Merge tag 'v5.15.70' into lf-5.15.y

This is the 5.15.70 stable release

* tag 'v5.15.70': (2444 commits)
  Linux 5.15.70
  ALSA: hda/sigmatel: Fix unused variable warning for beep power change
  cgroup: Add missing cpus_read_lock() to cgroup_attach_task_all()
  ...

Signed-off-by: Jason Liu <jason.hui.liu@nxp.com>

 Conflicts:
	arch/arm/boot/dts/imx6ul.dtsi
	arch/arm/mm/mmu.c
	arch/arm64/boot/dts/freescale/imx8mp-evk.dts
	drivers/gpu/drm/imx/dcss/dcss-kms.c
	drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
	drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.h
	drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
	drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
	drivers/soc/fsl/Kconfig
	drivers/soc/imx/gpcv2.c
	drivers/usb/dwc3/host.c
	net/dsa/slave.c
	sound/soc/fsl/imx-card.c

1 files changed, 111 insertions, 59 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39aaa21e28f7..11e73d02fb3a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -277,6 +277,8 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
 	STATS_DESC_COUNTER(VCPU, nested_run),
 	STATS_DESC_COUNTER(VCPU, directed_yield_attempted),
 	STATS_DESC_COUNTER(VCPU, directed_yield_successful),
+	STATS_DESC_COUNTER(VCPU, preemption_reported),
+	STATS_DESC_COUNTER(VCPU, preemption_other),
 	STATS_DESC_ICOUNTER(VCPU, guest_mode)
 };
 
@@ -1029,7 +1031,7 @@ int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv);
 
-bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	if (cr4 & cr4_reserved_bits)
 		return false;
@@ -1037,9 +1039,15 @@ bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (cr4 & vcpu->arch.cr4_guest_rsvd_bits)
 		return false;
 
-	return static_call(kvm_x86_is_valid_cr4)(vcpu, cr4);
+	return true;
+}
+EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4);
+
+static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	return __kvm_is_valid_cr4(vcpu, cr4) &&
+	       static_call(kvm_x86_is_valid_cr4)(vcpu, cr4);
 }
-EXPORT_SYMBOL_GPL(kvm_is_valid_cr4);
 
 void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4)
 {
@@ -1457,12 +1465,32 @@ static const u32 msr_based_features_all[] = {
 static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
 static unsigned int num_msr_based_features;
 
+/*
+ * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM
+ * does not yet virtualize. These include:
+ *   10 - MISC_PACKAGE_CTRLS
+ *   11 - ENERGY_FILTERING_CTL
+ *   12 - DOITM
+ *   18 - FB_CLEAR_CTRL
+ *   21 - XAPIC_DISABLE_STATUS
+ *   23 - OVERCLOCKING_STATUS
+ */
+
+#define KVM_SUPPORTED_ARCH_CAP \
+	(ARCH_CAP_RDCL_NO | ARCH_CAP_IBRS_ALL | ARCH_CAP_RSBA | \
+	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
+	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
+	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
+	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)
+
 static u64 kvm_get_arch_capabilities(void)
 {
 	u64 data = 0;
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
+		data &= KVM_SUPPORTED_ARCH_CAP;
+	}
 
 	/*
 	 * If nx_huge_pages is enabled, KVM's shadow paging will ensure that
@@ -1510,9 +1538,6 @@ static u64 kvm_get_arch_capabilities(void)
 		 */
 	}
 
-	/* Guests don't need to know "Fill buffer clear control" exists */
-	data &= ~ARCH_CAP_FB_CLEAR_CTRL;
-
 	return data;
 }
 
@@ -3094,17 +3119,20 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
 			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
-			 * this to avoid an uncatched #GP in the guest
+			 * this to avoid an uncatched #GP in the guest.
+			 *
+			 * UNIXWARE clears bit 0 of MC1_CTL to ignore
+			 * correctable, single-bit ECC data errors.
 			 */
 			if ((offset & 0x3) == 0 &&
-			    data != 0 && (data | (1 << 10)) != ~(u64)0)
-				return -1;
+			    data != 0 && (data | (1 << 10) | 1) != ~(u64)0)
+				return 1;
 
 			/* MCi_STATUS */
 			if (!msr_info->host_initiated &&
 			    (offset & 0x3) == 1 && data != 0) {
 				if (!can_set_mci_status(vcpu))
-					return -1;
+					return 1;
 			}
 
 			vcpu->arch.mce_banks[offset] = data;
@@ -3236,6 +3264,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
 	struct kvm_steal_time __user *st;
 	struct kvm_memslots *slots;
+	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
 	u64 steal;
 	u32 version;
 
@@ -3253,13 +3282,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	slots = kvm_memslots(vcpu->kvm);
 
 	if (unlikely(slots->generation != ghc->generation ||
+		     gpa != ghc->gpa ||
 		     kvm_is_error_hva(ghc->hva) || !ghc->memslot)) {
-		gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
-
 		/* We rely on the fact that it fits in a single page. */
 		BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS);
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) ||
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st)) ||
 		    kvm_is_error_hva(ghc->hva) || !ghc->memslot)
 			return;
 	}
@@ -4370,7 +4398,21 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	struct kvm_steal_time __user *st;
 	struct kvm_memslots *slots;
 	static const u8 preempted = KVM_VCPU_PREEMPTED;
+	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
 
+	/*
+	 * The vCPU can be marked preempted if and only if the VM-Exit was on
+	 * an instruction boundary and will not trigger guest emulation of any
+	 * kind (see vcpu_run).  Vendor specific code controls (conservatively)
+	 * when this is true, for example allowing the vCPU to be marked
+	 * preempted if and only if the VM-Exit was due to a host interrupt.
+	 */
+	if (!vcpu->arch.at_instruction_boundary) {
+		vcpu->stat.preemption_other++;
+		return;
+	}
+
+	vcpu->stat.preemption_reported++;
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
@@ -4384,6 +4426,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	slots = kvm_memslots(vcpu->kvm);
 
 	if (unlikely(slots->generation != ghc->generation ||
+		     gpa != ghc->gpa ||
 		     kvm_is_error_hva(ghc->hva) || !ghc->memslot))
 		return;
 
@@ -4400,19 +4443,21 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	int idx;
 
-	if (vcpu->preempted && !vcpu->arch.guest_state_protected)
-		vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
+	if (vcpu->preempted) {
+		if (!vcpu->arch.guest_state_protected)
+			vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
 
-	/*
-	 * Take the srcu lock as memslots will be accessed to check the gfn
-	 * cache generation against the memslots generation.
-	 */
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvm_xen_msr_enabled(vcpu->kvm))
-		kvm_xen_runstate_set_preempted(vcpu);
-	else
-		kvm_steal_time_set_preempted(vcpu);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		/*
+		 * Take the srcu lock as memslots will be accessed to check the gfn
+		 * cache generation against the memslots generation.
+		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		if (kvm_xen_msr_enabled(vcpu->kvm))
+			kvm_xen_runstate_set_preempted(vcpu);
+		else
+			kvm_steal_time_set_preempted(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	}
 
 	static_call(kvm_x86_vcpu_put)(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
@@ -6894,15 +6939,8 @@ static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
 				   exception, &write_emultor);
 }
 
-#define CMPXCHG_TYPE(t, ptr, old, new) \
-	(cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old))
-
-#ifdef CONFIG_X86_64
-#  define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new)
-#else
-#  define CMPXCHG64(ptr, old, new) \
-	(cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old))
-#endif
+#define emulator_try_cmpxchg_user(t, ptr, old, new) \
+	(__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t))
 
 static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 				     unsigned long addr,
@@ -6911,12 +6949,11 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 				     unsigned int bytes,
 				     struct x86_exception *exception)
 {
-	struct kvm_host_map map;
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u64 page_line_mask;
+	unsigned long hva;
 	gpa_t gpa;
-	char *kaddr;
-	bool exchanged;
+	int r;
 
 	/* guests cmpxchg8b have to be emulated atomically */
 	if (bytes > 8 || (bytes & (bytes - 1)))
@@ -6940,31 +6977,32 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 	if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask))
 		goto emul_write;
 
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(gpa), &map))
+	hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa));
+	if (kvm_is_error_hva(hva))
 		goto emul_write;
 
-	kaddr = map.hva + offset_in_page(gpa);
+	hva += offset_in_page(gpa);
 
 	switch (bytes) {
 	case 1:
-		exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u8, hva, old, new);
 		break;
 	case 2:
-		exchanged = CMPXCHG_TYPE(u16, kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u16, hva, old, new);
 		break;
 	case 4:
-		exchanged = CMPXCHG_TYPE(u32, kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u32, hva, old, new);
 		break;
 	case 8:
-		exchanged = CMPXCHG64(kaddr, old, new);
+		r = emulator_try_cmpxchg_user(u64, hva, old, new);
 		break;
 	default:
 		BUG();
 	}
 
-	kvm_vcpu_unmap(vcpu, &map, true);
-
-	if (!exchanged)
+	if (r < 0)
+		goto emul_write;
+	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
 	kvm_page_track_write(vcpu, gpa, new, bytes);
@@ -8713,15 +8751,17 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
  */
 static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 {
-	struct kvm_lapic_irq lapic_irq;
-
-	lapic_irq.shorthand = APIC_DEST_NOSHORT;
-	lapic_irq.dest_mode = APIC_DEST_PHYSICAL;
-	lapic_irq.level = 0;
-	lapic_irq.dest_id = apicid;
-	lapic_irq.msi_redir_hint = false;
+	/*
+	 * All other fields are unused for APIC_DM_REMRD, but may be consumed by
+	 * common code, e.g. for tracing. Defer initialization to the compiler.
+	 */
+	struct kvm_lapic_irq lapic_irq = {
+		.delivery_mode = APIC_DM_REMRD,
+		.dest_mode = APIC_DEST_PHYSICAL,
+		.shorthand = APIC_DEST_NOSHORT,
+		.dest_id = apicid,
+	};
 
-	lapic_irq.delivery_mode = APIC_DM_REMRD;
 	kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL);
 }
 
@@ -9517,6 +9557,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
 }
 
+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm)
+{
+	static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm);
+}
+
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	if (!lapic_in_kernel(vcpu))
@@ -9939,6 +9984,13 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
+		/*
+		 * If another guest vCPU requests a PV TLB flush in the middle
+		 * of instruction emulation, the rest of the emulation could
+		 * use a stale page translation. Assume that any code after
+		 * this point can start executing an instruction.
+		 */
+		vcpu->arch.at_instruction_boundary = false;
 		if (kvm_vcpu_running(vcpu)) {
 			r = vcpu_enter_guest(vcpu);
 		} else {
@@ -11552,7 +11604,7 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot,
 		if (slot->arch.rmap[i])
 			continue;
 
-		slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
+		slot->arch.rmap[i] = __vcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
 		if (!slot->arch.rmap[i]) {
 			memslot_rmap_free(slot);
 			return -ENOMEM;
@@ -11633,7 +11685,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm,
 
 		lpages = __kvm_mmu_slot_lpages(slot, npages, level);
 
-		linfo = kvcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT);
+		linfo = __vcalloc(lpages, sizeof(*linfo), GFP_KERNEL_ACCOUNT);
 		if (!linfo)
 			goto out_free;
 
@@ -12177,9 +12229,9 @@ void kvm_arch_end_assignment(struct kvm *kvm)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
 
-bool kvm_arch_has_assigned_device(struct kvm *kvm)
+bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm)
 {
-	return atomic_read(&kvm->arch.assigned_device_count);
+	return arch_atomic_read(&kvm->arch.assigned_device_count);
 }
 EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);