Merge tag 'nand/for-6.14' into mtd/next

* Raw NAND changes

A new controller driver, from Nuvoton, has been merged.

Bastien Curutchet has contributed a series improving the Davinci
controller driver, both on the organization of the code, but also on the
performance side. The binding has also been converted to yaml, received
a new OOB layout and now supports on-die ECC engines.

The Qualcomm controller driver has been deeply cleaned to extract some
parts of the code into a shared file with the Qualcomm SPI memory
controller.

Aside from these main changes, the Cadence binding has been converted to
yaml, the brcmnand controller driver has received a small fix, otherwise
some more minor changes have also made their way in.

* SPI NAND changes

The SPI NAND subsystem has seen a great improvement, with the advent of
DTR operations (DDR operations, which may be extended to the address
cycles). The first vendor driver to benefit from these improvements is
the Winbond driver.

A new manufacturer driver is added SkyHigh, with a new constraint for
the core, it is impossible to disable the on-die ECC engine.

A Foresee device is also now supported.

53 files changed, 923 insertions, 146 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 05f39fbfa485..6adcd1b92b20 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -40,7 +40,7 @@ struct irq_domain_ops;
 #include <asm/acpi.h>
 
 #ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "ACPI")
 #define __init_or_acpilib
 #define __initdata_or_acpilib
 #else
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 7c0786bdf9af..0bbbe537c5f9 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -63,7 +63,12 @@ static inline void set_codetag_empty(union codetag_ref *ref)
 #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
 static inline bool is_codetag_empty(union codetag_ref *ref) { return false; }
-static inline void set_codetag_empty(union codetag_ref *ref) {}
+
+static inline void set_codetag_empty(union codetag_ref *ref)
+{
+	if (ref)
+		ref->ct = NULL;
+}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
 
@@ -135,7 +140,7 @@ static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag)
 #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
 static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag)
 {
-	WARN_ONCE(ref && ref->ct,
+	WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref),
 		  "alloc_tag was not cleared (got tag for %s:%u)\n",
 		  ref->ct->filename, ref->ct->lineno);
 
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index a28e2a6a13d0..74169dd0f659 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev)
 	return dev_get_drvdata(&fdev->dev);
 }
 
+struct ffa_partition_info;
+
 #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT)
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
-				       const struct ffa_ops *ops);
+struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+		    const struct ffa_ops *ops);
 void ffa_device_unregister(struct ffa_device *ffa_dev);
 int ffa_driver_register(struct ffa_driver *driver, struct module *owner,
 			const char *mod_name);
@@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver);
 bool ffa_device_is_valid(struct ffa_device *ffa_dev);
 
 #else
-static inline
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
-				       const struct ffa_ops *ops)
+static inline struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+		    const struct ffa_ops *ops)
 {
 	return NULL;
 }
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 60830a6a5939..7a1b3b1a8fed 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -423,7 +423,7 @@ void __bio_add_page(struct bio *bio, struct page *page,
 void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
 			  size_t off);
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
-void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter);
+void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 08a727b40816..378d3a1a22fc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -200,8 +200,6 @@ struct gendisk {
 	spinlock_t              zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;
 	struct hlist_head       *zone_wplugs_hash;
-	struct list_head        zone_wplugs_err_list;
-	struct work_struct	zone_wplugs_work;
 	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
@@ -1421,6 +1419,9 @@ static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector)
 	return is_seq;
 }
 
+int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector,
+			   sector_t nr_sects, gfp_t gfp_mask);
+
 static inline unsigned int queue_dma_alignment(const struct request_queue *q)
 {
 	return q->limits.dma_alignment;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eaee2a819f4c..6e63dd3443b9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1527,6 +1527,7 @@ struct bpf_prog_aux {
 	bool is_extended; /* true if extended by freplace program */
 	bool jits_use_priv_stack;
 	bool priv_stack_requested;
+	bool changes_pkt_data;
 	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
 	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
 	struct bpf_arena *arena;
@@ -2193,26 +2194,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
  * rcu-protected dynamically sized maps.
  */
 static __always_inline u32
-bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
 			  const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
 	u32 ret = 1;
 
 	might_fault();
+	RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held");
+
+	if (unlikely(!array))
+		return ret;
 
-	rcu_read_lock_trace();
 	migrate_disable();
 
 	run_ctx.is_uprobe = true;
 
-	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
-	if (unlikely(!array))
-		goto out;
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
 	while ((prog = READ_ONCE(item->prog))) {
@@ -2227,9 +2227,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
 			rcu_read_unlock();
 	}
 	bpf_reset_run_ctx(old_run_ctx);
-out:
 	migrate_enable();
-	rcu_read_unlock_trace();
 	return ret;
 }
 
@@ -3516,10 +3514,4 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog)
 	return prog->aux->func_idx != 0;
 }
 
-static inline bool bpf_prog_is_raw_tp(const struct bpf_prog *prog)
-{
-	return prog->type == BPF_PROG_TYPE_TRACING &&
-	       prog->expected_attach_type == BPF_TRACE_RAW_TP;
-}
-
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f4290c179bee..48b7b2eeb7e2 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -659,6 +659,7 @@ struct bpf_subprog_info {
 	bool args_cached: 1;
 	/* true if bpf_fastcall stack region is used by functions that can't be inlined */
 	bool keep_fastcall_stack: 1;
+	bool changes_pkt_data: 1;
 
 	enum priv_stack_mode priv_stack_mode;
 	u8 arg_cnt;
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 108060612bb8..7ad736538649 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -155,8 +155,14 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level)
 
 #ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING
 #define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
 #else
 #include <asm/cachetype.h>
+
+#ifndef cpu_icache_is_aliasing
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
+#endif
+
 #endif
 
 #endif /* _LINUX_CACHEINFO_H */
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 966fcc5ff8ef..ec00e3f7af2b 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -273,12 +273,6 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
  *	an anonymous instance of the (guard) class, not recommended for
  *	conditional locks.
  *
- * if_not_guard(name, args...) { <error handling> }:
- *	convenience macro for conditional guards that calls the statement that
- *	follows only if the lock was not acquired (typically an error return).
- *
- *	Only for conditional locks.
- *
  * scoped_guard (name, args...) { }:
  *	similar to CLASS(name, scope)(args), except the variable (with the
  *	explicit name 'scope') is declard in a for-loop such that its scope is
@@ -350,14 +344,6 @@ _label:									\
 #define scoped_cond_guard(_name, _fail, args...)	\
 	__scoped_cond_guard(_name, _fail, __UNIQUE_ID(label), args)
 
-#define __if_not_guard(_name, _id, args...)		\
-	BUILD_BUG_ON(!__is_cond_ptr(_name));		\
-	CLASS(_name, _id)(args);			\
-	if (!__guard_ptr(_name)(&_id))
-
-#define if_not_guard(_name, args...) \
-	__if_not_guard(_name, __UNIQUE_ID(guard), args)
-
 /*
  * Additional helper macros for generating lock guards with types, either for
  * locks that don't have a native type (eg. RCU, preempt) or those that need a
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index ef1b16da6ad5..65b7c41471c3 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -49,6 +49,7 @@ struct module;
  * @archdata:		Optional arch-specific data
  * @max_cycles:		Maximum safe cycle value which won't overflow on
  *			multiplication
+ * @max_raw_delta:	Maximum safe delta value for negative motion detection
  * @name:		Pointer to clocksource name
  * @list:		List head for registration (internal)
  * @freq_khz:		Clocksource frequency in khz.
@@ -109,6 +110,7 @@ struct clocksource {
 	struct arch_clocksource_data archdata;
 #endif
 	u64			max_cycles;
+	u64			max_raw_delta;
 	const char		*name;
 	struct list_head	list;
 	u32			freq_khz;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 469a64dd6495..240c632c5b95 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -216,28 +216,43 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #endif /* __KERNEL__ */
 
+/**
+ * offset_to_ptr - convert a relative memory offset to an absolute pointer
+ * @off:	the address of the 32-bit offset value
+ */
+static inline void *offset_to_ptr(const int *off)
+{
+	return (void *)((unsigned long)off + *off);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_64BIT
+#define ARCH_SEL(a,b) a
+#else
+#define ARCH_SEL(a,b) b
+#endif
+
 /*
  * Force the compiler to emit 'sym' as a symbol, so that we can reference
  * it from inline assembler. Necessary in case 'sym' could be inlined
  * otherwise, or eliminated entirely due to lack of references that are
  * visible to the compiler.
  */
-#define ___ADDRESSABLE(sym, __attrs) \
-	static void * __used __attrs \
+#define ___ADDRESSABLE(sym, __attrs)						\
+	static void * __used __attrs						\
 	__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym;
+
 #define __ADDRESSABLE(sym) \
 	___ADDRESSABLE(sym, __section(".discard.addressable"))
 
-/**
- * offset_to_ptr - convert a relative memory offset to an absolute pointer
- * @off:	the address of the 32-bit offset value
- */
-static inline void *offset_to_ptr(const int *off)
-{
-	return (void *)((unsigned long)off + *off);
-}
+#define __ADDRESSABLE_ASM(sym)						\
+	.pushsection .discard.addressable,"aw";				\
+	.align ARCH_SEL(8,4);						\
+	ARCH_SEL(.quad, .long) __stringify(sym);			\
+	.popsection;
 
-#endif /* __ASSEMBLY__ */
+#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym))
 
 #ifdef __CHECKER__
 #define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index b137fdb56093..346251bf1026 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -84,7 +84,7 @@ enum dma_transfer_direction {
 	DMA_TRANS_NONE,
 };
 
-/**
+/*
  * Interleaved Transfer Request
  * ----------------------------
  * A chunk is collection of contiguous bytes to be transferred.
@@ -223,7 +223,7 @@ enum sum_check_bits {
 };
 
 /**
- * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations
+ * enum sum_check_flags - result of async_{xor,pq}_zero_sum operations
  * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise
  * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise
  */
@@ -286,7 +286,7 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t;
  *	pointer to the engine's metadata area
  *   4. Read out the metadata from the pointer
  *
- * Note: the two mode is not compatible and clients must use one mode for a
+ * Warning: the two modes are not compatible and clients must use one mode for a
  * descriptor.
  */
 enum dma_desc_metadata_mode {
@@ -594,9 +594,13 @@ struct dma_descriptor_metadata_ops {
  * @phys: physical address of the descriptor
  * @chan: target channel for this operation
  * @tx_submit: accept the descriptor, assign ordered cookie and mark the
+ * @desc_free: driver's callback function to free a resusable descriptor
+ *	after completion
  * descriptor pending. To be pushed on .issue_pending() call
  * @callback: routine to call after this operation is complete
+ * @callback_result: error result from a DMA transaction
  * @callback_param: general parameter to pass to the callback routine
+ * @unmap: hook for generic DMA unmap data
  * @desc_metadata_mode: core managed metadata mode to protect mixed use of
  *	DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise
  *	DESC_METADATA_NONE
@@ -827,6 +831,9 @@ struct dma_filter {
  * @device_prep_dma_memset: prepares a memset operation
  * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list
  * @device_prep_dma_interrupt: prepares an end of chain interrupt operation
+ * @device_prep_peripheral_dma_vec: prepares a scatter-gather DMA transfer,
+ *	where the address and size of each segment is located in one entry of
+ *	the dma_vec array.
  * @device_prep_slave_sg: prepares a slave dma operation
  * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio.
  *	The function takes a buffer of size buf_len. The callback function will
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index 6fbfbde68a37..620a3260fc08 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -15,6 +15,7 @@
 struct ocelot_skb_cb {
 	struct sk_buff *clone;
 	unsigned int ptp_class; /* valid only for clones */
+	unsigned long ptp_tx_time; /* valid only for clones */
 	u32 tstamp_lo;
 	u8 ptp_cmd;
 	u8 ts_id;
diff --git a/include/linux/export.h b/include/linux/export.h
index 0bbd02fd351d..2633df4d31e6 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -60,14 +60,14 @@
 #endif
 
 #ifdef DEFAULT_SYMBOL_NAMESPACE
-#define _EXPORT_SYMBOL(sym, license)	__EXPORT_SYMBOL(sym, license, __stringify(DEFAULT_SYMBOL_NAMESPACE))
+#define _EXPORT_SYMBOL(sym, license)	__EXPORT_SYMBOL(sym, license, DEFAULT_SYMBOL_NAMESPACE)
 #else
 #define _EXPORT_SYMBOL(sym, license)	__EXPORT_SYMBOL(sym, license, "")
 #endif
 
 #define EXPORT_SYMBOL(sym)		_EXPORT_SYMBOL(sym, "")
 #define EXPORT_SYMBOL_GPL(sym)		_EXPORT_SYMBOL(sym, "GPL")
-#define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", __stringify(ns))
-#define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "GPL", __stringify(ns))
+#define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", ns)
+#define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "GPL", ns)
 
 #endif /* _LINUX_EXPORT_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 3a21947f2fd4..0477254bc2d3 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1122,7 +1122,7 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);
 bool bpf_jit_supports_private_stack(void);
 u64 bpf_arch_uaddress_limit(void);
 void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
-bool bpf_helper_changes_pkt_data(void *func);
+bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id);
 
 static inline bool bpf_dump_raw_ok(const struct cred *cred)
 {
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 0d99bf11d260..e4ce1cae03bf 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -616,6 +616,12 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 	return false;
 }
 
+/*
+ * To work around what seems to be an optimizer bug, the macro arguments
+ * need to have const copies or the values end up changed by the time they
+ * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture
+ * __bos() results in const temp vars") for more details.
+ */
 #define __fortify_memcpy_chk(p, q, size, p_size, q_size,		\
 			     p_size_field, q_size_field, op) ({		\
 	const size_t __fortify_size = (size_t)(size);			\
@@ -623,6 +629,8 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 	const size_t __q_size = (q_size);				\
 	const size_t __p_size_field = (p_size_field);			\
 	const size_t __q_size_field = (q_size_field);			\
+	/* Keep a mutable version of the size for the final copy. */	\
+	size_t __copy_size = __fortify_size;				\
 	fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size,	\
 				     __q_size, __p_size_field,		\
 				     __q_size_field, FORTIFY_FUNC_ ##op), \
@@ -630,7 +638,11 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 		  __fortify_size,					\
 		  "field \"" #p "\" at " FILE_LINE,			\
 		  __p_size_field);					\
-	__underlying_##op(p, q, __fortify_size);			\
+	/* Hide only the run-time size from value range tracking to */	\
+	/* silence compile-time false positive bounds warnings. */	\
+	if (!__builtin_constant_p(__copy_size))				\
+		OPTIMIZER_HIDE_VAR(__copy_size);			\
+	__underlying_##op(p, q, __copy_size);				\
 })
 
 /*
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index 3ff4c277296f..9bd605b87c4c 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -54,7 +54,7 @@ int cdat_table_parse(enum acpi_cdat_type type,
 #define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x)
 #define __init_or_fwtbl_lib __init_or_acpilib
 #else
-#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, CXL)
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "CXL")
 #define __init_or_fwtbl_lib
 #endif
 
diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h
index a6876ab29004..a2e47dbcf82c 100644
--- a/include/linux/hid_bpf.h
+++ b/include/linux/hid_bpf.h
@@ -78,7 +78,7 @@ struct hid_ops {
 	const struct bus_type *bus_type;
 };
 
-extern struct hid_ops *hid_ops;
+extern const struct hid_ops *hid_ops;
 
 /**
  * struct hid_bpf_ops - A BPF struct_ops of callbacks allowing to attach HID-BPF
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 6e452bd8e7e3..5c6bea81a90e 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -224,7 +224,13 @@ static inline
 struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
 				   unsigned long vaddr)
 {
-	return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr);
+	struct folio *folio;
+
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
+	if (folio && user_alloc_needs_zeroing())
+		clear_user_highpage(&folio->page, vaddr);
+
+	return folio;
 }
 #endif
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 22c22fb91042..02a226bcf0ed 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1559,6 +1559,7 @@ struct hv_util_service {
 	void *channel;
 	void (*util_cb)(void *);
 	int (*util_init)(struct hv_util_service *);
+	int (*util_init_transport)(void);
 	void (*util_deinit)(void);
 	int (*util_pre_suspend)(void);
 	int (*util_pre_resume)(void);
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index c1645c86eed9..d65b5d71b93b 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -585,13 +585,16 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
  * @type: first vlan protocol
+ * @mac_offset: MAC offset
  * @depth: buffer to store length of eth and vlan tags in bytes
  *
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
-					 int *depth)
+static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb,
+						__be16 type,
+						int mac_offset,
+						int *depth)
 {
 	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
@@ -610,7 +613,8 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 		do {
 			struct vlan_hdr vhdr, *vh;
 
-			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			vh = skb_header_pointer(skb, mac_offset + vlan_depth,
+						sizeof(vhdr), &vhdr);
 			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
@@ -625,6 +629,12 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 	return type;
 }
 
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
+					 int *depth)
+{
+	return __vlan_get_protocol_offset(skb, type, 0, depth);
+}
+
 /**
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index e123d5e17b52..85fe4e6b275c 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -15,10 +15,8 @@ bool io_is_uring_fops(struct file *file);
 
 static inline void io_uring_files_cancel(void)
 {
-	if (current->io_uring) {
-		io_uring_unreg_ringfd();
+	if (current->io_uring)
 		__io_uring_cancel(false);
-	}
 }
 static inline void io_uring_task_cancel(void)
 {
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 578a3fdf5c71..0d5448c0b86c 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -43,7 +43,7 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
  * Note: the caller should never hard code @issue_flags and is only allowed
  * to pass the mask provided by the core io_uring code.
  */
-void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
+void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, u64 res2,
 			unsigned issue_flags);
 
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
@@ -67,7 +67,7 @@ static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 	return -EOPNOTSUPP;
 }
 static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
-		ssize_t ret2, unsigned issue_flags)
+		u64 ret2, unsigned issue_flags)
 {
 }
 static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 011860ade268..fd4cdb0860a2 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -345,7 +345,7 @@ struct io_ring_ctx {
 
 	/* timeouts */
 	struct {
-		spinlock_t		timeout_lock;
+		raw_spinlock_t		timeout_lock;
 		struct list_head	timeout_list;
 		struct list_head	ltimeout_list;
 		unsigned		cq_last_tm_flush;
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index 3f2cf339ceaf..d437e3070850 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -7,6 +7,7 @@
 #ifdef CONFIG_MEMFD_CREATE
 extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
 struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
+unsigned int *memfd_file_seals_ptr(struct file *file);
 #else
 static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
 {
@@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 {
 	return ERR_PTR(-EINVAL);
 }
+
+static inline unsigned int *memfd_file_seals_ptr(struct file *file)
+{
+	return NULL;
+}
 #endif
 
+/* Retrieve memfd seals associated with the file, if any. */
+static inline unsigned int memfd_file_seals(struct file *file)
+{
+	unsigned int *sealsp = memfd_file_seals_ptr(file);
+
+	return sealsp ? *sealsp : 0;
+}
+
 #endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/memory/ti-aemif.h b/include/linux/memory/ti-aemif.h
new file mode 100644
index 000000000000..da94a9d985e7
--- /dev/null
+++ b/include/linux/memory/ti-aemif.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __MEMORY_TI_AEMIF_H
+#define __MEMORY_TI_AEMIF_H
+
+/**
+ * struct aemif_cs_timings: structure to hold CS timing configuration
+ * values are expressed in number of clock cycles - 1
+ * @ta: minimum turn around time
+ * @rhold: read hold width
+ * @rstrobe: read strobe width
+ * @rsetup: read setup width
+ * @whold: write hold width
+ * @wstrobe: write strobe width
+ * @wsetup: write setup width
+ */
+struct aemif_cs_timings {
+	u32	ta;
+	u32	rhold;
+	u32	rstrobe;
+	u32	rsetup;
+	u32	whold;
+	u32	wstrobe;
+	u32	wsetup;
+};
+
+struct aemif_device;
+
+int aemif_set_cs_timings(struct aemif_device *aemif, u8 cs, struct aemif_cs_timings *timings);
+int aemif_check_cs_timings(struct aemif_cs_timings *timings);
+
+#endif // __MEMORY_TI_AEMIF_H
diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h
index 8db52324f416..eae82f421414 100644
--- a/include/linux/mfd/da9063/core.h
+++ b/include/linux/mfd/da9063/core.h
@@ -78,6 +78,7 @@ struct da9063 {
 	enum da9063_type type;
 	unsigned char	variant_code;
 	unsigned int	flags;
+	bool use_sw_pm;
 
 	/* Control interface */
 	struct regmap	*regmap;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fc7e6153b73d..ea48eb879a0f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -524,6 +524,7 @@ enum {
 	 * creation/deletion on drivers rescan. Unset during device attach.
 	 */
 	MLX5_PRIV_FLAGS_DETACH = 1 << 2,
+	MLX5_PRIV_FLAGS_SWITCH_LEGACY = 1 << 3,
 };
 
 struct mlx5_adev {
@@ -1202,6 +1203,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev)
 	return dev->coredev_type == MLX5_COREDEV_VF;
 }
 
+static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1,
+					       const struct mlx5_core_dev *dev2)
+{
+	return dev1->coredev_type == dev2->coredev_type;
+}
+
 static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 {
 	return dev->caps.embedded_cpu;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4fbbcf35498b..48d47181c7cd 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2119,7 +2119,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   migration_in_chunks[0x1];
 	u8	   reserved_at_d1[0x1];
 	u8	   sf_eq_usage[0x1];
-	u8	   reserved_at_d3[0xd];
+	u8	   reserved_at_d3[0x5];
+	u8	   multiplane[0x1];
+	u8	   reserved_at_d9[0x7];
 
 	u8	   cross_vhca_object_to_object_supported[0x20];
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c39c4945946c..b1c3db9cf355 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -31,6 +31,7 @@
 #include <linux/kasan.h>
 #include <linux/memremap.h>
 #include <linux/slab.h>
+#include <linux/cacheinfo.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -3010,7 +3011,15 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc)
 	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
 }
 
-pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
+pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
+static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr,
+			pmd_t *pmdvalp)
+{
+	pte_t *pte;
+
+	__cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp));
+	return pte;
+}
 static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr)
 {
 	return __pte_offset_map(pmd, addr, NULL);
@@ -3023,7 +3032,8 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 
-	__cond_lock(*ptlp, pte = __pte_offset_map_lock(mm, pmd, addr, ptlp));
+	__cond_lock(RCU, __cond_lock(*ptlp,
+			pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)));
 	return pte;
 }
 
@@ -3115,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc)
 	if (!pmd_ptlock_init(ptdesc))
 		return false;
 	__folio_set_pgtable(folio);
+	ptdesc_pmd_pts_init(ptdesc);
 	lruvec_stat_add_folio(folio, NR_PAGETABLE);
 	return true;
 }
@@ -4091,6 +4102,37 @@ void mem_dump_obj(void *object);
 static inline void mem_dump_obj(void *object) {}
 #endif
 
+static inline bool is_write_sealed(int seals)
+{
+	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
+}
+
+/**
+ * is_readonly_sealed - Checks whether write-sealed but mapped read-only,
+ *                      in which case writes should be disallowing moving
+ *                      forwards.
+ * @seals: the seals to check
+ * @vm_flags: the VMA flags to check
+ *
+ * Returns whether readonly sealed, in which case writess should be disallowed
+ * going forward.
+ */
+static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags)
+{
+	/*
+	 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
+	 * MAP_SHARED and read-only, take care to not allow mprotect to
+	 * revert protections on such mappings. Do this only for shared
+	 * mappings. For private mappings, don't need to mask
+	 * VM_MAYWRITE as we still want them to be COW-writable.
+	 */
+	if (is_write_sealed(seals) &&
+	    ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED))
+		return true;
+
+	return false;
+}
+
 /**
  * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and
  *                    handle them.
@@ -4102,24 +4144,15 @@ static inline void mem_dump_obj(void *object) {}
  */
 static inline int seal_check_write(int seals, struct vm_area_struct *vma)
 {
-	if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
-		/*
-		 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
-		 * write seals are active.
-		 */
-		if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
-			return -EPERM;
-
-		/*
-		 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
-		 * MAP_SHARED and read-only, take care to not allow mprotect to
-		 * revert protections on such mappings. Do this only for shared
-		 * mappings. For private mappings, don't need to mask
-		 * VM_MAYWRITE as we still want them to be COW-writable.
-		 */
-		if (vma->vm_flags & VM_SHARED)
-			vm_flags_clear(vma, VM_MAYWRITE);
-	}
+	if (!is_write_sealed(seals))
+		return 0;
+
+	/*
+	 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
+	 * write seals are active.
+	 */
+	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
+		return -EPERM;
 
 	return 0;
 }
@@ -4175,6 +4208,23 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla
 }
 #endif
 
+/*
+ * user_alloc_needs_zeroing checks if a user folio from page allocator needs to
+ * be zeroed or not.
+ */
+static inline bool user_alloc_needs_zeroing(void)
+{
+	/*
+	 * for user folios, arch with cache aliasing requires cache flush and
+	 * arc changes folio->flags to make icache coherent with dcache, so
+	 * always return false to make caller use
+	 * clear_user_page()/clear_user_highpage().
+	 */
+	return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() ||
+	       !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+				   &init_on_alloc);
+}
+
 int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
 int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
 int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7361a8f3ab68..332cee285662 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a);
  * @pt_index:         Used for s390 gmap.
  * @pt_mm:            Used for x86 pgds.
  * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
+ * @pt_share_count:   Used for HugeTLB PMD page table share count.
  * @_pt_pad_2:        Padding to ensure proper alignment.
  * @ptl:              Lock for the page table.
  * @__page_type:      Same as page->page_type. Unused for page tables.
@@ -471,6 +472,9 @@ struct ptdesc {
 		pgoff_t pt_index;
 		struct mm_struct *pt_mm;
 		atomic_t pt_frag_refcount;
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+		atomic_t pt_share_count;
+#endif
 	};
 
 	union {
@@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
 	const struct page *:		(const struct ptdesc *)(p),	\
 	struct page *:			(struct ptdesc *)(p)))
 
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+	atomic_set(&ptdesc->pt_share_count, 0);
+}
+
+static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc)
+{
+	atomic_inc(&ptdesc->pt_share_count);
+}
+
+static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc)
+{
+	atomic_dec(&ptdesc->pt_share_count);
+}
+
+static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc)
+{
+	return atomic_read(&ptdesc->pt_share_count);
+}
+#else
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+}
+#endif
+
 /*
  * Used for sizing the vmemmap region on some architectures
  */
diff --git a/include/linux/module.h b/include/linux/module.h
index c60ee39cb9b1..94acbacdcdf1 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -296,7 +296,7 @@ extern typeof(name) __mod_device_table__##type##__##name		\
  * files require multiple MODULE_FIRMWARE() specifiers */
 #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware)
 
-#define MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, __stringify(ns))
+#define MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, ns)
 
 struct notifier_block;
 
diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h
new file mode 100644
index 000000000000..4d9b736ff8b7
--- /dev/null
+++ b/include/linux/mtd/nand-qpic-common.h
@@ -0,0 +1,478 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * QCOM QPIC common APIs header file
+ *
+ * Copyright (c) 2023 Qualcomm Inc.
+ * Authors:	Md sadre Alam	<quic_mdalam@quicinc.com>
+ *
+ */
+#ifndef __MTD_NAND_QPIC_COMMON_H__
+#define __MTD_NAND_QPIC_COMMON_H__
+
+/* NANDc reg offsets */
+#define	NAND_FLASH_CMD			0x00
+#define	NAND_ADDR0			0x04
+#define	NAND_ADDR1			0x08
+#define	NAND_FLASH_CHIP_SELECT		0x0c
+#define	NAND_EXEC_CMD			0x10
+#define	NAND_FLASH_STATUS		0x14
+#define	NAND_BUFFER_STATUS		0x18
+#define	NAND_DEV0_CFG0			0x20
+#define	NAND_DEV0_CFG1			0x24
+#define	NAND_DEV0_ECC_CFG		0x28
+#define	NAND_AUTO_STATUS_EN		0x2c
+#define	NAND_DEV1_CFG0			0x30
+#define	NAND_DEV1_CFG1			0x34
+#define	NAND_READ_ID			0x40
+#define	NAND_READ_STATUS		0x44
+#define	NAND_DEV_CMD0			0xa0
+#define	NAND_DEV_CMD1			0xa4
+#define	NAND_DEV_CMD2			0xa8
+#define	NAND_DEV_CMD_VLD		0xac
+#define	SFLASHC_BURST_CFG		0xe0
+#define	NAND_ERASED_CW_DETECT_CFG	0xe8
+#define	NAND_ERASED_CW_DETECT_STATUS	0xec
+#define	NAND_EBI2_ECC_BUF_CFG		0xf0
+#define	FLASH_BUF_ACC			0x100
+
+#define	NAND_CTRL			0xf00
+#define	NAND_VERSION			0xf08
+#define	NAND_READ_LOCATION_0		0xf20
+#define	NAND_READ_LOCATION_1		0xf24
+#define	NAND_READ_LOCATION_2		0xf28
+#define	NAND_READ_LOCATION_3		0xf2c
+#define	NAND_READ_LOCATION_LAST_CW_0	0xf40
+#define	NAND_READ_LOCATION_LAST_CW_1	0xf44
+#define	NAND_READ_LOCATION_LAST_CW_2	0xf48
+#define	NAND_READ_LOCATION_LAST_CW_3	0xf4c
+
+/* dummy register offsets, used by qcom_write_reg_dma */
+#define	NAND_DEV_CMD1_RESTORE		0xdead
+#define	NAND_DEV_CMD_VLD_RESTORE	0xbeef
+
+/* NAND_FLASH_CMD bits */
+#define	PAGE_ACC			BIT(4)
+#define	LAST_PAGE			BIT(5)
+
+/* NAND_FLASH_CHIP_SELECT bits */
+#define	NAND_DEV_SEL			0
+#define	DM_EN				BIT(2)
+
+/* NAND_FLASH_STATUS bits */
+#define	FS_OP_ERR			BIT(4)
+#define	FS_READY_BSY_N			BIT(5)
+#define	FS_MPU_ERR			BIT(8)
+#define	FS_DEVICE_STS_ERR		BIT(16)
+#define	FS_DEVICE_WP			BIT(23)
+
+/* NAND_BUFFER_STATUS bits */
+#define	BS_UNCORRECTABLE_BIT		BIT(8)
+#define	BS_CORRECTABLE_ERR_MSK		0x1f
+
+/* NAND_DEVn_CFG0 bits */
+#define	DISABLE_STATUS_AFTER_WRITE	BIT(4)
+#define	CW_PER_PAGE			6
+#define	CW_PER_PAGE_MASK		GENMASK(8, 6)
+#define	UD_SIZE_BYTES			9
+#define	UD_SIZE_BYTES_MASK		GENMASK(18, 9)
+#define	ECC_PARITY_SIZE_BYTES_RS	GENMASK(22, 19)
+#define	SPARE_SIZE_BYTES		23
+#define	SPARE_SIZE_BYTES_MASK		GENMASK(26, 23)
+#define	NUM_ADDR_CYCLES			27
+#define	NUM_ADDR_CYCLES_MASK		GENMASK(29, 27)
+#define	STATUS_BFR_READ			BIT(30)
+#define	SET_RD_MODE_AFTER_STATUS	BIT(31)
+
+/* NAND_DEVn_CFG0 bits */
+#define	DEV0_CFG1_ECC_DISABLE		BIT(0)
+#define	WIDE_FLASH			BIT(1)
+#define	NAND_RECOVERY_CYCLES		2
+#define	NAND_RECOVERY_CYCLES_MASK	GENMASK(4, 2)
+#define	CS_ACTIVE_BSY			BIT(5)
+#define	BAD_BLOCK_BYTE_NUM		6
+#define	BAD_BLOCK_BYTE_NUM_MASK		GENMASK(15, 6)
+#define	BAD_BLOCK_IN_SPARE_AREA		BIT(16)
+#define	WR_RD_BSY_GAP			17
+#define	WR_RD_BSY_GAP_MASK		GENMASK(22, 17)
+#define	ENABLE_BCH_ECC			BIT(27)
+
+/* NAND_DEV0_ECC_CFG bits */
+#define	ECC_CFG_ECC_DISABLE		BIT(0)
+#define	ECC_SW_RESET			BIT(1)
+#define	ECC_MODE			4
+#define	ECC_MODE_MASK			GENMASK(5, 4)
+#define	ECC_PARITY_SIZE_BYTES_BCH	8
+#define	ECC_PARITY_SIZE_BYTES_BCH_MASK	GENMASK(12, 8)
+#define	ECC_NUM_DATA_BYTES		16
+#define	ECC_NUM_DATA_BYTES_MASK		GENMASK(25, 16)
+#define	ECC_FORCE_CLK_OPEN		BIT(30)
+
+/* NAND_DEV_CMD1 bits */
+#define	READ_ADDR			0
+
+/* NAND_DEV_CMD_VLD bits */
+#define	READ_START_VLD			BIT(0)
+#define	READ_STOP_VLD			BIT(1)
+#define	WRITE_START_VLD			BIT(2)
+#define	ERASE_START_VLD			BIT(3)
+#define	SEQ_READ_START_VLD		BIT(4)
+
+/* NAND_EBI2_ECC_BUF_CFG bits */
+#define	NUM_STEPS			0
+
+/* NAND_ERASED_CW_DETECT_CFG bits */
+#define	ERASED_CW_ECC_MASK		1
+#define	AUTO_DETECT_RES			0
+#define	MASK_ECC			BIT(ERASED_CW_ECC_MASK)
+#define	RESET_ERASED_DET		BIT(AUTO_DETECT_RES)
+#define	ACTIVE_ERASED_DET		(0 << AUTO_DETECT_RES)
+#define	CLR_ERASED_PAGE_DET		(RESET_ERASED_DET | MASK_ECC)
+#define	SET_ERASED_PAGE_DET		(ACTIVE_ERASED_DET | MASK_ECC)
+
+/* NAND_ERASED_CW_DETECT_STATUS bits */
+#define	PAGE_ALL_ERASED			BIT(7)
+#define	CODEWORD_ALL_ERASED		BIT(6)
+#define	PAGE_ERASED			BIT(5)
+#define	CODEWORD_ERASED			BIT(4)
+#define	ERASED_PAGE			(PAGE_ALL_ERASED | PAGE_ERASED)
+#define	ERASED_CW			(CODEWORD_ALL_ERASED | CODEWORD_ERASED)
+
+/* NAND_READ_LOCATION_n bits */
+#define READ_LOCATION_OFFSET		0
+#define READ_LOCATION_SIZE		16
+#define READ_LOCATION_LAST		31
+
+/* Version Mask */
+#define	NAND_VERSION_MAJOR_MASK		0xf0000000
+#define	NAND_VERSION_MAJOR_SHIFT	28
+#define	NAND_VERSION_MINOR_MASK		0x0fff0000
+#define	NAND_VERSION_MINOR_SHIFT	16
+
+/* NAND OP_CMDs */
+#define	OP_PAGE_READ			0x2
+#define	OP_PAGE_READ_WITH_ECC		0x3
+#define	OP_PAGE_READ_WITH_ECC_SPARE	0x4
+#define	OP_PAGE_READ_ONFI_READ		0x5
+#define	OP_PROGRAM_PAGE			0x6
+#define	OP_PAGE_PROGRAM_WITH_ECC	0x7
+#define	OP_PROGRAM_PAGE_SPARE		0x9
+#define	OP_BLOCK_ERASE			0xa
+#define	OP_CHECK_STATUS			0xc
+#define	OP_FETCH_ID			0xb
+#define	OP_RESET_DEVICE			0xd
+
+/* Default Value for NAND_DEV_CMD_VLD */
+#define NAND_DEV_CMD_VLD_VAL		(READ_START_VLD | WRITE_START_VLD | \
+					 ERASE_START_VLD | SEQ_READ_START_VLD)
+
+/* NAND_CTRL bits */
+#define	BAM_MODE_EN			BIT(0)
+
+/*
+ * the NAND controller performs reads/writes with ECC in 516 byte chunks.
+ * the driver calls the chunks 'step' or 'codeword' interchangeably
+ */
+#define	NANDC_STEP_SIZE			512
+
+/*
+ * the largest page size we support is 8K, this will have 16 steps/codewords
+ * of 512 bytes each
+ */
+#define	MAX_NUM_STEPS			(SZ_8K / NANDC_STEP_SIZE)
+
+/* we read at most 3 registers per codeword scan */
+#define	MAX_REG_RD			(3 * MAX_NUM_STEPS)
+
+/* ECC modes supported by the controller */
+#define	ECC_NONE	BIT(0)
+#define	ECC_RS_4BIT	BIT(1)
+#define	ECC_BCH_4BIT	BIT(2)
+#define	ECC_BCH_8BIT	BIT(3)
+
+/*
+ * Returns the actual register address for all NAND_DEV_ registers
+ * (i.e. NAND_DEV_CMD0, NAND_DEV_CMD1, NAND_DEV_CMD2 and NAND_DEV_CMD_VLD)
+ */
+#define dev_cmd_reg_addr(nandc, reg) ((nandc)->props->dev_cmd_reg_start + (reg))
+
+/* Returns the NAND register physical address */
+#define nandc_reg_phys(chip, offset) ((chip)->base_phys + (offset))
+
+/* Returns the dma address for reg read buffer */
+#define reg_buf_dma_addr(chip, vaddr) \
+	((chip)->reg_read_dma + \
+	((u8 *)(vaddr) - (u8 *)(chip)->reg_read_buf))
+
+#define QPIC_PER_CW_CMD_ELEMENTS	32
+#define QPIC_PER_CW_CMD_SGL		32
+#define QPIC_PER_CW_DATA_SGL		8
+
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
+/*
+ * Flags used in DMA descriptor preparation helper functions
+ * (i.e. qcom_read_reg_dma/qcom_write_reg_dma/qcom_read_data_dma/qcom_write_data_dma)
+ */
+/* Don't set the EOT in current tx BAM sgl */
+#define NAND_BAM_NO_EOT			BIT(0)
+/* Set the NWD flag in current BAM sgl */
+#define NAND_BAM_NWD			BIT(1)
+/* Finish writing in the current BAM sgl and start writing in another BAM sgl */
+#define NAND_BAM_NEXT_SGL		BIT(2)
+/*
+ * Erased codeword status is being used two times in single transfer so this
+ * flag will determine the current value of erased codeword status register
+ */
+#define NAND_ERASED_CW_SET		BIT(4)
+
+#define MAX_ADDRESS_CYCLE		5
+
+/*
+ * This data type corresponds to the BAM transaction which will be used for all
+ * NAND transfers.
+ * @bam_ce - the array of BAM command elements
+ * @cmd_sgl - sgl for NAND BAM command pipe
+ * @data_sgl - sgl for NAND BAM consumer/producer pipe
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
+ * @txn_done - completion for NAND transfer.
+ * @bam_ce_pos - the index in bam_ce which is available for next sgl
+ * @bam_ce_start - the index in bam_ce which marks the start position ce
+ *		   for current sgl. It will be used for size calculation
+ *		   for current sgl
+ * @cmd_sgl_pos - current index in command sgl.
+ * @cmd_sgl_start - start index in command sgl.
+ * @tx_sgl_pos - current index in data sgl for tx.
+ * @tx_sgl_start - start index in data sgl for tx.
+ * @rx_sgl_pos - current index in data sgl for rx.
+ * @rx_sgl_start - start index in data sgl for rx.
+ */
+struct bam_transaction {
+	struct bam_cmd_element *bam_ce;
+	struct scatterlist *cmd_sgl;
+	struct scatterlist *data_sgl;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
+	struct completion txn_done;
+	struct_group(bam_positions,
+		u32 bam_ce_pos;
+		u32 bam_ce_start;
+		u32 cmd_sgl_pos;
+		u32 cmd_sgl_start;
+		u32 tx_sgl_pos;
+		u32 tx_sgl_start;
+		u32 rx_sgl_pos;
+		u32 rx_sgl_start;
+
+	);
+};
+
+/*
+ * This data type corresponds to the nand dma descriptor
+ * @dma_desc - low level DMA engine descriptor
+ * @list - list for desc_info
+ *
+ * @adm_sgl - sgl which will be used for single sgl dma descriptor. Only used by
+ *	      ADM
+ * @bam_sgl - sgl which will be used for dma descriptor. Only used by BAM
+ * @sgl_cnt - number of SGL in bam_sgl. Only used by BAM
+ * @dir - DMA transfer direction
+ */
+struct desc_info {
+	struct dma_async_tx_descriptor *dma_desc;
+	struct list_head node;
+
+	union {
+		struct scatterlist adm_sgl;
+		struct {
+			struct scatterlist *bam_sgl;
+			int sgl_cnt;
+		};
+	};
+	enum dma_data_direction dir;
+};
+
+/*
+ * holds the current register values that we want to write. acts as a contiguous
+ * chunk of memory which we use to write the controller registers through DMA.
+ */
+struct nandc_regs {
+	__le32 cmd;
+	__le32 addr0;
+	__le32 addr1;
+	__le32 chip_sel;
+	__le32 exec;
+
+	__le32 cfg0;
+	__le32 cfg1;
+	__le32 ecc_bch_cfg;
+
+	__le32 clrflashstatus;
+	__le32 clrreadstatus;
+
+	__le32 cmd1;
+	__le32 vld;
+
+	__le32 orig_cmd1;
+	__le32 orig_vld;
+
+	__le32 ecc_buf_cfg;
+	__le32 read_location0;
+	__le32 read_location1;
+	__le32 read_location2;
+	__le32 read_location3;
+	__le32 read_location_last0;
+	__le32 read_location_last1;
+	__le32 read_location_last2;
+	__le32 read_location_last3;
+
+	__le32 erased_cw_detect_cfg_clr;
+	__le32 erased_cw_detect_cfg_set;
+};
+
+/*
+ * NAND controller data struct
+ *
+ * @dev:			parent device
+ *
+ * @base:			MMIO base
+ *
+ * @core_clk:			controller clock
+ * @aon_clk:			another controller clock
+ *
+ * @regs:			a contiguous chunk of memory for DMA register
+ *				writes. contains the register values to be
+ *				written to controller
+ *
+ * @props:			properties of current NAND controller,
+ *				initialized via DT match data
+ *
+ * @controller:			base controller structure
+ * @host_list:			list containing all the chips attached to the
+ *				controller
+ *
+ * @chan:			dma channel
+ * @cmd_crci:			ADM DMA CRCI for command flow control
+ * @data_crci:			ADM DMA CRCI for data flow control
+ *
+ * @desc_list:			DMA descriptor list (list of desc_infos)
+ *
+ * @data_buffer:		our local DMA buffer for page read/writes,
+ *				used when we can't use the buffer provided
+ *				by upper layers directly
+ * @reg_read_buf:		local buffer for reading back registers via DMA
+ *
+ * @base_phys:			physical base address of controller registers
+ * @base_dma:			dma base address of controller registers
+ * @reg_read_dma:		contains dma address for register read buffer
+ *
+ * @buf_size/count/start:	markers for chip->legacy.read_buf/write_buf
+ *				functions
+ * @max_cwperpage:		maximum QPIC codewords required. calculated
+ *				from all connected NAND devices pagesize
+ *
+ * @reg_read_pos:		marker for data read in reg_read_buf
+ *
+ * @cmd1/vld:			some fixed controller register values
+ *
+ * @exec_opwrite:		flag to select correct number of code word
+ *				while reading status
+ */
+struct qcom_nand_controller {
+	struct device *dev;
+
+	void __iomem *base;
+
+	struct clk *core_clk;
+	struct clk *aon_clk;
+
+	struct nandc_regs *regs;
+	struct bam_transaction *bam_txn;
+
+	const struct qcom_nandc_props *props;
+
+	struct nand_controller *controller;
+	struct list_head host_list;
+
+	union {
+		/* will be used only by QPIC for BAM DMA */
+		struct {
+			struct dma_chan *tx_chan;
+			struct dma_chan *rx_chan;
+			struct dma_chan *cmd_chan;
+		};
+
+		/* will be used only by EBI2 for ADM DMA */
+		struct {
+			struct dma_chan *chan;
+			unsigned int cmd_crci;
+			unsigned int data_crci;
+		};
+	};
+
+	struct list_head desc_list;
+
+	u8		*data_buffer;
+	__le32		*reg_read_buf;
+
+	phys_addr_t base_phys;
+	dma_addr_t base_dma;
+	dma_addr_t reg_read_dma;
+
+	int		buf_size;
+	int		buf_count;
+	int		buf_start;
+	unsigned int	max_cwperpage;
+
+	int reg_read_pos;
+
+	u32 cmd1, vld;
+	bool exec_opwrite;
+};
+
+/*
+ * This data type corresponds to the NAND controller properties which varies
+ * among different NAND controllers.
+ * @ecc_modes - ecc mode for NAND
+ * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset
+ * @supports_bam - whether NAND controller is using BAM
+ * @nandc_part_of_qpic - whether NAND controller is part of qpic IP
+ * @qpic_version2 - flag to indicate QPIC IP version 2
+ * @use_codeword_fixup - whether NAND has different layout for boot partitions
+ */
+struct qcom_nandc_props {
+	u32 ecc_modes;
+	u32 dev_cmd_reg_start;
+	bool supports_bam;
+	bool nandc_part_of_qpic;
+	bool qpic_version2;
+	bool use_codeword_fixup;
+};
+
+void qcom_free_bam_transaction(struct qcom_nand_controller *nandc);
+struct bam_transaction *qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc);
+void qcom_clear_bam_transaction(struct qcom_nand_controller *nandc);
+void qcom_qpic_bam_dma_done(void *data);
+void qcom_nandc_dev_to_mem(struct qcom_nand_controller *nandc, bool is_cpu);
+int qcom_prepare_bam_async_desc(struct qcom_nand_controller *nandc,
+				struct dma_chan *chan, unsigned long flags);
+int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read,
+			       int reg_off, const void *vaddr, int size, unsigned int flags);
+int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read,
+				const void *vaddr, int size, unsigned int flags);
+int qcom_prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, int reg_off,
+			   const void *vaddr, int size, bool flow_control);
+int qcom_read_reg_dma(struct qcom_nand_controller *nandc, int first, int num_regs,
+		      unsigned int flags);
+int qcom_write_reg_dma(struct qcom_nand_controller *nandc, __le32 *vaddr, int first,
+		       int num_regs, unsigned int flags);
+int qcom_read_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr,
+		       int size, unsigned int flags);
+int qcom_write_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr,
+			int size, unsigned int flags);
+int qcom_submit_descs(struct qcom_nand_controller *nandc);
+void qcom_clear_read_regs(struct qcom_nand_controller *nandc);
+void qcom_nandc_unalloc(struct qcom_nand_controller *nandc);
+int qcom_nandc_alloc(struct qcom_nand_controller *nandc);
+#endif
+
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 702e5fb13dae..0da8a1c7740e 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -62,18 +62,38 @@
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len)	\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
+#define SPINAND_PAGE_READ_FROM_CACHE_OP(addr, ndummy, buf, len, ...) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   __VA_OPT__(SPI_MEM_OP_MAX_FREQ(__VA_ARGS__)))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP(addr, ndummy, buf, len) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),			\
+			 SPI_MEM_OP_ADDR(2, addr, 1),			\
+			 SPI_MEM_OP_DUMMY(ndummy, 1),			\
+			 SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(addr, ndummy, buf, len) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 1))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(fast, addr, ndummy, buf, len) \
-	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
+#define SPINAND_PAGE_READ_FROM_CACHE_FAST_OP_3A(addr, ndummy, buf, len) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 1))
 
+#define SPINAND_PAGE_READ_FROM_CACHE_DTR_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
 #define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len)	\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
@@ -86,6 +106,13 @@
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 2))
 
+#define SPINAND_PAGE_READ_FROM_CACHE_X2_DTR_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
 #define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len)	\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
@@ -98,6 +125,13 @@
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 4))
 
+#define SPINAND_PAGE_READ_FROM_CACHE_X4_DTR_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
 #define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len)	\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 2),				\
@@ -110,6 +144,13 @@
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 2))
 
+#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_DTR_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbd, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 2),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 2),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
 #define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len)	\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 4),				\
@@ -122,6 +163,13 @@
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 4))
 
+#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_DTR_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xed, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 4),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 4),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
 #define SPINAND_PROG_EXEC_OP(addr)					\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
@@ -268,6 +316,7 @@ extern const struct spinand_manufacturer gigadevice_spinand_manufacturer;
 extern const struct spinand_manufacturer macronix_spinand_manufacturer;
 extern const struct spinand_manufacturer micron_spinand_manufacturer;
 extern const struct spinand_manufacturer paragon_spinand_manufacturer;
+extern const struct spinand_manufacturer skyhigh_spinand_manufacturer;
 extern const struct spinand_manufacturer toshiba_spinand_manufacturer;
 extern const struct spinand_manufacturer winbond_spinand_manufacturer;
 extern const struct spinand_manufacturer xtx_spinand_manufacturer;
@@ -314,6 +363,7 @@ struct spinand_ecc_info {
 #define SPINAND_HAS_CR_FEAT_BIT		BIT(1)
 #define SPINAND_HAS_PROG_PLANE_SELECT_BIT		BIT(2)
 #define SPINAND_HAS_READ_PLANE_SELECT_BIT		BIT(3)
+#define SPINAND_NO_RAW_ACCESS				BIT(4)
 
 /**
  * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 66e7d26b70a4..11be70a7929f 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -253,4 +253,11 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 				 NETIF_F_GSO_UDP_TUNNEL |		\
 				 NETIF_F_GSO_UDP_TUNNEL_CSUM)
 
+static inline netdev_features_t netdev_base_features(netdev_features_t features)
+{
+	features &= ~NETIF_F_ONE_FOR_ALL;
+	features |= NETIF_F_ALL_FOR_ALL;
+	return features;
+}
+
 #endif	/* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 2220bfec278e..691506bdf2c5 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -306,7 +306,7 @@ static const unsigned long *const_folio_flags(const struct folio *folio,
 {
 	const struct page *page = &folio->page;
 
-	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	VM_BUG_ON_PGFLAGS(page->compound_head & 1, page);
 	VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
 	return &page[n].flags;
 }
@@ -315,7 +315,7 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n)
 {
 	struct page *page = &folio->page;
 
-	VM_BUG_ON_PGFLAGS(PageTail(page), page);
+	VM_BUG_ON_PGFLAGS(page->compound_head & 1, page);
 	VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
 	return &page[n].flags;
 }
@@ -862,18 +862,10 @@ static inline void ClearPageCompound(struct page *page)
 	ClearPageHead(page);
 }
 FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE)
-FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
-/*
- * PG_partially_mapped is protected by deferred_split split_queue_lock,
- * so its safe to use non-atomic set/clear.
- */
-__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
-__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
+FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
 #else
 FOLIO_FLAG_FALSE(large_rmappable)
-FOLIO_TEST_FLAG_FALSE(partially_mapped)
-__FOLIO_SET_FLAG_NOOP(partially_mapped)
-__FOLIO_CLEAR_FLAG_NOOP(partially_mapped)
+FOLIO_FLAG_FALSE(partially_mapped)
 #endif
 
 #define PG_head_mask ((1UL << PG_head))
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 35842d1e3879..5b520fe86b60 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -221,10 +221,7 @@ do {									\
 } while (0)
 
 #define PERCPU_PTR(__p)							\
-({									\
-	unsigned long __pcpu_ptr = (__force unsigned long)(__p);	\
-	(typeof(*(__p)) __force __kernel *)(__pcpu_ptr);		\
-})
+	(typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p))
 
 #ifdef CONFIG_SMP
 
diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
index 0e43ab653ab6..3469c4b20105 100644
--- a/include/linux/pgalloc_tag.h
+++ b/include/linux/pgalloc_tag.h
@@ -231,7 +231,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
 }
 
 void pgalloc_tag_split(struct folio *folio, int old_order, int new_order);
-void pgalloc_tag_copy(struct folio *new, struct folio *old);
+void pgalloc_tag_swap(struct folio *new, struct folio *old);
 
 void __init alloc_tag_sec_init(void);
 
@@ -245,7 +245,7 @@ static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL
 static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {}
 static inline void alloc_tag_sec_init(void) {}
 static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {}
-static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) {}
+static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {}
 
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
diff --git a/include/linux/platform_data/amd_qdma.h b/include/linux/platform_data/amd_qdma.h
index 576d952f97ed..967a6ef31cf9 100644
--- a/include/linux/platform_data/amd_qdma.h
+++ b/include/linux/platform_data/amd_qdma.h
@@ -26,11 +26,13 @@ struct dma_slave_map;
  * @max_mm_channels: Maximum number of MM DMA channels in each direction
  * @device_map: DMA slave map
  * @irq_index: The index of first IRQ
+ * @dma_dev: The device pointer for dma operations
  */
 struct qdma_platdata {
 	u32			max_mm_channels;
 	u32			irq_index;
 	struct dma_slave_map	*device_map;
+	struct device		*dma_dev;
 };
 
 #endif /* _PLATDATA_AMD_QDMA_H */
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 7132623e4658..074754c23d33 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -235,17 +235,7 @@ extern void platform_device_put(struct platform_device *pdev);
 
 struct platform_driver {
 	int (*probe)(struct platform_device *);
-
-	/*
-	 * .remove_new() is a relic from a prototype conversion of .remove().
-	 * New drivers are supposed to implement .remove(). Once all drivers are
-	 * converted to not use .remove_new any more, it will be dropped.
-	 */
-	union {
-		void (*remove)(struct platform_device *);
-		void (*remove_new)(struct platform_device *);
-	};
-
+	void (*remove)(struct platform_device *);
 	void (*shutdown)(struct platform_device *);
 	int (*suspend)(struct platform_device *, pm_message_t state);
 	int (*resume)(struct platform_device *);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 97b0e23363c8..e7f0260f15ad 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -385,7 +385,7 @@ const struct dev_pm_ops name = { \
 #ifdef CONFIG_PM
 #define _EXPORT_DEV_PM_OPS(name, license, ns)		_EXPORT_PM_OPS(name, license, ns)
 #define EXPORT_PM_FN_GPL(name)				EXPORT_SYMBOL_GPL(name)
-#define EXPORT_PM_FN_NS_GPL(name, ns)			EXPORT_SYMBOL_NS_GPL(name, ns)
+#define EXPORT_PM_FN_NS_GPL(name, ns)			EXPORT_SYMBOL_NS_GPL(name, "ns")
 #else
 #define _EXPORT_DEV_PM_OPS(name, license, ns)		_DISCARD_PM_OPS(name, license, ns)
 #define EXPORT_PM_FN_GPL(name)
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 78827f312407..6853e29d9674 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -8,7 +8,7 @@
 #include <linux/mutex.h>
 #include <linux/of.h>
 
-MODULE_IMPORT_NS(PWM);
+MODULE_IMPORT_NS("PWM");
 
 struct pwm_chip;
 
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index c5e2239b550e..d836e7440ee8 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -313,7 +313,7 @@ static inline void sg_dma_mark_bus_address(struct scatterlist *sg)
 }
 
 /**
- * sg_unmark_bus_address - Unmark the scatterlist entry as a bus address
+ * sg_dma_unmark_bus_address - Unmark the scatterlist entry as a bus address
  * @sg:		 SG entry
  *
  * Description:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d380bffee2ef..64934e0830af 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -656,6 +656,12 @@ struct sched_dl_entity {
 	 * @dl_defer_armed tells if the deferrable server is waiting
 	 * for the replenishment timer to activate it.
 	 *
+	 * @dl_server_active tells if the dlserver is active(started).
+	 * dlserver is started on first cfs enqueue on an idle runqueue
+	 * and is stopped when a dequeue results in 0 cfs tasks on the
+	 * runqueue. In other words, dlserver is active only when cpu's
+	 * runqueue has atleast one cfs task.
+	 *
 	 * @dl_defer_running tells if the deferrable server is actually
 	 * running, skipping the defer phase.
 	 */
@@ -664,6 +670,7 @@ struct sched_dl_entity {
 	unsigned int			dl_non_contending : 1;
 	unsigned int			dl_overrun	  : 1;
 	unsigned int			dl_server         : 1;
+	unsigned int			dl_server_active  : 1;
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;
@@ -1630,8 +1637,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state,
 	 * We're lying here, but rather than expose a completely new task state
 	 * to userspace, we can make this appear as if the task has gone through
 	 * a regular rt_mutex_lock() call.
+	 * Report frozen tasks as uninterruptible.
 	 */
-	if (tsk_state & TASK_RTLOCK_WAIT)
+	if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN))
 		state = TASK_UNINTERRUPTIBLE;
 
 	return fls(state);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index d9b03e0746e7..2cbe0c22a32f 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
-static inline void sk_psock_queue_msg(struct sk_psock *psock,
+static inline bool sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
+	bool ret;
+
 	spin_lock_bh(&psock->ingress_lock);
-	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 		list_add_tail(&msg->list, &psock->ingress_msg);
-	else {
+		ret = true;
+	} else {
 		sk_msg_free(psock->sk, msg);
 		kfree(msg);
+		ret = false;
 	}
 	spin_unlock_bh(&psock->ingress_lock);
+	return ret;
 }
 
 static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock)
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index c46d2b8029be..c4830dfaff3d 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -15,16 +15,32 @@
 
 #define SPI_MEM_OP_CMD(__opcode, __buswidth)			\
 	{							\
+		.nbytes = 1,					\
 		.buswidth = __buswidth,				\
 		.opcode = __opcode,				\
+	}
+
+#define SPI_MEM_DTR_OP_CMD(__opcode, __buswidth)		\
+	{							\
 		.nbytes = 1,					\
+		.opcode = __opcode,				\
+		.buswidth = __buswidth,				\
+		.dtr = true,					\
 	}
 
 #define SPI_MEM_OP_ADDR(__nbytes, __val, __buswidth)		\
 	{							\
 		.nbytes = __nbytes,				\
+		.buswidth = __buswidth,				\
+		.val = __val,					\
+	}
+
+#define SPI_MEM_DTR_OP_ADDR(__nbytes, __val, __buswidth)	\
+	{							\
+		.nbytes = __nbytes,				\
 		.val = __val,					\
 		.buswidth = __buswidth,				\
+		.dtr = true,					\
 	}
 
 #define SPI_MEM_OP_NO_ADDR	{ }
@@ -35,22 +51,47 @@
 		.buswidth = __buswidth,				\
 	}
 
+#define SPI_MEM_DTR_OP_DUMMY(__nbytes, __buswidth)		\
+	{							\
+		.nbytes = __nbytes,				\
+		.buswidth = __buswidth,				\
+		.dtr = true,					\
+	}
+
 #define SPI_MEM_OP_NO_DUMMY	{ }
 
 #define SPI_MEM_OP_DATA_IN(__nbytes, __buf, __buswidth)		\
 	{							\
+		.buswidth = __buswidth,				\
+		.dir = SPI_MEM_DATA_IN,				\
+		.nbytes = __nbytes,				\
+		.buf.in = __buf,				\
+	}
+
+#define SPI_MEM_DTR_OP_DATA_IN(__nbytes, __buf, __buswidth)	\
+	{							\
 		.dir = SPI_MEM_DATA_IN,				\
 		.nbytes = __nbytes,				\
 		.buf.in = __buf,				\
 		.buswidth = __buswidth,				\
+		.dtr = true,					\
 	}
 
 #define SPI_MEM_OP_DATA_OUT(__nbytes, __buf, __buswidth)	\
 	{							\
+		.buswidth = __buswidth,				\
+		.dir = SPI_MEM_DATA_OUT,			\
+		.nbytes = __nbytes,				\
+		.buf.out = __buf,				\
+	}
+
+#define SPI_MEM_DTR_OP_DATA_OUT(__nbytes, __buf, __buswidth)	\
+	{							\
 		.dir = SPI_MEM_DATA_OUT,			\
 		.nbytes = __nbytes,				\
 		.buf.out = __buf,				\
 		.buswidth = __buswidth,				\
+		.dtr = true,					\
 	}
 
 #define SPI_MEM_OP_NO_DATA	{ }
@@ -68,6 +109,9 @@ enum spi_mem_data_dir {
 	SPI_MEM_DATA_OUT,
 };
 
+#define SPI_MEM_OP_MAX_FREQ(__freq)				\
+	.max_freq = __freq
+
 /**
  * struct spi_mem_op - describes a SPI memory operation
  * @cmd.nbytes: number of opcode bytes (only 1 or 2 are valid). The opcode is
@@ -97,6 +141,9 @@ enum spi_mem_data_dir {
  *		 operation does not involve transferring data
  * @data.buf.in: input buffer (must be DMA-able)
  * @data.buf.out: output buffer (must be DMA-able)
+ * @max_freq: frequency limitation wrt this operation. 0 means there is no
+ *	      specific constraint and the highest achievable frequency can be
+ *	      attempted.
  */
 struct spi_mem_op {
 	struct {
@@ -135,14 +182,17 @@ struct spi_mem_op {
 			const void *out;
 		} buf;
 	} data;
+
+	unsigned int max_freq;
 };
 
-#define SPI_MEM_OP(__cmd, __addr, __dummy, __data)		\
+#define SPI_MEM_OP(__cmd, __addr, __dummy, __data, ...)		\
 	{							\
 		.cmd = __cmd,					\
 		.addr = __addr,					\
 		.dummy = __dummy,				\
 		.data = __data,					\
+		__VA_ARGS__					\
 	}
 
 /**
@@ -302,11 +352,13 @@ struct spi_controller_mem_ops {
  * @ecc: Supports operations with error correction
  * @swap16: Supports swapping bytes on a 16 bit boundary when configured in
  *	    Octal DTR
+ * @per_op_freq: Supports per operation frequency switching
  */
 struct spi_controller_mem_caps {
 	bool dtr;
 	bool ecc;
 	bool swap16;
+	bool per_op_freq;
 };
 
 #define spi_mem_controller_is_capable(ctlr, cap)	\
@@ -371,6 +423,8 @@ bool spi_mem_default_supports_op(struct spi_mem *mem,
 #endif /* CONFIG_SPI_MEM */
 
 int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op);
+void spi_mem_adjust_op_freq(struct spi_mem *mem, struct spi_mem_op *op);
+u64 spi_mem_calc_op_duration(struct spi_mem_op *op);
 
 bool spi_mem_supports_op(struct spi_mem *mem,
 			 const struct spi_mem_op *op);
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index e9ec32fb97d4..2cc21ffcdaf9 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -147,7 +147,7 @@ static inline int stack_depot_early_init(void)	{ return 0; }
  * If the provided stack trace comes from the interrupt context, only the part
  * up to the interrupt entry is saved.
  *
- * Context: Any context, but setting STACK_DEPOT_FLAG_CAN_ALLOC is required if
+ * Context: Any context, but unsetting STACK_DEPOT_FLAG_CAN_ALLOC is required if
  *          alloc_pages() cannot be used from the current context. Currently
  *          this is the case for contexts where neither %GFP_ATOMIC nor
  *          %GFP_NOWAIT can be used (NMI, raw_spin_lock).
@@ -156,7 +156,7 @@ static inline int stack_depot_early_init(void)	{ return 0; }
  */
 depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 					    unsigned int nr_entries,
-					    gfp_t gfp_flags,
+					    gfp_t alloc_flags,
 					    depot_flags_t depot_flags);
 
 /**
@@ -175,7 +175,7 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
  * Return: Handle of the stack trace stored in depot, 0 on failure
  */
 depot_stack_handle_t stack_depot_save(unsigned long *entries,
-				      unsigned int nr_entries, gfp_t gfp_flags);
+				      unsigned int nr_entries, gfp_t alloc_flags);
 
 /**
  * __stack_depot_get_stack_record - Get a pointer to a stack_record struct
diff --git a/include/linux/static_call.h b/include/linux/static_call.h
index 141e6b176a1b..78a77a4ae0ea 100644
--- a/include/linux/static_call.h
+++ b/include/linux/static_call.h
@@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #ifdef CONFIG_HAVE_STATIC_CALL_INLINE
 
+extern int static_call_initialized;
+
 extern int __init static_call_init(void);
 
 extern void static_call_force_reinit(void);
@@ -225,6 +227,8 @@ extern long __static_call_return0(void);
 
 #elif defined(CONFIG_HAVE_STATIC_CALL)
 
+#define static_call_initialized 0
+
 static inline int static_call_init(void) { return 0; }
 
 #define DEFINE_STATIC_CALL(name, _func)					\
@@ -281,6 +285,8 @@ extern long __static_call_return0(void);
 
 #else /* Generic implementation */
 
+#define static_call_initialized 0
+
 static inline int static_call_init(void) { return 0; }
 
 static inline long __static_call_return0(void)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 2a5df5b62cfc..58ad4ead33fc 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -273,7 +273,8 @@ struct trace_event_fields {
 			const char *name;
 			const int  size;
 			const int  align;
-			const int  is_signed;
+			const unsigned int is_signed:1;
+			unsigned int needs_test:1;
 			const int  filter_type;
 			const int  len;
 		};
@@ -324,6 +325,7 @@ enum {
 	TRACE_EVENT_FL_EPROBE_BIT,
 	TRACE_EVENT_FL_FPROBE_BIT,
 	TRACE_EVENT_FL_CUSTOM_BIT,
+	TRACE_EVENT_FL_TEST_STR_BIT,
 };
 
 /*
@@ -340,6 +342,7 @@ enum {
  *  CUSTOM        - Event is a custom event (to be attached to an exsiting tracepoint)
  *                   This is set when the custom event has not been attached
  *                   to a tracepoint yet, then it is cleared when it is.
+ *  TEST_STR      - The event has a "%s" that points to a string outside the event
  */
 enum {
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
@@ -352,6 +355,7 @@ enum {
 	TRACE_EVENT_FL_EPROBE		= (1 << TRACE_EVENT_FL_EPROBE_BIT),
 	TRACE_EVENT_FL_FPROBE		= (1 << TRACE_EVENT_FL_FPROBE_BIT),
 	TRACE_EVENT_FL_CUSTOM		= (1 << TRACE_EVENT_FL_CUSTOM_BIT),
+	TRACE_EVENT_FL_TEST_STR		= (1 << TRACE_EVENT_FL_TEST_STR_BIT),
 };
 
 #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE)
@@ -360,7 +364,7 @@ struct trace_event_call {
 	struct list_head	list;
 	struct trace_event_class *class;
 	union {
-		char			*name;
+		const char		*name;
 		/* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */
 		struct tracepoint	*tp;
 	};
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index a54046bf37e5..939ceabcaf06 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -15,10 +15,10 @@
 #else
 #define MODULE_VERMAGIC_SMP ""
 #endif
-#ifdef CONFIG_PREEMPT_BUILD
-#define MODULE_VERMAGIC_PREEMPT "preempt "
-#elif defined(CONFIG_PREEMPT_RT)
+#ifdef CONFIG_PREEMPT_RT
 #define MODULE_VERMAGIC_PREEMPT "preempt_rt "
+#elif defined(CONFIG_PREEMPT_BUILD)
+#define MODULE_VERMAGIC_PREEMPT "preempt "
 #else
 #define MODULE_VERMAGIC_PREEMPT ""
 #endif
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 57cc4b07fd17..dd88682e27e3 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -109,9 +109,11 @@ dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq);
 dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq);
 
 int virtqueue_resize(struct virtqueue *vq, u32 num,
-		     void (*recycle)(struct virtqueue *vq, void *buf));
+		     void (*recycle)(struct virtqueue *vq, void *buf),
+		     void (*recycle_done)(struct virtqueue *vq));
 int virtqueue_reset(struct virtqueue *vq,
-		    void (*recycle)(struct virtqueue *vq, void *buf));
+		    void (*recycle)(struct virtqueue *vq, void *buf),
+		    void (*recycle_done)(struct virtqueue *vq));
 
 struct virtio_admin_cmd {
 	__le16 opcode;
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d2761bf8ff32..9f3a04345b86 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -515,7 +515,7 @@ static inline const char *node_stat_name(enum node_stat_item item)
 
 static inline const char *lru_list_name(enum lru_list lru)
 {
-	return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
+	return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_"
 }
 
 #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index a401a2f31a77..45ff6f7a872b 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -156,8 +156,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
 	debug_check_no_locks_freed((void *)ctx, sizeof(*ctx));
 	lockdep_init_map(&ctx->dep_map, ww_class->acquire_name,
 			 &ww_class->acquire_key, 0);
-	lockdep_init_map(&ctx->first_lock_dep_map, ww_class->mutex_name,
-			 &ww_class->mutex_key, 0);
+	lockdep_init_map_wait(&ctx->first_lock_dep_map, ww_class->mutex_name,
+			      &ww_class->mutex_key, 0, LD_WAIT_SLEEP);
 	mutex_acquire(&ctx->dep_map, 0, 0, _RET_IP_);
 	mutex_acquire_nest(&ctx->first_lock_dep_map, 0, 0, &ctx->dep_map, _RET_IP_);
 #endif