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>

6 files changed, 13 insertions, 11 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fab4599ba8b2..aa41e6dd6429 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 7529eb9463be..1e4dd54bfb5a 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 fafe33bdb619..59651af8cc27 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 96744b75db93..977fb86065b7 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 692b3e67fb54..6c71ed1caf16 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 b00f1f9611d6..559afd0ee7de 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. */