Hardware needs the local device mac address to support hw loopback for
rdma loopback connections.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
While reviewing seccomp code, we found that BPF_S_ANC_SECCOMP_LD_W has
been wrongly decoded by commit a8fc927780 ("sk-filter: Add ability to
get socket filter program (v2)") into the opcode BPF_LD|BPF_B|BPF_ABS
although it should have been decoded as BPF_LD|BPF_W|BPF_ABS.
In practice, this should not have much side-effect though, as such
conversion is/was being done through prctl(2) PR_SET_SECCOMP. Reverse
operation PR_GET_SECCOMP will only return the current seccomp mode, but
not the filter itself. Since the transition to the new BPF infrastructure,
it's also not used anymore, so we can simply remove this as it's
unreachable.
Fixes: a8fc927780 ("sk-filter: Add ability to get socket filter program (v2)")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Linus reports that on 32-bit x86 Chromium throws the following seccomp
resp. audit log messages:
audit: type=1326 audit(1397359304.356:28108): auid=500 uid=500
gid=500 ses=2 subj=unconfined_u:unconfined_r:chrome_sandbox_t:s0-s0:c0.c1023
pid=3677 comm="chrome" exe="/opt/google/chrome/chrome" sig=0
syscall=172 compat=0 ip=0xb2dd9852 code=0x30000
audit: type=1326 audit(1397359304.356:28109): auid=500 uid=500
gid=500 ses=2 subj=unconfined_u:unconfined_r:chrome_sandbox_t:s0-s0:c0.c1023
pid=3677 comm="chrome" exe="/opt/google/chrome/chrome" sig=0 syscall=5
compat=0 ip=0xb2dd9852 code=0x50000
These audit messages are being triggered via audit_seccomp() through
__secure_computing() in seccomp mode (BPF) filter with seccomp return
codes 0x30000 (== SECCOMP_RET_TRAP) and 0x50000 (== SECCOMP_RET_ERRNO)
during filter runtime. Moreover, Linus reports that x86_64 Chromium
seems fine.
The underlying issue that explains this is that the implementation of
populate_seccomp_data() is wrong. Our seccomp data structure sd that
is being shared with user ABI is:
struct seccomp_data {
int nr;
__u32 arch;
__u64 instruction_pointer;
__u64 args[6];
};
Therefore, a simple cast to 'unsigned long *' for storing the value of
the syscall argument via syscall_get_arguments() is just wrong as on
32-bit x86 (or any other 32bit arch), it would result in storing a0-a5
at wrong offsets in args[] member, and thus i) could leak stack memory
to user space and ii) tampers with the logic of seccomp BPF programs
that read out and check for syscall arguments:
syscall_get_arguments(task, regs, 0, 1, (unsigned long *) &sd->args[0]);
Tested on 32-bit x86 with Google Chrome, unfortunately only via remote
test machine through slow ssh X forwarding, but it fixes the issue on
my side. So fix it up by storing args in type correct variables, gcc
is clever and optimizes the copy away in other cases, e.g. x86_64.
Fixes: bd4cf0ed33 ("net: filter: rework/optimize internal BPF interpreter's instruction set")
Reported-and-bisected-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <james.l.morris@oracle.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some fields are missing from the event mailbox
struct definitions, which cause issues when
trying to handle some events.
Add the missing fields in order to align the
struct size (without adding actual support
for the new fields).
Reported-and-tested-by: Imre Kaloz <kaloz@openwrt.org>
Cc: stable@vger.kernel.org # 3.14+
Fixes: 028e724 ("wl18xx: move to new firmware (wl18xx-fw-3.bin)")
Signed-off-by: Eliad Peller <eliad@wizery.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Fix a potential memory leak in the error path of function
rsi_send_auto_rate_request(). In case memory allocation for array
'selected_rates' fails, the error path exits and leaves the previously
allocated skb in place. Detected by Coverity: CID 1195575.
Signed-off-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This array is used in debug string to display cw1200_link_status
defined in drivers/net/wireless/cw1200/cw1200.h.
Add missing strings for CW1200_LINK_RESET and CW1200_LINK_RESET_REMAP.
Signed-off-by: Frederic Danis <frederic.danis@linux.intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Sometimes the firmware sends a dummy packet event while we are in PLT
mode. This doesn't make sense, it's a firmware bug. Fix this by
ignoring dummy packet events when we're PLT mode.
Reported-by: Yegor Yefremov <yegorslists@googlemail.com>
Reported-by: Arik Nemtsov <arik@wizery.com>
Signed-off-by: Luciano Coelho <luca@coelho.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Fix a potential memory leak in function rsi_set_channel() that is used to
program channel changes. The channel check block for the frequency bands
directly exits the function in case of an error, thus leaving an already
allocated skb unreferenced. Move the checks above allocating the skb.
Detected by Coverity: CID 1195576.
Signed-off-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
drivers/net/wireless/rsi/rsi_91x_core.c: In function ‘rsi_core_determine_hal_queue’:
drivers/net/wireless/rsi/rsi_91x_core.c:91: warning: ‘ii’ may be used uninitialized in this function
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Shahed Shaikh says:
====================
qlcnic: Bug fixes
This patch series contains following bug fixes -
* Send INIT_NIC_FUNC mailbox command as first mailbox
* Fix a panic because of uninitialized delayed_work.
* Fix inconsistent calculation of max rings count.
* Fix PVID configuration issue. Driver needs to clear older
PVID before adding new one.
* Fix QLogic application/driver interface by packing vNIC information
array.
* Fix a crash when user tries to disable SR-IOV while VFs are
still assigned to VMs.
Please apply to net.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
o While disabling SR-IOV when VFs are assigned to VMs causes host crash
so return -EPERM when user request to disable SR-IOV using pci sysfs in
case of VFs are assigned to VMs.
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
o Application expect vNIC number as the array index but driver interface
return configuration in array index form.
o Pack the vNIC information array in the buffer such that application can
access it using vNIC number as the array index.
Signed-off-by: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not read max rings count from qlcnic_get_nic_info(). Use driver defined
values for 82xx adapters. In case of 83xx adapters, use minimum of firmware
provided and driver defined values.
Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
o INIT_NIC_FUNC should be first mailbox sent. Sending DCB capability and
parameter query commands after that command.
Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
o AEN event was being received before initializing delayed_work struct
and handlers for it. This was resulting in crash. This patch fixes it.
Signed-off-by: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Sathya Perla says:
====================
be2net: patch set
Patch 1/2 is a v2 of a patch that was submitted earlier (as a part of a
different patch-set). v2 incorporates a suggestion given by David Laight
for how long to poll for pending TX completions while disabling a device.
Patch 2/2 fixes a crash in be_remove()->be_close()
path after be2net has aborted an EEH error recovery
due to a permanant failure.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In the EEH error recovery path, when a permanent failure occurs,
we clean up adapter structure (i.e. destroy queues etc) by calling
be_clear() and return PCI_ERS_RESULT_DISCONNECT.
After this the stack tries to remove device from bus and calls
be_remove() which invokes netdev_unregister()->be_close().
be_close() operating on destroyed queues results in a
NULL dereference.
This patch fixes this problem by introducing a flag to keep track
of the setup state.
Signed-off-by: Kalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
be_close() currently waits for a max of 200ms to receive all pending
TX compls. This timeout value was roughly calculated based on 10G
transmission speeds and the TX queue depth. This timeout may not be
enough when the link is operating at lower speeds or in multi-channel/SR-IOV
configs with TX-rate limiting setting.
It is hard to calculate a "proper timeout value" that works in all
configurations. This patch solves this problem by continuing to reap
TX completions till the HW is completely silent for a period of 10ms or
a HW error is detected.
v2: implements the new scheme (as suggested by David Laight) instead of
just waiting longer than 200ms for reaping all completions.
Signed-off-by: Vasundhara Volam <vasundhara.volam@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix in commit [1] is not sufficient since a deferred VF initialization
could happen after pci_enable_sriov() is finished, but before the PF is
fully initialized.
Need to prevent VFs from initializing till the PF is fully ready and
comm channel is operational.
[1] - 9798935 "net/mlx4_core: mlx4_init_slave() shouldn't access comm
channel before PF is ready"
CC: Stuart Hayes <Stuart_Hayes@Dell.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When CONFIG_PM_SLEEP isn't enabled, bnx2_suspend/resume are unused; don't
build them when they aren't used.
Signed-off-by: Daniel J Blueman <daniel@quora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Francois reported that setting big mtu on loopback device could prevent
tcp sessions making progress.
We do not support (yet ?) IPv6 Jumbograms and cook corrupted packets.
We must limit the IPv6 MTU to (65535 + 40) bytes in theory.
Tested:
ifconfig lo mtu 70000
netperf -H ::1
Before patch : Throughput : 0.05 Mbits
After patch : Throughput : 35484 Mbits
Reported-by: Francois WELLENREITER <f.wellenreiter@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
nft_cmp_fast is used for equality comparisions of size <= 4. For
comparisions of size < 4 byte a mask is calculated that is applied to
both the data from userspace (during initialization) and the register
value (during runtime). Both values are stored using (in effect) memcpy
to a memory area that is then interpreted as u32 by nft_cmp_fast.
This works fine on little endian since smaller types have the same base
address, however on big endian this is not true and the smaller types
are interpreted as a big number with trailing zero bytes.
The mask therefore must not include the lower bytes, but the higher bytes
on big endian. Add a helper function that does a cpu_to_le32 to switch
the bytes on big endian. Since we're dealing with a mask of just consequitive
bits, this works out fine.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
The BPF_S_ANC_NLATTR and BPF_S_ANC_NLATTR_NEST extensions fail to check
for a minimal message length before testing the supplied offset to be
within the bounds of the message. This allows the subtraction of the nla
header to underflow and therefore -- as the data type is unsigned --
allowing far to big offset and length values for the search of the
netlink attribute.
The remainder calculation for the BPF_S_ANC_NLATTR_NEST extension is
also wrong. It has the minuend and subtrahend mixed up, therefore
calculates a huge length value, allowing to overrun the end of the
message while looking for the netlink attribute.
The following three BPF snippets will trigger the bugs when attached to
a UNIX datagram socket and parsing a message with length 1, 2 or 3.
,-[ PoC for missing size check in BPF_S_ANC_NLATTR ]--
| ld #0x87654321
| ldx #42
| ld #nla
| ret a
`---
,-[ PoC for the same bug in BPF_S_ANC_NLATTR_NEST ]--
| ld #0x87654321
| ldx #42
| ld #nlan
| ret a
`---
,-[ PoC for wrong remainder calculation in BPF_S_ANC_NLATTR_NEST ]--
| ; (needs a fake netlink header at offset 0)
| ld #0
| ldx #42
| ld #nlan
| ret a
`---
Fix the first issue by ensuring the message length fulfills the minimal
size constrains of a nla header. Fix the second bug by getting the math
for the remainder calculation right.
Fixes: 4738c1db15 ("[SKFILTER]: Add SKF_ADF_NLATTR instruction")
Fixes: d214c7537b ("filter: add SKF_AD_NLATTR_NEST to look for nested..")
Cc: Patrick McHardy <kaber@trash.net>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Mathias Krause <minipli@googlemail.com>
Acked-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Extend commit 13378cad02
("ipv4: Change rt->rt_iif encoding.") from 3.6 to return valid
RTA_IIF on 'ip route get ... iif DEVICE' instead of rt_iif 0
which is displayed as 'iif *'.
inet_iif is not appropriate to use because skb_iif is not set.
Use the skb->dev->ifindex instead.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit e3a8786c10. While
this commit allows to use the mvneta driver as a module on some
configurations, it breaks other configurations even if mvneta is used
built-in.
This breakage is due to the fact that on some RGMII platforms, the PCS
bit has to be set, and on some other platforms, it has to be
cleared. At the moment, we lack informations to know exactly the
significance of this bit (the datasheet only says "enables PCS"), and
so we can't produce a patch that will work on all platforms at this
point. And since this change is breaking the network completely for
many users, it's much better to revert it for now. We'll come back
later with a proper fix that takes into account all platforms.
Basically:
* Armada XP GP is configured as RGMII-ID, and needs the PCS bit to be
set.
* Armada 370 Mirabox is configured as RGMII-ID, and needs the PCS bit
to be cleared.
And at the moment, we don't know how to make the distinction between
those two cases. One hint is that the Armada XP GP appears in fact to
be using a QSGMII connection with the PHY (Quad-SGMII), but
configuring it as SGMII doesn't work, while RGMII-ID works. This needs
more investigation, but in the mean time, let's unbreak the network
for all those users.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Reported-by: Arnaud Ebalard <arno@natisbad.org>
Reported-by: Alexander Reuter <Alexander.Reuter@gmx.net>
Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=73401
Cc: stable@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
pci_match_id() just match the static pci_device_id, which may return NULL if
someone binds the driver to a device manually using
/sys/bus/pci/drivers/.../new_id.
This patch wrap up a helper function __mlx4_remove_one() which does the tear
down function but preserve the drv_data. Functions like
mlx4_pci_err_detected() and mlx4_restart_one() will call this one with out
releasing drvdata.
Fixes: 97a5221 "net/mlx4_core: pass pci_device_id.driver_data to __mlx4_init_one during reset".
CC: Bjorn Helgaas <bhelgaas@google.com>
CC: Amir Vadai <amirv@mellanox.com>
CC: Jack Morgenstein <jackm@dev.mellanox.co.il>
CC: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Plug a group_info refcount leak in ping_init.
group_info is only needed during initialization and
the code failed to release the reference on exit.
While here move grabbing the reference to a place
where it is actually needed.
Signed-off-by: Chuansheng Liu <chuansheng.liu@intel.com>
Signed-off-by: Zhang Dongxing <dongxing.zhang@intel.com>
Signed-off-by: xiaoming wang <xiaoming.wang@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some versions of gcc even warn about it:
mm/shmem.c: In function ‘shmem_file_aio_read’:
mm/shmem.c:1414: warning: ‘error’ may be used uninitialized in this function
If the loop is aborted during the first iteration by one of the two
first break statements, error will be uninitialized.
Introduced by commit 6e58e79db8 ("introduce copy_page_to_iter, kill
loop over iovec in generic_file_aio_read()").
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On 32 bit, size_t is "unsigned int", not "unsigned long", causing the
following warning when comparing with PAGE_SIZE, which is always "unsigned
long":
fs/cifs/file.c: In function ‘cifs_readdata_to_iov’:
fs/cifs/file.c:2757: warning: comparison of distinct pointer types lacks a cast
Introduced by commit 7f25bba819 ("cifs_iovec_read: keep iov_iter
between the calls of cifs_readdata_to_iov()"), which changed the
signedness of "remaining" and the code from min_t() to min().
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull slab changes from Pekka Enberg:
"The biggest change is byte-sized freelist indices which reduces slab
freelist memory usage:
https://lkml.org/lkml/2013/12/2/64"
* 'slab/next' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux:
mm: slab/slub: use page->list consistently instead of page->lru
mm/slab.c: cleanup outdated comments and unify variables naming
slab: fix wrongly used macro
slub: fix high order page allocation problem with __GFP_NOFAIL
slab: Make allocations with GFP_ZERO slightly more efficient
slab: make more slab management structure off the slab
slab: introduce byte sized index for the freelist of a slab
slab: restrict the number of objects in a slab
slab: introduce helper functions to get/set free object
slab: factor out calculate nr objects in cache_estimate
The per rate stats should be cleared when aggregation state changes
to avoid making rate scale decisions based on throughput figures which
were collected prior to the aggregation state change and are now stale.
While at it make sure any clearing of the per rate stats will get logged.
Cc: <stable@vger.kernel.org> [3.14]
Signed-off-by: Eyal Shapira <eyalx.shapira@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Allow switching back to legacy Tx columns so we'll stop doing
HT/VHT in case we're far from the AP. Stop active aggregation when
making a deciding to stay in a legacy column.
Despite having low legacy rates in the LQ table lower entries
it doesn't help much in case we're doing aggregations as the
aggregation was being transmitted in the initial rate of the table.
This should help traffic stalls when far from the AP.
Cc: <stable@vger.kernel.org> [3.14]
Signed-off-by: Eyal Shapira <eyalx.shapira@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
After being idle for a long time (>5sec) the rs statistics
will be stale so we prefer to reset rs and start from legacy
rates again. This gives better results when the attenuation
increased signficantly (e.g. we got further from the AP) and
after a while we start Tx
Note that the first Tx after the idle period will still go out
in the old modulation and rate but this seemed a simpler approach
compared to adding a timer or modifying mac80211 for this.
The negative impact is negligble as we'll recover quickly.
Cc: <stable@vger.kernel.org> [3.14]
Signed-off-by: Eyal Shapira <eyalx.shapira@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Change the down/upscale decision logic a bit to be based
on different success ratio thresholds. This fixes the implementation
compared to the rate scale algorithm which was planned to yield
optimal results. Also fix a case where a lower rate wasn't explored
despite being a potential for better throughput.
While at it rewrite rs_get_rate_action to be more clear and clean.
Cc: <stable@vger.kernel.org> [3.14]
Signed-off-by: Eyal Shapira <eyalx.shapira@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
The selection of the max expected throughput for a column
didn't take into account the maximal allowed rate for the current
peer. This can cause unnecessary switches during the search cycle
to columns which have no chance of beating the current throughput.
Signed-off-by: Eyal Shapira <eyalx.shapira@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
I forgot to send the new Look Up Table to the firmware and
I also forgot to free the command which is kzalloc'ed.
This code is relevant for 7265 device only.
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
mimo_delim was always set to 0 instead of pointing to
the first SISO entry after MIMO rates.
This can cause keep transmitting in MIMO even when we shouldn't.
For example when the peer is requesting static SMPS.
Cc: <stable@vger.kernel.org> [3.14]
Signed-off-by: Eyal Shapira <eyalx.shapira@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
If we have no beacon data before association, delay smart FIFO
enablement until after we have this data.
Not doing so can cause association failures in extremely silent
environments (usually only a shielded box/room) as beacon RX is
not sent to the host immediately, and then the association time
event ends without the host receiving any beacon even though it
was on the air - it's just stuck on the FIFO.
Cc: <stable@vger.kernel.org> [3.14]
Fixes: 1f3b0ff8ec ("iwlwifi: mvm: Add Smart FIFO support")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Pull misc kbuild changes from Michal Marek:
"Here is the non-critical part of kbuild:
- One bogus coccinelle check removed, one check fixed not to suggest
the obsolete PTR_RET macro
- scripts/tags.sh does not index the generated *.mod.c files
- new objdiff tool to list differences between two versions of an
object file
- A fix for scripts/bootgraph.pl"
* 'misc' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
scripts/coccinelle: Use PTR_ERR_OR_ZERO
scripts/bootgraph.pl: Add graphic header
scripts: objdiff: detect object code changes between two commits
Coccicheck: Remove memcpy to struct assignment test
scripts/tags.sh: Ignore *.mod.c
This patch fixes I/O errors with the sym53c8xx_2 driver when the disk
returns QUEUE FULL status.
When the controller encounters an error (including QUEUE FULL or BUSY
status), it aborts all not yet submitted requests in the function
sym_dequeue_from_squeue.
This function aborts them with DID_SOFT_ERROR.
If the disk has full tag queue, the request that caused the overflow is
aborted with QUEUE FULL status (and the scsi midlayer properly retries
it until it is accepted by the disk), but the sym53c8xx_2 driver aborts
the following requests with DID_SOFT_ERROR --- for them, the midlayer
does just a few retries and then signals the error up to sd.
The result is that disk returning QUEUE FULL causes request failures.
The error was reproduced on 53c895 with COMPAQ BD03685A24 disk
(rebranded ST336607LC) with command queue 48 or 64 tags. The disk has
64 tags, but under some access patterns it return QUEUE FULL when there
are less than 64 pending tags. The SCSI specification allows returning
QUEUE FULL anytime and it is up to the host to retry.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: James Bottomley <JBottomley@Parallels.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
