void (*swp)(void *lhs, void *rhs, void *args);
};
+/**
+ * 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 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 __always_inline
+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 __always_inline
+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 __always_inline
+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);
+}
+
+/*
+ * 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 ((void (*)(void *, void *, void *))0)
+#define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1)
+#define SWAP_BYTES ((void (*)(void *, void *, void *))2)
+
+/*
+ * Selects the appropriate swap function based on the element size.
+ */
+static __always_inline
+void *select_swap_func(const void *base, size_t size)
+{
+ if (is_aligned(base, size, 8))
+ return SWAP_WORDS_64;
+ else if (is_aligned(base, size, 4))
+ return SWAP_WORDS_32;
+ else
+ return SWAP_BYTES;
+}
+
+static __always_inline
+void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args),
+ void *priv)
+{
+ 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, 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.
{
const unsigned long lsbit = elem_size & -elem_size;
void *data = heap->data;
+ void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
/* pre-scale counters for performance */
size_t a = pos * elem_size;
size_t b, c, d;
size_t n = heap->nr * elem_size;
+ if (!swp)
+ swp = select_swap_func(data, elem_size);
+
/* Find the sift-down path all the way to the leaves. */
for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;)
b = func->less(data + c, data + d, args) ? c : d;
c = b;
while (b != a) {
b = parent(b, lsbit, elem_size);
- func->swp(data + b, data + c, args);
+ do_swap(data + b, data + c, elem_size, swp, args);
}
}
{
const unsigned long lsbit = elem_size & -elem_size;
void *data = heap->data;
+ void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
/* pre-scale counters for performance */
size_t a = idx * elem_size, b;
+ if (!swp)
+ swp = select_swap_func(data, elem_size);
+
while (a) {
b = parent(a, lsbit, elem_size);
if (func->less(data + b, data + a, args))
break;
- func->swp(data + a, data + b, args);
+ do_swap(data + a, data + b, elem_size, swp, args);
a = b;
}
}
const struct min_heap_callbacks *func, void *args)
{
void *data = heap->data;
+ void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
return false;
+ if (!swp)
+ swp = select_swap_func(data, elem_size);
+
/* Place last element at the root (position 0) and then sift down. */
heap->nr--;
if (idx == heap->nr)
return true;
- func->swp(data + (idx * elem_size), data + (heap->nr * elem_size), args);
+ do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args);
__min_heap_sift_up_inline(heap, elem_size, idx, func, args);
__min_heap_sift_down_inline(heap, idx, elem_size, func, args);
projects / linux-2.6-microblaze.git / commitdiff