litmus-rt-ext-res.git - LITMUS^RT with extended reservations for Forbidden Zones paper @ RTAS'20

about summary refs log tree commit diff stats

diff options

Diffstat (limited to 'include/linux/ftrace.h')

-rw-r--r--

1 files changed, 2 insertions, 1 deletions


diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9d88e1cb5dbb..ed0eb5254d1c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h
@@ -123,7 +123,8 @@ stack_trace_sysctl(struct ctl_table *table, int write,
123	struct ftrace_func_command {	123	struct ftrace_func_command {
124	struct list_head list;	124	struct list_head list;
125	char *name;	125	char *name;
126	int (func)(char func, char *cmd,	126	int (func)(struct ftrace_hash hash,
		127	char func, char cmd,
127	char *params, int enable);	128	char *params, int enable);
128	};	129	};
129		130

/a> 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703

/*
 * Copyright (c) 2007 Oracle.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 */
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/dma-mapping.h> /* for DMA_*_DEVICE */

#include "rdma.h"

/*
 * XXX
 *  - build with sparse
 *  - should we limit the size of a mr region?  let transport return failure?
 *  - should we detect duplicate keys on a socket?  hmm.
 *  - an rdma is an mlock, apply rlimit?
 */

/*
 * get the number of pages by looking at the page indices that the start and
 * end addresses fall in.
 *
 * Returns 0 if the vec is invalid.  It is invalid if the number of bytes
 * causes the address to wrap or overflows an unsigned int.  This comes
 * from being stored in the 'length' member of 'struct scatterlist'.
 */
static unsigned int rds_pages_in_vec(struct rds_iovec *vec)
{
	if ((vec->addr + vec->bytes <= vec->addr) ||
	    (vec->bytes > (u64)UINT_MAX))
		return 0;

	return ((vec->addr + vec->bytes + PAGE_SIZE - 1) >> PAGE_SHIFT) -
		(vec->addr >> PAGE_SHIFT);
}

static struct rds_mr *rds_mr_tree_walk(struct rb_root *root, u64 key,
				       struct rds_mr *insert)
{
	struct rb_node **p = &root->rb_node;
	struct rb_node *parent = NULL;
	struct rds_mr *mr;

	while (*p) {
		parent = *p;
		mr = rb_entry(parent, struct rds_mr, r_rb_node);

		if (key < mr->r_key)
			p = &(*p)->rb_left;
		else if (key > mr->r_key)
			p = &(*p)->rb_right;
		else
			return mr;
	}

	if (insert) {
		rb_link_node(&insert->r_rb_node, parent, p);
		rb_insert_color(&insert->r_rb_node, root);
		atomic_inc(&insert->r_refcount);
	}
	return NULL;
}

/*
 * Destroy the transport-specific part of a MR.
 */
static void rds_destroy_mr(struct rds_mr *mr)
{
	struct rds_sock *rs = mr->r_sock;
	void *trans_private = NULL;
	unsigned long flags;

	rdsdebug("RDS: destroy mr key is %x refcnt %u\n",
			mr->r_key, atomic_read(&mr->r_refcount));

	if (test_and_set_bit(RDS_MR_DEAD, &mr->r_state))
		return;

	spin_lock_irqsave(&rs->rs_rdma_lock, flags);
	if (!RB_EMPTY_NODE(&mr->r_rb_node))
		rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys);
	trans_private = mr->r_trans_private;
	mr->r_trans_private = NULL;
	spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);

	if (trans_private)
		mr->r_trans->free_mr(trans_private, mr->r_invalidate);
}

void __rds_put_mr_final(struct rds_mr *mr)
{
	rds_destroy_mr(mr);
	kfree(mr);
}

/*
 * By the time this is called we can't have any more ioctls called on
 * the socket so we don't need to worry about racing with others.
 */
void rds_rdma_drop_keys(struct rds_sock *rs)
{
	struct rds_mr *mr;
	struct rb_node *node;

	/* Release any MRs associated with this socket */
	while ((node = rb_first(&rs->rs_rdma_keys))) {
		mr = container_of(node, struct rds_mr, r_rb_node);
		if (mr->r_trans == rs->rs_transport)
			mr->r_invalidate = 0;
		rds_mr_put(mr);
	}

	if (rs->rs_transport && rs->rs_transport->flush_mrs)
		rs->rs_transport->flush_mrs();
}

/*
 * Helper function to pin user pages.
 */
static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages,
			struct page **pages, int write)
{
	int ret;

	ret = get_user_pages_fast(user_addr, nr_pages, write, pages);

	if (ret >= 0 && ret < nr_pages) {
		while (ret--)
			put_page(pages[ret]);
		ret = -EFAULT;
	}

	return ret;
}

static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
				u64 *cookie_ret, struct rds_mr **mr_ret)
{
	struct rds_mr *mr = NULL, *found;
	unsigned int nr_pages;
	struct page **pages = NULL;
	struct scatterlist *sg;
	void *trans_private;
	unsigned long flags;
	rds_rdma_cookie_t cookie;
	unsigned int nents;
	long i;
	int ret;

	if (rs->rs_bound_addr == 0) {
		ret = -ENOTCONN; /* XXX not a great errno */
		goto out;
	}

	if (rs->rs_transport->get_mr == NULL) {
		ret = -EOPNOTSUPP;
		goto out;
	}

	nr_pages = rds_pages_in_vec(&args->vec);
	if (nr_pages == 0) {
		ret = -EINVAL;
		goto out;
	}

	rdsdebug("RDS: get_mr addr %llx len %llu nr_pages %u\n",
		args->vec.addr, args->vec.bytes, nr_pages);

	/* XXX clamp nr_pages to limit the size of this alloc? */
	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
	if (pages == NULL) {
		ret = -ENOMEM;
		goto out;
	}

	mr = kzalloc(sizeof(struct rds_mr), GFP_KERNEL);
	if (mr == NULL) {
		ret = -ENOMEM;
		goto out;
	}

	atomic_set(&mr->r_refcount, 1);
	RB_CLEAR_NODE(&mr->r_rb_node);
	mr->r_trans = rs->rs_transport;
	mr->r_sock = rs;

	if (args->flags & RDS_RDMA_USE_ONCE)
		mr->r_use_once = 1;
	if (args->flags & RDS_RDMA_INVALIDATE)
		mr->r_invalidate = 1;
	if (args->flags & RDS_RDMA_READWRITE)
		mr->r_write = 1;

	/*
	 * Pin the pages that make up the user buffer and transfer the page
	 * pointers to the mr's sg array.  We check to see if we've mapped
	 * the whole region after transferring the partial page references
	 * to the sg array so that we can have one page ref cleanup path.
	 *
	 * For now we have no flag that tells us whether the mapping is
	 * r/o or r/w. We need to assume r/w, or we'll do a lot of RDMA to
	 * the zero page.
	 */
	ret = rds_pin_pages(args->vec.addr & PAGE_MASK, nr_pages, pages, 1);
	if (ret < 0)
		goto out;

	nents = ret;
	sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL);
	if (sg == NULL) {
		ret = -ENOMEM;
		goto out;
	}
	WARN_ON(!nents);
	sg_init_table(sg, nents);

	/* Stick all pages into the scatterlist */
	for (i = 0 ; i < nents; i++)
		sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0);

	rdsdebug("RDS: trans_private nents is %u\n", nents);

	/* Obtain a transport specific MR. If this succeeds, the
	 * s/g list is now owned by the MR.
	 * Note that dma_map() implies that pending writes are
	 * flushed to RAM, so no dma_sync is needed here. */
	trans_private = rs->rs_transport->get_mr(sg, nents, rs,
						 &mr->r_key);

	if (IS_ERR(trans_private)) {
		for (i = 0 ; i < nents; i++)
			put_page(sg_page(&sg[i]));
		kfree(sg);
		ret = PTR_ERR(trans_private);
		goto out;
	}

	mr->r_trans_private = trans_private;

	rdsdebug("RDS: get_mr put_user key is %x cookie_addr %p\n",
	       mr->r_key, (void *)(unsigned long) args->cookie_addr);

	/* The user may pass us an unaligned address, but we can only
	 * map page aligned regions. So we keep the offset, and build
	 * a 64bit cookie containing <R_Key, offset> and pass that
	 * around. */
	cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK);
	if (cookie_ret)
		*cookie_ret = cookie;

	if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) {
		ret = -EFAULT;
		goto out;
	}

	/* Inserting the new MR into the rbtree bumps its
	 * reference count. */
	spin_lock_irqsave(&rs->rs_rdma_lock, flags);
	found = rds_mr_tree_walk(&rs->rs_rdma_keys, mr->r_key, mr);
	spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);

	BUG_ON(found && found != mr);

	rdsdebug("RDS: get_mr key is %x\n", mr->r_key);
	if (mr_ret) {
		atomic_inc(&mr->r_refcount);
		*mr_ret = mr;
	}

	ret = 0;
out:
	kfree(pages);
	if (mr)
		rds_mr_put(mr);
	return ret;
}

int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen)
{
	struct rds_get_mr_args args;

	if (optlen != sizeof(struct rds_get_mr_args))
		return -EINVAL;

	if (copy_from_user(&args, (struct rds_get_mr_args __user *)optval,
			   sizeof(struct rds_get_mr_args)))
		return -EFAULT;

	return __rds_rdma_map(rs, &args, NULL, NULL);
}

int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen)
{
	struct rds_get_mr_for_dest_args args;
	struct rds_get_mr_args new_args;

	if (optlen != sizeof(struct rds_get_mr_for_dest_args))
		return -EINVAL;

	if (copy_from_user(&args, (struct rds_get_mr_for_dest_args __user *)optval,
			   sizeof(struct rds_get_mr_for_dest_args)))
		return -EFAULT;

	/*
	 * Initially, just behave like get_mr().
	 * TODO: Implement get_mr as wrapper around this
	 *	 and deprecate it.
	 */
	new_args.vec = args.vec;
	new_args.cookie_addr = args.cookie_addr;
	new_args.flags = args.flags;

	return __rds_rdma_map(rs, &new_args, NULL, NULL);
}

/*
 * Free the MR indicated by the given R_Key
 */
int rds_free_mr(struct rds_sock *rs, char __user *optval, int optlen)
{
	struct rds_free_mr_args args;
	struct rds_mr *mr;
	unsigned long flags;

	if (optlen != sizeof(struct rds_free_mr_args))
		return -EINVAL;

	if (copy_from_user(&args, (struct rds_free_mr_args __user *)optval,
			   sizeof(struct rds_free_mr_args)))
		return -EFAULT;

	/* Special case - a null cookie means flush all unused MRs */
	if (args.cookie == 0) {
		if (!rs->rs_transport || !rs->rs_transport->flush_mrs)
			return -EINVAL;
		rs->rs_transport->flush_mrs();
		return 0;
	}

	/* Look up the MR given its R_key and remove it from the rbtree
	 * so nobody else finds it.
	 * This should also prevent races with rds_rdma_unuse.
	 */
	spin_lock_irqsave(&rs->rs_rdma_lock, flags);
	mr = rds_mr_tree_walk(&rs->rs_rdma_keys, rds_rdma_cookie_key(args.cookie), NULL);
	if (mr) {
		rb_erase(&mr->r_rb_node, &rs->rs_rdma_keys);
		RB_CLEAR_NODE(&mr->r_rb_node);
		if (args.flags & RDS_RDMA_INVALIDATE)
			mr->r_invalidate = 1;
	}
	spin_unlock_irqrestore(&rs->rs_rdma_lock, flags);

	if (!mr)
		return -EINVAL;

	/*
	 * call rds_destroy_mr() ourselves so that we're sure it's done by the time
	 * we return.  If we let rds_mr_put() do it it might not happen until
	 * someone else drops their ref.
	 */
	rds_destroy_mr(mr);
	rds_mr_put(mr);
	return 0;
}

/*
 * This is called when we receive an extension header that
 * tells us this MR was used. It allows us to implement
 * use_once semantics
 */
void rds_rdma_unuse(struct rds_sock *rs, u32 r_key, int force)
{
	struct rds_mr *mr;
	unsigned long flags;
	int zot_me = 0;


context:
space:
mode: