aboutsummaryrefslogtreecommitdiffstats
path: root/lib/sort.c
blob: d54cf97e9548a93d7e7940ab2d0b2857d259a529 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
// SPDX-License-Identifier: GPL-2.0
/*
 * A fast, small, non-recursive O(n log n) sort for the Linux kernel
 *
 * This performs n*log2(n) + 0.37*n + o(n) comparisons on average,
 * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case.
 *
 * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n
 * better) at the expense of stack usage and much larger code to avoid
 * quicksort's O(n^2) worst case.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/types.h>
#include <linux/export.h>
#include <linux/sort.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)
{
	unsigned char lsbits = (unsigned char)size;

	(void)base;
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
	lsbits |= (unsigned char)(uintptr_t)base;
#endif
	return (lsbits & (align - 1)) == 0;
}

/**
 * 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 stil 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)
{
	do {
		u32 t = *(u32 *)(a + (n -= 4));
		*(u32 *)(a + n) = *(u32 *)(b + n);
		*(u32 *)(b + n) = t;
	} while (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)
{
	do {
#ifdef CONFIG_64BIT
		u64 t = *(u64 *)(a + (n -= 8));
		*(u64 *)(a + n) = *(u64 *)(b + n);
		*(u64 *)(b + n) = t;
#else
		/* Use two 32-bit transfers to avoid base+index+4 addressing */
		u32 t = *(u32 *)(a + (n -= 4));
		*(u32 *)(a + n) = *(u32 *)(b + n);
		*(u32 *)(b + n) = t;

		t = *(u32 *)(a + (n -= 4));
		*(u32 *)(a + n) = *(u32 *)(b + n);
		*(u32 *)(b + n) = t;
#endif
	} while (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)
{
	do {
		char t = ((char *)a)[--n];
		((char *)a)[n] = ((char *)b)[n];
		((char *)b)[n] = t;
	} while (n);
}

typedef void (*swap_func_t)(void *a, void *b, int size);

/*
 * 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 (swap_func_t)0
#define SWAP_WORDS_32 (swap_func_t)1
#define SWAP_BYTES    (swap_func_t)2

/*
 * 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_func_t swap_func)
{
	if (swap_func == SWAP_WORDS_64)
		swap_words_64(a, b, size);
	else if (swap_func == SWAP_WORDS_32)
		swap_words_32(a, b, size);
	else if (swap_func == SWAP_BYTES)
		swap_bytes(a, b, size);
	else
		swap_func(a, b, (int)size);
}

typedef int (*cmp_func_t)(const void *, const void *);
typedef int (*cmp_r_func_t)(const void *, const void *, const void *);
#define _CMP_WRAPPER ((cmp_r_func_t)0L)

static int do_cmp(const void *a, const void *b,
		  cmp_r_func_t cmp, const void *priv)
{
	if (cmp == _CMP_WRAPPER)
		return ((cmp_func_t)(priv))(a, b);
	return cmp(a, b, priv);
}

/**
 * parent - given the offset of the child, find the offset of the parent.
 * @i: the offset of the heap element whose parent is sought.  Non-zero.
 * @lsbit: a precomputed 1-bit mask, equal to "size & -size"
 * @size: size of each element
 *
 * In terms of array indexes, the parent of element j = @i/@size is simply
 * (j-1)/2.  But when working in byte offsets, we can't use implicit
 * truncation of integer divides.
 *
 * Fortunately, we only need one bit of the quotient, not the full divide.
 * @size has a least significant bit.  That bit will be clear if @i is
 * an even multiple of @size, and set if it's an odd multiple.
 *
 * Logically, we're doing "if (i & lsbit) i -= size;", but since the
 * branch is unpredictable, it's done with a bit of clever branch-free
 * code instead.
 */
__attribute_const__ __always_inline
static size_t parent(size_t i, unsigned int lsbit, size_t size)
{
	i -= size;
	i -= size & -(i & lsbit);
	return i / 2;
}

/**
 * sort_r - sort an array of elements
 * @base: pointer to data to sort
 * @num: number of elements
 * @size: size of each element
 * @cmp_func: pointer to comparison function
 * @swap_func: pointer to swap function or NULL
 * @priv: third argument passed to comparison function
 *
 * This function does a heapsort on the given array.  You may provide
 * a swap_func function if you need to do something more than a memory
 * copy (e.g. fix up pointers or auxiliary data), but the built-in swap
 * avoids a slow retpoline and so is significantly faster.
 *
 * Sorting time is O(n log n) both on average and worst-case. While
 * quicksort is slightly faster on average, it suffers from exploitable
 * O(n*n) worst-case behavior and extra memory requirements that make
 * it less suitable for kernel use.
 */
void sort_r(void *base, size_t num, size_t size,
	    int (*cmp_func)(const void *, const void *, const void *),
	    void (*swap_func)(void *, void *, int size),
	    const void *priv)
{
	/* pre-scale counters for performance */
	size_t n = num * size, a = (num/2) * size;
	const unsigned int lsbit = size & -size;  /* Used to find parent */

	if (!a)		/* num < 2 || size == 0 */
		return;

	if (!swap_func) {
		if (is_aligned(base, size, 8))
			swap_func = SWAP_WORDS_64;
		else if (is_aligned(base, size, 4))
			swap_func = SWAP_WORDS_32;
		else
			swap_func = SWAP_BYTES;
	}

	/*
	 * Loop invariants:
	 * 1. elements [a,n) satisfy the heap property (compare greater than
	 *    all of their children),
	 * 2. elements [n,num*size) are sorted, and
	 * 3. a <= b <= c <= d <= n (whenever they are valid).
	 */
	for (;;) {
		size_t b, c, d;

		if (a)			/* Building heap: sift down --a */
			a -= size;
		else if (n -= size)	/* Sorting: Extract root to --n */
			do_swap(base, base + n, size, swap_func);
		else			/* Sort complete */
			break;

		/*
		 * Sift element at "a" down into heap.  This is the
		 * "bottom-up" variant, which significantly reduces
		 * calls to cmp_func(): we find the sift-down path all
		 * the way to the leaves (one compare per level), then
		 * backtrack to find where to insert the target element.
		 *
		 * Because elements tend to sift down close to the leaves,
		 * this uses fewer compares than doing two per level
		 * on the way down.  (A bit more than half as many on
		 * average, 3/4 worst-case.)
		 */
		for (b = a; c = 2*b + size, (d = c + size) < n;)
			b = do_cmp(base + c, base + d, cmp_func, priv) >= 0 ? c : d;
		if (d == n)	/* Special case last leaf with no sibling */
			b = c;

		/* Now backtrack from "b" to the correct location for "a" */
		while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0)
			b = parent(b, lsbit, size);
		c = b;			/* Where "a" belongs */
		while (b != a) {	/* Shift it into place */
			b = parent(b, lsbit, size);
			do_swap(base + b, base + c, size, swap_func);
		}
	}
}
EXPORT_SYMBOL(sort_r);

void sort(void *base, size_t num, size_t size,
	  int (*cmp_func)(const void *, const void *),
	  void (*swap_func)(void *, void *, int size))
{
	return sort_r(base, num, size, _CMP_WRAPPER, swap_func, cmp_func);
}
EXPORT_SYMBOL(sort);