Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:

 - most of the rest of MM

 - procfs

 - lib/ updates

 - printk updates

 - bitops infrastructure tweaks

 - checkpatch updates

 - nilfs2 update

 - signals

 - various other misc bits: coredump, seqfile, kexec, pidns, zlib, ipc,
   dma-debug, dma-mapping, ...

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (102 commits)
  ipc,msg: drop dst nil validation in copy_msg
  include/linux/zutil.h: fix usage example of zlib_adler32()
  panic: release stale console lock to always get the logbuf printed out
  dma-debug: check nents in dma_sync_sg*
  dma-mapping: tidy up dma_parms default handling
  pidns: fix set/getpriority and ioprio_set/get in PRIO_USER mode
  kexec: use file name as the output message prefix
  fs, seqfile: always allow oom killer
  seq_file: reuse string_escape_str()
  fs/seq_file: use seq_* helpers in seq_hex_dump()
  coredump: change zap_threads() and zap_process() to use for_each_thread()
  coredump: ensure all coredumping tasks have SIGNAL_GROUP_COREDUMP
  signal: remove jffs2_garbage_collect_thread()->allow_signal(SIGCONT)
  signal: introduce kernel_signal_stop() to fix jffs2_garbage_collect_thread()
  signal: turn dequeue_signal_lock() into kernel_dequeue_signal()
  signals: kill block_all_signals() and unblock_all_signals()
  nilfs2: fix gcc uninitialized-variable warnings in powerpc build
  nilfs2: fix gcc unused-but-set-variable warnings
  MAINTAINERS: nilfs2: add header file for tracing
  nilfs2: add tracepoints for analyzing reading and writing metadata files
  ...

Documentation/printk-formats.txt

@@ -23,6 +23,10 @@ Example:
 
 Reminder: sizeof() result is of type size_t.
 
+The kernel's printf does not support %n. For obvious reasons, floating
+point formats (%e, %f, %g, %a) are also not recognized. Use of any
+unsupported specifier or length qualifier results in a WARN and early
+return from vsnprintf.
 
 Raw pointer value SHOULD be printed with %p. The kernel supports
 the following extended format specifiers for pointer types:
@@ -119,6 +123,7 @@ Raw buffer as an escaped string:
 	If field width is omitted the 1 byte only will be escaped.
 
 Raw buffer as a hex string:
+
 	%*ph	00 01 02  ...  3f
 	%*phC	00:01:02: ... :3f
 	%*phD	00-01-02- ... -3f
@@ -234,6 +239,7 @@ UUID/GUID addresses:
 	Passed by reference.
 
 dentry names:
+
 	%pd{,2,3,4}
 	%pD{,2,3,4}
 
@@ -256,6 +262,8 @@ struct va_format:
 		va_list *va;
 	};
 
+	Implements a "recursive vsnprintf".
+
 	Do not use this feature without some mechanism to verify the
 	correctness of the format string and va_list arguments.
 
@@ -284,6 +292,27 @@ bitmap and its derivatives such as cpumask and nodemask:
 
 	Passed by reference.
 
+Network device features:
+
+	%pNF	0x000000000000c000
+
+	For printing netdev_features_t.
+
+	Passed by reference.
+
+Command from struct task_struct
+
+	%pT	ls
+
+	For printing executable name excluding path from struct
+	task_struct.
+
+	Passed by reference.
+
+If you add other %p extensions, please extend lib/test_printf.c with
+one or more test cases, if at all feasible.
+
+
 Thank you for your cooperation and attention.
 
 

Documentation/vm/balance

@@ -1,12 +1,14 @@
 Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
 
-Memory balancing is needed for non __GFP_WAIT as well as for non
+Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
-__GFP_IO allocations.
+well as for non __GFP_IO allocations.
 
-There are two reasons to be requesting non __GFP_WAIT allocations:
+The first reason why a caller may avoid reclaim is that the caller can not
-the caller can not sleep (typically intr context), or does not want
+sleep due to holding a spinlock or is in interrupt context. The second may
-to incur cost overheads of page stealing and possible swap io for
+be that the caller is willing to fail the allocation without incurring the
-whatever reasons.
+overhead of page reclaim. This may happen for opportunistic high-order
+allocation requests that have order-0 fallback options. In such cases,
+the caller may also wish to avoid waking kswapd.
 
 __GFP_IO allocation requests are made to prevent file system deadlocks.
 

Documentation/vm/split_page_table_lock

@@ -54,8 +54,8 @@ everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
 which must be called on PTE table allocation / freeing.
 
 Make sure the architecture doesn't use slab allocator for page table
-allocation: slab uses page->slab_cache and page->first_page for its pages.
+allocation: slab uses page->slab_cache for its pages.
-These fields share storage with page->ptl.
+This field shares storage with page->ptl.
 
 PMD split lock only makes sense if you have more than two page table
 levels.

MAINTAINERS

@@ -4209,7 +4209,10 @@ L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon.git
 S:	Maintained
 F:	drivers/extcon/
+F:	include/linux/extcon/
+F:	include/linux/extcon.h
 F:	Documentation/extcon/
+F:	Documentation/devicetree/bindings/extcon/
 
 EXYNOS DP DRIVER
 M:	Jingoo Han <jingoohan1@gmail.com>
@@ -7490,6 +7493,7 @@ S:	Supported
 F:	Documentation/filesystems/nilfs2.txt
 F:	fs/nilfs2/
 F:	include/linux/nilfs2_fs.h
+F:	include/trace/events/nilfs2.h
 
 NINJA SCSI-3 / NINJA SCSI-32Bi (16bit/CardBus) PCMCIA SCSI HOST ADAPTER DRIVER
 M:	YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>

arch/arm/mm/dma-mapping.c

@@ -651,12 +651,12 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT))
+	else if (dev_get_cma_area(dev) && (gfp & __GFP_DIRECT_RECLAIM))
 		addr = __alloc_from_contiguous(dev, size, prot, &page,
 					       caller, want_vaddr);
 	else if (is_coherent)
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (!(gfp & __GFP_WAIT))
+	else if (!gfpflags_allow_blocking(gfp))
 		addr = __alloc_from_pool(size, &page);
 	else
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page,
@@ -1363,7 +1363,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
-	if (!(gfp & __GFP_WAIT))
+	if (!gfpflags_allow_blocking(gfp))
 		return __iommu_alloc_atomic(dev, size, handle);
 
 	/*

arch/arm/xen/mm.c

@@ -25,7 +25,7 @@
 unsigned long xen_get_swiotlb_free_pages(unsigned int order)
 {
 	struct memblock_region *reg;
-	gfp_t flags = __GFP_NOWARN;
+	gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM;
 
 	for_each_memblock(memory, reg) {
 		if (reg->base < (phys_addr_t)0xffffffff) {

arch/arm64/mm/dma-mapping.c

@@ -100,7 +100,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size,
 	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA;
-	if (dev_get_cma_area(dev) && (flags & __GFP_WAIT)) {
+	if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) {
 		struct page *page;
 		void *addr;
 
@@ -148,7 +148,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 
 	size = PAGE_ALIGN(size);
 
-	if (!coherent && !(flags & __GFP_WAIT)) {
+	if (!coherent && !gfpflags_allow_blocking(flags)) {
 		struct page *page = NULL;
 		void *addr = __alloc_from_pool(size, &page, flags);
 

arch/sh/kernel/cpu/sh5/unwind.c

@@ -159,7 +159,7 @@ static int lookup_prev_stack_frame(unsigned long fp, unsigned long pc,
 
 			/* Sign extend */
 			regcache[dest] =
-				((((s64)(u64)op >> 10) & 0xffff) << 54) >> 54;
+				sign_extend64((((u64)op >> 10) & 0xffff), 9);
 			break;
 		case (0xd0 >> 2): /* addi */
 		case (0xd4 >> 2): /* addi.l */

arch/sh/kernel/traps_64.c

@@ -101,7 +101,7 @@ static int generate_and_check_address(struct pt_regs *regs,
 	if (displacement_not_indexed) {
 		__s64 displacement;
 		displacement = (opcode >> 10) & 0x3ff;
-		displacement = ((displacement << 54) >> 54); /* sign extend */
+		displacement = sign_extend64(displacement, 9);
 		addr = (__u64)((__s64)base_address + (displacement << width_shift));
 	} else {
 		__u64 offset;

arch/x86/kernel/cpu/perf_event_msr.c

@@ -163,10 +163,9 @@ again:
 		goto again;
 
 	delta = now - prev;
-	if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) {
+	if (unlikely(event->hw.event_base == MSR_SMI_COUNT))
-		delta <<= 32;
+		delta = sign_extend64(delta, 31);
-		delta >>= 32; /* sign extend */
+
-	}
 	local64_add(now - prev, &event->count);
 }
 

arch/x86/kernel/pci-dma.c

@@ -90,7 +90,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 again:
 	page = NULL;
 	/* CMA can be used only in the context which permits sleeping */
-	if (flag & __GFP_WAIT) {
+	if (gfpflags_allow_blocking(flag)) {
 		page = dma_alloc_from_contiguous(dev, count, get_order(size));
 		if (page && page_to_phys(page) + size > dma_mask) {
 			dma_release_from_contiguous(dev, page, count);

arch/xtensa/configs/iss_defconfig

@@ -169,7 +169,6 @@ CONFIG_FLATMEM_MANUAL=y
 # CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 # CONFIG_PHYS_ADDR_T_64BIT is not set
 CONFIG_ZONE_DMA_FLAG=1

block/bio.c

@@ -211,7 +211,7 @@ fallback:
 		bvl = mempool_alloc(pool, gfp_mask);
 	} else {
 		struct biovec_slab *bvs = bvec_slabs + *idx;
-		gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);
+		gfp_t __gfp_mask = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_IO);
 
 		/*
 		 * Make this allocation restricted and don't dump info on
@@ -221,11 +221,11 @@ fallback:
 		__gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
 
 		/*
-		 * Try a slab allocation. If this fails and __GFP_WAIT
+		 * Try a slab allocation. If this fails and __GFP_DIRECT_RECLAIM
 		 * is set, retry with the 1-entry mempool
 		 */
 		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
-		if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) {
+		if (unlikely(!bvl && (gfp_mask & __GFP_DIRECT_RECLAIM))) {
 			*idx = BIOVEC_MAX_IDX;
 			goto fallback;
 		}
@@ -395,12 +395,12 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  *   If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
  *   backed by the @bs's mempool.
  *
- *   When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
+ *   When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will
- *   able to allocate a bio. This is due to the mempool guarantees. To make this
+ *   always be able to allocate a bio. This is due to the mempool guarantees.
- *   work, callers must never allocate more than 1 bio at a time from this pool.
+ *   To make this work, callers must never allocate more than 1 bio at a time
- *   Callers that need to allocate more than 1 bio must always submit the
+ *   from this pool. Callers that need to allocate more than 1 bio must always
- *   previously allocated bio for IO before attempting to allocate a new one.
+ *   submit the previously allocated bio for IO before attempting to allocate
- *   Failure to do so can cause deadlocks under memory pressure.
+ *   a new one. Failure to do so can cause deadlocks under memory pressure.
  *
  *   Note that when running under generic_make_request() (i.e. any block
  *   driver), bios are not submitted until after you return - see the code in
@@ -459,13 +459,13 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		 * We solve this, and guarantee forward progress, with a rescuer
 		 * workqueue per bio_set. If we go to allocate and there are
 		 * bios on current->bio_list, we first try the allocation
-		 * without __GFP_WAIT; if that fails, we punt those bios we
+		 * without __GFP_DIRECT_RECLAIM; if that fails, we punt those
-		 * would be blocking to the rescuer workqueue before we retry
+		 * bios we would be blocking to the rescuer workqueue before
-		 * with the original gfp_flags.
+		 * we retry with the original gfp_flags.
 		 */
 
 		if (current->bio_list && !bio_list_empty(current->bio_list))
-			gfp_mask &= ~__GFP_WAIT;
+			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
 		if (!p && gfp_mask != saved_gfp) {

block/blk-core.c

@@ -638,7 +638,7 @@ int blk_queue_enter(struct request_queue *q, gfp_t gfp)
 		if (percpu_ref_tryget_live(&q->q_usage_counter))
 			return 0;
 
-		if (!(gfp & __GFP_WAIT))
+		if (!gfpflags_allow_blocking(gfp))
 			return -EBUSY;
 
 		ret = wait_event_interruptible(q->mq_freeze_wq,
@@ -1206,8 +1206,8 @@ rq_starved:
  * @bio: bio to allocate request for (can be %NULL)
  * @gfp_mask: allocation mask
  *
- * Get a free request from @q.  If %__GFP_WAIT is set in @gfp_mask, this
+ * Get a free request from @q.  If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
- * function keeps retrying under memory pressure and fails iff @q is dead.
+ * this function keeps retrying under memory pressure and fails iff @q is dead.
  *
  * Must be called with @q->queue_lock held and,
  * Returns ERR_PTR on failure, with @q->queue_lock held.
@@ -1227,7 +1227,7 @@ retry:
 	if (!IS_ERR(rq))
 		return rq;
 
-	if (!(gfp_mask & __GFP_WAIT) || unlikely(blk_queue_dying(q))) {
+	if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return rq;
 	}
@@ -1305,11 +1305,11 @@ EXPORT_SYMBOL(blk_get_request);
  * BUG.
  *
  * WARNING: When allocating/cloning a bio-chain, careful consideration should be
- * given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
+ * given to how you allocate bios. In particular, you cannot use
- * anything but the first bio in the chain. Otherwise you risk waiting for IO
+ * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
- * completion of a bio that hasn't been submitted yet, thus resulting in a
+ * you risk waiting for IO completion of a bio that hasn't been submitted yet,
- * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
+ * thus resulting in a deadlock. Alternatively bios should be allocated using
- * of bio_alloc(), as that avoids the mempool deadlock.
+ * bio_kmalloc() instead of bio_alloc(), as that avoids the mempool deadlock.
  * If possible a big IO should be split into smaller parts when allocation
  * fails. Partial allocation should not be an error, or you risk a live-lock.
  */
@@ -2038,7 +2038,7 @@ void generic_make_request(struct bio *bio)
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
-		if (likely(blk_queue_enter(q, __GFP_WAIT) == 0)) {
+		if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) {
 
 			q->make_request_fn(q, bio);
 

block/blk-ioc.c

@@ -289,7 +289,7 @@ struct io_context *get_task_io_context(struct task_struct *task,
 {
 	struct io_context *ioc;
 
-	might_sleep_if(gfp_flags & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(gfp_flags));
 
 	do {
 		task_lock(task);

block/blk-mq-tag.c

@@ -268,7 +268,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 	if (tag != -1)
 		return tag;
 
-	if (!(data->gfp & __GFP_WAIT))
+	if (!gfpflags_allow_blocking(data->gfp))
 		return -1;
 
 	bs = bt_wait_ptr(bt, hctx);

block/blk-mq.c

@@ -244,11 +244,11 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-	blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_WAIT,
+	blk_mq_set_alloc_data(&alloc_data, q, gfp & ~__GFP_DIRECT_RECLAIM,
 			reserved, ctx, hctx);
 
 	rq = __blk_mq_alloc_request(&alloc_data, rw);
-	if (!rq && (gfp & __GFP_WAIT)) {
+	if (!rq && (gfp & __GFP_DIRECT_RECLAIM)) {
 		__blk_mq_run_hw_queue(hctx);
 		blk_mq_put_ctx(ctx);
 
@@ -1186,7 +1186,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 		ctx = blk_mq_get_ctx(q);
 		hctx = q->mq_ops->map_queue(q, ctx->cpu);
 		blk_mq_set_alloc_data(&alloc_data, q,
-				__GFP_WAIT|GFP_ATOMIC, false, ctx, hctx);
+				__GFP_RECLAIM|__GFP_HIGH, false, ctx, hctx);
 		rq = __blk_mq_alloc_request(&alloc_data, rw);
 		ctx = alloc_data.ctx;
 		hctx = alloc_data.hctx;

block/ioprio.c

@@ -123,7 +123,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 				break;
 
 			do_each_thread(g, p) {
-				if (!uid_eq(task_uid(p), uid))
+				if (!uid_eq(task_uid(p), uid) ||
+				    !task_pid_vnr(p))
 					continue;
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
@@ -220,7 +221,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				break;
 
 			do_each_thread(g, p) {
-				if (!uid_eq(task_uid(p), user->uid))
+				if (!uid_eq(task_uid(p), user->uid) ||
+				    !task_pid_vnr(p))
 					continue;
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)

block/scsi_ioctl.c

@@ -444,7 +444,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
+	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
@@ -495,7 +495,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		break;
 	}
 
-	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
+	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) {
 		err = DRIVER_ERROR << 24;
 		goto error;
 	}
@@ -536,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, WRITE, __GFP_WAIT);
+	rq = blk_get_request(q, WRITE, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	blk_rq_set_block_pc(rq);

drivers/block/drbd/drbd_bitmap.c

@@ -1007,7 +1007,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 	bm_set_page_unchanged(b->bm_pages[page_nr]);
 
 	if (ctx->flags & BM_AIO_COPY_PAGES) {
-		page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_WAIT);
+		page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM);
 		copy_highpage(page, b->bm_pages[page_nr]);
 		bm_store_page_idx(page, page_nr);
 	} else

drivers/block/drbd/drbd_receiver.c

@@ -357,7 +357,8 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
 	}
 
 	if (has_payload && data_size) {
-		page = drbd_alloc_pages(peer_device, nr_pages, (gfp_mask & __GFP_WAIT));
+		page = drbd_alloc_pages(peer_device, nr_pages,
+					gfpflags_allow_blocking(gfp_mask));
 		if (!page)
 			goto fail;
 	}

drivers/block/mtip32xx/mtip32xx.c

@@ -173,7 +173,7 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 {
 	struct request *rq;
 
-	rq = blk_mq_alloc_request(dd->queue, 0, __GFP_WAIT, true);
+	rq = blk_mq_alloc_request(dd->queue, 0, __GFP_RECLAIM, true);
 	return blk_mq_rq_to_pdu(rq);
 }
 

drivers/block/nbd.c

@@ -444,9 +444,7 @@ static int nbd_thread_recv(struct nbd_device *nbd)
 	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
 
 	if (signal_pending(current)) {
-		siginfo_t info;
+		ret = kernel_dequeue_signal(NULL);
-
-		ret = dequeue_signal_lock(current, &current->blocked, &info);
 		dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
 			 task_pid_nr(current), current->comm, ret);
 		mutex_lock(&nbd->tx_lock);
@@ -560,11 +558,8 @@ static int nbd_thread_send(void *data)
 					 !list_empty(&nbd->waiting_queue));
 
 		if (signal_pending(current)) {
-			siginfo_t info;
+			int ret = kernel_dequeue_signal(NULL);
-			int ret;
 
-			ret = dequeue_signal_lock(current, &current->blocked,
-						  &info);
 			dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
 				 task_pid_nr(current), current->comm, ret);
 			mutex_lock(&nbd->tx_lock);
@@ -592,10 +587,8 @@ static int nbd_thread_send(void *data)
 	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
 
 	/* Clear maybe pending signals */
-	if (signal_pending(current)) {
+	if (signal_pending(current))
-		siginfo_t info;
+		kernel_dequeue_signal(NULL);
-		dequeue_signal_lock(current, &current->blocked, &info);
-	}
 
 	return 0;
 }

drivers/block/osdblk.c

@@ -271,7 +271,7 @@ static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
 			goto err_out;
 
 		tmp->bi_bdev = NULL;
-		gfpmask &= ~__GFP_WAIT;
+		gfpmask &= ~__GFP_DIRECT_RECLAIM;
 		tmp->bi_next = NULL;
 
 		if (!new_chain)

drivers/block/paride/pd.c

@@ -723,7 +723,7 @@ static int pd_special_command(struct pd_unit *disk,
 	struct request *rq;
 	int err = 0;
 
-	rq = blk_get_request(disk->gd->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(disk->gd->queue, READ, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 

drivers/block/pktcdvd.c

@@ -704,14 +704,14 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 	int ret = 0;
 
 	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
-			     WRITE : READ, __GFP_WAIT);
+			     WRITE : READ, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	blk_rq_set_block_pc(rq);
 
 	if (cgc->buflen) {
 		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
-				      __GFP_WAIT);
+				      __GFP_RECLAIM);
 		if (ret)
 			goto out;
 	}

drivers/block/zram/zram_drv.c

@@ -106,7 +106,7 @@ static void zram_set_obj_size(struct zram_meta *meta,
 	meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
 }
 
-static inline int is_partial_io(struct bio_vec *bvec)
+static inline bool is_partial_io(struct bio_vec *bvec)
 {
 	return bvec->bv_len != PAGE_SIZE;
 }
@@ -114,25 +114,25 @@ static inline int is_partial_io(struct bio_vec *bvec)
 /*
  * Check if request is within bounds and aligned on zram logical blocks.
  */
-static inline int valid_io_request(struct zram *zram,
+static inline bool valid_io_request(struct zram *zram,
 		sector_t start, unsigned int size)
 {
 	u64 end, bound;
 
 	/* unaligned request */
 	if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
-		return 0;
+		return false;
 	if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
-		return 0;
+		return false;
 
 	end = start + (size >> SECTOR_SHIFT);
 	bound = zram->disksize >> SECTOR_SHIFT;
 	/* out of range range */
 	if (unlikely(start >= bound || end > bound || start > end))
-		return 0;
+		return false;
 
 	/* I/O request is valid */
-	return 1;
+	return true;
 }
 
 static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -157,7 +157,7 @@ static inline void update_used_max(struct zram *zram,
 	} while (old_max != cur_max);
 }
 
-static int page_zero_filled(void *ptr)
+static bool page_zero_filled(void *ptr)
 {
 	unsigned int pos;
 	unsigned long *page;
@@ -166,10 +166,10 @@ static int page_zero_filled(void *ptr)
 
 	for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
 		if (page[pos])
-			return 0;
+			return false;
 	}
 
-	return 1;
+	return true;
 }
 
 static void handle_zero_page(struct bio_vec *bvec)
@@ -365,6 +365,9 @@ static ssize_t comp_algorithm_store(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 	size_t sz;
 
+	if (!zcomp_available_algorithm(buf))
+		return -EINVAL;
+
 	down_write(&zram->init_lock);
 	if (init_done(zram)) {
 		up_write(&zram->init_lock);
@@ -378,9 +381,6 @@ static ssize_t comp_algorithm_store(struct device *dev,
 	if (sz > 0 && zram->compressor[sz - 1] == '\n')
 		zram->compressor[sz - 1] = 0x00;
 
-	if (!zcomp_available_algorithm(zram->compressor))
-		len = -EINVAL;
-
 	up_write(&zram->init_lock);
 	return len;
 }
@@ -726,14 +726,14 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	}
 
 	alloced_pages = zs_get_total_pages(meta->mem_pool);
+	update_used_max(zram, alloced_pages);
+
 	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
 		zs_free(meta->mem_pool, handle);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	update_used_max(zram, alloced_pages);
-
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
 
 	if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {

drivers/connector/connector.c

@@ -124,7 +124,8 @@ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group,
 	if (group)
 		return netlink_broadcast(dev->nls, skb, portid, group,
 					 gfp_mask);
-	return netlink_unicast(dev->nls, skb, portid, !(gfp_mask&__GFP_WAIT));
+	return netlink_unicast(dev->nls, skb, portid,
+			!gfpflags_allow_blocking(gfp_mask));
 }
 EXPORT_SYMBOL_GPL(cn_netlink_send_mult);
 

drivers/firewire/core-cdev.c

@@ -486,7 +486,7 @@ static int ioctl_get_info(struct client *client, union ioctl_arg *arg)
 static int add_client_resource(struct client *client,
 			       struct client_resource *resource, gfp_t gfp_mask)
 {
-	bool preload = !!(gfp_mask & __GFP_WAIT);
+	bool preload = gfpflags_allow_blocking(gfp_mask);
 	unsigned long flags;
 	int ret;
 

drivers/gpu/drm/drm_gem.c

@@ -491,7 +491,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj)
 		 * __GFP_DMA32 to be set in mapping_gfp_mask(inode->i_mapping)
 		 * so shmem can relocate pages during swapin if required.
 		 */
-		BUG_ON((mapping_gfp_mask(mapping) & __GFP_DMA32) &&
+		BUG_ON(mapping_gfp_constraint(mapping, __GFP_DMA32) &&
 				(page_to_pfn(p) >= 0x00100000UL));
 	}
 

drivers/gpu/drm/drm_lock.c

@@ -38,8 +38,6 @@
 #include "drm_legacy.h"
 #include "drm_internal.h"
 
-static int drm_notifier(void *priv);
-
 static int drm_lock_take(struct drm_lock_data *lock_data, unsigned int context);
 
 /**
@@ -118,14 +116,8 @@ int drm_legacy_lock(struct drm_device *dev, void *data,
 	 * really probably not the correct answer but lets us debug xkb
  	 * xserver for now */
 	if (!file_priv->is_master) {
-		sigemptyset(&dev->sigmask);
-		sigaddset(&dev->sigmask, SIGSTOP);
-		sigaddset(&dev->sigmask, SIGTSTP);
-		sigaddset(&dev->sigmask, SIGTTIN);
-		sigaddset(&dev->sigmask, SIGTTOU);
 		dev->sigdata.context = lock->context;
 		dev->sigdata.lock = master->lock.hw_lock;
-		block_all_signals(drm_notifier, dev, &dev->sigmask);
 	}
 
 	if (dev->driver->dma_quiescent && (lock->flags & _DRM_LOCK_QUIESCENT))
@@ -169,7 +161,6 @@ int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_
 		/* FIXME: Should really bail out here. */
 	}
 
-	unblock_all_signals();
 	return 0;
 }
 
@@ -287,38 +278,6 @@ int drm_legacy_lock_free(struct drm_lock_data *lock_data, unsigned int context)
 	return 0;
 }
 
-/**
- * If we get here, it means that the process has called DRM_IOCTL_LOCK
- * without calling DRM_IOCTL_UNLOCK.
- *
- * If the lock is not held, then let the signal proceed as usual.  If the lock
- * is held, then set the contended flag and keep the signal blocked.
- *
- * \param priv pointer to a drm_device structure.
- * \return one if the signal should be delivered normally, or zero if the
- * signal should be blocked.
- */
-static int drm_notifier(void *priv)
-{
-	struct drm_device *dev = priv;
-	struct drm_hw_lock *lock = dev->sigdata.lock;
-	unsigned int old, new, prev;
-
-	/* Allow signal delivery if lock isn't held */
-	if (!lock || !_DRM_LOCK_IS_HELD(lock->lock)
-	    || _DRM_LOCKING_CONTEXT(lock->lock) != dev->sigdata.context)
-		return 1;
-
-	/* Otherwise, set flag to force call to
-	   drmUnlock */
-	do {
-		old = lock->lock;
-		new = old | _DRM_LOCK_CONT;
-		prev = cmpxchg(&lock->lock, old, new);
-	} while (prev != old);
-	return 0;
-}
-
 /**
  * This function returns immediately and takes the hw lock
  * with the kernel context if it is free, otherwise it gets the highest priority when and if

drivers/gpu/drm/i915/i915_gem.c

@@ -2214,9 +2214,8 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
 	 * Fail silently without starting the shrinker
 	 */
 	mapping = file_inode(obj->base.filp)->i_mapping;
-	gfp = mapping_gfp_mask(mapping);
+	gfp = mapping_gfp_constraint(mapping, ~(__GFP_IO | __GFP_RECLAIM));
-	gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
+	gfp |= __GFP_NORETRY | __GFP_NOWARN;
-	gfp &= ~(__GFP_IO | __GFP_WAIT);
 	sg = st->sgl;
 	st->nents = 0;
 	for (i = 0; i < page_count; i++) {

drivers/ide/ide-atapi.c

@@ -92,7 +92,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	struct request *rq;
 	int error;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = (char *)pc;
 

drivers/ide/ide-cd.c

@@ -441,7 +441,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		struct request *rq;
 		int error;
 
-		rq = blk_get_request(drive->queue, write, __GFP_WAIT);
+		rq = blk_get_request(drive->queue, write, __GFP_RECLAIM);
 
 		memcpy(rq->cmd, cmd, BLK_MAX_CDB);
 		rq->cmd_type = REQ_TYPE_ATA_PC;

drivers/ide/ide-cd_ioctl.c

@@ -303,7 +303,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	struct request *rq;
 	int ret;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_flags = REQ_QUIET;
 	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);

drivers/ide/ide-devsets.c

@@ -165,7 +165,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	if (!(setting->flags & DS_SYNC))
 		return setting->set(drive, arg);
 
-	rq = blk_get_request(q, READ, __GFP_WAIT);
+	rq = blk_get_request(q, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_len = 5;
 	rq->cmd[0] = REQ_DEVSET_EXEC;

drivers/ide/ide-disk.c

@@ -477,7 +477,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
 	if (drive->special_flags & IDE_SFLAG_SET_MULTMODE)
 		return -EBUSY;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
 
 	drive->mult_req = arg;

drivers/ide/ide-ioctls.c

@@ -125,7 +125,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 	if (NULL == (void *) arg) {
 		struct request *rq;
 
-		rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+		rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 		rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
 		err = blk_execute_rq(drive->queue, NULL, rq, 0);
 		blk_put_request(rq);
@@ -221,7 +221,7 @@ static int generic_drive_reset(ide_drive_t *drive)
 	struct request *rq;
 	int ret = 0;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd_len = 1;
 	rq->cmd[0] = REQ_DRIVE_RESET;

drivers/ide/ide-park.c

@@ -31,7 +31,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	}
 	spin_unlock_irq(&hwif->lock);
 
-	rq = blk_get_request(q, READ, __GFP_WAIT);
+	rq = blk_get_request(q, READ, __GFP_RECLAIM);
 	rq->cmd[0] = REQ_PARK_HEADS;
 	rq->cmd_len = 1;
 	rq->cmd_type = REQ_TYPE_DRV_PRIV;

drivers/ide/ide-pm.c

@@ -18,7 +18,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
@@ -88,7 +88,7 @@ int generic_ide_resume(struct device *dev)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_ATA_PM_RESUME;
 	rq->cmd_flags |= REQ_PREEMPT;
 	rq->special = &rqpm;

drivers/ide/ide-tape.c

@@ -852,7 +852,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
 	BUG_ON(size < 0 || size % tape->blk_size);
 
-	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
@@ -860,7 +860,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 
 	if (size) {
 		ret = blk_rq_map_kern(drive->queue, rq, tape->buf, size,
-				      __GFP_WAIT);
+				      __GFP_RECLAIM);
 		if (ret)
 			goto out_put;
 	}

drivers/ide/ide-taskfile.c

@@ -430,7 +430,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 	int error;
 	int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE;
 
-	rq = blk_get_request(drive->queue, rw, __GFP_WAIT);
+	rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM);
 	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
 
 	/*
@@ -441,7 +441,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 	 */
 	if (nsect) {
 		error = blk_rq_map_kern(drive->queue, rq, buf,
-					nsect * SECTOR_SIZE, __GFP_WAIT);
+					nsect * SECTOR_SIZE, __GFP_RECLAIM);
 		if (error)
 			goto put_req;
 	}

drivers/infiniband/core/sa_query.c

@@ -1086,7 +1086,7 @@ static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent)
 
 static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 {
-	bool preload = !!(gfp_mask & __GFP_WAIT);
+	bool preload = gfpflags_allow_blocking(gfp_mask);
 	unsigned long flags;
 	int ret, id;
 

drivers/infiniband/hw/qib/qib_init.c

@@ -1680,7 +1680,7 @@ int qib_setup_eagerbufs(struct qib_ctxtdata *rcd)
 	 * heavy filesystem activity makes these fail, and we can
 	 * use compound pages.
 	 */
-	gfp_flags = __GFP_WAIT | __GFP_IO | __GFP_COMP;
+	gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP;
 
 	egrcnt = rcd->rcvegrcnt;
 	egroff = rcd->rcvegr_tid_base;

drivers/iommu/amd_iommu.c

@@ -2668,7 +2668,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 
 	page = alloc_pages(flag | __GFP_NOWARN,  get_order(size));
 	if (!page) {
-		if (!(flag & __GFP_WAIT))
+		if (!gfpflags_allow_blocking(flag))
 			return NULL;
 
 		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,

drivers/iommu/intel-iommu.c

@@ -3647,7 +3647,7 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
 			flags |= GFP_DMA32;
 	}
 
-	if (flags & __GFP_WAIT) {
+	if (gfpflags_allow_blocking(flags)) {
 		unsigned int count = size >> PAGE_SHIFT;
 
 		page = dma_alloc_from_contiguous(dev, count, order);

drivers/md/dm-crypt.c

@@ -994,7 +994,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
 	struct bio_vec *bvec;
 
 retry:
-	if (unlikely(gfp_mask & __GFP_WAIT))
+	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
 		mutex_lock(&cc->bio_alloc_lock);
 
 	clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
@@ -1010,7 +1010,7 @@ retry:
 		if (!page) {
 			crypt_free_buffer_pages(cc, clone);
 			bio_put(clone);
-			gfp_mask |= __GFP_WAIT;
+			gfp_mask |= __GFP_DIRECT_RECLAIM;
 			goto retry;
 		}
 
@@ -1027,7 +1027,7 @@ retry:
 	}
 
 return_clone:
-	if (unlikely(gfp_mask & __GFP_WAIT))
+	if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
 		mutex_unlock(&cc->bio_alloc_lock);
 
 	return clone;

drivers/md/dm-kcopyd.c

@@ -244,7 +244,7 @@ static int kcopyd_get_pages(struct dm_kcopyd_client *kc,
 	*pages = NULL;
 
 	do {
-		pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY);
+		pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY | __GFP_KSWAPD_RECLAIM);
 		if (unlikely(!pl)) {
 			/* Use reserved pages */
 			pl = kc->pages;

drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c

@@ -1297,7 +1297,7 @@ static struct solo_enc_dev *solo_enc_alloc(struct solo_dev *solo_dev,
 	solo_enc->vidq.ops = &solo_enc_video_qops;
 	solo_enc->vidq.mem_ops = &vb2_dma_sg_memops;
 	solo_enc->vidq.drv_priv = solo_enc;
-	solo_enc->vidq.gfp_flags = __GFP_DMA32;
+	solo_enc->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM;
 	solo_enc->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	solo_enc->vidq.buf_struct_size = sizeof(struct solo_vb2_buf);
 	solo_enc->vidq.lock = &solo_enc->lock;

drivers/media/pci/solo6x10/solo6x10-v4l2.c

@@ -678,7 +678,7 @@ int solo_v4l2_init(struct solo_dev *solo_dev, unsigned nr)
 	solo_dev->vidq.mem_ops = &vb2_dma_contig_memops;
 	solo_dev->vidq.drv_priv = solo_dev;
 	solo_dev->vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	solo_dev->vidq.gfp_flags = __GFP_DMA32;
+	solo_dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM;
 	solo_dev->vidq.buf_struct_size = sizeof(struct solo_vb2_buf);
 	solo_dev->vidq.lock = &solo_dev->lock;
 	ret = vb2_queue_init(&solo_dev->vidq);

drivers/media/pci/tw68/tw68-video.c

@@ -979,7 +979,7 @@ int tw68_video_init2(struct tw68_dev *dev, int video_nr)
 	dev->vidq.ops = &tw68_video_qops;
 	dev->vidq.mem_ops = &vb2_dma_sg_memops;
 	dev->vidq.drv_priv = dev;
-	dev->vidq.gfp_flags = __GFP_DMA32;
+	dev->vidq.gfp_flags = __GFP_DMA32 | __GFP_KSWAPD_RECLAIM;
 	dev->vidq.buf_struct_size = sizeof(struct tw68_buf);
 	dev->vidq.lock = &dev->lock;
 	dev->vidq.min_buffers_needed = 2;

drivers/misc/vmw_balloon.c

@@ -75,7 +75,7 @@ MODULE_LICENSE("GPL");
 
 /*
  * Use __GFP_HIGHMEM to allow pages from HIGHMEM zone. We don't
- * allow wait (__GFP_WAIT) for NOSLEEP page allocations. Use
+ * allow wait (__GFP_RECLAIM) for NOSLEEP page allocations. Use
  * __GFP_NOWARN, to suppress page allocation failure warnings.
  */
 #define VMW_PAGE_ALLOC_NOSLEEP		(__GFP_HIGHMEM|__GFP_NOWARN)

drivers/mtd/mtdcore.c

@@ -1216,8 +1216,7 @@ EXPORT_SYMBOL_GPL(mtd_writev);
  */
 void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
 {
-	gfp_t flags = __GFP_NOWARN | __GFP_WAIT |
+	gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY;
-		       __GFP_NORETRY | __GFP_NO_KSWAPD;
 	size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
 	void *kbuf;
 

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -691,7 +691,7 @@ static void *bnx2x_frag_alloc(const struct bnx2x_fastpath *fp, gfp_t gfp_mask)
 {
 	if (fp->rx_frag_size) {
 		/* GFP_KERNEL allocations are used only during initialization */
-		if (unlikely(gfp_mask & __GFP_WAIT))
+		if (unlikely(gfpflags_allow_blocking(gfp_mask)))
 			return (void *)__get_free_page(gfp_mask);
 
 		return netdev_alloc_frag(fp->rx_frag_size);

drivers/nvme/host/pci.c

@@ -1025,11 +1025,13 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
 	req->special = (void *)0;
 
 	if (buffer && bufflen) {
-		ret = blk_rq_map_kern(q, req, buffer, bufflen, __GFP_WAIT);
+		ret = blk_rq_map_kern(q, req, buffer, bufflen,
+				      __GFP_DIRECT_RECLAIM);
 		if (ret)
 			goto out;
 	} else if (ubuffer && bufflen) {
-		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, __GFP_WAIT);
+		ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen,
+				      __GFP_DIRECT_RECLAIM);
 		if (ret)
 			goto out;
 		bio = req->bio;

drivers/scsi/scsi_error.c

@@ -1970,7 +1970,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 	struct request *req;
 
 	/*
-	 * blk_get_request with GFP_KERNEL (__GFP_WAIT) sleeps until a
+	 * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a
 	 * request becomes available
 	 */
 	req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL);

drivers/scsi/scsi_lib.c

@@ -222,13 +222,13 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	int write = (data_direction == DMA_TO_DEVICE);
 	int ret = DRIVER_ERROR << 24;
 
-	req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);
+	req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM);
 	if (IS_ERR(req))
 		return ret;
 	blk_rq_set_block_pc(req);
 
 	if (bufflen &&	blk_rq_map_kern(sdev->request_queue, req,
-					buffer, bufflen, __GFP_WAIT))
+					buffer, bufflen, __GFP_RECLAIM))
 		goto out;
 
 	req->cmd_len = COMMAND_SIZE(cmd[0]);

drivers/staging/android/ion/ion_system_heap.c

@@ -27,7 +27,7 @@
 #include "ion_priv.h"
 
 static gfp_t high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN |
-				     __GFP_NORETRY) & ~__GFP_WAIT;
+				     __GFP_NORETRY) & ~__GFP_DIRECT_RECLAIM;
 static gfp_t low_order_gfp_flags  = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN);
 static const unsigned int orders[] = {8, 4, 0};
 static const int num_orders = ARRAY_SIZE(orders);

drivers/staging/lustre/include/linux/libcfs/libcfs_private.h

@@ -95,7 +95,7 @@ do {								    \
 do {									    \
 	LASSERT(!in_interrupt() ||					    \
 		((size) <= LIBCFS_VMALLOC_SIZE &&			    \
-		 ((mask) & __GFP_WAIT) == 0));				    \
+		 !gfpflags_allow_blocking(mask)));			    \
 } while (0)
 
 #define LIBCFS_ALLOC_POST(ptr, size)					    \

drivers/staging/lustre/lnet/lnet/router.c

@@ -1245,7 +1245,7 @@ lnet_new_rtrbuf(lnet_rtrbufpool_t *rbp, int cpt)
 	for (i = 0; i < npages; i++) {
 		page = alloc_pages_node(
 				cfs_cpt_spread_node(lnet_cpt_table(), cpt),
-				__GFP_ZERO | GFP_IOFS, 0);
+				GFP_KERNEL | __GFP_ZERO, 0);
 		if (page == NULL) {
 			while (--i >= 0)
 				__free_page(rb->rb_kiov[i].kiov_page);

drivers/staging/lustre/lnet/selftest/conrpc.c

@@ -860,7 +860,7 @@ lstcon_testrpc_prep(lstcon_node_t *nd, int transop, unsigned feats,
 			bulk->bk_iovs[i].kiov_offset = 0;
 			bulk->bk_iovs[i].kiov_len    = len;
 			bulk->bk_iovs[i].kiov_page   =
-				alloc_page(GFP_IOFS);
+				alloc_page(GFP_KERNEL);
 
 			if (bulk->bk_iovs[i].kiov_page == NULL) {
 				lstcon_rpc_put(*crpc);

drivers/staging/lustre/lnet/selftest/rpc.c

@@ -146,7 +146,7 @@ srpc_alloc_bulk(int cpt, unsigned bulk_npg, unsigned bulk_len, int sink)
 		int nob;
 
 		pg = alloc_pages_node(cfs_cpt_spread_node(lnet_cpt_table(), cpt),
-				      GFP_IOFS, 0);
+				      GFP_KERNEL, 0);
 		if (pg == NULL) {
 			CERROR("Can't allocate page %d of %d\n", i, bulk_npg);
 			srpc_free_bulk(bk);

drivers/staging/lustre/lustre/libcfs/module.c

@@ -319,7 +319,7 @@ static int libcfs_ioctl(struct cfs_psdev_file *pfile, unsigned long cmd, void *a
 	struct libcfs_ioctl_data *data;
 	int err = 0;
 
-	LIBCFS_ALLOC_GFP(buf, 1024, GFP_IOFS);
+	LIBCFS_ALLOC_GFP(buf, 1024, GFP_KERNEL);
 	if (buf == NULL)
 		return -ENOMEM;
 

drivers/staging/lustre/lustre/libcfs/tracefile.c

@@ -810,7 +810,7 @@ int cfs_trace_allocate_string_buffer(char **str, int nob)
 	if (nob > 2 * PAGE_CACHE_SIZE)	    /* string must be "sensible" */
 		return -EINVAL;
 
-	*str = kmalloc(nob, GFP_IOFS | __GFP_ZERO);
+	*str = kmalloc(nob, GFP_KERNEL | __GFP_ZERO);
 	if (*str == NULL)
 		return -ENOMEM;
 

drivers/staging/lustre/lustre/llite/remote_perm.c

@@ -82,7 +82,7 @@ static struct hlist_head *alloc_rmtperm_hash(void)
 	struct hlist_head *hash;
 	int i;
 
-	hash = kmem_cache_alloc(ll_rmtperm_hash_cachep, GFP_IOFS | __GFP_ZERO);
+	hash = kmem_cache_alloc(ll_rmtperm_hash_cachep, GFP_NOFS | __GFP_ZERO);
 	if (!hash)
 		return NULL;
 

drivers/staging/lustre/lustre/mgc/mgc_request.c

@@ -1112,7 +1112,7 @@ static int mgc_apply_recover_logs(struct obd_device *mgc,
 	LASSERT(cfg->cfg_instance != NULL);
 	LASSERT(cfg->cfg_sb == cfg->cfg_instance);
 
-	inst = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
+	inst = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
 	if (!inst)
 		return -ENOMEM;
 
@@ -1308,14 +1308,14 @@ static int mgc_process_recover_log(struct obd_device *obd,
 	if (cfg->cfg_last_idx == 0) /* the first time */
 		nrpages = CONFIG_READ_NRPAGES_INIT;
 
-	pages = kcalloc(nrpages, sizeof(*pages), GFP_NOFS);
+	pages = kcalloc(nrpages, sizeof(*pages), GFP_KERNEL);
 	if (pages == NULL) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
 	for (i = 0; i < nrpages; i++) {
-		pages[i] = alloc_page(GFP_IOFS);
+		pages[i] = alloc_page(GFP_KERNEL);
 		if (pages[i] == NULL) {
 			rc = -ENOMEM;
 			goto out;
@@ -1466,7 +1466,7 @@ static int mgc_process_cfg_log(struct obd_device *mgc,
 	if (cld->cld_cfg.cfg_sb)
 		lsi = s2lsi(cld->cld_cfg.cfg_sb);
 
-	env = kzalloc(sizeof(*env), GFP_NOFS);
+	env = kzalloc(sizeof(*env), GFP_KERNEL);
 	if (!env)
 		return -ENOMEM;
 

drivers/staging/lustre/lustre/obdecho/echo_client.c

@@ -1562,7 +1562,7 @@ static int echo_client_kbrw(struct echo_device *ed, int rw, struct obdo *oa,
 		  (oa->o_valid & OBD_MD_FLFLAGS) != 0 &&
 		  (oa->o_flags & OBD_FL_DEBUG_CHECK) != 0);
 
-	gfp_mask = ((ostid_id(&oa->o_oi) & 2) == 0) ? GFP_IOFS : GFP_HIGHUSER;
+	gfp_mask = ((ostid_id(&oa->o_oi) & 2) == 0) ? GFP_KERNEL : GFP_HIGHUSER;
 
 	LASSERT(rw == OBD_BRW_WRITE || rw == OBD_BRW_READ);
 	LASSERT(lsm != NULL);

drivers/staging/lustre/lustre/osc/osc_cache.c

@@ -346,7 +346,7 @@ static struct osc_extent *osc_extent_alloc(struct osc_object *obj)
 {
 	struct osc_extent *ext;
 
-	ext = kmem_cache_alloc(osc_extent_kmem, GFP_IOFS | __GFP_ZERO);
+	ext = kmem_cache_alloc(osc_extent_kmem, GFP_NOFS | __GFP_ZERO);
 	if (ext == NULL)
 		return NULL;
 

drivers/staging/rdma/hfi1/init.c

@@ -1560,7 +1560,7 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd)
 	 * heavy filesystem activity makes these fail, and we can
 	 * use compound pages.
 	 */
-	gfp_flags = __GFP_WAIT | __GFP_IO | __GFP_COMP;
+	gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP;
 
 	/*
 	 * The minimum size of the eager buffers is a groups of MTU-sized

drivers/staging/rdma/ipath/ipath_file_ops.c

@@ -905,7 +905,7 @@ static int ipath_create_user_egr(struct ipath_portdata *pd)
 	 * heavy filesystem activity makes these fail, and we can
 	 * use compound pages.
 	 */
-	gfp_flags = __GFP_WAIT | __GFP_IO | __GFP_COMP;
+	gfp_flags = __GFP_RECLAIM | __GFP_IO | __GFP_COMP;
 
 	egrcnt = dd->ipath_rcvegrcnt;
 	/* TID number offset for this port */

drivers/usb/gadget/function/f_mass_storage.c

@@ -2345,7 +2345,6 @@ static void fsg_disable(struct usb_function *f)
 
 static void handle_exception(struct fsg_common *common)
 {
-	siginfo_t		info;
 	int			i;
 	struct fsg_buffhd	*bh;
 	enum fsg_state		old_state;
@@ -2357,8 +2356,7 @@ static void handle_exception(struct fsg_common *common)
 	 * into a high-priority EXIT exception.
 	 */
 	for (;;) {
-		int sig =
+		int sig = kernel_dequeue_signal(NULL);
-			dequeue_signal_lock(current, &current->blocked, &info);
 		if (!sig)
 			break;
 		if (sig != SIGUSR1) {

drivers/usb/host/u132-hcd.c

@@ -2244,7 +2244,7 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
 {
 	struct u132 *u132 = hcd_to_u132(hcd);
 	if (irqs_disabled()) {
-		if (__GFP_WAIT & mem_flags) {
+		if (gfpflags_allow_blocking(mem_flags)) {
 			printk(KERN_ERR "invalid context for function that might sleep\n");
 			return -EINVAL;
 		}

drivers/video/fbdev/vermilion/vermilion.c

@@ -99,7 +99,7 @@ static int vmlfb_alloc_vram_area(struct vram_area *va, unsigned max_order,
 		 * below the first 16MB.
 		 */
 
-		flags = __GFP_DMA | __GFP_HIGH;
+		flags = __GFP_DMA | __GFP_HIGH | __GFP_KSWAPD_RECLAIM;
 		va->logical =
 			 __get_free_pages(flags, --max_order);
 	} while (va->logical == 0 && max_order > min_order);

fs/btrfs/compression.c

@@ -482,13 +482,12 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			goto next;
 		}
 
-		page = __page_cache_alloc(mapping_gfp_mask(mapping) &
+		page = __page_cache_alloc(mapping_gfp_constraint(mapping,
-								~__GFP_FS);
+								 ~__GFP_FS));
 		if (!page)
 			break;
 
-		if (add_to_page_cache_lru(page, mapping, pg_index,
+		if (add_to_page_cache_lru(page, mapping, pg_index, GFP_NOFS)) {
-								GFP_NOFS)) {
 			page_cache_release(page);
 			goto next;
 		}

fs/btrfs/ctree.h

@@ -3367,7 +3367,7 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
 
 static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 {
-	return mapping_gfp_mask(mapping) & ~__GFP_FS;
+	return mapping_gfp_constraint(mapping, ~__GFP_FS);
 }
 
 /* extent-tree.c */

fs/btrfs/disk-io.c

@@ -2575,7 +2575,7 @@ int open_ctree(struct super_block *sb,
 	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 	fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
 	/* readahead state */
-	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
+	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 	spin_lock_init(&fs_info->reada_lock);
 
 	fs_info->thread_pool_size = min_t(unsigned long,

fs/btrfs/extent_io.c

@@ -616,7 +616,7 @@ static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	if (bits & (EXTENT_IOBITS | EXTENT_BOUNDARY))
 		clear = 1;
 again:
-	if (!prealloc && (mask & __GFP_WAIT)) {
+	if (!prealloc && gfpflags_allow_blocking(mask)) {
 		/*
 		 * Don't care for allocation failure here because we might end
 		 * up not needing the pre-allocated extent state at all, which
@@ -741,7 +741,7 @@ search_again:
 	if (start > end)
 		goto out;
 	spin_unlock(&tree->lock);
-	if (mask & __GFP_WAIT)
+	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	goto again;
 }
@@ -874,7 +874,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 
 	bits |= EXTENT_FIRST_DELALLOC;
 again:
-	if (!prealloc && (mask & __GFP_WAIT)) {
+	if (!prealloc && gfpflags_allow_blocking(mask)) {
 		prealloc = alloc_extent_state(mask);
 		BUG_ON(!prealloc);
 	}
@@ -1052,7 +1052,7 @@ search_again:
 	if (start > end)
 		goto out;
 	spin_unlock(&tree->lock);
-	if (mask & __GFP_WAIT)
+	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	goto again;
 }
@@ -1100,7 +1100,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	btrfs_debug_check_extent_io_range(tree, start, end);
 
 again:
-	if (!prealloc && (mask & __GFP_WAIT)) {
+	if (!prealloc && gfpflags_allow_blocking(mask)) {
 		/*
 		 * Best effort, don't worry if extent state allocation fails
 		 * here for the first iteration. We might have a cached state
@@ -1278,7 +1278,7 @@ search_again:
 	if (start > end)
 		goto out;
 	spin_unlock(&tree->lock);
-	if (mask & __GFP_WAIT)
+	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	first_iteration = false;
 	goto again;
@@ -4386,7 +4386,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_CACHE_SIZE - 1;
 
-	if ((mask & __GFP_WAIT) &&
+	if (gfpflags_allow_blocking(mask) &&
 	    page->mapping->host->i_size > 16 * 1024 * 1024) {
 		u64 len;
 		while (start <= end) {

fs/btrfs/free-space-cache.c

@@ -85,8 +85,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	}
 
 	mapping_set_gfp_mask(inode->i_mapping,
-			mapping_gfp_mask(inode->i_mapping) &
+			mapping_gfp_constraint(inode->i_mapping,
-			~(__GFP_FS | __GFP_HIGHMEM));
+			~(__GFP_FS | __GFP_HIGHMEM)));
 
 	return inode;
 }

fs/btrfs/volumes.c

@@ -232,8 +232,8 @@ static struct btrfs_device *__alloc_device(void)
 	spin_lock_init(&dev->reada_lock);
 	atomic_set(&dev->reada_in_flight, 0);
 	atomic_set(&dev->dev_stats_ccnt, 0);
-	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_WAIT);
+	INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
-	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_WAIT);
+	INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 
 	return dev;
 }

fs/buffer.c

@@ -999,7 +999,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	int ret = 0;		/* Will call free_more_memory() */
 	gfp_t gfp_mask;
 
-	gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp;
+	gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp;
 
 	/*
 	 * XXX: __getblk_slow() can not really deal with failure and

fs/cachefiles/internal.h

@@ -30,7 +30,7 @@ extern unsigned cachefiles_debug;
 #define CACHEFILES_DEBUG_KLEAVE	2
 #define CACHEFILES_DEBUG_KDEBUG	4
 
-#define cachefiles_gfp (__GFP_WAIT | __GFP_NORETRY | __GFP_NOMEMALLOC)
+#define cachefiles_gfp (__GFP_RECLAIM | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
 /*
  * node records

fs/ceph/addr.c

@@ -1283,8 +1283,8 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		int ret1;
 		struct address_space *mapping = inode->i_mapping;
 		struct page *page = find_or_create_page(mapping, 0,
-						mapping_gfp_mask(mapping) &
+						mapping_gfp_constraint(mapping,
-						~__GFP_FS);
+						~__GFP_FS));
 		if (!page) {
 			ret = VM_FAULT_OOM;
 			goto out;
@@ -1428,7 +1428,8 @@ void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 		if (i_size_read(inode) == 0)
 			return;
 		page = find_or_create_page(mapping, 0,
-					   mapping_gfp_mask(mapping) & ~__GFP_FS);
+					   mapping_gfp_constraint(mapping,
+					   ~__GFP_FS));
 		if (!page)
 			return;
 		if (PageUptodate(page)) {

fs/cifs/file.c

@@ -3380,7 +3380,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	struct page *page, *tpage;
 	unsigned int expected_index;
 	int rc;
-	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping);
+	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
 
 	INIT_LIST_HEAD(tmplist);
 

fs/coredump.c

@@ -280,23 +280,24 @@ out:
 	return ispipe;
 }
 
-static int zap_process(struct task_struct *start, int exit_code)
+static int zap_process(struct task_struct *start, int exit_code, int flags)
 {
 	struct task_struct *t;
 	int nr = 0;
 
+	/* ignore all signals except SIGKILL, see prepare_signal() */
+	start->signal->flags = SIGNAL_GROUP_COREDUMP | flags;
 	start->signal->group_exit_code = exit_code;
 	start->signal->group_stop_count = 0;
 
-	t = start;
+	for_each_thread(start, t) {
-	do {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
 		if (t != current && t->mm) {
 			sigaddset(&t->pending.signal, SIGKILL);
 			signal_wake_up(t, 1);
 			nr++;
 		}
-	} while_each_thread(start, t);
+	}
 
 	return nr;
 }
@@ -311,10 +312,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	spin_lock_irq(&tsk->sighand->siglock);
 	if (!signal_group_exit(tsk->signal)) {
 		mm->core_state = core_state;
-		nr = zap_process(tsk, exit_code);
 		tsk->signal->group_exit_task = tsk;
-		/* ignore all signals except SIGKILL, see prepare_signal() */
+		nr = zap_process(tsk, exit_code, 0);
-		tsk->signal->flags = SIGNAL_GROUP_COREDUMP;
 		clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
 	}
 	spin_unlock_irq(&tsk->sighand->siglock);
@@ -360,18 +359,18 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 			continue;
 		if (g->flags & PF_KTHREAD)
 			continue;
-		p = g;
+
-		do {
+		for_each_thread(g, p) {
-			if (p->mm) {
+			if (unlikely(!p->mm))
+				continue;
 			if (unlikely(p->mm == mm)) {
 				lock_task_sighand(p, &flags);
-					nr += zap_process(p, exit_code);
+				nr += zap_process(p, exit_code,
-					p->signal->flags = SIGNAL_GROUP_EXIT;
+							SIGNAL_GROUP_EXIT);
 				unlock_task_sighand(p, &flags);
 			}
 			break;
 		}
-		} while_each_thread(g, p);
 	}
 	rcu_read_unlock();
 done:

fs/direct-io.c

@@ -361,7 +361,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 
 	/*
 	 * bio_alloc() is guaranteed to return a bio when called with
-	 * __GFP_WAIT and we request a valid number of vectors.
+	 * __GFP_RECLAIM and we request a valid number of vectors.
 	 */
 	bio = bio_alloc(GFP_KERNEL, nr_vecs);
 

fs/ext4/inode.c

@@ -3386,7 +3386,7 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 	int err = 0;
 
 	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
-				   mapping_gfp_mask(mapping) & ~__GFP_FS);
+				   mapping_gfp_constraint(mapping, ~__GFP_FS));
 	if (!page)
 		return -ENOMEM;
 

fs/ext4/readpage.c

@@ -166,7 +166,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping, page->index,
-					GFP_KERNEL & mapping_gfp_mask(mapping)))
+				  mapping_gfp_constraint(mapping, GFP_KERNEL)))
 				goto next_page;
 		}
 

fs/ext4/super.c

@@ -1061,7 +1061,7 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page,
 		return 0;
 	if (journal)
 		return jbd2_journal_try_to_free_buffers(journal, page,
-							wait & ~__GFP_WAIT);
+						wait & ~__GFP_DIRECT_RECLAIM);
 	return try_to_free_buffers(page);
 }
 

fs/fscache/cookie.c

@@ -111,7 +111,7 @@ struct fscache_cookie *__fscache_acquire_cookie(
 
 	/* radix tree insertion won't use the preallocation pool unless it's
 	 * told it may not wait */
-	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_WAIT);
+	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 
 	switch (cookie->def->type) {
 	case FSCACHE_COOKIE_TYPE_INDEX:

fs/fscache/page.c

@@ -58,7 +58,7 @@ bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page)
 
 /*
  * decide whether a page can be released, possibly by cancelling a store to it
- * - we're allowed to sleep if __GFP_WAIT is flagged
+ * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged
  */
 bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
 				  struct page *page,
@@ -122,7 +122,7 @@ page_busy:
 	 * allocator as the work threads writing to the cache may all end up
 	 * sleeping on memory allocation, so we may need to impose a timeout
 	 * too. */
-	if (!(gfp & __GFP_WAIT) || !(gfp & __GFP_FS)) {
+	if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) {
 		fscache_stat(&fscache_n_store_vmscan_busy);
 		return false;
 	}
@@ -132,7 +132,7 @@ page_busy:
 		_debug("fscache writeout timeout page: %p{%lx}",
 			page, page->index);
 
-	gfp &= ~__GFP_WAIT;
+	gfp &= ~__GFP_DIRECT_RECLAIM;
 	goto try_again;
 }
 EXPORT_SYMBOL(__fscache_maybe_release_page);

fs/jbd2/transaction.c

@@ -1937,8 +1937,8 @@ out:
  * @journal: journal for operation
  * @page: to try and free
  * @gfp_mask: we use the mask to detect how hard should we try to release
- * buffers. If __GFP_WAIT and __GFP_FS is set, we wait for commit code to
+ * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
- * release the buffers.
+ * code to release the buffers.
  *
  *
  * For all the buffers on this page,

fs/jffs2/background.c

@@ -80,7 +80,6 @@ static int jffs2_garbage_collect_thread(void *_c)
 	siginitset(&hupmask, sigmask(SIGHUP));
 	allow_signal(SIGKILL);
 	allow_signal(SIGSTOP);
-	allow_signal(SIGCONT);
 	allow_signal(SIGHUP);
 
 	c->gc_task = current;
@@ -121,20 +120,18 @@ static int jffs2_garbage_collect_thread(void *_c)
 		/* Put_super will send a SIGKILL and then wait on the sem.
 		 */
 		while (signal_pending(current) || freezing(current)) {
-			siginfo_t info;
 			unsigned long signr;
 
 			if (try_to_freeze())
 				goto again;
 
-			signr = dequeue_signal_lock(current, &current->blocked, &info);
+			signr = kernel_dequeue_signal(NULL);
 
 			switch(signr) {
 			case SIGSTOP:
 				jffs2_dbg(1, "%s(): SIGSTOP received\n",
 					  __func__);
-				set_current_state(TASK_STOPPED);
+				kernel_signal_stop();
-				schedule();
 				break;
 
 			case SIGKILL:

fs/jffs2/wbuf.c

@@ -1264,7 +1264,7 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 	if ((c->flash_size % c->sector_size) != 0) {
 		c->flash_size = (c->flash_size / c->sector_size) * c->sector_size;
 		pr_warn("flash size adjusted to %dKiB\n", c->flash_size);
-	};
+	}
 
 	c->wbuf_ofs = 0xFFFFFFFF;
 	c->wbuf = kmalloc(c->wbuf_pagesize, GFP_KERNEL);

fs/logfs/segment.c

@@ -57,7 +57,7 @@ static struct page *get_mapping_page(struct super_block *sb, pgoff_t index,
 	filler_t *filler = super->s_devops->readpage;
 	struct page *page;
 
-	BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS);
+	BUG_ON(mapping_gfp_constraint(mapping, __GFP_FS));
 	if (use_filler)
 		page = read_cache_page(mapping, index, filler, sb);
 	else {

fs/mpage.c

@@ -361,7 +361,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(mapping);
+	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
@@ -397,7 +397,7 @@ int mpage_readpage(struct page *page, get_block_t get_block)
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	gfp_t gfp = GFP_KERNEL & mapping_gfp_mask(page->mapping);
+	gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;

fs/namei.c

@@ -4604,7 +4604,7 @@ EXPORT_SYMBOL(__page_symlink);
 int page_symlink(struct inode *inode, const char *symname, int len)
 {
 	return __page_symlink(inode, symname, len,
-			!(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
+			!mapping_gfp_constraint(inode->i_mapping, __GFP_FS));
 }
 EXPORT_SYMBOL(page_symlink);
 

fs/nfs/file.c

@@ -473,8 +473,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
 	/* Always try to initiate a 'commit' if relevant, but only
-	 * wait for it if __GFP_WAIT is set.  Even then, only wait 1
+	 * wait for it if the caller allows blocking.  Even then,
-	 * second and only if the 'bdi' is not congested.
+	 * only wait 1 second and only if the 'bdi' is not congested.
 	 * Waiting indefinitely can cause deadlocks when the NFS
 	 * server is on this machine, when a new TCP connection is
 	 * needed and in other rare cases.  There is no particular
@@ -484,7 +484,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 	if (mapping) {
 		struct nfs_server *nfss = NFS_SERVER(mapping->host);
 		nfs_commit_inode(mapping->host, 0);
-		if ((gfp & __GFP_WAIT) &&
+		if (gfpflags_allow_blocking(gfp) &&
 		    !bdi_write_congested(&nfss->backing_dev_info)) {
 			wait_on_page_bit_killable_timeout(page, PG_private,
 							  HZ);

fs/nilfs2/alloc.c

@@ -133,38 +133,38 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group)
 
 /**
  * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group
- * @inode: inode of metadata file using this allocator
- * @group: group number
  * @desc: pointer to descriptor structure for the group
+ * @lock: spin lock protecting @desc
  */
 static unsigned long
-nilfs_palloc_group_desc_nfrees(struct inode *inode, unsigned long group,
+nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc,
-			       const struct nilfs_palloc_group_desc *desc)
+			       spinlock_t *lock)
 {
 	unsigned long nfree;
 
-	spin_lock(nilfs_mdt_bgl_lock(inode, group));
+	spin_lock(lock);
 	nfree = le32_to_cpu(desc->pg_nfrees);
-	spin_unlock(nilfs_mdt_bgl_lock(inode, group));
+	spin_unlock(lock);
 	return nfree;
 }
 
 /**
  * nilfs_palloc_group_desc_add_entries - adjust count of free entries
- * @inode: inode of metadata file using this allocator
- * @group: group number
  * @desc: pointer to descriptor structure for the group
+ * @lock: spin lock protecting @desc
  * @n: delta to be added
  */
-static void
+static u32
-nilfs_palloc_group_desc_add_entries(struct inode *inode,
+nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc,
-				    unsigned long group,
+				    spinlock_t *lock, u32 n)
-				    struct nilfs_palloc_group_desc *desc,
-				    u32 n)
 {
-	spin_lock(nilfs_mdt_bgl_lock(inode, group));
+	u32 nfree;
+
+	spin_lock(lock);
 	le32_add_cpu(&desc->pg_nfrees, n);
-	spin_unlock(nilfs_mdt_bgl_lock(inode, group));
+	nfree = le32_to_cpu(desc->pg_nfrees);
+	spin_unlock(lock);
+	return nfree;
 }
 
 /**
@@ -239,6 +239,26 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff,
 	return ret;
 }
 
+/**
+ * nilfs_palloc_delete_block - delete a block on the persistent allocator file
+ * @inode: inode of metadata file using this allocator
+ * @blkoff: block offset
+ * @prev: nilfs_bh_assoc struct of the last used buffer
+ * @lock: spin lock protecting @prev
+ */
+static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff,
+				     struct nilfs_bh_assoc *prev,
+				     spinlock_t *lock)
+{
+	spin_lock(lock);
+	if (prev->bh && blkoff == prev->blkoff) {
+		brelse(prev->bh);
+		prev->bh = NULL;
+	}
+	spin_unlock(lock);
+	return nilfs_mdt_delete_block(inode, blkoff);
+}
+
 /**
  * nilfs_palloc_get_desc_block - get buffer head of a group descriptor block
  * @inode: inode of metadata file using this allocator
@@ -277,6 +297,22 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode,
 				      &cache->prev_bitmap, &cache->lock);
 }
 
+/**
+ * nilfs_palloc_delete_bitmap_block - delete a bitmap block
+ * @inode: inode of metadata file using this allocator
+ * @group: group number
+ */
+static int nilfs_palloc_delete_bitmap_block(struct inode *inode,
+					    unsigned long group)
+{
+	struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache;
+
+	return nilfs_palloc_delete_block(inode,
+					 nilfs_palloc_bitmap_blkoff(inode,
+								    group),
+					 &cache->prev_bitmap, &cache->lock);
+}
+
 /**
  * nilfs_palloc_get_entry_block - get buffer head of an entry block
  * @inode: inode of metadata file using this allocator
@@ -295,6 +331,20 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr,
 				      &cache->prev_entry, &cache->lock);
 }
 
+/**
+ * nilfs_palloc_delete_entry_block - delete an entry block
+ * @inode: inode of metadata file using this allocator
+ * @nr: serial number of the entry
+ */
+static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr)
+{
+	struct nilfs_palloc_cache *cache = NILFS_MDT(inode)->mi_palloc_cache;
+
+	return nilfs_palloc_delete_block(inode,
+					 nilfs_palloc_entry_blkoff(inode, nr),
+					 &cache->prev_entry, &cache->lock);
+}
+
 /**
  * nilfs_palloc_block_get_group_desc - get kernel address of a group descriptor
  * @inode: inode of metadata file using this allocator
@@ -332,51 +382,40 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
 
 /**
  * nilfs_palloc_find_available_slot - find available slot in a group
- * @inode: inode of metadata file using this allocator
- * @group: group number
- * @target: offset number of an entry in the group (start point)
  * @bitmap: bitmap of the group
+ * @target: offset number of an entry in the group (start point)
  * @bsize: size in bits
+ * @lock: spin lock protecting @bitmap
  */
-static int nilfs_palloc_find_available_slot(struct inode *inode,
+static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
-					    unsigned long group,
 					    unsigned long target,
-					    unsigned char *bitmap,
+					    unsigned bsize,
-					    int bsize)
+					    spinlock_t *lock)
 {
-	int curr, pos, end, i;
+	int pos, end = bsize;
 
-	if (target > 0) {
+	if (likely(target < bsize)) {
-		end = (target + BITS_PER_LONG - 1) & ~(BITS_PER_LONG - 1);
+		pos = target;
-		if (end > bsize)
+		do {
-			end = bsize;
+			pos = nilfs_find_next_zero_bit(bitmap, end, pos);
-		pos = nilfs_find_next_zero_bit(bitmap, end, target);
+			if (pos >= end)
-		if (pos < end &&
+				break;
-		    !nilfs_set_bit_atomic(
+			if (!nilfs_set_bit_atomic(lock, pos, bitmap))
-			    nilfs_mdt_bgl_lock(inode, group), pos, bitmap))
 				return pos;
-	} else
+		} while (++pos < end);
-		end = 0;
+
+		end = target;
+	}
 
-	for (i = 0, curr = end;
-	     i < bsize;
-	     i += BITS_PER_LONG, curr += BITS_PER_LONG) {
 	/* wrap around */
-		if (curr >= bsize)
+	for (pos = 0; pos < end; pos++) {
-			curr = 0;
+		pos = nilfs_find_next_zero_bit(bitmap, end, pos);
-		while (*((unsigned long *)bitmap + curr / BITS_PER_LONG)
+		if (pos >= end)
-		       != ~0UL) {
+			break;
-			end = curr + BITS_PER_LONG;
+		if (!nilfs_set_bit_atomic(lock, pos, bitmap))
-			if (end > bsize)
-				end = bsize;
-			pos = nilfs_find_next_zero_bit(bitmap, end, curr);
-			if ((pos < end) &&
-			    !nilfs_set_bit_atomic(
-				    nilfs_mdt_bgl_lock(inode, group), pos,
-				    bitmap))
 			return pos;
 	}
-	}
+
 	return -ENOSPC;
 }
 
@@ -475,15 +514,15 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 	void *desc_kaddr, *bitmap_kaddr;
 	unsigned long group, maxgroup, ngroups;
 	unsigned long group_offset, maxgroup_offset;
-	unsigned long n, entries_per_group, groups_per_desc_block;
+	unsigned long n, entries_per_group;
 	unsigned long i, j;
+	spinlock_t *lock;
 	int pos, ret;
 
 	ngroups = nilfs_palloc_groups_count(inode);
 	maxgroup = ngroups - 1;
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
 	entries_per_group = nilfs_palloc_entries_per_group(inode);
-	groups_per_desc_block = nilfs_palloc_groups_per_desc_block(inode);
 
 	for (i = 0; i < ngroups; i += n) {
 		if (group >= ngroups) {
@@ -501,8 +540,8 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 		n = nilfs_palloc_rest_groups_in_desc_block(inode, group,
 							   maxgroup);
 		for (j = 0; j < n; j++, desc++, group++) {
-			if (nilfs_palloc_group_desc_nfrees(inode, group, desc)
+			lock = nilfs_mdt_bgl_lock(inode, group);
-			    > 0) {
+			if (nilfs_palloc_group_desc_nfrees(desc, lock) > 0) {
 				ret = nilfs_palloc_get_bitmap_block(
 					inode, group, 1, &bitmap_bh);
 				if (ret < 0)
@@ -510,12 +549,12 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 				bitmap_kaddr = kmap(bitmap_bh->b_page);
 				bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
 				pos = nilfs_palloc_find_available_slot(
-					inode, group, group_offset, bitmap,
+					bitmap, group_offset,
-					entries_per_group);
+					entries_per_group, lock);
 				if (pos >= 0) {
 					/* found a free entry */
 					nilfs_palloc_group_desc_add_entries(
-						inode, group, desc, -1);
+						desc, lock, -1);
 					req->pr_entry_nr =
 						entries_per_group * group + pos;
 					kunmap(desc_bh->b_page);
@@ -573,6 +612,7 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 	unsigned long group, group_offset;
 	unsigned char *bitmap;
 	void *desc_kaddr, *bitmap_kaddr;
+	spinlock_t *lock;
 
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
 	desc_kaddr = kmap(req->pr_desc_bh->b_page);
@@ -580,13 +620,15 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
 						 req->pr_desc_bh, desc_kaddr);
 	bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page);
 	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
+	lock = nilfs_mdt_bgl_lock(inode, group);
 
-	if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group),
+	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
-				    group_offset, bitmap))
+		nilfs_warning(inode->i_sb, __func__,
-		printk(KERN_WARNING "%s: entry number %llu already freed\n",
+			      "entry number %llu already freed: ino=%lu\n",
-		       __func__, (unsigned long long)req->pr_entry_nr);
+			      (unsigned long long)req->pr_entry_nr,
+			      (unsigned long)inode->i_ino);
 	else
-		nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
+		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
 	kunmap(req->pr_bitmap_bh->b_page);
 	kunmap(req->pr_desc_bh->b_page);
@@ -611,6 +653,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 	void *desc_kaddr, *bitmap_kaddr;
 	unsigned char *bitmap;
 	unsigned long group, group_offset;
+	spinlock_t *lock;
 
 	group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
 	desc_kaddr = kmap(req->pr_desc_bh->b_page);
@@ -618,12 +661,15 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 						 req->pr_desc_bh, desc_kaddr);
 	bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page);
 	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
-	if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group),
+	lock = nilfs_mdt_bgl_lock(inode, group);
-				    group_offset, bitmap))
+
-		printk(KERN_WARNING "%s: entry number %llu already freed\n",
+	if (!nilfs_clear_bit_atomic(lock, group_offset, bitmap))
-		       __func__, (unsigned long long)req->pr_entry_nr);
+		nilfs_warning(inode->i_sb, __func__,
+			      "entry number %llu already freed: ino=%lu\n",
+			      (unsigned long long)req->pr_entry_nr,
+			      (unsigned long)inode->i_ino);
 	else
-		nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
+		nilfs_palloc_group_desc_add_entries(desc, lock, 1);
 
 	kunmap(req->pr_bitmap_bh->b_page);
 	kunmap(req->pr_desc_bh->b_page);
@@ -679,22 +725,6 @@ void nilfs_palloc_abort_free_entry(struct inode *inode,
 	req->pr_desc_bh = NULL;
 }
 
-/**
- * nilfs_palloc_group_is_in - judge if an entry is in a group
- * @inode: inode of metadata file using this allocator
- * @group: group number
- * @nr: serial number of the entry (e.g. inode number)
- */
-static int
-nilfs_palloc_group_is_in(struct inode *inode, unsigned long group, __u64 nr)
-{
-	__u64 first, last;
-
-	first = group * nilfs_palloc_entries_per_group(inode);
-	last = first + nilfs_palloc_entries_per_group(inode) - 1;
-	return (nr >= first) && (nr <= last);
-}
-
 /**
  * nilfs_palloc_freev - deallocate a set of persistent objects
  * @inode: inode of metadata file using this allocator
@@ -708,9 +738,18 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 	unsigned char *bitmap;
 	void *desc_kaddr, *bitmap_kaddr;
 	unsigned long group, group_offset;
-	int i, j, n, ret;
+	__u64 group_min_nr, last_nrs[8];
+	const unsigned long epg = nilfs_palloc_entries_per_group(inode);
+	const unsigned epb = NILFS_MDT(inode)->mi_entries_per_block;
+	unsigned entry_start, end, pos;
+	spinlock_t *lock;
+	int i, j, k, ret;
+	u32 nfree;
 
 	for (i = 0; i < nitems; i = j) {
+		int change_group = false;
+		int nempties = 0, n = 0;
+
 		group = nilfs_palloc_group(inode, entry_nrs[i], &group_offset);
 		ret = nilfs_palloc_get_desc_block(inode, group, 0, &desc_bh);
 		if (ret < 0)
@@ -721,38 +760,89 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 			brelse(desc_bh);
 			return ret;
 		}
-		desc_kaddr = kmap(desc_bh->b_page);
+
-		desc = nilfs_palloc_block_get_group_desc(
+		/* Get the first entry number of the group */
-			inode, group, desc_bh, desc_kaddr);
+		group_min_nr = (__u64)group * epg;
+
 		bitmap_kaddr = kmap(bitmap_bh->b_page);
 		bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
-		for (j = i, n = 0;
+		lock = nilfs_mdt_bgl_lock(inode, group);
-		     (j < nitems) && nilfs_palloc_group_is_in(inode, group,
+
-							      entry_nrs[j]);
+		j = i;
-		     j++) {
+		entry_start = rounddown(group_offset, epb);
-			nilfs_palloc_group(inode, entry_nrs[j], &group_offset);
+		do {
-			if (!nilfs_clear_bit_atomic(
+			if (!nilfs_clear_bit_atomic(lock, group_offset,
-				    nilfs_mdt_bgl_lock(inode, group),
+						    bitmap)) {
-				    group_offset, bitmap)) {
+				nilfs_warning(inode->i_sb, __func__,
-				printk(KERN_WARNING
+					      "entry number %llu already freed: ino=%lu\n",
-				       "%s: entry number %llu already freed\n",
+					      (unsigned long long)entry_nrs[j],
-				       __func__,
+					      (unsigned long)inode->i_ino);
-				       (unsigned long long)entry_nrs[j]);
 			} else {
 				n++;
 			}
+
+			j++;
+			if (j >= nitems || entry_nrs[j] < group_min_nr ||
+			    entry_nrs[j] >= group_min_nr + epg) {
+				change_group = true;
+			} else {
+				group_offset = entry_nrs[j] - group_min_nr;
+				if (group_offset >= entry_start &&
+				    group_offset < entry_start + epb) {
+					/* This entry is in the same block */
+					continue;
 				}
-		nilfs_palloc_group_desc_add_entries(inode, group, desc, n);
+			}
+
+			/* Test if the entry block is empty or not */
+			end = entry_start + epb;
+			pos = nilfs_find_next_bit(bitmap, end, entry_start);
+			if (pos >= end) {
+				last_nrs[nempties++] = entry_nrs[j - 1];
+				if (nempties >= ARRAY_SIZE(last_nrs))
+					break;
+			}
+
+			if (change_group)
+				break;
+
+			/* Go on to the next entry block */
+			entry_start = rounddown(group_offset, epb);
+		} while (true);
 
 		kunmap(bitmap_bh->b_page);
-		kunmap(desc_bh->b_page);
-
-		mark_buffer_dirty(desc_bh);
 		mark_buffer_dirty(bitmap_bh);
-		nilfs_mdt_mark_dirty(inode);
-
 		brelse(bitmap_bh);
+
+		for (k = 0; k < nempties; k++) {
+			ret = nilfs_palloc_delete_entry_block(inode,
+							      last_nrs[k]);
+			if (ret && ret != -ENOENT) {
+				nilfs_warning(inode->i_sb, __func__,
+					      "failed to delete block of entry %llu: ino=%lu, err=%d\n",
+					      (unsigned long long)last_nrs[k],
+					      (unsigned long)inode->i_ino, ret);
+			}
+		}
+
+		desc_kaddr = kmap_atomic(desc_bh->b_page);
+		desc = nilfs_palloc_block_get_group_desc(
+			inode, group, desc_bh, desc_kaddr);
+		nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n);
+		kunmap_atomic(desc_kaddr);
+		mark_buffer_dirty(desc_bh);
+		nilfs_mdt_mark_dirty(inode);
 		brelse(desc_bh);
+
+		if (nfree == nilfs_palloc_entries_per_group(inode)) {
+			ret = nilfs_palloc_delete_bitmap_block(inode, group);
+			if (ret && ret != -ENOENT) {
+				nilfs_warning(inode->i_sb, __func__,
+					      "failed to delete bitmap block of group %lu: ino=%lu, err=%d\n",
+					      group,
+					      (unsigned long)inode->i_ino, ret);
+			}
+		}
 	}
 	return 0;
 }

fs/nilfs2/alloc.h

@@ -77,6 +77,7 @@ int nilfs_palloc_freev(struct inode *, __u64 *, size_t);
 #define nilfs_set_bit_atomic		ext2_set_bit_atomic
 #define nilfs_clear_bit_atomic		ext2_clear_bit_atomic
 #define nilfs_find_next_zero_bit	find_next_zero_bit_le
+#define nilfs_find_next_bit		find_next_bit_le
 
 /**
  * struct nilfs_bh_assoc - block offset and buffer head association

fs/nilfs2/btree.c

@@ -919,8 +919,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree,
 			      int level, __u64 *keyp, __u64 *ptrp)
 {
 	struct nilfs_btree_node *node, *right;
-	__u64 newkey;
-	__u64 newptr;
 	int nchildren, n, move, ncblk;
 
 	node = nilfs_btree_get_nonroot_node(path, level);
@@ -942,9 +940,6 @@ static void nilfs_btree_split(struct nilfs_bmap *btree,
 	if (!buffer_dirty(path[level].bp_sib_bh))
 		mark_buffer_dirty(path[level].bp_sib_bh);
 
-	newkey = nilfs_btree_node_get_key(right, 0);
-	newptr = path[level].bp_newreq.bpr_ptr;
-
 	if (move) {
 		path[level].bp_index -= nilfs_btree_node_get_nchildren(node);
 		nilfs_btree_node_insert(right, path[level].bp_index,
@@ -1856,7 +1851,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree,
 				   __u64 key, __u64 ptr,
 				   const __u64 *keys, const __u64 *ptrs, int n)
 {
-	struct buffer_head *bh;
+	struct buffer_head *bh = NULL;
 	union nilfs_bmap_ptr_req dreq, nreq, *di, *ni;
 	struct nilfs_bmap_stats stats;
 	int ret;