eytzinger.c | Explore in Territory

// SPDX-License-Identifier: GPL-2.0

#include "eytzinger.h"

/**
 * is_aligned - is this pointer & size okay for word-wide copying?
 * @base: pointer to data
 * @size: size of each element
 * @align: required alignment (typically 4 or 8)
 *
 * Returns true if elements can be copied using word loads and stores.
 * The size must be a multiple of the alignment, and the base address must
 * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
 *
 * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)"
 * to "if ((a | b) & mask)", so we do that by hand.
 */
__attribute_const__ __always_inline
static bool is_aligned(const void *base, size_t size, unsigned char align)
{ … }

/**
 * swap_words_32 - swap two elements in 32-bit chunks
 * @a: pointer to the first element to swap
 * @b: pointer to the second element to swap
 * @n: element size (must be a multiple of 4)
 *
 * Exchange the two objects in memory.  This exploits base+index addressing,
 * which basically all CPUs have, to minimize loop overhead computations.
 *
 * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
 * bottom of the loop, even though the zero flag is still valid from the
 * subtract (since the intervening mov instructions don't alter the flags).
 * Gcc 8.1.0 doesn't have that problem.
 */
static void swap_words_32(void *a, void *b, size_t n)
{ … }

/**
 * swap_words_64 - swap two elements in 64-bit chunks
 * @a: pointer to the first element to swap
 * @b: pointer to the second element to swap
 * @n: element size (must be a multiple of 8)
 *
 * Exchange the two objects in memory.  This exploits base+index
 * addressing, which basically all CPUs have, to minimize loop overhead
 * computations.
 *
 * We'd like to use 64-bit loads if possible.  If they're not, emulating
 * one requires base+index+4 addressing which x86 has but most other
 * processors do not.  If CONFIG_64BIT, we definitely have 64-bit loads,
 * but it's possible to have 64-bit loads without 64-bit pointers (e.g.
 * x32 ABI).  Are there any cases the kernel needs to worry about?
 */
static void swap_words_64(void *a, void *b, size_t n)
{ … }

/**
 * swap_bytes - swap two elements a byte at a time
 * @a: pointer to the first element to swap
 * @b: pointer to the second element to swap
 * @n: element size
 *
 * This is the fallback if alignment doesn't allow using larger chunks.
 */
static void swap_bytes(void *a, void *b, size_t n)
{ … }

/*
 * The values are arbitrary as long as they can't be confused with
 * a pointer, but small integers make for the smallest compare
 * instructions.
 */
#define SWAP_WORDS_64 …
#define SWAP_WORDS_32 …
#define SWAP_BYTES …
#define SWAP_WRAPPER …

struct wrapper { … };

/*
 * The function pointer is last to make tail calls most efficient if the
 * compiler decides not to inline this function.
 */
static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv)
{ … }

#define _CMP_WRAPPER …

static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv)
{ … }

static inline int eytzinger0_do_cmp(void *base, size_t n, size_t size,
			 cmp_r_func_t cmp_func, const void *priv,
			 size_t l, size_t r)
{ … }

static inline void eytzinger0_do_swap(void *base, size_t n, size_t size,
			   swap_r_func_t swap_func, const void *priv,
			   size_t l, size_t r)
{ … }

void eytzinger0_sort_r(void *base, size_t n, size_t size,
		       cmp_r_func_t cmp_func,
		       swap_r_func_t swap_func,
		       const void *priv)
{ … }

void eytzinger0_sort(void *base, size_t n, size_t size,
		     cmp_func_t cmp_func,
		     swap_func_t swap_func)
{ … }

#if 0
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/ktime.h>

static u64 cmp_count;

static int mycmp(const void *a, const void *b)
{
	u32 _a = *(u32 *)a;
	u32 _b = *(u32 *)b;

	cmp_count++;
	if (_a < _b)
		return -1;
	else if (_a > _b)
		return 1;
	else
		return 0;
}

static int test(void)
{
	size_t N, i;
	ktime_t start, end;
	s64 delta;
	u32 *arr;

	for (N = 10000; N <= 100000; N += 10000) {
		arr = kmalloc_array(N, sizeof(u32), GFP_KERNEL);
		cmp_count = 0;

		for (i = 0; i < N; i++)
			arr[i] = get_random_u32();

		start = ktime_get();
		eytzinger0_sort(arr, N, sizeof(u32), mycmp, NULL);
		end = ktime_get();

		delta = ktime_us_delta(end, start);
		printk(KERN_INFO "time: %lld\n", delta);
		printk(KERN_INFO "comparisons: %lld\n", cmp_count);

		u32 prev = 0;

		eytzinger0_for_each(i, N) {
			if (prev > arr[i])
				goto err;
			prev = arr[i];
		}

		kfree(arr);
	}
	return 0;

err:
	kfree(arr);
	return -1;
}
#endif
linux/fs/bcachefs/eytzinger.c
