| Age | Commit message (Collapse) | Author |
|---|
|
skb->head is currently allocated from kmalloc(). This is convenient but
has the drawback the data cannot be converted to a page fragment if
needed.
We have three spots were it hurts :
1) GRO aggregation
When a linear skb must be appended to another skb, GRO uses the
frag_list fallback, very inefficient since we keep all struct sk_buff
around. So drivers enabling GRO but delivering linear skbs to network
stack aren't enabling full GRO power.
2) splice(socket -> pipe).
We must copy the linear part to a page fragment.
This kind of defeats splice() purpose (zero copy claim)
3) TCP coalescing.
Recently introduced, this permits to group several contiguous segments
into a single skb. This shortens queue lengths and save kernel memory,
and greatly reduce probabilities of TCP collapses. This coalescing
doesnt work on linear skbs (or we would need to copy data, this would be
too slow)
Given all these issues, the following patch introduces the possibility
of having skb->head be a fragment in itself. We use a new skb flag,
skb->head_frag to carry this information.
build_skb() is changed to accept a frag_size argument. Drivers willing
to provide a page fragment instead of kmalloc() data will set a non zero
value, set to the fragment size.
Then, on situations we need to convert the skb head to a frag in itself,
we can check if skb->head_frag is set and avoid the copies or various
fallbacks we have.
This means drivers currently using frags could be updated to avoid the
current skb->head allocation and reduce their memory footprint (aka skb
truesize). (thats 512 or 1024 bytes saved per skb). This also makes
bpf/netfilter faster since the 'first frag' will be part of skb linear
part, no need to copy data.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Matt Carlson <mcarlson@broadcom.com>
Cc: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Insert an skb_tx_timestamp call in both ndo_start_xmit routines
Tested to work for the nv_start_xmit_optimized case
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eilon Greenstein <eilong@broadcom.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
|
|
The intent of git commit 6fbf9e7a90862988c278462d85ce9684605a52b2
"PCI: Introduce __pci_reset_function_locked to be used when holding
device_lock." was to have a non-locking function that would call
pci_dev_reset function.
But it fell short of that by just probing and not actually reseting
the device. To make that work we need a way to move the lock
around device_lock to not be in pci_dev_reset (as the caller of
__pci_reset_function_locked already holds said lock). We do this by
renaming pci_dev_reset to __pci_dev_reset and bubbling said mutex out
of __pci_dev_reset to pci_dev_reset (a wrapper around __pci_dev_reset).
The __pci_reset_function_locked can now call __pci_dev_reset without
having to worry about the dead-lock.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
As s3c2412-i2s is using the s3c_i2sv2 it should call the more specialised
s3c_i2sv2_register_dai instead of simply calling snd_soc_register_dai.
Without this call the snd_soc_dai_ops structure isn't initialised correctly.
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
|
|
The core allocates the live copies, we shouldn't try to duplicate it and
were buggy trying to do so as we were using uninitialised data for the
control data.
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
|
|
Pull ARM fixes from Russell King.
* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
ARM: 7406/1: hotplug: copy the affinity mask when forcefully migrating IRQs
ARM: 7405/1: kexec: call platform_cpu_kill on the killer rather than the victim
ARM: 7403/1: tls: remove covert channel via TPIDRURW
ARM: 7401/1: mm: Fix section mismatches
ARM: OMAP: fix DMA vs memory ordering
ARM: 7390/1: dts: versatile-pb/ab fix MMC IRQs
ARM: 7400/1: vfp: clear fpscr length and stride bits on entry to sig handler
ARM: 7399/1: vfp: move user vfp state save/restore code out of signal.c
ARM: 7398/1: l2x0: only write to debug registers on PL310
ARM: 7397/1: l2x0: only apply workaround for erratum #753970 on PL310
ARM: 7396/1: errata: only handle ARM erratum #326103 on affected cores
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI fixes from James Bottomley:
"This is a set of SAS and SATA fixes; there are one or two longstanding
bug fixes, but most of this is regression fixes."
* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
[SCSI] libfc: update mfs boundry checking
[SCSI] Revert "[SCSI] libsas: fix sas port naming"
[SCSI] libsas: fix false positive 'device attached' conditions
[SCSI] libsas, libata: fix start of life for a sas ata_port
[SCSI] libsas: fix ata_eh clobbering ex_phys via smp_ata_check_ready
[SCSI] libsas: unify domain_device sas_rphy lifetimes
[SCSI] libsas: fix sas_get_port_device regression
[SCSI] libsas: fix sas_find_bcast_phy() in the presence of 'vacant' phys
[SCSI] libsas: introduce sas_work to fix sas_drain_work vs sas_queue_work
[SCSI] libata: Pass correct DMA device to scsi host
[SCSI] scsi_lib: use correct DMA device in __scsi_alloc_queue
|
|
A common flaw in UEFI systems is a refusal to POST triggered by a malformed
boot variable. Once in this state, machines may only be restored by
reflashing their firmware with an external hardware device. While this is
obviously a firmware bug, the serious nature of the outcome suggests that
operating systems should filter their variable writes in order to prevent
a malicious user from rendering the machine unusable.
Signed-off-by: Matthew Garrett <mjg@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
More recent versions of the UEFI spec have added new attributes for
variables. Add them.
Signed-off-by: Matthew Garrett <mjg@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Set the use_single_rw flag for devices that use format_write() since
format_write() doesn't support any form of block operation.
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
|
|
Some devices does not support bulk read and write operations, for them
we have series of single write and read operations.
Signed-off-by: Anthony Olech <Anthony.Olech@diasemi.com>
Signed-off-by: Ashish Jangam <ashish.jangam@kpitcummins.com>
[Fixed coding style, don't check use_single_rw before assign --broonie ]
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
|
|
If we don't have a cached value for a register and we can cache it then
when we do a read a value we should add it to the cache to save rereading
it later on. Do this for single register reads, for block reads the code
would be a little more complex and this covers most practical usage.
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
|
|
A PCIe downstream port is a P2P bridge. Its secondary interface is
a link that should lead only to device 0 (unless ARI is enabled)[1], so
we don't probe for non-zero device numbers.
Some Stratus ftServer systems have a PCIe downstream port (02:00.0) that
leads to both an upstream port (03:00.0) and a downstream port (03:01.0),
and 03:01.0 has important devices below it:
[0000:02]-+-00.0-[03-3c]--+-00.0-[04-09]--...
\-01.0-[0a-0d]--+-[USB]
+-[NIC]
+-...
Previously, we didn't enumerate device 03:01.0, so USB and the network
didn't work. This patch adds a DMI quirk to scan all device numbers,
not just 0, below a downstream port.
Based on a patch by Prarit Bhargava.
[1] PCIe spec r3.0, sec 7.3.1
CC: Myron Stowe <mstowe@redhat.com>
CC: Don Dutile <ddutile@redhat.com>
CC: James Paradis <james.paradis@stratus.com>
CC: Matthew Wilcox <matthew.r.wilcox@intel.com>
CC: Jesse Barnes <jbarnes@virtuousgeek.org>
CC: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
pcibios_scan_root() and pci_scan_bus_on_node() were almost identical,
so this patch merges them.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
This dynamically allocates struct pci_root_info instead of using a
static array.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
Embed the x86 struct pci_sysdata in the struct pci_root_info so it
will be automatically freed in the remove path.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
We now keep the pci_root_info struct for the entire lifetime of the
host bridge, so just embed the name in the struct rather than
allocating it separately.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
1. Allocate pci_root_info instead of using stack. We need to pass around
info for release function.
2. Add release_pci_root_info
3. Set x86 host bridge release function to make sure root bridge
related resources get freed during root bus removal.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
Rename get_current_resources() to probe_pci_root_info.
1. Remove resource list head from pci_root_info
2. Make get_current_resources() not pass resources
3. Rename get_current_resources() to probe_pci_root_info()
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
We need a hook to release host bridge resources allocated when creating
root bus.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
sh_symtab is set but not used.
[ hpa: putting this in urgent because of the sheer harmlessness of the patch:
it quiets a build warning but does not change any generated code. ]
Signed-off-by: Kusanagi Kouichi <slash@ac.auone-net.jp>
Link: http://lkml.kernel.org/r/20120401082932.D5E066FC03D@msa105.auone-net.jp
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org>
|
|
<asm-generic/statfs.h> is exported to userspace, so using
BITS_PER_LONG is invalid. We need to use __BITS_PER_LONG instead.
This is kernel bugzilla 43165.
Reported-by: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1335465916-16965-1-git-send-email-hpa@linux.intel.com
Acked-by: Arnd Bergmann <arnd@arndb.de>
Cc: <stable@vger.kernel.org>
|
|
Some of the comment blocks are floating in limbo between two
functions, or between blocks of code. Delete the extra line
feeds between any comment and its associated following block
of code, to be consistent with the majority of the rest of
the kernel. Also delete trailing newlines at EOF and fix
a couple trivial typos in existing comments.
This is a 100% cosmetic change with no runtime impact. We get
rid of over 500 lines of non-code, and being blank line deletes,
they won't even show up as noise in git blame.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
|
|
Use that device for pci_root_bus bridge pointer.
Use pci_release_bus_bridge_dev() to release allocated pci_host_bridge in
remove path.
Use root bus bridge pointer to get host bridge pointer instead of searching
host bridge list. That leaves the host bridge list unused, so remove it.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
pci_host_bridge() looks like a C++ constructor. Also separate
find_pci_root_bus() out.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
In pci_scan_acpi_root(), when pci_use_crs is set, get_current_resources()
is used to get pci_root_info, and it will allocate name and resource array.
Later if pci_create_root_bus() can not create bus (could be already
there...) it will only free bus res list, but the name and res array is not
freed.
Let get_current_resource() take info pointer instead of using local info.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
Move host bridge-related code from probe.c to a new host-bridge.c.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
|
|
Fix printk format warnings -- both items are size_t,
so use %zu to print them.
fs/nfsd/nfs4recover.c:580:3: warning: format '%lu' expects type 'long unsigned int', but argument 3 has type 'size_t'
fs/nfsd/nfs4recover.c:580:3: warning: format '%lu' expects type 'long unsigned int', but argument 4 has type 'unsigned int'
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: linux-nfs@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
EAP frames for stations in an AP VLAN are sent on the main AP interface
to avoid race conditions wrt. moving stations.
For that to work properly, sta_info_get_bss must be used instead of
sta_info_get when sending EAP packets.
Previously this was only done for cooked monitor injected packets, so
this patch adds a check for tx->skb->protocol to the same place.
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Cc: stable@vger.kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc
Pull powerpc fixes from Benjamin Herrenschmidt:
"Here are a handful more fixes for powerpc. The irq stuff are all
regression fixes, and Gavin's patch is a simple compile fix."
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
tty/serial/pmac_zilog: Fix "nobody cared" IRQ message
powerpc/pseries: Rivet CONFIG_EEH for pSeries platform
powerpc/irqdomain: Fix broken NR_IRQ references
powerpc/8xx: Fix NR_IRQ bugs and refactor 8xx interrupt controller
|
|
Add srcu_torture_deferred_free() for srcu_ops so as to test the new
call_srcu(). Rename the original srcu_ops to srcu_sync_ops.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
This commit implements an SRCU state machine in support of call_srcu().
The state machine is preemptible, light-weight, and single-threaded,
minimizing synchronization overhead. In particular, there is no longer
any need for synchronize_srcu() to be guarded by a mutex.
Expedited processing is handled, at least in the absence of concurrent
grace-period operations on that same srcu_struct structure, by having
the synchronize_srcu_expedited() thread take on the role of the
workqueue thread for one iteration.
There is a reasonable probability that a given SRCU callback will
be invoked on the same CPU that registered it, however, there is no
guarantee. Concurrent SRCU grace-period primitives can cause callbacks
to be executed elsewhere, even in absence of CPU-hotplug operations.
Callbacks execute in process context, but under the influence of
local_bh_disable(), so it is illegal to sleep in an SRCU callback
function.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The earlier algorithm used an "expedited" flag combined with a "trycount"
counter to differentiate between normal and expedited SRCU grace periods.
However, the difference can be encoded into a single counter with a cutoff
value and different initial values for expedited and normal SRCU grace
periods. This commit makes that change.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Conflicts:
kernel/srcu.c
|
|
Expand the calls to srcu_readers_active_idx() from srcu_readers_active()
inline. This change improves cache locality by interating over the CPUs
once rather than twice.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The old srcu_barrier() macro is now unused. This commit removes it so
that it may be used for the SRCU flavor of rcu_barrier(), which will in
turn be needed to allow the upcoming call_srcu() to be used from within
modules.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
This commit implements a variant of Peter's algorithm, which may be found
at https://lkml.org/lkml/2012/2/1/119.
o Make the checking lock-free to enable parallel checking.
Parallel checking is required when (1) the original checking
task is preempted for a long time, (2) sychronize_srcu_expedited()
starts during an ongoing SRCU grace period, or (3) we wish to
avoid acquiring a lock.
o Since the checking is lock-free, we avoid a mutex in state machine
for call_srcu().
o Remove the SRCU_REF_MASK and remove the coupling with the flipping.
This might allow us to remove the preempt_disable() in future
versions, though such removal will need great care because it
rescinds the one-old-reader-per-CPU guarantee.
o Remove a smp_mb(), simplify the comments and make the smp_mb() pairs
more intuitive.
Inspired-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The safety of SRCU is provided byy wait_idx() rather than flipping.
The flipping actually prevents starvation.
This commit therefore updates the comments to more accurately and
precisely describe what is going on.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
This is an optimization of the SRCU grace period. To guard against
preempted readers with old values of the counter, it suffices to scan the
old counters once more, then flip ->completed only one time. The reason
this works is that the old readers must have incremented the old set of
counters (if they have not yet incremented, then their critical section
starts after this grace period, so they may be safely ignored).
This commit therefore optimizes the second flip out in favor of a simple
rescan.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The purpose of the upper bit of SRCU's per-CPU counters is to guarantee
that no reasonable series of srcu_read_lock() and srcu_read_unlock()
operations can return the value of the counter to its original value.
This guarantee is require only after the index has been switched to
the other set of counters, so at most one srcu_read_lock() can affect
a given CPU's counter. The number of srcu_read_unlock() operations
on a given counter is limited to the number of tasks in the system,
which given the Linux kernel's current structure is limited to far less
than 2^30 on 32-bit systems and far less than 2^62 on 64-bit systems.
(Something about a limited number of bytes in the kernel's address space.)
Therefore, if srcu_read_lock() increments the upper bits, then
srcu_read_unlock() need not do so. In this case, an srcu_read_lock() and
an srcu_read_unlock() will flip the lower bit of the upper field of the
counter. An unreasonably large additional number of srcu_read_unlock()
operations would be required to return the counter to its initial value,
thus preserving the guarantee.
This commit takes this approach, which further allows it to shrink
the size of the upper field to one bit, making the number of
srcu_read_unlock() operations required to return the counter to its
initial value even more unreasonable than before.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The fastpath in __synchronize_srcu() is designed to handle cases where
there are a large number of concurrent calls for the same srcu_struct
structure. However, the Linux kernel currently does not use SRCU in
this manner, so remove the fastpath checks for simplicity.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The current implementation of synchronize_srcu_expedited() can cause
severe OS jitter due to its use of synchronize_sched(), which in turn
invokes try_stop_cpus(), which causes each CPU to be sent an IPI.
This can result in severe performance degradation for real-time workloads
and especially for short-interation-length HPC workloads. Furthermore,
because only one instance of try_stop_cpus() can be making forward progress
at a given time, only one instance of synchronize_srcu_expedited() can
make forward progress at a time, even if they are all operating on
distinct srcu_struct structures.
This commit, inspired by an earlier implementation by Peter Zijlstra
(https://lkml.org/lkml/2012/1/31/211) and by further offline discussions,
takes a strictly algorithmic bits-in-memory approach. This has the
disadvantage of requiring one explicit memory-barrier instruction in
each of srcu_read_lock() and srcu_read_unlock(), but on the other hand
completely dispenses with OS jitter and furthermore allows SRCU to be
used freely by CPUs that RCU believes to be idle or offline.
The update-side implementation handles the single read-side memory
barrier by rechecking the per-CPU counters after summing them and
by running through the update-side state machine twice.
This implementation has passed moderate rcutorture testing on both
x86 and Power. Also updated to use this_cpu_ptr() instead of per_cpu_ptr(),
as suggested by Peter Zijlstra.
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
|
|
Although rcutorture does invoke rcu_barrier() and friends, it cannot
really be called a torture test given that it invokes them only once
at the end of the test. This commit therefore introduces heavy-duty
rcutorture testing for rcu_barrier(), which may be carried out
concurrently with normal rcutorture testing.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
When the cwnd reduction is done, ssthresh may be infinite
if TCP enters CWR via ECN or F-RTO. If cwnd is not undone, i.e.,
undo_marker is set, tcp_complete_cwr() falsely set cwnd to the
infinite ssthresh value. The correct operation is to keep cwnd
intact because it has been updated in ECN or F-RTO.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Now the helper function from filter.c for negative offsets is exported,
it can be used it in the jit to handle negative offsets.
First modify the asm load helper functions to handle:
- know positive offsets
- know negative offsets
- any offset
then the compiler can be modified to explicitly use these helper
when appropriate.
This fixes the case of a negative X register and allows to lift
the restriction that bpf programs with negative offsets can't
be jited.
Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Jan Seiffert <kaffeemonster@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Denys Fedoryshchenko reported frequent crashes on a proxy server and kindly
provided a lockdep report that explains it all :
[ 762.903868]
[ 762.903880] =================================
[ 762.903890] [ INFO: inconsistent lock state ]
[ 762.903903] 3.3.4-build-0061 #8 Not tainted
[ 762.904133] ---------------------------------
[ 762.904344] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
[ 762.904542] squid/1603 [HC0[0]:SC0[0]:HE1:SE1] takes:
[ 762.904542] (key#3){+.?...}, at: [<c0232cc4>]
__percpu_counter_sum+0xd/0x58
[ 762.904542] {IN-SOFTIRQ-W} state was registered at:
[ 762.904542] [<c0158b84>] __lock_acquire+0x284/0xc26
[ 762.904542] [<c01598e8>] lock_acquire+0x71/0x85
[ 762.904542] [<c0349765>] _raw_spin_lock+0x33/0x40
[ 762.904542] [<c0232c93>] __percpu_counter_add+0x58/0x7c
[ 762.904542] [<c02cfde1>] sk_clone_lock+0x1e5/0x200
[ 762.904542] [<c0303ee4>] inet_csk_clone_lock+0xe/0x78
[ 762.904542] [<c0315778>] tcp_create_openreq_child+0x1b/0x404
[ 762.904542] [<c031339c>] tcp_v4_syn_recv_sock+0x32/0x1c1
[ 762.904542] [<c031615a>] tcp_check_req+0x1fd/0x2d7
[ 762.904542] [<c0313f77>] tcp_v4_do_rcv+0xab/0x194
[ 762.904542] [<c03153bb>] tcp_v4_rcv+0x3b3/0x5cc
[ 762.904542] [<c02fc0c4>] ip_local_deliver_finish+0x13a/0x1e9
[ 762.904542] [<c02fc539>] NF_HOOK.clone.11+0x46/0x4d
[ 762.904542] [<c02fc652>] ip_local_deliver+0x41/0x45
[ 762.904542] [<c02fc4d1>] ip_rcv_finish+0x31a/0x33c
[ 762.904542] [<c02fc539>] NF_HOOK.clone.11+0x46/0x4d
[ 762.904542] [<c02fc857>] ip_rcv+0x201/0x23e
[ 762.904542] [<c02daa3a>] __netif_receive_skb+0x319/0x368
[ 762.904542] [<c02dac07>] netif_receive_skb+0x4e/0x7d
[ 762.904542] [<c02dacf6>] napi_skb_finish+0x1e/0x34
[ 762.904542] [<c02db122>] napi_gro_receive+0x20/0x24
[ 762.904542] [<f85d1743>] e1000_receive_skb+0x3f/0x45 [e1000e]
[ 762.904542] [<f85d3464>] e1000_clean_rx_irq+0x1f9/0x284 [e1000e]
[ 762.904542] [<f85d3926>] e1000_clean+0x62/0x1f4 [e1000e]
[ 762.904542] [<c02db228>] net_rx_action+0x90/0x160
[ 762.904542] [<c012a445>] __do_softirq+0x7b/0x118
[ 762.904542] irq event stamp: 156915469
[ 762.904542] hardirqs last enabled at (156915469): [<c019b4f4>]
__slab_alloc.clone.58.clone.63+0xc4/0x2de
[ 762.904542] hardirqs last disabled at (156915468): [<c019b452>]
__slab_alloc.clone.58.clone.63+0x22/0x2de
[ 762.904542] softirqs last enabled at (156915466): [<c02ce677>]
lock_sock_nested+0x64/0x6c
[ 762.904542] softirqs last disabled at (156915464): [<c0349914>]
_raw_spin_lock_bh+0xe/0x45
[ 762.904542]
[ 762.904542] other info that might help us debug this:
[ 762.904542] Possible unsafe locking scenario:
[ 762.904542]
[ 762.904542] CPU0
[ 762.904542] ----
[ 762.904542] lock(key#3);
[ 762.904542] <Interrupt>
[ 762.904542] lock(key#3);
[ 762.904542]
[ 762.904542] *** DEADLOCK ***
[ 762.904542]
[ 762.904542] 1 lock held by squid/1603:
[ 762.904542] #0: (sk_lock-AF_INET){+.+.+.}, at: [<c03055c0>]
lock_sock+0xa/0xc
[ 762.904542]
[ 762.904542] stack backtrace:
[ 762.904542] Pid: 1603, comm: squid Not tainted 3.3.4-build-0061 #8
[ 762.904542] Call Trace:
[ 762.904542] [<c0347b73>] ? printk+0x18/0x1d
[ 762.904542] [<c015873a>] valid_state+0x1f6/0x201
[ 762.904542] [<c0158816>] mark_lock+0xd1/0x1bb
[ 762.904542] [<c015876b>] ? mark_lock+0x26/0x1bb
[ 762.904542] [<c015805d>] ? check_usage_forwards+0x77/0x77
[ 762.904542] [<c0158bf8>] __lock_acquire+0x2f8/0xc26
[ 762.904542] [<c0159b8e>] ? mark_held_locks+0x5d/0x7b
[ 762.904542] [<c0159cf6>] ? trace_hardirqs_on+0xb/0xd
[ 762.904542] [<c0158dd4>] ? __lock_acquire+0x4d4/0xc26
[ 762.904542] [<c01598e8>] lock_acquire+0x71/0x85
[ 762.904542] [<c0232cc4>] ? __percpu_counter_sum+0xd/0x58
[ 762.904542] [<c0349765>] _raw_spin_lock+0x33/0x40
[ 762.904542] [<c0232cc4>] ? __percpu_counter_sum+0xd/0x58
[ 762.904542] [<c0232cc4>] __percpu_counter_sum+0xd/0x58
[ 762.904542] [<c02cebc4>] __sk_mem_schedule+0xdd/0x1c7
[ 762.904542] [<c02d178d>] ? __alloc_skb+0x76/0x100
[ 762.904542] [<c0305e8e>] sk_wmem_schedule+0x21/0x2d
[ 762.904542] [<c0306370>] sk_stream_alloc_skb+0x42/0xaa
[ 762.904542] [<c0306567>] tcp_sendmsg+0x18f/0x68b
[ 762.904542] [<c031f3dc>] ? ip_fast_csum+0x30/0x30
[ 762.904542] [<c0320193>] inet_sendmsg+0x53/0x5a
[ 762.904542] [<c02cb633>] sock_aio_write+0xd2/0xda
[ 762.904542] [<c015876b>] ? mark_lock+0x26/0x1bb
[ 762.904542] [<c01a1017>] do_sync_write+0x9f/0xd9
[ 762.904542] [<c01a2111>] ? file_free_rcu+0x2f/0x2f
[ 762.904542] [<c01a17a1>] vfs_write+0x8f/0xab
[ 762.904542] [<c01a284d>] ? fget_light+0x75/0x7c
[ 762.904542] [<c01a1900>] sys_write+0x3d/0x5e
[ 762.904542] [<c0349ec9>] syscall_call+0x7/0xb
[ 762.904542] [<c0340000>] ? rp_sidt+0x41/0x83
Bug is that sk_sockets_allocated_read_positive() calls
percpu_counter_sum_positive() without BH being disabled.
This bug was added in commit 180d8cd942ce33
(foundations of per-cgroup memory pressure controlling.), since previous
code was using percpu_counter_read_positive() which is IRQ safe.
In __sk_mem_schedule() we dont need the precise count of allocated
sockets and can revert to previous behavior.
Reported-by: Denys Fedoryshchenko <denys@visp.net.lb>
Sined-off-by: Eric Dumazet <edumazet@google.com>
Cc: Glauber Costa <glommer@parallels.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Unfortunately it seems that I didn't properly test the case of
an expired external querier in the recent multicast bridge series.
The setup of the timer in that case is completely broken and leads
to a NULL-pointer dereference. This patch fixes it.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
