Merge branch 'next' into for-linus

Prepare input updates for 6.2 merge window.

58 files changed, 873 insertions, 399 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7bf9ba1329be..51b9aa640ad2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -79,7 +79,7 @@ struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[];	/* Arbitrary size */
+	__u8	data[0];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
@@ -87,10 +87,35 @@ struct bpf_cgroup_storage_key {
 	__u32	attach_type;		/* program attach type (enum bpf_attach_type) */
 };
 
+enum bpf_cgroup_iter_order {
+	BPF_CGROUP_ITER_ORDER_UNSPEC = 0,
+	BPF_CGROUP_ITER_SELF_ONLY,		/* process only a single object. */
+	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
+	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
+	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+};
+
 union bpf_iter_link_info {
 	struct {
 		__u32	map_fd;
 	} map;
+	struct {
+		enum bpf_cgroup_iter_order order;
+
+		/* At most one of cgroup_fd and cgroup_id can be non-zero. If
+		 * both are zero, the walk starts from the default cgroup v2
+		 * root. For walking v1 hierarchy, one should always explicitly
+		 * specify cgroup_fd.
+		 */
+		__u32	cgroup_fd;
+		__u64	cgroup_id;
+	} cgroup;
+	/* Parameters of task iterators. */
+	struct {
+		__u32	tid;
+		__u32	pid;
+		__u32	pid_fd;
+	} task;
 };
 
 /* BPF syscall commands, see bpf(2) man-page for more details. */
@@ -909,6 +934,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
 	BPF_MAP_TYPE_BLOOM_FILTER,
+	BPF_MAP_TYPE_USER_RINGBUF,
 };
 
 /* Note that tracing related programs such as
@@ -1233,7 +1259,7 @@ enum {
 
 /* Query effective (directly attached + inherited from ancestor cgroups)
  * programs that will be executed for events within a cgroup.
- * attach_flags with this flag are returned only for directly attached programs.
+ * attach_flags with this flag are always returned 0.
  */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
@@ -1432,7 +1458,10 @@ union bpf_attr {
 		__u32		attach_flags;
 		__aligned_u64	prog_ids;
 		__u32		prog_cnt;
-		__aligned_u64	prog_attach_flags; /* output: per-program attach_flags */
+		/* output: per-program attach_flags.
+		 * not allowed to be set during effective query.
+		 */
+		__aligned_u64	prog_attach_flags;
 	} query;
 
 	struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */
@@ -2573,10 +2602,12 @@ union bpf_attr {
  *		There are two supported modes at this time:
  *
  *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
- *		  (room space is added or removed below the layer 2 header).
+ * 		  (room space is added or removed between the layer 2 and
+ * 		  layer 3 headers).
  *
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
- * 		  (room space is added or removed below the layer 3 header).
+ * 		  (room space is added or removed between the layer 3 and
+ * 		  layer 4 headers).
  *
  *		The following flags are supported at this time:
  *
@@ -3008,8 +3039,18 @@ union bpf_attr {
  * 		**BPF_F_USER_STACK**
  * 			Collect a user space stack instead of a kernel stack.
  * 		**BPF_F_USER_BUILD_ID**
- * 			Collect buildid+offset instead of ips for user stack,
- * 			only valid if **BPF_F_USER_STACK** is also specified.
+ * 			Collect (build_id, file_offset) instead of ips for user
+ * 			stack, only valid if **BPF_F_USER_STACK** is also
+ * 			specified.
+ *
+ * 			*file_offset* is an offset relative to the beginning
+ * 			of the executable or shared object file backing the vma
+ * 			which the *ip* falls in. It is *not* an offset relative
+ * 			to that object's base address. Accordingly, it must be
+ * 			adjusted by adding (sh_addr - sh_offset), where
+ * 			sh_{addr,offset} correspond to the executable section
+ * 			containing *file_offset* in the object, for comparisons
+ * 			to symbols' st_value to be valid.
  *
  * 		**bpf_get_stack**\ () can collect up to
  * 		**PERF_MAX_STACK_DEPTH** both kernel and user frames, subject
@@ -4425,7 +4466,7 @@ union bpf_attr {
  *
  *		**-EEXIST** if the option already exists.
  *
- *		**-EFAULT** on failrue to parse the existing header options.
+ *		**-EFAULT** on failure to parse the existing header options.
  *
  *		**-EPERM** if the helper cannot be used under the current
  *		*skops*\ **->op**.
@@ -4634,7 +4675,7 @@ union bpf_attr {
  *		a *map* with *task* as the **key**.  From this
  *		perspective,  the usage is not much different from
  *		**bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this
- *		helper enforces the key must be an task_struct and the map must also
+ *		helper enforces the key must be a task_struct and the map must also
  *		be a **BPF_MAP_TYPE_TASK_STORAGE**.
  *
  *		Underneath, the value is stored locally at *task* instead of
@@ -4692,7 +4733,7 @@ union bpf_attr {
  *
  * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size)
  *	Description
- *		Returns the stored IMA hash of the *inode* (if it's avaialable).
+ *		Returns the stored IMA hash of the *inode* (if it's available).
  *		If the hash is larger than *size*, then only *size*
  *		bytes will be copied to *dst*
  *	Return
@@ -4716,12 +4757,12 @@ union bpf_attr {
  *
  *		The argument *len_diff* can be used for querying with a planned
  *		size change. This allows to check MTU prior to changing packet
- *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		ctx. Providing a *len_diff* adjustment that is larger than the
  *		actual packet size (resulting in negative packet size) will in
- *		principle not exceed the MTU, why it is not considered a
- *		failure.  Other BPF-helpers are needed for performing the
- *		planned size change, why the responsability for catch a negative
- *		packet size belong in those helpers.
+ *		principle not exceed the MTU, which is why it is not considered
+ *		a failure.  Other BPF helpers are needed for performing the
+ *		planned size change; therefore the responsibility for catching
+ *		a negative packet size belongs in those helpers.
  *
  *		Specifying *ifindex* zero means the MTU check is performed
  *		against the current net device.  This is practical if this isn't
@@ -4919,6 +4960,7 @@ union bpf_attr {
  * 		Get address of the traced function (for tracing and kprobe programs).
  * 	Return
  * 		Address of the traced function.
+ * 		0 for kprobes placed within the function (not at the entry).
  *
  * u64 bpf_get_attach_cookie(void *ctx)
  * 	Description
@@ -5048,12 +5090,12 @@ union bpf_attr {
  *
  * long bpf_get_func_arg(void *ctx, u32 n, u64 *value)
  *	Description
- *		Get **n**-th argument (zero based) of the traced function (for tracing programs)
+ *		Get **n**-th argument register (zero based) of the traced function (for tracing programs)
  *		returned in **value**.
  *
  *	Return
  *		0 on success.
- *		**-EINVAL** if n >= arguments count of traced function.
+ *		**-EINVAL** if n >= argument register count of traced function.
  *
  * long bpf_get_func_ret(void *ctx, u64 *value)
  *	Description
@@ -5066,24 +5108,37 @@ union bpf_attr {
  *
  * long bpf_get_func_arg_cnt(void *ctx)
  *	Description
- *		Get number of arguments of the traced function (for tracing programs).
+ *		Get number of registers of the traced function (for tracing programs) where
+ *		function arguments are stored in these registers.
  *
  *	Return
- *		The number of arguments of the traced function.
+ *		The number of argument registers of the traced function.
  *
  * int bpf_get_retval(void)
  *	Description
- *		Get the syscall's return value that will be returned to userspace.
+ *		Get the BPF program's return value that will be returned to the upper layers.
  *
- *		This helper is currently supported by cgroup programs only.
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
  *	Return
- *		The syscall's return value.
+ *		The BPF program's return value.
  *
  * int bpf_set_retval(int retval)
  *	Description
- *		Set the syscall's return value that will be returned to userspace.
+ *		Set the BPF program's return value that will be returned to the upper layers.
+ *
+ *		This helper is currently supported by cgroup programs and only by the hooks
+ *		where BPF program's return value is returned to the userspace via errno.
+ *
+ *		Note that there is the following corner case where the program exports an error
+ *		via bpf_set_retval but signals success via 'return 1':
+ *
+ *			bpf_set_retval(-EPERM);
+ *			return 1;
+ *
+ *		In this case, the BPF program's return value will use helper's -EPERM. This
+ *		still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case.
  *
- *		This helper is currently supported by cgroup programs only.
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
@@ -5331,6 +5386,55 @@ union bpf_attr {
  *		**-EACCES** if the SYN cookie is not valid.
  *
  *		**-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin.
+ *
+ * u64 bpf_ktime_get_tai_ns(void)
+ *	Description
+ *		A nonsettable system-wide clock derived from wall-clock time but
+ *		ignoring leap seconds.  This clock does not experience
+ *		discontinuities and backwards jumps caused by NTP inserting leap
+ *		seconds as CLOCK_REALTIME does.
+ *
+ *		See: **clock_gettime**\ (**CLOCK_TAI**)
+ *	Return
+ *		Current *ktime*.
+ *
+ * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags)
+ *	Description
+ *		Drain samples from the specified user ring buffer, and invoke
+ *		the provided callback for each such sample:
+ *
+ *		long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx);
+ *
+ *		If **callback_fn** returns 0, the helper will continue to try
+ *		and drain the next sample, up to a maximum of
+ *		BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1,
+ *		the helper will skip the rest of the samples and return. Other
+ *		return values are not used now, and will be rejected by the
+ *		verifier.
+ *	Return
+ *		The number of drained samples if no error was encountered while
+ *		draining samples, or 0 if no samples were present in the ring
+ *		buffer. If a user-space producer was epoll-waiting on this map,
+ *		and at least one sample was drained, they will receive an event
+ *		notification notifying them of available space in the ring
+ *		buffer. If the BPF_RB_NO_WAKEUP flag is passed to this
+ *		function, no wakeup notification will be sent. If the
+ *		BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will
+ *		be sent even if no sample was drained.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EBUSY** if the ring buffer is contended, and another calling
+ *		context was concurrently draining the ring buffer.
+ *
+ *		**-EINVAL** if user-space is not properly tracking the ring
+ *		buffer due to the producer position not being aligned to 8
+ *		bytes, a sample not being aligned to 8 bytes, or the producer
+ *		position not matching the advertised length of a sample.
+ *
+ *		**-E2BIG** if user-space has tried to publish a sample which is
+ *		larger than the size of the ring buffer, or which cannot fit
+ *		within a struct bpf_dynptr.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5541,6 +5645,8 @@ union bpf_attr {
 	FN(tcp_raw_gen_syncookie_ipv6),	\
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
+	FN(ktime_get_tai_ns),		\
+	FN(user_ringbuf_drain),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5603,6 +5709,11 @@ enum {
 	BPF_F_SEQ_NUMBER		= (1ULL << 3),
 };
 
+/* BPF_FUNC_skb_get_tunnel_key flags. */
+enum {
+	BPF_F_TUNINFO_FLAGS		= (1ULL << 4),
+};
+
 /* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and
  * BPF_FUNC_perf_event_read_value flags.
  */
@@ -5792,7 +5903,10 @@ struct bpf_tunnel_key {
 	};
 	__u8 tunnel_tos;
 	__u8 tunnel_ttl;
-	__u16 tunnel_ext;	/* Padding, future use. */
+	union {
+		__u16 tunnel_ext;	/* compat */
+		__be16 tunnel_flags;
+	};
 	__u32 tunnel_label;
 	union {
 		__u32 local_ipv4;
@@ -5836,6 +5950,11 @@ enum bpf_ret_code {
 	 *    represented by BPF_REDIRECT above).
 	 */
 	BPF_LWT_REROUTE = 128,
+	/* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+	 *   to indicate that no custom dissection was performed, and
+	 *   fallback to standard dissector is requested.
+	 */
+	BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {
@@ -6134,11 +6253,26 @@ struct bpf_link_info {
 		struct {
 			__aligned_u64 target_name; /* in/out: target_name buffer ptr */
 			__u32 target_name_len;	   /* in/out: target_name buffer len */
+
+			/* If the iter specific field is 32 bits, it can be put
+			 * in the first or second union. Otherwise it should be
+			 * put in the second union.
+			 */
 			union {
 				struct {
 					__u32 map_id;
 				} map;
 			};
+			union {
+				struct {
+					__u64 cgroup_id;
+					__u32 order;
+				} cgroup;
+				struct {
+					__u32 tid;
+					__u32 pid;
+				} task;
+			};
 		} iter;
 		struct  {
 			__u32 netns_ino;
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 7ada84e4a3ed..5655e89b962b 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -290,6 +290,12 @@ struct btrfs_ioctl_fs_info_args {
 #define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID	(1ULL << 1)
 #define BTRFS_FEATURE_COMPAT_RO_VERITY			(1ULL << 2)
 
+/*
+ * Put all block group items into a dedicated block group tree, greatly
+ * reducing mount time for large filesystem due to better locality.
+ */
+#define BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE	(1ULL << 3)
+
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index 5f32a2a495dc..1f7a38ec6ac3 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -965,6 +965,10 @@ static inline __u16 btrfs_qgroup_level(__u64 qgroupid)
  */
 #define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT	(1ULL << 2)
 
+#define BTRFS_QGROUP_STATUS_FLAGS_MASK	(BTRFS_QGROUP_STATUS_FLAG_ON |		\
+					 BTRFS_QGROUP_STATUS_FLAG_RESCAN |	\
+					 BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)
+
 #define BTRFS_QGROUP_STATUS_VERSION        1
 
 struct btrfs_qgroup_status_item {
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index 90801ada2bbe..dd645ea72306 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -48,6 +48,7 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
+#include <linux/stddef.h> /* for offsetof */
 
 /* controller area network (CAN) kernel definitions */
 
@@ -60,6 +61,7 @@
 #define CAN_SFF_MASK 0x000007FFU /* standard frame format (SFF) */
 #define CAN_EFF_MASK 0x1FFFFFFFU /* extended frame format (EFF) */
 #define CAN_ERR_MASK 0x1FFFFFFFU /* omit EFF, RTR, ERR flags */
+#define CANXL_PRIO_MASK CAN_SFF_MASK /* 11 bit priority mask */
 
 /*
  * Controller Area Network Identifier structure
@@ -73,6 +75,7 @@ typedef __u32 canid_t;
 
 #define CAN_SFF_ID_BITS		11
 #define CAN_EFF_ID_BITS		29
+#define CANXL_PRIO_BITS		CAN_SFF_ID_BITS
 
 /*
  * Controller Area Network Error Message Frame Mask structure
@@ -91,6 +94,16 @@ typedef __u32 can_err_mask_t;
 #define CANFD_MAX_DLC 15
 #define CANFD_MAX_DLEN 64
 
+/*
+ * CAN XL payload length and DLC definitions according to ISO 11898-1
+ * CAN XL DLC ranges from 0 .. 2047 => data length from 1 .. 2048 byte
+ */
+#define CANXL_MIN_DLC 0
+#define CANXL_MAX_DLC 2047
+#define CANXL_MAX_DLC_MASK 0x07FF
+#define CANXL_MIN_DLEN 1
+#define CANXL_MAX_DLEN 2048
+
 /**
  * struct can_frame - Classical CAN frame structure (aka CAN 2.0B)
  * @can_id:   CAN ID of the frame and CAN_*_FLAG flags, see canid_t definition
@@ -141,8 +154,8 @@ struct can_frame {
  * When this is done the former differentiation via CAN_MTU / CANFD_MTU gets
  * lost. CANFD_FDF allows programmers to mark CAN FD frames in the case of
  * using struct canfd_frame for mixed CAN / CAN FD content (dual use).
- * N.B. the Kernel APIs do NOT provide mixed CAN / CAN FD content inside of
- * struct canfd_frame therefore the CANFD_FDF flag is disregarded by Linux.
+ * Since the introduction of CAN XL the CANFD_FDF flag is set in all CAN FD
+ * frame structures provided by the CAN subsystem of the Linux kernel.
  */
 #define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */
 #define CANFD_ESI 0x02 /* error state indicator of the transmitting node */
@@ -166,8 +179,46 @@ struct canfd_frame {
 	__u8    data[CANFD_MAX_DLEN] __attribute__((aligned(8)));
 };
 
+/*
+ * defined bits for canxl_frame.flags
+ *
+ * The canxl_frame.flags element contains two bits CANXL_XLF and CANXL_SEC
+ * and shares the relative position of the struct can[fd]_frame.len element.
+ * The CANXL_XLF bit ALWAYS needs to be set to indicate a valid CAN XL frame.
+ * As a side effect setting this bit intentionally breaks the length checks
+ * for Classical CAN and CAN FD frames.
+ *
+ * Undefined bits in canxl_frame.flags are reserved and shall be set to zero.
+ */
+#define CANXL_XLF 0x80 /* mandatory CAN XL frame flag (must always be set!) */
+#define CANXL_SEC 0x01 /* Simple Extended Content (security/segmentation) */
+
+/**
+ * struct canxl_frame - CAN with e'X'tended frame 'L'ength frame structure
+ * @prio:  11 bit arbitration priority with zero'ed CAN_*_FLAG flags
+ * @flags: additional flags for CAN XL
+ * @sdt:   SDU (service data unit) type
+ * @len:   frame payload length in byte (CANXL_MIN_DLEN .. CANXL_MAX_DLEN)
+ * @af:    acceptance field
+ * @data:  CAN XL frame payload (CANXL_MIN_DLEN .. CANXL_MAX_DLEN byte)
+ *
+ * @prio shares the same position as @can_id from struct can[fd]_frame.
+ */
+struct canxl_frame {
+	canid_t prio;  /* 11 bit priority for arbitration (canid_t) */
+	__u8    flags; /* additional flags for CAN XL */
+	__u8    sdt;   /* SDU (service data unit) type */
+	__u16   len;   /* frame payload length in byte */
+	__u32   af;    /* acceptance field */
+	__u8    data[CANXL_MAX_DLEN];
+};
+
 #define CAN_MTU		(sizeof(struct can_frame))
 #define CANFD_MTU	(sizeof(struct canfd_frame))
+#define CANXL_MTU	(sizeof(struct canxl_frame))
+#define CANXL_HDR_SIZE	(offsetof(struct canxl_frame, data))
+#define CANXL_MIN_MTU	(CANXL_HDR_SIZE + 64)
+#define CANXL_MAX_MTU	CANXL_MTU
 
 /* particular protocols of the protocol family PF_CAN */
 #define CAN_RAW		1 /* RAW sockets */
diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h
index 3386aa81fdf2..ff12f525c37c 100644
--- a/include/uapi/linux/can/raw.h
+++ b/include/uapi/linux/can/raw.h
@@ -62,6 +62,7 @@ enum {
 	CAN_RAW_RECV_OWN_MSGS,	/* receive my own msgs (default:off) */
 	CAN_RAW_FD_FRAMES,	/* allow CAN FD frames (default:off) */
 	CAN_RAW_JOIN_FILTERS,	/* all filters must match to trigger */
+	CAN_RAW_XL_FRAMES,	/* allow CAN XL frames (default:off) */
 };
 
 #endif /* !_UAPI_CAN_RAW_H */
diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h
index 96c5ffd368ad..8ab12d731e3b 100644
--- a/include/uapi/linux/counter.h
+++ b/include/uapi/linux/counter.h
@@ -63,6 +63,8 @@ enum counter_event_type {
 	COUNTER_EVENT_INDEX,
 	/* State of counter is changed */
 	COUNTER_EVENT_CHANGE_OF_STATE,
+	/* Count value captured */
+	COUNTER_EVENT_CAPTURE,
 };
 
 /**
@@ -153,4 +155,10 @@ enum counter_synapse_action {
 	COUNTER_SYNAPSE_ACTION_BOTH_EDGES,
 };
 
+/* Signal polarity values */
+enum counter_signal_polarity {
+	COUNTER_SIGNAL_POLARITY_POSITIVE,
+	COUNTER_SIGNAL_POLARITY_NEGATIVE,
+};
+
 #endif /* _UAPI_COUNTER_H_ */
diff --git a/include/uapi/linux/dlm.h b/include/uapi/linux/dlm.h
index 0d2eca287567..1923f4f3b05e 100644
--- a/include/uapi/linux/dl