24 files changed, 247 insertions, 94 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index c31157135598..07e02d6df5ad 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -190,6 +190,7 @@ struct backing_dev_info {
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */
 	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
+	struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
 #else
 	struct bdi_writeback_congested *wb_congested;
 #endif
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 5c7e7f859a24..d66bf5f32610 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -287,7 +287,7 @@ enum req_opf {
 	REQ_OP_DISCARD		= 3,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= 5,
-	/* seset a zone write pointer */
+	/* reset a zone write pointer */
 	REQ_OP_ZONE_RESET	= 6,
 	/* write the same sector many times */
 	REQ_OP_WRITE_SAME	= 7,
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 8804753805ac..7bb2d8de9f30 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
 
 static inline sector_t blk_rq_trace_sector(struct request *rq)
 {
-	return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq);
+	/*
+	 * Tracing should ignore starting sector for passthrough requests and
+	 * requests where starting sector didn't get set.
+	 */
+	if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1)
+		return 0;
+	return blk_rq_pos(rq);
 }
 
 static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq)
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 218df7f4d3e1..5041357d0297 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -180,12 +180,10 @@ enum cpuhp_smt_control {
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
 extern enum cpuhp_smt_control cpu_smt_control;
 extern void cpu_smt_disable(bool force);
-extern void cpu_smt_check_topology_early(void);
 extern void cpu_smt_check_topology(void);
 #else
 # define cpu_smt_control		(CPU_SMT_ENABLED)
 static inline void cpu_smt_disable(bool force) { }
-static inline void cpu_smt_check_topology_early(void) { }
 static inline void cpu_smt_check_topology(void) { }
 #endif
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index ef4b70f64f33..60996e64c579 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -62,9 +62,10 @@ extern const struct qstr slash_name;
 struct dentry_stat_t {
 	long nr_dentry;
 	long nr_unused;
-	long age_limit;          /* age in seconds */
-	long want_pages;         /* pages requested by system */
-	long dummy[2];
+	long age_limit;		/* age in seconds */
+	long want_pages;	/* pages requested by system */
+	long nr_negative;	/* # of unused negative dentries */
+	long dummy;		/* Reserved for future use */
 };
 extern struct dentry_stat_t dentry_stat;
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ad106d845b22..e532fcc6e4b5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 	return qdisc_skb_cb(skb)->data;
 }
 
-static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
-				       struct sk_buff *skb)
+static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog,
+					 struct sk_buff *skb)
 {
 	u8 *cb_data = bpf_skb_cb(skb);
 	u8 cb_saved[BPF_SKB_CB_LEN];
@@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
 	return res;
 }
 
+static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog,
+				       struct sk_buff *skb)
+{
+	u32 res;
+
+	preempt_disable();
+	res = __bpf_prog_run_save_cb(prog, skb);
+	preempt_enable();
+	return res;
+}
+
 static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
 					struct sk_buff *skb)
 {
 	u8 *cb_data = bpf_skb_cb(skb);
+	u32 res;
 
 	if (unlikely(prog->cb_access))
 		memset(cb_data, 0, BPF_SKB_CB_LEN);
 
-	return BPF_PROG_RUN(prog, skb);
+	preempt_disable();
+	res = BPF_PROG_RUN(prog, skb);
+	preempt_enable();
+	return res;
 }
 
 static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 811c77743dad..29d8e2cfed0e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1479,11 +1479,12 @@ struct super_block {
 	struct user_namespace *s_user_ns;
 
 	/*
-	 * Keep the lru lists last in the structure so they always sit on their
-	 * own individual cachelines.
+	 * The list_lru structure is essentially just a pointer to a table
+	 * of per-node lru lists, each of which has its own spinlock.
+	 * There is no need to put them into separate cachelines.
 	 */
-	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
-	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
+	struct list_lru		s_dentry_lru;
+	struct list_lru		s_inode_lru;
 	struct rcu_head		rcu;
 	struct work_struct	destroy_work;
 
diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h
index 8663f216c563..2d6100edf204 100644
--- a/include/linux/hid-debug.h
+++ b/include/linux/hid-debug.h
@@ -24,7 +24,10 @@
 
 #ifdef CONFIG_DEBUG_FS
 
+#include <linux/kfifo.h>
+
 #define HID_DEBUG_BUFSIZE 512
+#define HID_DEBUG_FIFOSIZE 512
 
 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32);
 void hid_dump_report(struct hid_device *, int , u8 *, int);
@@ -37,11 +40,8 @@ void hid_debug_init(void);
 void hid_debug_exit(void);
 void hid_debug_event(struct hid_device *, char *);
 
-
 struct hid_debug_list {
-	char *hid_debug_buf;
-	int head;
-	int tail;
+	DECLARE_KFIFO_PTR(hid_debug_fifo, char);
 	struct fasync_struct *fasync;
 	struct hid_device *hdev;
 	struct list_head node;
@@ -64,4 +64,3 @@ struct hid_debug_list {
 #endif
 
 #endif
-
diff --git a/include/linux/hid.h b/include/linux/hid.h
index d99287327ef2..f9707d1dcb58 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -430,7 +430,7 @@ struct hid_local {
  */
 
 struct hid_collection {
-	struct hid_collection *parent;
+	int parent_idx; /* device->collection */
 	unsigned type;
 	unsigned usage;
 	unsigned level;
@@ -658,7 +658,6 @@ struct hid_parser {
 	unsigned int         *collection_stack;
 	unsigned int          collection_stack_ptr;
 	unsigned int          collection_stack_size;
-	struct hid_collection *active_collection;
 	struct hid_device    *device;
 	unsigned int          scan_flags;
 };
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index f0885cc01db6..dcb6977afce9 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1159,8 +1159,9 @@ struct hv_ring_buffer_debug_info {
 	u32 bytes_avail_towrite;
 };
 
-void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info,
-			    struct hv_ring_buffer_debug_info *debug_info);
+
+int hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info,
+				struct hv_ring_buffer_debug_info *debug_info);
 
 /* Vmbus interface */
 #define vmbus_driver_register(driver)	\
diff --git a/include/linux/ide.h b/include/linux/ide.h
index e7d29ae633cd..971cf76a78a0 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -615,6 +615,7 @@ struct ide_drive_s {
 
 	/* current sense rq and buffer */
 	bool sense_rq_armed;
+	bool sense_rq_active;
 	struct request *sense_rq;
 	struct request_sense sense_data;
 
@@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout);
 extern void ide_timer_expiry(struct timer_list *t);
 extern irqreturn_t ide_intr(int irq, void *dev_id);
 extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *);
+extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool);
 extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq);
 
 void ide_init_disk(struct gendisk *, ide_drive_t *);
diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index 6756fea18b69..e44746de95cd 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -54,6 +54,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev)
 	case ARPHRD_IPGRE:
 	case ARPHRD_VOID:
 	case ARPHRD_NONE:
+	case ARPHRD_RAWIP:
 		return false;
 	default:
 		return true;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index c672f34235e7..4a728dba02e2 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -260,6 +260,7 @@ struct irq_affinity {
 /**
  * struct irq_affinity_desc - Interrupt affinity descriptor
  * @mask:	cpumask to hold the affinity assignment
+ * @is_managed: 1 if the interrupt is managed internally
  */
 struct irq_affinity_desc {
 	struct cpumask	mask;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 071b4cbdf010..c848a7cc502e 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -319,7 +319,7 @@
 #define GITS_TYPER_PLPIS		(1UL << 0)
 #define GITS_TYPER_VLPIS		(1UL << 1)
 #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT	4
-#define GITS_TYPER_ITT_ENTRY_SIZE(r)	((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
+#define GITS_TYPER_ITT_ENTRY_SIZE(r)	((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1)
 #define GITS_TYPER_IDBITS_SHIFT		8
 #define GITS_TYPER_DEVBITS_SHIFT	13
 #define GITS_TYPER_DEVBITS(r)		((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 7315977b64da..ad609617aeb8 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -235,7 +235,6 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus,
 			cmd_mask, num_flush, flush_wpq, NULL, NULL);
 }
 
-int nvdimm_security_setup_events(struct nvdimm *nvdimm);
 const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd);
 const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd);
 u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd,
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 07da5c6c5ba0..368267c1b71b 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -21,14 +21,16 @@ struct vmem_altmap;
  * walkers which rely on the fully initialized page->flags and others
  * should use this rather than pfn_valid && pfn_to_page
  */
-#define pfn_to_online_page(pfn)				\
-({							\
-	struct page *___page = NULL;			\
-	unsigned long ___nr = pfn_to_section_nr(pfn);	\
-							\
-	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
-		___page = pfn_to_page(pfn);		\
-	___page;					\
+#define pfn_to_online_page(pfn)					   \
+({								   \
+	struct page *___page = NULL;				   \
+	unsigned long ___pfn = pfn;				   \
+	unsigned long ___nr = pfn_to_section_nr(___pfn);	   \
+								   \
+	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \
+	    pfn_valid_within(___pfn))				   \
+		___page = pfn_to_page(___pfn);			   \
+	___page;						   \
 })
 
 /*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1377d085ef99..86dbb3e29139 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1483,6 +1483,7 @@ struct net_device_ops {
  * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook
  * @IFF_FAILOVER: device is a failover master device
  * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
+ * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1514,6 +1515,7 @@ enum netdev_priv_flags {
 	IFF_NO_RX_HANDLER		= 1<<26,
 	IFF_FAILOVER			= 1<<27,
 	IFF_FAILOVER_SLAVE		= 1<<28,
+	IFF_L3MDEV_RX_HANDLER		= 1<<29,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1544,6 +1546,7 @@ enum netdev_priv_flags {
 #define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
 #define IFF_FAILOVER			IFF_FAILOVER
 #define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
+#define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -4549,6 +4552,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev)
 	return dev->priv_flags & IFF_SUPP_NOFCS;
 }
 
+static inline bool netif_has_l3_rx_handler(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_L3MDEV_RX_HANDLER;
+}
+
 static inline bool netif_is_l3_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_L3MDEV_MASTER;
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 54af4eef169f..fed5be706bc9 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev)
 
 static inline void pm_runtime_mark_last_busy(struct device *dev)
 {
-	WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get()));
+	WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns());
 }
 
 static inline bool pm_runtime_is_irq_safe(struct device *dev)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2f90fa92468..bba3afb4e9bf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -995,7 +995,7 @@ struct task_struct {
 	/* cg_list protected by css_set_lock and tsk->alloc_lock: */
 	struct list_head		cg_list;
 #endif
-#ifdef CONFIG_X86_RESCTRL
+#ifdef CONFIG_X86_CPU_RESCTRL
 	u32				closid;
 	u32				rmid;
 #endif
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ec912d01126f..ecdc6542070f 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HUGE_ZERO_PAGE	23      /* mm has ever used the global huge zero page */
 #define MMF_DISABLE_THP		24	/* disable THP for all VMAs */
 #define MMF_OOM_VICTIM		25	/* mm is the oom victim */
+#define MMF_OOM_REAP_QUEUED	26	/* mm was queued for oom_reaper */
 #define MMF_DISABLE_THP_MASK	(1 << MMF_DISABLE_THP)
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 10b19a192b2d..545f37138057 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -24,9 +24,13 @@
  * called near the end of a function. Otherwise, the list can be
  * re-initialized for later re-use by wake_q_init().
  *
- * Note that this can cause spurious wakeups. schedule() callers
+ * NOTE that this can cause spurious wakeups. schedule() callers
  * must ensure the call is done inside a loop, confirming that the
  * wakeup condition has in fact occurred.
+ *
+ * NOTE that there is no guarantee the wakeup will happen any later than the
+ * wake_q_add() location. Therefore task must be ready to be woken at the
+ * location of the wake_q_add().
  */
 
 #include <linux/sched.h>
diff --git a/include/linux/signal.h b/include/linux/signal.h
index cc7e2c1cd444..9702016734b1 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig);
 #endif
 
 #define siginmask(sig, mask) \
-	((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask)))
+	((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask)))
 
 #define SIG_KERNEL_ONLY_MASK (\
 	rt_sigmask(SIGKILL)   |  rt_sigmask(SIGSTOP))
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 7ddfc65586b0..4335bd771ce5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -184,6 +184,7 @@ struct plat_stmmacenet_data {
 	struct clk *pclk;
 	struct clk *clk_ptp_ref;
 	unsigned int clk_ptp_rate;
+	unsigned int clk_ref_rate;
 	struct reset_control *stmmac_rst;
 	struct stmmac_axi *axi;
 	int has_gmac4;
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index f492e21c4aa2..5d9d318bcf7a 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -176,7 +176,8 @@ static inline bool xa_is_internal(const void *entry)
  */
 static inline bool xa_is_err(const void *entry)
 {
-	return unlikely(xa_is_internal(entry));
+	return unlikely(xa_is_internal(entry) &&
+			entry >= xa_mk_internal(-MAX_ERRNO));
 }
 
 /**
@@ -286,7 +287,6 @@ struct xarray {
  */
 #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC)
 
-void xa_init_flags(struct xarray *, gfp_t flags);
 void *xa_load(struct xarray *, unsigned long index);
 void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void *xa_erase(struct xarray *, unsigned long index);
@@ -304,6 +304,24 @@ unsigned int xa_extract(struct xarray *, void **dst, unsigned long start,
 void xa_destroy(struct xarray *);
 
 /**
+ * xa_init_flags() - Initialise an empty XArray with flags.
+ * @xa: XArray.
+ * @flags: XA_FLAG values.
+ *
+ * If you need to initialise an XArray with special flags (eg you need
+ * to take the lock from interrupt context), use this function instead
+ * of xa_init().
+ *
+ * Context: Any context.
+ */
+static inline void xa_init_flags(struct xarray *xa, gfp_t flags)
+{
+	spin_lock_init(&xa->xa_lock);
+	xa->xa_flags = flags;
+	xa->xa_head = NULL;
+}
+
+/**
  * xa_init() - Initialise an empty XArray.
  * @xa: XArray.
  *
@@ -342,20 +360,45 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
 }
 
 /**
- * xa_for_each() - Iterate over a portion of an XArray.
+ * xa_for_each_start() - Iterate over a portion of an XArray.
  * @xa: XArray.
+ * @index: Index of @entry.
  * @entry: Entry retrieved from array.
+ * @start: First index to retrieve from array.
+ *
+ * During the iteration, @entry will have the value of the entry stored
+ * in @xa at @index.  You may modify @index during the iteration if you
+ * want to skip or reprocess indices.  It is safe to modify the array
+ * during the iteration.  At the end of the iteration, @entry will be set
+ * to NULL and @index will have a value less than or equal to max.
+ *
+ * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n).  You have
+ * to handle your own locking with xas_for_each(), and if you have to unlock
+ * after each iteration, it will also end up being O(n.log(n)).
+ * xa_for_each_start() will spin if it hits a retry entry; if you intend to
+ * see retry entries, you should use the xas_for_each() iterator instead.
+ * The xas_for_each() iterator will expand into more inline code than
+ * xa_for_each_start().
+ *
+ * Context: Any context.  Takes and releases the RCU lock.
+ */
+#define xa_for_each_start(xa, index, entry, start)			\
+	for (index = start,						\
+	     entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT);	\
+	     entry;							\
+	     entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT))
+
+/**
+ * xa_for_each() - Iterate over present entries in an XArray.
+ * @xa: XArray.
  * @index: Index of @entry.
- * @max: Maximum index to retrieve from array.
- * @filter: Selection criterion.
+ * @entry: Entry retrieved from array.
  *
- * Initialise @index to the lowest index you want to retrieve from the
- * array.  During the iteration, @entry will have the value of the entry
- * stored in @xa at @index.  The iteration will skip all entries in the
- * array which do not match @filter.  You may modify @index during the
- * iteration if you want to skip or reprocess indices.  It is safe to modify
- * the array during the iteration.  At the end of the iteration, @entry will
- * be set to NULL and @index will have a value less than or equal to max.
+ * During the iteration, @entry will have the value of the entry stored
+ * in @xa at @index.  You may modify @index during the iteration if you want
+ * to skip or reprocess indices.  It is safe to modify the array during the
+ * iteration.  At the end of the iteration, @entry will be set to NULL and
+ * @index will have a value less than or equal to max.
  *
  * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n).  You have
  * to handle your own locking with xas_for_each(), and if you have to unlock
@@ -366,9 +409,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark)
  *
  * Context: Any context.  Takes and releases the RCU lock.
  */
-#define xa_for_each(xa, entry, index, max, filter) \
-	for (entry = xa_find(xa, &index, max, filter); entry; \
-	     entry = xa_find_after(xa, &index, max, filter))
+#define xa_for_each(xa, index, entry) \
+	xa_for_each_start(xa, index, entry, 0)
+
+/**
+ * xa_for_each_marked() - Iterate over marked entries in an XArray.
+ * @xa: XArray.
+ * @index: Index of @entry.
+ * @entry: Entry retrieved from array.
+ * @filter: Selection criterion.
+ *
+ * During the iteration, @entry will have the value of the entry stored
+ * in @xa at @index.  The iteration will skip all entries in the array
+ * which do not match @filter.  You may modify @index during the iteration
+ * if you want to skip or reprocess indices.  It is safe to modify the array
+ * during the iteration.  At the end of the iteration, @entry will be set to
+ * NULL and @index will have a value less than or equal to max.
+ *
+ * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n).
+ * You have to handle your own locking with xas_for_each(), and if you have
+ * to unlock after each iteration, it will also end up being O(n.log(n)).
+ * xa_for_each_marked() will spin if it hits a retry entry; if you intend to
+ * see retry entries, you should use the xas_for_each_marked() iterator
+ * instead.  The xas_for_each_marked() iterator will expand into more inline
+ * code than xa_for_each_marked().
+ *
+ * Context: Any context.  Takes and releases the RCU lock.
+ */
+#define xa_for_each_marked(xa, index, entry, filter) \
+	for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \
+	     entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter))
 
 #define xa_trylock(xa)		spin_trylock(&(xa)->xa_lock)
 #define xa_lock(xa)		spin_lock(&(xa)->xa_lock)
@@ -393,40 +463,13 @@ void *__xa_erase(struct xarray *, unsigned long index);
 void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t);
 void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old,
 		void *entry, gfp_t);
+int __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t);
 int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t);
 int __xa_reserve(struct xarray *, unsigned long index, gfp_t);
 void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t);
 void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t);
 
 /**
- * __xa_insert() - Store this entry in the XArray unless another entry is
- *			already present.
- * @xa: XArray.
- * @index: Index into array.
- * @entry: New entry.
- * @gfp: Memory allocation flags.
- *
- * If you would rather see the existing entry in the array, use __xa_cmpxchg().
- * This function is for users who don't care what the entry is, only that
- * one is present.
- *
- * Context: Any context.  Expects xa_lock to be held on entry.  May
- *	    release and reacquire xa_lock if the @gfp flags permit.
- * Return: 0 if the store succeeded.  -EEXIST if another entry was present.
- * -ENOMEM if memory could not be allocated.
- */
-static inline int __xa_insert(struct xarray *xa, unsigned long index,
-		void *entry, gfp_t gfp)
-{
-	void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp);
-	if (!curr)
-		return 0;
-	if (xa_is_err(curr))
-		return xa_err(curr);
-	return -EEXIST;
-}
-
-/**
  * xa_store_bh() - Store this entry in the XArray.
  * @xa: XArray.
  * @index: Index into array.
@@ -453,7 +496,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index,
 }
 
 /**
- * xa_store_irq() - Erase this entry from the XArray.
+ * xa_store_irq() - Store this entry in the XArray.
  * @xa: XArray.
  * @index: Index into array.
  * @entry: New entry.
@@ -615,24 +658,83 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index,
  * @entry: New entry.
  * @gfp: Memory allocation flags.
  *
- * If you would rather see the existing entry in the array, use xa_cmpxchg().
- * This function is for users who don't care what the entry is, only that
- * one is present.
+ * Inserting a NULL entry will store a reserved entry (like xa_reserve())
+ * if no entry is present.  Inserting will fail if a reserved entry is
+ * present, even though loading from this index will return NULL.
  *
- * Context: Process context.  Takes and releases the xa_lock.
- *	    May sleep if the @gfp flags permit.
+ * Context: Any context.  Takes and releases the xa_lock.  May sleep if
+ * the @gfp flags permit.
  * Return: 0 if the store succeeded.  -EEXIST if another entry was present.
  * -ENOMEM if memory could not be allocated.
  */
 static inline int xa_insert(struct xarray *xa, unsigned long index,
 		void *entry, gfp_t gfp)
 {
-	void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp);
-	if (!curr)
-		return 0;
-	if (xa_is_err(curr))
-		return xa_err(curr);
-	return -EEXIST;
+	int err;
+
+	xa_lock(xa);
+	err = __xa_insert(xa, index, entry, gfp);
+	xa_unlock(xa);
+
+	return err;
+}
+
+/**
+ * xa_insert_bh() - Store this entry in the XArray unless another entry is
+ *			already present.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * Inserting a NULL entry will store a reserved entry (like xa_reserve())
+ * if no entry is present.  Inserting will fail if a reserved entry is
+ * present, even though loading from this index will return NULL.
+ *
+ * Context: Any context.  Takes and releases the xa_lock while
+ * disabling softirqs.  May sleep if the @gfp flags permit.
+ * Return: 0 if the store succeeded.  -EEXIST if another entry was present.
+ * -ENOMEM if memory could not be allocated.
+ */
+static inline int xa_insert_bh(struct xarray *xa, unsigned long index,
+		void *entry, gfp_t gfp)
+{
+	int err;
+
+	xa_lock_bh(xa);
+	err = __xa_insert(xa, index, entry, gfp);
+	xa_unlock_bh(xa);
+
+	return err;
+}
+
+/**
+ * xa_insert_irq() - Store this entry in the XArray unless another entry is
+ *			already present.
+ * @xa: XArray.
+ * @index: Index into array.
+ * @entry: New entry.
+ * @gfp: Memory allocation flags.
+ *
+ * Inserting a NULL entry will store a reserved entry (like xa_reserve())
+ * if no entry is present.  Inserting will fail if a reserved entry is
+ * present, even though loading from this index will return NULL.
+ *
+ * Context: Process context.  Takes and releases the xa_lock while
+ * disabling interrupts.  May sleep if the @gfp flags permit.
+ * Return: 0 if the store succeeded.  -EEXIST if another entry was present.
+ * -ENOMEM if memory could not be allocated.
+ */
+static inline int xa_insert_irq(struct xarray *xa, unsigned long index,
+		void *entry, gfp_t gfp)
+{
+	int err;
+
+	xa_lock_irq(xa);
+	err = __xa_insert(xa, index, entry, gfp);
+	xa_unlock_irq(xa);
+
+	return err;
 }
 
 /**
@@ -970,8 +1072,8 @@ static inline bool xa_is_sibling(const void *entry)
 		(entry < xa_mk_sibling(XA_CHUNK_SIZE - 1));
 }
 
-#define XA_ZERO_ENTRY		xa_mk_internal(256)
-#define XA_RETRY_ENTRY		xa_mk_internal(257)
+#define XA_RETRY_ENTRY		xa_mk_internal(256)
+#define XA_ZERO_ENTRY		xa_mk_internal(257)
 
 /**
  * xa_is_zero() - Is the entry a zero entry?
@@ -996,6 +1098,17 @@ static inline bool xa_is_retry(const void *entry)
 }
 
 /**
+ * xa_is_advanced() - Is the entry only permitted for the advanced API?
+ * @entry: Entry to be stored in the XArray.
+ *
+ * Return: %true if the entry cannot be stored by the normal API.
+ */
+static inline bool xa_is_advanced(const void *entry)
+{
+	return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY);
+}
+
+/**
  * typedef xa_update_node_t - A callback function from the XArray.
  * @node: The node which is being processed
  *