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

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Proper emulation of the OSLock feature of the debug architecture

   - Scalibility improvements for the MMU lock when dirty logging is on

   - New VMID allocator, which will eventually help with SVA in VMs

   - Better support for PMUs in heterogenous systems

   - PSCI 1.1 support, enabling support for SYSTEM_RESET2

   - Implement CONFIG_DEBUG_LIST at EL2

   - Make CONFIG_ARM64_ERRATUM_2077057 default y

   - Reduce the overhead of VM exit when no interrupt is pending

   - Remove traces of 32bit ARM host support from the documentation

   - Updated vgic selftests

   - Various cleanups, doc updates and spelling fixes

  RISC-V:
   - Prevent KVM_COMPAT from being selected

   - Optimize __kvm_riscv_switch_to() implementation

   - RISC-V SBI v0.3 support

  s390:
   - memop selftest

   - fix SCK locking

   - adapter interruptions virtualization for secure guests

   - add Claudio Imbrenda as maintainer

   - first step to do proper storage key checking

  x86:
   - Continue switching kvm_x86_ops to static_call(); introduce
     static_call_cond() and __static_call_ret0 when applicable.

   - Cleanup unused arguments in several functions

   - Synthesize AMD 0x80000021 leaf

   - Fixes and optimization for Hyper-V sparse-bank hypercalls

   - Implement Hyper-V's enlightened MSR bitmap for nested SVM

   - Remove MMU auditing

   - Eager splitting of page tables (new aka "TDP" MMU only) when dirty
     page tracking is enabled

   - Cleanup the implementation of the guest PGD cache

   - Preparation for the implementation of Intel IPI virtualization

   - Fix some segment descriptor checks in the emulator

   - Allow AMD AVIC support on systems with physical APIC ID above 255

   - Better API to disable virtualization quirks

   - Fixes and optimizations for the zapping of page tables:

      - Zap roots in two passes, avoiding RCU read-side critical
        sections that last too long for very large guests backed by 4
        KiB SPTEs.

      - Zap invalid and defunct roots asynchronously via
        concurrency-managed work queue.

      - Allowing yielding when zapping TDP MMU roots in response to the
        root's last reference being put.

      - Batch more TLB flushes with an RCU trick. Whoever frees the
        paging structure now holds RCU as a proxy for all vCPUs running
        in the guest, i.e. to prolongs the grace period on their behalf.
        It then kicks the the vCPUs out of guest mode before doing
        rcu_read_unlock().

  Generic:
   - Introduce __vcalloc and use it for very large allocations that need
     memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
  KVM: use kvcalloc for array allocations
  KVM: x86: Introduce KVM_CAP_DISABLE_QUIRKS2
  kvm: x86: Require const tsc for RT
  KVM: x86: synthesize CPUID leaf 0x80000021h if useful
  KVM: x86: add support for CPUID leaf 0x80000021
  KVM: x86: do not use KVM_X86_OP_OPTIONAL_RET0 for get_mt_mask
  Revert "KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range()"
  kvm: x86/mmu: Flush TLB before zap_gfn_range releases RCU
  KVM: arm64: fix typos in comments
  KVM: arm64: Generalise VM features into a set of flags
  KVM: s390: selftests: Add error memop tests
  KVM: s390: selftests: Add more copy memop tests
  KVM: s390: selftests: Add named stages for memop test
  KVM: s390: selftests: Add macro as abstraction for MEM_OP
  KVM: s390: selftests: Split memop tests
  KVM: s390x: fix SCK locking
  RISC-V: KVM: Implement SBI HSM suspend call
  RISC-V: KVM: Add common kvm_riscv_vcpu_wfi() function
  RISC-V: Add SBI HSM suspend related defines
  RISC-V: KVM: Implement SBI v0.3 SRST extension
  ...

1 files changed, 57 insertions, 17 deletions

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index baa65292bbc2..7b45c040cc27 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -44,6 +44,10 @@
  * 64bit interface.
  */
 
+static int reg_from_user(u64 *val, const void __user *uaddr, u64 id);
+static int reg_to_user(void __user *uaddr, const u64 *val, u64 id);
+static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
+
 static bool read_from_write_only(struct kvm_vcpu *vcpu,
 				 struct sys_reg_params *params,
 				 const struct sys_reg_desc *r)
@@ -287,16 +291,55 @@ static bool trap_loregion(struct kvm_vcpu *vcpu,
 	return trap_raz_wi(vcpu, p, r);
 }
 
+static bool trap_oslar_el1(struct kvm_vcpu *vcpu,
+			   struct sys_reg_params *p,
+			   const struct sys_reg_desc *r)
+{
+	u64 oslsr;
+
+	if (!p->is_write)
+		return read_from_write_only(vcpu, p, r);
+
+	/* Forward the OSLK bit to OSLSR */
+	oslsr = __vcpu_sys_reg(vcpu, OSLSR_EL1) & ~SYS_OSLSR_OSLK;
+	if (p->regval & SYS_OSLAR_OSLK)
+		oslsr |= SYS_OSLSR_OSLK;
+
+	__vcpu_sys_reg(vcpu, OSLSR_EL1) = oslsr;
+	return true;
+}
+
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	if (p->is_write) {
-		return ignore_write(vcpu, p);
-	} else {
-		p->regval = (1 << 3);
-		return true;
-	}
+	if (p->is_write)
+		return write_to_read_only(vcpu, p, r);
+
+	p->regval = __vcpu_sys_reg(vcpu, r->reg);
+	return true;
+}
+
+static int set_oslsr_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+			 const struct kvm_one_reg *reg, void __user *uaddr)
+{
+	u64 id = sys_reg_to_index(rd);
+	u64 val;
+	int err;
+
+	err = reg_from_user(&val, uaddr, id);
+	if (err)
+		return err;
+
+	/*
+	 * The only modifiable bit is the OSLK bit. Refuse the write if
+	 * userspace attempts to change any other bit in the register.
+	 */
+	if ((val ^ rd->val) & ~SYS_OSLSR_OSLK)
+		return -EINVAL;
+
+	__vcpu_sys_reg(vcpu, rd->reg) = val;
+	return 0;
 }
 
 static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
@@ -1169,10 +1212,6 @@ static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
 	return __access_id_reg(vcpu, p, r, true);
 }
 
-static int reg_from_user(u64 *val, const void __user *uaddr, u64 id);
-static int reg_to_user(void __user *uaddr, const u64 *val, u64 id);
-static u64 sys_reg_to_index(const struct sys_reg_desc *reg);
-
 /* Visibility overrides for SVE-specific control registers */
 static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
 				   const struct sys_reg_desc *rd)
@@ -1423,9 +1462,9 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
  * Debug handling: We do trap most, if not all debug related system
  * registers. The implementation is good enough to ensure that a guest
  * can use these with minimal performance degradation. The drawback is
- * that we don't implement any of the external debug, none of the
- * OSlock protocol. This should be revisited if we ever encounter a
- * more demanding guest...
+ * that we don't implement any of the external debug architecture.
+ * This should be revisited if we ever encounter a more demanding
+ * guest...
  */
 static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_DC_ISW), access_dcsw },
@@ -1452,8 +1491,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	DBG_BCR_BVR_WCR_WVR_EL1(15),
 
 	{ SYS_DESC(SYS_MDRAR_EL1), trap_raz_wi },
-	{ SYS_DESC(SYS_OSLAR_EL1), trap_raz_wi },
-	{ SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1 },
+	{ SYS_DESC(SYS_OSLAR_EL1), trap_oslar_el1 },
+	{ SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1, reset_val, OSLSR_EL1,
+		SYS_OSLSR_OSLM_IMPLEMENTED, .set_user = set_oslsr_el1, },
 	{ SYS_DESC(SYS_OSDLR_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_DBGPRCR_EL1), trap_raz_wi },
 	{ SYS_DESC(SYS_DBGCLAIMSET_EL1), trap_raz_wi },
@@ -1925,10 +1965,10 @@ static const struct sys_reg_desc cp14_regs[] = {
 
 	DBGBXVR(0),
 	/* DBGOSLAR */
-	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+	{ Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_oslar_el1 },
 	DBGBXVR(1),
 	/* DBGOSLSR */
-	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+	{ Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1, NULL, OSLSR_EL1 },
 	DBGBXVR(2),
 	DBGBXVR(3),
 	/* DBGOSDLR */