- 09 May, 2007 40 commits
-
-
Ken Chen authored
The internal hugetlb resv_huge_pages variable can permanently leak nonzero value in the error path of hugetlb page fault handler when hugetlb page is used in combination of cpuset. The leaked count can permanently trap N number of hugetlb pages in unusable "reserved" state. Steps to reproduce the bug: (1) create two cpuset, user1 and user2 (2) reserve 50 htlb pages in cpuset user1 (3) attempt to shmget/shmat 50 htlb page inside cpuset user2 (4) kernel oom the user process in step 3 (5) ipcrm the shm segment At this point resv_huge_pages will have a count of 49, even though there are no active hugetlbfs file nor hugetlb shared memory segment in the system. The leak is permanent and there is no recovery method other than system reboot. The leaked count will hold up all future use of that many htlb pages in all cpusets. The culprit is that the error path of alloc_huge_page() did not properly undo the change it made to resv_huge_page, causing inconsistent state. Signed-off-by:
Ken Chen <kenchen@google.com> Cc: David Gibson <david@gibson.dropbear.id.au> Cc: Adam Litke <agl@us.ibm.com> Cc: Martin Bligh <mbligh@google.com> Acked-by:
David Gibson <dwg@au1.ibm.com> Cc: <stable@kernel.org> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Jonathan Brassow authored
This patch removes the possibility of having uninitialized log state if the log device has failed. When a mirror resumes operation, it calls 'resume' on the logging module. If disk based logging is being used, the log device is read to fill in the log state. If the log device has failed, we cannot simply return, because this would leave the in-memory log state uninitialized. Instead, we assume all regions are out-of-sync and reset the log state. Failure to do this could result in the logging code reporting a region as in-sync, even though it isn't; which could result in a corrupted mirror. Signed-off-by:
Jonathan Brassow <jbrassow@redhat.com> Signed-off-by:
Alasdair G Kergon <agk@redhat.com> Signed-off-by:
-
Jonathan Brassow authored
The call to rh_in_sync() in do_reads() should be allowed to block. It is in the mirror worker thread which already permits blocking operations. This will be needed to support clustered mirroring which will perform network operations. Signed-off-by:
-
Jonathan Brassow authored
With the code as it is, it is possible for oustanding clear region requests never to get flushed when a mirror is deactivated or suspended. This means there will always be some resync work required when a mirror is activated, even though it may very well be in-sync. Always requesting the flush doesn't hurt us. This is because the log tracks whether any changes occurred and, if not, no flush is performed. Signed-off-by:
-
Heinz Mauelshagen authored
New device-mapper target that can delay I/O (for testing). Reads can be separated from writes, redirected to different underlying devices and delayed by differing amounts of time. Signed-off-by:
Heinz Mauelshagen <mauelshagen@redhat.com> Signed-off-by:
Milan Broz <mbroz@redhat.com> Signed-off-by:
-
Heinz Mauelshagen authored
More bio_list helper functions for new targets (including dm-delay and dm-loop) to manipulate lists of bios. Signed-off-by:
Heinz Mauelshagen <hjm@redhat.com> Signed-off-by:
Bryn Reeves <breeves@redhat.com> Signed-off-by:
-
Milan Broz authored
Remove old dm-io interface. Signed-off-by:
-
Milan Broz authored
This patch ports dm-raid1.c to the new dm-io interface. Signed-off-by:
-
Heinz Mauelshagen authored
This patch ports dm-log.c to the new dm-io interface in order to make it scalable to have a large number of persistent dirty logs active in parallel. Signed-off-by:
Heinz Mauelshagen <heinzm@redhat.com> Cc: Milan Broz <mbroz@redhat.com> Signed-off-by:
-
Heinz Mauelshagen authored
This patch ports dm-exception-store.c to the new, scalable dm_io() interface. It replaces dm_io_get()/dm_io_put() by dm_io_client_create()/dm_io_client_destroy() calls and dm_io_sync_vm() by dm_io() to achive this. Signed-off-by:
-
Milan Broz authored
This patch ports kcopyd.c to the new, scalable dm_io() interface. Signed-off-by:
-
Heinz Mauelshagen authored
Add a new API to dm-io.c that uses a private mempool and bio_set for each client. The new functions to use are dm_io_client_create(), dm_io_client_destroy(), dm_io_client_resize() and dm_io(). Signed-off-by:
-
Heinz Mauelshagen authored
Introduce struct dm_io_client to prepare for per-client mempools and bio_sets. Temporary functions bios() and io_pool() choose between the per-client structures and the global ones so the old and new interfaces can co-exist. Make error_bits optional. Signed-off-by:
-
Heinz Mauelshagen authored
Delay decrementing the 'struct io' reference count until after the bio has been freed so that a bio destructor function may reference it. Required by a later patch. Signed-off-by:
-
Jonathan E Brassow authored
This patch adds the ability to specify desired features in the mirror constructor/mapping table. The first feature of interest is "handle_errors". Currently, mirroring will ignore any I/O errors from the devices. Subsequent patches will check for this flag and handle the errors. If flag/feature is not present, mirror will do nothing - maintaining backwards compatibility. Signed-off-by:
-
Jonathan E Brassow authored
This patch reports the status of the log device so that userspace can detect the error and take appropriate action. Signed-off-by:
-
Jonathan E Brassow authored
This patch gives the disk logging code the ability to store the fact that an error occured on the log device. In addition, an event is raised when an error is encountered during I/O to the log device. Signed-off-by:
-
Mike Anderson authored
Allow check_device_area to succeed if a device has an i_size of zero. This addresses an issue seen on DASD devices setting up a multipath table for paths in online and offline state. Signed-off-by:
Mike Anderson <andmike@us.ibm.com> Signed-off-by:
-
Edward Goggin authored
Make the mapped device structure accessible to hardware handlers so error messages can include the device name. Signed-off-by:
Edward Goggin <egoggin@emc.com> Signed-off-by:
-
Ludwig Nussel authored
Add a new IV generation method 'null' to read old filesystem images created with SuSE's loop_fish2 module. Signed-off-by:
Ludwig Nussel <ludwig.nussel@suse.de> Acked-By:
Christophe Saout <christophe@saout.de> Signed-off-by:
-
Olaf Kirch authored
Allocate smaller clones With the previous dm-crypt fixes, there is no need for the clone bios to have the same bvec size as the original - we just need to make them big enough for the remaining number of pages. The only requirement is that we clear the "out" index in convert_context, so that crypt_convert starts storing data at the right position within the clone bio. Signed-off-by:
Olaf Kirch <olaf.kirch@oracle.com> Signed-off-by:
-
Olaf Kirch authored
Get rid of first_clone in dm-crypt This gets rid of first_clone, which is not really needed. Apparently, cloned bios used to share their bvec some time way in the past - this is no longer the case. Contrarily, this even hurts us if we try to create a clone off first_clone after it has completed, and crypt_endio has destroyed its bvec. Signed-off-by:
-
Olaf Kirch authored
Do not access the bio after generic_make_request We should never access a bio after generic_make_request - there's no guarantee it still exists. Signed-off-by:
-
Olaf Kirch authored
Call clone_init early We need to call clone_init as early as possible - at least before call bio_put(clone) in any error path. Otherwise, the destructor will try to dereference bi_private, which may still be NULL. Signed-off-by:
-
Milan Broz authored
Disable barriers in dm-crypt because of current workqueue processing can reorder requests. This must be addresed later but for now disabling barriers is needed to prevent data corruption. Signed-off-by:
-
Holger Smolinski authored
This patch replaces the single instance of kmirrord by one instance per mirror set. This change is required to avoid a deadlock in kmirrord when the persistent dirty log of a mirror itself resides on a mirror. The single instance of kmirrord then issues a sync write to the dirty log in write_bits which gets deferred to kmirrord itself later in the call chain. But kmirrord never does the deferred work because it is still waiting for the sync write_bits. _mirror_sets is removed as it no longer needed, and we always flush the workqueue before destroying it to ensure all work is complete before destroying it. Signed-off-by:
Holger Smolinski <smolinski@de.ibm.com> Signed-off-by:
-
Christoph Lameter authored
This is done in order to be able to run SLUB which expects no modifications to its page structs. Signed-off-by:
Christoph Lameter <clameter@sgi.com> Signed-off-by:
David Howells <dhowells@redhat.com> Signed-off-by:
-
Christoph Lameter authored
Fix some of the spelling issues. Fix sentences. Discourage SLOB use since SLUB can pack objects denser. Signed-off-by:
-
Pekka J Enberg authored
No "blank" (or "*") line is allowed between the function name and lines for it parameter(s). Cc: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by:
Pekka Enberg <penberg@cs.helsinki.fi> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by:
-
Christoph Lameter authored
In some cases SLUB is creating uselessly slabs that are larger than slub_max_order. Also the layout of some of the slabs was not satisfactory. Go to an iterarive approach. Signed-off-by:
-
Christoph Lameter authored
We have information about how long an object existed and about the nodes and cpus where the allocations and frees took place. Add that information to the tracking output in /sys/slab/xx/alloc_calls and /sys/slab/free_calls This will then enable slabinfo to output nice reports like this: christoph@qirst:~/slub$ ./slabinfo kmalloc-128 Slabcache: kmalloc-128 Aliases: 0 Order : 0 Sizes (bytes) Slabs Debug Memory ------------------------------------------------------------------------ Object : 128 Total : 12 Sanity Checks : On Total: 49152 SlabObj: 200 Full : 7 Redzoning : On Used : 24832 SlabSiz: 4096 Partial: 4 Poisoning : On Loss : 24320 Loss : 72 CpuSlab: 1 Tracking : On Lalig: 13968 Align : 8 Objects: 20 Tracing : Off Lpadd: 1152 kmalloc-128 has no kmem_cache operations kmalloc-128: Kernel object allocation ----------------------------------------------------------------------- 6 param_sysfs_setup+0x71/0x130 age=284512/284512/284512 pid=1 nodes=0-1,3 11 percpu_populate+0x39/0x80 age=283914/284428/284512 pid=1 nodes=0 21 __register_chrdev_region+0x31/0x170 age=282896/284347/284473 pid=1-1705 nodes=0-2 1 sys_inotify_init+0x76/0x1c0 age=283423 pid=1004 nodes=0 19 as_get_io_context+0x32/0xd0 age=6/247567/283988 pid=1-11782 nodes=0,2 10 ida_pre_get+0x4a/0x80 age=277666/283773/284526 pid=0-2177 nodes=0,2 24 kobject_kset_add_dir+0x37/0xb0 age=282727/283860/284472 pid=1-1723 nodes=0-2 1 acpi_ds_build_internal_buffer_obj+0xd3/0x11d age=284508 pid=1 nodes=0 24 con_insert_unipair+0xd7/0x110 age=284438/284438/284438 pid=1 nodes=0,2 1 uart_open+0x2d2/0x4b0 age=283896 pid=1 nodes=0 26 dma_pool_create+0x73/0x1a0 age=282762/282833/282916 pid=1705-1723 nodes=0 1 neigh_table_init_no_netlink+0xd2/0x210 age=284461 pid=1 nodes=0 2 neigh_parms_alloc+0x2b/0xe0 age=284410/284411/284412 pid=1 nodes=2 2 neigh_resolve_output+0x1e1/0x280 age=276289/276291/276293 pid=0-2443 nodes=0 1 netlink_kernel_create+0x90/0x170 age=284472 pid=1 nodes=0 4 xt_alloc_table_info+0x39/0xf0 age=283958/283958/283959 pid=1 nodes=1 3 fn_hash_insert+0x473/0x720 age=277653/277661/277666 pid=2177-2185 nodes=0 1 get_mtrr_state+0x285/0x2a0 age=284526 pid=0 nodes=0 1 cacheinfo_cpu_callback+0x26d/0x3e0 age=284458 pid=1 nodes=0 29 kernel_param_sysfs_setup+0x25/0x90 age=284511/284511/284512 pid=1 nodes=0-1,3 5 process_zones+0x5e/0x170 age=284546/284546/284546 pid=0 nodes=0 1 drm_core_init+0x48/0x160 age=284421 pid=1 nodes=2 kmalloc-128: Kernel object freeing ------------------------------------------------------------------------ 163 <not-available> age=4295176847 pid=0 nodes=0-3 1 __vunmap+0x6e/0xf0 age=282907 pid=1723 nodes=0 28 free_as_io_context+0x12/0x90 age=9243/262197/283474 pid=42-11754 nodes=0 1 acpi_get_object_info+0x1b7/0x1d4 age=284475 pid=1 nodes=0 1 do_acpi_find_child+0x45/0x4e age=284475 pid=1 nodes=0 NUMA nodes : 0 1 2 3 ------------------------------------------ All slabs 7 2 2 1 Partial slabs 2 2 0 0 Signed-off-by: -
Christoph Lameter authored
CONFIG_SLUB_DEBUG can be used to switch off the debugging and sysfs components of SLUB. Thus SLUB will be able to replace SLOB. SLUB can arrange objects in a denser way than SLOB and the code size should be minimal without debugging and sysfs support. Note that CONFIG_SLUB_DEBUG is materially different from CONFIG_SLAB_DEBUG. CONFIG_SLAB_DEBUG is used to enable slab debugging in SLAB. SLUB enables debugging via a boot parameter. SLUB debug code should always be present. CONFIG_SLUB_DEBUG can be modified in the embedded config section. Signed-off-by:
-
Christoph Lameter authored
Move the tracking definitions and the check_valid_pointer() function away from the debugging related functions. Signed-off-by:
-
Christoph Lameter authored
Trace in both slab_alloc and slab_free has a lot of common code. Use a single function for both. Signed-off-by:
-
Christoph Lameter authored
This replaces the PageError() checking. DebugSlab is clearer and allows for future changes to the page bit used. We also need it to support CONFIG_SLUB_DEBUG. Signed-off-by:
-
Christoph Lameter authored
Move the resiliency check into the SYSFS section after validate_slab that is used by the resiliency check. This will avoid a forward declaration. Signed-off-by:
-
Christoph Lameter authored
Scanning of objects happens in a number of functions. Consolidate that code. DECLARE_BITMAP instead of coding the declaration for bitmaps. Signed-off-by:
-
Christoph Lameter authored
Update comments throughout SLUB to reflect the new developments. Fix up various awkward sentences. Signed-off-by:
-
Christoph Lameter authored
Its only purpose was to bring some sort of symmetry to sysfs usage when dealing with bootstrapping per cpu flushing. Since we do not time out slabs anymore we have no need to run finish_bootstrap even without sysfs. Fold it back into slab_sysfs_init and drop the initcall for the !SYFS case. Signed-off-by:
-
Christoph Lameter authored
We really do not need all this gaga there. ksize gives us all the information we need to figure out if the object can cope with the new size. Signed-off-by:
-
