It may happen that uasp will free the request in irq conntext, the
callchain:
uasp_cmd_release() -> transport_generic_free_cmd() -> core_dec_lacl_count()
where the last function enables the IRQ. Those irqs are re-disabled
later (due to the spin.*irq_restore) but in between we could get hurt.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The multiple calls to pr_debug() each with one letter results in a new
line. This patch merges the multiple requests into one call per line
so we don't have the multiple line cuts.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds a work-around for handling zero allocation length
control CDBs (type SCF_SCSI_CONTROL_SG_IO_CDB) that was causing an
OOPs with the following raw calls:
# sg_raw -v /dev/sdd 3 0 0 0 0 0
# sg_raw -v /dev/sdd 0x1a 0 1 0 0 0
This patch will follow existing zero-length handling for data I/O
and silently return with GOOD status. This addresses the zero length
issue, but the proper long-term resolution for handling arbitary
allocation lengths will be to refactor out data-phase handling in
individual CDB emulation logic within target_core_cdb.c
Reported-by: Roland Dreier <roland@purestorage.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
According to SPC-4, the sense key for commands that are failed with
INVALID FIELD IN PARAMETER LIST and INVALID FIELD IN CDB should be
ILLEGAL REQUEST (5h) rather than ABORTED COMMAND (Bh). Without this
patch, a tcm_loop LUN incorrectly gives:
# sg_raw -r 1 -v /dev/sda 3 1 0 0 ff 0
Sense Information:
Fixed format, current; Sense key: Aborted Command
Additional sense: Invalid field in cdb
Raw sense data (in hex):
70 00 0b 00 00 00 00 0a 00 00 00 00 24 00 00 00
00 00
While a real SCSI disk gives:
Sense Information:
Fixed format, current; Sense key: Illegal Request
Additional sense: Invalid field in cdb
Raw sense data (in hex):
70 00 05 00 00 00 00 18 00 00 00 00 24 00 00 00
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
with the main point being that the real disk gives a sense key of
ILLEGAL REQUEST (5h).
Signed-off-by: Roland Dreier <roland@purestorage.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Doing alloc_page(GFP_KERNEL | __GFP_ZERO) to get pages used for data
buffers wastes a lot of CPU clearing pages that will be quickly be
overwritten by the actual data. However, for emulated control
commands such as INQUIRY and so on, the code does assume that the
buffer is zeroed.
To avoid this CPU overhead, skip the __GFP_ZERO for commands that are
actually moving data, ie cmds that have SCF_SCSI_DATA_SG_IO_CDB set.
Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Initiators that aren't the active reservation holder should be able to
do a PERSISTENT RESERVE IN command in all cases, so add it to the list
of allowed CDBs in core_scsi3_pr_seq_non_holder().
Signed-off-by: Marco Sanvido <marco@purestorage.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The comments quote the right parts of the spec:
* d) Establish a unit attention condition for the
* initiator port associated with every I_T nexus
* that lost its registration other than the I_T
* nexus on which the PERSISTENT RESERVE OUT command
* was received, with the additional sense code set
* to REGISTRATIONS PREEMPTED.
and
* e) Establish a unit attention condition for the initiator
* port associated with every I_T nexus that lost its
* persistent reservation and/or registration, with the
* additional sense code set to REGISTRATIONS PREEMPTED;
but the actual code accidentally uses ASCQ_2AH_RESERVATIONS_PREEMPTED
instead of ASCQ_2AH_REGISTRATIONS_PREEMPTED. Fix this.
Signed-off-by: Marco Sanvido <marco@purestorage.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
We never embedd the bio into a structure, so there is no need to allocate
64 bytes of headroom per bio.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The target code was not setting the additional sense length field in the
sense data it returned, which meant that at least the Linux stack
ignored the ASC/ASCQ fields. For example, without this patch, on a
tcm_loop device:
# sg_raw -v /dev/sda 2 0 0 0 0 0
gives
cdb to send: 02 00 00 00 00 00
SCSI Status: Check Condition
Sense Information:
Fixed format, current; Sense key: Illegal Request
Raw sense data (in hex):
70 00 05 00 00 00 00 00
while after the patch we correctly get the following (which matches what
a regular disk returns):
cdb to send: 02 00 00 00 00 00
SCSI Status: Check Condition
Sense Information:
Fixed format, current; Sense key: Illegal Request
Additional sense: Invalid command operation code
Raw sense data (in hex):
70 00 05 00 00 00 00 0a 00 00 00 00 20 00 00 00
00 00
Signed-off-by: Roland Dreier <roland@purestorage.com>
Cc: stable@kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch removes a legacy se_dev_check_online() check from within
transport_execute_tasks() that should no longer be necessary as
transport_lookup_cmd_lun() is already making this call.
Using transport_cmd_check_stop() from transport_execute_tasks() should
already be checking per se_cmd context for each descriptor upon active
I/O shutdown, so no need to acquire dev->dev_status_lock again while
executing se_task submission.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch removes the original usage of __transport_execute_tasks() ahead
of every transport_get_cmd_from_queue() call in transport_processing_thread().
This helps reduce se_device->execute_task_lock contention between qla2xxx wq
with target_submit_cmd() for READs and transport_processing_thread()
context servicing WRITEs with full payloads for I/O submission.
It also adds a __transport_execute_tasks() to kick the task queue again
without a *se_cmd descriptor with existing queue full logic, but this may
end up not being necessary.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch makes __transport_execute_tasks() perform the addition of
tasks to dev->execute_task_list via __transport_add_tasks_from_cmd()
while holding dev->execute_task_lock during normal I/O fast path
submission.
It effectively removes the unnecessary re-acquire of dev->execute_task_lock
during transport_execute_tasks() -> transport_add_tasks_from_cmd() ahead
of calling __transport_execute_tasks() to queue tasks for the passed
*se_cmd descriptor.
(v2: Re-add goto check_depth usage for multi-task submission for now..)
Cc: Christoph Hellwig <hch@lst.de>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Historically, pSCSI devices have been the ones that required target-core
to enforce a per se_device->depth_left. This patch changes target-core
to no longer (by default) enforce a per se_device->depth_left or sleep in
transport_tcq_window_closed() when we out of queue slots for all backend
export cases.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch makes __transport_execute_tasks() use a local *se_dev
reference to prevent direct se_cmd->se_dev access after
transport_cmd_check_stop() -> transport_add_tasks_from_cmd()
has been called, as in the current implementation we can expect
__transport_execute_tasks() may be called from another context
that may have already completed the I/O.
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Remove the now unused target_core_fabric_ops->check_release_cmd() as
target_core handles this directly for se_cmd->cmd_kref objects now.
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch converts the main ft_send_work() I/O path to use
target_submit_cmd() with a single se_cmd->cmd_kref reference
that is released via the existing ft_check_stop_free() response
path callback.
It also makes ft_send_tm() use transport_init_se_cmd() and
target_get_sess_cmd() to also use single se_cmd->cmd_kref
reference.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch adds a target_submit_cmd() caller that can be used by fabrics
to submit an uninitialized se_cmd descriptor to an struct se_session +
unpacked_lun from workqueue process context. This call will invoke the
following steps:
- transport_init_se_cmd() to setup se_cmd specific pointers
- Obtain se_cmd->cmd_kref references with target_get_sess_cmd()
- set se_cmd->t_tasks_bidi
- transport_lookup_cmd_lun() to setup struct se_cmd->se_lun from
the passed unpacked_lun
- transport_generic_allocate_tasks() to setup the passed *cdb, and
- transport_handle_cdb_direct() handle READ dispatch or WRITE
ready-to-transfer callback to fabric
v2 changes from hch feedback:
*) Add target_sc_flags_table for target_submit_cmd flags
*) Rename bidi parameter to flags, add TARGET_SCF_BIDI_OP
*) Convert checks to BUG_ON
*) Add out_check_cond for transport_send_check_condition_and_sense
usage
v3 changes:
*) Add TARGET_SCF_ACK_KREF for target_submit_cmd into
target_get_sess_cmd to determine when the fabric caller is expecting
a second kref_put() from fabric packet acknowledgement.
Cc: Christoph Hellwig <hch@lst.de>
Cc: Roland Dreier <roland@purestorage.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch moves target_put_sess_cmd() to use a se_cmd->cmd_kref
callback target_release_cmd_kref when performing driver release of
fabric->se_cmd descriptor memory. It sets the default cmd_kref
count value to '2' within target_get_sess_cmd() setup, and
currently assumes TFO->check_stop_free() usage.
It drops se_tfo->check_release_cmd() usage in the main
transport_release_cmd codepath.
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Current SCSI specs say that the "response format" field in the standard
INQUIRY response should be set to 2, and all the real SCSI devices I
have do put 2 here. So let's do that too.
Signed-off-by: Roland Dreier <roland@purestorage.com>
Cc: stable@kernel.org
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This includes:
- remove on _ in "__NAMELEN" in $fabric _make_tport
- target_fabric_configfs_init() returns an error pointer and not NULL
anymore. Consider that.
- replace (!(var_name)) with (!var_name). The extra () are not required
- remove #ifdef MODULE. If the code is builtin it needs an init function
or the code is useless
- put exit/clean functions into __exit
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch fixes TFO->release_cmd() and removes legacy pack_lun() usage
and new_cmd_failure when generating new TCM fabric skeleton from the
tcm_mod_builder.py script.
Reported-by: Stefan Bergstrand <stefan.bergstrand@sdsab.se>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
If we want dynamically allocated objects to be cacheline aligned we need
to tell that to the slab allocator by using the proper flags and not
by liberally sprinkling annotations onto all structures.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
There is not reason to artifically limit max_sectors in tcm_loop, set
it to UINT_MAX to allow stressing the large I/O handling in the target
core using the loopback driver. Also remove various superflous defines
hiding the values set in the host template.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch strips the trailing newline from backend device udev_path and
alias attributes.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This patch makes chap_server_compute_md5() use proper unsigned long
usage for the CHAP_I (identifier) and check for values beyond 255 as
per RFC-1994.
Reported-by: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
A reader should spend an extra moment whenever noticing a cast,
because either something special is going on that deserves extra
attention or, as is all too often the case, the code is wrong.
These casts, afaics, have all been useless. They cast a foo* to a
foo*, cast a void* to the assigned type, cast a foo* to void*, before
assigning it to a void* variable, etc.
In a few cases I also removed an additional &...[0], which is equally
useless.
Lastly I added three FIXMEs where, to the best of my judgement, the
code appears to have a bug. It would be good if someone could check
these.
Signed-off-by: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
- rename to target_check_cdb_and_preempt
- use non-safe list_for_each_entry
- move common check into callee (simplifying callers)
Signed-off-by: Joern Engel <joern@logfs.org>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
The command
| echo rd_pages=32768 > ramdisk/control
Does not work because it writes "rd_pages=32768\n" and the parser which
matches for "rd_pages=%d" does not recognize it due to the \n. One way
of fixing this would be using "echo -n" instead.
This patch adds \n to the list of separators so we don't have to use the
-n argument which I find is more convinient.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
There is no need to make task_state_active an atomic_t given that it is
always set under the execute_task_lock so we can make it a simple bool.
Also rename it to t_state_active to be closer to the list it guards,
and make sure all checks before the list addion/removal actually happen
under execute_task_lock.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
We only reach transport_complete_task once per task, so the test and set on
task_error_status is never going to have an effect.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
This reorganized the headers under include/target into:
- target_core_base.h stays as is with all target-wide data stuctures and defines
- target_core_backend.h contains the whole interface to I/O backends
- target_core_fabric.h contains the whole interface to fabric modules
Except for those only the various configfs macro headers stay around.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
Create a new headers, drivers/target/target_core_internal.h that is supposed
to hold all target_core-internal prototypes. Move all non-exported includes
from include/target to it, and merge the smaller prototype-only includes
inside drivers/target into it as well. Mark functions that were found to
not be called outside their implementation file static.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>
* git://git.samba.org/sfrench/cifs-2.6:
cifs: check for NULL last_entry before calling cifs_save_resume_key
cifs: attempt to freeze while looping on a receive attempt
cifs: Fix sparse warning when calling cifs_strtoUCS
CIFS: Add descriptions to the brlock cache functions
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, efi: Calling __pa() with an ioremap()ed address is invalid
x86, hpet: Immediately disable HPET timer 1 if rtc irq is masked
x86/intel_mid: Kconfig select fix
x86/intel_mid: Fix the Kconfig for MID selection
* 'spi/for-3.2' of git://git.pengutronix.de/git/wsa/linux-2.6:
spi/gpio: fix section mismatch warning
spi/fsl-espi: disable CONFIG_SPI_FSL_ESPI=m build
spi/nuc900: Include linux/module.h
spi/ath79: fix compile error due to missing include
* 'for-linus' of git://neil.brown.name/md:
md: raid5 crash during degradation
md/raid5: never wait for bad-block acks on failed device.
md: ensure new badblocks are handled promptly.
md: bad blocks shouldn't cause a Blocked status on a Faulty device.
md: take a reference to mddev during sysfs access.
md: refine interpretation of "hold_active == UNTIL_IOCTL".
md/lock: ensure updates to page_attrs are properly locked.
* git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
arch/tile: use new generic {enable,disable}_percpu_irq() routines
drivers/net/ethernet/tile: use skb_frag_page() API
asm-generic/unistd.h: support new process_vm_{readv,write} syscalls
arch/tile: fix double-free bug in homecache_free_pages()
arch/tile: add a few #includes and an EXPORT to catch up with kernel changes.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound:
ALSA: hda/realtek - Fix lost speaker volume controls
ALSA: hda/realtek - Create "Bass Speaker" for two speaker pins
ALSA: hda/realtek - Don't create extra controls with channel suffix
ALSA: hda - Fix remaining VREF mute-LED NID check in post-3.1 changes
ALSA: hda - Fix GPIO LED setup for IDT 92HD75 codecs
ASoC: Provide a more complete DMA driver stub
ASoC: Remove references to corgi and spitz from machine driver document
ASoC: Make SND_SOC_MX27VIS_AIC32X4 depend on I2C
ASoC: Fix dependency for SND_SOC_RAUMFELD and SND_PXA2XX_SOC_HX4700
ASoC: uda1380: Return proper error in uda1380_modinit failure path
ASoC: kirkwood: Make SND_KIRKWOOD_SOC_OPENRD and SND_KIRKWOOD_SOC_T5325 depend on I2C
ASoC: Mark WM8994 ADC muxes as virtual
ALSA: hda/realtek - Fix Oops in alc_mux_select()
ALSA: sis7019 - give slow codecs more time to reset
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf: Do no try to schedule task events if there are none
lockdep, kmemcheck: Annotate ->lock in lockdep_init_map()
perf header: Use event_name() to get an event name
perf stat: Failure with "Operation not supported"
In order to safely dereference current->real_parent inside an
rcu_read_lock, we need an rcu_dereference.
Signed-off-by: Mandeep Singh Baines <msb@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Modify initialization of PCIe capability registers in Tsi721 mport driver:
- change Completion Timeout value to avoid unexpected data transfer
aborts during intensive traffic.
- replace hardcoded offset of PCIe capability block by making it use the
common function.
This patch is applicable to kernel versions starting from 3.2-rc1.
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Bug fix for Tsi721 RapidIO mport driver: Tsi721 supports four RapidIO
mailboxes (MBOX0 - MBOX3) as defined by RapidIO specification. Mailbox
resources has to be properly reported to allow use of all available
mailboxes (initial version reports only MBOX0).
This patch is applicable to kernel versions staring from 3.2-rc1.
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace the pair dma_alloc_coherent()+memset() with the new
dma_zalloc_coherent() added by Andrew Morton for kernel version 3.2
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since commit a25cac5198 ("proc: Consider NO_HZ when printing idle and
iowait times") we are reporting idle/io_wait time also while a CPU is
tickless. We rely on get_{idle,iowait}_time functions to retrieve
proper data.
These functions, however, use usecs_to_cputime to translate micro
seconds time to cputime64_t. This is just an alias to usecs_to_jiffies
which reduces the data type from u64 to unsigned int and also checks
whether the given parameter overflows jiffies_to_usecs(MAX_JIFFY_OFFSET)
and returns MAX_JIFFY_OFFSET in that case.
When we overflow depends on CONFIG_HZ but especially for CONFIG_HZ_300
it is quite low (1431649781) so we are getting MAX_JIFFY_OFFSET for
>3000s! until we overflow unsigned int. Just for reference
CONFIG_HZ_100 has an overflow window around 20s, CONFIG_HZ_250 ~8s and
CONFIG_HZ_1000 ~2s.
This results in a bug when people saw [h]top going mad reporting 100%
CPU usage even though there was basically no CPU load. The reason was
simply that /proc/stat stopped reporting idle/io_wait changes (and
reported MAX_JIFFY_OFFSET) and so the only change happening was for user
system time.
Let's use nsecs_to_jiffies64 instead which doesn't reduce the precision
to 32b type and it is much more appropriate for cumulative time values
(unlike usecs_to_jiffies which intended for timeout calculations).
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Artem S. Tashkinov <t.artem@mailcity.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit f5252e00 ("mm: avoid null pointer access in vm_struct via
/proc/vmallocinfo") adds newly allocated vm_structs to the vmlist after
it is fully initialised. Unfortunately, it did not check that
__vmalloc_area_node() successfully populated the area. In the event of
allocation failure, the vmalloc area is freed but the pointer to freed
memory is inserted into the vmlist leading to a a crash later in
get_vmalloc_info().
This patch adds a check for ____vmalloc_area_node() failure within
__vmalloc_node_range. It does not use "goto fail" as in the previous
error path as a warning was already displayed by __vmalloc_area_node()
before it called vfree in its failure path.
Credit goes to Luciano Chavez for doing all the real work of identifying
exactly where the problem was.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Luciano Chavez <lnx1138@linux.vnet.ibm.com>
Tested-by: Luciano Chavez <lnx1138@linux.vnet.ibm.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: <stable@vger.kernel.org> [3.1.x+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
setup_zone_migrate_reserve() expects that zone->start_pfn starts at
pageblock_nr_pages aligned pfn otherwise we could access beyond an
existing memblock resulting in the following panic if
CONFIG_HOLES_IN_ZONE is not configured and we do not check pfn_valid:
IP: [<c02d331d>] setup_zone_migrate_reserve+0xcd/0x180
*pdpt = 0000000000000000 *pde = f000ff53f000ff53
Oops: 0000 [#1] SMP
Pid: 1, comm: swapper Not tainted 3.0.7-0.7-pae #1 VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform
EIP: 0060:[<c02d331d>] EFLAGS: 00010006 CPU: 0
EIP is at setup_zone_migrate_reserve+0xcd/0x180
EAX: 000c0000 EBX: f5801fc0 ECX: 000c0000 EDX: 00000000
ESI: 000c01fe EDI: 000c01fe EBP: 00140000 ESP: f2475f58
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Process swapper (pid: 1, ti=f2474000 task=f2472cd0 task.ti=f2474000)
Call Trace:
[<c02d389c>] __setup_per_zone_wmarks+0xec/0x160
[<c02d3a1f>] setup_per_zone_wmarks+0xf/0x20
[<c08a771c>] init_per_zone_wmark_min+0x27/0x86
[<c020111b>] do_one_initcall+0x2b/0x160
[<c086639d>] kernel_init+0xbe/0x157
[<c05cae26>] kernel_thread_helper+0x6/0xd
Code: a5 39 f5 89 f7 0f 46 fd 39 cf 76 40 8b 03 f6 c4 08 74 32 eb 91 90 89 c8 c1 e8 0e 0f be 80 80 2f 86 c0 8b 14 85 60 2f 86 c0 89 c8 <2b> 82 b4 12 00 00 c1 e0 05 03 82 ac 12 00 00 8b 00 f6 c4 08 0f
EIP: [<c02d331d>] setup_zone_migrate_reserve+0xcd/0x180 SS:ESP 0068:f2475f58
CR2: 00000000000012b4
We crashed in pageblock_is_reserved() when accessing pfn 0xc0000 because
highstart_pfn = 0x36ffe.
The issue was introduced in 3.0-rc1 by 6d3163ce ("mm: check if any page
in a pageblock is reserved before marking it MIGRATE_RESERVE").
Make sure that start_pfn is always aligned to pageblock_nr_pages to
ensure that pfn_valid s always called at the start of each pageblock.
Architectures with holes in pageblocks will be correctly handled by
pfn_valid_within in pageblock_is_reserved.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Tested-by: Dang Bo <bdang@vmware.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Arve Hjnnevg <arve@android.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> [3.0+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
