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

Pull more kvm updates from Paolo Bonzini:
 "s390:
   - nested virtualization fixes

  x86:
   - split svm.c

   - miscellaneous fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: VMX: fix crash cleanup when KVM wasn't used
  KVM: X86: Filter out the broadcast dest for IPI fastpath
  KVM: s390: vsie: Fix possible race when shadowing region 3 tables
  KVM: s390: vsie: Fix delivery of addressing exceptions
  KVM: s390: vsie: Fix region 1 ASCE sanity shadow address checks
  KVM: nVMX: don't clear mtf_pending when nested events are blocked
  KVM: VMX: Remove unnecessary exception trampoline in vmx_vmenter
  KVM: SVM: Split svm_vcpu_run inline assembly to separate file
  KVM: SVM: Move SEV code to separate file
  KVM: SVM: Move AVIC code to separate file
  KVM: SVM: Move Nested SVM Implementation to nested.c
  kVM SVM: Move SVM related files to own sub-directory

arch/s390/kvm/vsie.c

@@ -1202,6 +1202,7 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		scb_s->iprcc = PGM_ADDRESSING;
 		scb_s->pgmilc = 4;
 		scb_s->gpsw.addr = __rewind_psw(scb_s->gpsw, 4);
+		rc = 1;
 	}
 	return rc;
 }

arch/s390/mm/gmap.c

@@ -787,14 +787,18 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
 static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 					     unsigned long gaddr, int level)
 {
+	const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
 	unsigned long *table;
 
 	if ((gmap->asce & _ASCE_TYPE_MASK) + 4 < (level * 4))
 		return NULL;
 	if (gmap_is_shadow(gmap) && gmap->removed)
 		return NULL;
-	if (gaddr & (-1UL << (31 + ((gmap->asce & _ASCE_TYPE_MASK) >> 2)*11)))
+
+	if (asce_type != _ASCE_TYPE_REGION1 &&
+	    gaddr & (-1UL << (31 + (asce_type >> 2) * 11)))
 		return NULL;
+
 	table = gmap->table;
 	switch (gmap->asce & _ASCE_TYPE_MASK) {
 	case _ASCE_TYPE_REGION1:
@@ -1840,6 +1844,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
 		goto out_free;
 	} else if (*table & _REGION_ENTRY_ORIGIN) {
 		rc = -EAGAIN;		/* Race with shadow */
+		goto out_free;
 	}
 	crst_table_init(s_r3t, _REGION3_ENTRY_EMPTY);
 	/* mark as invalid as long as the parent table is not protected */

arch/x86/kvm/Makefile

@@ -14,7 +14,7 @@ kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
 			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o
 
 kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
-kvm-amd-y		+= svm.o pmu_amd.o
+kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
 obj-$(CONFIG_KVM_INTEL)	+= kvm-intel.o

arch/x86/kvm/lapic.c

@@ -59,9 +59,6 @@
 #define MAX_APIC_VECTOR			256
 #define APIC_VECTORS_PER_REG		32
 
-#define APIC_BROADCAST			0xFF
-#define X2APIC_BROADCAST		0xFFFFFFFFul
-
 static bool lapic_timer_advance_dynamic __read_mostly;
 #define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */
 #define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */

arch/x86/kvm/lapic.h

@@ -17,6 +17,9 @@
 #define APIC_BUS_CYCLE_NS       1
 #define APIC_BUS_FREQUENCY      (1000000000ULL / APIC_BUS_CYCLE_NS)
 
+#define APIC_BROADCAST			0xFF
+#define X2APIC_BROADCAST		0xFFFFFFFFul
+
 enum lapic_mode {
 	LAPIC_MODE_DISABLED = 0,
 	LAPIC_MODE_INVALID = X2APIC_ENABLE,

arch/x86/kvm/svm/vmenter.S

+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/bitsperlong.h>
+#include <asm/kvm_vcpu_regs.h>
+
+#define WORD_SIZE (BITS_PER_LONG / 8)
+
+/* Intentionally omit RAX as it's context switched by hardware */
+#define VCPU_RCX	__VCPU_REGS_RCX * WORD_SIZE
+#define VCPU_RDX	__VCPU_REGS_RDX * WORD_SIZE
+#define VCPU_RBX	__VCPU_REGS_RBX * WORD_SIZE
+/* Intentionally omit RSP as it's context switched by hardware */
+#define VCPU_RBP	__VCPU_REGS_RBP * WORD_SIZE
+#define VCPU_RSI	__VCPU_REGS_RSI * WORD_SIZE
+#define VCPU_RDI	__VCPU_REGS_RDI * WORD_SIZE
+
+#ifdef CONFIG_X86_64
+#define VCPU_R8		__VCPU_REGS_R8  * WORD_SIZE
+#define VCPU_R9		__VCPU_REGS_R9  * WORD_SIZE
+#define VCPU_R10	__VCPU_REGS_R10 * WORD_SIZE
+#define VCPU_R11	__VCPU_REGS_R11 * WORD_SIZE
+#define VCPU_R12	__VCPU_REGS_R12 * WORD_SIZE
+#define VCPU_R13	__VCPU_REGS_R13 * WORD_SIZE
+#define VCPU_R14	__VCPU_REGS_R14 * WORD_SIZE
+#define VCPU_R15	__VCPU_REGS_R15 * WORD_SIZE
+#endif
+
+	.text
+
+/**
+ * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode
+ * @vmcb_pa:	unsigned long
+ * @regs:	unsigned long * (to guest registers)
+ */
+SYM_FUNC_START(__svm_vcpu_run)
+	push %_ASM_BP
+	mov  %_ASM_SP, %_ASM_BP
+#ifdef CONFIG_X86_64
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+#else
+	push %edi
+	push %esi
+#endif
+	push %_ASM_BX
+
+	/* Save @regs. */
+	push %_ASM_ARG2
+
+	/* Save @vmcb. */
+	push %_ASM_ARG1
+
+	/* Move @regs to RAX. */
+	mov %_ASM_ARG2, %_ASM_AX
+
+	/* Load guest registers. */
+	mov VCPU_RCX(%_ASM_AX), %_ASM_CX
+	mov VCPU_RDX(%_ASM_AX), %_ASM_DX
+	mov VCPU_RBX(%_ASM_AX), %_ASM_BX
+	mov VCPU_RBP(%_ASM_AX), %_ASM_BP
+	mov VCPU_RSI(%_ASM_AX), %_ASM_SI
+	mov VCPU_RDI(%_ASM_AX), %_ASM_DI
+#ifdef CONFIG_X86_64
+	mov VCPU_R8 (%_ASM_AX),  %r8
+	mov VCPU_R9 (%_ASM_AX),  %r9
+	mov VCPU_R10(%_ASM_AX), %r10
+	mov VCPU_R11(%_ASM_AX), %r11
+	mov VCPU_R12(%_ASM_AX), %r12
+	mov VCPU_R13(%_ASM_AX), %r13
+	mov VCPU_R14(%_ASM_AX), %r14
+	mov VCPU_R15(%_ASM_AX), %r15
+#endif
+
+	/* "POP" @vmcb to RAX. */
+	pop %_ASM_AX
+
+	/* Enter guest mode */
+1:	vmload %_ASM_AX
+	jmp 3f
+2:	cmpb $0, kvm_rebooting
+	jne 3f
+	ud2
+	_ASM_EXTABLE(1b, 2b)
+
+3:	vmrun %_ASM_AX
+	jmp 5f
+4:	cmpb $0, kvm_rebooting
+	jne 5f
+	ud2
+	_ASM_EXTABLE(3b, 4b)
+
+5:	vmsave %_ASM_AX
+	jmp 7f
+6:	cmpb $0, kvm_rebooting
+	jne 7f
+	ud2
+	_ASM_EXTABLE(5b, 6b)
+7:
+	/* "POP" @regs to RAX. */
+	pop %_ASM_AX
+
+	/* Save all guest registers.  */
+	mov %_ASM_CX,   VCPU_RCX(%_ASM_AX)
+	mov %_ASM_DX,   VCPU_RDX(%_ASM_AX)
+	mov %_ASM_BX,   VCPU_RBX(%_ASM_AX)
+	mov %_ASM_BP,   VCPU_RBP(%_ASM_AX)
+	mov %_ASM_SI,   VCPU_RSI(%_ASM_AX)
+	mov %_ASM_DI,   VCPU_RDI(%_ASM_AX)
+#ifdef CONFIG_X86_64
+	mov %r8,  VCPU_R8 (%_ASM_AX)
+	mov %r9,  VCPU_R9 (%_ASM_AX)
+	mov %r10, VCPU_R10(%_ASM_AX)
+	mov %r11, VCPU_R11(%_ASM_AX)
+	mov %r12, VCPU_R12(%_ASM_AX)
+	mov %r13, VCPU_R13(%_ASM_AX)
+	mov %r14, VCPU_R14(%_ASM_AX)
+	mov %r15, VCPU_R15(%_ASM_AX)
+#endif
+
+	/*
+	 * Clear all general purpose registers except RSP and RAX to prevent
+	 * speculative use of the guest's values, even those that are reloaded
+	 * via the stack.  In theory, an L1 cache miss when restoring registers
+	 * could lead to speculative execution with the guest's values.
+	 * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
+	 * free.  RSP and RAX are exempt as they are restored by hardware
+	 * during VM-Exit.
+	 */
+	xor %ecx, %ecx
+	xor %edx, %edx
+	xor %ebx, %ebx
+	xor %ebp, %ebp
+	xor %esi, %esi
+	xor %edi, %edi
+#ifdef CONFIG_X86_64
+	xor %r8d,  %r8d
+	xor %r9d,  %r9d
+	xor %r10d, %r10d
+	xor %r11d, %r11d
+	xor %r12d, %r12d
+	xor %r13d, %r13d
+	xor %r14d, %r14d
+	xor %r15d, %r15d
+#endif
+
+	pop %_ASM_BX
+
+#ifdef CONFIG_X86_64
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+#else
+	pop %esi
+	pop %edi
+#endif
+	pop %_ASM_BP
+	ret
+SYM_FUNC_END(__svm_vcpu_run)

arch/x86/kvm/vmx/nested.c

@@ -3645,6 +3645,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 	 * Clear the MTF state. If a higher priority VM-exit is delivered first,
 	 * this state is discarded.
 	 */
+	if (!block_nested_events)
 		vmx->nested.mtf_pending = false;
 
 	if (lapic_in_kernel(vcpu) &&

arch/x86/kvm/vmx/vmenter.S

@@ -58,12 +58,8 @@ SYM_FUNC_START(vmx_vmenter)
 	ret
 4:	ud2
 
-	.pushsection .fixup, "ax"
-5:	jmp 3b
-	.popsection
-
-	_ASM_EXTABLE(1b, 5b)
-	_ASM_EXTABLE(2b, 5b)
+	_ASM_EXTABLE(1b, 3b)
+	_ASM_EXTABLE(2b, 3b)
 
 SYM_FUNC_END(vmx_vmenter)
 

arch/x86/kvm/vmx/vmx.c

@@ -2261,10 +2261,6 @@ static int hardware_enable(void)
 	    !hv_get_vp_assist_page(cpu))
 		return -EFAULT;
 
-	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-
 	r = kvm_cpu_vmxon(phys_addr);
 	if (r)
 		return r;
@@ -8044,7 +8040,7 @@ module_exit(vmx_exit);
 
 static int __init vmx_init(void)
 {
-	int r;
+	int r, cpu;
 
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
@@ -8098,6 +8094,12 @@ static int __init vmx_init(void)
 		return r;
 	}
 
+	for_each_possible_cpu(cpu) {
+		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+		INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+		spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);

arch/x86/kvm/x86.c

@@ -1586,7 +1586,8 @@ static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data
 
 	if (((data & APIC_SHORT_MASK) == APIC_DEST_NOSHORT) &&
 		((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) &&
-		((data & APIC_MODE_MASK) == APIC_DM_FIXED)) {
+		((data & APIC_MODE_MASK) == APIC_DM_FIXED) &&
+		((u32)(data >> 32) != X2APIC_BROADCAST)) {
 
 		data &= ~(1 << 12);
 		kvm_apic_send_ipi(vcpu->arch.apic, (u32)data, (u32)(data >> 32));