Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next into net-accept-more

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1557 commits)
  net: qede: use extack in qede_parse_actions()
  net: qede: propagate extack through qede_flow_spec_validate()
  net: qede: use faked extack in qede_flow_spec_to_rule()
  net: qede: use extack in qede_parse_flow_attr()
  net: qede: add extack in qede_add_tc_flower_fltr()
  net: qede: use extack in qede_flow_parse_udp_v4()
  net: qede: use extack in qede_flow_parse_udp_v6()
  net: qede: use extack in qede_flow_parse_tcp_v4()
  net: qede: use extack in qede_flow_parse_tcp_v6()
  net: qede: use extack in qede_flow_parse_v4_common()
  net: qede: use extack in qede_flow_parse_v6_common()
  net: qede: use extack in qede_set_v4_tuple_to_profile()
  net: qede: use extack in qede_set_v6_tuple_to_profile()
  net: qede: use extack in qede_flow_parse_ports()
  net: usb: smsc95xx: stop lying about skb->truesize
  net: dsa: microchip: Fix spellig mistake "configur" -> "configure"
  af_unix: Add dead flag to struct scm_fp_list.
  net: ethernet: adi: adin1110: Replace linux/gpio.h by proper one
  octeontx2-pf: Reuse Transmit queue/Send queue index of HTB class
  gve: Use ethtool_sprintf/puts() to fill stats strings
  ...

40 files changed, 847 insertions, 328 deletions

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index aa4096126553..8c4768c44a01 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -83,6 +83,10 @@ struct device;
  *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
  *  bitmap_get_value8(map, start)               Get 8bit value from map at start
  *  bitmap_set_value8(map, value, start)        Set 8bit value to map at start
+ *  bitmap_read(map, start, nbits)              Read an nbits-sized value from
+ *                                              map at start
+ *  bitmap_write(map, value, start, nbits)      Write an nbits-sized value to
+ *                                              map at start
  *
  * Note, bitmap_zero() and bitmap_fill() operate over the region of
  * unsigned longs, that is, bits behind bitmap till the unsigned long
@@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
 
+#define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
 static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = 0;
@@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 
 static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = ~0UL;
@@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 			unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = *src;
@@ -722,38 +728,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 }
 
 /**
- * bitmap_get_value8 - get an 8-bit value within a memory region
+ * bitmap_read - read a value of n-bits from the memory region
  * @map: address to the bitmap memory region
- * @start: bit offset of the 8-bit value; must be a multiple of 8
+ * @start: bit offset of the n-bit value
+ * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG
  *
- * Returns the 8-bit value located at the @start bit offset within the @src
- * memory region.
+ * Returns: value of @nbits bits located at the @start bit offset within the
+ * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return
+ * value is undefined.
  */
-static inline unsigned long bitmap_get_value8(const unsigned long *map,
-					      unsigned long start)
+static inline unsigned long bitmap_read(const unsigned long *map,
+					unsigned long start,
+					unsigned long nbits)
 {
-	const size_t index = BIT_WORD(start);
-	const unsigned long offset = start % BITS_PER_LONG;
+	size_t index = BIT_WORD(start);
+	unsigned long offset = start % BITS_PER_LONG;
+	unsigned long space = BITS_PER_LONG - offset;
+	unsigned long value_low, value_high;
+
+	if (unlikely(!nbits || nbits > BITS_PER_LONG))
+		return 0;
+
+	if (space >= nbits)
+		return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits);
 
-	return (map[index] >> offset) & 0xFF;
+	value_low = map[index] & BITMAP_FIRST_WORD_MASK(start);
+	value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits);
+	return (value_low >> offset) | (value_high << space);
 }
 
 /**
- * bitmap_set_value8 - set an 8-bit value within a memory region
+ * bitmap_write - write n-bit value within a memory region
  * @map: address to the bitmap memory region
- * @value: the 8-bit value; values wider than 8 bits may clobber bitmap
- * @start: bit offset of the 8-bit value; must be a multiple of 8
+ * @value: value to write, clamped to nbits
+ * @start: bit offset of the n-bit value
+ * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG.
+ *
+ * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(),
+ * i.e. bits beyond @nbits are ignored:
+ *
+ *   for (bit = 0; bit < nbits; bit++)
+ *           __assign_bit(start + bit, bitmap, val & BIT(bit));
+ *
+ * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed.
  */
-static inline void bitmap_set_value8(unsigned long *map, unsigned long value,
-				     unsigned long start)
-{
-	const size_t index = BIT_WORD(start);
-	const unsigned long offset = start % BITS_PER_LONG;
-
-	map[index] &= ~(0xFFUL << offset);
+static inline void bitmap_write(unsigned long *map, unsigned long value,
+				unsigned long start, unsigned long nbits)
+{
+	size_t index;
+	unsigned long offset;
+	unsigned long space;
+	unsigned long mask;
+	bool fit;
+
+	if (unlikely(!nbits || nbits > BITS_PER_LONG))
+		return;
+
+	mask = BITMAP_LAST_WORD_MASK(nbits);
+	value &= mask;
+	offset = start % BITS_PER_LONG;
+	space = BITS_PER_LONG - offset;
+	fit = space >= nbits;
+	index = BIT_WORD(start);
+
+	map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start));
 	map[index] |= value << offset;
+	if (fit)
+		return;
+
+	map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits);
+	map[index + 1] |= (value >> space);
 }
 
+#define bitmap_get_value8(map, start)			\
+	bitmap_read(map, start, BITS_PER_BYTE)
+#define bitmap_set_value8(map, value, start)		\
+	bitmap_write(map, value, start, BITS_PER_BYTE)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __LINUX_BITMAP_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 2ba557e067fe..b25dc8742124 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -21,6 +21,8 @@
 #define BITS_TO_U32(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
 #define BITS_TO_BYTES(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
 
+#define BYTES_TO_BITS(nb)	((nb) * BITS_PER_BYTE)
+
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
 extern unsigned int __sw_hweight32(unsigned int w);
@@ -80,6 +82,7 @@ __check_bitop_pr(__test_and_set_bit);
 __check_bitop_pr(__test_and_clear_bit);
 __check_bitop_pr(__test_and_change_bit);
 __check_bitop_pr(test_bit);
+__check_bitop_pr(test_bit_acquire);
 
 #undef __check_bitop_pr
 
@@ -272,23 +275,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n)
  * @addr: the address to start counting from
  * @value: the value to assign
  */
-static __always_inline void assign_bit(long nr, volatile unsigned long *addr,
-				       bool value)
-{
-	if (value)
-		set_bit(nr, addr);
-	else
-		clear_bit(nr, addr);
-}
+#define assign_bit(nr, addr, value)					\
+	((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr)))
 
-static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
-					 bool value)
-{
-	if (value)
-		__set_bit(nr, addr);
-	else
-		__clear_bit(nr, addr);
-}
+#define __assign_bit(nr, addr, value)					\
+	((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr)))
 
 /**
  * __ptr_set_bit - Set bit in a pointer's value
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 890e152d553e..90094400cc63 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -184,8 +184,8 @@ struct bpf_map_ops {
 };
 
 enum {
-	/* Support at most 10 fields in a BTF type */
-	BTF_FIELDS_MAX	   = 10,
+	/* Support at most 11 fields in a BTF type */
+	BTF_FIELDS_MAX	   = 11,
 };
 
 enum btf_field_type {
@@ -202,6 +202,7 @@ enum btf_field_type {
 	BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE,
 	BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD,
 	BPF_REFCOUNT   = (1 << 9),
+	BPF_WORKQUEUE  = (1 << 10),
 };
 
 typedef void (*btf_dtor_kfunc_t)(void *);
@@ -238,6 +239,7 @@ struct btf_record {
 	u32 field_mask;
 	int spin_lock_off;
 	int timer_off;
+	int wq_off;
 	int refcount_off;
 	struct btf_field fields[];
 };
@@ -312,6 +314,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 		return "bpf_spin_lock";
 	case BPF_TIMER:
 		return "bpf_timer";
+	case BPF_WORKQUEUE:
+		return "bpf_wq";
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return "kptr";
@@ -340,6 +344,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 		return sizeof(struct bpf_spin_lock);
 	case BPF_TIMER:
 		return sizeof(struct bpf_timer);
+	case BPF_WORKQUEUE:
+		return sizeof(struct bpf_wq);
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
@@ -367,6 +373,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 		return __alignof__(struct bpf_spin_lock);
 	case BPF_TIMER:
 		return __alignof__(struct bpf_timer);
+	case BPF_WORKQUEUE:
+		return __alignof__(struct bpf_wq);
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
@@ -406,6 +414,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
 		/* RB_ROOT_CACHED 0-inits, no need to do anything after memset */
 	case BPF_SPIN_LOCK:
 	case BPF_TIMER:
+	case BPF_WORKQUEUE:
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 	case BPF_KPTR_PERCPU:
@@ -525,6 +534,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
 void bpf_timer_cancel_and_free(void *timer);
+void bpf_wq_cancel_and_free(void *timer);
 void bpf_list_head_free(const struct btf_field *field, void *list_head,
 			struct bpf_spin_lock *spin_lock);
 void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
@@ -1116,8 +1126,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 				void *func_addr);
 void *arch_alloc_bpf_trampoline(unsigned int size);
 void arch_free_bpf_trampoline(void *image, unsigned int size);
-void arch_protect_bpf_trampoline(void *image, unsigned int size);
-void arch_unprotect_bpf_trampoline(void *image, unsigned int size);
+int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size);
 int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 			     struct bpf_tramp_links *tlinks, void *func_addr);
 
@@ -1266,6 +1275,7 @@ int bpf_dynptr_check_size(u32 size);
 u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
 const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len);
 void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len);
+bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr);
 
 #ifdef CONFIG_BPF_JIT
 int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
@@ -1622,6 +1632,12 @@ struct bpf_tracing_link {
 	struct bpf_prog *tgt_prog;
 };
 
+struct bpf_raw_tp_link {
+	struct bpf_link link;
+	struct bpf_raw_event_map *btp;
+	u64 cookie;
+};
+
 struct bpf_link_primer {
 	struct bpf_link *link;
 	struct file *file;
@@ -2204,6 +2220,7 @@ void bpf_map_free_record(struct bpf_map *map);
 struct btf_record *btf_record_dup(const struct btf_record *rec);
 bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
 void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
+void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj);
 void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
 void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
 
@@ -3005,6 +3022,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
 int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
+int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog);
 
 void sock_map_unhash(struct sock *sk);
 void sock_map_destroy(struct sock *sk);
@@ -3103,6 +3121,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h
new file mode 100644
index 000000000000..a41e71d4e2d9
--- /dev/null
+++ b/include/linux/bpf_crypto.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#ifndef _BPF_CRYPTO_H
+#define _BPF_CRYPTO_H
+
+struct bpf_crypto_type {
+	void *(*alloc_tfm)(const char *algo);
+	void (*free_tfm)(void *tfm);
+	int (*has_algo)(const char *algo);
+	int (*setkey)(void *tfm, const u8 *key, unsigned int keylen);
+	int (*setauthsize)(void *tfm, unsigned int authsize);
+	int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv);
+	int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv);
+	unsigned int (*ivsize)(void *tfm);
+	unsigned int (*statesize)(void *tfm);
+	u32 (*get_flags)(void *tfm);
+	struct module *owner;
+	char name[14];
+};
+
+int bpf_crypto_register_type(const struct bpf_crypto_type *type);
+int bpf_crypto_unregister_type(const struct bpf_crypto_type *type);
+
+#endif /* _BPF_CRYPTO_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7cb1b75eee38..50aa87f8d77f 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -421,11 +421,13 @@ struct bpf_verifier_state {
 	struct bpf_active_lock active_lock;
 	bool speculative;
 	bool active_rcu_lock;
+	u32 active_preempt_lock;
 	/* If this state was ever pointed-to by other state's loop_entry field
 	 * this flag would be set to true. Used to avoid freeing such states
 	 * while they are still in use.
 	 */
 	bool used_as_loop_entry;
+	bool in_sleepable;
 
 	/* first and last insn idx of this verifier state */
 	u32 first_insn_idx;
@@ -502,6 +504,13 @@ struct bpf_loop_inline_state {
 	u32 callback_subprogno; /* valid when fit_for_inline is true */
 };
 
+/* pointer and state for maps */
+struct bpf_map_ptr_state {
+	struct bpf_map *map_ptr;
+	bool poison;
+	bool unpriv;
+};
+
 /* Possible states for alu_state member. */
 #define BPF_ALU_SANITIZE_SRC		(1U << 0)
 #define BPF_ALU_SANITIZE_DST		(1U << 1)
@@ -514,7 +523,7 @@ struct bpf_loop_inline_state {
 struct bpf_insn_aux_data {
 	union {
 		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
-		unsigned long map_ptr_state;	/* pointer/poison value for maps */
+		struct bpf_map_ptr_state map_ptr_state;
 		s32 call_imm;			/* saved imm field of call insn */
 		u32 alu_limit;			/* limit for add/sub register with pointer */
 		struct {
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 8f8236317d5b..422343ace39c 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -293,6 +293,17 @@ struct ftrace_likely_data {
 #define __no_sanitize_or_inline __always_inline
 #endif
 
+/*
+ * Apply __counted_by() when the Endianness matches to increase test coverage.
+ */
+#ifdef __LITTLE_ENDIAN
+#define __counted_by_le(member)	__counted_by(member)
+#define __counted_by_be(member)
+#else
+#define __counted_by_le(member)
+#define __counted_by_be(member)	__counted_by(member)
+#endif
+
 /* Do not trap wrapping arithmetic within an annotated function. */
 #ifdef CONFIG_UBSAN_SIGNED_WRAP
 # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow")))
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 1c29947db848..6519f9c77709 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -853,7 +853,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
  */
 static inline unsigned int cpumask_size(void)
 {
-	return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long);
+	return bitmap_size(large_cpumask_bits);
 }
 
 /*
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 5693a4be0d9a..281298e77a15 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -50,6 +50,9 @@ struct dql {
 	unsigned int	adj_limit;		/* limit + num_completed */
 	unsigned int	last_obj_cnt;		/* Count at last queuing */
 
+	/* Stall threshold (in jiffies), defined by user */
+	unsigned short	stall_thrs;
+
 	unsigned long	history_head;		/* top 58 bits of jiffies */
 	/* stall entries, a bit per entry */
 	unsigned long	history[DQL_HIST_LEN];
@@ -71,8 +74,6 @@ struct dql {
 	unsigned int	min_limit;		/* Minimum limit */
 	unsigned int	slack_hold_time;	/* Time to measure slack */
 
-	/* Stall threshold (in jiffies), defined by user */
-	unsigned short	stall_thrs;
 	/* Longest stall detected, reported to user */
 	unsigned short	stall_max;
 	unsigned long	last_reap;		/* Last reap (in jiffies) */
@@ -83,27 +84,11 @@ struct dql {
 #define DQL_MAX_OBJECT (UINT_MAX / 16)
 #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT)
 
-/*
- * Record number of objects queued. Assumes that caller has already checked
- * availability in the queue with dql_avail.
- */
-static inline void dql_queued(struct dql *dql, unsigned int count)
+/* Populate the bitmap to be processed later in dql_check_stall() */
+static inline void dql_queue_stall(struct dql *dql)
 {
 	unsigned long map, now, now_hi, i;
 
-	BUG_ON(count > DQL_MAX_OBJECT);
-
-	dql->last_obj_cnt = count;
-
-	/* We want to force a write first, so that cpu do not attempt
-	 * to get cache line containing last_obj_cnt, num_queued, adj_limit
-	 * in Shared state, but directly does a Request For Ownership
-	 * It is only a hint, we use barrier() only.
-	 */
-	barrier();
-
-	dql->num_queued += count;
-
 	now = jiffies;
 	now_hi = now / BITS_PER_LONG;
 
@@ -133,6 +118,31 @@ static inline void dql_queued(struct dql *dql, unsigned int count)
 		WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now));
 }
 
+/*
+ * Record number of objects queued. Assumes that caller has already checked
+ * availability in the queue with dql_avail.
+ */
+static inline void dql_queued(struct dql *dql, unsigned int count)
+{
+	if (WARN_ON_ONCE(count > DQL_MAX_OBJECT))
+		return;
+
+	dql->last_obj_cnt = count;
+
+	/* We want to force a write first, so that cpu do not attempt
+	 * to get cache line containing last_obj_cnt, num_queued, adj_limit
+	 * in Shared state, but directly does a Request For Ownership
+	 * It is only a hint, we use barrier() only.
+	 */
+	barrier();
+
+	dql->num_queued += count;
+
+	/* Only populate stall information if the threshold is set */
+	if (READ_ONCE(dql->stall_thrs))
+		dql_queue_stall(dql);
+}
+
 /* Returns how many objects can be queued, < 0 indicates over limit. */
 static inline int dql_avail(const struct dql *dql)
 {
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 297231854ada..2ad1ffa4ccb9 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -71,6 +71,12 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
 { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
 #define eth_stp_addr eth_reserved_addr_base
 
+static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) =
+{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 };
+
+static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) =
+{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 };
+
 /**
  * is_link_local_ether_addr - Determine if given Ethernet address is link-local
  * @addr: Pointer to a six-byte array containing the Ethernet address
@@ -430,18 +436,16 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2,
 
 static inline bool ether_addr_is_ipv4_mcast(const u8 *addr)
 {
-	u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 };
 	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 };
 
-	return ether_addr_equal_masked(addr, base, mask);
+	return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask);
 }
 
 static inline bool ether_addr_is_ipv6_mcast(const u8 *addr)
 {
-	u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 };
 	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 };
 
-	return ether_addr_equal_masked(addr, base, mask);
+	return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask);
 }
 
 static inline bool ether_addr_is_ip_mcast(const u8 *addr)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 9901e563f706..6fd9107d3cc0 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -480,6 +480,26 @@ struct ethtool_rmon_stats {
 	);
 };
 
+/**
+ * struct ethtool_ts_stats - HW timestamping statistics
+ * @pkts: Number of packets successfully timestamped by the hardware.
+ * @lost: Number of hardware timestamping requests where the timestamping
+ *	information from the hardware never arrived for submission with
+ *	the skb.
+ * @err: Number of arbitrary timestamp generation error events that the
+ *	hardware encountered, exclusive of @lost statistics. Cases such
+ *	as resource exhaustion, unavailability, firmware errors, and
+ *	detected illogical timestamp values not submitted with the skb
+ *	are inclusive to this counter.
+ */
+struct ethtool_ts_stats {
+	struct_group(tx_stats,
+		u64 pkts;
+		u64 lost;
+		u64 err;
+	);
+};
+
 #define ETH_MODULE_EEPROM_PAGE_LEN	128
 #define ETH_MODULE_MAX_I2C_ADDRESS	0x7f
 
@@ -755,7 +775,10 @@ struct ethtool_rxfh_param {
  * @get_ts_info: Get the time stamping and PTP hardware clock capabilities.
  *	It may be called with RCU, or rtnl or reference on the device.
  *	Drivers supporting transmit time stamps in software should set this to
- *	ethtool_op_get_ts_info().
+ *	ethtool_op_get_ts_info(). Drivers must not zero statistics which they
+ *	don't report. The stats	structure is initialized to ETHTOOL_STAT_NOT_SET
+ *	indicating driver does not report statistics.
+ * @get_ts_stats: Query the device hardware timestamping statistics.
  * @get_module_info: Get the size and type of the eeprom contained within
  *	a plug-in module.
  * @get_module_eeprom: Get the eeprom information from the plug-in module
@@ -898,6 +921,8 @@ struct ethtool_ops {
 				 struct ethtool_dump *, void *);
 	int	(*set_dump)(struct net_device *, struct ethtool_dump *);
 	int	(*get_ts_info)(struct net_device *, struct ethtool_ts_info *);
+	void	(*get_ts_stats)(struct net_device *dev,
+				struct ethtool_ts_stats *ts_stats);
 	int     (*get_module_info)(struct net_device *,
 				   struct ethtool_modinfo *);
 	int     (*get_module_eeprom)(struct net_device *,
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 219ee7a76874..d5fea03cb6e6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -75,6 +75,9 @@ struct ctl_table_header;
 /* unused opcode to mark special load instruction. Same as BPF_MSH */
 #define BPF_PROBE_MEM32	0xa0
 
+/* unused opcode to mark special atomic instruction */
+#define BPF_PROBE_ATOMIC 0xe0
+
 /* unused opcode to mark call to interpreter with arguments */
 #define BPF_CALL_ARGS	0xe0
 
@@ -178,6 +181,25 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = 0 })
 
+/* Special (internal-only) form of mov, used to resolve per-CPU addrs:
+ * dst_reg = src_reg + <percpu_base_off>
+ * BPF_ADDR_PERCPU is used as a special insn->off value.
+ */
+#define BPF_ADDR_PERCPU	(-1)
+
+#define BPF_MOV64_PERCPU_REG(DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = BPF_ADDR_PERCPU,			\
+		.imm   = 0 })
+
+static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_ALU64 | BP