1/*
2 * Copyright (c) 2004 Topspin Communications.  All rights reserved.
3 *
4 * This software is available to you under a choice of one of two
5 * licenses.  You may choose to be licensed under the terms of the GNU
6 * General Public License (GPL) Version 2, available from the file
7 * COPYING in the main directory of this source tree, or the
8 * OpenIB.org BSD license below:
9 *
10 *     Redistribution and use in source and binary forms, with or
11 *     without modification, are permitted provided that the following
12 *     conditions are met:
13 *
14 *      - Redistributions of source code must retain the above
15 *        copyright notice, this list of conditions and the following
16 *        disclaimer.
17 *
18 *      - Redistributions in binary form must reproduce the above
19 *        copyright notice, this list of conditions and the following
20 *        disclaimer in the documentation and/or other materials
21 *        provided with the distribution.
22 *
23 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
24 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
25 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
26 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
27 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
28 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
29 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
30 * SOFTWARE.
31 */
32
33#include <linux/errno.h>
34#include <linux/slab.h>
35#include <linux/bitmap.h>
36
37#include "mthca_dev.h"
38
39/* Trivial bitmap-based allocator */
40u32 mthca_alloc(struct mthca_alloc *alloc)
41{
42	unsigned long flags;
43	u32 obj;
44
45	spin_lock_irqsave(&alloc->lock, flags);
46
47	obj = find_next_zero_bit(alloc->table, alloc->max, alloc->last);
48	if (obj >= alloc->max) {
49		alloc->top = (alloc->top + alloc->max) & alloc->mask;
50		obj = find_first_zero_bit(alloc->table, alloc->max);
51	}
52
53	if (obj < alloc->max) {
54		set_bit(obj, alloc->table);
55		obj |= alloc->top;
56	} else
57		obj = -1;
58
59	spin_unlock_irqrestore(&alloc->lock, flags);
60
61	return obj;
62}
63
64void mthca_free(struct mthca_alloc *alloc, u32 obj)
65{
66	unsigned long flags;
67
68	obj &= alloc->max - 1;
69
70	spin_lock_irqsave(&alloc->lock, flags);
71
72	clear_bit(obj, alloc->table);
73	alloc->last = min(alloc->last, obj);
74	alloc->top = (alloc->top + alloc->max) & alloc->mask;
75
76	spin_unlock_irqrestore(&alloc->lock, flags);
77}
78
79int mthca_alloc_init(struct mthca_alloc *alloc, u32 num, u32 mask,
80		     u32 reserved)
81{
82	int i;
83
84	/* num must be a power of 2 */
85	if (num != 1 << (ffs(num) - 1))
86		return -EINVAL;
87
88	alloc->last = 0;
89	alloc->top  = 0;
90	alloc->max  = num;
91	alloc->mask = mask;
92	spin_lock_init(&alloc->lock);
93	alloc->table = kmalloc_array(BITS_TO_LONGS(num), sizeof(long),
94				     GFP_KERNEL);
95	if (!alloc->table)
96		return -ENOMEM;
97
98	bitmap_zero(alloc->table, num);
99	for (i = 0; i < reserved; ++i)
100		set_bit(i, alloc->table);
101
102	return 0;
103}
104
105void mthca_alloc_cleanup(struct mthca_alloc *alloc)
106{
107	kfree(alloc->table);
108}
109
110/*
111 * Array of pointers with lazy allocation of leaf pages.  Callers of
112 * _get, _set and _clear methods must use a lock or otherwise
113 * serialize access to the array.
114 */
115
116#define MTHCA_ARRAY_MASK (PAGE_SIZE / sizeof (void *) - 1)
117
118void *mthca_array_get(struct mthca_array *array, int index)
119{
120	int p = (index * sizeof (void *)) >> PAGE_SHIFT;
121
122	if (array->page_list[p].page)
123		return array->page_list[p].page[index & MTHCA_ARRAY_MASK];
124	else
125		return NULL;
126}
127
128int mthca_array_set(struct mthca_array *array, int index, void *value)
129{
130	int p = (index * sizeof (void *)) >> PAGE_SHIFT;
131
132	/* Allocate with GFP_ATOMIC because we'll be called with locks held. */
133	if (!array->page_list[p].page)
134		array->page_list[p].page = (void **) get_zeroed_page(GFP_ATOMIC);
135
136	if (!array->page_list[p].page)
137		return -ENOMEM;
138
139	array->page_list[p].page[index & MTHCA_ARRAY_MASK] = value;
140	++array->page_list[p].used;
141
142	return 0;
143}
144
145void mthca_array_clear(struct mthca_array *array, int index)
146{
147	int p = (index * sizeof (void *)) >> PAGE_SHIFT;
148
149	if (--array->page_list[p].used == 0) {
150		free_page((unsigned long) array->page_list[p].page);
151		array->page_list[p].page = NULL;
152	} else
153		array->page_list[p].page[index & MTHCA_ARRAY_MASK] = NULL;
154
155	if (array->page_list[p].used < 0)
156		pr_debug("Array %p index %d page %d with ref count %d < 0\n",
157			 array, index, p, array->page_list[p].used);
158}
159
160int mthca_array_init(struct mthca_array *array, int nent)
161{
162	int npage = (nent * sizeof (void *) + PAGE_SIZE - 1) / PAGE_SIZE;
163	int i;
164
165	array->page_list = kmalloc_array(npage, sizeof(*array->page_list),
166					 GFP_KERNEL);
167	if (!array->page_list)
168		return -ENOMEM;
169
170	for (i = 0; i < npage; ++i) {
171		array->page_list[i].page = NULL;
172		array->page_list[i].used = 0;
173	}
174
175	return 0;
176}
177
178void mthca_array_cleanup(struct mthca_array *array, int nent)
179{
180	int i;
181
182	for (i = 0; i < (nent * sizeof (void *) + PAGE_SIZE - 1) / PAGE_SIZE; ++i)
183		free_page((unsigned long) array->page_list[i].page);
184
185	kfree(array->page_list);
186}
187
188/*
189 * Handling for queue buffers -- we allocate a bunch of memory and
190 * register it in a memory region at HCA virtual address 0.  If the
191 * requested size is > max_direct, we split the allocation into
192 * multiple pages, so we don't require too much contiguous memory.
193 */
194
195int mthca_buf_alloc(struct mthca_dev *dev, int size, int max_direct,
196		    union mthca_buf *buf, int *is_direct, struct mthca_pd *pd,
197		    int hca_write, struct mthca_mr *mr)
198{
199	int err = -ENOMEM;
200	int npages, shift;
201	u64 *dma_list = NULL;
202	dma_addr_t t;
203	int i;
204
205	if (size <= max_direct) {
206		*is_direct = 1;
207		npages     = 1;
208		shift      = get_order(size) + PAGE_SHIFT;
209
210		buf->direct.buf = dma_alloc_coherent(&dev->pdev->dev,
211						     size, &t, GFP_KERNEL);
212		if (!buf->direct.buf)
213			return -ENOMEM;
214
215		dma_unmap_addr_set(&buf->direct, mapping, t);
216
217		while (t & ((1 << shift) - 1)) {
218			--shift;
219			npages *= 2;
220		}
221
222		dma_list = kmalloc_array(npages, sizeof(*dma_list),
223					 GFP_KERNEL);
224		if (!dma_list)
225			goto err_free;
226
227		for (i = 0; i < npages; ++i)
228			dma_list[i] = t + i * (1 << shift);
229	} else {
230		*is_direct = 0;
231		npages     = (size + PAGE_SIZE - 1) / PAGE_SIZE;
232		shift      = PAGE_SHIFT;
233
234		dma_list = kmalloc_array(npages, sizeof(*dma_list),
235					 GFP_KERNEL);
236		if (!dma_list)
237			return -ENOMEM;
238
239		buf->page_list = kmalloc_array(npages,
240					       sizeof(*buf->page_list),
241					       GFP_KERNEL);
242		if (!buf->page_list)
243			goto err_out;
244
245		for (i = 0; i < npages; ++i)
246			buf->page_list[i].buf = NULL;
247
248		for (i = 0; i < npages; ++i) {
249			buf->page_list[i].buf =
250				dma_alloc_coherent(&dev->pdev->dev, PAGE_SIZE,
251						   &t, GFP_KERNEL);
252			if (!buf->page_list[i].buf)
253				goto err_free;
254
255			dma_list[i] = t;
256			dma_unmap_addr_set(&buf->page_list[i], mapping, t);
257
258			clear_page(buf->page_list[i].buf);
259		}
260	}
261
262	err = mthca_mr_alloc_phys(dev, pd->pd_num,
263				  dma_list, shift, npages,
264				  0, size,
265				  MTHCA_MPT_FLAG_LOCAL_READ |
266				  (hca_write ? MTHCA_MPT_FLAG_LOCAL_WRITE : 0),
267				  mr);
268	if (err)
269		goto err_free;
270
271	kfree(dma_list);
272
273	return 0;
274
275err_free:
276	mthca_buf_free(dev, size, buf, *is_direct, NULL);
277
278err_out:
279	kfree(dma_list);
280
281	return err;
282}
283
284void mthca_buf_free(struct mthca_dev *dev, int size, union mthca_buf *buf,
285		    int is_direct, struct mthca_mr *mr)
286{
287	int i;
288
289	if (mr)
290		mthca_free_mr(dev, mr);
291
292	if (is_direct)
293		dma_free_coherent(&dev->pdev->dev, size, buf->direct.buf,
294				  dma_unmap_addr(&buf->direct, mapping));
295	else {
296		for (i = 0; i < (size + PAGE_SIZE - 1) / PAGE_SIZE; ++i)
297			dma_free_coherent(&dev->pdev->dev, PAGE_SIZE,
298					  buf->page_list[i].buf,
299					  dma_unmap_addr(&buf->page_list[i],
300							 mapping));
301		kfree(buf->page_list);
302	}
303}
304