Merge 4.13-rc5 into char-misc-next

We want the firmware, and other changes, in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

52 files changed, 276 insertions, 167 deletions

diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index d4b72944ccda..1e3a74f94131 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -3,6 +3,7 @@
 
 #ifdef CONFIG_ACPI_NUMA
 #include <linux/kernel.h>
+#include <linux/numa.h>
 
 /* Proximity bitmap length */
 #if MAX_NUMNODES > 256
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 8afa4335e5b2..faddde44de8c 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -112,10 +112,11 @@ struct mmu_gather {
 
 #define HAVE_GENERIC_MMU_GATHER
 
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end);
+void arch_tlb_gather_mmu(struct mmu_gather *tlb,
+	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
-void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
-							unsigned long end);
+void arch_tlb_finish_mmu(struct mmu_gather *tlb,
+			 unsigned long start, unsigned long end, bool force);
 extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 				   int page_size);
 
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index f6e030617467..f87fe20fcb05 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -48,7 +48,6 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val);
-void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu);
 bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu);
@@ -86,7 +85,6 @@ static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_disable_counter(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_enable_counter(struct kvm_vcpu *vcpu, u64 val) {}
-static inline void kvm_pmu_overflow_set(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {}
 static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu)
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index c749eef1daa1..27b4b6615263 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1209,6 +1209,7 @@ static inline bool acpi_has_watchdog(void) { return false; }
 #endif
 
 #ifdef CONFIG_ACPI_SPCR_TABLE
+extern bool qdf2400_e44_present;
 int parse_spcr(bool earlycon);
 #else
 static inline int parse_spcr(bool earlycon) { return 0; }
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index c6d96a5f46fd..adf670ecaf94 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -148,6 +148,7 @@ struct ceph_osd_request_target {
 	int size;
 	int min_size;
 	bool sort_bitwise;
+	bool recovery_deletes;
 
 	unsigned int flags;                /* CEPH_OSD_FLAG_* */
 	bool paused;
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index a0996cb9faed..af3444a5bfdd 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -272,6 +272,8 @@ bool ceph_is_new_interval(const struct ceph_osds *old_acting,
 			  u32 new_pg_num,
 			  bool old_sort_bitwise,
 			  bool new_sort_bitwise,
+			  bool old_recovery_deletes,
+			  bool new_recovery_deletes,
 			  const struct ceph_pg *pgid);
 bool ceph_osds_changed(const struct ceph_osds *old_acting,
 		       const struct ceph_osds *new_acting,
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 385db08bb8b2..b8281feda9c7 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -158,6 +158,10 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSDMAP_NOTIERAGENT (1<<13) /* disable tiering agent */
 #define CEPH_OSDMAP_NOREBALANCE (1<<14) /* block osd backfill unless pg is degraded */
 #define CEPH_OSDMAP_SORTBITWISE (1<<15) /* use bitwise hobject_t sort */
+#define CEPH_OSDMAP_REQUIRE_JEWEL    (1<<16) /* require jewel for booting osds */
+#define CEPH_OSDMAP_REQUIRE_KRAKEN   (1<<17) /* require kraken for booting osds */
+#define CEPH_OSDMAP_REQUIRE_LUMINOUS (1<<18) /* require l for booting osds */
+#define CEPH_OSDMAP_RECOVERY_DELETES (1<<19) /* deletes performed during recovery instead of peering */
 
 /*
  * The error code to return when an OSD can't handle a write
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index b56573bf440d..82b30e638430 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -39,8 +39,6 @@ enum cpuhp_state {
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_INTEL_DEAD,
 	CPUHP_LUSTRE_CFS_DEAD,
-	CPUHP_SCSI_BNX2FC_DEAD,
-	CPUHP_SCSI_BNX2I_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 119a3f9604b0..898cfe2eeb42 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -18,6 +18,19 @@
 
 #ifdef CONFIG_CPUSETS
 
+/*
+ * Static branch rewrites can happen in an arbitrary order for a given
+ * key. In code paths where we need to loop with read_mems_allowed_begin() and
+ * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need
+ * to ensure that begin() always gets rewritten before retry() in the
+ * disabled -> enabled transition. If not, then if local irqs are disabled
+ * around the loop, we can deadlock since retry() would always be
+ * comparing the latest value of the mems_allowed seqcount against 0 as
+ * begin() still would see cpusets_enabled() as false. The enabled -> disabled
+ * transition should happen in reverse order for the same reasons (want to stop
+ * looking at real value of mems_allowed.sequence in retry() first).
+ */
+extern struct static_key_false cpusets_pre_enable_key;
 extern struct static_key_false cpusets_enabled_key;
 static inline bool cpusets_enabled(void)
 {
@@ -32,12 +45,14 @@ static inline int nr_cpusets(void)
 
 static inline void cpuset_inc(void)
 {
+	static_branch_inc(&cpusets_pre_enable_key);
 	static_branch_inc(&cpusets_enabled_key);
 }
 
 static inline void cpuset_dec(void)
 {
 	static_branch_dec(&cpusets_enabled_key);
+	static_branch_dec(&cpusets_pre_enable_key);
 }
 
 extern int cpuset_init(void);
@@ -115,7 +130,7 @@ extern void cpuset_print_current_mems_allowed(void);
  */
 static inline unsigned int read_mems_allowed_begin(void)
 {
-	if (!cpusets_enabled())
+	if (!static_branch_unlikely(&cpusets_pre_enable_key))
 		return 0;
 
 	return read_seqcount_begin(&current->mems_allowed_seq);
@@ -129,7 +144,7 @@ static inline unsigned int read_mems_allowed_begin(void)
  */
 static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	if (!cpusets_enabled())
+	if (!static_branch_unlikely(&cpusets_enabled_key))
 		return false;
 
 	return read_seqcount_retry(&current->mems_allowed_seq, seq);
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 92e165d417a6..07eed95e10c7 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -193,7 +193,7 @@ struct crush_choose_arg {
 struct crush_choose_arg_map {
 #ifdef __KERNEL__
 	struct rb_node node;
-	u64 choose_args_index;
+	s64 choose_args_index;
 #endif
 	struct crush_choose_arg *args; /*!< replacement for each bucket
                                             in the crushmap */
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 794811875732..df97b7af7e2c 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -87,6 +87,7 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t size);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
+bool dax_write_cache_enabled(struct dax_device *dax_dev);
 
 /*
  * We use lowest available bit in exceptional entry for locking, one bit for
diff --git a/include/linux/device.h b/include/linux/device.h
index 723cd54b94da..beabdbc08420 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -843,7 +843,7 @@ struct dev_links_info {
  * 		hibernation, system resume and during runtime PM transitions
  * 		along with subsystem-level and driver-level callbacks.
  * @pins:	For device pin management.
- *		See Documentation/pinctrl.txt for details.
+ *		See Documentation/driver-api/pinctl.rst for details.
  * @msi_list:	Hosts MSI descriptors
  * @msi_domain: The generic MSI domain this device is using.
  * @numa_node:	NUMA node this device is close to.
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 843ab866e0f4..03c0196a6f24 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -157,16 +157,40 @@ static inline int is_device_dma_capable(struct device *dev)
  * These three functions are only for dma allocator.
  * Don't use them in device drivers.
  */
-int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
 				       dma_addr_t *dma_handle, void **ret);
-int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
 
-int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
 			    void *cpu_addr, size_t size, int *ret);
+
+void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle);
+int dma_release_from_global_coherent(int order, void *vaddr);
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
+				  size_t size, int *ret);
+
 #else
-#define dma_alloc_from_coherent(dev, size, handle, ret) (0)
-#define dma_release_from_coherent(dev, order, vaddr) (0)
-#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
+#define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_dev_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
+
+static inline void *dma_alloc_from_global_coherent(ssize_t size,
+						   dma_addr_t *dma_handle)
+{
+	return NULL;
+}
+
+static inline int dma_release_from_global_coherent(int order, void *vaddr)
+{
+	return 0;
+}
+
+static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
+						void *cpu_addr, size_t size,
+						int *ret)
+{
+	return 0;
+}
 #endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
 
 #ifdef CONFIG_HAS_DMA
@@ -481,7 +505,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 
 	BUG_ON(!ops);
 
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr))
+	if (dma_alloc_from_dev_coherent(dev, size, dma_handle, &cpu_addr))
 		return cpu_addr;
 
 	if (!arch_dma_alloc_attrs(&dev, &flag))
@@ -503,7 +527,7 @@ static inline void dma_free_attrs(struct device *dev, size_t size,
 	BUG_ON(!ops);
 	WARN_ON(irqs_disabled());
 
-	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
+	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
 		return;
 
 	if (!ops->free || !cpu_addr)
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 00ca5b86a753..d501d3956f13 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -689,7 +689,8 @@ i2c_unlock_adapter(struct i2c_adapter *adapter)
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
 #define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
 #define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
-#define I2C_CLASS_DEPRECATED	(1<<8)	/* Warn users that adapter will stop using classes */
+/* Warn users that the adapter doesn't support classes anymore */
+#define I2C_CLASS_DEPRECATED	(1<<8)
 
 /* Internal numbers to terminate lists */
 #define I2C_CLIENT_END		0xfffeU
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 497f2b3a5a62..97f1b465d04f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -105,6 +105,11 @@ struct st_sensor_fullscale {
 	struct st_sensor_fullscale_avl fs_avl[ST_SENSORS_FULLSCALE_AVL_MAX];
 };
 
+struct st_sensor_sim {
+	u8 addr;
+	u8 value;
+};
+
 /**
  * struct st_sensor_bdu - ST sensor device block data update
  * @addr: address of the register.
@@ -197,6 +202,7 @@ struct st_sensor_transfer_function {
  * @bdu: Block data update register.
  * @das: Data Alignment Selection register.
  * @drdy_irq: Data ready register of the sensor.
+ * @sim: SPI serial interface mode register of the sensor.
  * @multi_read_bit: Use or not particular bit for [I2C/SPI] multi-read.
  * @bootime: samples to discard when sensor passing from power-down to power-up.
  */
@@ -213,6 +219,7 @@ struct st_sensor_settings {
 	struct st_sensor_bdu bdu;
 	struct st_sensor_das das;
 	struct st_sensor_data_ready_irq drdy_irq;
+	struct st_sensor_sim sim;
 	bool multi_read_bit;
 	unsigned int bootime;
 };
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index e1b442996f81..474d6bbc158c 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -128,6 +128,7 @@ struct inet6_skb_parm {
 #define IP6SKB_FRAGMENTED      16
 #define IP6SKB_HOPBYHOP        32
 #define IP6SKB_L3SLAVE         64
+#define IP6SKB_JUMBOGRAM      128
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
@@ -152,6 +153,11 @@ static inline int inet6_iif(const struct sk_buff *skb)
 	return l3_slave ? skb->skb_iif : IP6CB(skb)->iif;
 }
 
+static inline bool inet6_is_jumbogram(const struct sk_buff *skb)
+{
+	return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM);
+}
+
 /* can not be used in TCP layer after tcp_v6_fill_cb */
 static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
 {
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 00db35b61e9e..d2d543794093 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -388,7 +388,12 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_mask_ack:	ack and mask an interrupt source
  * @irq_unmask:		unmask an interrupt source
  * @irq_eoi:		end of interrupt
- * @irq_set_affinity:	set the CPU affinity on SMP machines
+ * @irq_set_affinity:	Set the CPU affinity on SMP machines. If the force
+ *			argument is true, it tells the driver to
+ *			unconditionally apply the affinity setting. Sanity
+ *			checks against the supplied affinity mask are not
+ *			required. This is used for CPU hotplug where the
+ *			target CPU is not yet set in the cpu_online_mask.
  * @irq_retrigger:	resend an IRQ to the CPU
  * @irq_set_type:	set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
  * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 4fec8b775895..82e197eeac91 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -15,7 +15,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
  * @threadfn: the function to run in the thread
  * @data: data pointer for @threadfn()
  * @namefmt: printf-style format string for the thread name
- * @...: arguments for @namefmt.
+ * @arg...: arguments for @namefmt.
  *
  * This macro will create a kthread on the current node, leaving it in
  * the stopped state.  This is just a helper for kthread_create_on_node();
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 648b34cabb38..21a6fd6c44af 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -445,6 +445,7 @@ struct kvm {
 	struct kvm_stat_data **debugfs_stat_data;
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
+	pid_t userspace_pid;
 };
 
 #define kvm_err(fmt, ...) \
@@ -476,7 +477,8 @@ struct kvm {
 static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
 {
 	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
-				      lockdep_is_held(&kvm->slots_lock));
+				      lockdep_is_held(&kvm->slots_lock) ||
+				      !refcount_read(&kvm->users_count));
 }
 
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
@@ -569,7 +571,8 @@ void kvm_put_kvm(struct kvm *kvm);
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
-			lockdep_is_held(&kvm->slots_lock));
+			lockdep_is_held(&kvm->slots_lock) ||
+			!refcount_read(&kvm->users_count));
 }
 
 static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 55de3da58b1c..931c32f1f18d 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -435,7 +435,7 @@ enum {
 	ATA_HORKAGE_NOLPM	= (1 << 20),	/* don't use LPM */
 	ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21),	/* some WDs have broken LPM */
 	ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */
-	ATA_HORKAGE_NO_NCQ_LOG	= (1 << 23),	/* don't use NCQ for log read */
+	ATA_HORKAGE_NO_DMA_LOG	= (1 << 23),	/* don't use DMA for log read */
 	ATA_HORKAGE_NOTRIM	= (1 << 24),	/* don't use TRIM */
 	ATA_HORKAGE_MAX_SEC_1024 = (1 << 25),	/* Limit max sects to 1024 */
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index aad5d81dfb44..b54517c05e9a 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -620,6 +620,7 @@ struct mlx4_caps {
 	u32			dmfs_high_rate_qpn_base;
 	u32			dmfs_high_rate_qpn_range;
 	u32			vf_caps;
+	bool			wol_port[MLX4_MAX_PORTS + 1];
 	struct mlx4_rate_limit_caps rl_caps;
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 87869c04849a..3030121b4746 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -7749,8 +7749,10 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x7f];
+	u8         reserved_at_0[0x7d];
 
+	u8         mtpps_enh_out_per_adj[0x1];
+	u8         mtpps_fs[0x1];
 	u8         pcie_performance_group[0x1];
 };
 
@@ -8159,7 +8161,8 @@ struct mlx5_ifc_mtpps_reg_bits {
 	u8         reserved_at_78[0x4];
 	u8         cap_pin_4_mode[0x4];
 
-	u8         reserved_at_80[0x80];
+	u8         field_select[0x20];
+	u8         reserved_at_a0[0x60];
 
 	u8         enable[0x1];
 	u8         reserved_at_101[0xb];
@@ -8174,8 +8177,9 @@ struct mlx5_ifc_mtpps_reg_bits {
 
 	u8         out_pulse_duration[0x10];
 	u8         out_periodic_adjustment[0x10];
+	u8         enhanced_out_periodic_adjustment[0x20];
 
-	u8         reserved_at_1a0[0x60];
+	u8         reserved_at_1c0[0x20];
 };
 
 struct mlx5_ifc_mtppse_reg_bits {
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 6f41270d80c0..f378dc0e7eaf 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg {
 #define MLX5_WQE_CTRL_OPCODE_MASK 0xff
 #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00
 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8
-#define MLX5_WQE_AV_EXT 0x80000000
 
 enum {
 	MLX5_ETH_WQE_L3_INNER_CSUM      = 1 << 4,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ff151814a02d..3cadee0a3508 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -487,13 +487,15 @@ struct mm_struct {
 	/* numa_scan_seq prevents two threads setting pte_numa */
 	int numa_scan_seq;
 #endif
-#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
 	/*
 	 * An operation with batched TLB flushing is going on. Anything that
 	 * can move process memory needs to flush the TLB when moving a
 	 * PROT_NONE or PROT_NUMA mapped page.
 	 */
-	bool tlb_flush_pending;
+	atomic_t tlb_flush_pending;
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	/* See flush_tlb_batched_pending() */
+	bool tlb_flush_batched;
 #endif
 	struct uprobes_state uprobes_state;
 #ifdef CONFIG_HUGETLB_PAGE
@@ -518,46 +520,60 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 	return mm->cpu_vm_mask_var;
 }
 
-#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+struct mmu_gather;
+extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+				unsigned long start, unsigned long end);
+extern void tlb_finish_mmu(struct mmu_gather *tlb,
+				unsigned long start, unsigned long end);
+
 /*
  * Memory barriers to keep this state in sync are graciously provided by
  * the page table locks, outside of which no page table modifications happen.
- * The barriers below prevent the compiler from re-ordering the instructions
- * around the memory barriers that are already present in the code.
+ * The barriers are used to ensure the order between tlb_flush_pending updates,
+ * which happen while the lock is not taken, and the PTE updates, which happen
+ * while the lock is taken, are serialized.
  */
 static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
 {
-	barrier();
-	return mm->tlb_flush_pending;
+	return atomic_read(&mm->tlb_flush_pending) > 0;
 }
-static inline void set_tlb_flush_pending(struct mm_struct *mm)
+
+/*
+ * Returns true if there are two above TLB batching threads in parallel.
+ */
+static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
 {
-	mm->tlb_flush_pending = true;
+	return atomic_read(&mm->tlb_flush_pending) > 1;
+}
+
+static inline void init_tlb_flush_pending(struct mm_struct *mm)
+{
+	atomic_set(&mm->tlb_flush_pending, 0);
+}
+
+static inline void inc_tlb_flush_pending(struct mm_struct *mm)
+{
+	atomic_inc(&mm->tlb_flush_pending);
 
 	/*
-	 * Guarantee that the tlb_flush_pending store does not leak into the
+	 * Guarantee that the tlb_flush_pending increase does not leak into the
 	 * critical section updating the page tables
 	 */
 	smp_mb__before_spinlock();
 }
+
 /* Clearing is done after a TLB flush, which also provides a barrier. */
-static inline void clear_tlb_flush_pending(struct mm_struct *mm)
-{