Larry Woodman db38c179a7 [NET]: __alloc_pages() failures reported due to fragmentation ...

We have seen a couple of __alloc_pages() failures due to
fragmentation, there is plenty of free memory but no large order pages
available.  I think the problem is in sock_alloc_send_pskb(), the
gfp_mask includes __GFP_REPEAT but its never used/passed to the page
allocator.  Shouldnt the gfp_mask be passed to alloc_skb() ?

Signed-off-by: Larry Woodman <lwoodman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2006-11-05 14:11:32 -08:00

..

datagram.c

…

dev_mcast.c

…

dev.c

[PATCH] rename net_random to random32

2006-10-17 08:18:43 -07:00

dst.c

…

dv.c

…

ethtool.c

…

fib_rules.c

…

filter.c

…

flow.c

IPsec: propagate security module errors up from flow_cache_lookup

2006-10-11 23:59:34 -07:00

gen_estimator.c

…

gen_stats.c

…

iovec.c

…

link_watch.c

…

Makefile

…

neighbour.c

…

net-sysfs.c

…

netevent.c

…

netpoll.c

[NETPOLL]: initialize skb for UDP

2006-10-19 23:58:23 -07:00

pktgen.c

[PKTGEN]: TCI endianness fixes

2006-11-05 14:11:31 -08:00

request_sock.c

…

rtnetlink.c

[RTNETLINK]: Fix use of wrong skb in do_getlink()

2006-10-12 01:50:30 -07:00

scm.c

[NET]: File descriptor loss while receiving SCM_RIGHTS

2006-10-11 23:59:48 -07:00

skbuff.c

[NET]: Fix segmentation of linear packets

2006-10-30 15:24:36 -08:00

sock.c

[NET]: __alloc_pages() failures reported due to fragmentation

2006-11-05 14:11:32 -08:00

stream.c

…

sysctl_net_core.c

…

user_dma.c

…

utils.c

[PATCH] rename net_random to random32

2006-10-17 08:18:43 -07:00

wireless.c

[PATCH] wireless: WE-20 compatibility for ESSID and NICKN ioctls

2006-10-19 17:08:19 -04:00