linux-toradex.git/net/netlink, branch v4.4.93

netlink: Allow direct reclaim for fallback allocation

2017-05-08T05:46:02+00:00

The backport of d35c99ff77ec ("netlink: do not enter direct reclaim from
netlink_dump()") to the 4.4 branch (first in 4.4.32) mistakenly removed
direct claim from the initial large allocation _and_ the fallback
allocation which means that allocations can spuriously fail.
Fix the issue by adding back the direct reclaim flag to the fallback
allocation.

Fixes: 6d123f1d396b ("netlink: do not enter direct reclaim from netlink_dump()")
Signed-off-by: Ross Lagerwall 
Signed-off-by: Greg Kroah-Hartman

netlink: remove mmapped netlink support

2017-03-22T11:04:13+00:00

commit d1b4c689d4130bcfd3532680b64db562300716b6 upstream.

mmapped netlink has a number of unresolved issues:

- TX zerocopy support had to be disabled more than a year ago via
  commit 4682a0358639b29cf ("netlink: Always copy on mmap TX.")
  because the content of the mmapped area can change after netlink
  attribute validation but before message processing.

- RX support was implemented mainly to speed up nfqueue dumping packet
  payload to userspace.  However, since commit ae08ce0021087a5d812d2
  ("netfilter: nfnetlink_queue: zero copy support") we avoid one copy
  with the socket-based interface too (via the skb_zerocopy helper).

The other problem is that skbs attached to mmaped netlink socket
behave different from normal skbs:

- they don't have a shinfo area, so all functions that use skb_shinfo()
(e.g. skb_clone) cannot be used.

- reserving headroom prevents userspace from seeing the content as
it expects message to start at skb->head.
See for instance
commit aa3a022094fa ("netlink: not trim skb for mmaped socket when dump").

- skbs handed e.g. to netlink_ack must have non-NULL skb->sk, else we
crash because it needs the sk to check if a tx ring is attached.

Also not obvious, leads to non-intuitive bug fixes such as 7c7bdf359
("netfilter: nfnetlink: use original skbuff when acking batches").

mmaped netlink also didn't play nicely with the skb_zerocopy helper
used by nfqueue and openvswitch.  Daniel Borkmann fixed this via
commit 6bb0fef489f6 ("netlink, mmap: fix edge-case leakages in nf queue
zero-copy")' but at the cost of also needing to provide remaining
length to the allocation function.

nfqueue also has problems when used with mmaped rx netlink:
- mmaped netlink doesn't allow use of nfqueue batch verdict messages.
  Problem is that in the mmap case, the allocation time also determines
  the ordering in which the frame will be seen by userspace (A
  allocating before B means that A is located in earlier ring slot,
  but this also means that B might get a lower sequence number then A
  since seqno is decided later.  To fix this we would need to extend the
  spinlocked region to also cover the allocation and message setup which
  isn't desirable.
- nfqueue can now be configured to queue large (GSO) skbs to userspace.
  Queing GSO packets is faster than having to force a software segmentation
  in the kernel, so this is a desirable option.  However, with a mmap based
  ring one has to use 64kb per ring slot element, else mmap has to fall back
  to the socket path (NL_MMAP_STATUS_COPY) for all large packets.

To use the mmap interface, userspace not only has to probe for mmap netlink
support, it also has to implement a recv/socket receive path in order to
handle messages that exceed the size of an rx ring element.

Cc: Daniel Borkmann 
Cc: Ken-ichirou MATSUZAWA 
Cc: Pablo Neira Ayuso 
Cc: Patrick McHardy 
Cc: Thomas Graf 
Signed-off-by: Florian Westphal 
Signed-off-by: David S. Miller 
Cc: Shi Yuejie 
Signed-off-by: Greg Kroah-Hartman

netlink: Do not schedule work from sk_destruct

2016-12-10T18:07:23+00:00

[ Upstream commit ed5d7788a934a4b6d6d025e948ed4da496b4f12e ]

It is wrong to schedule a work from sk_destruct using the socket
as the memory reserve because the socket will be freed immediately
after the return from sk_destruct.

Instead we should do the deferral prior to sk_free.

This patch does just that.

Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread")
Signed-off-by: Herbert Xu 
Tested-by: Andrey Konovalov 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

netlink: Call cb->done from a worker thread

2016-12-10T18:07:23+00:00

[ Upstream commit 707693c8a498697aa8db240b93eb76ec62e30892 ]

The cb->done interface expects to be called in process context.
This was broken by the netlink RCU conversion.  This patch fixes
it by adding a worker struct to make the cb->done call where
necessary.

Fixes: 21e4902aea80 ("netlink: Lockless lookup with RCU grace...")
Reported-by: Subash Abhinov Kasiviswanathan 
Signed-off-by: Herbert Xu 
Acked-by: Cong Wang 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

netlink: do not enter direct reclaim from netlink_dump()

2016-11-15T06:46:37+00:00

[ Upstream commit d35c99ff77ecb2eb239731b799386f3b3637a31e ]

Since linux-3.15, netlink_dump() can use up to 16384 bytes skb
allocations.

Due to struct skb_shared_info ~320 bytes overhead, we end up using
order-3 (on x86) page allocations, that might trigger direct reclaim and
add stress.

The intent was really to attempt a large allocation but immediately
fallback to a smaller one (order-1 on x86) in case of memory stress.

On recent kernels (linux-4.4), we can remove __GFP_DIRECT_RECLAIM to
meet the goal. Old kernels would need to remove __GFP_WAIT

While we are at it, since we do an order-3 allocation, allow to use
all the allocated bytes instead of 16384 to reduce syscalls during
large dumps.

iproute2 already uses 32KB recvmsg() buffer sizes.

Alexei provided an initial patch downsizing to SKB_WITH_OVERHEAD(16384)

Fixes: 9063e21fb026 ("netlink: autosize skb lengthes")
Signed-off-by: Eric Dumazet 
Reported-by: Alexei Starovoitov 
Cc: Greg Thelen 
Reviewed-by: Greg Rose 
Acked-by: Alexei Starovoitov 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

netlink: Fix dump skb leak/double free

2016-06-24T17:18:16+00:00

[ Upstream commit 92964c79b357efd980812c4de5c1fd2ec8bb5520 ]

When we free cb->skb after a dump, we do it after releasing the
lock.  This means that a new dump could have started in the time
being and we'll end up freeing their skb instead of ours.

This patch saves the skb and module before we unlock so we free
the right memory.

Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.")
Reported-by: Baozeng Ding 
Signed-off-by: Herbert Xu 
Acked-by: Cong Wang 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

netlink: don't send NETLINK_URELEASE for unbound sockets

2016-05-04T21:48:45+00:00

commit e27260203912b40751fa353d009eaa5a642c739f upstream.

All existing users of NETLINK_URELEASE use it to clean up resources that
were previously allocated to a socket via some command. As a result, no
users require getting this notification for unbound sockets.

Sending it for unbound sockets, however, is a problem because any user
(including unprivileged users) can create a socket that uses the same ID
as an existing socket. Binding this new socket will fail, but if the
NETLINK_URELEASE notification is generated for such sockets, the users
thereof will be tricked into thinking the socket that they allocated the
resources for is closed.

In the nl80211 case, this will cause destruction of virtual interfaces
that still belong to an existing hostapd process; this is the case that
Dmitry noticed. In the NFC case, it will cause a poll abort. In the case
of netlink log/queue it will cause them to stop reporting events, as if
NFULNL_CFG_CMD_UNBIND/NFQNL_CFG_CMD_UNBIND had been called.

Fix this problem by checking that the socket is bound before generating
the NETLINK_URELEASE notification.

Signed-off-by: Dmitry Ivanov 
Signed-off-by: Johannes Berg 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

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

2015-11-07T01:50:42+00:00

__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 
Acked-by: Vlastimil Babka 
Acked-by: Michal Hocko 
Acked-by: Johannes Weiner 
Cc: Christoph Lameter 
Cc: David Rientjes 
Cc: Vitaly Wool 
Cc: Rik van Riel 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2015-10-24T13:54:12+00:00

Conflicts:
	net/ipv6/xfrm6_output.c
	net/openvswitch/flow_netlink.c
	net/openvswitch/vport-gre.c
	net/openvswitch/vport-vxlan.c
	net/openvswitch/vport.c
	net/openvswitch/vport.h

The openvswitch conflicts were overlapping changes.  One was
the egress tunnel info fix in 'net' and the other was the
vport ->send() op simplification in 'net-next'.

The xfrm6_output.c conflicts was also a simplification
overlapping a bug fix.

Signed-off-by: David S. Miller

netlink: fix locking around NETLINK_LIST_MEMBERSHIPS

2015-10-22T14:18:28+00:00

Currently, NETLINK_LIST_MEMBERSHIPS grabs the netlink table while copying
the membership state to user-space. However, grabing the netlink table is
effectively a write_lock_irq(), and as such we should not be triggering
page-faults in the critical section.

This can be easily reproduced by the following snippet:
    int s = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
    void *p = mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0);
    int r = getsockopt(s, 0x10e, 9, p, (void*)((char*)p + 4092));

This should work just fine, but currently triggers EFAULT and a possible
WARN_ON below handle_mm_fault().

Fix this by reducing locking of NETLINK_LIST_MEMBERSHIPS to a read-side
lock. The write-lock was overkill in the first place, and the read-lock
allows page-faults just fine.

Reported-by: Dmitry Vyukov 
Signed-off-by: David Herrmann 
Signed-off-by: David S. Miller