/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
 * CUBELinux: the coordinate interface.
 *
 * The kernel's native interface to the store. Operations are the verbs the command language
 * already defines — one language, and this is its kernel form (DESIGN-cube-interface.md).
 *
 * A coordinate is not a name and not a path: it is *where* a record is, and knowing it is the
 * authorisation to use it. Nothing here resolves a name, and nothing enumerates.
 */
#ifndef _UAPI_LINUX_CUBE_H
#define _UAPI_LINUX_CUBE_H

#include <linux/types.h>

/* Which cube, and where in it. 32-byte space: unguessable, deliberately. */
struct cube_coord {
	__u8 space[32];
	__u64 x;
	__u64 y;
	__u64 z;
};

/*
 * The argument block. `size` first, and checked: an interface that cannot grow is an
 * interface that has to be replaced, and syscall numbers are permanent.
 */
struct cube_args {
	__u32 size;		/* sizeof(struct cube_args) as the caller built it */
	__u32 op;		/* CUBE_OP_* */
	struct cube_coord coord;	/* unused by CUBE_OP_SYNC */
	__u64 value;		/* user pointer: bytes to write, or where to put them */
	__u64 len;		/* in: bytes offered, or the buffer's capacity.
				 * out: on -ERANGE, the bytes that would be needed;
				 *      on success for CUBE_OP_GET, the bytes read.
				 */
};

#define CUBE_OP_PUT	1	/* store bytes at a coordinate */
#define CUBE_OP_GET	2	/* read them back */
#define CUBE_OP_DEL	3	/* remove the record */
#define CUBE_OP_SYNC	4	/* fold the log into the image */
#define CUBE_OP_ENUM	5	/* walk the records of a space, in batches */
#define CUBE_OP_SPACES	6	/* walk the spaces that hold records */
#define CUBE_OP_RANGE	7	/* walk the records of a space that lie in a box */

/*
 * The walk's argument block: its own block rather than a wider `cube_args`, because it needs a
 * cursor and a buffer, and the coordinate would otherwise be both an input and an output.
 *
 * Records are packed as `key(24) | value_len(u32, little-endian) | value`, in the store's own
 * order — space first, then key — which is the order a checkpoint writes them and the order the
 * userspace store returns them, so a kernel listing and a userspace listing can be compared
 * directly. The space is not repeated per record: the caller named it.
 *
 * A walk ends when the cursor stops moving, and that is the only end signal: a batch holds as
 * many whole records as fit, so most batches come back short, and reading a short batch as the
 * end truncates a listing to its first batch. CUBE_OP_ENUM answers a finished walk with no
 * records and the cursor unchanged; CUBE_OP_SPACES answers it with -ENOENT, because asking for
 * the space after the last one is asking for a space that is not there. -ERANGE keeps its usual
 * meaning: not one whole record fits, and `len` says how much one needs.
 */
struct cube_enum_args {
	__u32 size;		/* sizeof(struct cube_enum_args) as the caller built it */
	__u32 op;		/* CUBE_OP_ENUM or CUBE_OP_SPACES */
	__u8 space[32];		/* in: the space to walk; out: the space found (CUBE_OP_SPACES) */
	__u64 cursor;		/* in: 0 to start, or what the last call returned;
				 * out: what to pass next — see the end-of-walk rule above
				 */
	__u64 value;		/* user pointer: where to put the records */
	__u64 len;		/* in: the buffer's capacity;
				 * out: bytes written, or on -ERANGE what would be needed
				 */
};

/*
 * The region walk's argument block: its own block, for the walk's reason — it needs a box, a cursor
 * and a buffer, and the coordinate would otherwise be both an input and an output. It is versioned
 * by `size` like the other two, so this interface grows by gaining a block rather than by being
 * replaced.
 *
 * A region is a box, inclusive on both corners. Records come back packed exactly as CUBE_OP_ENUM
 * packs them — `key(24) | value_len(u32, little-endian) | value`, in the store's own order — so a
 * kernel region answer and a userspace one can be compared byte for byte.
 *
 * The cursor is a COUNT OF RECORDS ALREADY RETURNED, and it is the end-of-walk signal for the same
 * reason as the walk's: a batch holds as many whole records as fit, so most batches come back
 * short, and reading a short batch as the end truncates the answer. The one difference is what it
 * counts — a walk counts the records of the space, a region walk counts the records *in the box*,
 * because those are the records it returns.
 *
 * Implementation, because it is what makes this cheap: **the kernel seeks.** The box's two corner
 * keys bound every key inside it (`cube_format::key_span`), so a v3 image's sorted index is
 * binary-searched for the foot of that span and read forward to its head. The span is a BOUND, not
 * the set — records *outside* the box also have keys inside it (Z-order amplification) — so each
 * candidate is decoded and tested against the box before it is returned. More records may therefore
 * be examined than are returned, and that over-coverage is the honest cost of the span.
 */
struct cube_range_args {
	__u32 size;		/* sizeof(struct cube_range_args) as the caller built it */
	__u32 op;		/* CUBE_OP_RANGE */
	__u8 space[32];		/* in: the space to search */
	__u64 lo[3];		/* in: the region's near corner, inclusive */
	__u64 hi[3];		/* in: the region's far corner, inclusive */
	__u64 cursor;		/* in: 0 to start, or what the last call returned;
				 * out: what to pass next — see the end-of-walk rule above
				 */
	__u64 value;		/* user pointer: where to put the records */
	__u64 len;		/* in: the buffer's capacity;
				 * out: bytes written, or on -ERANGE what would be needed
				 */
};

#endif /* _UAPI_LINUX_CUBE_H */