// 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. * * Quicksort 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. */ #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) { … } /** * 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) { … } /** * 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) { … } /** * 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, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { … } EXPORT_SYMBOL(…); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { … } EXPORT_SYMBOL(…);
Codebase Browser
linux