Samuel Ortiz says:
====================
NFC: 4.1 pull request
This is the NFC pull request for 4.1.
This is a shorter one than usual, as the Intel Field Peak NFC
driver could not make it in time.
We have:
- A new driver for NXP NCI based chipsets, like e.g. the NPC100 or
the PN7150. It currently only supports an i2c physical layer, but
could easily be extended to work on top of e.g. SPI.
This driver also includes support for user space triggered firmware
updates.
- A few minor st21nfc[ab] fixes, cleanups, and comments improvements.
- A pn533 error return fix.
- A few NFC related logs formatting cleanups.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The PCI Firmware Specification, r3.0, sec 4.6.4.1.3, defines a single UUID
for an ACPI _DSM method to provide device-specific control functions. This
_DSM method support several functions, including PCI Express Slot
Information, PCI Express Slot Number, PCI Bus Capabilities, etc.
Move the UUID definition from pci/pci-label.c, where it could be used only
for one function, to pci/pci-acpi.c where it can be shared for all these
functions.
[bhelgaas: changelog]
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
In the media drivers, the v4l2 core knows about all submodules
and calls into them from a common function. However this cannot
work if the modules that get called are loadable and the
core is built-in. In that case we get
drivers/built-in.o: In function `set_type':
drivers/media/v4l2-core/tuner-core.c:301: undefined reference to `tea5767_attach'
drivers/media/v4l2-core/tuner-core.c:307: undefined reference to `tea5761_attach'
drivers/media/v4l2-core/tuner-core.c:349: undefined reference to `tda9887_attach'
drivers/media/v4l2-core/tuner-core.c:405: undefined reference to `xc4000_attach'
This was working previously, until the IS_ENABLED() macro was used
to replace the construct like
#if defined(CONFIG_DVB_CX24110) || (defined(CONFIG_DVB_CX24110_MODULE) && defined(MODULE))
with the difference that the new code no longer checks whether it is being
built as a loadable module itself.
To fix this, this new patch adds an 'IS_REACHABLE' macro, which evaluates
true in exactly the condition that was used previously. The downside
of this is that this trades an obvious link error for a more subtle
runtime failure, but it is clear that the change that introduced the
link error was unintentional and it seems better to revert it for
now. Also, a similar change was originally created by Trent Piepho
and then reverted by teh change to the IS_ENABLED macro.
Ideally Kconfig would be used to avoid the case of a broken dependency,
or the code restructured in a way to turn around the dependency, but either
way would require much larger changes here.
Fixes: 7b34be71db ("[media] use IS_ENABLED() macro")
See-also: c5dec9fb24 ("V4L/DVB (4751): Fix DBV_FE_CUSTOMISE for card drivers compiled into kernel")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
SCSI transport drivers and SCSI LLDs block a SCSI device if the
transport layer is not operational. This means that in this state
no requests should be processed, even if the REQ_PREEMPT flag has
been set. This patch avoids that a rescan shortly after a cable
pull sporadically triggers the following kernel oops:
BUG: unable to handle kernel paging request at ffffc9001a6bc084
IP: [<ffffffffa04e08f2>] mlx4_ib_post_send+0xd2/0xb30 [mlx4_ib]
Process rescan-scsi-bus (pid: 9241, threadinfo ffff88053484a000, task ffff880534aae100)
Call Trace:
[<ffffffffa0718135>] srp_post_send+0x65/0x70 [ib_srp]
[<ffffffffa071b9df>] srp_queuecommand+0x1cf/0x3e0 [ib_srp]
[<ffffffffa0001ff1>] scsi_dispatch_cmd+0x101/0x280 [scsi_mod]
[<ffffffffa0009ad1>] scsi_request_fn+0x411/0x4d0 [scsi_mod]
[<ffffffff81223b37>] __blk_run_queue+0x27/0x30
[<ffffffff8122a8d2>] blk_execute_rq_nowait+0x82/0x110
[<ffffffff8122a9c2>] blk_execute_rq+0x62/0xf0
[<ffffffffa000b0e8>] scsi_execute+0xe8/0x190 [scsi_mod]
[<ffffffffa000b2f3>] scsi_execute_req+0xa3/0x130 [scsi_mod]
[<ffffffffa000c1aa>] scsi_probe_lun+0x17a/0x450 [scsi_mod]
[<ffffffffa000ce86>] scsi_probe_and_add_lun+0x156/0x480 [scsi_mod]
[<ffffffffa000dc2f>] __scsi_scan_target+0xdf/0x1f0 [scsi_mod]
[<ffffffffa000dfa3>] scsi_scan_host_selected+0x183/0x1c0 [scsi_mod]
[<ffffffffa000edfb>] scsi_scan+0xdb/0xe0 [scsi_mod]
[<ffffffffa000ee13>] store_scan+0x13/0x20 [scsi_mod]
[<ffffffff811c8d9b>] sysfs_write_file+0xcb/0x160
[<ffffffff811589de>] vfs_write+0xce/0x140
[<ffffffff81158b53>] sys_write+0x53/0xa0
[<ffffffff81464592>] system_call_fastpath+0x16/0x1b
[<00007f611c9d9300>] 0x7f611c9d92ff
Reported-by: Max Gurtuvoy <maxg@mellanox.com>
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Mike Christie <michaelc@cs.wisc.edu>
Cc: <stable@vger.kernel.org>
Signed-off-by: James Bottomley <JBottomley@Odin.com>
Add an userdata set extension and allow the user to attach arbitrary
data to set elements. This is intended to hold TLV encoded data like
comments or DNS annotations that have no meaning to the kernel.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Add a new "dynset" expression for dynamic set updates.
A new set op ->update() is added which, for non existant elements,
invokes an initialization callback and inserts the new element.
For both new or existing elements the extenstion pointer is returned
to the caller to optionally perform timer updates or other actions.
Element removal is not supported so far, however that seems to be a
rather exotic need and can be added later on.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Currently a set binding is assumed to be related to a lookup and, in
case of maps, a data load.
In order to use bindings for set updates, the loop detection checks
must be restricted to map operations only. Add a flags member to the
binding struct to hold the set "action" flags such as NFT_SET_MAP,
and perform loop detection based on these.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Use atomic operations for the element count to avoid races with async
updates.
To properly handle the transactional semantics during netlink updates,
deleted but not yet committed elements are accounted for seperately and
are treated as being already removed. This means for the duration of
a netlink transaction, the limit might be exceeded by the amount of
elements deleted. Set implementations must be prepared to handle this.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Enums used by tracepoints for __print_symbolic() are shown in the
tracepoint format files with just their names and not their values.
This makes it difficult for user space tools to know how to convert the
binary data into their string representations.
By adding the use of TRACE_DEFINE_ENUM(), the enum names will be mapped
to their values and shown in the tracing file system to let tools
convert the data as necessary.
Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org
Acked-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
nf_bridge_info->mask is used for several things, for example to
remember if skb->pkt_type was set to OTHER_HOST.
For a bridge, OTHER_HOST is expected case. For ip forward its a non-starter
though -- routing expects PACKET_HOST.
Bridge netfilter thus changes OTHER_HOST to PACKET_HOST before hook
invocation and then un-does it after hook traversal.
This information is irrelevant outside of br_netfilter.
After this change, ->mask now only contains flags that need to be
known outside of br_netfilter in fast-path.
Future patch changes mask into a 2bit state field in sk_buff, so that
we can remove skb->nf_bridge pointer for good and consider all remaining
places that access nf_bridge info content a not-so fastpath.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
->mask is a bit info field that mixes various use cases.
In particular, we have flags that are mutually exlusive, and flags that
are only used within br_netfilter while others need to be exposed to
other parts of the kernel.
Remove BRNF_8021Q/PPPoE flags. They're mutually exclusive and only
needed within br_netfilter context.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
right now we store this in the nf_bridge_info struct, accessible
via skb->nf_bridge. This patch prepares removal of this pointer from skb:
Instead of using skb->nf_bridge->x, we use helpers to obtain the in/out
device (or ifindexes).
Followup patches to netfilter will then allow nf_bridge_info to be
obtained by a call into the br_netfilter core, rather than keeping a
pointer to it in sk_buff.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
br_netfilter maintains an extra state, nf_bridge_info, which is attached
to skb via skb->nf_bridge pointer.
Amongst other things we use skb->nf_bridge->data to store the original
mac header for every processed skb.
This is required for ip refragmentation when using conntrack
on top of bridge, because ip_fragment doesn't copy it from original skb.
However there is no need anymore to do this unconditionally.
Move this to the one place where its needed -- when br_netfilter calls
ip_fragment().
Also switch to percpu storage for this so we can handle fragmenting
without accessing nf_bridge meta data.
Only user left is neigh resolution when DNAT is detected, to hold
the original source mac address (neigh resolution builds new mac header
using bridge mac), so rename ->data and reduce its size to whats needed.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The enums used in tracepoints with __print_symbolic() have their
names shown in the tracepoint format files and not their values.
This makes it difficult for user space tools to convert the binary
data to the strings as user space does not know what those enums
are about.
By having them use TRACE_DEFINE_ENUM(), the names of the enums will
be mapped to the values and shown to user space.
Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Several tracepoints use the helper functions __print_symbolic() or
__print_flags() and pass in enums that do the mapping between the
binary data stored and the value to print. This works well for reading
the ASCII trace files, but when the data is read via userspace tools
such as perf and trace-cmd, the conversion of the binary value to a
human string format is lost if an enum is used, as userspace does not
have access to what the ENUM is.
For example, the tracepoint trace_tlb_flush() has:
__print_symbolic(REC->reason,
{ TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" },
{ TLB_REMOTE_SHOOTDOWN, "remote shootdown" },
{ TLB_LOCAL_SHOOTDOWN, "local shootdown" },
{ TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" })
Which maps the enum values to the strings they represent. But perf and
trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would
not be able to map it.
With TRACE_DEFINE_ENUM(), developers can place these in the event header
files and ftrace will convert the enums to their values:
By adding:
TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH);
TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN);
TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN);
TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN);
$ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format
[...]
__print_symbolic(REC->reason,
{ 0, "flush on task switch" },
{ 1, "remote shootdown" },
{ 2, "local shootdown" },
{ 3, "local mm shootdown" })
The above is what userspace expects to see, and tools do not need to
be modified to parse them.
Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org
Cc: Guilherme Cox <cox@computer.org>
Cc: Tony Luck <tony.luck@gmail.com>
Cc: Xie XiuQi <xiexiuqi@huawei.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Normally the compiler will use the same pointer for a string throughout
the file. But there's no guarantee of that happening. Later changes will
require that all events have the same pointer to the system string.
Name the system string and have all events point to it.
Testing this, it did not increases the size of the text, except for the
notes section, which should not harm the real size any.
Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Currently, snd_hdac_power_up()/down() helpers checks whether the codec
is being in pm (suspend/resume), and skips the call of runtime get/put
during it. This is needed as there are lots of power up/down
sequences called in the paths that are also used in the PM itself. An
example is found in hda_codec.c::codec_exec_verb(), where this can
power up the codec while it may be called again in its power up
sequence, too.
The above works in most cases, but sometimes we really want to wait
for the real power up. For example, the control element get/put may
want explicit power up so that the value change is assured to reach to
the hardware. Using the current snd_hdac_power_up(), however,
results in a race, e.g. when it's called during the runtime suspend is
being performed. In the worst case, as found in patch_ca0132.c, it
can even lead to the deadlock because the code assumes the power up
while it was skipped due to the check above.
For dealing with such cases, this patch makes snd_hdac_power_up() and
_down() to two variants: with and without in_pm flag check. The
version with pm flag check is named as snd_hdac_power_up_pm() while
the version without pm flag check is still kept as
snd_hdac_power_up(). (Just because the usage of the former is fewer.)
Then finally, the patch replaces each call potentially done in PM with
the new _pm() variant.
In theory, we can implement a unified version -- if we can distinguish
the current context whether it's in the pm path. But such an
implementation is cumbersome, so leave the code like this a bit messy
way for now...
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=96271
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Everybody expects the error field in the struct mmc_command|data to be
and int but it's actually an unsigned int. Let's convert it into an int
to meet the expectations.
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
In the past the V4L2_DV_BT_STD_CEA861 standard bit was used to
determine whether the format is a CE (Consumer Electronics) format
or not. However, the 640x480p59.94 format is part of the CEA-861
standard, but it is *not* a CE video format.
Add a new flag to make this explicit. This information is needed
in order to determine the default R'G'B' encoding for the format:
for CE video this is limited range (16-235) instead of full range
(0-255).
The header with all the timings has been updated with this new
flag.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Martin Bugge <marbugge@cisco.com>
Cc: Mats Randgaard <mats.randgaard@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Create a new flag that represent controls which its value needs to be
passed to the driver even if it has not changed.
They typically represent actions, like triggering a flash or clearing an
error flag. So writing to such a control means some action is executed.
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
After reset, the CPU can change the BSP, which will be used upon INIT. Reset
should return the BSP which QEMU asked for, and therefore handled accordingly.
To quote: "If the MP protocol has completed and a BSP is chosen, subsequent
INITs (either to a specific processor or system wide) do not cause the MP
protocol to be repeated."
[Intel SDM 8.4.2: MP Initialization Protocol Requirements and Restrictions]
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Message-Id: <1427933438-12782-3-git-send-email-namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch updates iscsi/iser-target to add a new fabric_prot_type
TPG attribute for iser-target, used for controlling LLD level
protection into LIO when the backend device does not support T10-PI.
This is required for ib_isert to enable WRITE_STRIP + READ_INSERT
hardware offloads.
It's disabled by default and controls which se_sesion->sess_prot_type
are set at iscsi_target_locate_portal() session registration time.
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Martin Petersen <martin.petersen@oracle.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds a new target_core_fabric_ops callback for allowing fabric
drivers to expose a TPG attribute for signaling when a T10-PI protected
fabric wants to function with an un-protected device without T10-PI.
This specifically is to allow LIO to perform WRITE_STRIP + READ_INSERT
operations when functioning with non T10-PI enabled devices, seperate
from any available hw offloads the fabric supports.
This is done using a new se_sess->sess_prot_type that is set at fabric
session creation time based upon the TPG attribute. It currently cannot
be changed for individual sessions after initial creation.
Also, update existing target_core_sbc.c code to honor sess_prot_type when
setting up cmd->prot_op + cmd->prot_type assignments.
(Add unlikely and !! boolean conversion in sbc_check_prot - Sagi)
Cc: Martin Petersen <martin.petersen@oracle.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Doug Gilbert <dgilbert@interlog.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
drm/panel: Changes for v4.1-rc1
This set of changes adds support for a whole bunch of new panels, mostly
simple ones. There's now also support for panels to provide display
timings rather than fixed modes, which should allow panels to work with
a larger number of display drivers. Eventually drivers should migrate to
this new interface and the fixed modes removed from panels.
There are also a couple of sparse fixes for the PS8622 and PS8625 bridge
drivers.
* tag 'drm/panel/for-4.1-rc1' of git://anongit.freedesktop.org/tegra/linux:
drm/panel: Add support for Ampire AM-800480R3TMQW-A1H 800x480 7" panel
of: Add vendor prefix for Ampire Co., Ltd.
drm/panel: Add display timing for HannStar HSD070PWW1
drm/panel: simple: Add display timing support
drm/panel: Add display timing support
drm/panel: Add support for OrtusTech COM43H4M85ULC panel
of: Add vendor prefix for Ortus Technology Co., Ltd.
drm/panel: Add bus format for Giantplus GPG482739QS5 panel
drm/panel: simple: Add support for AUO b101ean01 panel
drm/panel: simple: Add support for Innolux ZJ070NA-01P
drm/panel: simple: Add support for Innolux AT043TN24
drm/panel: simple: Add support for Shelly SCA07010-BFN-LNN
drm/panel: simple: Add support for Samsung LTN140AT29 panel
drm: Remove unused DRM_MODE_OBJECT_BRIDGE
drm/bridge: ptn3460: Fix sparse warnings
drm/bridge: ps8622: Fix sparse warnings
drm/bridge: Add I2C based driver for ps8622/ps8625 bridge
drm/tegra: Changes for v4.1-rc1
Perhaps the most noteworthy change in this set is the implementation of
a hardware VBLANK counter using host1x syncpoints. The SOR registers can
now be dumped via debugfs, which can be useful while debugging. The IOVA
address space maintained by the driver can also be dumped via debugfs.
Other than than, these changes are mostly cleanup work, such as making
register names more consistent or removing unused code (that was left
over after the atomic mode-setting conversion). There's also a fix for
eDP that makes the driver cope with firmware that already initialized
the display (such as the firmware on the Tegra-based Chromebooks).
* tag 'drm/tegra/for-4.1-rc1' of git://anongit.freedesktop.org/tegra/linux:
drm/tegra: sor: Reset during initialization
drm/tegra: gem: Return 64-bit offset for mmap(2)
drm/tegra: hdmi: Name register fields consistently
drm/tegra: hdmi: Resets are synchronous
drm/tegra: dc: Document tegra_dc_state_setup_clock()
drm/tegra: dc: Remove unused callbacks
drm/tegra: dc: Remove unused function
drm/tegra: dc: Use base atomic state helpers
drm/atomic: Add helpers for state-subclassing drivers
drm/tegra: dc: Implement hardware VBLANK counter
gpu: host1x: Export host1x_syncpt_read()
drm/tegra: sor: Dump registers via debugfs
drm/tegra: sor: Registers are 32-bit
drm/tegra: Provide debugfs file for the IOVA space
drm/tegra: dc: Check for valid parent clock
This adds support for the extended metadata formats through the submit
IO ioctl, and simplifies the rest when using a separate metadata format.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull media updates from Mauro Carvalho Chehab:
"A series of fixup patches for version 4.0:
- one VB2 core fixup, when stopping the stream;
- one VB2 core fixup for dma-contig memory type;
- driver fixes at rtl28xx, s5p (tv, jpeg, mfc, soc-camera, sh_veu,
cx23885, gspca"
* tag 'media/v3.20-2' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-media:
[media] rtl28xxu: return success for unimplemented FE callback
[media] rtl2832: disable regmap register cache
[media] vb2: Fix dma_dir setting for dma-contig mem type
[media] media: s5p-mfc: fix broken pointer cast on 64bit arch
[media] media: s5p-mfc: fix mmap support for 64bit arch
[media] cx23885: fix querycap
[media] sh_veu: v4l2_dev wasn't set
[media] s5p-mfc: Fix NULL pointer dereference caused by not set q->lock
[media] s5p-jpeg: exynos3250: fix erroneous reset procedure
[media] s5p-tv: hdmi needs I2C support
[media] s5p-jpeg: Initialize cb and cr to zero
[media] media: fix gspca drivers build dependencies
[media] soc-camera: Fix devm_kfree() in soc_of_bind()
[media] media: atmel-isi: increase the burst length to improve the performance
[media] vb2: fix 'UNBALANCED' warnings when calling vb2_thread_stop()
dmapool uses struct device in function arguments but relies on an
implicit inclusion to declare struct device causing warnings in some
configurations:
include/linux/dmapool.h:31:7: warning: 'struct device' declared inside parameter list
Fix this by adding a struct device declaration to the file.
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Huang Ying reported the following problem due to commit 3484b2de94 ("mm:
rearrange zone fields into read-only, page alloc, statistics and page
reclaim lines") from the Intel performance tests
24b7e5819a3484b2de94
---------------- --------------------------
%stddev %change %stddev
\ | \
152288 \261 0% -46.2% 81911 \261 0% aim7.jobs-per-min
237 \261 0% +85.6% 440 \261 0% aim7.time.elapsed_time
237 \261 0% +85.6% 440 \261 0% aim7.time.elapsed_time.max
25026 \261 0% +70.7% 42712 \261 0% aim7.time.system_time
2186645 \261 5% +32.0% 2885949 \261 4% aim7.time.voluntary_context_switches
4576561 \261 1% +24.9% 5715773 \261 0% aim7.time.involuntary_context_switches
The problem is specific to very large machines under stress. It was not
reproducible with the machines I had used to justify the original patch
because large numbers of CPUs are required. When pressure is high enough,
the cache line is bouncing between CPUs trying to acquire the lock and the
holder of the lock adjusting free lists. The intention was that the
acquirer of the lock would automatically have the cache line holding the
free lists but according to Huang, this is not a universal win.
One possibility is to move the zone lock to its own cache line but it
increases the size of the zone. This patch moves the lock to the other
end of the free lists where they do not contend under high pressure. It
does mean the page allocator paths now require more cache lines but Huang
reports that it restores performance to previous levels on large machines
%stddev %change %stddev
\ | \
84568 \261 1% +94.3% 164280 \261 1% aim7.jobs-per-min
2881944 \261 2% -35.1% 1870386 \261 8% aim7.time.voluntary_context_switches
681 \261 1% -3.4% 658 \261 0% aim7.time.user_time
5538139 \261 0% -12.1% 4867884 \261 0% aim7.time.involuntary_context_switches
44174 \261 1% -46.0% 23848 \261 1% aim7.time.system_time
426 \261 1% -48.4% 219 \261 1% aim7.time.elapsed_time
426 \261 1% -48.4% 219 \261 1% aim7.time.elapsed_time.max
468 \261 1% -43.1% 266 \261 2% uptime.boot
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Huang Ying <ying.huang@intel.com>
Tested-by: Huang Ying <ying.huang@intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fast Open has been using an experimental option with a magic number
(RFC6994). This patch makes the client by default use the RFC7413
option (34) to get and send Fast Open cookies. This patch makes
the client solicit cookies from a given server first with the
RFC7413 option. If that fails to elicit a cookie, then it tries
the RFC6994 experimental option. If that also fails, it uses the
RFC7413 option on all subsequent connect attempts. If the server
returns a Fast Open cookie then the client caches the form of the
option that successfully elicited a cookie, and uses that form on
later connects when it presents that cookie.
The idea is to gradually obsolete the use of experimental options as
the servers and clients upgrade, while keeping the interoperability
meanwhile.
Signed-off-by: Daniel Lee <Longinus00@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fast Open has been using the experimental option with a magic number
(RFC6994) to request and grant Fast Open cookies. This patch enables
the server to support the official IANA option 34 in RFC7413 in
addition.
The change has passed all existing Fast Open tests with both
old and new options at Google.
Signed-off-by: Daniel Lee <Longinus00@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Also move 'group' description to match the order of the net_device structure.
Fixes: 7a66bbc96c ("net: remove iflink field from struct net_device")
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With this patch, netns ids that are created and deleted are advertised into the
group RTNLGRP_NSID.
Because callers of rtnl_net_notifyid() already know the id of the peer, there is
no need to call __peernet2id() in rtnl_net_fill().
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since Bluetooth 4.1 there are two additional values for SSP OOB data,
namely C-256 and R-256. This patch updates the EIR definitions to take
into account both the 192 and 256 bit variants of C and R.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
That was we can make sure the output path of ipv4/ipv6 operate on
the UDP socket rather than whatever random thing happens to be in
skb->sk.
Based upon a patch by Jiri Pirko.
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
On the output paths in particular, we have to sometimes deal with two
socket contexts. First, and usually skb->sk, is the local socket that
generated the frame.
And second, is potentially the socket used to control a tunneling
socket, such as one the encapsulates using UDP.
We do not want to disassociate skb->sk when encapsulating in order
to fix this, because that would break socket memory accounting.
The most extreme case where this can cause huge problems is an
AF_PACKET socket transmitting over a vxlan device. We hit code
paths doing checks that assume they are dealing with an ipv4
socket, but are actually operating upon the AF_PACKET one.
Signed-off-by: David S. Miller <davem@davemloft.net>
