Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit e61cf2e3 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm 

Pull first set of KVM updates from Paolo Bonzini:
 "PPC:
   - minor code cleanups

  x86:
   - PCID emulation and CR3 caching for shadow page tables
   - nested VMX live migration
   - nested VMCS shadowing
   - optimized IPI hypercall
   - some optimizations

  ARM will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (85 commits)
  kvm: x86: Set highest physical address bits in non-present/reserved SPTEs
  KVM/x86: Use CC_SET()/CC_OUT in arch/x86/kvm/vmx.c
  KVM: X86: Implement PV IPIs in linux guest
  KVM: X86: Add kvm hypervisor init time platform setup callback
  KVM: X86: Implement "send IPI" hypercall
  KVM/x86: Move X86_CR4_OSXSAVE check into kvm_valid_sregs()
  KVM: x86: Skip pae_root shadow allocation if tdp enabled
  KVM/MMU: Combine flushing remote tlb in mmu_set_spte()
  KVM: vmx: skip VMWRITE of HOST_{FS,GS}_BASE when possible
  KVM: vmx: skip VMWRITE of HOST_{FS,GS}_SEL when possible
  KVM: vmx: always initialize HOST_{FS,GS}_BASE to zero during setup
  KVM: vmx: move struct host_state usage to struct loaded_vmcs
  KVM: vmx: compute need to reload FS/GS/LDT on demand
  KVM: nVMX: remove a misleading comment regarding vmcs02 fields
  KVM: vmx: rename __vmx_load_host_state() and vmx_save_host_state()
  KVM: vmx: add dedicated utility to access guest's kernel_gs_base
  KVM: vmx: track host_state.loaded using a loaded_vmcs pointer
  KVM: vmx: refactor segmentation code in vmx_save_host_state()
  kvm: nVMX: Fix fault priority for VMX operations
  kvm: nVMX: Fix fault vector for VMX operation at CPL > 0
  ...
parents 1009aa12 28a1f3ac

Documentation/virtual/kvm/api.txt

+56 −0
Original line number Original line Diff line number Diff line
@@ -3561,6 +3561,62 @@ Returns: 0 on success, 
	-ENOENT on deassign if the conn_id isn't registered

	-ENOENT on deassign if the conn_id isn't registered

	-EEXIST on assign if the conn_id is already registered

	-EEXIST on assign if the conn_id is already registered





4.114 KVM_GET_NESTED_STATE



Capability: KVM_CAP_NESTED_STATE

Architectures: x86

Type: vcpu ioctl

Parameters: struct kvm_nested_state (in/out)

Returns: 0 on success, -1 on error

Errors:

  E2BIG:     the total state size (including the fixed-size part of struct

             kvm_nested_state) exceeds the value of 'size' specified by

             the user; the size required will be written into size.



struct kvm_nested_state {

	__u16 flags;

	__u16 format;

	__u32 size;

	union {

		struct kvm_vmx_nested_state vmx;

		struct kvm_svm_nested_state svm;

		__u8 pad[120];

	};

	__u8 data[0];

};



#define KVM_STATE_NESTED_GUEST_MODE	0x00000001

#define KVM_STATE_NESTED_RUN_PENDING	0x00000002



#define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001

#define KVM_STATE_NESTED_SMM_VMXON	0x00000002



struct kvm_vmx_nested_state {

	__u64 vmxon_pa;

	__u64 vmcs_pa;



	struct {

		__u16 flags;

	} smm;

};



This ioctl copies the vcpu's nested virtualization state from the kernel to

userspace.



The maximum size of the state, including the fixed-size part of struct

kvm_nested_state, can be retrieved by passing KVM_CAP_NESTED_STATE to

the KVM_CHECK_EXTENSION ioctl().



4.115 KVM_SET_NESTED_STATE



Capability: KVM_CAP_NESTED_STATE

Architectures: x86

Type: vcpu ioctl

Parameters: struct kvm_nested_state (in)

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.





5. The kvm_run structure

5. The kvm_run structure

------------------------

------------------------

Documentation/virtual/kvm/cpuid.txt

+4 −0
Original line number Original line Diff line number Diff line
@@ -62,6 +62,10 @@ KVM_FEATURE_ASYNC_PF_VMEXIT || 10 || paravirtualized async PF VM exit 
                                   ||       || can be enabled by setting bit 2

                                   ||       || can be enabled by setting bit 2

                                   ||       || when writing to msr 0x4b564d02

                                   ||       || when writing to msr 0x4b564d02

------------------------------------------------------------------------------

------------------------------------------------------------------------------

KVM_FEATURE_PV_SEND_IPI            ||    11 || guest checks this feature bit

                                   ||       || before using paravirtualized

                                   ||       || send IPIs.

------------------------------------------------------------------------------

KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side

KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side

                                   ||       || per-cpu warps are expected in

                                   ||       || per-cpu warps are expected in

                                   ||       || kvmclock.

                                   ||       || kvmclock.

Documentation/virtual/kvm/hypercalls.txt

+20 −0
Original line number Original line Diff line number Diff line
@@ -121,3 +121,23 @@ compute the CLOCK_REALTIME for its clock, at the same instant. 




Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,

Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,

or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.

or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.



6. KVM_HC_SEND_IPI

------------------------

Architecture: x86

Status: active

Purpose: Send IPIs to multiple vCPUs.



a0: lower part of the bitmap of destination APIC IDs

a1: higher part of the bitmap of destination APIC IDs

a2: the lowest APIC ID in bitmap

a3: APIC ICR



The hypercall lets a guest send multicast IPIs, with at most 128

128 destinations per hypercall in 64-bit mode and 64 vCPUs per

hypercall in 32-bit mode.  The destinations are represented by a

bitmap contained in the first two arguments (a0 and a1). Bit 0 of

a0 corresponds to the APIC ID in the third argument (a2), bit 1

corresponds to the APIC ID a2+1, and so on.



Returns the number of CPUs to which the IPIs were delivered successfully.

arch/powerpc/include/asm/kvm_book3s.h

+47 −0
Original line number Original line Diff line number Diff line
@@ -390,4 +390,51 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); 
#define SPLIT_HACK_MASK			0xff000000

#define SPLIT_HACK_MASK			0xff000000

#define SPLIT_HACK_OFFS			0xfb000000

#define SPLIT_HACK_OFFS			0xfb000000





/*

 * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the

 * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride

 * (but not its actual threading mode, which is not available) to avoid

 * collisions.

 *

 * The implementation leaves VCPU IDs from the range [0..KVM_MAX_VCPUS) (block

 * 0) unchanged: if the guest is filling each VCORE completely then it will be

 * using consecutive IDs and it will fill the space without any packing.

 *

 * For higher VCPU IDs, the packed ID is based on the VCPU ID modulo

 * KVM_MAX_VCPUS (effectively masking off the top bits) and then an offset is

 * added to avoid collisions.

 *

 * VCPU IDs in the range [KVM_MAX_VCPUS..(KVM_MAX_VCPUS*2)) (block 1) are only

 * possible if the guest is leaving at least 1/2 of each VCORE empty, so IDs

 * can be safely packed into the second half of each VCORE by adding an offset

 * of (stride / 2).

 *

 * Similarly, if VCPU IDs in the range [(KVM_MAX_VCPUS*2)..(KVM_MAX_VCPUS*4))

 * (blocks 2 and 3) are seen, the guest must be leaving at least 3/4 of each

 * VCORE empty so packed IDs can be offset by (stride / 4) and (stride * 3 / 4).

 *

 * Finally, VCPU IDs from blocks 5..7 will only be seen if the guest is using a

 * stride of 8 and 1 thread per core so the remaining offsets of 1, 5, 3 and 7

 * must be free to use.

 *

 * (The offsets for each block are stored in block_offsets[], indexed by the

 * block number if the stride is 8. For cases where the guest's stride is less

 * than 8, we can re-use the block_offsets array by multiplying the block

 * number by (MAX_SMT_THREADS / stride) to reach the correct entry.)

 */

static inline u32 kvmppc_pack_vcpu_id(struct kvm *kvm, u32 id)

{

	const int block_offsets[MAX_SMT_THREADS] = {0, 4, 2, 6, 1, 5, 3, 7};

	int stride = kvm->arch.emul_smt_mode;

	int block = (id / KVM_MAX_VCPUS) * (MAX_SMT_THREADS / stride);

	u32 packed_id;



	if (WARN_ONCE(block >= MAX_SMT_THREADS, "VCPU ID too large to pack"))

		return 0;

	packed_id = (id % KVM_MAX_VCPUS) + block_offsets[block];

	if (WARN_ONCE(packed_id >= KVM_MAX_VCPUS, "VCPU ID packing failed"))

		return 0;

	return packed_id;

}



#endif /* __ASM_KVM_BOOK3S_H__ */
 
#endif /* __ASM_KVM_BOOK3S_H__ */

arch/powerpc/include/asm/kvm_host.h

+16 −10
Original line number Original line Diff line number Diff line
@@ -42,7 +42,14 @@ 
#define KVM_USER_MEM_SLOTS	512

#define KVM_USER_MEM_SLOTS	512





#include <asm/cputhreads.h>

#include <asm/cputhreads.h>

#define KVM_MAX_VCPU_ID                (threads_per_subcore * KVM_MAX_VCORES)



#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE

#include <asm/kvm_book3s_asm.h>		/* for MAX_SMT_THREADS */

#define KVM_MAX_VCPU_ID		(MAX_SMT_THREADS * KVM_MAX_VCORES)



#else

#define KVM_MAX_VCPU_ID		KVM_MAX_VCPUS

#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */





#define __KVM_HAVE_ARCH_INTC_INITIALIZED

#define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -672,7 +679,7 @@ struct kvm_vcpu_arch { 
	gva_t vaddr_accessed;

	gva_t vaddr_accessed;

	pgd_t *pgdir;

	pgd_t *pgdir;





	u8 io_gpr; /* GPR used as IO source/target */

	u16 io_gpr; /* GPR used as IO source/target */

	u8 mmio_host_swabbed;

	u8 mmio_host_swabbed;

	u8 mmio_sign_extend;

	u8 mmio_sign_extend;

	/* conversion between single and double precision */

	/* conversion between single and double precision */
@@ -688,7 +695,6 @@ struct kvm_vcpu_arch { 
	 */

	 */

	u8 mmio_vsx_copy_nums;

	u8 mmio_vsx_copy_nums;

	u8 mmio_vsx_offset;

	u8 mmio_vsx_offset;

	u8 mmio_vsx_tx_sx_enabled;

	u8 mmio_vmx_copy_nums;

	u8 mmio_vmx_copy_nums;

	u8 mmio_vmx_offset;

	u8 mmio_vmx_offset;

	u8 mmio_copy_type;

	u8 mmio_copy_type;
@@ -801,14 +807,14 @@ struct kvm_vcpu_arch { 
#define KVMPPC_VCPU_BUSY_IN_HOST	2

#define KVMPPC_VCPU_BUSY_IN_HOST	2





/* Values for vcpu->arch.io_gpr */

/* Values for vcpu->arch.io_gpr */

#define KVM_MMIO_REG_MASK	0x001f

#define KVM_MMIO_REG_MASK	0x003f

#define KVM_MMIO_REG_EXT_MASK	0xffe0

#define KVM_MMIO_REG_EXT_MASK	0xffc0

#define KVM_MMIO_REG_GPR	0x0000

#define KVM_MMIO_REG_GPR	0x0000

#define KVM_MMIO_REG_FPR	0x0020

#define KVM_MMIO_REG_FPR	0x0040

#define KVM_MMIO_REG_QPR	0x0040

#define KVM_MMIO_REG_QPR	0x0080

#define KVM_MMIO_REG_FQPR	0x0060

#define KVM_MMIO_REG_FQPR	0x00c0

#define KVM_MMIO_REG_VSX	0x0080

#define KVM_MMIO_REG_VSX	0x0100

#define KVM_MMIO_REG_VMX	0x00c0

#define KVM_MMIO_REG_VMX	0x0180





#define __KVM_HAVE_ARCH_WQP

#define __KVM_HAVE_ARCH_WQP

#define __KVM_HAVE_CREATE_DEVICE

#define __KVM_HAVE_CREATE_DEVICE