aboutsummaryrefslogtreecommitdiffstats
path: root/net/ceph/osd_client.c
diff options
context:
space:
mode:
authorIlya Dryomov <idryomov@redhat.com>2014-11-05 07:45:58 -0500
committerIlya Dryomov <idryomov@redhat.com>2014-11-13 14:21:14 -0500
commitba9d114ec5578e6e99a4dfa37ff8ae688040fd64 (patch)
treeafdc6c5bbf5c1f690498e22908f3492f50f950d8 /net/ceph/osd_client.c
parenta390de0208e7f2f8fdb2fbf970240e4f7b308037 (diff)
libceph: clear r_req_lru_item in __unregister_linger_request()
kick_requests() can put linger requests on the notarget list. This means we need to clear the much-overloaded req->r_req_lru_item in __unregister_linger_request() as well, or we get an assertion failure in ceph_osdc_release_request() - !list_empty(&req->r_req_lru_item). AFAICT the assumption was that registered linger requests cannot be on any of req->r_req_lru_item lists, but that's clearly not the case. Signed-off-by: Ilya Dryomov <idryomov@redhat.com> Reviewed-by: Alex Elder <elder@linaro.org>
Diffstat (limited to 'net/ceph/osd_client.c')
-rw-r--r--net/ceph/osd_client.c2
1 files changed, 2 insertions, 0 deletions
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 75abaa87abac..decc3b74e65f 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1254,6 +1254,8 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc,
1254 if (list_empty(&req->r_osd_item)) 1254 if (list_empty(&req->r_osd_item))
1255 req->r_osd = NULL; 1255 req->r_osd = NULL;
1256 } 1256 }
1257
1258 list_del_init(&req->r_req_lru_item); /* can be on notarget */
1257 ceph_osdc_put_request(req); 1259 ceph_osdc_put_request(req);
1258} 1260}
1259 1261
generated by cgit v1.2.2 (git 2.25.0) at 2025-09-20 11:04:10 -0400
n226' href='#n226'>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 
#ifndef _LINUX_PAGEMAP_H
#define _LINUX_PAGEMAP_H

/*
 * Copyright 1995 Linus Torvalds
 */
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/compiler.h>
#include <asm/uaccess.h>
#include <linux/gfp.h>
#include <linux/bitops.h>
#include <linux/hardirq.h> /* for in_interrupt() */
#include <linux/hugetlb_inline.h>

/*
 * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
 * allocation mode flags.
 */
enum mapping_flags {
	AS_EIO		= __GFP_BITS_SHIFT + 0,	/* IO error on async write */
	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
};

static inline void mapping_set_error(struct address_space *mapping, int error)
{
	if (unlikely(error)) {
		if (error == -ENOSPC)
			set_bit(AS_ENOSPC, &mapping->flags);
		else
			set_bit(AS_EIO, &mapping->flags);
	}
}

static inline void mapping_set_unevictable(struct address_space *mapping)
{
	set_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline void mapping_clear_unevictable(struct address_space *mapping)
{
	clear_bit(AS_UNEVICTABLE, &mapping->flags);
}

static inline int mapping_unevictable(struct address_space *mapping)
{
	if (mapping)
		return test_bit(AS_UNEVICTABLE, &mapping->flags);
	return !!mapping;
}

static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
}

/*
 * This is non-atomic.  Only to be used before the mapping is activated.
 * Probably needs a barrier...
 */
static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
{
	m->flags = (m->flags & ~(__force unsigned long)__GFP_BITS_MASK) |
				(__force unsigned long)mask;
}

/*
 * The page cache can done in larger chunks than
 * one page, because it allows for more efficient
 * throughput (it can then be mapped into user
 * space in smaller chunks for same flexibility).
 *
 * Or rather, it _will_ be done in larger chunks.
 */
#define PAGE_CACHE_SHIFT	PAGE_SHIFT
#define PAGE_CACHE_SIZE		PAGE_SIZE
#define PAGE_CACHE_MASK		PAGE_MASK
#define PAGE_CACHE_ALIGN(addr)	(((addr)+PAGE_CACHE_SIZE-1)&PAGE_CACHE_MASK)

#define page_cache_get(page)		get_page(page)
#define page_cache_release(page)	put_page(page)
void release_pages(struct page **pages, int nr, int cold);

/*
 * speculatively take a reference to a page.
 * If the page is free (_count == 0), then _count is untouched, and 0
 * is returned. Otherwise, _count is incremented by 1 and 1 is returned.
 *
 * This function must be called inside the same rcu_read_lock() section as has
 * been used to lookup the page in the pagecache radix-tree (or page table):
 * this allows allocators to use a synchronize_rcu() to stabilize _count.
 *
 * Unless an RCU grace period has passed, the count of all pages coming out
 * of the allocator must be considered unstable. page_count may return higher
 * than expected, and put_page must be able to do the right thing when the
 * page has been finished with, no matter what it is subsequently allocated
 * for (because put_page is what is used here to drop an invalid speculative
 * reference).
 *
 * This is the interesting part of the lockless pagecache (and lockless
 * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
 * has the following pattern:
 * 1. find page in radix tree
 * 2. conditionally increment refcount
 * 3. check the page is still in pagecache (if no, goto 1)
 *
 * Remove-side that cares about stability of _count (eg. reclaim) has the
 * following (with tree_lock held for write):
 * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
 * B. remove page from pagecache
 * C. free the page
 *
 * There are 2 critical interleavings that matter:
 * - 2 runs before A: in this case, A sees elevated refcount and bails out
 * - A runs before 2: in this case, 2 sees zero refcount and retries;
 *   subsequently, B will complete and 1 will find no page, causing the
 *   lookup to return NULL.
 *
 * It is possible that between 1 and 2, the page is removed then the exact same
 * page is inserted into the same position in pagecache. That's OK: the
 * old find_get_page using tree_lock could equally have run before or after
 * such a re-insertion, depending on order that locks are granted.
 *
 * Lookups racing against pagecache insertion isn't a big problem: either 1
 * will find the page or it will not. Likewise, the old find_get_page could run
 * either before the insertion or afterwards, depending on timing.
 */
static inline int page_cache_get_speculative(struct page *page)
{
	VM_BUG_ON(in_interrupt());

#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
# ifdef CONFIG_PREEMPT
	VM_BUG_ON(!in_atomic());
# endif
	/*
	 * Preempt must be disabled here - we rely on rcu_read_lock doing
	 * this for us.
	 *
	 * Pagecache won't be truncated from interrupt context, so if we have
	 * found a page in the radix tree here, we have pinned its refcount by
	 * disabling preempt, and hence no need for the "speculative get" that
	 * SMP requires.
	 */
	VM_BUG_ON(page_count(page) == 0);
	atomic_inc(&page->_count);

#else
	if (unlikely(!get_page_unless_zero(page))) {
		/*
		 * Either the page has been freed, or will be freed.
		 * In either case, retry here and the caller should
		 * do the right thing (see comments above).
		 */
		return 0;
	}
#endif
	VM_BUG_ON(PageTail(page));

	return 1;
}

/*
 * Same as above, but add instead of inc (could just be merged)
 */
static inline int page_cache_add_speculative(struct page *page, int count)
{
	VM_BUG_ON(in_interrupt());

#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
# ifdef CONFIG_PREEMPT
	VM_BUG_ON(!in_atomic());
# endif
	VM_BUG_ON(page_count(page) == 0);