mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd

__GFP_WAIT has been used to identify atomic context in callers that hold
spinlocks or are in interrupts.  They are expected to be high priority and
have access one of two watermarks lower than "min" which can be referred
to as the "atomic reserve".  __GFP_HIGH users get access to the first
lower watermark and can be called the "high priority reserve".

Over time, callers had a requirement to not block when fallback options
were available.  Some have abused __GFP_WAIT leading to a situation where
an optimisitic allocation with a fallback option can access atomic
reserves.

This patch uses __GFP_ATOMIC to identify callers that are truely atomic,
cannot sleep and have no alternative.  High priority users continue to use
__GFP_HIGH.  __GFP_DIRECT_RECLAIM identifies callers that can sleep and
are willing to enter direct reclaim.  __GFP_KSWAPD_RECLAIM to identify
callers that want to wake kswapd for background reclaim.  __GFP_WAIT is
redefined as a caller that is willing to enter direct reclaim and wake
kswapd for background reclaim.

This patch then converts a number of sites

o __GFP_ATOMIC is used by callers that are high priority and have memory
  pools for those requests. GFP_ATOMIC uses this flag.

o Callers that have a limited mempool to guarantee forward progress clear
  __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall
  into this category where kswapd will still be woken but atomic reserves
  are not used as there is a one-entry mempool to guarantee progress.

o Callers that are checking if they are non-blocking should use the
  helper gfpflags_allow_blocking() where possible. This is because
  checking for __GFP_WAIT as was done historically now can trigger false
  positives. Some exceptions like dm-crypt.c exist where the code intent
  is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to
  flag manipulations.

o Callers that built their own GFP flags instead of starting with GFP_KERNEL
  and friends now also need to specify __GFP_KSWAPD_RECLAIM.

The first key hazard to watch out for is callers that removed __GFP_WAIT
and was depending on access to atomic reserves for inconspicuous reasons.
In some cases it may be appropriate for them to use __GFP_HIGH.

The second key hazard is callers that assembled their own combination of
GFP flags instead of starting with something like GFP_KERNEL.  They may
now wish to specify __GFP_KSWAPD_RECLAIM.  It's almost certainly harmless
if it's missed in most cases as other activity will wake kswapd.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

19 files changed, 23 insertions, 22 deletions

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c097909c589c..b4b5680ac6ad 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 e22942596207..1b709a4e3b5e 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 30f522848c73..d7373ca69c99 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 2a3973a7c441..36a7c2d89a01 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 4d631a946481..d58cb9e034fe 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 8c014b33d8e0..59ab264c99c4 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 0d533bba4ad1..8b2be1e7714f 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 7cf80c1a8a16..f1042daef9ad 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 3729b394432c..917d47e290ae 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 @@ 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;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 3a7cade5e27d..1452ed9aacb4 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 1bd2fd47421f..4432fd69b7cb 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 26df903585d7..f7ce493b1fee 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 4c3293dcddbc..46642ef9151b 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 8bbbb751bf45..2dfb291a47c6 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 44173be5cbf0..f8d7a2f06950 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 ada724aab3d5..d4c3e5512dd5 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 6af733de69ca..f0b0423a716b 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 0a94895a358d..692ccc69345e 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 6b70d7f62b2f..1c1e95a0b8fa 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);