- 08 Nov, 2013 40 commits
-
-
Bartlomiej Zolnierkiewicz authored
Cc: Akhil Bhansali <abhansali@stec-inc.com> Cc: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Bartlomiej Zolnierkiewicz authored
register_blkdev() is called before pci_register_driver() in skd_init() so unregister_blkdev() should be called after pci_unregister_driver() in skd_exit(). Fix it. Cc: Akhil Bhansali <abhansali@stec-inc.com> Cc: Jeff Moyer <jmoyer@redhat.com> Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Mike Snitzer authored
Remove skd_flush_cmd structure and skd_flush_slab. Remove skd_end_request wrapper around skd_end_request_blk. Remove skd_requeue_request, use blk_requeue_request directly. Cleanup some comments (remove "bio" info) and whitespace. Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Jens Axboe authored
Just call the block functions directly, don't wrap them in skd helpers. With only one queueing model enabled, there's no point in doing that. Also kill the ->start_time and ->bio from the skd_request_context, we don't use those anymore. Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Jens Axboe authored
The skd driver has a selectable rq or bio based queueing model. For 3.14, we want to turn this into a single blk-mq interface instead. With the immutable biovecs being merged in 3.13, the bio model would need patches to even work. So rip it out, with a conversion pending for blk-mq in the next release. Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Wei Yongjun authored
Fix to return -ENOMEM in the skd construct error handling case instead of 0, as done elsewhere in this function. Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Heiko Carstens authored
"elevator: Fix a race in elevator switching and md device initialization" changed the semantics of elevator_init() in a way that now enforces to hold the corresponding request queue's sysfs_lock when calling elevator_init() to fix a race. The patch did not convert the s390 dasd device driver which is the only device driver which also calls elevator_init(). So add the missing locking. Cc: Tomoki Sekiyama <tomoki.sekiyama@hds.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Stephen M. Cameron authored
A return value of 1 is interpreted as an error Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
rchinthekindi authored
Replaced DPRINTK() and VPRINTK() with pr_debug(). Signed-off-by: Ramprasad C <ramprasad.chinthekindi@hgst.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Akhil Bhansali authored
This patch fixes checkpatch.pl errors for assignment in if condition. It also removes unused readq / readl function calls. As Andrew had disabled the compilation of drivers for 32 bit, I have modified format specifiers in few VPRINTKs to avoid warnings during 64 bit compilation. Signed-off-by: Akhil Bhansali <abhansali@stec-inc.com> Reviewed-by: Ramprasad Chinthekindi <rchinthekindi@stec-inc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philip J Kelleher authored
This patch fixes a possible Kernel Panic on driver load if the configuration on the card is messed up or not yet set. The driver could possible give a 32 bit unsigned all Fs to the kernel as the device's block size. Now we only write the block size to the kernel if the configuration from the card is valid. Also, driver version is being updated. Signed-off-by: Philip J Kelleher <pjk1939@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philip J Kelleher authored
This patch fixes a bug in which discards were always calling pci_unmap_page. Discards should never call the pci_unmap_page function call because they are never mapped. This caused a race condition on PowerPC systems when issuing discards, writes, and reads all at the same time. The pci_map_page function would eventually map logical address 0 for a read or write. Discards are always assigned a DMA address of 0 because they are never mapped. So if pci_map_page mapped address 0 for a DMA and a discard was "unmapped" then the address would be freed and would cause an EEH event to occur when Hardware accesses the address. This was injected/uncovered in commit: b347f9cf0bc8d42ee95ba1d3837fd93045ab336b The pci_dma_mapping_error function declares -1 a DMA_ERROR not 0 like initially thought So before we would never unmap discards because they were considered NULL. This patch should fall on top of commit id: fc1967bb08a6184ed44ef990e1dd4389901b809c Also, the driver version is being up dated. Signed-off-by: Philip J Kelleher <pjk1939@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Lars Ellenberg authored
For a long time, the receiving side has spread "too large" incoming requests over multiple bios. No need to shrink our max_bio_size (max_hw_sectors) if the peer is reconfigured to use a different storage. The problem manifests itself if we are not the top of the device stack (DRBD is used a LVM PV). A hardware reconfiguration on the peer may cause the supported max_bio_size to shrink, and the connection handshake would now unnecessarily shrink the max_bio_size on the active node. There is no way to notify upper layers that they have to "re-stack" their limits. So they won't notice at all, and may keep submitting bios that are suddenly considered "too large for device". We already check for compatibility and ignore changes on the peer, the code only was masked out unless we have a fully established connection. We just need to allow it a bit earlier during the handshake. Also consider max_hw_sectors in our merge bvec function, just in case. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Lars Ellenberg authored
Symptoms: disconnect after bitmap exchange due to bitmap overflow (e:49731075554) while decoding bm RLE packet In the decoding step of the variable length integer run length encoding there was potentially an uncatched bitshift by wordsize (variable >> 64). The result of which is "undefined" :( (only "sometimes" the result is the desired 0) Fix: don't do any bit shift magic for shift == 64, just assign. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philipp Reisner authored
Online adding of new minors with freshly created meta data to an resource with an established connection failed, with a wrong state transition on one side on one side of the new minor. Freshly created meta-data has a la_size (last agreed size) of 0. When we online add such devices, the code wrongly got into the code path for resyncing new storage that was added while the disk was detached. Fixed that by making the GREW from ZERO a special case. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philipp Reisner authored
Since drbd-8.4.0 it is possible to change the allow-two-primaries network option while the connection is established. The sequence code used to partially order packets from the data socket with packets from the meta-data socket, still assued that the allow-two-primaries option is constant while the connection is established. I.e. On a node that has the RESOLVE_CONFLICTS bits set, after enabling allow-two-primaries, when receiving the next data packet it timed out while waiting for the necessary packets on the data socket to arrive (wait_for_and_update_peer_seq() function). Fixed that by always tracking the sequence number, but only waiting for it if allow-two-primaries is set. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Lars Ellenberg authored
If we want to iterate over the (as of yet still empty) list in the cleanup path, we need to initialize the list before the first goto fail. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Jens Axboe authored
Mike writes: "cpqarray hasn't been used in over 12 years. It's doubtful that anyone still uses the board. It's time the driver was removed from the mainline kernel. The only updates these days are minor and mostly done by people outside of HP." If nobody yells, we'll remove it from the kernel tree completely for 3.15. Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Akhil Bhansali authored
Signed-off-by: Akhil Bhansali <abhansali@stec-inc.com> Signed-off-by: Ramprasad Chinthekindi <rchinthekindi@stec-inc.com> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> Folded patch, contributions to clean up this driver from: Jens Axboe Dan Carpenter Andrew Morton Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philip J Kelleher authored
This fixes a kernel panic injected by commit id 8d26750143341831bc312f61c5ed141eeb75b8d0 where discards are getting mapped through the pci_map_page function call. The driver will now start verifying that a dma is not a discard before issuing a the pci_map_page function call. Also, we are updating the driver version. Signed-off-by: Philip J Kelleher <pjk1939@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
David Milburn authored
Dynamically allocate buf to prevent warnings: drivers/block/mtip32xx/mtip32xx.c: In function ‘mtip_hw_read_device_status’: drivers/block/mtip32xx/mtip32xx.c:2823: warning: the frame size of 1056 bytes is larger than 1024 bytes drivers/block/mtip32xx/mtip32xx.c: In function ‘mtip_hw_read_registers’: drivers/block/mtip32xx/mtip32xx.c:2894: warning: the frame size of 1056 bytes is larger than 1024 bytes drivers/block/mtip32xx/mtip32xx.c: In function ‘mtip_hw_read_flags’: drivers/block/mtip32xx/mtip32xx.c:2917: warning: the frame size of 1056 bytes is larger than 1024 bytes Signed-off-by: David Milburn <dmilburn@redhat.com> Acked-by: Asai Thambi S P <asamymuthupa@micron.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Asai Thambi S P authored
This patch add support for SRSI(Surprise Removal Surprise Insertion). Approach: --------- Surprise Removal: ----------------- On surprise removal of the device, gendisk, request queue, device index, sysfs entries, etc are retained as long as device is in use - mounted filesystem, device opened by an application, etc. The service thread breaks out of the main while loop, waits for pci remove to exit, and then waits for device to become free. When there no holders of the device, service thread cleans up the block and device related stuff and returns. Surprise Insertion: ------------------- No change, this scenario follows the normal pci probe() function flow. Signed-off-by: Asai Thambi S P <asamymuthupa@micron.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philip J Kelleher authored
The pci_map_page function has been moved into our issued workqueue to prevent an us running out of mappable addresses on non-HWWD PCIe x8 slots. The maximum amount that can possible be mapped at one time now is: 255 dmas X 4 dma channels X 4096 Bytes. Signed-off-by: Philip J Kelleher <pjk1939@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Philip J Kelleher authored
The rsxx driver was not checking the correct value during a pci_map_page failure. Fixing this also uncovered a double free if the bio was returned before it was broken up into indiviadual 4k dmas, that is also fixed here. Signed-off-by: Philip J Kelleher <pjk1939@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Mikulas Patocka authored
When the loop module is loaded, it creates 8 loop devices /dev/loop[0-7]. The devices have no request routine and thus, when they are used without being assigned, a crash happens. For example, these commands cause crash (assuming there are no used loop devices): Kernel Fault: Code=26 regs=000000007f420980 (Addr=0000000000000010) CPU: 1 PID: 50 Comm: kworker/1:1 Not tainted 3.11.0 #1 Workqueue: ksnaphd do_metadata [dm_snapshot] task: 000000007fcf4078 ti: 000000007f420000 task.ti: 000000007f420000 [ 116.319988] YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI PSW: 00001000000001001111111100001111 Not tainted r00-03 000000ff0804ff0f 00000000408bf5d0 00000000402d8204 000000007b7ff6c0 r04-07 00000000408a95d0 000000007f420950 000000007b7ff6c0 000000007d06c930 r08-11 000000007f4205c0 0000000000000001 000000007f4205c0 000000007f4204b8 r12-15 0000000000000010 0000000000000000 0000000000000000 0000000000000000 r16-19 000000001108dd48 000000004061cd7c 000000007d859800 000000000800000f r20-23 0000000000000000 0000000000000008 0000000000000000 0000000000000000 r24-27 00000000ffffffff 000000007b7ff6c0 000000007d859800 00000000408a95d0 r28-31 0000000000000000 000000007f420950 000000007f420980 000000007f4208e8 sr00-03 0000000000000000 0000000000000000 0000000000000000 0000000000303000 sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 117.549988] IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000402d82fc 00000000402d8300 IIR: 53820020 ISR: 0000000000000000 IOR: 0000000000000010 CPU: 1 CR30: 000000007f420000 CR31: ffffffffffffffff ORIG_R28: 0000000000000001 IAOQ[0]: generic_make_request+0x11c/0x1a0 IAOQ[1]: generic_make_request+0x120/0x1a0 RP(r2): generic_make_request+0x24/0x1a0 Backtrace: [<00000000402d83f0>] submit_bio+0x70/0x140 [<0000000011087c4c>] dispatch_io+0x234/0x478 [dm_mod] [<0000000011087f44>] sync_io+0xb4/0x190 [dm_mod] [<00000000110883bc>] dm_io+0x2c4/0x310 [dm_mod] [<00000000110bfcd0>] do_metadata+0x28/0xb0 [dm_snapshot] [<00000000401591d8>] process_one_work+0x160/0x460 [<0000000040159bc0>] worker_thread+0x300/0x478 [<0000000040161a70>] kthread+0x118/0x128 [<0000000040104020>] end_fault_vector+0x20/0x28 [<0000000040177220>] task_tick_fair+0x420/0x4d0 [<00000000401aa048>] invoke_rcu_core+0x50/0x60 [<00000000401ad5b8>] rcu_check_callbacks+0x210/0x8d8 [<000000004014aaa0>] update_process_times+0xa8/0xc0 [<00000000401ab86c>] rcu_process_callbacks+0x4b4/0x598 [<0000000040142408>] __do_softirq+0x250/0x2c0 [<00000000401789d0>] find_busiest_group+0x3c0/0xc70 [ 119.379988] Kernel panic - not syncing: Kernel Fault Rebooting in 1 seconds.. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Vegard Nossum authored
If the permission check fails, we drop a reference to the blkif without having taken it in the first place. The bug was introduced in commit 604c499c (xen/blkback: Check device permissions before allowing OP_DISCARD). Cc: stable@vger.kernel.org Cc: Jan Beulich <JBeulich@suse.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Roger Pau Monne authored
Improve the calculation of required grants to process a request by using nr_phys_segments instead of always assuming a request is going to use all posible segments. nr_phys_segments contains the number of scatter-gather DMA addr+len pairs, which is basically what we put at every granted page. for_each_sg iterates over the DMA addr+len pairs and uses a grant page for each of them. Signed-off-by: Roger Pau Monné <roger.pau@citrix.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: David Vrabel <david.vrabel@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Roger Pau Monne authored
There's no need to keep the foreign access in a grant if it is not persistently mapped by the backend. This allows us to free grants that are not mapped by the backend, thus preventing blkfront from hoarding all grants. The main effect of this is that blkfront will only persistently map the same grants as the backend, and it will always try to use grants that are already mapped by the backend. Also the number of persistent grants in blkfront is the same as in blkback (and is controlled by the value in blkback). Signed-off-by: Roger Pau Monné <roger.pau@citrix.com> Reviewed-by: David Vrabel <david.vrabel@citrix.com> Acked-by: Matt Wilson <msw@amazon.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: David Vrabel <david.vrabel@citrix.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Michael Opdenacker authored
This patch proposes to remove the use of the IRQF_DISABLED flag It's a NOOP since 2.6.35 and it will be removed one day. Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Duan Jiong authored
This patch fixes coccinelle error regarding usage of IS_ERR and PTR_ERR instead of PTR_ERR_OR_ZERO. Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Duan Jiong authored
This patch fixes coccinelle error regarding usage of IS_ERR and PTR_ERR instead of PTR_ERR_OR_ZERO. Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Geert Uytterhoeven authored
do_div() (called by sector_div() if CONFIG_LBDAF=y) is meant for divisions of 64-bit number by 32-bit numbers. Passing 64-bit divisor types caused issues in the past on 32-bit platforms, cfr. commit ea077b1b ("m68k: Truncate base in do_div()"). As queue_limits.max_discard_sectors and .discard_granularity are unsigned int, max_discard_sectors and granularity should be unsigned int. As bdev_discard_alignment() returns int, alignment should be int. Now 2 calls to sector_div() can be replaced by 32-bit arithmetic: - The 64-bit modulo operation can become a 32-bit modulo operation, - The 64-bit division and multiplication can be replaced by a 32-bit modulo operation and a subtraction. Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Chen Gang authored
do_blk_trace_setup() will fully initialize 'buts.name', so can remove the related memcpy(). And also use BLKTRACE_BDEV_SIZE and ARRAY_SIZE instead of hard code number '32'. Signed-off-by: Chen Gang <gang.chen@asianux.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Kent Overstreet authored
Someone cut and pasted md's md_trim_bio() into xen-blkfront.c. Come on, we should know better than this. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Neil Brown <neilb@suse.de> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Kent Overstreet authored
No need for silly open coding - and struct sg_iovec has exactly the same layout as struct iovec... Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Alireza Haghdoost authored
This patch enables the sysfs to control I/O request merge functionality in the plug list. While this control has been implemented for the request queue, it was dismissed in the plug list. Therefore, block layer merges requests together (or attempt to merge) even if the merge capability was disable using sysfs nomerge parameter value 2. This limitation is directly affects functionality of io_submit() system call. The system call enables user to submit a bunch of IO requests from user space using struct iocb **ios input argument. However, the unconditioned merging functionality in the plug list potentially merges these requests together down the road. Therefore, there is no way to distinguish between an application sending bunch of sequential IOs and an application sending one big IO. Ultimately, all requests generated by the former app merge within the plug list together and looks similar to the second app. While the merging functionality is a desirable feature to improve the performance of IO subsystem for some applications, it is not useful for other application like ours at all. Signed-off-by: Alireza Haghdoost <alireza@cs.umn.edu> Reviewed-by: Jeff Moyer <jmoyer@redhat.com> Coding style modified. Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Mike Snitzer authored
Without this patch all DM devices will default to BLK_MAX_SEGMENT_SIZE (65536) even if the underlying device(s) have a larger value -- this is due to blk_stack_limits() using min_not_zero() when stacking the max_segment_size limit. 1073741824 before patch: 65536 after patch: 1073741824 Reported-by: Lukasz Flis <l.flis@cyfronet.pl> Signed-off-by: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # v3.3+ Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Tomoki Sekiyama authored
Add locking of q->sysfs_lock into elevator_change() (an exported function) to ensure it is held to protect q->elevator from elevator_init(), even if elevator_change() is called from non-sysfs paths. sysfs path (elv_iosched_store) uses __elevator_change(), non-locking version, as the lock is already taken by elv_iosched_store(). Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama@hds.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Tomoki Sekiyama authored
The soft lockup below happens at the boot time of the system using dm multipath and the udev rules to switch scheduler. [ 356.127001] BUG: soft lockup - CPU#3 stuck for 22s! [sh:483] [ 356.127001] RIP: 0010:[<ffffffff81072a7d>] [<ffffffff81072a7d>] lock_timer_base.isra.35+0x1d/0x50 ... [ 356.127001] Call Trace: [ 356.127001] [<ffffffff81073810>] try_to_del_timer_sync+0x20/0x70 [ 356.127001] [<ffffffff8118b08a>] ? kmem_cache_alloc_node_trace+0x20a/0x230 [ 356.127001] [<ffffffff810738b2>] del_timer_sync+0x52/0x60 [ 356.127001] [<ffffffff812ece22>] cfq_exit_queue+0x32/0xf0 [ 356.127001] [<ffffffff812c98df>] elevator_exit+0x2f/0x50 [ 356.127001] [<ffffffff812c9f21>] elevator_change+0xf1/0x1c0 [ 356.127001] [<ffffffff812caa50>] elv_iosched_store+0x20/0x50 [ 356.127001] [<ffffffff812d1d09>] queue_attr_store+0x59/0xb0 [ 356.127001] [<ffffffff812143f6>] sysfs_write_file+0xc6/0x140 [ 356.127001] [<ffffffff811a326d>] vfs_write+0xbd/0x1e0 [ 356.127001] [<ffffffff811a3ca9>] SyS_write+0x49/0xa0 [ 356.127001] [<ffffffff8164e899>] system_call_fastpath+0x16/0x1b This is caused by a race between md device initialization by multipathd and shell script to switch the scheduler using sysfs. - multipathd: SyS_ioctl -> do_vfs_ioctl -> dm_ctl_ioctl -> ctl_ioctl -> table_load -> dm_setup_md_queue -> blk_init_allocated_queue -> elevator_init q->elevator = elevator_alloc(q, e); // not yet initialized - sh -c 'echo deadline > /sys/$DEVPATH/queue/scheduler': elevator_switch (in the call trace above) struct elevator_queue *old = q->elevator; q->elevator = elevator_alloc(q, new_e); elevator_exit(old); // lockup! (*) - multipathd: (cont.) err = e->ops.elevator_init_fn(q); // init fails; q->elevator is modified (*) When del_timer_sync() is called, lock_timer_base() will loop infinitely while timer->base == NULL. In this case, as timer will never initialized, it results in lockup. This patch introduces acquisition of q->sysfs_lock around elevator_init() into blk_init_allocated_queue(), to provide mutual exclusion between initialization of the q->scheduler and switching of the scheduler. This should fix this bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=902012Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama@hds.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-
Christoph Lameter authored
__get_cpu_var() is used for multiple purposes in the kernel source. One of them is address calculation via the form &__get_cpu_var(x). This calculates the address for the instance of the percpu variable of the current processor based on an offset. Other use cases are for storing and retrieving data from the current processors percpu area. __get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment. __get_cpu_var() is defined as : #define __get_cpu_var(var) (*this_cpu_ptr(&(var))) __get_cpu_var() always only does an address determination. However, store and retrieve operations could use a segment prefix (or global register on other platforms) to avoid the address calculation. this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use optimized assembly code to read and write per cpu variables. This patch converts __get_cpu_var into either an explicit address calculation using this_cpu_ptr() or into a use of this_cpu operations that use the offset. Thereby address calculations are avoided and less registers are used when code is generated. At the end of the patch set all uses of __get_cpu_var have been removed so the macro is removed too. The patch set includes passes over all arches as well. Once these operations are used throughout then specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by f.e. using a global register that may be set to the per cpu base. Transformations done to __get_cpu_var() 1. Determine the address of the percpu instance of the current processor. DEFINE_PER_CPU(int, y); int *x = &__get_cpu_var(y); Converts to int *x = this_cpu_ptr(&y); 2. Same as #1 but this time an array structure is involved. DEFINE_PER_CPU(int, y[20]); int *x = __get_cpu_var(y); Converts to int *x = this_cpu_ptr(y); 3. Retrieve the content of the current processors instance of a per cpu variable. DEFINE_PER_CPU(int, y); int x = __get_cpu_var(y) Converts to int x = __this_cpu_read(y); 4. Retrieve the content of a percpu struct DEFINE_PER_CPU(struct mystruct, y); struct mystruct x = __get_cpu_var(y); Converts to memcpy(&x, this_cpu_ptr(&y), sizeof(x)); 5. Assignment to a per cpu variable DEFINE_PER_CPU(int, y) __get_cpu_var(y) = x; Converts to this_cpu_write(y, x); 6. Increment/Decrement etc of a per cpu variable DEFINE_PER_CPU(int, y); __get_cpu_var(y)++ Converts to this_cpu_inc(y) Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-