- 03 Jul, 2013 31 commits
-
-
Noboru Iwamatsu authored
Under heavy I/O load, writing the disk heartbeat can be forced to wait for minutes, and this causes the node to be fenced. This patch tries to use WRITE_SYNC in submitting the heartbeat bio, so that writing the heartbeat will have a priority over other requests. Signed-off-by:
Noboru Iwamatsu <n_iwamatsu@jp.fujitsu.com> Acked-by:
Tao Ma <tm@tao.ma> Acked-by:
Sunil Mushran <sunil.mushran@gmail.com> Cc: Srinivas Eeeda <srinivas.eeda@oracle.com> Reviewed-by:
Jie Liu <jeff.liu@oracle.com> Tested-by:
Gurudas Pai <gurudas.pai@oracle.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Junxiao Bi authored
Inlined xattr shared free space of inode block with inlined data or data extent record, so the size of the later two should be adjusted when inlined xattr is enabled. See ocfs2_xattr_ibody_init(). But this isn't done well when reflink. For inode with inlined data, its max inlined data size is adjusted in ocfs2_duplicate_inline_data(), no problem. But for inode with data extent record, its record count isn't adjusted. Fix it, or data extent record and inlined xattr may overwrite each other, then cause data corruption or xattr failure. One panic caused by this bug in our test environment is the following: kernel BUG at fs/ocfs2/xattr.c:1435! invalid opcode: 0000 [#1] SMP Pid: 10871, comm: multi_reflink_t Not tainted 2.6.39-300.17.1.el5uek #1 RIP: ocfs2_xa_offset_pointer+0x17/0x20 [ocfs2] RSP: e02b:ffff88007a587948 EFLAGS: 00010283 RAX: 0000000000000000 RBX: 0000000000000010 RCX: 00000000000051e4 RDX: ffff880057092060 RSI: 0000000000000f80 RDI: ffff88007a587a68 RBP: ffff88007a587948 R08: 00000000000062f4 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000010 R13: ffff88007a587a68 R14: 0000000000000001 R15: ffff88007a587c68 FS: 00007fccff7f06e0(0000) GS:ffff88007fc00000(0000) knlGS:0000000000000000 CS: e033 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000015cf000 CR3: 000000007aa76000 CR4: 0000000000000660 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process multi_reflink_t Call Trace: ocfs2_xa_reuse_entry+0x60/0x280 [ocfs2] ocfs2_xa_prepare_entry+0x17e/0x2a0 [ocfs2] ocfs2_xa_set+0xcc/0x250 [ocfs2] ocfs2_xattr_ibody_set+0x98/0x230 [ocfs2] __ocfs2_xattr_set_handle+0x4f/0x700 [ocfs2] ocfs2_xattr_set+0x6c6/0x890 [ocfs2] ocfs2_xattr_user_set+0x46/0x50 [ocfs2] generic_setxattr+0x70/0x90 __vfs_setxattr_noperm+0x80/0x1a0 vfs_setxattr+0xa9/0xb0 setxattr+0xc3/0x120 sys_fsetxattr+0xa8/0xd0 system_call_fastpath+0x16/0x1b Signed-off-by:Junxiao Bi <junxiao.bi@oracle.com> Reviewed-by:
Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: <stable@kernel.org> Signed-off-by:
-
Younger Liu authored
While deleting a file with ocfs2_unlink(), there is a bug in this function. This bug will result in filesystem read-only. After calling ocfs2_orphan_add(), the file which will be deleted is added into orphan dir. If ocfs2_delete_entry() fails, the file still exists in the parent dir. And this scenario introduces a conflict of metadata. If a file is added into orphan dir, when we put inode of the file with iput(), the inode i_flags is setted (~OCFS2_VALID_FL) in ocfs2_remove_inode(), and then write back to disk. But as previously mentioned, the file still exists in the parent dir. On other nodes, the file can be still accessed. When first read the file with ocfs2_read_blocks() from disk, It will check and avalidate inode using ocfs2_validate_inode_block(). So File system will be readonly because the inode is invalid. In other words, the inode i_flags has been set (~OCFS2_VALID_FL). [akpm@linux-foundation.org: cleanups] [jeff.liu@oracle.com: s/inode_is_unlinkable/ocfs2_inode_is_unlinkable/] Signed-off-by:
Younger Liu <younger.liu@huawei.com> Signed-off-by:
Jensen <shencanquan@huawei.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Signed-off-by:
-
Andrew Morton authored
Cc: Jie Liu <jeff.liu@oracle.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: Younger Liu <younger.liu@huawei.com> Signed-off-by:
-
Jie Liu authored
In ocfs2_relink_block_group(), we roll back all those changes if notify intent to modify buffers for metadata update failed even if the relevant buffer has not yet been modified/got dirty at that point, that are not quite right because of: - None buffer has been modified/dirty if failed to call ocfs2_journal_access_gd() against the previous block group buffer - Only the previous block group buffer has got dirty if failed to call ocfs2_journal_access_gd() against the block group buffer - There is no need to roll back the change for file entry buffer at all Those problems will not cause anything wrong but unnecessary. This patch fix them and kill the useless bg_ptr variable as well. Signed-off-by:
-
Younger Liu authored
While adding a file into orphan dir in ocfs2_orphan_add(), it calls __ocfs2_add_entry() before ocfs2_journal_access_di(). If ocfs2_journal_access_di() failed, the file is added into orphan dir, and orphan dir dinode updated, but file dinode has not been updated. Accordingly, the data is not consistent between file dinode and orphan dir. So, need to call ocfs2_journal_access_di() before __ocfs2_add_entry(), and if ocfs2_journal_access_di() failed, orphan_fe and orphan_dir_inode->i_nlink need rollback. This bug was added by 3939fda4 ("Ocfs2: Journaling i_flags and i_orphaned_slot when adding inode to orphan dir."). Signed-off-by:
-
Xue jiufei authored
dlmlock_master() returns DLM_RECOVERING/DLM_MIGRATING/ DLM_FORWAR after adding lock to blocked list if lockres has the state DLM_LOCK_RES_RECOVERING/DLM_LOCK_RES_MIGRATING/ DLM_LOCK_RES_IN_PROGRESS. so it will retry in dlmlock(). And this may cause dlm_thread fall into an infinite loop Thread1 dlm_thread calls dlm_lock->dlmlock_master, if lockresA is in state DLM_LOCK_RES_RECOVERING, calls __dlm_wait_on_lockres() and waits until others threads clear this state; If cannot grant this lock, adding lock to blocked list, and return DLM_RECOVERING; Grant this lock and move it to grant list; After a while, retry and calls list_add_tail(), adding lock to blocked list again. Granted and blocked list of this lockres will become the following conditions: lock_res->granted.next = dlm_lock->list_head; lock_res->blocked.next = dlm_lock->list_head; dlm_lock->list_head.next = dlm_lock_resource->blocked; When dlm_thread traverses the granted list, it will fall into an endless loop, checking dlm_lock.list_head, dlm_lock->list_head.next (i.e.lock_res->blocked), lock_res->blocked.next(i.e.dlm_lock.list_head again) ..... Signed-off-by:joyce <xuejiufei@huawei.com> Reviewed-by:
-
Junxiao Bi authored
Free space checking will be done in ocfs2_xattr_ibody_init(). So remove here. [akpm@linux-foundation.org: remove unused local] Signed-off-by:
-
Younger Liu authored
There is a memory leak in sc_kref_release(). When free struct o2net_sock_container (sc), we should release sc->sc_page. Signed-off-by:
-
Goldwyn Rodrigues authored
While adding extends to a file, the credits are calculated incorrectly and if the requested clusters is more than one (or more because we used a conservative limit) then we run out of journal credits and we hit an assert in journalling code. The function parameter bits_wanted variable was not used at all. Signed-off-by:
Goldwyn Rodrigues <rgoldwyn@suse.com> Reviewed-by:
-
Joseph Qi authored
In ocfs2_remove_btree_range, when calling ocfs2_lock_refcount_tree and ocfs2_prepare_refcount_change_for_del failed, it goes to out and then tries to call mutex_unlock without mutex_lock before. And when calling ocfs2_reserve_blocks_for_rec_trunc failed, it should free ref_tree before return. Signed-off-by:
Joseph Qi <joseph.qi@huawei.com> Reviewed-by:
-
Goldwyn Rodrigues authored
Code cleanup: needs_checkpoint is assigned to but never used. Delete the variable. Signed-off-by:
-
Xue jiufei authored
dlm_begin_reco_handler() returns without putting dlm when dlm recovery state is DLM_RECO_STATE_FINALIZE. Signed-off-by:
-
Joseph Qi authored
If we use le32_add_cpu to set ocfs2_dinode i_flags, it may lead to the corresponding flag corrupted. So we should change it to bitwise and/or operation. Signed-off-by:
-
Joseph Qi authored
In dlm_request_all_locks, ret is type enum. But o2net_send_message returns a type int value. Then it will never run into the following error branch. So we should change the ret type from enum to int. Signed-off-by:
-
Joseph Qi authored
Below 3 functions have already been declared in dlmcommon.h, so we have no need to declare them again in dlmrecovery.c: dlm_complete_recovery_thread dlm_launch_recovery_thread dlm_kick_recovery_thread Signed-off-by:
-
Dan Carpenter authored
The difference between "count" and "len" is that "len" is capped at 4095. Changing it like this makes it match how sysfs_write_file() is implemented. This is a static analysis patch. I haven't found any store_attribute() functions where this change makes a difference. Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Acked-by:
-
Andrew Morton authored
spacr64 gcc-3.4.5 (at least) spits this back. Cc: Andrey Smirnov <andrey.smirnov@convergeddevices.net> Cc: Mark Brown <broonie@opensource.wolfsonmicro.com> Cc: Takashi Iwai <tiwai@suse.de> Signed-off-by:
-
Bartlomiej Zolnierkiewicz authored
tasklet_kill() may sleep so call it before taking pch->lock. Fixes following lockup: BUG: scheduling while atomic: cat/2383/0x00000002 Modules linked in: unwind_backtrace+0x0/0xfc __schedule_bug+0x4c/0x58 __schedule+0x690/0x6e0 sys_sched_yield+0x70/0x78 tasklet_kill+0x34/0x8c pl330_free_chan_resources+0x24/0x88 dma_chan_put+0x4c/0x50 [...] BUG: spinlock lockup suspected on CPU#0, swapper/0/0 lock: 0xe52aa04c, .magic: dead4ead, .owner: cat/2383, .owner_cpu: 1 unwind_backtrace+0x0/0xfc do_raw_spin_lock+0x194/0x204 _raw_spin_lock_irqsave+0x20/0x28 pl330_tasklet+0x2c/0x5a8 tasklet_action+0xfc/0x114 __do_softirq+0xe4/0x19c irq_exit+0x98/0x9c handle_IPI+0x124/0x16c gic_handle_irq+0x64/0x68 __irq_svc+0x40/0x70 cpuidle_wrap_enter+0x4c/0xa0 cpuidle_enter_state+0x18/0x68 cpuidle_idle_call+0xac/0xe0 cpu_idle+0xac/0xf0 Signed-off-by:Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by:
Kyungmin Park <kyungmin.park@samsung.com> Acked-by:
Jassi Brar <jassisinghbrar@gmail.com> Cc: Vinod Koul <vinod.koul@linux.intel.com> Cc: Tomasz Figa <t.figa@samsung.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Chen Gang authored
Need include "asm/uaccess.h" to pass compiling. The related error (with allmodconfig): arch/c6x/mm/init.c: In function `paging_init': arch/c6x/mm/init.c:46:2: error: implicit declaration of function `set_fs' [-Werror=implicit-function-declaration] arch/c6x/mm/init.c:46:9: error: `KERNEL_DS' undeclared (first use in this function) arch/c6x/mm/init.c:46:9: note: each undeclared identifier is reported only once for each function it appears in Signed-off-by:
Chen Gang <gang.chen@asianux.com> Cc: <stable@vger.kernel.org> [3.10.x] Signed-off-by:
-
Andrew Morton authored
Commit f21afc25 ("smp.h: Use local_irq_{save,restore}() in !SMP version of on_each_cpu()") converted on_each_cpu() to a C function. This required inclusion of irqflags.h, which broke ia64 and mn10300 (at least) due to header ordering hell. Switch on_each_cpu() back to a macro to fix this. Reported-by:
Geert Uytterhoeven <geert@linux-m68k.org> Acked-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64Linus Torvalds authored
Pull ARM64 updates from Catalin Marinas: "Main features: - KVM and Xen ports to AArch64 - Hugetlbfs and transparent huge pages support for arm64 - Applied Micro X-Gene Kconfig entry and dts file - Cache flushing improvements For arm64 huge pages support, there are x86 changes moving part of arch/x86/mm/hugetlbpage.c into mm/hugetlb.c to be re-used by arm64" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-aarch64: (66 commits) arm64: Add initial DTS for APM X-Gene Storm SOC and APM Mustang board arm64: Add defines for APM ARMv8 implementation arm64: Enable APM X-Gene SOC family in the defconfig arm64: Add Kconfig option for APM X-Gene SOC family arm64/Makefile: provide vdso_install target ARM64: mm: THP support. ARM64: mm: Raise MAX_ORDER for 64KB pages and THP. ARM64: mm: HugeTLB support. ARM64: mm: Move PTE_PROT_NONE bit. ARM64: mm: Make PAGE_NONE pages read only and no-execute. ARM64: mm: Restore memblock limit when map_mem finished. mm: thp: Correct the HPAGE_PMD_ORDER check. x86: mm: Remove general hugetlb code from x86. mm: hugetlb: Copy general hugetlb code from x86 to mm. x86: mm: Remove x86 version of huge_pmd_share. mm: hugetlb: Copy huge_pmd_share from x86 to mm. arm64: KVM: document kernel object mappings in HYP arm64: KVM: MAINTAINERS update arm64: KVM: userspace API documentation arm64: KVM: enable initialization of a 32bit vcpu ...
-
git://git.linaro.org/people/rmk/linux-armLinus Torvalds authored
Pull ARM updates from Russell King: "This contains the usual updates from other people (listed below) and the usual random muddle of miscellaneous ARM updates which cover some low priority bug fixes and performance improvements. I've started to put the pull request wording into the merge commits, which are: - NoMMU stuff: This includes the following series sent earlier to the list: - nommu-fixes - R7 Support - MPU support I've left out the ARCH_MULTIPLATFORM/!MMU stuff that Arnd and I were discussing today until we've reached a conclusion/that's had some more review. This is rebased (and re-tested) on your devel-stable branch because otherwise there were going to be conflicts with Uwe's V7M work now that you've merged that. I've included the fix for limiting MPU to CPU_V7. - Huge page support These changes bring both HugeTLB support and Transparent HugePage (THP) support to ARM. Only long descriptors (LPAE) are supported in this series. The code has been tested on an Arndale board (Exynos 5250). - LPAE updates Please pull these miscellaneous LPAE fixes I've been collecting for a while now for 3.11. They've been tested and reviewed by quite a few people, and most of the patches are pretty trivial. -- Will Deacon. - arch_timer cleanups Please pull these arch_timer cleanups I've been holding onto for a while. They're the same as my last posting, but have been rebased to v3.10-rc3. - mpidr linearisation (multiprocessor id register - identifies which CPU number we are in the system) This patch series that implements MPIDR linearization through a simple hashing algorithm and updates current cpu_{suspend}/{resume} code to use the newly created hash structures to retrieve context pointers. It represents a stepping stone for the implementation of power management code on forthcoming multi-cluster ARM systems. It has been tested on TC2 (dual cluster A15xA7 system), iMX6q, OMAP4 and Tegra, with processors hitting low-power states requiring warm-boot resume through the cpu_resume code path" * 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits) ARM: 7775/1: mm: Remove do_sect_fault from LPAE code ARM: 7777/1: Avoid extra calls to the C compiler ARM: 7774/1: Fix dtb dependency to use order-only prerequisites ARM: 7770/1: remove residual ARMv2 support from decompressor ARM: 7769/1: Cortex-A15: fix erratum 798181 implementation ARM: 7768/1: prevent risks of out-of-bound access in ASID allocator ARM: 7767/1: let the ASID allocator handle suspended animation ARM: 7766/1: versatile: don't mark pen as __INIT ARM: 7765/1: perf: Record the user-mode PC in the call chain. ARM: 7735/2: Preserve the user r/w register TPIDRURW on context switch and fork ARM: kernel: implement stack pointer save array through MPIDR hashing ARM: kernel: build MPIDR hash function data structure ARM: mpu: Ensure that MPU depends on CPU_V7 ARM: mpu: protect the vectors page with an MPU region ARM: mpu: Allow enabling of the MPU via kconfig ARM: 7758/1: introduce config HAS_BANDGAP ARM: 7757/1: mm: don't flush icache in switch_mm with hardware broadcasting ARM: 7751/1: zImage: don't overwrite ourself with a page table ARM: 7749/1: spinlock: retry trylock operation if strex fails on free lock ARM: 7748/1: oabi: handle faults when loading swi instruction from userspace ... -
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfsLinus Torvalds authored
Pull second set of VFS changes from Al Viro: "Assorted f_pos race fixes, making do_splice_direct() safe to call with i_mutex on parent, O_TMPFILE support, Jeff's locks.c series, ->d_hash/->d_compare calling conventions changes from Linus, misc stuff all over the place." * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits) Document ->tmpfile() ext4: ->tmpfile() support vfs: export lseek_execute() to modules lseek_execute() doesn't need an inode passed to it block_dev: switch to fixed_size_llseek() cpqphp_sysfs: switch to fixed_size_llseek() tile-srom: switch to fixed_size_llseek() proc_powerpc: switch to fixed_size_llseek() ubi/cdev: switch to fixed_size_llseek() pci/proc: switch to fixed_size_llseek() isapnp: switch to fixed_size_llseek() lpfc: switch to fixed_size_llseek() locks: give the blocked_hash its own spinlock locks: add a new "lm_owner_key" lock operation locks: turn the blocked_list into a hashtable locks: convert fl_link to a hlist_node locks: avoid taking global lock if possible when waking up blocked waiters locks: protect most of the file_lock handling with i_lock locks: encapsulate the fl_link list handling locks: make "added" in __posix_lock_file a bool ...
-
Al Viro authored
Signed-off-by:Al Viro <viro@zeniv.linux.org.uk>
-
Al Viro authored
very similar to ext3 counterpart... Signed-off-by: -
Jie Liu authored
For those file systems(btrfs/ext4/ocfs2/tmpfs) that support SEEK_DATA/SEEK_HOLE functions, we end up handling the similar matter in lseek_execute() to update the current file offset to the desired offset if it is valid, ceph also does the simliar things at ceph_llseek(). To reduce the duplications, this patch make lseek_execute() public accessible so that we can call it directly from the underlying file systems. Thanks Dave Chinner for this suggestion. [AV: call it vfs_setpos(), don't bring the removed 'inode' argument back] v2->v1: - Add kernel-doc comments for lseek_execute() - Call lseek_execute() in ceph->llseek() Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroupLinus Torvalds authored
Pull cpuset changes from Tejun Heo: "cpuset has always been rather odd about its configurations - a cgroup right after creation didn't allow any task executions before configuration, changing configuration in the parent modifies the descendants irreversibly and so on. These behaviors are inherently nasty and almost hostile against sharing the hierarchy with other controllers making it very difficult to use in unified hierarchy. Li is currently in the process of updating the behaviors for __DEVEL__sane_behavior which is the bulk of changes in this pull request. It isn't complete yet and the behaviors will change further but all changes are gated behind sane_behavior. In the process, the rather hairy work-item punting which was used to work around the limitations of cgroup descendant iterator was simplified." * 'for-3.11-cpuset' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: cpuset: rename @cont to @cgrp cpuset: fix to migrate mm correctly in a corner case cpuset: allow to move tasks to empty cpusets cpuset: allow to keep tasks in empty cpusets cpuset: introduce effective_{cpumask|nodemask}_cpuset() cpuset: record old_mems_allowed in struct cpuset cpuset: remove async hotplug propagation work cpuset: let hotplug propagation work wait for task attaching cpuset: re-structure update_cpumask() a bit cpuset: remove cpuset_test_cpumask() cpuset: remove unnecessary variable in cpuset_attach() cpuset: cleanup guarantee_online_{cpus|mems}() cpuset: remove redundant check in cpuset_cpus_allowed_fallback()
-
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroupLinus Torvalds authored
Pull cgroup changes from Tejun Heo: "This pull request contains the following changes. - cgroup_subsys_state (css) reference counting has been converted to percpu-ref. css is what each resource controller embeds into its own control structure and perform reference count against. It may be used in hot paths of various subsystems and is similar to module refcnt in that aspect. For example, block-cgroup's css refcnting was showing up a lot in Mikulaus's device-mapper scalability work and this should alleviate it. - cgroup subtree iterator has been updated so that RCU read lock can be released after grabbing reference. This allows simplifying its users which requires blocking which used to build iteration list under RCU read lock and then traverse it outside. This pull request contains simplification of cgroup core and device-cgroup. A separate pull request will update cpuset. - Fixes for various bugs including corner race conditions and RCU usage bugs. - A lot of cleanups and some prepartory work for the planned unified hierarchy support." * 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (48 commits) cgroup: CGRP_ROOT_SUBSYS_BOUND should also be ignored when mounting an existing hierarchy cgroup: CGRP_ROOT_SUBSYS_BOUND should be ignored when comparing mount options cgroup: fix deadlock on cgroup_mutex via drop_parsed_module_refcounts() cgroup: always use RCU accessors for protected accesses cgroup: fix RCU accesses around task->cgroups cgroup: fix RCU accesses to task->cgroups cgroup: grab cgroup_mutex in drop_parsed_module_refcounts() cgroup: fix cgroupfs_root early destruction path cgroup: reserve ID 0 for dummy_root and 1 for unified hierarchy cgroup: implement for_each_[builtin_]subsys() cgroup: move init_css_set initialization inside cgroup_mutex cgroup: s/for_each_subsys()/for_each_root_subsys()/ cgroup: clean up find_css_set() and friends cgroup: remove cgroup->actual_subsys_mask cgroup: prefix global variables with "cgroup_" cgroup: convert CFTYPE_* flags to enums cgroup: rename cont to cgrp cgroup: clean up cgroup_serial_nr_cursor cgroup: convert cgroup_cft_commit() to use cgroup_for_each_descendant_pre() cgroup: make serial_nr_cursor available throughout cgroup.c ... -
git://git.kernel.org/pub/scm/linux/kernel/git/tj/wqLinus Torvalds authored
Pull workqueue changes from Tejun Heo: "Surprisingly, Lai and I didn't break too many things implementing custom pools and stuff last time around and there aren't any follow-up changes necessary at this point. The only change in this pull request is Viresh's patches to make some per-cpu workqueues to behave as unbound workqueues dependent on a boot param whose default can be configured via a config option. This leads to higher processing overhead / lower bandwidth as more work items are bounced across CPUs; however, it can lead to noticeable powersave in certain configurations - ~10% w/ idlish constant workload on a big.LITTLE configuration according to Viresh. This is because per-cpu workqueues interfere with how the scheduler perceives whether or not each CPU is idle by forcing pinned tasks on them, which makes the scheduler's power-aware scheduling decisions less effective. Its effectiveness is likely less pronounced on homogenous configurations and this type of optimization can probably be made automatic; however, the changes are pretty minimal and the affected workqueues are clearly marked, so it's an easy gain for some configurations for the time being with pretty unintrusive changes." * 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: fbcon: queue work on power efficient wq block: queue work on power efficient wq PHYLIB: queue work on system_power_efficient_wq workqueue: Add system wide power_efficient workqueues workqueues: Introduce new flag WQ_POWER_EFFICIENT for power oriented workqueues
-
git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpuLinus Torvalds authored
Pull per-cpu changes from Tejun Heo: "This pull request contains Kent's per-cpu reference counter. It has gone through several iterations since the last time and the dynamic allocation is gone. The usual usage is relatively straight-forward although async kill confirm interface, which is not used int most cases, is somewhat icky. There also are some interface concerns - e.g. I'm not sure about passing in @relesae callback during init as that becomes funny when we later implement synchronous kill_and_drain - but nothing too serious and it's quite useable now. cgroup_subsys_state refcnting has already been converted and we should convert module refcnt (Kent?)" * 'for-3.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: percpu-refcount: use RCU-sched insted of normal RCU percpu-refcount: implement percpu_tryget() along with percpu_ref_kill_and_confirm() percpu-refcount: implement percpu_ref_cancel_init() percpu-refcount: add __must_check to percpu_ref_init() and don't use ACCESS_ONCE() in percpu_ref_kill_rcu() percpu-refcount: cosmetic updates percpu-refcount: consistently use plain (non-sched) RCU percpu-refcount: Don't use silly cmpxchg() percpu: implement generic percpu refcounting
-
- 02 Jul, 2013 9 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 UV update from Ingo Molnar: "There's a single commit in this tree, which adds support for a new SGI UV GRU (Global Reference Unit - fast NUMA messaging ASIC) hardware feature to scale up and beyond: an optional distributed mode that will allow per-node address mapping of local GRU space, as opposed to mapping all GRU hardware to the same contiguous high space" * 'x86-uv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/UV: Add GRU distributed mode mappings
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 tracing updates from Ingo Molnar: "This tree adds IRQ vector tracepoints that are named after the handler and which output the vector #, based on a zero-overhead approach that relies on changing the IDT entries, by Seiji Aguchi. The new tracepoints look like this: # perf list | grep -i irq_vector irq_vectors:local_timer_entry [Tracepoint event] irq_vectors:local_timer_exit [Tracepoint event] irq_vectors:reschedule_entry [Tracepoint event] irq_vectors:reschedule_exit [Tracepoint event] irq_vectors:spurious_apic_entry [Tracepoint event] irq_vectors:spurious_apic_exit [Tracepoint event] irq_vectors:error_apic_entry [Tracepoint event] irq_vectors:error_apic_exit [Tracepoint event] [...]" * 'x86-tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/tracing: Add config option checking to the definitions of mce handlers trace,x86: Do not call local_irq_save() in load_current_idt() trace,x86: Move creation of irq tracepoints from apic.c to irq.c x86, trace: Add irq vector tracepoints x86: Rename variables for debugging x86, trace: Introduce entering/exiting_irq() tracing: Add DEFINE_EVENT_FN() macro -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 RAS update from Ingo Molnar: "The changes in this tree are: - ACPI APEI (ACPI Platform Error Interface) improvements, by Chen Gong - misc MCE fixes/cleanups" * 'x86-ras-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mce: Update MCE severity condition check mce: acpi/apei: Add comments to clarify usage of the various bitfields in the MCA subsystem ACPI/APEI: Update einj documentation for param1/param2 ACPI/APEI: Add parameter check before error injection ACPI, APEI, EINJ: Fix error return code in einj_init() x86, mce: Fix "braodcast" typo -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 platform updates from Ingo Molnar: "Two changes: - A Kconfig dependency fix/cleanup - Introduce the 'make kvmconfig' KVM configuration helper utility that turns the current .config into a KVM-bootable config. Useful for debugging specific native kernel configs that have no KVM config options enabled on VM setups." * 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/platform: Make X86_GOLDFISH depend on X86_EXTENDED_PLATFORM x86/platform: Add kvmconfig to the phony targets x86, platform, kvm, kconfig: Turn existing .config's into KVM-capable configs -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 mm changes from Ingo Molnar: "Misc improvements: - Fix /proc/mtrr reporting - Fix ioremap printout - Remove the unused pvclock fixmap entry on 32-bit - misc cleanups" * 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/ioremap: Correct function name output x86: Fix /proc/mtrr with base/size more than 44bits ix86: Don't waste fixmap entries x86/mm: Drop unneeded include <asm/*pgtable, page*_types.h> x86_64: Correct phys_addr in cleanup_highmap comment
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 microcode loading update from Ingo Molnar: "Two main changes that improve microcode loading on AMD CPUs: - Add support for all-in-one binary microcode files that concatenate the microcode images of multiple processor families, by Jacob Shin - Add early microcode loading (embedded in the initrd) support, also by Jacob Shin" * 'x86-microcode-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86, microcode, amd: Another early loading fixup x86, microcode, amd: Allow multiple families' bin files appended together x86, microcode, amd: Make find_ucode_in_initrd() __init x86, microcode, amd: Fix warnings and errors on with CONFIG_MICROCODE=m x86, microcode, amd: Early microcode patch loading support for AMD x86, microcode, amd: Refactor functions to prepare for early loading x86, microcode: Vendor abstract out save_microcode_in_initrd() x86, microcode, intel: Correct typo in printk -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 FPU changes from Ingo Molnar: "There are two bigger changes in this tree: - Add an [early-use-]safe static_cpu_has() variant and other robustness improvements, including the new X86_DEBUG_STATIC_CPU_HAS configurable debugging facility, motivated by recent obscure FPU code bugs, by Borislav Petkov - Reimplement FPU detection code in C and drop the old asm code, by Peter Anvin." * 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86, fpu: Use static_cpu_has_safe before alternatives x86: Add a static_cpu_has_safe variant x86: Sanity-check static_cpu_has usage x86, cpu: Add a synthetic, always true, cpu feature x86: Get rid of ->hard_math and all the FPU asm fu -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 EFI changes from Ingo Molnar: "Two fixes that should in principle increase robustness of our interaction with the EFI firmware, and a cleanup" * 'x86-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86, efi: retry ExitBootServices() on failure efi: Convert runtime services function ptrs UEFI: Don't pass boot services regions to SetVirtualAddressMap()
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 debug update from Ingo Molnar: "Misc debuggability improvements: - Optimize the x86 CPU register printout a bit - Expose the tboot TXT log via debugfs - Small do_debug() cleanup" * 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/tboot: Provide debugfs interfaces to access TXT log x86: Remove weird PTR_ERR() in do_debug x86/debug: Only print out DR registers if they are not power-on defaults
-
