23 files changed, 89 insertions, 28 deletions

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/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 890b706d1943..21a6fd6c44af 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -477,7 +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)
@@ -570,7 +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..7f384bb62d8e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -495,6 +495,10 @@ struct mm_struct {
 	 */
 	bool tlb_flush_pending;
 #endif
+#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
 	atomic_long_t hugetlb_usage;
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 892148c448cc..5216d2eb2289 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -681,10 +681,10 @@ struct nand_buffers {
  * @tWW_min: WP# transition to WE# low
  */
 struct nand_sdr_timings {
-	u32 tBERS_max;
+	u64 tBERS_max;
 	u32 tCCS_min;
-	u32 tPROG_max;
-	u32 tR_max;
+	u64 tPROG_max;
+	u64 tR_max;
 	u32 tALH_min;
 	u32 tADL_min;
 	u32 tALS_min;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index ca3bcc4ed4e5..62cbcb842f99 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1235,7 +1235,7 @@ struct nfs41_state_protection {
 
 struct nfs41_exchange_id_args {
 	struct nfs_client		*client;
-	nfs4_verifier			*verifier;
+	nfs4_verifier			verifier;
 	u32				flags;
 	struct nfs41_state_protection	state_protect;
 };
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index baa9344dcd10..79b36f57c3ba 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -163,8 +163,6 @@ void release_pages(struct page **pages, int nr, bool cold);
  */
 static inline int page_cache_get_speculative(struct page *page)
 {
-	VM_BUG_ON(in_interrupt());
-
 #ifdef CONFIG_TINY_RCU
 # ifdef CONFIG_PREEMPT_COUNT
 	VM_BUG_ON(!in_atomic() && !irqs_disabled());
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 2a9567bb8186..0bb5b212ab42 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -830,7 +830,7 @@ static inline int phy_read_status(struct phy_device *phydev)
 	dev_err(&_phydev->mdio.dev, format, ##args)
 
 #define phydev_dbg(_phydev, format, args...)	\
-	dev_dbg(&_phydev->mdio.dev, format, ##args);
+	dev_dbg(&_phydev->mdio.dev, format, ##args)
 
 static inline const char *phydev_name(const struct phy_device *phydev)
 {
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index a026bfd089db..51349d124ee5 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -99,6 +99,11 @@ struct system_device_crosststamp;
  *            parameter func: the desired function to use.
  *            parameter chan: the function channel index to use.
  *
+ * @do_work:  Request driver to perform auxiliary (periodic) operations
+ *	      Driver should return delay of the next auxiliary work scheduling
+ *	      time (>=0) or negative value in case further scheduling
+ *	      is not required.
+ *
  * Drivers should embed their ptp_clock_info within a private
  * structure, obtaining a reference to it using container_of().
  *
@@ -126,6 +131,7 @@ struct ptp_clock_info {
 		      struct ptp_clock_request *request, int on);
 	int (*verify)(struct ptp_clock_info *ptp, unsigned int pin,
 		      enum ptp_pin_function func, unsigned int chan);
+	long (*do_aux_work)(struct ptp_clock_info *ptp);
 };
 
 struct ptp_clock;
@@ -211,6 +217,16 @@ extern int ptp_clock_index(struct ptp_clock *ptp);
 int ptp_find_pin(struct ptp_clock *ptp,
 		 enum ptp_pin_function func, unsigned int chan);
 
+/**
+ * ptp_schedule_worker() - schedule ptp auxiliary work
+ *
+ * @ptp:    The clock obtained from ptp_clock_register().
+ * @delay:  number of jiffies to wait before queuing
+ *          See kthread_queue_delayed_work() for more info.
+ */
+
+int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay);
+
 #else
 static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 						   struct device *parent)
@@ -225,6 +241,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp)
 static inline int ptp_find_pin(struct ptp_clock *ptp,
 			       enum ptp_pin_function func, unsigned int chan)
 { return -1; }
+static inline int ptp_schedule_worker(struct ptp_clock *ptp,
+				      unsigned long delay)
+{ return -EOPNOTSUPP; }
+
 #endif
 
 #endif
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 586809abb273..a47b985341d1 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -152,7 +152,7 @@ extern int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr,
 					      size_t *data_size);
 
 struct pci_dev;
-#ifdef CONFIG_EEH
+#if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH)
 extern void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
 extern void vfio_spapr_pci_eeh_release(struct pci_dev *pdev);
 extern long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
@@ -173,7 +173,7 @@ static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
 {
 	return -ENOTTY;
 }
-#endif /* CONFIG_EEH */
+#endif /* CONFIG_VFIO_SPAPR_EEH */
 
 /*
  * IRQfd - generic
diff --git a/include/linux/wait.h b/include/linux/wait.h
index b289c96151ee..5b74e36c0ca8 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -529,13 +529,13 @@ do {										\
 
 /**
  * wait_event_interruptible_hrtimeout - sleep until a condition gets true or a timeout elapses
- * @wq_head: the waitqueue to wait on
+ * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout, as a ktime_t
  *
  * The process is put to sleep (TASK_INTERRUPTIBLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq_head is woken up.
+ * The @condition is checked each time the waitqueue @wq is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
@@ -735,12 +735,12 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *);
 
 /**
  * wait_event_killable - sleep until a condition gets true
- * @wq: the waitqueue to wait on
+ * @wq_head: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
  * The process is put to sleep (TASK_KILLABLE) until the
  * @condition evaluates to true or a signal is received.
- * The @condition is checked each time the waitqueue @wq is woken up.
+ * The @condition is checked each time the waitqueue @wq_head is woken up.
  *
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index c102ef65cb64..db6dc9dc0482 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -323,6 +323,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_ORDERED_EXPLICIT	= 1 << 18, /* internal: alloc_ordered_workqueue() */
 	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
@@ -422,7 +423,8 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue(fmt, flags, args...)			\
-	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
+	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED |		\
+			__WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
 	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))