1 files changed, 200 insertions, 54 deletions

diff --git a/lib/sort.c b/lib/sort.c
index d6b7a202b0b6..50855ea8c262 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -1,8 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * A fast, small, non-recursive O(nlog n) sort for the Linux kernel
+ * A fast, small, non-recursive O(n log n) sort for the Linux kernel
  *
- * Jan 23 2005  Matt Mackall <mpm@selenic.com>
+ * 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
@@ -11,35 +16,155 @@
 #include <linux/export.h>
 #include <linux/sort.h>
 
-static int alignment_ok(const void *base, int align)
+/**
+ * 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)
 {
-	return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
-		((unsigned long)base & (align - 1)) == 0;
+	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;
 }
 
-static void u32_swap(void *a, void *b, int size)
+/**
+ * swap_words_32 - swap two elements in 32-bit chunks
+ * @a, @b: pointers to the elements
+ * @size: 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)
 {
-	u32 t = *(u32 *)a;
-	*(u32 *)a = *(u32 *)b;
-	*(u32 *)b = t;
+	do {
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+	} while (n);
 }
 
-static void u64_swap(void *a, void *b, int size)
+/**
+ * swap_words_64 - swap two elements in 64-bit chunks
+ * @a, @b: pointers to the elements
+ * @size: 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)
 {
-	u64 t = *(u64 *)a;
-	*(u64 *)a = *(u64 *)b;
-	*(u64 *)b = t;
+	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);
 }
 
-static void generic_swap(void *a, void *b, int size)
+/**
+ * swap_bytes - swap two elements a byte at a time
+ * @a, @b: pointers to the elements
+ * @size: 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)
 {
-	char t;
-
 	do {
-		t = *(char *)a;
-		*(char *)a++ = *(char *)b;
-		*(char *)b++ = t;
-	} while (--size > 0);
+		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);
+}
+
+/**
+ * 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;
 }
 
 /**
@@ -50,57 +175,78 @@ static void generic_swap(void *a, void *b, int size)
  * @cmp_func: pointer to comparison function
  * @swap_func: pointer to swap function or NULL
  *
- * This function does a heapsort on the given array. You may provide a
- * swap_func function optimized to your element type.
+ * 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
- * qsort is about 20% faster on average, it suffers from exploitable
+ * 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(void *base, size_t num, size_t size,
 	  int (*cmp_func)(const void *, const void *),
 	  void (*swap_func)(void *, void *, int size))
 {
 	/* pre-scale counters for performance */
-	int i = (num/2 - 1) * size, n = num * size, c, r;
+	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 (size == 4 && alignment_ok(base, 4))
-			swap_func = u32_swap;
-		else if (size == 8 && alignment_ok(base, 8))
-			swap_func = u64_swap;
+		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 = generic_swap;
+			swap_func = SWAP_BYTES;
 	}
 
-	/* heapify */
-	for ( ; i >= 0; i -= size) {
-		for (r = i; r * 2 + size < n; r  = c) {
-			c = r * 2 + size;
-			if (c < n - size &&
-					cmp_func(base + c, base + c + size) < 0)
-				c += size;
-			if (cmp_func(base + r, base + c) >= 0)
-				break;
-			swap_func(base + r, base + c, size);
-		}
-	}
+	/*
+	 * 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;
 
-	/* sort */
-	for (i = n - size; i > 0; i -= size) {
-		swap_func(base, base + i, size);
-		for (r = 0; r * 2 + size < i; r = c) {
-			c = r * 2 + size;
-			if (c < i - size &&
-					cmp_func(base + c, base + c + size) < 0)
-				c += size;
-			if (cmp_func(base + r, base + c) >= 0)
-				break;
-			swap_func(base + r, base + c, size);
+		/*
+		 * 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 = cmp_func(base + c, base + d) >= 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 && cmp_func(base + a, base + b) >= 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);