All bus drivers do device setup themselves. This requires us to adjust all
of them if we introduce new core features. Thus, merge all these into a
uniform drm_dev_register() helper.
Note that this removes the drm_lastclose() error path for AGP as it is
horribly broken. Moreover, no bus driver called this in any other error
path either. Instead, we use the recently introduced AGP cleanup helpers.
We also keep a DRIVER_MODESET condition around pci_set_drvdata() to keep
semantics.
[airlied: keep passing flags through so drivers don't oops on load]
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Add hwmod data for High Speed USB host and TLL modules
CC: Paul Walmsley <paul@pwsan.com>
Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
This patch adds Synchronous Serial Interface (SSI) hwmod support for
OMAP34xx SoCs.
Signed-off-by: Sebastian Reichel <sre@debian.org>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Paul Walmsley <paul@pwsan.com>
The hwmod init sequence involves initializing and idling all the
hwmods during bootup. If a module class has sysconfig, the init
sequence utilizes the module register base for performing any
sysc configuration.
The module address space is being removed from hwmod database and
retrieved from the <reg> property of the corresponding DT node.
If a hwmod does not have its corresponding DT node defined and the
memory address space is not defined in the corresponding
omap_hwmod_ocp_if, then the module register target address space
would be NULL and any sysc programming would result in a NULL
pointer dereference and a kernel boot hang.
Handle this scenario by checking for a valid module address space
during the _init of each hwmod, and leaving it in the registered
state if no module register address base is defined in either of
the hwmod data or the DT data.
Signed-off-by: Suman Anna <s-anna@ti.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Tested-by: Nishanth Menon <nm@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
[paul@pwsan.com: use -ENXIO rather than -ENOMEM to indicate a missing address
space error; fixed checkpatch.pl problem]
Signed-off-by: Paul Walmsley <paul@pwsan.com>
Instead of managing device allocation+initialization in each bus-driver,
we should do that in a central place. drm_fill_in_dev() already does most
of it, but also requires the global drm lock for partial AGP device
registration.
Split both apart so we have a clean device initialization/allocation
phase, and a registration phase.
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
All drivers embed gem-objects into their own buffer objects. There is no
reason to keep drm_gem_object_alloc(), gem->driver_private and
->gem_init_object() anymore.
New drivers are highly encouraged to do the same. There is no benefit in
allocating gem-objects separately.
Cc: Dave Airlie <airlied@gmail.com>
Cc: Alex Deucher <alexdeucher@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Inki Dae <inki.dae@samsung.com>
Cc: Ben Skeggs <skeggsb@gmail.com>
Cc: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
There is no reason to keep the gem object separately allocated. nouveau is
the last user of gem_obj->driver_private, so if we embed it, we can get
rid of 8bytes per gem-object.
The implementation follows the radeon driver. bo->gem is only valid, iff
the bo was created via the gem helpers _and_ iff the user holds a valid
gem reference. That is, as the gem object holds a reference to the
nouveau_bo. If you use nouveau_ref() to gain a bo reference, you are not
guaranteed to also hold a gem reference. The gem object might get
destroyed after the last user drops the gem-ref via
drm_gem_object_unreference(). Use drm_gem_object_reference() to gain a
gem-reference.
For debugging, we can use bo->gem.filp != NULL to test whether a gem-bo is
valid. However, this shouldn't be used for real functionality to avoid
gem-internal dependencies.
Note that the implementation follows the previous style. However, we no
longer can check for bo->gem != NULL to test for a valid gem object. This
wasn't done before, so we should be safe now.
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This will enable intel_powerclamp driver on newer Intel CPUs
including some Ivy Bridge and Haswell processors.
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
TCP listener refactoring, part 4 :
To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common
Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.
Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).
inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6
This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.
inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr
And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.
We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch
* adds missing kfree() for cpu_clamping_mask
* adds return value checking for alloc_percpu()
* unregister hotcpu notifier in exit path
Signed-off-by: Durgadoss R <durgadoss.r@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
TCP listener refactoring, part 3 :
Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.
Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.
As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.
If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.
[ INET_TW_MATCH() is no longer needed ]
I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()
This way, SYN_RECV pseudo sockets will be supported the same.
A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].
Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()
Before patch :
dmesg | grep "TCP established"
TCP established hash table entries: 524288 (order: 11, 8388608 bytes)
After patch :
TCP established hash table entries: 524288 (order: 10, 4194304 bytes)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Conflicts:
include/linux/netdevice.h
net/core/sock.c
Trivial merge issues.
Removal of "extern" for functions declaration in netdevice.h
at the same time "const" was added to an argument.
Two parallel line additions in net/core/sock.c
Signed-off-by: David S. Miller <davem@davemloft.net>
Ben Hutchings says:
====================
Some more fixes for EF10 support; hopefully the last lot:
1. Fixes for reading statistics, from Edward Cree and Jon Cooper.
2. Addition of ethtool statistics for packets dropped by the hardware
before they were associated with a specific function, from Edward Cree.
3. Only bind to functions that are in control of their associated port,
as the driver currently assumes this is the case.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Steinar reported FQ pacing was not working for UDP flows.
It looks like the initial sk->sk_pacing_rate value of 0 was
a wrong choice. We should init it to ~0U (unlimited)
Then, TCA_FQ_FLOW_DEFAULT_RATE should be removed because it makes
no real sense. The default rate is really unlimited, and we
need to avoid a zero divide.
Reported-by: Steinar H. Gunderson <sesse@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 612c337306.
As per Stephen Hemminger, the layout of the netlink attribute
is not implemented correctly so revert this for now.
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently we get the following errors on imx51-babbage:
/display@di0: could not find display-timings node
/display@di0: no timings specified
/display@di1: could not find display-timings node
/display@di1: no timings specified
imx-drm imx-drm: failed to allocate buffer with size 0
Provide timing values for IPU1, which is connected to a DVI bridge and
to IPU2, which can be connected to the WVGA panel, so that both of them can
be functional.
While at it, disable the WVGA panel, so that DVI output becomes the default one.
Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
The e-mail address rjw@sisk.pl that I have been using for quite some
time is going to expire at one point, so replace it with a new one,
rjw@rjwysocki.net, everywhere in MAINTAINERS and Documentation/ABI.
Signed-off-by: Rafael J. Wysocki <rjw@rjwysocki.net>
The xfs_inactive() return value is meaningless. Turn xfs_inactive()
into a void function and clean up the error handling appropriately.
Kill the VN_INACTIVE_[NO]CACHE directives as they are not relevant
to Linux.
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
Push the inode free work performed during xfs_inactive() down into
a new xfs_inactive_ifree() helper. This clears xfs_inactive() from
all inode locking and transaction management more directly
associated with freeing the inode xattrs, extents and the inode
itself.
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
Currently the qconf program invoked by 'make xconfig' stores GUI
settings in the file ~/.config/Unknown\ Organization.conf. This name
is apparently generated by the QSettings class when no organisation
or application name are specified.
This is obviously not a sensible filename (nor does it seem sensible
that these QSettings parameters are optional!). Pass the names
'kernel.org' and 'qconf', resuling in the filename
~/.config/kernel.org/qconf.conf.
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Reviewed-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
Tested-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
Signed-off-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
The struct gstr has a capacity that may differ from the actual string length.
However, a string manipulation in the function search_conf made the assumption
that it is the same, which led to messing up some search results, especially
when the content of the gstr in use had not yet reached at least 63 chars.
Signed-off-by: Martin Walch <walch.martin@web.de>
Acked-by: Wang YanQing <udknight@gmail.com>
Acked-by: Benjamin Poirier <bpoirier@suse.de>
Reviewed-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
Signed-off-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
The definition ws [ \n\t] is not used anywhere. Drop it to avoid confusion.
As it is a dead definition, any changes in the resulting code generated by
flex would be surprising (actually testing this showed that there are really
no changes). So, there is no need to touch the existing zconf.lex.c_shipped.
Signed-off-by: Martin Walch <walch.martin@web.de>
Reviewed-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
Signed-off-by: "Yann E. MORIN: <yann.morin.1998@free.fr>
Each symbol must have exactly one type assigned. However, if a symbol happens
to have two different types assigned at runtime, a warning is printed and the
first type is preserved while the second type is being ignored.
The warning message says
type of <symbol name> redefined from <first type> to <second type>
which may be misleading as it may create the impression that the second type
replaces the first type.
This patch clarifies this by changing the warning to
ignoring type redefinition of <symbol name> from <first type> to <second type>
Signed-off-by: Martin Walch <walch.martin@web.de>
Acked-by: Wang YanQing <udknight@gmail.com>
Reviewed-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
Signed-off-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
This fixes lots of typos in comments and strings.
It also updates the documentation strings in mconf to reflect the changes in
the user interface from the two commits
6364fd0cb1
menuconfig: Add Save/Load buttons
1bdbac478a
menuconfig: Get rid of the top-level entries for "Load an Alternate/Save an Alternate"
And it updates the layout of the example search result, i. e. moves down the
"Defined at" and "Depends on" lines and adds a symbol state ([=n]) to the
symbol in the "Selected by" line.
Furthermore, the help texts now should fit in 80 columns again when viewed
in mconf.
Signed-off-by: Martin Walch <walch.martin@web.de>
Reviewed-by: Jean Delvare <jdelvare@suse.de>
Reviewed-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
replace the question mark in the comment after SYMBOL_WRITE with an explanation
Signed-off-by: Martin Walch <walch.martin@web.de>
Signed-off-by: "Yann E. MORIN" <yann.morin.1998@free.fr>
OMAP5 ES1.0 was intended as a test chip and has major register level
differences w.r.t ES2.0 revision of the chip. All register defines,
dts support has been solely added for ES2.0 version of the chip.
Further, all ES1.0 chips and platforms are supposed to have been
removed from circulation. Hence, there is no need to further retain
any resemblence of ES1.0 support in id detection code.
Remove the omap_revision handling and BUG() instead to prevent folks
who mistakenly try an older unsupported chip and report bogus errors.
Signed-off-by: Nishanth Menon <nm@ti.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
The real time counter also called master counter, is a free-running
counter. It produces the count used by the CPU local timer peripherals
in the MPU cluster. The timer counts at a rate of 6.144 MHz.
The ratio registers are missing for a sys-clk of 20MHZ which is used
by DRA7 socs. So because of this, the counter was getting wrongly
programmed for a sys-clk of 38.4Mhz(default). So adding the ratio
registers for 20MHZ sys-clk.
Tested-by: Nishanth Menon <nm@ti.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Signed-off-by: Sricharan R <r.sricharan@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Move omap_vout device creation inside the omap_display_init so that we can
correctly create the device based on the presence of omapdss within the
platform.
For example, on a kernel image supporting multiple platforms, omap_init_vout
will create a omapdrm platform device on a AM33xx platform even though it
doesn't have a DSS block.
Signed-off-by: Archit Taneja <archit@ti.com>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Move omapfb and omapvrfb device creation inside the omap_display_init so that
we can correctly create the device based on the presence of omapdss within the
platform.
For example, on a kernel image supporting multiple platforms, omap_init_vrfb and
omap_init_fb will create omapvrfb and omapfb platform devices respectively on a
AM33xx platform even though it doesn't have a VRFB or DSS block.
Signed-off-by: Archit Taneja <archit@ti.com>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Move omapdrm device creation inside the omap_display_init so that we can
correctly create the device based on the presence of omapdss within the
platform.
For example, on a kernel image supporting multiple platforms, omap_init_drm
will create a omapdrm platform device on a AM33xx platform even though it
doesn't have a DSS block.
Originally worked on by Andy Gross.
Cc: Andy Gross <andygro@gmail.com>
Signed-off-by: Archit Taneja <archit@ti.com>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
DMM exists on omap4+ platforms, these platforms are always expected to boot with
DT. Remove the current method of searching the dmm hwmod and building an
omap_device for dmm.
For OMAP4, the address and irq data for DMM hwmod(along with other blocks) were
removed, so the current method fails in the dmm driver's probe anyway.
The addition of DMM nodes in DT will ensure that a DMM device is built
correctly.
Cc: Andy Gross <andygro@gmail.com>
Signed-off-by: Archit Taneja <archit@ti.com>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Add the missing destroy_workqueue() before return from
qlcnic_probe() in the error handling case.
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fix the error handling in moxart_mac_probe():
- return -ENOMEM in some memory alloc fail cases
- add missing free_netdev() in the error handling case
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes the calculation of the nlmsg size, by adding the missing
nla_total_size().
Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCA_FQ_INITIAL_QUANTUM should set q->initial_quantum
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Unlike ipv4, the struct member hlen holds the length of the GRE and ipv6
headers. This length is also counted in dev->hard_header_len.
Perhaps, it's more clean to modify the hlen to count only the GRE header
without ipv6 header as the variable name suggest, but the simple way to fix
this without regression risk is simply modify the calculation of the limit
in ip6gre_tunnel_change_mtu function.
Verified in kernel version v3.11.
Signed-off-by: Oussama Ghorbel <ou.ghorbel@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Create the new xfs_inactive_truncate() function to handle the
truncate portion of xfs_inactive(). Push the locking and
transaction management into the new function.
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
We can get classid through cgroup_subsys_state,
this is directviewing and effective.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since the tasks have been migrated to the cgroup,
there is no need to call task_netprioidx to get
task's cgroup id.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The since the removal of the routing cache computing
fib_compute_spec_dst() does a fib_table lookup for each UDP multicast
packet received. This has introduced a performance regression for some
UDP workloads.
This change skips populating the packet info for sockets that do not have
IP_PKTINFO set.
Benchmark results from a netperf UDP_RR test:
Before 89789.68 transactions/s
After 90587.62 transactions/s
Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.63us RTT
After 12.48us RTT
Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The removal of the routing cache introduced a performance regression for
some UDP workloads since a dst lookup must be done for each packet.
This change caches the dst per socket in a similar manner to what we do
for TCP by implementing early_demux.
For UDP multicast we can only cache the dst if there is only one
receiving socket on the host. Since caching only works when there is
one receiving socket we do the multicast socket lookup using RCU.
For UDP unicast we only demux sockets with an exact match in order to
not break forwarding setups. Additionally since the hash chains may be
long we only check the first socket to see if it is a match and not
waste extra time searching the whole chain when we might not find an
exact match.
Benchmark results from a netperf UDP_RR test:
Before 87961.22 transactions/s
After 89789.68 transactions/s
Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.97us RTT
After 12.63us RTT
Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
UDP sockets can receive packets from multiple endpoints and thus may be
received on multiple receive queues. Since packets packets can arrive
on multiple receive queues we should not mark the napi_id for all
packets. This makes busy read/poll only work for connected UDP sockets.
This additionally enables busy read/poll for UDP multicast packets as
long as the socket is connected by moving the check into
__udp_queue_rcv_skb().
Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
qdisc_tree_decrease_qlen() is called when some packets are dropped
on a qdisc, and we want to notify parents of qlen changes.
We also can increment parents qdisc qstats drop counters.
This permits more accurate drop counters up to root qdisc.
For example a graft operation typically resets a qdisc
(drops all packets) and call qdisc_tree_decrease_qlen()
Note that callers are responsible for their drop counters.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a guest is destroyed without transitioning its frontend to CLOSED,
the domain becomes a zombie as netback was not grant unmapping the
shared rings.
When removing a VIF, transition the backend to CLOSED so the VIF is
disconnected if necessary (which will unmap the shared rings etc).
This fixes a regression introduced by
279f438e36 (xen-netback: Don't destroy
the netdev until the vif is shut down).
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Paul Durrant <Paul.Durrant@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Amir Vadai says:
====================
net/mlx4_en: Fix pages never dma unmapped on rx
This patchset fixes a bug introduced by commit 51151a16 (mlx4: allow order-0
memory allocations in RX path). Where dma_unmap_page wasn't called.
Changes from V0:
- Added "Rename name of mlx4_en_rx_alloc members". Old names were confusing.
- Last frag in page calculation was wrong. Since all frags in page are of the
same size, need to add this frag_stride to end of frag offset, and not the
size of next frag in skb.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes a bug introduced by commit 51151a16 (mlx4: allow
order-0 memory allocations in RX path).
dma_unmap_page never reached because condition to detect last fragment
in page is wrong. offset+frag_stride can't be greater than size, need to
make sure no additional frag will fit in page => compare offset +
frag_stride + next_frag_size instead.
next_frag_size is the same as the current one, since page is shared only
with frags of the same size.
CC: Eric Dumazet <edumazet@google.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
