pages",
+};
+
+/*
+ * VM Create
*
* Input Args:
- * mode - VM Mode (e.g. VM_MODE_FLAT48PG)
+ * mode - VM Mode (e.g. VM_MODE_P52V48_4K)
* phy_pages - Physical memory pages
* perm - permission
*
@@ -110,7 +116,7 @@ static void vm_open(struct kvm_vm *vm, int perm)
* Return:
* Pointer to opaque structure that describes the created VM.
*
- * Creates a VM with the mode specified by mode (e.g. VM_MODE_FLAT48PG).
+ * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K).
* When phy_pages is non-zero, a memory region of phy_pages physical pages
* is created and mapped starting at guest physical address 0. The file
* descriptor to control the created VM is created with the permissions
@@ -121,7 +127,6 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
struct kvm_vm *vm;
int kvm_fd;
- /* Allocate memory. */
vm = calloc(1, sizeof(*vm));
TEST_ASSERT(vm != NULL, "Insufficent Memory");
@@ -130,26 +135,48 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
/* Setup mode specific traits. */
switch (vm->mode) {
- case VM_MODE_FLAT48PG:
+ case VM_MODE_P52V48_4K:
+ vm->pgtable_levels = 4;
vm->page_size = 0x1000;
vm->page_shift = 12;
-
- /* Limit to 48-bit canonical virtual addresses. */
- vm->vpages_valid = sparsebit_alloc();
- sparsebit_set_num(vm->vpages_valid,
- 0, (1ULL << (48 - 1)) >> vm->page_shift);
- sparsebit_set_num(vm->vpages_valid,
- (~((1ULL << (48 - 1)) - 1)) >> vm->page_shift,
- (1ULL << (48 - 1)) >> vm->page_shift);
-
- /* Limit physical addresses to 52-bits. */
- vm->max_gfn = ((1ULL << 52) >> vm->page_shift) - 1;
+ vm->va_bits = 48;
+ break;
+ case VM_MODE_P52V48_64K:
+ vm->pgtable_levels = 3;
+ vm->pa_bits = 52;
+ vm->page_size = 0x10000;
+ vm->page_shift = 16;
+ vm->va_bits = 48;
+ break;
+ case VM_MODE_P40V48_4K:
+ vm->pgtable_levels = 4;
+ vm->pa_bits = 40;
+ vm->va_bits = 48;
+ vm->page_size = 0x1000;
+ vm->page_shift = 12;
+ break;
+ case VM_MODE_P40V48_64K:
+ vm->pgtable_levels = 3;
+ vm->pa_bits = 40;
+ vm->va_bits = 48;
+ vm->page_size = 0x10000;
+ vm->page_shift = 16;
break;
-
default:
TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
}
+ /* Limit to VA-bit canonical virtual addresses. */
+ vm->vpages_valid = sparsebit_alloc();
+ sparsebit_set_num(vm->vpages_valid,
+ 0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift);
+ sparsebit_set_num(vm->vpages_valid,
+ (~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift,
+ (1ULL << (vm->va_bits - 1)) >> vm->page_shift);
+
+ /* Limit physical addresses to PA-bits. */
+ vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+
/* Allocate and setup memory for guest. */
vm->vpages_mapped = sparsebit_alloc();
if (phy_pages != 0)
@@ -159,7 +186,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
return vm;
}
-/* VM Restart
+/*
+ * VM Restart
*
* Input Args:
* vm - VM that has been released before
@@ -186,7 +214,8 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm)
" rc: %i errno: %i\n"
" slot: %u flags: 0x%x\n"
" guest_phys_addr: 0x%lx size: 0x%lx",
- ret, errno, region->region.slot, region->region.flags,
+ ret, errno, region->region.slot,
+ region->region.flags,
region->region.guest_phys_addr,
region->region.memory_size);
}
@@ -202,7 +231,8 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
strerror(-ret));
}
-/* Userspace Memory Region Find
+/*
+ * Userspace Memory Region Find
*
* Input Args:
* vm - Virtual Machine
@@ -220,8 +250,8 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
* of the regions is returned. Null is returned only when no overlapping
* region exists.
*/
-static struct userspace_mem_region *userspace_mem_region_find(
- struct kvm_vm *vm, uint64_t start, uint64_t end)
+static struct userspace_mem_region *
+userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
{
struct userspace_mem_region *region;
@@ -237,7 +267,8 @@ static struct userspace_mem_region *userspace_mem_region_find(
return NULL;
}
-/* KVM Userspace Memory Region Find
+/*
+ * KVM Userspace Memory Region Find
*
* Input Args:
* vm - Virtual Machine
@@ -265,7 +296,8 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
return &region->region;
}
-/* VCPU Find
+/*
+ * VCPU Find
*
* Input Args:
* vm - Virtual Machine
@@ -280,8 +312,7 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
* returns a pointer to it. Returns NULL if the VM doesn't contain a VCPU
* for the specified vcpuid.
*/
-struct vcpu *vcpu_find(struct kvm_vm *vm,
- uint32_t vcpuid)
+struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid)
{
struct vcpu *vcpup;
@@ -293,7 +324,8 @@ struct vcpu *vcpu_find(struct kvm_vm *vm,
return NULL;
}
-/* VM VCPU Remove
+/*
+ * VM VCPU Remove
*
* Input Args:
* vm - Virtual Machine
@@ -330,11 +362,9 @@ void kvm_vm_release(struct kvm_vm *vmp)
{
int ret;
- /* Free VCPUs. */
while (vmp->vcpu_head)
vm_vcpu_rm(vmp, vmp->vcpu_head->id);
- /* Close file descriptor for the VM. */
ret = close(vmp->fd);
TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
" vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno);
@@ -344,7 +374,8 @@ void kvm_vm_release(struct kvm_vm *vmp)
" vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno);
}
-/* Destroys and frees the VM pointed to by vmp.
+/*
+ * Destroys and frees the VM pointed to by vmp.
*/
void kvm_vm_free(struct kvm_vm *vmp)
{
@@ -383,7 +414,8 @@ void kvm_vm_free(struct kvm_vm *vmp)
free(vmp);
}
-/* Memory Compare, host virtual to guest virtual
+/*
+ * Memory Compare, host virtual to guest virtual
*
* Input Args:
* hva - Starting host virtual address
@@ -405,23 +437,25 @@ void kvm_vm_free(struct kvm_vm *vmp)
* a length of len, to the guest bytes starting at the guest virtual
* address given by gva.
*/
-int kvm_memcmp_hva_gva(void *hva,
- struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
{
size_t amt;
- /* Compare a batch of bytes until either a match is found
+ /*
+ * Compare a batch of bytes until either a match is found
* or all the bytes have been compared.
*/
for (uintptr_t offset = 0; offset < len; offset += amt) {
uintptr_t ptr1 = (uintptr_t)hva + offset;
- /* Determine host address for guest virtual address
+ /*
+ * Determine host address for guest virtual address
* at offset.
*/
uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);
- /* Determine amount to compare on this pass.
+ /*
+ * Determine amount to compare on this pass.
* Don't allow the comparsion to cross a page boundary.
*/
amt = len - offset;
@@ -433,7 +467,8 @@ int kvm_memcmp_hva_gva(void *hva,
assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));
- /* Perform the comparison. If there is a difference
+ /*
+ * Perform the comparison. If there is a difference
* return that result to the caller, otherwise need
* to continue on looking for a mismatch.
*/
@@ -442,109 +477,15 @@ int kvm_memcmp_hva_gva(void *hva,
return ret;
}
- /* No mismatch found. Let the caller know the two memory
+ /*
+ * No mismatch found. Let the caller know the two memory
* areas are equal.
*/
return 0;
}
-/* Allocate an instance of struct kvm_cpuid2
- *
- * Input Args: None
- *
- * Output Args: None
- *
- * Return: A pointer to the allocated struct. The caller is responsible
- * for freeing this struct.
- *
- * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
- * array to be decided at allocation time, allocation is slightly
- * complicated. This function uses a reasonable default length for
- * the array and performs the appropriate allocation.
- */
-static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
-{
- struct kvm_cpuid2 *cpuid;
- int nent = 100;
- size_t size;
-
- size = sizeof(*cpuid);
- size += nent * sizeof(struct kvm_cpuid_entry2);
- cpuid = malloc(size);
- if (!cpuid) {
- perror("malloc");
- abort();
- }
-
- cpuid->nent = nent;
-
- return cpuid;
-}
-
-/* KVM Supported CPUID Get
- *
- * Input Args: None
- *
- * Output Args:
- *
- * Return: The supported KVM CPUID
- *
- * Get the guest CPUID supported by KVM.
- */
-struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
-{
- static struct kvm_cpuid2 *cpuid;
- int ret;
- int kvm_fd;
-
- if (cpuid)
- return cpuid;
-
- cpuid = allocate_kvm_cpuid2();
- kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- if (kvm_fd < 0)
- exit(KSFT_SKIP);
-
- ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
- TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
- ret, errno);
-
- close(kvm_fd);
- return cpuid;
-}
-
-/* Locate a cpuid entry.
- *
- * Input Args:
- * cpuid: The cpuid.
- * function: The function of the cpuid entry to find.
- *
- * Output Args: None
- *
- * Return: A pointer to the cpuid entry. Never returns NULL.
- */
-struct kvm_cpuid_entry2 *
-kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
-{
- struct kvm_cpuid2 *cpuid;
- struct kvm_cpuid_entry2 *entry = NULL;
- int i;
-
- cpuid = kvm_get_supported_cpuid();
- for (i = 0; i < cpuid->nent; i++) {
- if (cpuid->entries[i].function == function &&
- cpuid->entries[i].index == index) {
- entry = &cpuid->entries[i];
- break;
- }
- }
-
- TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
- function, index);
- return entry;
-}
-
-/* VM Userspace Memory Region Add
+/*
+ * VM Userspace Memory Region Add
*
* Input Args:
* vm - Virtual Machine
@@ -586,7 +527,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
" vm->max_gfn: 0x%lx vm->page_size: 0x%x",
guest_paddr, npages, vm->max_gfn, vm->page_size);
- /* Confirm a mem region with an overlapping address doesn't
+ /*
+ * Confirm a mem region with an overlapping address doesn't
* already exist.
*/
region = (struct userspace_mem_region *) userspace_mem_region_find(
@@ -677,7 +619,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
vm->userspace_mem_region_head = region;
}
-/* Memslot to region
+/*
+ * Memslot to region
*
* Input Args:
* vm - Virtual Machine
@@ -691,8 +634,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
* on error (e.g. currently no memory region using memslot as a KVM
* memory slot ID).
*/
-static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
- uint32_t memslot)
+static struct userspace_mem_region *
+memslot2region(struct kvm_vm *vm, uint32_t memslot)
{
struct userspace_mem_region *region;
@@ -712,7 +655,8 @@ static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
return region;
}
-/* VM Memory Region Flags Set
+/*
+ * VM Memory Region Flags Set
*
* Input Args:
* vm - Virtual Machine
@@ -730,7 +674,6 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
int ret;
struct userspace_mem_region *region;
- /* Locate memory region. */
region = memslot2region(vm, slot);
region->region.flags = flags;
@@ -742,7 +685,8 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
ret, errno, slot, flags);
}
-/* VCPU mmap Size
+/*
+ * VCPU mmap Size
*
* Input Args: None
*
@@ -772,7 +716,8 @@ static int vcpu_mmap_sz(void)
return ret;
}
-/* VM VCPU Add
+/*
+ * VM VCPU Add
*
* Input Args:
* vm - Virtual Machine
@@ -785,7 +730,8 @@ static int vcpu_mmap_sz(void)
* Creates and adds to the VM specified by vm and virtual CPU with
* the ID given by vcpuid.
*/
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_memslot)
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot,
+ int gdt_memslot)
{
struct vcpu *vcpu;
@@ -823,7 +769,8 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_me
vcpu_setup(vm, vcpuid, pgd_memslot, gdt_memslot);
}
-/* VM Virtual Address Unused Gap
+/*
+ * VM Virtual Address Unused Gap
*
* Input Args:
* vm - Virtual Machine
@@ -843,14 +790,14 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid, int pgd_memslot, int gdt_me
* sz unallocated bytes >= vaddr_min is available.
*/
static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
- vm_vaddr_t vaddr_min)
+ vm_vaddr_t vaddr_min)
{
uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;
/* Determine lowest permitted virtual page index. */
uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift;
if ((pgidx_start * vm->page_size) < vaddr_min)
- goto no_va_found;
+ goto no_va_found;
/* Loop over section with enough valid virtual page indexes. */
if (!sparsebit_is_set_num(vm->vpages_valid,
@@ -909,7 +856,8 @@ va_found:
return pgidx_start * vm->page_size;
}
-/* VM Virtual Address Allocate
+/*
+ * VM Virtual Address Allocate
*
* Input Args:
* vm - Virtual Machine
@@ -930,13 +878,14 @@ va_found:
* a page.
*/
vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
- uint32_t data_memslot, uint32_t pgd_memslot)
+ uint32_t data_memslot, uint32_t pgd_memslot)
{
uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
virt_pgd_alloc(vm, pgd_memslot);
- /* Find an unused range of virtual page addresses of at least
+ /*
+ * Find an unused range of virtual page addresses of at least
* pages in length.
*/
vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min);
@@ -946,7 +895,8 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
pages--, vaddr += vm->page_size) {
vm_paddr_t paddr;
- paddr = vm_phy_page_alloc(vm, KVM_UTIL_MIN_PADDR, data_memslot);
+ paddr = vm_phy_page_alloc(vm,
+ KVM_UTIL_MIN_PFN * vm->page_size, data_memslot);
virt_pg_map(vm, vaddr, paddr, pgd_memslot);
@@ -990,7 +940,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
}
}
-/* Address VM Physical to Host Virtual
+/*
+ * Address VM Physical to Host Virtual
*
* Input Args:
* vm - Virtual Machine
@@ -1022,7 +973,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
return NULL;
}
-/* Address Host Virtual to VM Physical
+/*
+ * Address Host Virtual to VM Physical
*
* Input Args:
* vm - Virtual Machine
@@ -1056,7 +1008,8 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
return -1;
}
-/* VM Create IRQ Chip
+/*
+ * VM Create IRQ Chip
*
* Input Args:
* vm - Virtual Machine
@@ -1078,7 +1031,8 @@ void vm_create_irqchip(struct kvm_vm *vm)
vm->has_irqchip = true;
}
-/* VM VCPU State
+/*
+ * VM VCPU State
*
* Input Args:
* vm - Virtual Machine
@@ -1100,7 +1054,8 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid)
return vcpu->state;
}
-/* VM VCPU Run
+/*
+ * VM VCPU Run
*
* Input Args:
* vm - Virtual Machine
@@ -1126,13 +1081,14 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
int rc;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- do {
+ do {
rc = ioctl(vcpu->fd, KVM_RUN, NULL);
} while (rc == -1 && errno == EINTR);
return rc;
}
-/* VM VCPU Set MP State
+/*
+ * VM VCPU Set MP State
*
* Input Args:
* vm - Virtual Machine
@@ -1147,7 +1103,7 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
* by mp_state.
*/
void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_mp_state *mp_state)
+ struct kvm_mp_state *mp_state)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
@@ -1159,7 +1115,8 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
"rc: %i errno: %i", ret, errno);
}
-/* VM VCPU Regs Get
+/*
+ * VM VCPU Regs Get
*
* Input Args:
* vm - Virtual Machine
@@ -1173,21 +1130,20 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
* Obtains the current register state for the VCPU specified by vcpuid
* and stores it at the location given by regs.
*/
-void vcpu_regs_get(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_regs *regs)
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- /* Get the regs. */
ret = ioctl(vcpu->fd, KVM_GET_REGS, regs);
TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i",
ret, errno);
}
-/* VM VCPU Regs Set
+/*
+ * VM VCPU Regs Set
*
* Input Args:
* vm - Virtual Machine
@@ -1201,165 +1157,46 @@ void vcpu_regs_get(struct kvm_vm *vm,
* Sets the regs of the VCPU specified by vcpuid to the values
* given by regs.
*/
-void vcpu_regs_set(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_regs *regs)
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- /* Set the regs. */
ret = ioctl(vcpu->fd, KVM_SET_REGS, regs);
TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i",
ret, errno);
}
void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events)
+ struct kvm_vcpu_events *events)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- /* Get the regs. */
ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events);
TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i",
ret, errno);
}
void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events)
+ struct kvm_vcpu_events *events)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- /* Set the regs. */
ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events);
TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i",
ret, errno);
}
-/* VCPU Get MSR
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * msr_index - Index of MSR
- *
- * Output Args: None
- *
- * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
- *
- * Get value of MSR for VCPU.
- */
-uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
-{
- struct vcpu *vcpu = vcpu_find(vm, vcpuid);
- struct {
- struct kvm_msrs header;
- struct kvm_msr_entry entry;
- } buffer = {};
- int r;
-
- TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- buffer.header.nmsrs = 1;
- buffer.entry.index = msr_index;
- r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
- TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
- " rc: %i errno: %i", r, errno);
-
- return buffer.entry.data;
-}
-
-/* VCPU Set MSR
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * msr_index - Index of MSR
- * msr_value - New value of MSR
- *
- * Output Args: None
- *
- * Return: On success, nothing. On failure a TEST_ASSERT is produced.
- *
- * Set value of MSR for VCPU.
- */
-void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
- uint64_t msr_value)
-{
- struct vcpu *vcpu = vcpu_find(vm, vcpuid);
- struct {
- struct kvm_msrs header;
- struct kvm_msr_entry entry;
- } buffer = {};
- int r;
-
- TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- memset(&buffer, 0, sizeof(buffer));
- buffer.header.nmsrs = 1;
- buffer.entry.index = msr_index;
- buffer.entry.data = msr_value;
- r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
- TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
- " rc: %i errno: %i", r, errno);
-}
-
-/* VM VCPU Args Set
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * num - number of arguments
- * ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first num function input arguments to the values
- * given as variable args. Each of the variable args is expected to
- * be of type uint64_t.
- */
-void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
-{
- va_list ap;
- struct kvm_regs regs;
-
- TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
- " num: %u\n",
- num);
-
- va_start(ap, num);
- vcpu_regs_get(vm, vcpuid, &regs);
-
- if (num >= 1)
- regs.rdi = va_arg(ap, uint64_t);
-
- if (num >= 2)
- regs.rsi = va_arg(ap, uint64_t);
-
- if (num >= 3)
- regs.rdx = va_arg(ap, uint64_t);
-
- if (num >= 4)
- regs.rcx = va_arg(ap, uint64_t);
-
- if (num >= 5)
- regs.r8 = va_arg(ap, uint64_t);
-
- if (num >= 6)
- regs.r9 = va_arg(ap, uint64_t);
-
- vcpu_regs_set(vm, vcpuid, &regs);
- va_end(ap);
-}
-
-/* VM VCPU System Regs Get
+/*
+ * VM VCPU System Regs Get
*
* Input Args:
* vm - Virtual Machine
@@ -1373,22 +1210,20 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
* Obtains the current system register state for the VCPU specified by
* vcpuid and stores it at the location given by sregs.
*/
-void vcpu_sregs_get(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_sregs *sregs)
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- /* Get the regs. */
- /* Get the regs. */
ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs);
TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i",
ret, errno);
}
-/* VM VCPU System Regs Set
+/*
+ * VM VCPU System Regs Set
*
* Input Args:
* vm - Virtual Machine
@@ -1402,27 +1237,25 @@ void vcpu_sregs_get(struct kvm_vm *vm,
* Sets the system regs of the VCPU specified by vcpuid to the values
* given by sregs.
*/
-void vcpu_sregs_set(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_sregs *sregs)
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
{
int ret = _vcpu_sregs_set(vm, vcpuid, sregs);
TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
"rc: %i errno: %i", ret, errno);
}
-int _vcpu_sregs_set(struct kvm_vm *vm,
- uint32_t vcpuid, struct kvm_sregs *sregs)
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
- /* Get the regs. */
return ioctl(vcpu->fd, KVM_SET_SREGS, sregs);
}
-/* VCPU Ioctl
+/*
+ * VCPU Ioctl
*
* Input Args:
* vm - Virtual Machine
@@ -1434,8 +1267,8 @@ int _vcpu_sregs_set(struct kvm_vm *vm,
*
* Issues an arbitrary ioctl on a VCPU fd.
*/
-void vcpu_ioctl(struct kvm_vm *vm,
- uint32_t vcpuid, unsigned long cmd, void *arg)
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid,
+ unsigned long cmd, void *arg)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int ret;
@@ -1447,7 +1280,8 @@ void vcpu_ioctl(struct kvm_vm *vm,
cmd, ret, errno, strerror(errno));
}
-/* VM Ioctl
+/*
+ * VM Ioctl
*
* Input Args:
* vm - Virtual Machine
@@ -1467,7 +1301,8 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
cmd, ret, errno, strerror(errno));
}
-/* VM Dump
+/*
+ * VM Dump
*
* Input Args:
* vm - Virtual Machine
@@ -1514,38 +1349,6 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
vcpu_dump(stream, vm, vcpu->id, indent + 2);
}
-/* VM VCPU Dump
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * indent - Left margin indent amount
- *
- * Output Args:
- * stream - Output FILE stream
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by vcpuid, within the VM
- * given by vm, to the FILE stream given by stream.
- */
-void vcpu_dump(FILE *stream, struct kvm_vm *vm,
- uint32_t vcpuid, uint8_t indent)
-{
- struct kvm_regs regs;
- struct kvm_sregs sregs;
-
- fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
-
- fprintf(stream, "%*sregs:\n", indent + 2, "");
- vcpu_regs_get(vm, vcpuid, &regs);
- regs_dump(stream, &regs, indent + 4);
-
- fprintf(stream, "%*ssregs:\n", indent + 2, "");
- vcpu_sregs_get(vm, vcpuid, &sregs);
- sregs_dump(stream, &sregs, indent + 4);
-}
-
/* Known KVM exit reasons */
static struct exit_reason {
unsigned int reason;
@@ -1576,7 +1379,8 @@ static struct exit_reason {
#endif
};
-/* Exit Reason String
+/*
+ * Exit Reason String
*
* Input Args:
* exit_reason - Exit reason
@@ -1602,10 +1406,12 @@ const char *exit_reason_str(unsigned int exit_reason)
return "Unknown";
}
-/* Physical Page Allocate
+/*
+ * Physical Contiguous Page Allocator
*
* Input Args:
* vm - Virtual Machine
+ * num - number of pages
* paddr_min - Physical address minimum
* memslot - Memory region to allocate page from
*
@@ -1614,47 +1420,59 @@ const char *exit_reason_str(unsigned int exit_reason)
* Return:
* Starting physical address
*
- * Within the VM specified by vm, locates an available physical page
- * at or above paddr_min. If found, the page is marked as in use
- * and its address is returned. A TEST_ASSERT failure occurs if no
- * page is available at or above paddr_min.
+ * Within the VM specified by vm, locates a range of available physical
+ * pages at or above paddr_min. If found, the pages are marked as in use
+ * and thier base address is returned. A TEST_ASSERT failure occurs if
+ * not enough pages are available at or above paddr_min.
*/
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
- vm_paddr_t paddr_min, uint32_t memslot)
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+ vm_paddr_t paddr_min, uint32_t memslot)
{
struct userspace_mem_region *region;
- sparsebit_idx_t pg;
+ sparsebit_idx_t pg, base;
+
+ TEST_ASSERT(num > 0, "Must allocate at least one page");
TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
"not divisible by page size.\n"
" paddr_min: 0x%lx page_size: 0x%x",
paddr_min, vm->page_size);
- /* Locate memory region. */
region = memslot2region(vm, memslot);
+ base = pg = paddr_min >> vm->page_shift;
- /* Locate next available physical page at or above paddr_min. */
- pg = paddr_min >> vm->page_shift;
-
- if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
- pg = sparsebit_next_set(region->unused_phy_pages, pg);
- if (pg == 0) {
- fprintf(stderr, "No guest physical page available, "
- "paddr_min: 0x%lx page_size: 0x%x memslot: %u",
- paddr_min, vm->page_size, memslot);
- fputs("---- vm dump ----\n", stderr);
- vm_dump(stderr, vm, 2);
- abort();
+ do {
+ for (; pg < base + num; ++pg) {
+ if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
+ base = pg = sparsebit_next_set(region->unused_phy_pages, pg);
+ break;
+ }
}
+ } while (pg && pg != base + num);
+
+ if (pg == 0) {
+ fprintf(stderr, "No guest physical page available, "
+ "paddr_min: 0x%lx page_size: 0x%x memslot: %u\n",
+ paddr_min, vm->page_size, memslot);
+ fputs("---- vm dump ----\n", stderr);
+ vm_dump(stderr, vm, 2);
+ abort();
}
- /* Specify page as in use and return its address. */
- sparsebit_clear(region->unused_phy_pages, pg);
+ for (pg = base; pg < base + num; ++pg)
+ sparsebit_clear(region->unused_phy_pages, pg);
+
+ return base * vm->page_size;
+}
- return pg * vm->page_size;
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+ uint32_t memslot)
+{
+ return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
}
-/* Address Guest Virtual to Host Virtual
+/*
+ * Address Guest Virtual to Host Virtual
*
* Input Args:
* vm - Virtual Machine
@@ -1669,17 +1487,3 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
{
return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
}
-
-void guest_args_read(struct kvm_vm *vm, uint32_t vcpu_id,
- struct guest_args *args)
-{
- struct kvm_run *run = vcpu_state(vm, vcpu_id);
- struct kvm_regs regs;
-
- memset(&regs, 0, sizeof(regs));
- vcpu_regs_get(vm, vcpu_id, &regs);
-
- args->port = run->io.port;
- args->arg0 = regs.rdi;
- args->arg1 = regs.rsi;
-}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 542ed606b338..52701db0f253 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -1,28 +1,29 @@
/*
- * tools/testing/selftests/kvm/lib/kvm_util.c
+ * tools/testing/selftests/kvm/lib/kvm_util_internal.h
*
* Copyright (C) 2018, Google LLC.
*
* This work is licensed under the terms of the GNU GPL, version 2.
*/
-#ifndef KVM_UTIL_INTERNAL_H
-#define KVM_UTIL_INTERNAL_H 1
+#ifndef SELFTEST_KVM_UTIL_INTERNAL_H
+#define SELFTEST_KVM_UTIL_INTERNAL_H
#include "sparsebit.h"
+#define KVM_DEV_PATH "/dev/kvm"
+
#ifndef BITS_PER_BYTE
-#define BITS_PER_BYTE 8
+#define BITS_PER_BYTE 8
#endif
#ifndef BITS_PER_LONG
-#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
+#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
#endif
#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
-#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG)
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG)
-/* Concrete definition of struct kvm_vm. */
struct userspace_mem_region {
struct userspace_mem_region *next, *prev;
struct kvm_userspace_memory_region region;
@@ -45,14 +46,16 @@ struct kvm_vm {
int mode;
int kvm_fd;
int fd;
+ unsigned int pgtable_levels;
unsigned int page_size;
unsigned int page_shift;
+ unsigned int pa_bits;
+ unsigned int va_bits;
uint64_t max_gfn;
struct vcpu *vcpu_head;
struct userspace_mem_region *userspace_mem_region_head;
struct sparsebit *vpages_valid;
struct sparsebit *vpages_mapped;
-
bool has_irqchip;
bool pgd_created;
vm_paddr_t pgd;
@@ -60,13 +63,11 @@ struct kvm_vm {
vm_vaddr_t tss;
};
-struct vcpu *vcpu_find(struct kvm_vm *vm,
- uint32_t vcpuid);
-void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot);
+struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot,
+ int gdt_memslot);
void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-void regs_dump(FILE *stream, struct kvm_regs *regs,
- uint8_t indent);
-void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
- uint8_t indent);
+void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
-#endif
+#endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/ucall.c b/tools/testing/selftests/kvm/lib/ucall.c
new file mode 100644
index 000000000000..4777f9bb5194
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/ucall.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+#include "kvm_util_internal.h"
+
+#define UCALL_PIO_PORT ((uint16_t)0x1000)
+
+static ucall_type_t ucall_type;
+static vm_vaddr_t *ucall_exit_mmio_addr;
+
+static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+ if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1))
+ return false;
+
+ virt_pg_map(vm, gpa, gpa, 0);
+
+ ucall_exit_mmio_addr = (vm_vaddr_t *)gpa;
+ sync_global_to_guest(vm, ucall_exit_mmio_addr);
+
+ return true;
+}
+
+void ucall_init(struct kvm_vm *vm, ucall_type_t type, void *arg)
+{
+ ucall_type = type;
+ sync_global_to_guest(vm, ucall_type);
+
+ if (type == UCALL_PIO)
+ return;
+
+ if (type == UCALL_MMIO) {
+ vm_paddr_t gpa, start, end, step;
+ bool ret;
+
+ if (arg) {
+ gpa = (vm_paddr_t)arg;
+ ret = ucall_mmio_init(vm, gpa);
+ TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa);
+ return;
+ }
+
+ /*
+ * Find an address within the allowed virtual address space,
+ * that does _not_ have a KVM memory region associated with it.
+ * Identity mapping an address like this allows the guest to
+ * access it, but as KVM doesn't know what to do with it, it
+ * will assume it's something userspace handles and exit with
+ * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
+ * Here we start with a guess that the addresses around two
+ * thirds of the VA space are unmapped and then work both down
+ * and up from there in 1/6 VA space sized steps.
+ */
+ start = 1ul << (vm->va_bits * 2 / 3);
+ end = 1ul << vm->va_bits;
+ step = 1ul << (vm->va_bits / 6);
+ for (gpa = start; gpa >= 0; gpa -= step) {
+ if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+ return;
+ }
+ for (gpa = start + step; gpa < end; gpa += step) {
+ if (ucall_mmio_init(vm, gpa & ~(vm->page_size - 1)))
+ return;
+ }
+ TEST_ASSERT(false, "Can't find a ucall mmio address");
+ }
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+ ucall_type = 0;
+ sync_global_to_guest(vm, ucall_type);
+ ucall_exit_mmio_addr = 0;
+ sync_global_to_guest(vm, ucall_exit_mmio_addr);
+}
+
+static void ucall_pio_exit(struct ucall *uc)
+{
+#ifdef __x86_64__
+ asm volatile("in %[port], %%al"
+ : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax");
+#endif
+}
+
+static void ucall_mmio_exit(struct ucall *uc)
+{
+ *ucall_exit_mmio_addr = (vm_vaddr_t)uc;
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+ struct ucall uc = {
+ .cmd = cmd,
+ };
+ va_list va;
+ int i;
+
+ nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+ va_start(va, nargs);
+ for (i = 0; i < nargs; ++i)
+ uc.args[i] = va_arg(va, uint64_t);
+ va_end(va);
+
+ switch (ucall_type) {
+ case UCALL_PIO:
+ ucall_pio_exit(&uc);
+ break;
+ case UCALL_MMIO:
+ ucall_mmio_exit(&uc);
+ break;
+ };
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+ struct kvm_run *run = vcpu_state(vm, vcpu_id);
+
+ memset(uc, 0, sizeof(*uc));
+
+#ifdef __x86_64__
+ if (ucall_type == UCALL_PIO && run->exit_reason == KVM_EXIT_IO &&
+ run->io.port == UCALL_PIO_PORT) {
+ struct kvm_regs regs;
+ vcpu_regs_get(vm, vcpu_id, &regs);
+ memcpy(uc, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi), sizeof(*uc));
+ return uc->cmd;
+ }
+#endif
+ if (ucall_type == UCALL_MMIO && run->exit_reason == KVM_EXIT_MMIO &&
+ run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
+ vm_vaddr_t gva;
+ TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
+ "Unexpected ucall exit mmio address access");
+ gva = *(vm_vaddr_t *)run->mmio.data;
+ memcpy(uc, addr_gva2hva(vm, gva), sizeof(*uc));
+ }
+
+ return uc->cmd;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index a3122f1949a8..f28127f4a3af 100644
--- a/tools/testing/selftests/kvm/lib/x86.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1,5 +1,5 @@
/*
- * tools/testing/selftests/kvm/lib/x86.c
+ * tools/testing/selftests/kvm/lib/x86_64/processor.c
*
* Copyright (C) 2018, Google LLC.
*
@@ -10,8 +10,8 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "kvm_util_internal.h"
-#include "x86.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
/* Minimum physical address used for virtual translation tables. */
#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
@@ -231,7 +231,7 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
{
int rc;
- TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+ TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
/* If needed, create page map l4 table. */
@@ -264,7 +264,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
uint16_t index[4];
struct pageMapL4Entry *pml4e;
- TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+ TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -551,7 +551,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
struct pageTableEntry *pte;
void *hva;
- TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+ TEST_ASSERT(vm->mode == VM_MODE_P52V48_4K, "Attempt to use "
"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
index[0] = (gva >> 12) & 0x1ffu;
@@ -624,9 +624,9 @@ void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
switch (vm->mode) {
- case VM_MODE_FLAT48PG:
+ case VM_MODE_P52V48_4K:
sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
- sregs.cr4 |= X86_CR4_PAE;
+ sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
kvm_seg_set_unusable(&sregs.ldt);
@@ -672,6 +672,102 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
vcpu_set_mp_state(vm, vcpuid, &mp_state);
}
+/* Allocate an instance of struct kvm_cpuid2
+ *
+ * Input Args: None
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the allocated struct. The caller is responsible
+ * for freeing this struct.
+ *
+ * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
+ * array to be decided at allocation time, allocation is slightly
+ * complicated. This function uses a reasonable default length for
+ * the array and performs the appropriate allocation.
+ */
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+{
+ struct kvm_cpuid2 *cpuid;
+ int nent = 100;
+ size_t size;
+
+ size = sizeof(*cpuid);
+ size += nent * sizeof(struct kvm_cpuid_entry2);
+ cpuid = malloc(size);
+ if (!cpuid) {
+ perror("malloc");
+ abort();
+ }
+
+ cpuid->nent = nent;
+
+ return cpuid;
+}
+
+/* KVM Supported CPUID Get
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *
+ * Return: The supported KVM CPUID
+ *
+ * Get the guest CPUID supported by KVM.
+ */
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
+{
+ static struct kvm_cpuid2 *cpuid;
+ int ret;
+ int kvm_fd;
+
+ if (cpuid)
+ return cpuid;
+
+ cpuid = allocate_kvm_cpuid2();
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
+ TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
+ ret, errno);
+
+ close(kvm_fd);
+ return cpuid;
+}
+
+/* Locate a cpuid entry.
+ *
+ * Input Args:
+ * cpuid: The cpuid.
+ * function: The function of the cpuid entry to find.
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the cpuid entry. Never returns NULL.
+ */
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
+{
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_cpuid_entry2 *entry = NULL;
+ int i;
+
+ cpuid = kvm_get_supported_cpuid();
+ for (i = 0; i < cpuid->nent; i++) {
+ if (cpuid->entries[i].function == function &&
+ cpuid->entries[i].index == index) {
+ entry = &cpuid->entries[i];
+ break;
+ }
+ }
+
+ TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
+ function, index);
+ return entry;
+}
+
/* VM VCPU CPUID Set
*
* Input Args:
@@ -698,6 +794,7 @@ void vcpu_set_cpuid(struct kvm_vm *vm,
rc, errno);
}
+
/* Create a VM with reasonable defaults
*
* Input Args:
@@ -726,7 +823,7 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
/* Create VM */
- vm = vm_create(VM_MODE_FLAT48PG,
+ vm = vm_create(VM_MODE_P52V48_4K,
DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
O_RDWR);
@@ -742,6 +839,154 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
return vm;
}
+/* VCPU Get MSR
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * msr_index - Index of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
+ *
+ * Get value of MSR for VCPU.
+ */
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ struct {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+ } buffer = {};
+ int r;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+ buffer.header.nmsrs = 1;
+ buffer.entry.index = msr_index;
+ r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
+ TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
+ " rc: %i errno: %i", r, errno);
+
+ return buffer.entry.data;
+}
+
+/* VCPU Set MSR
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * msr_index - Index of MSR
+ * msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ *
+ * Set value of MSR for VCPU.
+ */
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+ uint64_t msr_value)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ struct {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+ } buffer = {};
+ int r;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+ memset(&buffer, 0, sizeof(buffer));
+ buffer.header.nmsrs = 1;
+ buffer.entry.index = msr_index;
+ buffer.entry.data = msr_value;
+ r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
+ TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
+ " rc: %i errno: %i", r, errno);
+}
+
+/* VM VCPU Args Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * num - number of arguments
+ * ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first num function input arguments to the values
+ * given as variable args. Each of the variable args is expected to
+ * be of type uint64_t.
+ */
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ struct kvm_regs regs;
+
+ TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
+ " num: %u\n",
+ num);
+
+ va_start(ap, num);
+ vcpu_regs_get(vm, vcpuid, &regs);
+
+ if (num >= 1)
+ regs.rdi = va_arg(ap, uint64_t);
+
+ if (num >= 2)
+ regs.rsi = va_arg(ap, uint64_t);
+
+ if (num >= 3)
+ regs.rdx = va_arg(ap, uint64_t);
+
+ if (num >= 4)
+ regs.rcx = va_arg(ap, uint64_t);
+
+ if (num >= 5)
+ regs.r8 = va_arg(ap, uint64_t);
+
+ if (num >= 6)
+ regs.r9 = va_arg(ap, uint64_t);
+
+ vcpu_regs_set(vm, vcpuid, &regs);
+ va_end(ap);
+}
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * indent - Left margin indent amount
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by vcpuid, within the VM
+ * given by vm, to the FILE stream given by stream.
+ */
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+
+ fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
+
+ fprintf(stream, "%*sregs:\n", indent + 2, "");
+ vcpu_regs_get(vm, vcpuid, &regs);
+ regs_dump(stream, &regs, indent + 4);
+
+ fprintf(stream, "%*ssregs:\n", indent + 2, "");
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+ sregs_dump(stream, &sregs, indent + 4);
+}
+
struct kvm_x86_state {
struct kvm_vcpu_events events;
struct kvm_mp_state mp_state;
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index b987c3c970eb..771ba6bf751c 100644
--- a/tools/testing/selftests/kvm/lib/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -1,5 +1,5 @@
/*
- * tools/testing/selftests/kvm/lib/x86.c
+ * tools/testing/selftests/kvm/lib/x86_64/vmx.c
*
* Copyright (C) 2018, Google LLC.
*
@@ -10,9 +10,11 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#include "vmx.h"
+bool enable_evmcs;
+
/* Allocate memory regions for nested VMX tests.
*
* Input Args:
@@ -62,6 +64,20 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
memset(vmx->vmwrite_hva, 0, getpagesize());
+ /* Setup of a region of guest memory for the VP Assist page. */
+ vmx->vp_assist = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist);
+ vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist);
+
+ /* Setup of a region of guest memory for the enlightened VMCS. */
+ vmx->enlightened_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->enlightened_vmcs_hva =
+ addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs);
+ vmx->enlightened_vmcs_gpa =
+ addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs);
+
*p_vmx_gva = vmx_gva;
return vmx;
}
@@ -107,18 +123,31 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx)
if (vmxon(vmx->vmxon_gpa))
return false;
- /* Load a VMCS. */
- *(uint32_t *)(vmx->vmcs) = vmcs_revision();
- if (vmclear(vmx->vmcs_gpa))
- return false;
-
- if (vmptrld(vmx->vmcs_gpa))
- return false;
+ return true;
+}
- /* Setup shadow VMCS, do not load it yet. */
- *(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
- if (vmclear(vmx->shadow_vmcs_gpa))
- return false;
+bool load_vmcs(struct vmx_pages *vmx)
+{
+ if (!enable_evmcs) {
+ /* Load a VMCS. */
+ *(uint32_t *)(vmx->vmcs) = vmcs_revision();
+ if (vmclear(vmx->vmcs_gpa))
+ return false;
+
+ if (vmptrld(vmx->vmcs_gpa))
+ return false;
+
+ /* Setup shadow VMCS, do not load it yet. */
+ *(uint32_t *)(vmx->shadow_vmcs) =
+ vmcs_revision() | 0x80000000ul;
+ if (vmclear(vmx->shadow_vmcs_gpa))
+ return false;
+ } else {
+ if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
+ vmx->enlightened_vmcs))
+ return false;
+ current_evmcs->revision_id = vmcs_revision();
+ }
return true;
}
diff --git a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index 11ec358bf969..d503a51fad30 100644
--- a/tools/testing/selftests/kvm/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -17,7 +17,7 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#define X86_FEATURE_XSAVE (1<<26)
#define X86_FEATURE_OSXSAVE (1<<27)
@@ -67,6 +67,7 @@ int main(int argc, char *argv[])
struct kvm_vm *vm;
struct kvm_sregs sregs;
struct kvm_cpuid_entry2 *entry;
+ struct ucall uc;
int rc;
entry = kvm_get_supported_cpuid_entry(1);
@@ -87,21 +88,20 @@ int main(int argc, char *argv[])
rc = _vcpu_run(vm, VCPU_ID);
if (run->exit_reason == KVM_EXIT_IO) {
- switch (run->io.port) {
- case GUEST_PORT_SYNC:
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_SYNC:
/* emulate hypervisor clearing CR4.OSXSAVE */
vcpu_sregs_get(vm, VCPU_ID, &sregs);
sregs.cr4 &= ~X86_CR4_OSXSAVE;
vcpu_sregs_set(vm, VCPU_ID, &sregs);
break;
- case GUEST_PORT_ABORT:
+ case UCALL_ABORT:
TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
break;
- case GUEST_PORT_DONE:
+ case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false, "Unknown port 0x%x.",
- run->io.port);
+ TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
}
}
}
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
new file mode 100644
index 000000000000..92c2cfd1b182
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for Enlightened VMCS, including nested guest state.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+
+#include "vmx.h"
+
+#define VCPU_ID 5
+
+static bool have_nested_state;
+
+void l2_guest_code(void)
+{
+ GUEST_SYNC(6);
+
+ GUEST_SYNC(7);
+
+ /* Done, exit to L1 and never come back. */
+ vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+ enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist);
+
+ GUEST_ASSERT(vmx_pages->vmcs_gpa);
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_SYNC(3);
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+ GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+
+ GUEST_SYNC(4);
+ GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ GUEST_SYNC(5);
+ GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ GUEST_SYNC(8);
+ GUEST_ASSERT(!vmresume());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+ GUEST_SYNC(9);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+ GUEST_SYNC(1);
+ GUEST_SYNC(2);
+
+ if (vmx_pages)
+ l1_guest_code(vmx_pages);
+
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ struct vmx_pages *vmx_pages = NULL;
+ vm_vaddr_t vmx_pages_gva = 0;
+
+ struct kvm_regs regs1, regs2;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_x86_state *state;
+ struct ucall uc;
+ int stage;
+ uint16_t evmcs_ver;
+ struct kvm_enable_cap enable_evmcs_cap = {
+ .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+ .args[0] = (unsigned long)&evmcs_ver
+ };
+
+ struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+ if (!kvm_check_cap(KVM_CAP_NESTED_STATE) ||
+ !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+ printf("capabilities not available, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+
+ vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+
+ for (stage = 1;; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ memset(&regs1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ break;
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+ }
+
+ /* UCALL_SYNC is handled here. */
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+ stage, (ulong)uc.args[1]);
+
+ state = vcpu_save_state(vm, VCPU_ID);
+ kvm_vm_release(vm);
+
+ /* Restore state in a new VM. */
+ kvm_vm_restart(vm, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID, 0, 0);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vcpu_load_state(vm, VCPU_ID, state);
+ run = vcpu_state(vm, VCPU_ID);
+ free(state);
+
+ memset(&regs2, 0, sizeof(regs2));
+ vcpu_regs_get(vm, VCPU_ID, &regs2);
+ TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+ "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+ (ulong) regs2.rdi, (ulong) regs2.rsi);
+ }
+
+done:
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index 3764e7121265..eb3e7a838cb4 100644
--- a/tools/testing/selftests/kvm/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -19,7 +19,7 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#define VCPU_ID 0
#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00
@@ -48,7 +48,7 @@ static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable)
static void test_msr_platform_info_enabled(struct kvm_vm *vm)
{
struct kvm_run *run = vcpu_state(vm, VCPU_ID);
- struct guest_args args;
+ struct ucall uc;
set_msr_platform_info_enabled(vm, true);
vcpu_run(vm, VCPU_ID);
@@ -56,11 +56,11 @@ static void test_msr_platform_info_enabled(struct kvm_vm *vm)
"Exit_reason other than KVM_EXIT_IO: %u (%s),\n",
run->exit_reason,
exit_reason_str(run->exit_reason));
- guest_args_read(vm, VCPU_ID, &args);
- TEST_ASSERT(args.port == GUEST_PORT_SYNC,
- "Received IO from port other than PORT_HOST_SYNC: %u\n",
- run->io.port);
- TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
+ get_ucall(vm, VCPU_ID, &uc);
+ TEST_ASSERT(uc.cmd == UCALL_SYNC,
+ "Received ucall other than UCALL_SYNC: %u\n",
+ ucall);
+ TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) ==
MSR_PLATFORM_INFO_MAX_TURBO_RATIO,
"Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.",
MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
diff --git a/tools/testing/selftests/kvm/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
index 881419d5746e..35640e8e95bc 100644
--- a/tools/testing/selftests/kvm/set_sregs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
@@ -22,7 +22,7 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#define VCPU_ID 5
diff --git a/tools/testing/selftests/kvm/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 900e3e9dfb9f..03da41f0f736 100644
--- a/tools/testing/selftests/kvm/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -17,7 +17,7 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#include "vmx.h"
#define VCPU_ID 5
@@ -26,20 +26,20 @@ static bool have_nested_state;
void l2_guest_code(void)
{
- GUEST_SYNC(5);
+ GUEST_SYNC(6);
/* Exit to L1 */
vmcall();
/* L1 has now set up a shadow VMCS for us. */
GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
- GUEST_SYNC(9);
+ GUEST_SYNC(10);
GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0fffee));
- GUEST_SYNC(10);
+ GUEST_SYNC(11);
GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0fffee);
GUEST_ASSERT(!vmwrite(GUEST_RIP, 0xc0ffffee));
- GUEST_SYNC(11);
+ GUEST_SYNC(12);
/* Done, exit to L1 and never come back. */
vmcall();
@@ -52,15 +52,17 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_ASSERT(vmx_pages->vmcs_gpa);
GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_SYNC(3);
+ GUEST_ASSERT(load_vmcs(vmx_pages));
GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
- GUEST_SYNC(3);
+ GUEST_SYNC(4);
GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
prepare_vmcs(vmx_pages, l2_guest_code,
&l2_guest_stack[L2_GUEST_STACK_SIZE]);
- GUEST_SYNC(4);
+ GUEST_SYNC(5);
GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
GUEST_ASSERT(!vmlaunch());
GUEST_ASSERT(vmptrstz() == vmx_pages->vmcs_gpa);
@@ -72,7 +74,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_ASSERT(!vmresume());
GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
- GUEST_SYNC(6);
+ GUEST_SYNC(7);
GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
GUEST_ASSERT(!vmresume());
@@ -85,12 +87,12 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_ASSERT(!vmptrld(vmx_pages->shadow_vmcs_gpa));
GUEST_ASSERT(vmlaunch());
- GUEST_SYNC(7);
+ GUEST_SYNC(8);
GUEST_ASSERT(vmlaunch());
GUEST_ASSERT(vmresume());
vmwrite(GUEST_RIP, 0xc0ffee);
- GUEST_SYNC(8);
+ GUEST_SYNC(9);
GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffee);
GUEST_ASSERT(!vmptrld(vmx_pages->vmcs_gpa));
@@ -101,7 +103,7 @@ void l1_guest_code(struct vmx_pages *vmx_pages)
GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
GUEST_ASSERT(vmlaunch());
GUEST_ASSERT(vmresume());
- GUEST_SYNC(12);
+ GUEST_SYNC(13);
GUEST_ASSERT(vmreadz(GUEST_RIP) == 0xc0ffffee);
GUEST_ASSERT(vmlaunch());
GUEST_ASSERT(vmresume());
@@ -127,6 +129,7 @@ int main(int argc, char *argv[])
struct kvm_vm *vm;
struct kvm_run *run;
struct kvm_x86_state *state;
+ struct ucall uc;
int stage;
struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
@@ -155,23 +158,23 @@ int main(int argc, char *argv[])
memset(&regs1, 0, sizeof(regs1));
vcpu_regs_get(vm, VCPU_ID, &regs1);
- switch (run->io.port) {
- case GUEST_PORT_ABORT:
- TEST_ASSERT(false, "%s at %s:%d", (const char *) regs1.rdi,
- __FILE__, regs1.rsi);
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
/* NOT REACHED */
- case GUEST_PORT_SYNC:
+ case UCALL_SYNC:
break;
- case GUEST_PORT_DONE:
+ case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+ TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
}
- /* PORT_SYNC is handled here. */
- TEST_ASSERT(!strcmp((const char *)regs1.rdi, "hello") &&
- regs1.rsi == stage, "Unexpected register values vmexit #%lx, got %lx",
- stage, (ulong) regs1.rsi);
+ /* UCALL_SYNC is handled here. */
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage, "Unexpected register values vmexit #%lx, got %lx",
+ stage, (ulong)uc.args[1]);
state = vcpu_save_state(vm, VCPU_ID);
kvm_vm_release(vm);
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 213343e5dff9..c8478ce9ea77 100644
--- a/tools/testing/selftests/kvm/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -19,7 +19,7 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#define VCPU_ID 5
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 49bcc68b0235..18fa64db0d7a 100644
--- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -1,5 +1,5 @@
/*
- * gtests/tests/vmx_tsc_adjust_test.c
+ * vmx_tsc_adjust_test
*
* Copyright (C) 2018, Google LLC.
*
@@ -22,13 +22,13 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "x86.h"
+#include "processor.h"
#include "vmx.h"
#include <string.h>
#include <sys/ioctl.h>
-#include "../kselftest.h"
+#include "kselftest.h"
#ifndef MSR_IA32_TSC_ADJUST
#define MSR_IA32_TSC_ADJUST 0x3b
@@ -94,6 +94,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
/* Prepare the VMCS for L2 execution. */
prepare_vmcs(vmx_pages, l2_guest_code,
@@ -146,26 +147,25 @@ int main(int argc, char *argv[])
for (;;) {
volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
- struct guest_args args;
+ struct ucall uc;
vcpu_run(vm, VCPU_ID);
- guest_args_read(vm, VCPU_ID, &args);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
"Got exit_reason other than KVM_EXIT_IO: %u (%s)\n",
run->exit_reason,
exit_reason_str(run->exit_reason));
- switch (args.port) {
- case GUEST_PORT_ABORT:
- TEST_ASSERT(false, "%s", (const char *) args.arg0);
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s", (const char *)uc.args[0]);
/* NOT REACHED */
- case GUEST_PORT_SYNC:
- report(args.arg1);
+ case UCALL_SYNC:
+ report(uc.args[1]);
break;
- case GUEST_PORT_DONE:
+ case UCALL_DONE:
goto done;
default:
- TEST_ASSERT(false, "Unknown port 0x%x.", args.port);
+ TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
}
}
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index c92053bc3f96..11b98b2b0486 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -120,8 +120,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int ret, cpu;
- if (type)
- return -EINVAL;
+ ret = kvm_arm_setup_stage2(kvm, type);
+ if (ret)
+ return ret;
kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran));
if (!kvm->arch.last_vcpu_ran)
@@ -212,6 +213,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_READONLY_MEM:
case KVM_CAP_MP_STATE:
case KVM_CAP_IMMEDIATE_EXIT:
+ case KVM_CAP_VCPU_EVENTS:
r = 1;
break;
case KVM_CAP_ARM_SET_DEVICE_ADDR:
@@ -240,7 +242,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = 1;
break;
default:
- r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
+ r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
break;
}
return r;
@@ -544,7 +546,7 @@ static void update_vttbr(struct kvm *kvm)
/* update vttbr to be used with the new vmid */
pgd_phys = virt_to_phys(kvm->arch.pgd);
- BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
+ BUG_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm));
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid;
@@ -1295,8 +1297,6 @@ static void cpu_init_hyp_mode(void *dummy)
__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
__cpu_init_stage2();
-
- kvm_arm_init_debug();
}
static void cpu_hyp_reset(void)
@@ -1309,16 +1309,12 @@ static void cpu_hyp_reinit(void)
{
cpu_hyp_reset();
- if (is_kernel_in_hyp_mode()) {
- /*
- * __cpu_init_stage2() is safe to call even if the PM
- * event was cancelled before the CPU was reset.
- */
- __cpu_init_stage2();
+ if (is_kernel_in_hyp_mode())
kvm_timer_init_vhe();
- } else {
+ else
cpu_init_hyp_mode(NULL);
- }
+
+ kvm_arm_init_debug();
if (vgic_present)
kvm_vgic_init_cpu_hardware();
@@ -1412,6 +1408,8 @@ static int init_common_resources(void)
kvm_vmid_bits = kvm_get_vmid_bits();
kvm_info("%d-bit VMID\n", kvm_vmid_bits);
+ kvm_set_ipa_limit();
+
return 0;
}
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index ed162a6c57c5..c23a1b323aad 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -45,7 +45,6 @@ static phys_addr_t hyp_idmap_vector;
static unsigned long io_map_base;
-#define S2_PGD_SIZE (PTRS_PER_S2_PGD * sizeof(pgd_t))
#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0)
@@ -150,20 +149,20 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
{
- pud_t *pud_table __maybe_unused = stage2_pud_offset(pgd, 0UL);
- stage2_pgd_clear(pgd);
+ pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, pgd, 0UL);
+ stage2_pgd_clear(kvm, pgd);
kvm_tlb_flush_vmid_ipa(kvm, addr);
- stage2_pud_free(pud_table);
+ stage2_pud_free(kvm, pud_table);
put_page(virt_to_page(pgd));
}
static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
{
- pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(pud, 0);
- VM_BUG_ON(stage2_pud_huge(*pud));
- stage2_pud_clear(pud);
+ pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0);
+ VM_BUG_ON(stage2_pud_huge(kvm, *pud));
+ stage2_pud_clear(kvm, pud);
kvm_tlb_flush_vmid_ipa(kvm, addr);
- stage2_pmd_free(pmd_table);
+ stage2_pmd_free(kvm, pmd_table);
put_page(virt_to_page(pud));
}
@@ -252,7 +251,7 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd,
}
} while (pte++, addr += PAGE_SIZE, addr != end);
- if (stage2_pte_table_empty(start_pte))
+ if (stage2_pte_table_empty(kvm, start_pte))
clear_stage2_pmd_entry(kvm, pmd, start_addr);
}
@@ -262,9 +261,9 @@ static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
phys_addr_t next, start_addr = addr;
pmd_t *pmd, *start_pmd;
- start_pmd = pmd = stage2_pmd_offset(pud, addr);
+ start_pmd = pmd = stage2_pmd_offset(kvm, pud, addr);
do {
- next = stage2_pmd_addr_end(addr, end);
+ next = stage2_pmd_addr_end(kvm, addr, end);
if (!pmd_none(*pmd)) {
if (pmd_thp_or_huge(*pmd)) {
pmd_t old_pmd = *pmd;
@@ -281,7 +280,7 @@ static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud,
}
} while (pmd++, addr = next, addr != end);
- if (stage2_pmd_table_empty(start_pmd))
+ if (stage2_pmd_table_empty(kvm, start_pmd))
clear_stage2_pud_entry(kvm, pud, start_addr);
}
@@ -291,14 +290,14 @@ static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd,
phys_addr_t next, start_addr = addr;
pud_t *pud, *start_pud;
- start_pud = pud = stage2_pud_offset(pgd, addr);
+ start_pud = pud = stage2_pud_offset(kvm, pgd, addr);
do {
- next = stage2_pud_addr_end(addr, end);
- if (!stage2_pud_none(*pud)) {
- if (stage2_pud_huge(*pud)) {
+ next = stage2_pud_addr_end(kvm, addr, end);
+ if (!stage2_pud_none(kvm, *pud)) {
+ if (stage2_pud_huge(kvm, *pud)) {
pud_t old_pud = *pud;
- stage2_pud_clear(pud);
+ stage2_pud_clear(kvm, pud);
kvm_tlb_flush_vmid_ipa(kvm, addr);
kvm_flush_dcache_pud(old_pud);
put_page(virt_to_page(pud));
@@ -308,7 +307,7 @@ static void unmap_stage2_puds(struct kvm *kvm, pgd_t *pgd,
}
} while (pud++, addr = next, addr != end);
- if (stage2_pud_table_empty(start_pud))
+ if (stage2_pud_table_empty(kvm, start_pud))
clear_stage2_pgd_entry(kvm, pgd, start_addr);
}
@@ -332,7 +331,7 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
assert_spin_locked(&kvm->mmu_lock);
WARN_ON(size & ~PAGE_MASK);
- pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+ pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
do {
/*
* Make sure the page table is still active, as another thread
@@ -341,8 +340,8 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
*/
if (!READ_ONCE(kvm->arch.pgd))
break;
- next = stage2_pgd_addr_end(addr, end);
- if (!stage2_pgd_none(*pgd))
+ next = stage2_pgd_addr_end(kvm, addr, end);
+ if (!stage2_pgd_none(kvm, *pgd))
unmap_stage2_puds(kvm, pgd, addr, next);
/*
* If the range is too large, release the kvm->mmu_lock
@@ -371,9 +370,9 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
pmd_t *pmd;
phys_addr_t next;
- pmd = stage2_pmd_offset(pud, addr);
+ pmd = stage2_pmd_offset(kvm, pud, addr);
do {
- next = stage2_pmd_addr_end(addr, end);
+ next = stage2_pmd_addr_end(kvm, addr, end);
if (!pmd_none(*pmd)) {
if (pmd_thp_or_huge(*pmd))
kvm_flush_dcache_pmd(*pmd);
@@ -389,11 +388,11 @@ static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
pud_t *pud;
phys_addr_t next;
- pud = stage2_pud_offset(pgd, addr);
+ pud = stage2_pud_offset(kvm, pgd, addr);
do {
- next = stage2_pud_addr_end(addr, end);
- if (!stage2_pud_none(*pud)) {
- if (stage2_pud_huge(*pud))
+ next = stage2_pud_addr_end(kvm, addr, end);
+ if (!stage2_pud_none(kvm, *pud)) {
+ if (stage2_pud_huge(kvm, *pud))
kvm_flush_dcache_pud(*pud);
else
stage2_flush_pmds(kvm, pud, addr, next);
@@ -409,10 +408,11 @@ static void stage2_flush_memslot(struct kvm *kvm,
phys_addr_t next;
pgd_t *pgd;
- pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+ pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
do {
- next = stage2_pgd_addr_end(addr, end);
- stage2_flush_puds(kvm, pgd, addr, next);
+ next = stage2_pgd_addr_end(kvm, addr, end);
+ if (!stage2_pgd_none(kvm, *pgd))
+ stage2_flush_puds(kvm, pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
@@ -897,7 +897,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
}
/* Allocate the HW PGD, making sure that each page gets its own refcount */
- pgd = alloc_pages_exact(S2_PGD_SIZE, GFP_KERNEL | __GFP_ZERO);
+ pgd = alloc_pages_exact(stage2_pgd_size(kvm), GFP_KERNEL | __GFP_ZERO);
if (!pgd)
return -ENOMEM;
@@ -986,7 +986,7 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
spin_lock(&kvm->mmu_lock);
if (kvm->arch.pgd) {
- unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+ unmap_stage2_range(kvm, 0, kvm_phys_size(kvm));
pgd = READ_ONCE(kvm->arch.pgd);
kvm->arch.pgd = NULL;
}
@@ -994,7 +994,7 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
/* Free the HW pgd, one page at a time */
if (pgd)
- free_pages_exact(pgd, S2_PGD_SIZE);
+ free_pages_exact(pgd, stage2_pgd_size(kvm));
}
static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -1003,16 +1003,16 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
pgd_t *pgd;
pud_t *pud;
- pgd = kvm->arch.pgd + stage2_pgd_index(addr);
- if (WARN_ON(stage2_pgd_none(*pgd))) {
+ pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+ if (stage2_pgd_none(kvm, *pgd)) {
if (!cache)
return NULL;
pud = mmu_memory_cache_alloc(cache);
- stage2_pgd_populate(pgd, pud);
+ stage2_pgd_populate(kvm, pgd, pud);
get_page(virt_to_page(pgd));
}
- return stage2_pud_offset(pgd, addr);
+ return stage2_pud_offset(kvm, pgd, addr);
}
static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -1025,15 +1025,15 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache
if (!pud)
return NULL;
- if (stage2_pud_none(*pud)) {
+ if (stage2_pud_none(kvm, *pud)) {
if (!cache)
return NULL;
pmd = mmu_memory_cache_alloc(cache);
- stage2_pud_populate(pud, pmd);
+ stage2_pud_populate(kvm, pud, pmd);
get_page(virt_to_page(pud));
}
- return stage2_pmd_offset(pud, addr);
+ return stage2_pmd_offset(kvm, pud, addr);
}
static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
@@ -1207,8 +1207,9 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
if (writable)
pte = kvm_s2pte_mkwrite(pte);
- ret = mmu_topup_memory_cache(&cache, KVM_MMU_CACHE_MIN_PAGES,
- KVM_NR_MEM_OBJS);
+ ret = mmu_topup_memory_cache(&cache,
+ kvm_mmu_cache_min_pages(kvm),
+ KVM_NR_MEM_OBJS);
if (ret)
goto out;
spin_lock(&kvm->mmu_lock);
@@ -1230,8 +1231,14 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
{
kvm_pfn_t pfn = *pfnp;
gfn_t gfn = *ipap >> PAGE_SHIFT;
+ struct page *page = pfn_to_page(pfn);
- if (PageTransCompoundMap(pfn_to_page(pfn))) {
+ /*
+ * PageTransCompoungMap() returns true for THP and
+ * hugetlbfs. Make sure the adjustment is done only for THP
+ * pages.
+ */
+ if (!PageHuge(page) && PageTransCompoundMap(page)) {
unsigned long mask;
/*
* The address we faulted on is backed by a transparent huge
@@ -1296,19 +1303,21 @@ static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end)
/**
* stage2_wp_pmds - write protect PUD range
+ * kvm: kvm instance for the VM
* @pud: pointer to pud entry
* @addr: range start address
* @end: range end address
*/
-static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
+static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
+ phys_addr_t addr, phys_addr_t end)
{
pmd_t *pmd;
phys_addr_t next;
- pmd = stage2_pmd_offset(pud, addr);
+ pmd = stage2_pmd_offset(kvm, pud, addr);
do {
- next = stage2_pmd_addr_end(addr, end);
+ next = stage2_pmd_addr_end(kvm, addr, end);
if (!pmd_none(*pmd)) {
if (pmd_thp_or_huge(*pmd)) {
if (!kvm_s2pmd_readonly(pmd))
@@ -1328,18 +1337,19 @@ static void stage2_wp_pmds(pud_t *pud, phys_addr_t addr, phys_addr_t end)
*
* Process PUD entries, for a huge PUD we cause a panic.
*/
-static void stage2_wp_puds(pgd_t *pgd, phys_addr_t addr, phys_addr_t end)
+static void stage2_wp_puds(struct kvm *kvm, pgd_t *pgd,
+ phys_addr_t addr, phys_addr_t end)
{
pud_t *pud;
phys_addr_t next;
- pud = stage2_pud_offset(pgd, addr);
+ pud = stage2_pud_offset(kvm, pgd, addr);
do {
- next = stage2_pud_addr_end(addr, end);
- if (!stage2_pud_none(*pud)) {
+ next = stage2_pud_addr_end(kvm, addr, end);
+ if (!stage2_pud_none(kvm, *pud)) {
/* TODO:PUD not supported, revisit later if supported */
- BUG_ON(stage2_pud_huge(*pud));
- stage2_wp_pmds(pud, addr, next);
+ BUG_ON(stage2_pud_huge(kvm, *pud));
+ stage2_wp_pmds(kvm, pud, addr, next);
}
} while (pud++, addr = next, addr != end);
}
@@ -1355,7 +1365,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
pgd_t *pgd;
phys_addr_t next;
- pgd = kvm->arch.pgd + stage2_pgd_index(addr);
+ pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
do {
/*
* Release kvm_mmu_lock periodically if the memory region is
@@ -1369,9 +1379,9 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
cond_resched_lock(&kvm->mmu_lock);
if (!READ_ONCE(kvm->arch.pgd))
break;
- next = stage2_pgd_addr_end(addr, end);
- if (stage2_pgd_present(*pgd))
- stage2_wp_puds(pgd, addr, next);
+ next = stage2_pgd_addr_end(kvm, addr, end);
+ if (stage2_pgd_present(kvm, *pgd))
+ stage2_wp_puds(kvm, pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
@@ -1520,7 +1530,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
up_read(&current->mm->mmap_sem);
/* We need minimum second+third level pages */
- ret = mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES,
+ ret = mmu_topup_memory_cache(memcache, kvm_mmu_cache_min_pages(kvm),
KVM_NR_MEM_OBJS);
if (ret)
return ret;
@@ -1763,7 +1773,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
}
/* Userspace should not be able to register out-of-bounds IPAs */
- VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE);
+ VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
if (fault_status == FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
@@ -2062,7 +2072,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
* space addressable by the KVM guest IPA space.
*/
if (memslot->base_gfn + memslot->npages >=
- (KVM_PHYS_SIZE >> PAGE_SHIFT))
+ (kvm_phys_size(kvm) >> PAGE_SHIFT))
return -EFAULT;
down_read(&current->mm->mmap_sem);
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 12502251727e..eb2a390a6c86 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -241,13 +241,6 @@ static struct its_ite *find_ite(struct vgic_its *its, u32 device_id,
list_for_each_entry(dev, &(its)->device_list, dev_list) \
list_for_each_entry(ite, &(dev)->itt_head, ite_list)
-/*
- * We only implement 48 bits of PA at the moment, although the ITS
- * supports more. Let's be restrictive here.
- */
-#define BASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 16))
-#define CBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 12))
-
#define GIC_LPI_OFFSET 8192
#define VITS_TYPER_IDBITS 16
@@ -759,6 +752,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
{
int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
+ phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser);
int esz = GITS_BASER_ENTRY_SIZE(baser);
int index;
gfn_t gfn;
@@ -783,7 +777,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
if (id >= (l1_tbl_size / esz))
return false;
- addr = BASER_ADDRESS(baser) + id * esz;
+ addr = base + id * esz;
gfn = addr >> PAGE_SHIFT;
if (eaddr)
@@ -798,7 +792,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
/* Each 1st level entry is represented by a 64-bit value. */
if (kvm_read_guest_lock(its->dev->kvm,
- BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
+ base + index * sizeof(indirect_ptr),
&indirect_ptr, sizeof(indirect_ptr)))
return false;
@@ -808,11 +802,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
if (!(indirect_ptr & BIT_ULL(63)))
return false;
- /*
- * Mask the guest physical address and calculate the frame number.
- * Any address beyond our supported 48 bits of PA will be caught
- * by the actual check in the final step.
- */
+ /* Mask the guest physical address and calculate the frame number. */
indirect_ptr &= GENMASK_ULL(51, 16);
/* Find the address of the actual entry */
@@ -1304,9 +1294,6 @@ static u64 vgic_sanitise_its_baser(u64 reg)
GITS_BASER_OUTER_CACHEABILITY_SHIFT,
vgic_sanitise_outer_cacheability);
- /* Bits 15:12 contain bits 51:48 of the PA, which we don't support. */
- reg &= ~GENMASK_ULL(15, 12);
-
/* We support only one (ITS) page size: 64K */
reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K;
@@ -1325,11 +1312,8 @@ static u64 vgic_sanitise_its_cbaser(u64 reg)
GITS_CBASER_OUTER_CACHEABILITY_SHIFT,
vgic_sanitise_outer_cacheability);
- /*
- * Sanitise the physical address to be 64k aligned.
- * Also limit the physical addresses to 48 bits.
- */
- reg &= ~(GENMASK_ULL(51, 48) | GENMASK_ULL(15, 12));
+ /* Sanitise the physical address to be 64k aligned. */
+ reg &= ~GENMASK_ULL(15, 12);
return reg;
}
@@ -1375,7 +1359,7 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
if (!its->enabled)
return;
- cbaser = CBASER_ADDRESS(its->cbaser);
+ cbaser = GITS_CBASER_ADDRESS(its->cbaser);
while (its->cwriter != its->creadr) {
int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr,
@@ -2233,7 +2217,7 @@ static int vgic_its_restore_device_tables(struct vgic_its *its)
if (!(baser & GITS_BASER_VALID))
return 0;
- l1_gpa = BASER_ADDRESS(baser);
+ l1_gpa = GITS_BASER_ADDR_48_to_52(baser);
if (baser & GITS_BASER_INDIRECT) {
l1_esz = GITS_LVL1_ENTRY_SIZE;
@@ -2305,7 +2289,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
{
const struct vgic_its_abi *abi = vgic_its_get_abi(its);
u64 baser = its->baser_coll_table;
- gpa_t gpa = BASER_ADDRESS(baser);
+ gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser);
struct its_collection *collection;
u64 val;
size_t max_size, filled = 0;
@@ -2354,7 +2338,7 @@ static int vgic_its_restore_collection_table(struct vgic_its *its)
if (!(baser & GITS_BASER_VALID))
return 0;
- gpa = BASER_ADDRESS(baser);
+ gpa = GITS_BASER_ADDR_48_to_52(baser);
max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
index 6ada2432e37c..114dce9f4bf5 100644
--- a/virt/kvm/arm/vgic/vgic-kvm-device.c
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -25,7 +25,7 @@
int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
phys_addr_t addr, phys_addr_t alignment)
{
- if (addr & ~KVM_PHYS_MASK)
+ if (addr & ~kvm_phys_mask(kvm))
return -E2BIG;
if (!IS_ALIGNED(addr, alignment))
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index a2a175b08b17..b3d1f0985117 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -364,7 +364,6 @@ static u64 vgic_sanitise_pendbaser(u64 reg)
vgic_sanitise_outer_cacheability);
reg &= ~PENDBASER_RES0_MASK;
- reg &= ~GENMASK_ULL(51, 48);
return reg;
}
@@ -382,7 +381,6 @@ static u64 vgic_sanitise_propbaser(u64 reg)
vgic_sanitise_outer_cacheability);
reg &= ~PROPBASER_RES0_MASK;
- reg &= ~GENMASK_ULL(51, 48);
return reg;
}
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 9e65feb6fa58..3710342cf6ad 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -83,6 +83,7 @@ static int coalesced_mmio_write(struct kvm_vcpu *vcpu,
ring->coalesced_mmio[ring->last].phys_addr = addr;
ring->coalesced_mmio[ring->last].len = len;
memcpy(ring->coalesced_mmio[ring->last].data, val, len);
+ ring->coalesced_mmio[ring->last].pio = dev->zone.pio;
smp_wmb();
ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
spin_unlock(&dev->kvm->ring_lock);
@@ -140,6 +141,9 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
int ret;
struct kvm_coalesced_mmio_dev *dev;
+ if (zone->pio != 1 && zone->pio != 0)
+ return -EINVAL;
+
dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
if (!dev)
return -ENOMEM;
@@ -149,8 +153,9 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
dev->zone = *zone;
mutex_lock(&kvm->slots_lock);
- ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, zone->addr,
- zone->size, &dev->dev);
+ ret = kvm_io_bus_register_dev(kvm,
+ zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS,
+ zone->addr, zone->size, &dev->dev);
if (ret < 0)
goto out_free_dev;
list_add_tail(&dev->list, &kvm->coalesced_zones);
@@ -174,7 +179,8 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list)
if (coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &dev->dev);
+ kvm_io_bus_unregister_dev(kvm,
+ zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
kvm_iodevice_destructor(&dev->dev);
}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f986e31fa68c..786ade1843a2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -219,7 +219,7 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
me = get_cpu();
kvm_for_each_vcpu(i, vcpu, kvm) {
- if (!test_bit(i, vcpu_bitmap))
+ if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
continue;
kvm_make_request(req, vcpu);
@@ -243,12 +243,10 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
cpumask_var_t cpus;
bool called;
- static unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]
- = {[0 ... BITS_TO_LONGS(KVM_MAX_VCPUS)-1] = ULONG_MAX};
zalloc_cpumask_var(&cpus, GFP_ATOMIC);
- called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap, cpus);
+ called = kvm_make_vcpus_request_mask(kvm, req, NULL, cpus);
free_cpumask_var(cpus);
return called;
@@ -807,20 +805,25 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
* sorted array and known changed memslot position.
*/
static void update_memslots(struct kvm_memslots *slots,
- struct kvm_memory_slot *new)
+ struct kvm_memory_slot *new,
+ enum kvm_mr_change change)
{
int id = new->id;
int i = slots->id_to_index[id];
struct kvm_memory_slot *mslots = slots->memslots;
WARN_ON(mslots[i].id != id);
- if (!new->npages) {
- WARN_ON(!mslots[i].npages);
- if (mslots[i].npages)
- slots->used_slots--;
- } else {
- if (!mslots[i].npages)
- slots->used_slots++;
+ switch (change) {
+ case KVM_MR_CREATE:
+ slots->used_slots++;
+ WARN_ON(mslots[i].npages || !new->npages);
+ break;
+ case KVM_MR_DELETE:
+ slots->used_slots--;
+ WARN_ON(new->npages || !mslots[i].npages);
+ break;
+ default:
+ break;
}
while (i < KVM_MEM_SLOTS_NUM - 1 &&
@@ -1056,7 +1059,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
memset(&new.arch, 0, sizeof(new.arch));
}
- update_memslots(slots, &new);
+ update_memslots(slots, &new, change);
old_memslots = install_new_memslots(kvm, as_id, slots);
kvm_arch_commit_memory_region(kvm, mem, &old, &new, change);
@@ -1311,8 +1314,12 @@ unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn)
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva);
/*
- * If writable is set to false, the hva returned by this function is only
- * allowed to be read.
+ * Return the hva of a @gfn and the R/W attribute if possible.
+ *
+ * @slot: the kvm_memory_slot which contains @gfn
+ * @gfn: the gfn to be translated
+ * @writable: used to return the read/write attribute of the @slot if the hva
+ * is valid and @writable is not NULL
*/
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
gfn_t gfn, bool *writable)
@@ -2946,6 +2953,8 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
#ifdef CONFIG_KVM_MMIO
case KVM_CAP_COALESCED_MMIO:
return KVM_COALESCED_MMIO_PAGE_OFFSET;
+ case KVM_CAP_COALESCED_PIO:
+ return 1;
#endif
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
case KVM_CAP_IRQ_ROUTING: