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

Pull kvm updates from Paolo Bonzini:
 "S390:

   - Changes to FPU handling came in via the main s390 pull request

   - Only deliver to the guest the SCLP events that userspace has
     requested

   - More virtual vs physical address fixes (only a cleanup since
     virtual and physical address spaces are currently the same)

   - Fix selftests undefined behavior

  x86:

   - Fix a restriction that the guest can't program a PMU event whose
     encoding matches an architectural event that isn't included in the
     guest CPUID. The enumeration of an architectural event only says
     that if a CPU supports an architectural event, then the event can
     be programmed *using the architectural encoding*. The enumeration
     does NOT say anything about the encoding when the CPU doesn't
     report support the event *in general*. It might support it, and it
     might support it using the same encoding that made it into the
     architectural PMU spec

   - Fix a variety of bugs in KVM's emulation of RDPMC (more details on
     individual commits) and add a selftest to verify KVM correctly
     emulates RDMPC, counter availability, and a variety of other
     PMC-related behaviors that depend on guest CPUID and therefore are
     easier to validate with selftests than with custom guests (aka
     kvm-unit-tests)

   - Zero out PMU state on AMD if the virtual PMU is disabled, it does
     not cause any bug but it wastes time in various cases where KVM
     would check if a PMC event needs to be synthesized

   - Optimize triggering of emulated events, with a nice ~10%
     performance improvement in VM-Exit microbenchmarks when a vPMU is
     exposed to the guest

   - Tighten the check for "PMI in guest" to reduce false positives if
     an NMI arrives in the host while KVM is handling an IRQ VM-Exit

   - Fix a bug where KVM would report stale/bogus exit qualification
     information when exiting to userspace with an internal error exit
     code

   - Add a VMX flag in /proc/cpuinfo to report 5-level EPT support

   - Rework TDP MMU root unload, free, and alloc to run with mmu_lock
     held for read, e.g. to avoid serializing vCPUs when userspace
     deletes a memslot

   - Tear down TDP MMU page tables at 4KiB granularity (used to be
     1GiB). KVM doesn't support yielding in the middle of processing a
     zap, and 1GiB granularity resulted in multi-millisecond lags that
     are quite impolite for CONFIG_PREEMPT kernels

   - Allocate write-tracking metadata on-demand to avoid the memory
     overhead when a kernel is built with i915 virtualization support
     but the workloads use neither shadow paging nor i915 virtualization

   - Explicitly initialize a variety of on-stack variables in the
     emulator that triggered KMSAN false positives

   - Fix the debugregs ABI for 32-bit KVM

   - Rework the "force immediate exit" code so that vendor code
     ultimately decides how and when to force the exit, which allowed
     some optimization for both Intel and AMD

   - Fix a long-standing bug where kvm_has_noapic_vcpu could be left
     elevated if vCPU creation ultimately failed, causing extra
     unnecessary work

   - Cleanup the logic for checking if the currently loaded vCPU is
     in-kernel

   - Harden against underflowing the active mmu_notifier invalidation
     count, so that "bad" invalidations (usually due to bugs elsehwere
     in the kernel) are detected earlier and are less likely to hang the
     kernel

  x86 Xen emulation:

   - Overlay pages can now be cached based on host virtual address,
     instead of guest physical addresses. This removes the need to
     reconfigure and invalidate the cache if the guest changes the gpa
     but the underlying host virtual address remains the same

   - When possible, use a single host TSC value when computing the
     deadline for Xen timers in order to improve the accuracy of the
     timer emulation

   - Inject pending upcall events when the vCPU software-enables its
     APIC to fix a bug where an upcall can be lost (and to follow Xen's
     behavior)

   - Fall back to the slow path instead of warning if "fast" IRQ
     delivery of Xen events fails, e.g. if the guest has aliased xAPIC
     IDs

  RISC-V:

   - Support exception and interrupt handling in selftests

   - New self test for RISC-V architectural timer (Sstc extension)

   - New extension support (Ztso, Zacas)

   - Support userspace emulation of random number seed CSRs

  ARM:

   - Infrastructure for building KVM's trap configuration based on the
     architectural features (or lack thereof) advertised in the VM's ID
     registers

   - Support for mapping vfio-pci BARs as Normal-NC (vaguely similar to
     x86's WC) at stage-2, improving the performance of interacting with
     assigned devices that can tolerate it

   - Conversion of KVM's representation of LPIs to an xarray, utilized
     to address serialization some of the serialization on the LPI
     injection path

   - Support for _architectural_ VHE-only systems, advertised through
     the absence of FEAT_E2H0 in the CPU's ID register

   - Miscellaneous cleanups, fixes, and spelling corrections to KVM and
     selftests

  LoongArch:

   - Set reserved bits as zero in CPUCFG

   - Start SW timer only when vcpu is blocking

   - Do not restart SW timer when it is expired

   - Remove unnecessary CSR register saving during enter guest

   - Misc cleanups and fixes as usual

  Generic:

   - Clean up Kconfig by removing CONFIG_HAVE_KVM, which was basically
     always true on all architectures except MIPS (where Kconfig
     determines the available depending on CPU capabilities). It is
     replaced either by an architecture-dependent symbol for MIPS, and
     IS_ENABLED(CONFIG_KVM) everywhere else

   - Factor common "select" statements in common code instead of
     requiring each architecture to specify it

   - Remove thoroughly obsolete APIs from the uapi headers

   - Move architecture-dependent stuff to uapi/asm/kvm.h

   - Always flush the async page fault workqueue when a work item is
     being removed, especially during vCPU destruction, to ensure that
     there are no workers running in KVM code when all references to
     KVM-the-module are gone, i.e. to prevent a very unlikely
     use-after-free if kvm.ko is unloaded

   - Grab a reference to the VM's mm_struct in the async #PF worker
     itself instead of gifting the worker a reference, so that there's
     no need to remember to *conditionally* clean up after the worker

  Selftests:

   - Reduce boilerplate especially when utilize selftest TAP
     infrastructure

   - Add basic smoke tests for SEV and SEV-ES, along with a pile of
     library support for handling private/encrypted/protected memory

   - Fix benign bugs where tests neglect to close() guest_memfd files"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
  selftests: kvm: remove meaningless assignments in Makefiles
  KVM: riscv: selftests: Add Zacas extension to get-reg-list test
  RISC-V: KVM: Allow Zacas extension for Guest/VM
  KVM: riscv: selftests: Add Ztso extension to get-reg-list test
  RISC-V: KVM: Allow Ztso extension for Guest/VM
  RISC-V: KVM: Forward SEED CSR access to user space
  KVM: riscv: selftests: Add sstc timer test
  KVM: riscv: selftests: Change vcpu_has_ext to a common function
  KVM: riscv: selftests: Add guest helper to get vcpu id
  KVM: riscv: selftests: Add exception handling support
  LoongArch: KVM: Remove unnecessary CSR register saving during enter guest
  LoongArch: KVM: Do not restart SW timer when it is expired
  LoongArch: KVM: Start SW timer only when vcpu is blocking
  LoongArch: KVM: Set reserved bits as zero in CPUCFG
  KVM: selftests: Explicitly close guest_memfd files in some gmem tests
  KVM: x86/xen: fix recursive deadlock in timer injection
  KVM: pfncache: simplify locking and make more self-contained
  KVM: x86/xen: remove WARN_ON_ONCE() with false positives in evtchn delivery
  KVM: x86/xen: inject vCPU upcall vector when local APIC is enabled
  KVM: x86/xen: improve accuracy of Xen timers
  ...

4 files changed, 20 insertions, 1 deletions

diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h
index 7499e88a947c0..b1c503c2959c3 100644
--- a/arch/riscv/include/uapi/asm/kvm.h
+++ b/arch/riscv/include/uapi/asm/kvm.h
@@ -16,7 +16,6 @@
 #include <asm/ptrace.h>
 
 #define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
@@ -166,6 +165,8 @@ enum KVM_RISCV_ISA_EXT_ID {
 	KVM_RISCV_ISA_EXT_ZVFH,
 	KVM_RISCV_ISA_EXT_ZVFHMIN,
 	KVM_RISCV_ISA_EXT_ZFA,
+	KVM_RISCV_ISA_EXT_ZTSO,
+	KVM_RISCV_ISA_EXT_ZACAS,
 	KVM_RISCV_ISA_EXT_MAX,
 };
 
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index d490db9438588..26d1727f0550d 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -24,6 +24,7 @@ config KVM
 	select HAVE_KVM_IRQ_ROUTING
 	select HAVE_KVM_MSI
 	select HAVE_KVM_VCPU_ASYNC_IOCTL
+	select HAVE_KVM_READONLY_MEM
 	select KVM_COMMON
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c
index 7a6abed41bc17..ee7215f4071f5 100644
--- a/arch/riscv/kvm/vcpu_insn.c
+++ b/arch/riscv/kvm/vcpu_insn.c
@@ -7,6 +7,8 @@
 #include <linux/bitops.h>
 #include <linux/kvm_host.h>
 
+#include <asm/cpufeature.h>
+
 #define INSN_OPCODE_MASK	0x007c
 #define INSN_OPCODE_SHIFT	2
 #define INSN_OPCODE_SYSTEM	28
@@ -213,9 +215,20 @@ struct csr_func {
 		    unsigned long wr_mask);
 };
 
+static int seed_csr_rmw(struct kvm_vcpu *vcpu, unsigned int csr_num,
+			unsigned long *val, unsigned long new_val,
+			unsigned long wr_mask)
+{
+	if (!riscv_isa_extension_available(vcpu->arch.isa, ZKR))
+		return KVM_INSN_ILLEGAL_TRAP;
+
+	return KVM_INSN_EXIT_TO_USER_SPACE;
+}
+
 static const struct csr_func csr_funcs[] = {
 	KVM_RISCV_VCPU_AIA_CSR_FUNCS
 	KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS
+	{ .base = CSR_SEED, .count = 1, .func = seed_csr_rmw },
 };
 
 /**
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 5f7355e960084..f4a6124d25c93 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -40,6 +40,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVINVAL),
 	KVM_ISA_EXT_ARR(SVNAPOT),
 	KVM_ISA_EXT_ARR(SVPBMT),
+	KVM_ISA_EXT_ARR(ZACAS),
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
 	KVM_ISA_EXT_ARR(ZBC),
@@ -66,6 +67,7 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(ZKSED),
 	KVM_ISA_EXT_ARR(ZKSH),
 	KVM_ISA_EXT_ARR(ZKT),
+	KVM_ISA_EXT_ARR(ZTSO),
 	KVM_ISA_EXT_ARR(ZVBB),
 	KVM_ISA_EXT_ARR(ZVBC),
 	KVM_ISA_EXT_ARR(ZVFH),
@@ -117,6 +119,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SSTC:
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
+	case KVM_RISCV_ISA_EXT_ZACAS:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
 	case KVM_RISCV_ISA_EXT_ZBC:
@@ -141,6 +144,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_ZKSED:
 	case KVM_RISCV_ISA_EXT_ZKSH:
 	case KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_RISCV_ISA_EXT_ZTSO:
 	case KVM_RISCV_ISA_EXT_ZVBB:
 	case KVM_RISCV_ISA_EXT_ZVBC:
 	case KVM_RISCV_ISA_EXT_ZVFH: