Commit f311d498 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 more kvm updates from Paolo Bonzini:
 "The main batch of ARM + RISC-V changes, and a few fixes and cleanups
  for x86 (PMU virtualization and selftests).

  ARM:

   - Fixes for single-stepping in the presence of an async exception as
     well as the preservation of PSTATE.SS

   - Better handling of AArch32 ID registers on AArch64-only systems

   - Fixes for the dirty-ring API, allowing it to work on architectures
     with relaxed memory ordering

   - Advertise the new kvmarm mailing list

   - Various minor cleanups and spelling fixes

  RISC-V:

   - Improved instruction encoding infrastructure for instructions not
     yet supported by binutils

   - Svinval support for both KVM Host and KVM Guest

   - Zihintpause support for KVM Guest

   - Zicbom support for KVM Guest

   - Record number of signal exits as a VCPU stat

   - Use generic guest entry infrastructure

  x86:

   - Misc PMU fixes and cleanups.

   - selftests: fixes for Hyper-V hypercall

   - selftests: fix nx_huge_pages_test on TDP-disabled hosts

   - selftests: cleanups for fix_hypercall_test"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (57 commits)
  riscv: select HAVE_POSIX_CPU_TIMERS_TASK_WORK
  RISC-V: KVM: Use generic guest entry infrastructure
  RISC-V: KVM: Record number of signal exits as a vCPU stat
  RISC-V: KVM: add __init annotation to riscv_kvm_init()
  RISC-V: KVM: Expose Zicbom to the guest
  RISC-V: KVM: Provide UAPI for Zicbom block size
  RISC-V: KVM: Make ISA ext mappings explicit
  RISC-V: KVM: Allow Guest use Zihintpause extension
  RISC-V: KVM: Allow Guest use Svinval extension
  RISC-V: KVM: Use Svinval for local TLB maintenance when available
  RISC-V: Probe Svinval extension form ISA string
  RISC-V: KVM: Change the SBI specification version to v1.0
  riscv: KVM: Apply insn-def to hlv encodings
  riscv: KVM: Apply insn-def to hfence encodings
  riscv: Introduce support for defining instructions
  riscv: Add X register names to gpr-nums
  KVM: arm64: Advertise new kvmarm mailing list
  kvm: vmx: keep constant definition format consistent
  kvm: mmu: fix typos in struct kvm_arch
  KVM: selftests: Fix nx_huge_pages_test on TDP-disabled hosts
  ...
parents d465bff1 e18d6152

Documentation/virt/kvm/api.rst

+15 −2
Original line number Diff line number Diff line
@@ -7918,8 +7918,8 @@ guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf 
(0x40000001). Otherwise, a guest may use the paravirtual features

regardless of what has actually been exposed through the CPUID leaf.



8.29 KVM_CAP_DIRTY_LOG_RING

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

8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL

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



:Architectures: x86

:Parameters: args[0] - size of the dirty log ring
@@ -7977,6 +7977,11 @@ on to the next GFN. The userspace should continue to do this until the 
flags of a GFN have the DIRTY bit cleared, meaning that it has harvested

all the dirty GFNs that were available.



Note that on weakly ordered architectures, userspace accesses to the

ring buffer (and more specifically the 'flags' field) must be ordered,

using load-acquire/store-release accessors when available, or any

other memory barrier that will ensure this ordering.



It's not necessary for userspace to harvest the all dirty GFNs at once.

However it must collect the dirty GFNs in sequence, i.e., the userspace

program cannot skip one dirty GFN to collect the one next to it.
@@ -8005,6 +8010,14 @@ KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual 
machine will switch to ring-buffer dirty page tracking and further

KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail.



NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that

should be exposed by weakly ordered architecture, in order to indicate

the additional memory ordering requirements imposed on userspace when

reading the state of an entry and mutating it from DIRTY to HARVESTED.

Architecture with TSO-like ordering (such as x86) are allowed to

expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL

to userspace.



8.30 KVM_CAP_XEN_HVM

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

MAINTAINERS

+2 −1
Original line number Diff line number Diff line
@@ -11204,7 +11204,8 @@ R: Alexandru Elisei <alexandru.elisei@arm.com> 
R:	Suzuki K Poulose <suzuki.poulose@arm.com>

R:	Oliver Upton <oliver.upton@linux.dev>

L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)

L:	kvmarm@lists.cs.columbia.edu (moderated for non-subscribers)

L:	kvmarm@lists.linux.dev

L:	kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)

S:	Maintained

T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git

F:	arch/arm64/include/asm/kvm*

arch/arm64/include/asm/kvm_host.h

+4 −0
Original line number Diff line number Diff line
@@ -393,6 +393,7 @@ struct kvm_vcpu_arch { 
	 */

	struct {

		u32	mdscr_el1;

		bool	pstate_ss;

	} guest_debug_preserved;



	/* vcpu power state */
@@ -535,6 +536,9 @@ struct kvm_vcpu_arch { 
#define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))

/* vcpu system registers loaded on physical CPU */

#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))

/* Software step state is Active-pending */

#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))





/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */

#define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) +	\

arch/arm64/kvm/arm.c

+10 −5
Original line number Diff line number Diff line
@@ -2269,6 +2269,16 @@ static int __init early_kvm_mode_cfg(char *arg) 
	if (!arg)

		return -EINVAL;



	if (strcmp(arg, "none") == 0) {

		kvm_mode = KVM_MODE_NONE;

		return 0;

	}



	if (!is_hyp_mode_available()) {

		pr_warn_once("KVM is not available. Ignoring kvm-arm.mode\n");

		return 0;

	}



	if (strcmp(arg, "protected") == 0) {

		if (!is_kernel_in_hyp_mode())

			kvm_mode = KVM_MODE_PROTECTED;
@@ -2283,11 +2293,6 @@ static int __init early_kvm_mode_cfg(char *arg) 
		return 0;

	}



	if (strcmp(arg, "none") == 0) {

		kvm_mode = KVM_MODE_NONE;

		return 0;

	}



	return -EINVAL;

}

early_param("kvm-arm.mode", early_kvm_mode_cfg);

arch/arm64/kvm/debug.c

+33 −1
Original line number Diff line number Diff line
@@ -32,6 +32,10 @@ static DEFINE_PER_CPU(u64, mdcr_el2); 
 *

 * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled

 * after we have restored the preserved value to the main context.

 *

 * When single-step is enabled by userspace, we tweak PSTATE.SS on every

 * guest entry. Preserve PSTATE.SS so we can restore the original value

 * for the vcpu after the single-step is disabled.

 */

static void save_guest_debug_regs(struct kvm_vcpu *vcpu)

{
@@ -41,6 +45,9 @@ static void save_guest_debug_regs(struct kvm_vcpu *vcpu) 


	trace_kvm_arm_set_dreg32("Saved MDSCR_EL1",

				vcpu->arch.guest_debug_preserved.mdscr_el1);



	vcpu->arch.guest_debug_preserved.pstate_ss =

					(*vcpu_cpsr(vcpu) & DBG_SPSR_SS);

}



static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
@@ -51,6 +58,11 @@ static void restore_guest_debug_regs(struct kvm_vcpu *vcpu) 


	trace_kvm_arm_set_dreg32("Restored MDSCR_EL1",

				vcpu_read_sys_reg(vcpu, MDSCR_EL1));



	if (vcpu->arch.guest_debug_preserved.pstate_ss)

		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;

	else

		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;

}



/**
@@ -188,7 +200,18 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) 
		 * debugging the system.

		 */

		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {

			/*

			 * If the software step state at the last guest exit

			 * was Active-pending, we don't set DBG_SPSR_SS so

			 * that the state is maintained (to not run another

			 * single-step until the pending Software Step

			 * exception is taken).

			 */

			if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING))

				*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;

			else

				*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;



			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);

			mdscr |= DBG_MDSCR_SS;

			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
@@ -262,6 +285,15 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) 
	 * Restore the guest's debug registers if we were using them.

	 */

	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {

		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {

			if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS))

				/*

				 * Mark the vcpu as ACTIVE_PENDING

				 * until Software Step exception is taken.

				 */

				vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING);

		}



		restore_guest_debug_regs(vcpu);



		/*