5.4.19-stable review

@@ -1555,16 +1555,16 @@ struct match_list_head {
 	struct match_list first;
 };
 
-static void free_match_list(struct match_list_head *head)
+static void free_match_list(struct match_list_head *head, bool ft_locked)
 {
 	if (!list_empty(&head->list)) {
 		struct match_list *iter, *match_tmp;
 
 		list_del(&head->first.list);
-		tree_put_node(&head->first.g->node, false);
+		tree_put_node(&head->first.g->node, ft_locked);
 		list_for_each_entry_safe(iter, match_tmp, &head->list,
 					 list) {
-			tree_put_node(&iter->g->node, false);
+			tree_put_node(&iter->g->node, ft_locked);
 			list_del(&iter->list);
 			kfree(iter);
 		}

@@ -1573,7 +1573,8 @@ static void free_match_list(struct match
 
 static int build_match_list(struct match_list_head *match_head,
 			    struct mlx5_flow_table *ft,
-			    const struct mlx5_flow_spec *spec)
+			    const struct mlx5_flow_spec *spec,
+			    bool ft_locked)
 {
 	struct rhlist_head *tmp, *list;
 	struct mlx5_flow_group *g;

@@ -1598,7 +1599,7 @@ static int build_match_list(struct match
 
 		curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC);
 		if (!curr_match) {
-			free_match_list(match_head);
+			free_match_list(match_head, ft_locked);
 			err = -ENOMEM;
 			goto out;
 		}

@@ -1778,7 +1779,7 @@ search_again_locked:
 	version = atomic_read(&ft->node.version);
 
 	/* Collect all fgs which has a matching match_criteria */
-	err = build_match_list(&match_head, ft, spec);
+	err = build_match_list(&match_head, ft, spec, take_write);
 	if (err) {
 		if (take_write)
 			up_write_ref_node(&ft->node, false);

@@ -1792,7 +1793,7 @@ search_again_locked:
 
 	rule = try_add_to_existing_fg(ft, &match_head.list, spec, flow_act, dest,
 				      dest_num, version);
-	free_match_list(&match_head);
+	free_match_list(&match_head, take_write);
 	if (!IS_ERR(rule) ||
 	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
 		if (take_write)

@@ -45,7 +45,7 @@ void mlx5_ktls_destroy_key(struct mlx5_c
 
 static inline bool mlx5_accel_is_ktls_device(struct mlx5_core_dev *mdev)
 {
-	if (!MLX5_CAP_GEN(mdev, tls))
+	if (!MLX5_CAP_GEN(mdev, tls_tx))
 		return false;
 
 	if (!MLX5_CAP_GEN(mdev, log_max_dek))

@@ -269,7 +269,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(
 	int datalen;
 	u32 skb_seq;
 
-	if (MLX5_CAP_GEN(sq->channel->mdev, tls)) {
+	if (MLX5_CAP_GEN(sq->channel->mdev, tls_tx)) {
 		skb = mlx5e_ktls_handle_tx_skb(netdev, sq, skb, wqe, pi);
 		goto out;
 	}

@@ -239,7 +239,7 @@ int mlx5_query_hca_caps(struct mlx5_core
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, tls)) {
+	if (MLX5_CAP_GEN(dev, tls_tx)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_TLS);
 		if (err)
 			return err;

@@ -1417,14 +1417,15 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_440[0x20];
 
-	u8         tls[0x1];
-	u8         reserved_at_461[0x2];
+	u8         reserved_at_460[0x3];
 	u8         log_max_uctx[0x5];
 	u8         reserved_at_468[0x3];
 	u8         log_max_umem[0x5];
 	u8         max_num_eqs[0x10];
 
-	u8         reserved_at_480[0x3];
+	u8         reserved_at_480[0x1];
+	u8         tls_tx[0x1];
+	u8         reserved_at_482[0x1];
 	u8         log_max_l2_table[0x5];
 	u8         reserved_at_488[0x8];
 	u8         log_uar_page_sz[0x10];

@@ -38,16 +38,19 @@ int skl_hda_hdmi_add_pcm(struct snd_soc_
 	return 0;
 }
 
-SND_SOC_DAILINK_DEFS(idisp1,
-	DAILINK_COMP_ARRAY(COMP_CPU("iDisp1 Pin")),
+SND_SOC_DAILINK_DEF(idisp1_cpu,
+	DAILINK_COMP_ARRAY(COMP_CPU("iDisp1 Pin")));
+SND_SOC_DAILINK_DEF(idisp1_codec,
 	DAILINK_COMP_ARRAY(COMP_CODEC("ehdaudio0D2", "intel-hdmi-hifi1")));
 
-SND_SOC_DAILINK_DEFS(idisp2,
-	DAILINK_COMP_ARRAY(COMP_CPU("iDisp2 Pin")),
+SND_SOC_DAILINK_DEF(idisp2_cpu,
+	DAILINK_COMP_ARRAY(COMP_CPU("iDisp2 Pin")));
+SND_SOC_DAILINK_DEF(idisp2_codec,
 	DAILINK_COMP_ARRAY(COMP_CODEC("ehdaudio0D2", "intel-hdmi-hifi2")));
 
-SND_SOC_DAILINK_DEFS(idisp3,
-	DAILINK_COMP_ARRAY(COMP_CPU("iDisp3 Pin")),
+SND_SOC_DAILINK_DEF(idisp3_cpu,
+	DAILINK_COMP_ARRAY(COMP_CPU("iDisp3 Pin")));
+SND_SOC_DAILINK_DEF(idisp3_codec,
 	DAILINK_COMP_ARRAY(COMP_CODEC("ehdaudio0D2", "intel-hdmi-hifi3")));
 
 SND_SOC_DAILINK_DEF(analog_cpu,

@@ -80,21 +83,21 @@ struct snd_soc_dai_link skl_hda_be_dai_l
 		.id = 1,
 		.dpcm_playback = 1,
 		.no_pcm = 1,
-		SND_SOC_DAILINK_REG(idisp1),
+		SND_SOC_DAILINK_REG(idisp1_cpu, idisp1_codec, platform),
 	},
 	{
 		.name = "iDisp2",
 		.id = 2,
 		.dpcm_playback = 1,
 		.no_pcm = 1,
-		SND_SOC_DAILINK_REG(idisp2),
+		SND_SOC_DAILINK_REG(idisp2_cpu, idisp2_codec, platform),
 	},
 	{
 		.name = "iDisp3",
 		.id = 3,
 		.dpcm_playback = 1,
 		.no_pcm = 1,
-		SND_SOC_DAILINK_REG(idisp3),
+		SND_SOC_DAILINK_REG(idisp3_cpu, idisp3_codec, platform),
 	},
 	{
 		.name = "Analog Playback and Capture",

@@ -248,7 +248,7 @@ static const struct mfd_cell da9062_devs
 		.name		= "da9062-watchdog",
 		.num_resources	= ARRAY_SIZE(da9062_wdt_resources),
 		.resources	= da9062_wdt_resources,
-		.of_compatible  = "dlg,da9062-wdt",
+		.of_compatible  = "dlg,da9062-watchdog",
 	},
 	{
 		.name		= "da9062-thermal",

@@ -26,6 +26,7 @@ static bool rn5t618_volatile_reg(struct
 	case RN5T618_WATCHDOGCNT:
 	case RN5T618_DCIRQ:
 	case RN5T618_ILIMDATAH ... RN5T618_AIN0DATAL:
+	case RN5T618_ADCCNT3:
 	case RN5T618_IR_ADC1 ... RN5T618_IR_ADC3:
 	case RN5T618_IR_GPR:
 	case RN5T618_IR_GPF:

@@ -317,7 +317,7 @@ enum {
 #define BD70528_MASK_RTC_MINUTE		0x7f
 #define BD70528_MASK_RTC_HOUR_24H	0x80
 #define BD70528_MASK_RTC_HOUR_PM	0x20
-#define BD70528_MASK_RTC_HOUR		0x1f
+#define BD70528_MASK_RTC_HOUR		0x3f
 #define BD70528_MASK_RTC_DAY		0x3f
 #define BD70528_MASK_RTC_WEEK		0x07
 #define BD70528_MASK_RTC_MONTH		0x1f

@@ -140,6 +140,7 @@ extern void apic_soft_disable(void);
 extern void lapic_shutdown(void);
 extern void sync_Arb_IDs(void);
 extern void init_bsp_APIC(void);
+extern void apic_intr_mode_select(void);
 extern void apic_intr_mode_init(void);
 extern void init_apic_mappings(void);
 void register_lapic_address(unsigned long address);

@@ -188,6 +189,7 @@ static inline void disable_local_APIC(vo
 # define setup_secondary_APIC_clock x86_init_noop
 static inline void lapic_update_tsc_freq(void) { }
 static inline void init_bsp_APIC(void) { }
+static inline void apic_intr_mode_select(void) { }
 static inline void apic_intr_mode_init(void) { }
 static inline void lapic_assign_system_vectors(void) { }
 static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }

@@ -51,12 +51,14 @@ struct x86_init_resources {
  *				are set up.
  * @intr_init:			interrupt init code
  * @trap_init:			platform specific trap setup
+ * @intr_mode_select:		interrupt delivery mode selection
  * @intr_mode_init:		interrupt delivery mode setup
  */
 struct x86_init_irqs {
 	void (*pre_vector_init)(void);
 	void (*intr_init)(void);
 	void (*trap_init)(void);
+	void (*intr_mode_select)(void);
 	void (*intr_mode_init)(void);
 };
 

@@ -830,8 +830,17 @@ bool __init apic_needs_pit(void)
 	if (!tsc_khz || !cpu_khz)
 		return true;
 
-	/* Is there an APIC at all? */
-	if (!boot_cpu_has(X86_FEATURE_APIC))
+	/* Is there an APIC at all or is it disabled? */
+	if (!boot_cpu_has(X86_FEATURE_APIC) || disable_apic)
+		return true;
+
+	/*
+	 * If interrupt delivery mode is legacy PIC or virtual wire without
+	 * configuration, the local APIC timer wont be set up. Make sure
+	 * that the PIT is initialized.
+	 */
+	if (apic_intr_mode == APIC_PIC ||
+	    apic_intr_mode == APIC_VIRTUAL_WIRE_NO_CONFIG)
 		return true;
 
 	/* Virt guests may lack ARAT, but still have DEADLINE */

@@ -1322,7 +1331,7 @@ void __init sync_Arb_IDs(void)
 
 enum apic_intr_mode_id apic_intr_mode __ro_after_init;
 
-static int __init apic_intr_mode_select(void)
+static int __init __apic_intr_mode_select(void)
 {
 	/* Check kernel option */
 	if (disable_apic) {

@@ -1384,6 +1393,12 @@ static int __init apic_intr_mode_select(
 	return APIC_SYMMETRIC_IO;
 }
 
+/* Select the interrupt delivery mode for the BSP */
+void __init apic_intr_mode_select(void)
+{
+	apic_intr_mode = __apic_intr_mode_select();
+}
+
 /*
  * An initial setup of the virtual wire mode.
  */

@@ -1440,8 +1455,6 @@ void __init apic_intr_mode_init(void)
 {
 	bool upmode = IS_ENABLED(CONFIG_UP_LATE_INIT);
 
-	apic_intr_mode = apic_intr_mode_select();
-
 	switch (apic_intr_mode) {
 	case APIC_PIC:
 		pr_info("APIC: Keep in PIC mode(8259)\n");

@@ -91,10 +91,18 @@ void __init hpet_time_init(void)
 
 static __init void x86_late_time_init(void)
 {
+	/*
+	 * Before PIT/HPET init, select the interrupt mode. This is required
+	 * to make the decision whether PIT should be initialized correct.
+	 */
+	x86_init.irqs.intr_mode_select();
+
+	/* Setup the legacy timers */
 	x86_init.timers.timer_init();
+
 	/*
-	 * After PIT/HPET timers init, select and setup
-	 * the final interrupt mode for delivering IRQs.
+	 * After PIT/HPET timers init, set up the final interrupt mode for
+	 * delivering IRQs.
 	 */
 	x86_init.irqs.intr_mode_init();
 	tsc_init();

@@ -58,6 +58,7 @@ struct x86_init_ops x86_init __initdata
 		.pre_vector_init	= init_ISA_irqs,
 		.intr_init		= native_init_IRQ,
 		.trap_init		= x86_init_noop,
+		.intr_mode_select	= apic_intr_mode_select,
 		.intr_mode_init		= apic_intr_mode_init
 	},
 

@@ -1215,6 +1215,7 @@ asmlinkage __visible void __init xen_sta
 	x86_platform.get_nmi_reason = xen_get_nmi_reason;
 
 	x86_init.resources.memory_setup = xen_memory_setup;
+	x86_init.irqs.intr_mode_select	= x86_init_noop;
 	x86_init.irqs.intr_mode_init	= x86_init_noop;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;

index 68266928a4aa7..835abaabd67d6 100644
@@ -2016,7 +2016,7 @@ static void free_root_extent_buffers(struct btrfs_root *root)
 }
 
 /* helper to cleanup tree roots */
-static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
+static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 {
 	free_root_extent_buffers(info->tree_root);
 

@@ -2025,7 +2025,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 	free_root_extent_buffers(info->csum_root);
 	free_root_extent_buffers(info->quota_root);
 	free_root_extent_buffers(info->uuid_root);
-	if (chunk_root)
+	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 	free_root_extent_buffers(info->free_space_root);
 }

@@ -3323,7 +3323,7 @@ int open_ctree(struct super_block *sb,
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
 fail_sb_buffer:

@@ -3355,7 +3355,7 @@ int open_ctree(struct super_block *sb,
 	if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
 		goto fail_tree_roots;
 
-	free_root_pointers(fs_info, 0);
+	free_root_pointers(fs_info, false);
 
 	/* don't use the log in recovery mode, it won't be valid */
 	btrfs_set_super_log_root(disk_super, 0);

@@ -4049,7 +4049,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_free_block_groups(fs_info);
 
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
-	free_root_pointers(fs_info, 1);
+	free_root_pointers(fs_info, true);
 
 	iput(fs_info->btree_inode);
 

index 835abaabd67d6..7becc5e96f923 100644
@@ -4046,11 +4046,18 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
-	btrfs_free_block_groups(fs_info);
-
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, true);
 
+	/*
+	 * We must free the block groups after dropping the fs_roots as we could
+	 * have had an IO error and have left over tree log blocks that aren't
+	 * cleaned up until the fs roots are freed.  This makes the block group
+	 * accounting appear to be wrong because there's pending reserved bytes,
+	 * so make sure we do the block group cleanup afterwards.
+	 */
+	btrfs_free_block_groups(fs_info);
+
 	iput(fs_info->btree_inode);
 
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY

index a48a4c21b1b38..c5e9e2305fffc 100644
@@ -2694,6 +2694,7 @@ static bool drm_dp_get_vc_payload_bw(int dp_link_bw,
 int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state)
 {
 	int ret = 0;
+	int i = 0;
 	struct drm_dp_mst_branch *mstb = NULL;
 
 	mutex_lock(&mgr->lock);

@@ -2754,10 +2755,21 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 		/* this can fail if the device is gone */
 		drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, 0);
 		ret = 0;
+		mutex_lock(&mgr->payload_lock);
 		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
+		for (i = 0; i < mgr->max_payloads; i++) {
+			struct drm_dp_vcpi *vcpi = mgr->proposed_vcpis[i];
+
+			if (vcpi) {
+				vcpi->vcpi = 0;
+				vcpi->num_slots = 0;
+			}
+			mgr->proposed_vcpis[i] = NULL;
+		}
 		mgr->vcpi_mask = 0;
+		mutex_unlock(&mgr->payload_lock);
 	}
 
 out_unlock:

index 2ce9da58611ed..3644ac215567b 100644
@@ -6249,7 +6249,7 @@ static void kvm_set_mmio_spte_mask(void)
 	 * If reserved bit is not supported, clear the present bit to disable
 	 * mmio page fault.
 	 */
-	if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52)
+	if (shadow_phys_bits == 52)
 		mask &= ~1ull;
 
 	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);

index 3644ac215567b..d05c10651398f 100644
@@ -538,16 +538,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 static u8 kvm_get_shadow_phys_bits(void)
 {
 	/*
-	 * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
-	 * in CPU detection code, but MKTME treats those reduced bits as
-	 * 'keyID' thus they are not reserved bits. Therefore for MKTME
-	 * we should still return physical address bits reported by CPUID.
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+	 * in CPU detection code, but the processor treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+	 * the physical address bits reported by CPUID.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_TME) ||
-	    WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
-		return boot_cpu_data.x86_phys_bits;
+	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+		return cpuid_eax(0x80000008) & 0xff;
 
-	return cpuid_eax(0x80000008) & 0xff;
+	/*
+	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+	 * custom CPUID.  Proceed with whatever the kernel found since these features
+	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+	 */
+	return boot_cpu_data.x86_phys_bits;
 }
 
 static void kvm_mmu_reset_all_pte_masks(void)

index 10434cf402dee..c1ed054c103c3 100644
@@ -380,12 +380,12 @@ struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
-	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+	int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
 			  bool prefault);
 	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
 				  struct x86_exception *fault);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
-			    struct x86_exception *exception);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
+			    u32 access, struct x86_exception *exception);
 	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
 			       struct x86_exception *exception);
 	int (*sync_page)(struct kvm_vcpu *vcpu,

@@ -1451,7 +1451,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);

214 lines not on this page · raw message

index 7ca8831c7d1a2..3c6522b84ff11 100644
@@ -249,13 +249,13 @@ TRACE_EVENT(
 
 TRACE_EVENT(
 	fast_page_fault,
-	TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+	TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,
 		 u64 *sptep, u64 old_spte, bool retry),
-	TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry),
+	TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry),
 
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
-		__field(gva_t, gva)
+		__field(gpa_t, cr2_or_gpa)
 		__field(u32, error_code)
 		__field(u64 *, sptep)
 		__field(u64, old_spte)

@@ -265,7 +265,7 @@ TRACE_EVENT(
 
 	TP_fast_assign(
 		__entry->vcpu_id = vcpu->vcpu_id;
-		__entry->gva = gva;
+		__entry->cr2_or_gpa = cr2_or_gpa;
 		__entry->error_code = error_code;
 		__entry->sptep = sptep;
 		__entry->old_spte = old_spte;

@@ -273,9 +273,9 @@ TRACE_EVENT(
 		__entry->retry = retry;
 	),
 
-	TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx"
+	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
 		  " new %llx spurious %d fixed %d", __entry->vcpu_id,
-		  __entry->gva, __print_flags(__entry->error_code, "|",
+		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
 		  kvm_mmu_trace_pferr_flags), __entry->sptep,
 		  __entry->old_spte, __entry->new_spte,
 		  __spte_satisfied(old_spte), __spte_satisfied(new_spte)

index 97b21e7fd013d..c1d7b866a03fa 100644
@@ -291,11 +291,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
 }
 
 /*
- * Fetch a guest pte for a guest virtual address
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
  */
 static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				    gva_t addr, u32 access)
+				    gpa_t addr, u32 access)
 {
 	int ret;
 	pt_element_t pte;

@@ -496,7 +496,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 }
 
 static int FNAME(walk_addr)(struct guest_walker *walker,
-			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
+			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
 {
 	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);

@@ -611,7 +611,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * If the guest tries to write a write-protected page, we need to
  * emulate this operation, return 1 to indicate this case.
  */
-static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
 			 kvm_pfn_t pfn, bool map_writable, bool prefault,

@@ -765,7 +765,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;

@@ -945,18 +945,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 

@@ -964,7 +965,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 }
 
 #if PTTYPE != PTTYPE_EPT
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
+/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
+static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
 {

@@ -972,6 +974,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit GVA should be impossible on 32-bit KVM. */
+	WARN_ON_ONCE(vaddr >> 32);
+#endif
+
 	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
 
 	if (r) {

index 92e025d1b5175..edde5ee8c6f50 100644
@@ -6409,11 +6409,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 	return 1;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  bool write_fault_to_shadow_pgtable,
 				  int emulation_type)
 {
-	gpa_t gpa = cr2;
+	gpa_t gpa = cr2_or_gpa;
 	kvm_pfn_t pfn;
 
 	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))

@@ -6427,7 +6427,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
 		 */
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 		/*
 		 * If the mapping is invalid in guest, let cpu retry

@@ -6484,10 +6484,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
-			      unsigned long cr2,  int emulation_type)
+			      gpa_t cr2_or_gpa,  int emulation_type)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;
 
 	last_retry_eip = vcpu->arch.last_retry_eip;
 	last_retry_addr = vcpu->arch.last_retry_addr;

@@ -6516,14 +6516,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	if (x86_page_table_writing_insn(ctxt))
 		return false;
 
-	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
 		return false;
 
 	vcpu->arch.last_retry_eip = ctxt->eip;
-	vcpu->arch.last_retry_addr = cr2;
+	vcpu->arch.last_retry_addr = cr2_or_gpa;
 
 	if (!vcpu->arch.mmu->direct_map)
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 

@@ -6669,11 +6669,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
 	return false;
 }
 
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			    unsigned long cr2,
-			    int emulation_type,
-			    void *insn,
-			    int insn_len)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			    int emulation_type, void *insn, int insn_len)
 {
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;

@@ -6719,8 +6716,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 				kvm_queue_exception(vcpu, UD_VECTOR);
 				return 1;
 			}
-			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
-						emulation_type))
+			if (reexecute_instruction(vcpu, cr2_or_gpa,
+						  write_fault_to_spt,
+						  emulation_type))
 				return 1;
 			if (ctxt->have_exception) {
 				/*

@@ -6754,7 +6752,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		return 1;
 	}
 
-	if (retry_instruction(ctxt, cr2, emulation_type))
+	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
 		return 1;
 
 	/* this is needed for vmware backdoor interface to work since it

@@ -6766,7 +6764,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 restart:
 	/* Save the faulting GPA (cr2) in the address field */
-	ctxt->exception.address = cr2;
+	ctxt->exception.address = cr2_or_gpa;
 
 	r = x86_emulate_insn(ctxt);
 

@@ -6774,7 +6772,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		return 1;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
 					emulation_type))
 			return 1;
 

@@ -10051,7 +10049,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)

@@ -10164,7 +10162,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
 	if (kvm_can_deliver_async_pf(vcpu) &&

@@ -10199,7 +10197,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
 
 	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
 	    !apf_get_user(vcpu, &val)) {

index dbf7442a822b6..de6b55484876a 100644
@@ -286,7 +286,7 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
 bool kvm_vector_hashing_enabled(void);
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \

index abfc2fbde957c..7d1564c408972 100644
@@ -204,7 +204,7 @@ struct kvm_async_pf {
 	struct list_head queue;
 	struct kvm_vcpu *vcpu;
 	struct mm_struct *mm;
-	gva_t gva;
+	gpa_t cr2_or_gpa;
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
 	bool   wakeup_all;

@@ -212,8 +212,8 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
-		       struct kvm_arch_async_pf *arch);
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+		       unsigned long hva, struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 

index 35305d6e68cc6..d8ef708a2ef67 100644
@@ -64,7 +64,7 @@ static void async_pf_execute(struct work_struct *work)
 	struct mm_struct *mm = apf->mm;
 	struct kvm_vcpu *vcpu = apf->vcpu;
 	unsigned long addr = apf->addr;
-	gva_t gva = apf->gva;
+	gpa_t cr2_or_gpa = apf->cr2_or_gpa;
 	int locked = 1;
 
 	might_sleep();

@@ -92,7 +92,7 @@ static void async_pf_execute(struct work_struct *work)
 	 * this point
 	 */
 
-	trace_kvm_async_pf_completed(addr, gva);
+	trace_kvm_async_pf_completed(addr, cr2_or_gpa);
 
 	if (swq_has_sleeper(&vcpu->wq))
 		swake_up_one(&vcpu->wq);

@@ -165,8 +165,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
-		       struct kvm_arch_async_pf *arch)
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+		       unsigned long hva, struct kvm_arch_async_pf *arch)
 {
 	struct kvm_async_pf *work;
 

@@ -185,7 +185,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 
 	work->wakeup_all = false;
 	work->vcpu = vcpu;
-	work->gva = gva;
+	work->cr2_or_gpa = cr2_or_gpa;
 	work->addr = hva;
 	work->arch = *arch;
 	work->mm = current->mm;

index d7aa34bb318a5..46070da9e08f8 100644
@@ -418,22 +418,24 @@ static inline bool is_access_track_spte(u64 spte)
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(18, 0)
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(17, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
 #define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
 						    MMIO_SPTE_GEN_LOW_START)
 
-#define MMIO_SPTE_GEN_HIGH_START	52
-#define MMIO_SPTE_GEN_HIGH_END		61
+#define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
+#define MMIO_SPTE_GEN_HIGH_END		62
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
+
 static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
+	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
 	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
 	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;

@@ -444,8 +446,6 @@ static u64 get_mmio_spte_generation(u64 spte)
 {
 	u64 gen;
 
-	spte &= ~shadow_mmio_mask;
-
 	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
 	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
 	return gen;

index d0523741fb037..931d3b5f3acd4 100644
@@ -4663,8 +4663,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 				vmx_instruction_info, true, len, &gva))
 			return 1;
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
-		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) {
 			kvm_inject_page_fault(vcpu, &e);
+			return 1;
+		}
 	}
 
 	return nested_vmx_succeed(vcpu);

index 5a3373e06e60b..235d57d6c205e 100644
@@ -638,7 +638,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 	if (1ull << kvm_eq.qshift > page_size) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
 		pr_warn("Incompatible host page size %lx!\n", page_size);

index 46070da9e08f8..518100ea5ef47 100644
@@ -1286,12 +1286,12 @@ static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
 }
 
-static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
+static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	unsigned long page_size;
 	int i, ret = 0;
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 
 	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		if (page_size >= KVM_HPAGE_SIZE(i))

@@ -1341,7 +1341,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
 	if (unlikely(*force_pt_level))
 		return PT_PAGE_TABLE_LEVEL;
 
-	host_level = host_mapping_level(vcpu->kvm, large_gfn);
+	host_level = host_mapping_level(vcpu, large_gfn);
 
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;

index 7d1564c408972..b81f0f1ded5f9 100644
@@ -751,7 +751,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);

index 6f0287ad927ee..877ce955b99cf 100644
@@ -1394,14 +1394,14 @@ bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, size;
 
 	size = PAGE_SIZE;
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
 	if (kvm_is_error_hva(addr))
 		return PAGE_SIZE;
 

index 877ce955b99cf..b5ea1bafe513c 100644
@@ -1401,7 +1401,7 @@ unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 
 	size = PAGE_SIZE;
 
-	addr = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+	addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return PAGE_SIZE;
 

@@ -350,9 +350,14 @@ smb2_reconnect(__le16 smb2_command, stru
 	}
 
 	rc = cifs_negotiate_protocol(0, tcon->ses);
-	if (!rc && tcon->ses->need_reconnect)
+	if (!rc && tcon->ses->need_reconnect) {
 		rc = cifs_setup_session(0, tcon->ses, nls_codepage);
-
+		if ((rc == -EACCES) && !tcon->retry) {
+			rc = -EHOSTDOWN;
+			mutex_unlock(&tcon->ses->session_mutex);
+			goto failed;
+		}
+	}
 	if (rc || !tcon->need_reconnect) {
 		mutex_unlock(&tcon->ses->session_mutex);
 		goto out;

@@ -397,6 +402,7 @@ out:
 	case SMB2_SET_INFO:
 		rc = -EAGAIN;
 	}
+failed:
 	unload_nls(nls_codepage);
 	return rc;
 }

@@ -174,7 +174,8 @@ cifs_fill_common_info(struct cifs_fattr
 	 * may look wrong since the inodes may not have timed out by the time
 	 * "ls" does a stat() call on them.
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
+	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
+	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID))
 		fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL &&

@@ -174,7 +174,8 @@ cifs_fill_common_info(struct cifs_fattr
 	 * may look wrong since the inodes may not have timed out by the time
 	 * "ls" does a stat() call on them.
 	 */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
+	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) ||
+	    (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID))
 		fattr->cf_flags |= CIFS_FATTR_NEED_REVAL;
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL &&

@@ -454,6 +454,14 @@ static inline void ack_APIC_irq(void)
 	apic_eoi();
 }
 
+
+static inline bool lapic_vector_set_in_irr(unsigned int vector)
+{
+	u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+
+	return !!(irr & (1U << (vector % 32)));
+}
+
 static inline unsigned default_get_apic_id(unsigned long x)
 {
 	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));

153 lines not on this page · raw message

@@ -209,6 +209,8 @@ struct irq_data {
  * IRQD_SINGLE_TARGET		- IRQ allows only a single affinity target
  * IRQD_DEFAULT_TRIGGER_SET	- Expected trigger already been set
  * IRQD_CAN_RESERVE		- Can use reservation mode
+ * IRQD_MSI_NOMASK_QUIRK	- Non-maskable MSI quirk for affinity change
+ *				  required
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,

@@ -231,6 +233,7 @@ enum {
 	IRQD_SINGLE_TARGET		= (1 << 24),
 	IRQD_DEFAULT_TRIGGER_SET	= (1 << 25),
 	IRQD_CAN_RESERVE		= (1 << 26),
+	IRQD_MSI_NOMASK_QUIRK		= (1 << 27),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)

@@ -390,6 +393,21 @@ static inline bool irqd_can_reserve(stru
 	return __irqd_to_state(d) & IRQD_CAN_RESERVE;
 }
 
+static inline void irqd_set_msi_nomask_quirk(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK;
+}
+
+static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d)
+{
+	__irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK;
+}
+
+static inline bool irqd_msi_nomask_quirk(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK;
+}
+
 #undef __irqd_to_state
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)

@@ -206,6 +206,13 @@ enum {
 	IRQ_DOMAIN_FLAG_MSI_REMAP	= (1 << 5),
 
 	/*
+	 * Quirk to handle MSI implementations which do not provide
+	 * masking. Currently known to affect x86, but partially
+	 * handled in core code.
+	 */
+	IRQ_DOMAIN_MSI_NOMASK_QUIRK	= (1 << 6),
+
+	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
 	 * core code.

@@ -114,6 +114,7 @@ static const struct irq_bit_descr irqdat
 	BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
 	BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
 	BIT_MASK_DESCR(IRQD_CAN_RESERVE),
+	BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK),
 
 	BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
 

@@ -453,8 +453,11 @@ int msi_domain_alloc_irqs(struct irq_dom
 			continue;
 
 		irq_data = irq_domain_get_irq_data(domain, desc->irq);
-		if (!can_reserve)
+		if (!can_reserve) {
 			irqd_clr_can_reserve(irq_data);
+			if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
+				irqd_set_msi_nomask_quirk(irq_data);
+		}
 		ret = irq_domain_activate_irq(irq_data, can_reserve);
 		if (ret)
 			goto cleanup;

@@ -293,8 +293,15 @@ static void clocksource_watchdog(struct
 	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
 	if (next_cpu >= nr_cpu_ids)
 		next_cpu = cpumask_first(cpu_online_mask);
-	watchdog_timer.expires += WATCHDOG_INTERVAL;
-	add_timer_on(&watchdog_timer, next_cpu);
+
+	/*
+	 * Arm timer if not already pending: could race with concurrent
+	 * pair clocksource_stop_watchdog() clocksource_start_watchdog().
+	 */
+	if (!timer_pending(&watchdog_timer)) {
+		watchdog_timer.expires += WATCHDOG_INTERVAL;
+		add_timer_on(&watchdog_timer, next_cpu);
+	}
 out:
 	spin_unlock(&watchdog_lock);
 }

@@ -5823,7 +5823,15 @@ accounting:
 	 */
 	user_lock_limit *= num_online_cpus();
 
-	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
+	user_locked = atomic_long_read(&user->locked_vm);
+
+	/*
+	 * sysctl_perf_event_mlock may have changed, so that
+	 *     user->locked_vm > user_lock_limit
+	 */
+	if (user_locked > user_lock_limit)
+		user_locked = user_lock_limit;
+	user_locked += user_extra;
 
 	if (user_locked <= user_lock_limit) {
 		/* charge all to locked_vm */

index c0b3154f7a7e1..19e141eeed17d 100644
@@ -171,8 +171,6 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
 
 	_enter("%d,%x", conn->debug_id, call->cid);
 
-	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
-
 	if (rcu_access_pointer(chan->call) == call) {
 		/* Save the result of the call so that we can repeat it if necessary
 		 * through the channel, whilst disposing of the actual call record.

@@ -225,6 +223,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	__rxrpc_disconnect_call(conn, call);
 	spin_unlock(&conn->channel_lock);
 
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 	conn->idle_timestamp = jiffies;
 }
 

index 2c89d886595cb..6a92fd3105a31 100644
@@ -596,7 +596,7 @@ regulator_bulk_set_supply_names(struct regulator_bulk_data *consumers,
 }
 
 static inline bool
-regulator_is_equal(struct regulator *reg1, struct regulator *reg2);
+regulator_is_equal(struct regulator *reg1, struct regulator *reg2)
 {
 	return false;
 }

index d88008c8eb852..91c8f1d9bceef 100644
@@ -102,11 +102,13 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 	isync();	/* Context sync required after mtsrin() */
 }
 
-static inline void allow_user_access(void __user *to, const void __user *from, u32 size)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      u32 size, unsigned long dir)
 {
 	u32 addr, end;
 
-	if (__builtin_constant_p(to) && to == NULL)
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (!(dir & KUAP_WRITE))
 		return;
 
 	addr = (__force u32)to;

@@ -119,11 +121,16 @@ static inline void allow_user_access(void __user *to, const void __user *from, u
 	kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end);	/* Clear Ks */
 }
 
-static inline void prevent_user_access(void __user *to, const void __user *from, u32 size)
+static __always_inline void prevent_user_access(void __user *to, const void __user *from,
+						u32 size, unsigned long dir)
 {
 	u32 addr = (__force u32)to;
 	u32 end = min(addr + size, TASK_SIZE);
 
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (!(dir & KUAP_WRITE))
+		return;
+
 	if (!addr || addr >= TASK_SIZE || !size)
 		return;
 

index dbbd22cb80f5a..c8d1076e0ebbf 100644
@@ -77,20 +77,21 @@ static inline void set_kuap(unsigned long value)
 	isync();
 }
 
-static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir)
 {
 	// This is written so we can resolve to a single case at build time
-	if (__builtin_constant_p(to) && to == NULL)
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (dir == KUAP_READ)
 		set_kuap(AMR_KUAP_BLOCK_WRITE);
-	else if (__builtin_constant_p(from) && from == NULL)
+	else if (dir == KUAP_WRITE)
 		set_kuap(AMR_KUAP_BLOCK_READ);
 	else
 		set_kuap(0);
 }
 
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size)
+				       unsigned long size, unsigned long dir)
 {
 	set_kuap(AMR_KUAP_BLOCKED);
 }

index 812e66f31934f..94f24928916a8 100644
@@ -2,6 +2,10 @@
 #ifndef _ASM_POWERPC_KUP_H_
 #define _ASM_POWERPC_KUP_H_
 
+#define KUAP_READ	1
+#define KUAP_WRITE	2
+#define KUAP_READ_WRITE	(KUAP_READ | KUAP_WRITE)
+
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/kup-radix.h>
 #endif

@@ -42,9 +46,9 @@ void setup_kuap(bool disabled);
 #else
 static inline void setup_kuap(bool disabled) { }
 static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size) { }
+				     unsigned long size, unsigned long dir) { }
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size) { }
+				       unsigned long size, unsigned long dir) { }
 static inline bool
 bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {

@@ -54,24 +58,36 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 
 static inline void allow_read_from_user(const void __user *from, unsigned long size)
 {
-	allow_user_access(NULL, from, size);
+	allow_user_access(NULL, from, size, KUAP_READ);
 }
 
 static inline void allow_write_to_user(void __user *to, unsigned long size)
 {
-	allow_user_access(to, NULL, size);
+	allow_user_access(to, NULL, size, KUAP_WRITE);
+}
+
+static inline void allow_read_write_user(void __user *to, const void __user *from,
+					 unsigned long size)
+{
+	allow_user_access(to, from, size, KUAP_READ_WRITE);
 }
 
 static inline void prevent_read_from_user(const void __user *from, unsigned long size)
 {
-	prevent_user_access(NULL, from, size);
+	prevent_user_access(NULL, from, size, KUAP_READ);
 }
 
 static inline void prevent_write_to_user(void __user *to, unsigned long size)
 {
-	prevent_user_access(to, NULL, size);
+	prevent_user_access(to, NULL, size, KUAP_WRITE);
+}
+
+static inline void prevent_read_write_user(void __user *to, const void __user *from,
+					   unsigned long size)
+{
+	prevent_user_access(to, from, size, KUAP_READ_WRITE);
 }
 
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _ASM_POWERPC_KUP_H_ */
+#endif /* _ASM_POWERPC_KUAP_H_ */

index 9d1fe811aa5d6..6fe97465e350b 100644
@@ -34,13 +34,13 @@
 #include <asm/reg.h>
 
 static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size)
+				     unsigned long size, unsigned long dir)
 {
 	mtspr(SPRN_MD_AP, MD_APG_INIT);
 }
 
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size)
+				       unsigned long size, unsigned long dir)
 {
 	mtspr(SPRN_MD_AP, MD_APG_KUAP);
 }

index c92fe7fe9692c..cafad1960e766 100644
@@ -313,9 +313,9 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 	unsigned long ret;
 
 	barrier_nospec();
-	allow_user_access(to, from, n);
+	allow_read_write_user(to, from, n);
 	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(to, from, n);
+	prevent_read_write_user(to, from, n);
 	return ret;
 }
 #endif /* __powerpc64__ */