Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

net/batman-adv/hard-interface.c
  commit 690bb6fb64f5 ("batman-adv: Request iflink once in batadv-on-batadv check")
  commit 6ee3c393eeb7 ("batman-adv: Demote batadv-on-batadv skip error message")
https://lore.kernel.org/all/20220302163049.101957-1-sw@simonwunderlich.de/

net/smc/af_smc.c
  commit 4d08b7b57ece ("net/smc: Fix cleanup when register ULP fails")
  commit 462791bbfa35 ("net/smc: add sysctl interface for SMC")
https://lore.kernel.org/all/20220302112209.355def40@canb.auug.org.au/

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 95 insertions, 31 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6dcccb304775..ec9830d2aabf 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -703,7 +703,6 @@ struct kvm_vcpu_arch {
 	struct fpu_guest guest_fpu;
 
 	u64 xcr0;
-	u64 guest_supported_xcr0;
 
 	struct kvm_pio_request pio;
 	void *pio_data;
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 02b3ddaf4f75..7c7824ae7862 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1558,7 +1558,10 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 		fpregs_restore_userregs();
 
 	newfps->xfeatures = curfps->xfeatures | xfeatures;
-	newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+
+	if (!guest_fpu)
+		newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+
 	newfps->xfd = curfps->xfd & ~xfeatures;
 
 	/* Do the final updates within the locked region */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a438217cbfac..f734e3b0cfec 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -462,19 +462,22 @@ static bool pv_tlb_flush_supported(void)
 {
 	return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
 		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) &&
+		(num_possible_cpus() != 1));
 }
 
 static bool pv_ipi_supported(void)
 {
-	return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
+	return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) &&
+	       (num_possible_cpus() != 1));
 }
 
 static bool pv_sched_yield_supported(void)
 {
 	return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
 		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) &&
+	    (num_possible_cpus() != 1));
 }
 
 #define KVM_IPI_CLUSTER_SIZE	(2 * BITS_PER_LONG)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 494d4d351859..b8f8d268d058 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -282,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct kvm_cpuid_entry2 *best;
+	u64 guest_supported_xcr0;
 
 	best = kvm_find_cpuid_entry(vcpu, 1, 0);
 	if (best && apic) {
@@ -293,9 +294,11 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_apic_set_version(vcpu);
 	}
 
-	vcpu->arch.guest_supported_xcr0 =
+	guest_supported_xcr0 =
 		cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
 
+	vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0;
+
 	kvm_update_pv_runtime(vcpu);
 
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 593093b52395..8e24f73bf60b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
+static u32 alloc_apf_token(struct kvm_vcpu *vcpu)
+{
+	/* make sure the token value is not 0 */
+	u32 id = vcpu->arch.apf.id;
+
+	if (id << 12 == 0)
+		vcpu->arch.apf.id = 1;
+
+	return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
+}
+
 static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				    gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
-	arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
+	arch.token = alloc_apf_token(vcpu);
 	arch.gfn = gfn;
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 821edf664e7a..fd3a00c892c7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -2693,8 +2693,23 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	u64 data = msr->data;
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:
-		if (!msr->host_initiated && !svm->tsc_scaling_enabled)
-			return 1;
+
+		if (!svm->tsc_scaling_enabled) {
+
+			if (!msr->host_initiated)
+				return 1;
+			/*
+			 * In case TSC scaling is not enabled, always
+			 * leave this MSR at the default value.
+			 *
+			 * Due to bug in qemu 6.2.0, it would try to set
+			 * this msr to 0 if tsc scaling is not enabled.
+			 * Ignore this value as well.
+			 */
+			if (data != 0 && data != svm->tsc_ratio_msr)
+				return 1;
+			break;
+		}
 
 		if (data & TSC_RATIO_RSVD)
 			return 1;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index ba34e94049c7..dc822a1d403d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -246,8 +246,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 	src = &prev->host_state;
 	dest = &vmx->loaded_vmcs->host_state;
 
-	vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel,
-				src->fs_base, src->gs_base);
+	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
 	dest->ldt_sel = src->ldt_sel;
 #ifdef CONFIG_X86_64
 	dest->ds_sel = src->ds_sel;
@@ -3056,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr4;
+	unsigned long cr3, cr4;
 	bool vm_fail;
 
 	if (!nested_early_check)
@@ -3079,6 +3078,12 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	 */
 	vmcs_writel(GUEST_RFLAGS, 0);
 
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index efda5e4d6247..b730d799c26e 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1080,14 +1080,9 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
 		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 }
 
-void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3,
-			     u16 fs_sel, u16 gs_sel,
-			     unsigned long fs_base, unsigned long gs_base)
+void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
+			unsigned long fs_base, unsigned long gs_base)
 {
-	if (unlikely(cr3 != host->cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		host->cr3 = cr3;
-	}
 	if (unlikely(fs_sel != host->fs_sel)) {
 		if (!(fs_sel & 7))
 			vmcs_write16(HOST_FS_SELECTOR, fs_sel);
@@ -1182,9 +1177,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	gs_base = segment_base(gs_sel);
 #endif
 
-	vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(),
-				fs_sel, gs_sel, fs_base, gs_base);
-
+	vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
 	vmx->guest_state_loaded = true;
 }
 
@@ -6791,7 +6784,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr4;
+	unsigned long cr3, cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!enable_vnmi &&
@@ -6834,6 +6827,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 	vcpu->arch.regs_dirty = 0;
 
+	/*
+	 * Refresh vmcs.HOST_CR3 if necessary.  This must be done immediately
+	 * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
+	 * it switches back to the current->mm, which can occur in KVM context
+	 * when switching to a temporary mm to patch kernel code, e.g. if KVM
+	 * toggles a static key while handling a VM-Exit.
+	 */
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 7f2c82e7f38f..9c6bfcd84008 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -374,9 +374,8 @@ int allocate_vpid(void);
 void free_vpid(int vpid);
 void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
 void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
-void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3,
-			     u16 fs_sel, u16 gs_sel,
-			     unsigned long fs_base, unsigned long gs_base);
+void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
+			unsigned long fs_base, unsigned long gs_base);
 int vmx_get_cpl(struct kvm_vcpu *vcpu);
 bool vmx_emulation_required(struct kvm_vcpu *vcpu);
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 641044db415d..82a9dcd8c67f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -984,6 +984,18 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
+static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.guest_fpu.fpstate->user_xfeatures;
+}
+
+#ifdef CONFIG_X86_64
+static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu)
+{
+	return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC;
+}
+#endif
+
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
 	u64 xcr0 = xcr;
@@ -1003,7 +1015,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	 * saving.  However, xcr0 bit 0 is always set, even if the
 	 * emulated CPU does not support XSAVE (see kvm_vcpu_reset()).
 	 */
-	valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
+	valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP;
 	if (xcr0 & ~valid_bits)
 		return 1;
 
@@ -2351,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 	return tsc;
 }
 
+#ifdef CONFIG_X86_64
 static inline int gtod_is_based_on_tsc(int mode)
 {
 	return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK;
 }
+#endif
 
 static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 {
@@ -3706,8 +3720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
 			return 1;
 
-		if (data & ~(XFEATURE_MASK_USER_DYNAMIC &
-			     vcpu->arch.guest_supported_xcr0))
+		if (data & ~kvm_guest_supported_xfd(vcpu))
 			return 1;
 
 		fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data);
@@ -3717,8 +3730,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    !guest_cpuid_has(vcpu, X86_FEATURE_XFD))
 			return 1;
 
-		if (data & ~(XFEATURE_MASK_USER_DYNAMIC &
-			     vcpu->arch.guest_supported_xcr0))
+		if (data & ~kvm_guest_supported_xfd(vcpu))
 			return 1;
 
 		vcpu->arch.guest_fpu.xfd_err = data;
@@ -4233,6 +4245,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
 	case KVM_CAP_VCPU_ATTRIBUTES:
 	case KVM_CAP_SYS_ATTRIBUTES:
+	case KVM_CAP_ENABLE_CAP:
 		r = 1;
 		break;
 	case KVM_CAP_EXIT_HYPERCALL:
@@ -8942,6 +8955,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
 	if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK)
 		return -KVM_EOPNOTSUPP;
 
+	/*
+	 * When tsc is in permanent catchup mode guests won't be able to use
+	 * pvclock_read_retry loop to get consistent view of pvclock
+	 */
+	if (vcpu->arch.tsc_always_catchup)
+		return -KVM_EOPNOTSUPP;
+
 	if (!kvm_get_walltime_and_clockread(&ts, &cycle))
 		return -KVM_EOPNOTSUPP;