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

Pull KVM updates from Paolo Bonzini:
 "s390:
   - implement diag318

  x86:
   - Report last CPU for debugging
   - Emulate smaller MAXPHYADDR in the guest than in the host
   - .noinstr and tracing fixes from Thomas
   - nested SVM page table switching optimization and fixes

  Generic:
   - Unify shadow MMU cache data structures across architectures"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (127 commits)
  KVM: SVM: Fix sev_pin_memory() error handling
  KVM: LAPIC: Set the TDCR settable bits
  KVM: x86: Specify max TDP level via kvm_configure_mmu()
  KVM: x86/mmu: Rename max_page_level to max_huge_page_level
  KVM: x86: Dynamically calculate TDP level from max level and MAXPHYADDR
  KVM: VXM: Remove temporary WARN on expected vs. actual EPTP level mismatch
  KVM: x86: Pull the PGD's level from the MMU instead of recalculating it
  KVM: VMX: Make vmx_load_mmu_pgd() static
  KVM: x86/mmu: Add separate helper for shadow NPT root page role calc
  KVM: VMX: Drop a duplicate declaration of construct_eptp()
  KVM: nSVM: Correctly set the shadow NPT root level in its MMU role
  KVM: Using macros instead of magic values
  MIPS: KVM: Fix build error caused by 'kvm_run' cleanup
  KVM: nSVM: remove nonsensical EXITINFO1 adjustment on nested NPF
  KVM: x86: Add a capability for GUEST_MAXPHYADDR < HOST_MAXPHYADDR support
  KVM: VMX: optimize #PF injection when MAXPHYADDR does not match
  KVM: VMX: Add guest physical address check in EPT violation and misconfig
  KVM: VMX: introduce vmx_need_pf_intercept
  KVM: x86: update exception bitmap on CPUID changes
  KVM: x86: rename update_bp_intercept to update_exception_bitmap
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -5804,8 +5804,9 @@
 			panic() code such as dumping handler.
 
 	xen_nopvspin	[X86,XEN]
-			Disables the ticketlock slowpath using Xen PV
-			optimizations.
+			Disables the qspinlock slowpath using Xen PV optimizations.
+			This parameter is obsoleted by "nopvspin" parameter, which
+			has equivalent effect for XEN platform.
 
 	xen_nopv	[X86]
 			Disables the PV optimizations forcing the HVM guest to
@@ -5831,6 +5832,11 @@
 			as generic guest with no PV drivers. Currently support
 			XEN HVM, KVM, HYPER_V and VMWARE guest.
 
+	nopvspin	[X86,XEN,KVM]
+			Disables the qspinlock slow path using PV optimizations
+			which allow the hypervisor to 'idle' the guest on lock
+			contention.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

Documentation/virt/kvm/api.rst

@@ -669,6 +669,10 @@ MSRs that have been set successfully.
 Defines the vcpu responses to the cpuid instruction.  Applications
 should use the KVM_SET_CPUID2 ioctl if available.
 
+Note, when this IOCTL fails, KVM gives no guarantees that previous valid CPUID
+configuration (if there is) is not corrupted. Userspace can get a copy of the
+resulting CPUID configuration through KVM_GET_CPUID2 in case.
+
 ::
 
   struct kvm_cpuid_entry {
@@ -4795,6 +4799,7 @@ hardware_exit_reason.
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
+			__u32 cpu; /* if KVM_LAST_CPU */
 		} fail_entry;
 
 If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due

arch/arm64/include/asm/kvm_coproc.h

@@ -27,12 +27,12 @@ struct kvm_sys_reg_target_table {
 void kvm_register_target_sys_reg_table(unsigned int target,
 				       struct kvm_sys_reg_target_table *table);
 
-int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu);
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu);
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu);
+int kvm_handle_sys_reg(struct kvm_vcpu *vcpu);
 
 #define kvm_coproc_table_init kvm_sys_reg_table_init
 void kvm_sys_reg_table_init(void);

arch/arm64/include/asm/kvm_host.h

@@ -97,17 +97,6 @@ struct kvm_arch {
 	bool return_nisv_io_abort_to_user;
 };
 
-#define KVM_NR_MEM_OBJS     40
-
-/*
- * We don't want allocation failures within the mmu code, so we preallocate
- * enough memory for a single page fault in a cache.
- */
-struct kvm_mmu_memory_cache {
-	int nobjs;
-	void *objects[KVM_NR_MEM_OBJS];
-};
-
 struct kvm_vcpu_fault_info {
 	u32 esr_el2;		/* Hyp Syndrom Register */
 	u64 far_el2;		/* Hyp Fault Address Register */
@@ -486,18 +475,15 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 void force_vm_exit(const cpumask_t *mask);
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
-int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		int exception_index);
-void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		       int exception_index);
+int handle_exit(struct kvm_vcpu *vcpu, int exception_index);
+void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index);
 
 /* MMIO helpers */
 void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
 unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
 
-int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		 phys_addr_t fault_ipa);
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu);
+int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa);
 
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);

arch/arm64/include/asm/kvm_mmu.h

@@ -139,7 +139,7 @@ void kvm_free_stage2_pgd(struct kvm *kvm);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
-int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 

arch/arm64/include/asm/kvm_types.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_KVM_TYPES_H
+#define _ASM_ARM64_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40
+
+#endif /* _ASM_ARM64_KVM_TYPES_H */
+

arch/arm64/kvm/arm.c

@@ -270,6 +270,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.target = -1;
 	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 
+	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
+
 	/* Set up the timer */
 	kvm_timer_vcpu_init(vcpu);
 
@@ -658,7 +660,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		return ret;
 
 	if (run->exit_reason == KVM_EXIT_MMIO) {
-		ret = kvm_handle_mmio_return(vcpu, run);
+		ret = kvm_handle_mmio_return(vcpu);
 		if (ret)
 			return ret;
 	}
@@ -810,11 +812,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
 
 		/* Exit types that need handling before we can be preempted */
-		handle_exit_early(vcpu, run, ret);
+		handle_exit_early(vcpu, ret);
 
 		preempt_enable();
 
-		ret = handle_exit(vcpu, run, ret);
+		ret = handle_exit(vcpu, ret);
 	}
 
 	/* Tell userspace about in-kernel device output levels */

arch/arm64/kvm/handle_exit.c

@@ -25,15 +25,15 @@
 #define CREATE_TRACE_POINTS
 #include "trace_handle_exit.h"
 
-typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+typedef int (*exit_handle_fn)(struct kvm_vcpu *);
 
 static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u32 esr)
 {
 	if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(NULL, esr))
 		kvm_inject_vabt(vcpu);
 }
 
-static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_hvc(struct kvm_vcpu *vcpu)
 {
 	int ret;
 
@@ -50,7 +50,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return ret;
 }
 
-static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_smc(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * "If an SMC instruction executed at Non-secure EL1 is
@@ -69,7 +69,7 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * Guest access to FP/ASIMD registers are routed to this handler only
  * when the system doesn't support FP/ASIMD.
  */
-static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_no_fpsimd(struct kvm_vcpu *vcpu)
 {
 	kvm_inject_undefined(vcpu);
 	return 1;
@@ -87,7 +87,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * world-switches and schedule other host processes until there is an
  * incoming IRQ or FIQ to the VM.
  */
-static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
 {
 	if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
@@ -109,16 +109,16 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * kvm_handle_guest_debug - handle a debug exception instruction
  *
  * @vcpu:	the vcpu pointer
- * @run:	access to the kvm_run structure for results
  *
  * We route all debug exceptions through the same handler. If both the
  * guest and host are using the same debug facilities it will be up to
  * userspace to re-inject the correct exception for guest delivery.
  *
- * @return: 0 (while setting run->exit_reason), -1 for error
+ * @return: 0 (while setting vcpu->run->exit_reason), -1 for error
  */
-static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 {
+	struct kvm_run *run = vcpu->run;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 	int ret = 0;
 
@@ -144,7 +144,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return ret;
 }
 
-static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
 {
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
 
@@ -155,7 +155,7 @@ static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
-static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_sve(struct kvm_vcpu *vcpu)
 {
 	/* Until SVE is supported for guests: */
 	kvm_inject_undefined(vcpu);
@@ -167,7 +167,7 @@ static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * a NOP). If we get here, it is that we didn't fixup ptrauth on exit, and all
  * that we can do is give the guest an UNDEF.
  */
-static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu)
 {
 	kvm_inject_undefined(vcpu);
 	return 1;
@@ -212,7 +212,7 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
  * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
  * emulation first.
  */
-static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int handle_trap_exceptions(struct kvm_vcpu *vcpu)
 {
 	int handled;
 
@@ -227,7 +227,7 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		exit_handle_fn exit_handler;
 
 		exit_handler = kvm_get_exit_handler(vcpu);
-		handled = exit_handler(vcpu, run);
+		handled = exit_handler(vcpu);
 	}
 
 	return handled;
@@ -237,9 +237,10 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
  * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
  * proper exit to userspace.
  */
-int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		       int exception_index)
+int handle_exit(struct kvm_vcpu *vcpu, int exception_index)
 {
+	struct kvm_run *run = vcpu->run;
+
 	if (ARM_SERROR_PENDING(exception_index)) {
 		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
 
@@ -265,7 +266,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	case ARM_EXCEPTION_EL1_SERROR:
 		return 1;
 	case ARM_EXCEPTION_TRAP:
-		return handle_trap_exceptions(vcpu, run);
+		return handle_trap_exceptions(vcpu);
 	case ARM_EXCEPTION_HYP_GONE:
 		/*
 		 * EL2 has been reset to the hyp-stub. This happens when a guest
@@ -289,8 +290,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 }
 
 /* For exit types that need handling before we can be preempted */
-void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		       int exception_index)
+void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
 {
 	if (ARM_SERROR_PENDING(exception_index)) {
 		if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) {

arch/arm64/kvm/mmio.c

@@ -77,9 +77,8 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len)
  *			     or in-kernel IO emulation
  *
  * @vcpu: The VCPU pointer
- * @run:  The VCPU run struct containing the mmio data
  */
-int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu)
 {
 	unsigned long data;
 	unsigned int len;
@@ -92,6 +91,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	vcpu->mmio_needed = 0;
 
 	if (!kvm_vcpu_dabt_iswrite(vcpu)) {
+		struct kvm_run *run = vcpu->run;
+
 		len = kvm_vcpu_dabt_get_as(vcpu);
 		data = kvm_mmio_read_buf(run->mmio.data, len);
 
@@ -119,9 +120,9 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 0;
 }
 
-int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		 phys_addr_t fault_ipa)
+int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
+	struct kvm_run *run = vcpu->run;
 	unsigned long data;
 	unsigned long rt;
 	int ret;
@@ -188,7 +189,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (!is_write)
 			memcpy(run->mmio.data, data_buf, len);
 		vcpu->stat.mmio_exit_kernel++;
-		kvm_handle_mmio_return(vcpu, run);
+		kvm_handle_mmio_return(vcpu);
 		return 1;
 	}