diff --git a/Documentation/vm/balance b/Documentation/vm/balance
index c46e68cf93449aadb652bdce92953c53bb00ca22..964595481af683a7a9c344182ca707fd1c2a33fa 100644
--- a/Documentation/vm/balance
+++ b/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
-__GFP_IO allocations.
+Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
+well as for non __GFP_IO allocations.
-There are two reasons to be requesting non __GFP_WAIT allocations:
-the caller can not sleep (typically intr context), or does not want
-to incur cost overheads of page stealing and possible swap io for
-whatever reasons.
+The first reason why a caller may avoid reclaim is that the caller can not
+sleep due to holding a spinlock or is in interrupt context. The second may
+be that the caller is willing to fail the allocation without incurring the
+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.
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ad4eb2d26e1697fc6a16f47a8805e532e198a693..e62400e5fb99fdbf864af966e718a98decf85e29 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/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);
/*
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 7c34f7126b046abe9d61637a1716a2ae5139bfe5..c5f9a9e3d1f393daa161ce8349c820462870a942 100644
--- a/arch/arm/xen/mm.c
+++ b/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) {
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 6320361d8d4c703cf4072ba2e47fdf7884c7f779..bb4bf6a06ad6370ebf54e293b8c027367796c518 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/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);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index cd99433b8ba17597cbc9e91aba9c40eee7e05e4b..6ba014c61d62d20a078dd260103f23465a47a8cd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/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);
diff --git a/block/bio.c b/block/bio.c
index ad3f276d74bcb5a21474c49c786dee82f2f1b9f6..4f184d938942dcbbbbedbac3b330f6e4bb39a4a9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -211,7 +211,7 @@ struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
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 @@ struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
__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
- * able to allocate a bio. This is due to the mempool guarantees. To make this
- * work, callers must never allocate more than 1 bio at a time from this pool.
- * Callers that need to allocate more than 1 bio must always submit the
- * previously allocated bio for IO before attempting to allocate a new one.
- * Failure to do so can cause deadlocks under memory pressure.
+ * When @bs is not NULL, if %__GFP_DIRECT_RECLAIM is set then bio_alloc will
+ * always be able to allocate a bio. This is due to the mempool guarantees.
+ * To make this work, callers must never allocate more than 1 bio at a time
+ * from this pool. Callers that need to allocate more than 1 bio must always
+ * submit the previously allocated bio for IO before attempting to allocate
+ * 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
- * would be blocking to the rescuer workqueue before we retry
- * with the original gfp_flags.
+ * without __GFP_DIRECT_RECLAIM; if that fails, we punt those
+ * bios we would be blocking to the rescuer workqueue before
+ * 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) {
diff --git a/block/blk-core.c b/block/blk-core.c
index 89eec79658702a7e53712bc52178dae25bddcc22..9e32f0868e365b753ee721ab75fca46b13d8a414 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1206,8 +1206,8 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
* @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
- * function keeps retrying under memory pressure and fails iff @q is dead.
+ * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask,
+ * 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 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
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
- * anything but the first bio in the chain. Otherwise you risk waiting for IO
- * completion of a bio that hasn't been submitted yet, thus resulting in a
- * deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
- * of bio_alloc(), as that avoids the mempool deadlock.
+ * given to how you allocate bios. In particular, you cannot use
+ * __GFP_DIRECT_RECLAIM for anything but the first bio in the chain. Otherwise
+ * you risk waiting for IO completion of a bio that hasn't been submitted yet,
+ * thus resulting in a deadlock. Alternatively bios should be allocated using
+ * 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.
*/
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 1a27f45ec776a4e0a951a89de3185dc2ead26a42..381cb50a673c33ed86f6f5d597331137f2881ce3 100644
--- a/block/blk-ioc.c
+++ b/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);
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 60ac684c8b8c52f26fe8a83d290fbd8f75f76581..a07ca3488d96fb7a96159fbe48c0c9e5e95391ec 100644
--- a/block/blk-mq-tag.c
+++ b/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);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1c27b3eaef645ab1ff12d93ac400fcbdd3ebb655..68c0a3416b341cc33327315b9abd88965f10cafa 100644
--- a/block/blk-mq.c
+++ b/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_WAIT|__GFP_HIGH, false, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, rw);
ctx = alloc_data.ctx;
hctx = alloc_data.hctx;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c097909c589c240e4b9d2ca44e1a9b7084ea9b15..b4b5680ac6adb1dcdbda2428b08398d38e2c8d4b 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/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;
}
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index e229425962074cf358ee234b853af452435495ea..1b709a4e3b5ec62eaf9709b366ea11c0d097ffd3 100644
--- a/drivers/block/osdblk.c
+++ b/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)
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 30f522848c7353166af0d9605215205101c0b013..d7373ca69c9947a83dd8a1d67b77c7fc9e77209e 100644
--- a/drivers/connector/connector.c
+++ b/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);
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index 2a3973a7c44179457f635196696bc78e756a76e1..36a7c2d89a010e7a567224c89a01a2ebe0c8fd20 100644
--- a/drivers/firewire/core-cdev.c
+++ b/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;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4d631a94648194957512d096e89da0e5242bd822..d58cb9e034fe896acf71d6a399cf00e599ff357b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2215,7 +2215,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
*/
mapping = file_inode(obj->base.filp)->i_mapping;
gfp = mapping_gfp_mask(mapping);
- gfp |= __GFP_NORETRY | __GFP_NOWARN | __GFP_NO_KSWAPD;
+ gfp |= __GFP_NORETRY | __GFP_NOWARN;
gfp &= ~(__GFP_IO | __GFP_WAIT);
sg = st->sgl;
st->nents = 0;
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 8c014b33d8e0a5bc97e6e2408b3ded37ddfd06c2..59ab264c99c4f4a87c92cf654f14cc0806539cd6 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1083,7 +1083,7 @@ 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;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 0d533bba4ad18097e447be3dca3fa41e5d9abeab..8b2be1e7714f8bb7aa1d62193d3b3320fab64414 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/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,
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 7cf80c1a8a1607f2d2ea675b270600bed70c6ad7..f1042daef9ada83e931ae450623ce491ebd55959 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/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);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 3729b394432c9d66c7c219a8a52ddbf9be987869..917d47e290ae08be08f4c964a3326f1f67acd077 100644
--- a/drivers/md/dm-crypt.c
+++ b/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 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
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 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
}
return_clone:
- if (unlikely(gfp_mask & __GFP_WAIT))
+ if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM))
mutex_unlock(&cc->bio_alloc_lock);
return clone;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 3a7cade5e27d828ffa2df3b9254f9064ec078c84..1452ed9aacb4222e4ee86c28480ddf373ac5e3c7 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/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;
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c b/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
index 1bd2fd47421fc43e02b7ad39c28546e55b3ea69e..4432fd69b7cbf86db946fb9aa6bfa753cb21434c 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2-enc.c
+++ b/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;
diff --git a/drivers/media/pci/solo6x10/solo6x10-v4l2.c b/drivers/media/pci/solo6x10/solo6x10-v4l2.c
index 26df903585d7dd02a54077bc24bbba8acda87b40..f7ce493b1feed72c27dd4f9d58e1ebe15bec5708 100644
--- a/drivers/media/pci/solo6x10/solo6x10-v4l2.c
+++ b/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);
diff --git a/drivers/media/pci/tw68/tw68-video.c b/drivers/media/pci/tw68/tw68-video.c
index 4c3293dcddbcde3cd6b37584c6665d870fef1bc8..46642ef9151b644413c3de4e33ee5e9279d2107d 100644
--- a/drivers/media/pci/tw68/tw68-video.c
+++ b/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;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 8bbbb751bf45e2340e727439b6368c78d148089f..2dfb291a47c6da6e64caa1788f1329305658b9c5 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1188,8 +1188,7 @@ 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_NORETRY | __GFP_NO_KSWAPD;
+ gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY;
size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
void *kbuf;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 44173be5cbf0d914111304ba2420954f44d5a7e7..f8d7a2f06950139b936dc7d793bb884bb579980d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/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);
diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c
index ada724aab3d586ebb81193909a2518a1e68872fb..d4c3e5512dd54dbcf0b3f6d9a927a1e8bbb3fc5a 100644
--- a/drivers/staging/android/ion/ion_system_heap.c
+++ b/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);
diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
index 6af733de69caddbf7672b80e75e1827304e7b237..f0b0423a716bd09252b74f5f9d22506fddc7c4dd 100644
--- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h
+++ b/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) \
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index 0a94895a358d47e8e51cf32722afbdce0d6104d9..692ccc69345e4a9998246a53b6af817a56a5d435 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/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;
}
diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c
index 6b70d7f62b2fa43aa9f286d51b6aa8983fd08353..1c1e95a0b8faa04006c857158c79ac11bc904d96 100644
--- a/drivers/video/fbdev/vermilion/vermilion.c
+++ b/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);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1e60d00d4ea7c42104614ede9e203a1f56e6408a..c339d561e59654935378fb8c23593f418aee2c8f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2572,7 +2572,7 @@ 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,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3915c9473e9445d4aeada81c8fb96af7fb521f2c..032abfbebe76e6e4ba41e25d7c9326079ed71f68 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -594,7 +594,7 @@ 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
@@ -718,7 +718,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
}
@@ -850,7 +850,7 @@ __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);
}
@@ -1028,7 +1028,7 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
if (start > end)
goto out;
spin_unlock(&tree->lock);
- if (mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
}
@@ -1076,7 +1076,7 @@ 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
@@ -1253,7 +1253,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
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;
@@ -4319,7 +4319,7 @@ 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) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6fc735869c186c35fb79fa66decc7d3519ed2e93..e023919b447064cbc6fad6984065731cbbde68c3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -156,8 +156,8 @@ 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_extents, GFP_NOFS & ~__GFP_WAIT);
+ INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
+ INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
return dev;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a63c7b0a10cfca3b3075f4dc14435add1bcec91b..49f6c78ee3afe26aa45941d443c5ea242ef95676 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1058,7 +1058,7 @@ 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);
}
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index d403c69bee0829fba9187114bc318dd810e8d179..4304072161aa08c14d24291bf24eb2481c567874 100644
--- a/fs/fscache/cookie.c
+++ b/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:
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 483bbc613bf04528cbc66d5d54a5b54b6a8dc85b..79483b3d8c6f273f9a8e8a5c0c997efa949d48ff 100644
--- a/fs/fscache/page.c
+++ b/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 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
* 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 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
_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);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 6b8338ec246454444d0dce734b9dee36b15c9f30..89463eee67914643a02ce711463e62fac0b83c8d 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1937,8 +1937,8 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
* @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
- * release the buffers.
+ * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit
+ * code to release the buffers.
*
*
* For all the buffers on this page,
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 37f639d50af580396bf016a2fb40c2b427c7b1dd..93e236429c5d785a1711d643d0b4676dfe4396cf 100644
--- a/fs/nfs/file.c
+++ b/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
- * second and only if the 'bdi' is not congested.
+ * wait for it if the caller allows blocking. Even then,
+ * 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);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index eac9549efd52c824d7e298b494a470f43923936e..587174fd4f2c216637eda70b9986848a0980fd09 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -525,7 +525,7 @@ xfs_qm_shrink_scan(
unsigned long freed;
int error;
- if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
+ if ((sc->gfp_mask & (__GFP_FS|__GFP_DIRECT_RECLAIM)) != (__GFP_FS|__GFP_DIRECT_RECLAIM))
return 0;
INIT_LIST_HEAD(&isol.buffers);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 440fca3e7e5d2acbf77c85ee1fe9ea8b28003996..b56e811b6f7c77f91a3535da405c919574c2f4f7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -29,12 +29,13 @@ struct vm_area_struct;
#define ___GFP_NOMEMALLOC 0x10000u
#define ___GFP_HARDWALL 0x20000u
#define ___GFP_THISNODE 0x40000u
-#define ___GFP_WAIT 0x80000u
+#define ___GFP_ATOMIC 0x80000u
#define ___GFP_NOACCOUNT 0x100000u
#define ___GFP_NOTRACK 0x200000u
-#define ___GFP_NO_KSWAPD 0x400000u
+#define ___GFP_DIRECT_RECLAIM 0x400000u
#define ___GFP_OTHER_NODE 0x800000u
#define ___GFP_WRITE 0x1000000u
+#define ___GFP_KSWAPD_RECLAIM 0x2000000u
/* If the above are modified, __GFP_BITS_SHIFT may need updating */
/*
@@ -71,7 +72,7 @@ struct vm_area_struct;
* __GFP_MOVABLE: Flag that this page will be movable by the page migration
* mechanism or reclaimed
*/
-#define __GFP_WAIT ((__force gfp_t)___GFP_WAIT) /* Can wait and reschedule? */
+#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) /* Caller cannot wait or reschedule */
#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) /* Should access emergency pools? */
#define __GFP_IO ((__force gfp_t)___GFP_IO) /* Can start physical IO? */
#define __GFP_FS ((__force gfp_t)___GFP_FS) /* Can call down to low-level FS? */
@@ -94,23 +95,37 @@ struct vm_area_struct;
#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */
#define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */
-#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */
+/*
+ * A caller that is willing to wait may enter direct reclaim and will
+ * wake kswapd to reclaim pages in the background until the high
+ * watermark is met. A caller may wish to clear __GFP_DIRECT_RECLAIM to
+ * avoid unnecessary delays when a fallback option is available but
+ * still allow kswapd to reclaim in the background. The kswapd flag
+ * can be cleared when the reclaiming of pages would cause unnecessary
+ * disruption.
+ */
+#define __GFP_WAIT ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
+#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
+#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
+
/*
* This may seem redundant, but it's a way of annotating false positives vs.
* allocations that simply cannot be supported (e.g. page tables).
*/
#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
-#define __GFP_BITS_SHIFT 25 /* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 26 /* Room for N __GFP_FOO bits */
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
-/* This equals 0, but use constants in case they ever change */
-#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH)
-/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */
-#define GFP_ATOMIC (__GFP_HIGH)
+/*
+ * GFP_ATOMIC callers can not sleep, need the allocation to succeed.
+ * A lower watermark is applied to allow access to "atomic reserves"
+ */
+#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
+#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
#define GFP_NOIO (__GFP_WAIT)
#define GFP_NOFS (__GFP_WAIT | __GFP_IO)
#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS)
@@ -119,10 +134,10 @@ struct vm_area_struct;
#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM)
#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE)
-#define GFP_IOFS (__GFP_IO | __GFP_FS)
-#define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
- __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
- __GFP_NO_KSWAPD)
+#define GFP_IOFS (__GFP_IO | __GFP_FS | __GFP_KSWAPD_RECLAIM)
+#define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+ __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
+ ~__GFP_KSWAPD_RECLAIM)
/* This mask makes up all the page movable related flags */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -164,6 +179,11 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
}
+static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
+{
+ return gfp_flags & __GFP_DIRECT_RECLAIM;
+}
+
#ifdef CONFIG_HIGHMEM
#define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
#else
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 24f4dfd94c517b3b387682509180dee161e0912d..4355129fff91b6f188136af2a499d6100f2e5bfd 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1224,7 +1224,7 @@ static inline int skb_cloned(const struct sk_buff *skb)
static inline int skb_unclone(struct sk_buff *skb, gfp_t pri)
{
- might_sleep_if(pri & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_cloned(skb))
return pskb_expand_head(skb, 0, 0, pri);
@@ -1308,7 +1308,7 @@ static inline int skb_shared(const struct sk_buff *skb)
*/
static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
{
- might_sleep_if(pri & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_shared(skb)) {
struct sk_buff *nskb = skb_clone(skb, pri);
@@ -1344,7 +1344,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
gfp_t pri)
{
- might_sleep_if(pri & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(pri));
if (skb_cloned(skb)) {
struct sk_buff *nskb = skb_copy(skb, pri);
diff --git a/include/net/sock.h b/include/net/sock.h
index f570e75e3da927c54438340988f2a56762220060..bbf7c2cf15b4ec278bca5426b3319ca501454d66 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2041,7 +2041,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
*/
static inline struct page_frag *sk_page_frag(struct sock *sk)
{
- if (sk->sk_allocation & __GFP_WAIT)
+ if (gfpflags_allow_blocking(sk->sk_allocation))
return ¤t->task_frag;
return &sk->sk_frag;
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index d6fd8e5b14b76c41bfd532c3fa86255e4e92b0f3..dde6bf092c8ac356d1502b7d444e73ce8b8c143a 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -20,7 +20,7 @@
{(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \
{(unsigned long)GFP_NOIO, "GFP_NOIO"}, \
{(unsigned long)__GFP_HIGH, "GFP_HIGH"}, \
- {(unsigned long)__GFP_WAIT, "GFP_WAIT"}, \
+ {(unsigned long)__GFP_ATOMIC, "GFP_ATOMIC"}, \
{(unsigned long)__GFP_IO, "GFP_IO"}, \
{(unsigned long)__GFP_COLD, "GFP_COLD"}, \
{(unsigned long)__GFP_NOWARN, "GFP_NOWARN"}, \
@@ -36,7 +36,8 @@
{(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \
{(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \
{(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \
- {(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \
+ {(unsigned long)__GFP_DIRECT_RECLAIM, "GFP_DIRECT_RECLAIM"}, \
+ {(unsigned long)__GFP_KSWAPD_RECLAIM, "GFP_KSWAPD_RECLAIM"}, \
{(unsigned long)__GFP_OTHER_NODE, "GFP_OTHER_NODE"} \
) : "GFP_NOWAIT"
diff --git a/kernel/audit.c b/kernel/audit.c
index 8a056a32ded7d2b4560612af7d84ac317f7a17b3..5ffcbd354a520b88781ed2d66c7839a7aaa7f86d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1371,16 +1371,16 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
if (unlikely(audit_filter_type(type)))
return NULL;
- if (gfp_mask & __GFP_WAIT) {
+ if (gfp_mask & __GFP_DIRECT_RECLAIM) {
if (audit_pid && audit_pid == current->pid)
- gfp_mask &= ~__GFP_WAIT;
+ gfp_mask &= ~__GFP_DIRECT_RECLAIM;
else
reserve = 0;
}
while (audit_backlog_limit
&& skb_queue_len(&audit_skb_queue) > audit_backlog_limit + reserve) {
- if (gfp_mask & __GFP_WAIT && audit_backlog_wait_time) {
+ if (gfp_mask & __GFP_DIRECT_RECLAIM && audit_backlog_wait_time) {
long sleep_time;
sleep_time = timeout_start + audit_backlog_wait_time - jiffies;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b9d0cce3f9ce54937fea988b531d0cc7bf52f692..f1603c153890d2b9dbd37a5c687fd297c6137f24 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -299,7 +299,7 @@ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
idr_preload(gfp_mask);
spin_lock_bh(&cgroup_idr_lock);
- ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_WAIT);
+ ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM);
spin_unlock_bh(&cgroup_idr_lock);
idr_preload_end();
return ret;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4e49cc4c9952ca82eff8a2b5e5e61765d48ea96f..deae3907ac1eec585bbe71a44f6dc57ad024784a 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2738,7 +2738,7 @@ static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
return;
/* no reclaim without waiting on it */
- if (!(gfp_mask & __GFP_WAIT))
+ if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
return;
/* this guy won't enter reclaim */
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5235dd4e1e2f68a97fa6836d98854d2e8e46724e..3a970604308ff5365f431e8190d1b82f7ac306d1 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1779,7 +1779,7 @@ alloc_highmem_pages(struct memory_bitmap *bm, unsigned int nr_highmem)
while (to_alloc-- > 0) {
struct page *page;
- page = alloc_image_page(__GFP_HIGHMEM);
+ page = alloc_image_page(__GFP_HIGHMEM|__GFP_KSWAPD_RECLAIM);
memory_bm_set_bit(bm, page_to_pfn(page));
}
return nr_highmem;
diff --git a/kernel/smp.c b/kernel/smp.c
index 07854477c16447ff87df874b4f117bcafadd4f33..d903c02223afbaa2776b2610f00ae3def7de442e 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -669,7 +669,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
cpumask_var_t cpus;
int cpu, ret;
- might_sleep_if(gfp_flags & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(gfp_flags));
if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
preempt_disable();
diff --git a/lib/idr.c b/lib/idr.c
index 5335c43adf46af55bb90717aa63afe33a6a30e9c..6098336df2672e09f0d022aa5c1a1c8252aa73c7 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -399,7 +399,7 @@ void idr_preload(gfp_t gfp_mask)
* allocation guarantee. Disallow usage from those contexts.
*/
WARN_ON_ONCE(in_interrupt());
- might_sleep_if(gfp_mask & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(gfp_mask));
preempt_disable();
@@ -453,7 +453,7 @@ int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask)
struct idr_layer *pa[MAX_IDR_LEVEL + 1];
int id;
- might_sleep_if(gfp_mask & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(gfp_mask));
/* sanity checks */
if (WARN_ON_ONCE(start < 0))
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index f9ebe1c82060ec330ac7ae7a9d1678f18058cf65..fcf5d98574ce46871dca087d2c803dbfb67c0b81 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -188,7 +188,7 @@ radix_tree_node_alloc(struct radix_tree_root *root)
* preloading in the interrupt anyway as all the allocations have to
* be atomic. So just do normal allocation when in interrupt.
*/
- if (!(gfp_mask & __GFP_WAIT) && !in_interrupt()) {
+ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) {
struct radix_tree_preload *rtp;
/*
@@ -249,7 +249,7 @@ radix_tree_node_free(struct radix_tree_node *node)
* with preemption not disabled.
*
* To make use of this facility, the radix tree must be initialised without
- * __GFP_WAIT being passed to INIT_RADIX_TREE().
+ * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE().
*/
static int __radix_tree_preload(gfp_t gfp_mask)
{
@@ -286,12 +286,12 @@ static int __radix_tree_preload(gfp_t gfp_mask)
* with preemption not disabled.
*
* To make use of this facility, the radix tree must be initialised without
- * __GFP_WAIT being passed to INIT_RADIX_TREE().
+ * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE().
*/
int radix_tree_preload(gfp_t gfp_mask)
{
/* Warn on non-sensical use... */
- WARN_ON_ONCE(!(gfp_mask & __GFP_WAIT));
+ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask));
return __radix_tree_preload(gfp_mask);
}
EXPORT_SYMBOL(radix_tree_preload);
@@ -303,7 +303,7 @@ EXPORT_SYMBOL(radix_tree_preload);
*/
int radix_tree_maybe_preload(gfp_t gfp_mask)
{
- if (gfp_mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(gfp_mask))
return __radix_tree_preload(gfp_mask);
/* Preloading doesn't help anything with this gfp mask, skip it */
preempt_disable();
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 619984fc07ec32792349c7fe8aec7c8b56e3d2a3..8ed2ffd963c53b910f91e1b60b04c56385a3129f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -637,7 +637,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
{
struct bdi_writeback *wb;
- might_sleep_if(gfp & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(gfp));
if (!memcg_css->parent)
return &bdi->wb;
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 312a716fa14c2ef0d2780832bc378c05a3d08d16..57312b5d6e12aaf2da3f6acd38a19bbe28959077 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -326,7 +326,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
size_t offset;
void *retval;
- might_sleep_if(mem_flags & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(mem_flags));
spin_lock_irqsave(&pool->lock, flags);
list_for_each_entry(page, &pool->page_list, page_list) {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bc502e590366d41aaa9f54d23fb33bf5d44a5d76..05374f09339ccf57678433ab3db6d83587c7077c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2046,7 +2046,7 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
if (unlikely(task_in_memcg_oom(current)))
goto nomem;
- if (!(gfp_mask & __GFP_WAIT))
+ if (!gfpflags_allow_blocking(gfp_mask))
goto nomem;
mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1);
@@ -4364,8 +4364,8 @@ static int mem_cgroup_do_precharge(unsigned long count)
{
int ret;
- /* Try a single bulk charge without reclaim first */
- ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count);
+ /* Try a single bulk charge without reclaim first, kswapd may wake */
+ ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count);
if (!ret) {
mc.precharge += count;
return ret;
diff --git a/mm/mempool.c b/mm/mempool.c
index 4c533bc51d733989f12c9f5e25cad713f647baea..004d42b1dfaf928ab174e057696afa580447f3d9 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -320,13 +320,13 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
gfp_t gfp_temp;
VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);
- might_sleep_if(gfp_mask & __GFP_WAIT);
+ might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
- gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);
+ gfp_temp = gfp_mask & ~(__GFP_DIRECT_RECLAIM|__GFP_IO);
repeat_alloc:
@@ -349,7 +349,7 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
}
/*
- * We use gfp mask w/o __GFP_WAIT or IO for the first round. If
+ * We use gfp mask w/o direct reclaim or IO for the first round. If
* alloc failed with that and @pool was empty, retry immediately.
*/
if (gfp_temp != gfp_mask) {
@@ -358,8 +358,8 @@ void * mempool_alloc(mempool_t *pool, gfp_t gfp_mask)
goto repeat_alloc;
}
- /* We must not sleep if !__GFP_WAIT */
- if (!(gfp_mask & __GFP_WAIT)) {
+ /* We must not sleep if !__GFP_DIRECT_RECLAIM */
+ if (!(gfp_mask & __GFP_DIRECT_RECLAIM)) {
spin_unlock_irqrestore(&pool->lock, flags);
return NULL;
}
diff --git a/mm/migrate.c b/mm/migrate.c
index 2834faba719a9e4ea1e49af6037d2b70efcf0ad2..e60379eb23f8402bf65cb18e8a6e3fb3e3c98411 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1578,7 +1578,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
(GFP_HIGHUSER_MOVABLE |
__GFP_THISNODE | __GFP_NOMEMALLOC |
__GFP_NORETRY | __GFP_NOWARN) &
- ~GFP_IOFS, 0);
+ ~(__GFP_IO | __GFP_FS), 0);
return newpage;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 67390988881a9d74cc2883df94dd0fdb5a146f46..70461f3e3378691499d63005bd74059ba54c4566 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -169,12 +169,12 @@ void pm_restrict_gfp_mask(void)
WARN_ON(!mutex_is_locked(&pm_mutex));
WARN_ON(saved_gfp_mask);
saved_gfp_mask = gfp_allowed_mask;
- gfp_allowed_mask &= ~GFP_IOFS;
+ gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
}
bool pm_suspended_storage(void)
{
- if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+ if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
return false;
return true;
}
@@ -2183,7 +2183,7 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
return false;
if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
return false;
- if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
+ if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_DIRECT_RECLAIM))
return false;
return should_fail(&fail_page_alloc.attr, 1 << order);
@@ -2685,7 +2685,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
if (test_thread_flag(TIF_MEMDIE) ||
(current->flags & (PF_MEMALLOC | PF_EXITING)))
filter &= ~SHOW_MEM_FILTER_NODES;
- if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+ if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
filter &= ~SHOW_MEM_FILTER_NODES;
if (fmt) {
@@ -2945,7 +2945,6 @@ static inline int
gfp_to_alloc_flags(gfp_t gfp_mask)
{
int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2954,11 +2953,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
- * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
+ * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
- if (atomic) {
+ if (gfp_mask & __GFP_ATOMIC) {
/*
* Not worth trying to allocate harder for __GFP_NOMEMALLOC even
* if it can't schedule.
@@ -2995,11 +2994,16 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
}
+static inline bool is_thp_gfp_mask(gfp_t gfp_mask)
+{
+ return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE;
+}
+
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
- const gfp_t wait = gfp_mask & __GFP_WAIT;
+ bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
struct page *page = NULL;
int alloc_flags;
unsigned long pages_reclaimed = 0;
@@ -3019,16 +3023,24 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
return NULL;
}
+ /*
+ * We also sanity check to catch abuse of atomic reserves being used by
+ * callers that are not in atomic context.
+ */
+ if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
+ (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
+ gfp_mask &= ~__GFP_ATOMIC;
+
/*
* If this allocation cannot block and it is for a specific node, then
* fail early. There's no need to wakeup kswapd or retry for a
* speculative node-specific allocation.
*/
- if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait)
+ if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim)
goto nopage;
retry:
- if (!(gfp_mask & __GFP_NO_KSWAPD))
+ if (gfp_mask & __GFP_KSWAPD_RECLAIM)
wake_all_kswapds(order, ac);
/*
@@ -3071,8 +3083,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
}
}
- /* Atomic allocations - we can't balance anything */
- if (!wait) {
+ /* Caller is not willing to reclaim, we can't balance anything */
+ if (!can_direct_reclaim) {
/*
* All existing users of the deprecated __GFP_NOFAIL are
* blockable, so warn of any new users that actually allow this
@@ -3102,7 +3114,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
goto got_pg;
/* Checks for THP-specific high-order allocations */
- if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
+ if (is_thp_gfp_mask(gfp_mask)) {
/*
* If compaction is deferred for high-order allocations, it is
* because sync compaction recently failed. If this is the case
@@ -3137,8 +3149,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* fault, so use asynchronous memory compaction for THP unless it is
* khugepaged trying to collapse.
*/
- if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE ||
- (current->flags & PF_KTHREAD))
+ if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD))
migration_mode = MIGRATE_SYNC_LIGHT;
/* Try direct reclaim and then allocating */
@@ -3209,7 +3220,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
lockdep_trace_alloc(gfp_mask);
- might_sleep_if(gfp_mask & __GFP_WAIT);
+ might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
if (should_fail_alloc_page(gfp_mask, order))
return NULL;
diff --git a/mm/slab.c b/mm/slab.c
index 272e809404d507e19edd74842811ada8fcf600a2..a9ef77d19a9ada7f06b5ffbaec4f45aa5d897de0 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1031,12 +1031,12 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
}
/*
- * Construct gfp mask to allocate from a specific node but do not invoke reclaim
- * or warn about failures.
+ * Construct gfp mask to allocate from a specific node but do not direct reclaim
+ * or warn about failures. kswapd may still wake to reclaim in the background.
*/
static inline gfp_t gfp_exact_node(gfp_t flags)
{
- return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_WAIT;
+ return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_DIRECT_RECLAIM;
}
#endif
@@ -2633,7 +2633,7 @@ static int cache_grow(struct kmem_cache *cachep,
offset *= cachep->colour_off;
- if (local_flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(local_flags))
local_irq_enable();
/*
@@ -2663,7 +2663,7 @@ static int cache_grow(struct kmem_cache *cachep,
cache_init_objs(cachep, page);
- if (local_flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(local_flags))
local_irq_disable();
check_irq_off();
spin_lock(&n->list_lock);
@@ -2677,7 +2677,7 @@ static int cache_grow(struct kmem_cache *cachep,
opps1:
kmem_freepages(cachep, page);
failed:
- if (local_flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(local_flags))
local_irq_disable();
return 0;
}
@@ -2869,7 +2869,7 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
gfp_t flags)
{
- might_sleep_if(flags & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(flags));
#if DEBUG
kmem_flagcheck(cachep, flags);
#endif
@@ -3057,11 +3057,11 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
*/
struct page *page;
- if (local_flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(local_flags))
local_irq_enable();
kmem_flagcheck(cache, flags);
page = kmem_getpages(cache, local_flags, numa_mem_id());
- if (local_flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(local_flags))
local_irq_disable();
if (page) {
/*
diff --git a/mm/slub.c b/mm/slub.c
index 75a5fa92ac2a2fd5c4e56cdfd02b7b754392d9a5..97695622a85808cb92e69d807a07aed9101bacce 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1265,7 +1265,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
{
flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
- might_sleep_if(flags & __GFP_WAIT);
+ might_sleep_if(gfpflags_allow_blocking(flags));
if (should_failslab(s->object_size, flags, s->flags))
return NULL;
@@ -1353,7 +1353,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
flags &= gfp_allowed_mask;
- if (flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(flags))
local_irq_enable();
flags |= s->allocflags;
@@ -1363,8 +1363,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
* so we fall-back to the minimum order allocation.
*/
alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
- if ((alloc_gfp & __GFP_WAIT) && oo_order(oo) > oo_order(s->min))
- alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_WAIT;
+ if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
+ alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_DIRECT_RECLAIM;
page = alloc_slab_page(s, alloc_gfp, node, oo);
if (unlikely(!page)) {
@@ -1424,7 +1424,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
page->frozen = 1;
out:
- if (flags & __GFP_WAIT)
+ if (gfpflags_allow_blocking(flags))
local_irq_disable();
if (!page)
return NULL;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 9db9ef5e8481a15e3bf99bf34276a0588fb2e674..7ee94dc1000031004c15524e00df351aeeac7a59 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1617,7 +1617,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
goto fail;
}
area->pages[i] = page;
- if (gfp_mask & __GFP_WAIT)
+ if (gfpflags_allow_blocking(gfp_mask))
cond_resched();
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e0cd7eed4e380a3eacdc6e99320e204f01b212ee..2aec4241b42a9f0b02c8f4124698d6b595c96390 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1476,7 +1476,7 @@ static int too_many_isolated(struct zone *zone, int file,
* won't get blocked by normal direct-reclaimers, forming a circular
* deadlock.
*/
- if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
+ if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
inactive >>= 3;
return isolated > inactive;
@@ -3791,7 +3791,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
/*
* Do not scan if the allocation should not be delayed.
*/
- if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
+ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC))
return ZONE_RECLAIM_NOSCAN;
/*
diff --git a/mm/zswap.c b/mm/zswap.c
index 4043df7c672fb6f5b1be298b8d510fd17a3bbf42..e54166d3732e8e4bae250a0b06607a42863f42c2 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -571,7 +571,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
{
struct zswap_pool *pool;
- gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
pool = kzalloc(sizeof(*pool), GFP_KERNEL);
if (!pool) {
@@ -1011,7 +1011,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* store */
len = dlen + sizeof(struct zswap_header);
ret = zpool_malloc(entry->pool->zpool, len,
- __GFP_NORETRY | __GFP_NOWARN, &handle);
+ __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM,
+ &handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
goto put_dstmem;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fab4599ba8b261dc43977af8349a336edc4d2799..aa41e6dd642913f2181832145e22ec1dad6fa7b8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -414,7 +414,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
len += NET_SKB_PAD;
if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
- (gfp_mask & (__GFP_WAIT | GFP_DMA))) {
+ (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
if (!skb)
goto skb_fail;
@@ -481,7 +481,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
len += NET_SKB_PAD + NET_IP_ALIGN;
if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
- (gfp_mask & (__GFP_WAIT | GFP_DMA))) {
+ (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
if (!skb)
goto skb_fail;
@@ -4452,7 +4452,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
return NULL;
gfp_head = gfp_mask;
- if (gfp_head & __GFP_WAIT)
+ if (gfp_head & __GFP_DIRECT_RECLAIM)
gfp_head |= __GFP_REPEAT;
*errcode = -ENOBUFS;
@@ -4467,7 +4467,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
while (order) {
if (npages >= 1 << order) {
- page = alloc_pages((gfp_mask & ~__GFP_WAIT) |
+ page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP |
__GFP_NOWARN |
__GFP_NORETRY,
diff --git a/net/core/sock.c b/net/core/sock.c
index 7529eb9463be21a92dab4180adf5059cc0587807..1e4dd54bfb5a525ef6070905f07472f60e9f137f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1944,8 +1944,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
pfrag->offset = 0;
if (SKB_FRAG_PAGE_ORDER) {
- pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP |
- __GFP_NOWARN | __GFP_NORETRY,
+ /* Avoid direct reclaim but allow kswapd to wake */
+ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
+ __GFP_COMP | __GFP_NOWARN |
+ __GFP_NORETRY,
SKB_FRAG_PAGE_ORDER);
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fafe33bdb61989e680dc4b26dbe99dcc1d4064b5..59651af8cc2705b39f3ad1ea71ab0b161668af02 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2116,7 +2116,7 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid
consume_skb(info.skb2);
if (info.delivered) {
- if (info.congested && (allocation & __GFP_WAIT))
+ if (info.congested && gfpflags_allow_blocking(allocation))
yield();
return 0;
}
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 96744b75db9387aa2ef3b28d8ea103d81997a9ab..977fb86065b75dbef916bd0acb9b94876c0f5c04 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -305,7 +305,7 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn,
gfp_t slab_mask = GFP_NOWAIT;
gfp_t page_mask = GFP_NOWAIT;
- if (gfp & __GFP_WAIT) {
+ if (gfp & __GFP_DIRECT_RECLAIM) {
slab_mask = GFP_KERNEL;
page_mask = GFP_HIGHUSER;
}
@@ -379,7 +379,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
struct ib_recv_wr *failed_wr;
unsigned int posted = 0;
int ret = 0;
- bool can_wait = !!(gfp & __GFP_WAIT);
+ bool can_wait = !!(gfp & __GFP_DIRECT_RECLAIM);
u32 pos;
/* the goal here is to just make sure that someone, somewhere
diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c
index 692b3e67fb54418ffb143491b9e2f1dc82d8d503..6c71ed1caf16727a587c90ff81dcd6a7abd3d10b 100644
--- a/net/rxrpc/ar-connection.c
+++ b/net/rxrpc/ar-connection.c
@@ -500,7 +500,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
if (bundle->num_conns >= 20) {
_debug("too many conns");
- if (!(gfp & __GFP_WAIT)) {
+ if (!gfpflags_allow_blocking(gfp)) {
_leave(" = -EAGAIN");
return -EAGAIN;
}
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index b00f1f9611d64a7f46fdd37460d9c5ec9711f37f..559afd0ee7de099ba013c8921045fedb4e7e5488 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1590,7 +1590,7 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc,
/* Set an association id for a given association */
int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp)
{
- bool preload = !!(gfp & __GFP_WAIT);
+ bool preload = gfpflags_allow_blocking(gfp);
int ret;
/* If the id is already assigned, keep it. */