summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-07-12 11:40:28 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-12 11:40:28 -0700
commitef8f3d48afd6a17a0dae8c277c2f539c2f19fd16 (patch)
tree5c28f9f287a552ad1a655b9e29e5330966652e89 /fs
parentd7d170a8e357bd9926cc6bfea5c2385c2eac65b2 (diff)
parent2c207985f354dfb549e5a543102a3e084eea81f6 (diff)
downloadlinux-ef8f3d48afd6a17a0dae8c277c2f539c2f19fd16.tar.bz2
Merge branch 'akpm' (patches from Andrew)
Merge updates from Andrew Morton: "Am experimenting with splitting MM up into identifiable subsystems perhaps with a view to gitifying it in complex ways. Also with more verbose "incoming" emails. Most of MM is here and a few other trees. Subsystems affected by this patch series: - hotfixes - iommu - scripts - arch/sh - ocfs2 - mm:slab-generic - mm:slub - mm:kmemleak - mm:kasan - mm:cleanups - mm:debug - mm:pagecache - mm:swap - mm:memcg - mm:gup - mm:pagemap - mm:infrastructure - mm:vmalloc - mm:initialization - mm:pagealloc - mm:vmscan - mm:tools - mm:proc - mm:ras - mm:oom-kill hotfixes: mm: vmscan: scan anonymous pages on file refaults mm/nvdimm: add is_ioremap_addr and use that to check ioremap address mm/memcontrol: fix wrong statistics in memory.stat mm/z3fold.c: lock z3fold page before __SetPageMovable() nilfs2: do not use unexported cpu_to_le32()/le32_to_cpu() in uapi header MAINTAINERS: nilfs2: update email address iommu: include/linux/dmar.h: replace single-char identifiers in macros scripts: scripts/decode_stacktrace: match basepath using shell prefix operator, not regex scripts/decode_stacktrace: look for modules with .ko.debug extension scripts/spelling.txt: drop "sepc" from the misspelling list scripts/spelling.txt: add spelling fix for prohibited scripts/decode_stacktrace: Accept dash/underscore in modules scripts/spelling.txt: add more spellings to spelling.txt arch/sh: arch/sh/configs/sdk7786_defconfig: remove CONFIG_LOGFS sh: config: remove left-over BACKLIGHT_LCD_SUPPORT sh: prevent warnings when using iounmap ocfs2: fs: ocfs: fix spelling mistake "hearbeating" -> "heartbeat" ocfs2/dlm: use struct_size() helper ocfs2: add last unlock times in locking_state ocfs2: add locking filter debugfs file ocfs2: add first lock wait time in locking_state ocfs: no need to check return value of debugfs_create functions fs/ocfs2/dlmglue.c: unneeded variable: "status" ocfs2: use kmemdup rather than duplicating its implementation mm:slab-generic: Patch series "mm/slab: Improved sanity checking": mm/slab: validate cache membership under freelist hardening mm/slab: sanity-check page type when looking up cache lkdtm/heap: add tests for freelist hardening mm:slub: mm/slub.c: avoid double string traverse in kmem_cache_flags() slub: don't panic for memcg kmem cache creation failure mm:kmemleak: mm/kmemleak.c: fix check for softirq context mm/kmemleak.c: change error at _write when kmemleak is disabled docs: kmemleak: add more documentation details mm:kasan: mm/kasan: print frame description for stack bugs Patch series "Bitops instrumentation for KASAN", v5: lib/test_kasan: add bitops tests x86: use static_cpu_has in uaccess region to avoid instrumentation asm-generic, x86: add bitops instrumentation for KASAN Patch series "mm/kasan: Add object validation in ksize()", v3: mm/kasan: introduce __kasan_check_{read,write} mm/kasan: change kasan_check_{read,write} to return boolean lib/test_kasan: Add test for double-kzfree detection mm/slab: refactor common ksize KASAN logic into slab_common.c mm/kasan: add object validation in ksize() mm:cleanups: include/linux/pfn_t.h: remove pfn_t_to_virt() Patch series "remove ARCH_SELECT_MEMORY_MODEL where it has no effect": arm: remove ARCH_SELECT_MEMORY_MODEL s390: remove ARCH_SELECT_MEMORY_MODEL sparc: remove ARCH_SELECT_MEMORY_MODEL mm/gup.c: make follow_page_mask() static mm/memory.c: trivial clean up in insert_page() mm: make !CONFIG_HUGE_PAGE wrappers into static inlines include/linux/mm_types.h: ifdef struct vm_area_struct::swap_readahead_info mm: remove the account_page_dirtied export mm/page_isolation.c: change the prototype of undo_isolate_page_range() include/linux/vmpressure.h: use spinlock_t instead of struct spinlock mm: remove the exporting of totalram_pages include/linux/pagemap.h: document trylock_page() return value mm:debug: mm/failslab.c: by default, do not fail allocations with direct reclaim only Patch series "debug_pagealloc improvements": mm, debug_pagelloc: use static keys to enable debugging mm, page_alloc: more extensive free page checking with debug_pagealloc mm, debug_pagealloc: use a page type instead of page_ext flag mm:pagecache: Patch series "fix filler_t callback type mismatches", v2: mm/filemap.c: fix an overly long line in read_cache_page mm/filemap: don't cast ->readpage to filler_t for do_read_cache_page jffs2: pass the correct prototype to read_cache_page 9p: pass the correct prototype to read_cache_page mm/filemap.c: correct the comment about VM_FAULT_RETRY mm:swap: mm, swap: fix race between swapoff and some swap operations mm/swap_state.c: simplify total_swapcache_pages() with get_swap_device() mm, swap: use rbtree for swap_extent mm/mincore.c: fix race between swapoff and mincore mm:memcg: memcg, oom: no oom-kill for __GFP_RETRY_MAYFAIL memcg, fsnotify: no oom-kill for remote memcg charging mm, memcg: introduce memory.events.local mm: memcontrol: dump memory.stat during cgroup OOM Patch series "mm: reparent slab memory on cgroup removal", v7: mm: memcg/slab: postpone kmem_cache memcg pointer initialization to memcg_link_cache() mm: memcg/slab: rename slab delayed deactivation functions and fields mm: memcg/slab: generalize postponed non-root kmem_cache deactivation mm: memcg/slab: introduce __memcg_kmem_uncharge_memcg() mm: memcg/slab: unify SLAB and SLUB page accounting mm: memcg/slab: don't check the dying flag on kmem_cache creation mm: memcg/slab: synchronize access to kmem_cache dying flag using a spinlock mm: memcg/slab: rework non-root kmem_cache lifecycle management mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages mm: memcg/slab: reparent memcg kmem_caches on cgroup removal mm, memcg: add a memcg_slabinfo debugfs file mm:gup: Patch series "switch the remaining architectures to use generic GUP", v4: mm: use untagged_addr() for get_user_pages_fast addresses mm: simplify gup_fast_permitted mm: lift the x86_32 PAE version of gup_get_pte to common code MIPS: use the generic get_user_pages_fast code sh: add the missing pud_page definition sh: use the generic get_user_pages_fast code sparc64: add the missing pgd_page definition sparc64: define untagged_addr() sparc64: use the generic get_user_pages_fast code mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP mm: reorder code blocks in gup.c mm: consolidate the get_user_pages* implementations mm: validate get_user_pages_fast flags mm: move the powerpc hugepd code to mm/gup.c mm: switch gup_hugepte to use try_get_compound_head mm: mark the page referenced in gup_hugepte mm/gup: speed up check_and_migrate_cma_pages() on huge page mm/gup.c: remove some BUG_ONs from get_gate_page() mm/gup.c: mark undo_dev_pagemap as __maybe_unused mm:pagemap: asm-generic, x86: introduce generic pte_{alloc,free}_one[_kernel] alpha: switch to generic version of pte allocation arm: switch to generic version of pte allocation arm64: switch to generic version of pte allocation csky: switch to generic version of pte allocation m68k: sun3: switch to generic version of pte allocation mips: switch to generic version of pte allocation nds32: switch to generic version of pte allocation nios2: switch to generic version of pte allocation parisc: switch to generic version of pte allocation riscv: switch to generic version of pte allocation um: switch to generic version of pte allocation unicore32: switch to generic version of pte allocation mm/pgtable: drop pgtable_t variable from pte_fn_t functions mm/memory.c: fail when offset == num in first check of __vm_map_pages() mm:infrastructure: mm/mmu_notifier: use hlist_add_head_rcu() mm:vmalloc: Patch series "Some cleanups for the KVA/vmalloc", v5: mm/vmalloc.c: remove "node" argument mm/vmalloc.c: preload a CPU with one object for split purpose mm/vmalloc.c: get rid of one single unlink_va() when merge mm/vmalloc.c: switch to WARN_ON() and move it under unlink_va() mm/vmalloc.c: spelling> s/informaion/information/ mm:initialization: mm/large system hash: use vmalloc for size > MAX_ORDER when !hashdist mm/large system hash: clear hashdist when only one node with memory is booted mm:pagealloc: arm64: move jump_label_init() before parse_early_param() Patch series "add init_on_alloc/init_on_free boot options", v10: mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options mm: init: report memory auto-initialization features at boot time mm:vmscan: mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned mm: vmscan: correct some vmscan counters for THP swapout mm:tools: tools/vm/slabinfo: order command line options tools/vm/slabinfo: add partial slab listing to -X tools/vm/slabinfo: add option to sort by partial slabs tools/vm/slabinfo: add sorting info to help menu mm:proc: proc: use down_read_killable mmap_sem for /proc/pid/maps proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup proc: use down_read_killable mmap_sem for /proc/pid/pagemap proc: use down_read_killable mmap_sem for /proc/pid/clear_refs proc: use down_read_killable mmap_sem for /proc/pid/map_files mm: use down_read_killable for locking mmap_sem in access_remote_vm mm: smaps: split PSS into components mm: vmalloc: show number of vmalloc pages in /proc/meminfo mm:ras: mm/memory-failure.c: clarify error message mm:oom-kill: mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks() mm, oom: refactor dump_tasks for memcg OOMs mm, oom: remove redundant task_in_mem_cgroup() check oom: decouple mems_allowed from oom_unkillable_task mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process()" * akpm: (147 commits) mm/oom_kill.c: remove redundant OOM score normalization in select_bad_process() oom: decouple mems_allowed from oom_unkillable_task mm, oom: remove redundant task_in_mem_cgroup() check mm, oom: refactor dump_tasks for memcg OOMs mm: memcontrol: use CSS_TASK_ITER_PROCS at mem_cgroup_scan_tasks() mm/memory-failure.c: clarify error message mm: vmalloc: show number of vmalloc pages in /proc/meminfo mm: smaps: split PSS into components mm: use down_read_killable for locking mmap_sem in access_remote_vm proc: use down_read_killable mmap_sem for /proc/pid/map_files proc: use down_read_killable mmap_sem for /proc/pid/clear_refs proc: use down_read_killable mmap_sem for /proc/pid/pagemap proc: use down_read_killable mmap_sem for /proc/pid/smaps_rollup proc: use down_read_killable mmap_sem for /proc/pid/maps tools/vm/slabinfo: add sorting info to help menu tools/vm/slabinfo: add option to sort by partial slabs tools/vm/slabinfo: add partial slab listing to -X tools/vm/slabinfo: order command line options mm: vmscan: correct some vmscan counters for THP swapout mm: vmscan: remove double slab pressure by inc'ing sc->nr_scanned ...
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_addr.c6
-rw-r--r--fs/jffs2/file.c4
-rw-r--r--fs/jffs2/fs.c2
-rw-r--r--fs/jffs2/os-linux.h2
-rw-r--r--fs/notify/fanotify/fanotify.c5
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c8
-rw-r--r--fs/ocfs2/alloc.c10
-rw-r--r--fs/ocfs2/blockcheck.c56
-rw-r--r--fs/ocfs2/blockcheck.h7
-rw-r--r--fs/ocfs2/cluster/heartbeat.c102
-rw-r--r--fs/ocfs2/cluster/heartbeat.h2
-rw-r--r--fs/ocfs2/cluster/netdebug.c39
-rw-r--r--fs/ocfs2/cluster/nodemanager.c4
-rw-r--r--fs/ocfs2/cluster/quorum.c2
-rw-r--r--fs/ocfs2/cluster/tcp.c5
-rw-r--r--fs/ocfs2/cluster/tcp.h5
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c44
-rw-r--r--fs/ocfs2/dlm/dlmdebug.h10
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c10
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c2
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c8
-rw-r--r--fs/ocfs2/dlmglue.c96
-rw-r--r--fs/ocfs2/localalloc.c6
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--fs/ocfs2/super.c29
-rw-r--r--fs/proc/base.c31
-rw-r--r--fs/proc/meminfo.c2
-rw-r--r--fs/proc/task_mmu.c115
-rw-r--r--fs/proc/task_nommu.c6
29 files changed, 291 insertions, 331 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index bc57ae9e2963..cce9ace651a2 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -35,8 +35,9 @@
* @page: structure to page
*
*/
-static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page)
+static int v9fs_fid_readpage(void *data, struct page *page)
{
+ struct p9_fid *fid = data;
struct inode *inode = page->mapping->host;
struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE};
struct iov_iter to;
@@ -107,7 +108,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping,
if (ret == 0)
return ret;
- ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp);
+ ret = read_cache_pages(mapping, pages, v9fs_fid_readpage,
+ filp->private_data);
p9_debug(P9_DEBUG_VFS, " = %d\n", ret);
return ret;
}
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 7d8654a1472e..f8fb89b10227 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -109,9 +109,9 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
return ret;
}
-int jffs2_do_readpage_unlock(struct inode *inode, struct page *pg)
+int jffs2_do_readpage_unlock(void *data, struct page *pg)
{
- int ret = jffs2_do_readpage_nolock(inode, pg);
+ int ret = jffs2_do_readpage_nolock(data, pg);
unlock_page(pg);
return ret;
}
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 112d85849db1..8a20ddd25f2d 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
struct page *pg;
pg = read_cache_page(inode->i_mapping, offset >> PAGE_SHIFT,
- (void *)jffs2_do_readpage_unlock, inode);
+ jffs2_do_readpage_unlock, inode);
if (IS_ERR(pg))
return (void *)pg;
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index a2dbbb3f4c74..bd3d5f0ddc34 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -155,7 +155,7 @@ extern const struct file_operations jffs2_file_operations;
extern const struct inode_operations jffs2_file_inode_operations;
extern const struct address_space_operations jffs2_file_address_operations;
int jffs2_fsync(struct file *, loff_t, loff_t, int);
-int jffs2_do_readpage_unlock (struct inode *inode, struct page *pg);
+int jffs2_do_readpage_unlock(void *data, struct page *pg);
/* ioctl.c */
long jffs2_ioctl(struct file *, unsigned int, unsigned long);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index b428c295d13f..5778d1347b35 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -288,10 +288,13 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
/*
* For queues with unlimited length lost events are not expected and
* can possibly have security implications. Avoid losing events when
- * memory is short.
+ * memory is short. For the limited size queues, avoid OOM killer in the
+ * target monitoring memcg as it may have security repercussion.
*/
if (group->max_events == UINT_MAX)
gfp |= __GFP_NOFAIL;
+ else
+ gfp |= __GFP_RETRY_MAYFAIL;
/* Whoever is interested in the event, pays for the allocation. */
memalloc_use_memcg(group->memcg);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 2fda08b2b885..d510223d302c 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -90,9 +90,13 @@ int inotify_handle_event(struct fsnotify_group *group,
i_mark = container_of(inode_mark, struct inotify_inode_mark,
fsn_mark);
- /* Whoever is interested in the event, pays for the allocation. */
+ /*
+ * Whoever is interested in the event, pays for the allocation. Do not
+ * trigger OOM killer in the target monitoring memcg as it may have
+ * security repercussion.
+ */
memalloc_use_memcg(group->memcg);
- event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT);
+ event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
memalloc_unuse_memcg();
if (unlikely(!event)) {
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d1348fc4ca6d..0c335b51043d 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6191,17 +6191,17 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb,
if (le16_to_cpu(tl->tl_used)) {
trace_ocfs2_truncate_log_recovery_num(le16_to_cpu(tl->tl_used));
- *tl_copy = kmalloc(tl_bh->b_size, GFP_KERNEL);
+ /*
+ * Assuming the write-out below goes well, this copy will be
+ * passed back to recovery for processing.
+ */
+ *tl_copy = kmemdup(tl_bh->b_data, tl_bh->b_size, GFP_KERNEL);
if (!(*tl_copy)) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
- /* Assuming the write-out below goes well, this copy
- * will be passed back to recovery for processing. */
- memcpy(*tl_copy, tl_bh->b_data, tl_bh->b_size);
-
/* All we need to do to clear the truncate log is set
* tl_used. */
tl->tl_used = 0;
diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c
index 005b813a56b6..429e6a8359a5 100644
--- a/fs/ocfs2/blockcheck.c
+++ b/fs/ocfs2/blockcheck.c
@@ -242,57 +242,29 @@ static struct dentry *blockcheck_debugfs_create(const char *name,
static void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats)
{
if (stats) {
- debugfs_remove(stats->b_debug_check);
- stats->b_debug_check = NULL;
- debugfs_remove(stats->b_debug_failure);
- stats->b_debug_failure = NULL;
- debugfs_remove(stats->b_debug_recover);
- stats->b_debug_recover = NULL;
- debugfs_remove(stats->b_debug_dir);
+ debugfs_remove_recursive(stats->b_debug_dir);
stats->b_debug_dir = NULL;
}
}
-static int ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats,
- struct dentry *parent)
+static void ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats,
+ struct dentry *parent)
{
- int rc = -EINVAL;
-
- if (!stats)
- goto out;
-
stats->b_debug_dir = debugfs_create_dir("blockcheck", parent);
- if (!stats->b_debug_dir)
- goto out;
- stats->b_debug_check =
- blockcheck_debugfs_create("blocks_checked",
- stats->b_debug_dir,
- &stats->b_check_count);
+ blockcheck_debugfs_create("blocks_checked", stats->b_debug_dir,
+ &stats->b_check_count);
- stats->b_debug_failure =
- blockcheck_debugfs_create("checksums_failed",
- stats->b_debug_dir,
- &stats->b_failure_count);
+ blockcheck_debugfs_create("checksums_failed", stats->b_debug_dir,
+ &stats->b_failure_count);
- stats->b_debug_recover =
- blockcheck_debugfs_create("ecc_recoveries",
- stats->b_debug_dir,
- &stats->b_recover_count);
- if (stats->b_debug_check && stats->b_debug_failure &&
- stats->b_debug_recover)
- rc = 0;
-
-out:
- if (rc)
- ocfs2_blockcheck_debug_remove(stats);
- return rc;
+ blockcheck_debugfs_create("ecc_recoveries", stats->b_debug_dir,
+ &stats->b_recover_count);
}
#else
-static inline int ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats,
- struct dentry *parent)
+static inline void ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats,
+ struct dentry *parent)
{
- return 0;
}
static inline void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats)
@@ -301,10 +273,10 @@ static inline void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *
#endif /* CONFIG_DEBUG_FS */
/* Always-called wrappers for starting and stopping the debugfs files */
-int ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats,
- struct dentry *parent)
+void ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats,
+ struct dentry *parent)
{
- return ocfs2_blockcheck_debug_install(stats, parent);
+ ocfs2_blockcheck_debug_install(stats, parent);
}
void ocfs2_blockcheck_stats_debugfs_remove(struct ocfs2_blockcheck_stats *stats)
diff --git a/fs/ocfs2/blockcheck.h b/fs/ocfs2/blockcheck.h
index f2d2689407fa..8f17d2c85f40 100644
--- a/fs/ocfs2/blockcheck.h
+++ b/fs/ocfs2/blockcheck.h
@@ -25,9 +25,6 @@ struct ocfs2_blockcheck_stats {
* ocfs2_blockcheck_stats_debugfs_install()
*/
struct dentry *b_debug_dir; /* Parent of the debugfs files */
- struct dentry *b_debug_check; /* Exposes b_check_count */
- struct dentry *b_debug_failure; /* Exposes b_failure_count */
- struct dentry *b_debug_recover; /* Exposes b_recover_count */
};
@@ -56,8 +53,8 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr,
struct ocfs2_blockcheck_stats *stats);
/* Debug Initialization */
-int ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats,
- struct dentry *parent);
+void ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats,
+ struct dentry *parent);
void ocfs2_blockcheck_stats_debugfs_remove(struct ocfs2_blockcheck_stats *stats);
/*
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 7a3a096856a8..f1b613327ac8 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -92,10 +92,6 @@ static struct o2hb_debug_buf *o2hb_db_failedregions;
#define O2HB_DEBUG_REGION_PINNED "pinned"
static struct dentry *o2hb_debug_dir;
-static struct dentry *o2hb_debug_livenodes;
-static struct dentry *o2hb_debug_liveregions;
-static struct dentry *o2hb_debug_quorumregions;
-static struct dentry *o2hb_debug_failedregions;
static LIST_HEAD(o2hb_all_regions);
@@ -1184,7 +1180,7 @@ bail:
if (atomic_read(&reg->hr_steady_iterations) != 0) {
if (atomic_dec_and_test(&reg->hr_unsteady_iterations)) {
printk(KERN_NOTICE "o2hb: Unable to stabilize "
- "heartbeart on region %s (%s)\n",
+ "heartbeat on region %s (%s)\n",
config_item_name(&reg->hr_item),
reg->hr_dev_name);
atomic_set(&reg->hr_steady_iterations, 0);
@@ -1391,11 +1387,7 @@ static const struct file_operations o2hb_debug_fops = {
void o2hb_exit(void)
{
- debugfs_remove(o2hb_debug_failedregions);
- debugfs_remove(o2hb_debug_quorumregions);
- debugfs_remove(o2hb_debug_liveregions);
- debugfs_remove(o2hb_debug_livenodes);
- debugfs_remove(o2hb_debug_dir);
+ debugfs_remove_recursive(o2hb_debug_dir);
kfree(o2hb_db_livenodes);
kfree(o2hb_db_liveregions);
kfree(o2hb_db_quorumregions);
@@ -1419,79 +1411,37 @@ static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir,
&o2hb_debug_fops);
}
-static int o2hb_debug_init(void)
+static void o2hb_debug_init(void)
{
- int ret = -ENOMEM;
-
o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL);
- if (!o2hb_debug_dir) {
- mlog_errno(ret);
- goto bail;
- }
- o2hb_debug_livenodes = o2hb_debug_create(O2HB_DEBUG_LIVENODES,
- o2hb_debug_dir,
- &o2hb_db_livenodes,
- sizeof(*o2hb_db_livenodes),
- O2HB_DB_TYPE_LIVENODES,
- sizeof(o2hb_live_node_bitmap),
- O2NM_MAX_NODES,
- o2hb_live_node_bitmap);
- if (!o2hb_debug_livenodes) {
- mlog_errno(ret);
- goto bail;
- }
+ o2hb_debug_create(O2HB_DEBUG_LIVENODES, o2hb_debug_dir,
+ &o2hb_db_livenodes, sizeof(*o2hb_db_livenodes),
+ O2HB_DB_TYPE_LIVENODES, sizeof(o2hb_live_node_bitmap),
+ O2NM_MAX_NODES, o2hb_live_node_bitmap);
- o2hb_debug_liveregions = o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS,
- o2hb_debug_dir,
- &o2hb_db_liveregions,
- sizeof(*o2hb_db_liveregions),
- O2HB_DB_TYPE_LIVEREGIONS,
- sizeof(o2hb_live_region_bitmap),
- O2NM_MAX_REGIONS,
- o2hb_live_region_bitmap);
- if (!o2hb_debug_liveregions) {
- mlog_errno(ret);
- goto bail;
- }
+ o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS, o2hb_debug_dir,
+ &o2hb_db_liveregions, sizeof(*o2hb_db_liveregions),
+ O2HB_DB_TYPE_LIVEREGIONS,
+ sizeof(o2hb_live_region_bitmap), O2NM_MAX_REGIONS,
+ o2hb_live_region_bitmap);
- o2hb_debug_quorumregions =
- o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS,
- o2hb_debug_dir,
- &o2hb_db_quorumregions,
- sizeof(*o2hb_db_quorumregions),
- O2HB_DB_TYPE_QUORUMREGIONS,
- sizeof(o2hb_quorum_region_bitmap),
- O2NM_MAX_REGIONS,
- o2hb_quorum_region_bitmap);
- if (!o2hb_debug_quorumregions) {
- mlog_errno(ret);
- goto bail;
- }
-
- o2hb_debug_failedregions =
- o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS,
- o2hb_debug_dir,
- &o2hb_db_failedregions,
- sizeof(*o2hb_db_failedregions),
- O2HB_DB_TYPE_FAILEDREGIONS,
- sizeof(o2hb_failed_region_bitmap),
- O2NM_MAX_REGIONS,
- o2hb_failed_region_bitmap);
- if (!o2hb_debug_failedregions) {
- mlog_errno(ret);
- goto bail;
- }
+ o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS, o2hb_debug_dir,
+ &o2hb_db_quorumregions,
+ sizeof(*o2hb_db_quorumregions),
+ O2HB_DB_TYPE_QUORUMREGIONS,
+ sizeof(o2hb_quorum_region_bitmap), O2NM_MAX_REGIONS,
+ o2hb_quorum_region_bitmap);
- ret = 0;
-bail:
- if (ret)
- o2hb_exit();
-
- return ret;
+ o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS, o2hb_debug_dir,
+ &o2hb_db_failedregions,
+ sizeof(*o2hb_db_failedregions),
+ O2HB_DB_TYPE_FAILEDREGIONS,
+ sizeof(o2hb_failed_region_bitmap), O2NM_MAX_REGIONS,
+ o2hb_failed_region_bitmap);
}
-int o2hb_init(void)
+void o2hb_init(void)
{
int i;
@@ -1511,7 +1461,7 @@ int o2hb_init(void)
o2hb_dependent_users = 0;
- return o2hb_debug_init();
+ o2hb_debug_init();
}
/* if we're already in a callback then we're already serialized by the sem */
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index 7f37540ac4ab..beed31ea86cf 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -63,7 +63,7 @@ void o2hb_unregister_callback(const char *region_uuid,
void o2hb_fill_node_map(unsigned long *map,
unsigned bytes);
void o2hb_exit(void);
-int o2hb_init(void);
+void o2hb_init(void);
int o2hb_check_node_heartbeating_no_sem(u8 node_num);
int o2hb_check_node_heartbeating_from_callback(u8 node_num);
void o2hb_stop_all_regions(void);
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 0784575f4c2a..02bf4a1774cc 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -38,10 +38,6 @@
#define SHOW_SOCK_STATS 1
static struct dentry *o2net_dentry;
-static struct dentry *sc_dentry;
-static struct dentry *nst_dentry;
-static struct dentry *stats_dentry;
-static struct dentry *nodes_dentry;
static DEFINE_SPINLOCK(o2net_debug_lock);
@@ -490,36 +486,23 @@ static const struct file_operations nodes_fops = {
void o2net_debugfs_exit(void)
{
- debugfs_remove(nodes_dentry);
- debugfs_remove(stats_dentry);
- debugfs_remove(sc_dentry);
- debugfs_remove(nst_dentry);
- debugfs_remove(o2net_dentry);
+ debugfs_remove_recursive(o2net_dentry);
}
-int o2net_debugfs_init(void)
+void o2net_debugfs_init(void)
{
umode_t mode = S_IFREG|S_IRUSR;
o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
- if (o2net_dentry)
- nst_dentry = debugfs_create_file(NST_DEBUG_NAME, mode,
- o2net_dentry, NULL, &nst_seq_fops);
- if (nst_dentry)
- sc_dentry = debugfs_create_file(SC_DEBUG_NAME, mode,
- o2net_dentry, NULL, &sc_seq_fops);
- if (sc_dentry)
- stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, mode,
- o2net_dentry, NULL, &stats_seq_fops);
- if (stats_dentry)
- nodes_dentry = debugfs_create_file(NODES_DEBUG_NAME, mode,
- o2net_dentry, NULL, &nodes_fops);
- if (nodes_dentry)
- return 0;
-
- o2net_debugfs_exit();
- mlog_errno(-ENOMEM);
- return -ENOMEM;
+
+ debugfs_create_file(NST_DEBUG_NAME, mode, o2net_dentry, NULL,
+ &nst_seq_fops);
+ debugfs_create_file(SC_DEBUG_NAME, mode, o2net_dentry, NULL,
+ &sc_seq_fops);
+ debugfs_create_file(STATS_DEBUG_NAME, mode, o2net_dentry, NULL,
+ &stats_seq_fops);
+ debugfs_create_file(NODES_DEBUG_NAME, mode, o2net_dentry, NULL,
+ &nodes_fops);
}
#endif /* CONFIG_DEBUG_FS */
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 2234f7fd1f7c..7a7640c59f3c 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -828,9 +828,7 @@ static int __init init_o2nm(void)
{
int ret = -1;
- ret = o2hb_init();
- if (ret)
- goto out;
+ o2hb_init();
ret = o2net_init();
if (ret)
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 3d5d4b2b1356..5c424a099280 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -76,7 +76,7 @@ static void o2quo_fence_self(void)
};
}
-/* Indicate that a timeout occurred on a hearbeat region write. The
+/* Indicate that a timeout occurred on a heartbeat region write. The
* other nodes in the cluster may consider us dead at that time so we
* want to "fence" ourselves so that we don't scribble on the disk
* after they think they've recovered us. This can't solve all
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index c599463d0694..48a3398f0bf5 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1762,7 +1762,7 @@ static void o2net_hb_node_up_cb(struct o2nm_node *node, int node_num,
(msecs_to_jiffies(o2net_reconnect_delay()) + 1);
if (node_num != o2nm_this_node()) {
- /* believe it or not, accept and node hearbeating testing
+ /* believe it or not, accept and node heartbeating testing
* can succeed for this node before we got here.. so
* only use set_nn_state to clear the persistent error
* if that hasn't already happened */
@@ -2129,8 +2129,7 @@ int o2net_init(void)
o2quo_init();
- if (o2net_debugfs_init())
- goto out;
+ o2net_debugfs_init();
o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index dd4242be3f1f..de87cbffd175 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -109,16 +109,15 @@ struct o2net_send_tracking;
struct o2net_sock_container;
#ifdef CONFIG_DEBUG_FS
-int o2net_debugfs_init(void);
+void o2net_debugfs_init(void);
void o2net_debugfs_exit(void);
void o2net_debug_add_nst(struct o2net_send_tracking *nst);
void o2net_debug_del_nst(struct o2net_send_tracking *nst);
void o2net_debug_add_sc(struct o2net_sock_container *sc);
void o2net_debug_del_sc(struct o2net_sock_container *sc);
#else
-static inline int o2net_debugfs_init(void)
+static inline void o2net_debugfs_init(void)
{
- return 0;
}
static inline void o2net_debugfs_exit(void)
{
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index c8af5bc9e980..a4b58ba99927 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -851,7 +851,7 @@ static const struct file_operations debug_state_fops = {
/* end - debug state funcs */
/* files in subroot */
-int dlm_debug_init(struct dlm_ctxt *dlm)
+void dlm_debug_init(struct dlm_ctxt *dlm)
{
struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt;
@@ -860,10 +860,6 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
S_IFREG|S_IRUSR,
dlm->dlm_debugfs_subroot,
dlm, &debug_state_fops);
- if (!dc->debug_state_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
/* for dumping lockres */
dc->debug_lockres_dentry =
@@ -871,20 +867,12 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
S_IFREG|S_IRUSR,
dlm->dlm_debugfs_subroot,
dlm, &debug_lockres_fops);
- if (!dc->debug_lockres_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
/* for dumping mles */
dc->debug_mle_dentry = debugfs_create_file(DLM_DEBUGFS_MLE_STATE,
S_IFREG|S_IRUSR,
dlm->dlm_debugfs_subroot,
dlm, &debug_mle_fops);
- if (!dc->debug_mle_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
/* for dumping lockres on the purge list */
dc->debug_purgelist_dentry =
@@ -892,15 +880,6 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
S_IFREG|S_IRUSR,
dlm->dlm_debugfs_subroot,
dlm, &debug_purgelist_fops);
- if (!dc->debug_purgelist_dentry) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
-
- return 0;
-
-bail:
- return -ENOMEM;
}
void dlm_debug_shutdown(struct dlm_ctxt *dlm)
@@ -920,24 +899,16 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm)
/* subroot - domain dir */
int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
{
- dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name,
- dlm_debugfs_root);
- if (!dlm->dlm_debugfs_subroot) {
- mlog_errno(-ENOMEM);
- goto bail;
- }
-
dlm->dlm_debug_ctxt = kzalloc(sizeof(struct dlm_debug_ctxt),
GFP_KERNEL);
if (!dlm->dlm_debug_ctxt) {
mlog_errno(-ENOMEM);
- goto bail;
+ return -ENOMEM;
}
+ dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name,
+ dlm_debugfs_root);
return 0;
-bail:
- dlm_destroy_debugfs_subroot(dlm);
- return -ENOMEM;
}
void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
@@ -946,14 +917,9 @@ void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
}
/* debugfs root */
-int dlm_create_debugfs_root(void)
+void dlm_create_debugfs_root(void)
{
dlm_debugfs_root = debugfs_create_dir(DLM_DEBUGFS_DIR, NULL);
- if (!dlm_debugfs_root) {
- mlog_errno(-ENOMEM);
- return -ENOMEM;
- }
- return 0;
}
void dlm_destroy_debugfs_root(void)
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index 74d019694c7e..7d0c7c9013ce 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -28,20 +28,19 @@ struct debug_lockres {
struct dlm_lock_resource *dl_res;
};
-int dlm_debug_init(struct dlm_ctxt *dlm);
+void dlm_debug_init(struct dlm_ctxt *dlm);
void dlm_debug_shutdown(struct dlm_ctxt *dlm);
int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm);
void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm);
-int dlm_create_debugfs_root(void);
+void dlm_create_debugfs_root(void);
void dlm_destroy_debugfs_root(void);
#else
-static inline int dlm_debug_init(struct dlm_ctxt *dlm)
+static inline void dlm_debug_init(struct dlm_ctxt *dlm)
{
- return 0;
}
static inline void dlm_debug_shutdown(struct dlm_ctxt *dlm)
{
@@ -53,9 +52,8 @@ static inline int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
static inline void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm)
{
}
-static inline int dlm_create_debugfs_root(void)
+static inline void dlm_create_debugfs_root(void)
{
- return 0;
}
static inline void dlm_destroy_debugfs_root(void)
{
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 9021e72e1f98..7338b5d4647c 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1881,11 +1881,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
goto bail;
}
- status = dlm_debug_init(dlm);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
+ dlm_debug_init(dlm);
snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name);
dlm->dlm_worker = alloc_workqueue(wq_name, WQ_MEM_RECLAIM, 0);
@@ -2346,9 +2342,7 @@ static int __init dlm_init(void)
goto error;
}
- status = dlm_create_debugfs_root();
- if (status)
- goto error;
+ dlm_create_debugfs_root();
return 0;
error:
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 810f841494ef..74b768ca1cd8 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2161,7 +2161,7 @@ put:
* think that $RECOVERY is currently mastered by a dead node. If so,
* we wait a short time to allow that node to get notified by its own
* heartbeat stack, then check again. All $RECOVERY lock resources
- * mastered by dead nodes are purged when the hearbeat callback is
+ * mastered by dead nodes are purged when the heartbeat callback is
* fired, so we can know for sure that it is safe to continue once
* the node returns a live node or no node. */
static int dlm_pre_master_reco_lockres(struct dlm_ctxt *dlm,
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index e22d6a115220..064ce5bbc3f6 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1109,7 +1109,7 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm,
{
u64 mig_cookie = be64_to_cpu(mres->mig_cookie);
int mres_total_locks = be32_to_cpu(mres->total_locks);
- int sz, ret = 0, status = 0;
+ int ret = 0, status = 0;
u8 orig_flags = mres->flags,
orig_master = mres->master;
@@ -1117,9 +1117,6 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm,
if (!mres->num_locks)
return 0;
- sz = sizeof(struct dlm_migratable_lockres) +
- (mres->num_locks * sizeof(struct dlm_migratable_lock));
-
/* add an all-done flag if we reached the last lock */
orig_flags = mres->flags;
BUG_ON(total_locks > mres_total_locks);
@@ -1133,7 +1130,8 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm,
/* send it */
ret = o2net_send_message(DLM_MIG_LOCKRES_MSG, dlm->key, mres,
- sz, send_to, &status);
+ struct_size(mres, ml, mres->num_locks),
+ send_to, &status);
if (ret < 0) {
/* XXX: negative status is not handled.
* this will end up killing this node. */
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b5fc5d3c7525..14207234fa3d 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -426,6 +426,7 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res)
static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res)
{
res->l_lock_refresh = 0;
+ res->l_lock_wait = 0;
memset(&res->l_lock_prmode, 0, sizeof(struct ocfs2_lock_stats));
memset(&res->l_lock_exmode, 0, sizeof(struct ocfs2_lock_stats));
}
@@ -460,6 +461,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level,
if (ret)
stats->ls_fail++;
+
+ stats->ls_last = ktime_to_us(ktime_get_real());
}
static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
@@ -467,6 +470,21 @@ static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
lockres->l_lock_refresh++;
}
+static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres)
+{
+ struct ocfs2_mask_waiter *mw;
+
+ if (list_empty(&lockres->l_mask_waiters)) {
+ lockres->l_lock_wait = 0;
+ return;
+ }
+
+ mw = list_first_entry(&lockres->l_mask_waiters,
+ struct ocfs2_mask_waiter, mw_item);
+ lockres->l_lock_wait =
+ ktime_to_us(ktime_mono_to_real(mw->mw_lock_start));
+}
+
static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
{
mw->mw_lock_start = ktime_get();
@@ -482,6 +500,9 @@ static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res,
static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres)
{
}
+static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres)
+{
+}
static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw)
{
}
@@ -875,6 +896,7 @@ static void lockres_set_flags(struct ocfs2_lock_res *lockres,
list_del_init(&mw->mw_item);
mw->mw_status = 0;
complete(&mw->mw_complete);
+ ocfs2_track_lock_wait(lockres);
}
}
static void lockres_or_flags(struct ocfs2_lock_res *lockres, unsigned long or)
@@ -1386,6 +1408,7 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres,
list_add_tail(&mw->mw_item, &lockres->l_mask_waiters);
mw->mw_mask = mask;
mw->mw_goal = goal;
+ ocfs2_track_lock_wait(lockres);
}
/* returns 0 if the mw that was removed was already satisfied, -EBUSY
@@ -1402,6 +1425,7 @@ static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
list_del_init(&mw->mw_item);
init_completion(&mw->mw_complete);
+ ocfs2_track_lock_wait(lockres);
}
return ret;
@@ -2989,6 +3013,8 @@ struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void)
kref_init(&dlm_debug->d_refcnt);
INIT_LIST_HEAD(&dlm_debug->d_lockres_tracking);
dlm_debug->d_locking_state = NULL;
+ dlm_debug->d_locking_filter = NULL;
+ dlm_debug->d_filter_secs = 0;
out:
return dlm_debug;
}
@@ -3079,17 +3105,43 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos)
* - Lock stats printed
* New in version 3
* - Max time in lock stats is in usecs (instead of nsecs)
+ * New in version 4
+ * - Add last pr/ex unlock times and first lock wait time in usecs
*/
-#define OCFS2_DLM_DEBUG_STR_VERSION 3
+#define OCFS2_DLM_DEBUG_STR_VERSION 4
static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
{
int i;
char *lvb;
struct ocfs2_lock_res *lockres = v;
+#ifdef CONFIG_OCFS2_FS_STATS
+ u64 now, last;
+ struct ocfs2_dlm_debug *dlm_debug =
+ ((struct ocfs2_dlm_seq_priv *)m->private)->p_dlm_debug;
+#endif
if (!lockres)
return -EINVAL;
+#ifdef CONFIG_OCFS2_FS_STATS
+ if (!lockres->l_lock_wait && dlm_debug->d_filter_secs) {
+ now = ktime_to_us(ktime_get_real());
+ if (lockres->l_lock_prmode.ls_last >
+ lockres->l_lock_exmode.ls_last)
+ last = lockres->l_lock_prmode.ls_last;
+ else
+ last = lockres->l_lock_exmode.ls_last;
+ /*
+ * Use d_filter_secs field to filter lock resources dump,
+ * the default d_filter_secs(0) value filters nothing,
+ * otherwise, only dump the last N seconds active lock
+ * resources.
+ */
+ if (div_u64(now - last, 1000000) > dlm_debug->d_filter_secs)
+ return 0;
+ }
+#endif
+
seq_printf(m, "0x%x\t", OCFS2_DLM_DEBUG_STR_VERSION);
if (lockres->l_type == OCFS2_LOCK_TYPE_DENTRY)
@@ -3131,6 +3183,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
# define lock_max_prmode(_l) ((_l)->l_lock_prmode.ls_max)
# define lock_max_exmode(_l) ((_l)->l_lock_exmode.ls_max)
# define lock_refresh(_l) ((_l)->l_lock_refresh)
+# define lock_last_prmode(_l) ((_l)->l_lock_prmode.ls_last)
+# define lock_last_exmode(_l) ((_l)->l_lock_exmode.ls_last)
+# define lock_wait(_l) ((_l)->l_lock_wait)
#else
# define lock_num_prmode(_l) (0)
# define lock_num_exmode(_l) (0)
@@ -3141,6 +3196,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
# define lock_max_prmode(_l) (0)
# define lock_max_exmode(_l) (0)
# define lock_refresh(_l) (0)
+# define lock_last_prmode(_l) (0ULL)
+# define lock_last_exmode(_l) (0ULL)
+# define lock_wait(_l) (0ULL)
#endif
/* The following seq_print was added in version 2 of this output */
seq_printf(m, "%u\t"
@@ -3151,7 +3209,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
"%llu\t"
"%u\t"
"%u\t"
- "%u\t",
+ "%u\t"
+ "%llu\t"
+ "%llu\t"
+ "%llu\t",
lock_num_prmode(lockres),
lock_num_exmode(lockres),
lock_num_prmode_failed(lockres),
@@ -3160,7 +3221,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
lock_total_exmode(lockres),
lock_max_prmode(lockres),
lock_max_exmode(lockres),
- lock_refresh(lockres));
+ lock_refresh(lockres),
+ lock_last_prmode(lockres),
+ lock_last_exmode(lockres),
+ lock_wait(lockres));
/* End the line */
seq_printf(m, "\n");
@@ -3214,9 +3278,8 @@ static const struct file_operations ocfs2_dlm_debug_fops = {
.llseek = seq_lseek,
};
-static int ocfs2_dlm_init_debug(struct ocfs2_super *osb)
+static void ocfs2_dlm_init_debug(struct ocfs2_super *osb)
{
- int ret = 0;
struct ocfs2_dlm_debug *dlm_debug = osb->osb_dlm_debug;
dlm_debug->d_locking_state = debugfs_create_file("locking_state",
@@ -3224,16 +3287,11 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb)
osb->osb_debug_root,
osb,
&ocfs2_dlm_debug_fops);
- if (!dlm_debug->d_locking_state) {
- ret = -EINVAL;
- mlog(ML_ERROR,
- "Unable to create locking state debugfs file.\n");
- goto out;
- }
- ocfs2_get_dlm_debug(dlm_debug);
-out:
- return ret;
+ dlm_debug->d_locking_filter = debugfs_create_u32("locking_filter",
+ 0600,
+ osb->osb_debug_root,
+ &dlm_debug->d_filter_secs);
}
static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
@@ -3242,6 +3300,7 @@ static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb)
if (dlm_debug) {
debugfs_remove(dlm_debug->d_locking_state);
+ debugfs_remove(dlm_debug->d_locking_filter);
ocfs2_put_dlm_debug(dlm_debug);
}
}
@@ -3256,11 +3315,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
goto local;
}
- status = ocfs2_dlm_init_debug(osb);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
+ ocfs2_dlm_init_debug(osb);
/* launch downconvert thread */
osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s",
@@ -4352,7 +4407,6 @@ static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb)
static int ocfs2_downconvert_thread(void *arg)
{
- int status = 0;
struct ocfs2_super *osb = arg;
/* only quit once we've been asked to stop and there is no more
@@ -4370,7 +4424,7 @@ static int ocfs2_downconvert_thread(void *arg)
}
osb->dc_task = NULL;
- return status;
+ return 0;
}
void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index f03674afbd30..158e5af767fd 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -424,12 +424,11 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
bh = osb->local_alloc_bh;
alloc = (struct ocfs2_dinode *) bh->b_data;
- alloc_copy = kmalloc(bh->b_size, GFP_NOFS);
+ alloc_copy = kmemdup(alloc, bh->b_size, GFP_NOFS);
if (!alloc_copy) {
status = -ENOMEM;
goto out_commit;
}
- memcpy(alloc_copy, alloc, bh->b_size);
status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode),
bh, OCFS2_JOURNAL_ACCESS_WRITE);
@@ -1272,13 +1271,12 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
* local alloc shutdown won't try to double free main bitmap
* bits. Make a copy so the sync function knows which bits to
* free. */
- alloc_copy = kmalloc(osb->local_alloc_bh->b_size, GFP_NOFS);
+ alloc_copy = kmemdup(alloc, osb->local_alloc_bh->b_size, GFP_NOFS);
if (!alloc_copy) {
status = -ENOMEM;
mlog_errno(status);
goto bail;
}
- memcpy(alloc_copy, alloc, osb->local_alloc_bh->b_size);
status = ocfs2_journal_access_di(handle,
INODE_CACHE(local_alloc_inode),
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index a4647a646f07..fddbbd60f434 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -150,6 +150,7 @@ struct ocfs2_lock_stats {
/* Storing max wait in usecs saves 24 bytes per inode */
u32 ls_max; /* Max wait in USEC */
+ u64 ls_last; /* Last unlock time in USEC */
};
#endif
@@ -191,6 +192,7 @@ struct ocfs2_lock_res {
#ifdef CONFIG_OCFS2_FS_STATS
struct ocfs2_lock_stats l_lock_prmode; /* PR mode stats */
u32 l_lock_refresh; /* Disk refreshes */
+ u64 l_lock_wait; /* First lock wait time */
struct ocfs2_lock_stats l_lock_exmode; /* EX mode stats */
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -222,6 +224,8 @@ struct ocfs2_orphan_scan {
struct ocfs2_dlm_debug {
struct kref d_refcnt;
struct dentry *d_locking_state;
+ struct dentry *d_locking_filter;
+ u32 d_filter_secs;
struct list_head d_lockres_tracking;
};
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a201f9780b35..8b2f39506648 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1079,33 +1079,15 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
osb->osb_debug_root = debugfs_create_dir(osb->uuid_str,
ocfs2_debugfs_root);
- if (!osb->osb_debug_root) {
- status = -EINVAL;
- mlog(ML_ERROR, "Unable to create per-mount debugfs root.\n");
- goto read_super_error;
- }
osb->osb_ctxt = debugfs_create_file("fs_state", S_IFREG|S_IRUSR,
osb->osb_debug_root,
osb,
&ocfs2_osb_debug_fops);
- if (!osb->osb_ctxt) {
- status = -EINVAL;
- mlog_errno(status);
- goto read_super_error;
- }
- if (ocfs2_meta_ecc(osb)) {
- status = ocfs2_blockcheck_stats_debugfs_install(
- &osb->osb_ecc_stats,
- osb->osb_debug_root);
- if (status) {
- mlog(ML_ERROR,
- "Unable to create blockcheck statistics "
- "files\n");
- goto read_super_error;
- }
- }
+ if (ocfs2_meta_ecc(osb))
+ ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats,
+ osb->osb_debug_root);
status = ocfs2_mount_volume(sb);
if (status < 0)
@@ -1592,11 +1574,6 @@ static int __init ocfs2_init(void)
goto out2;
ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
- if (!ocfs2_debugfs_root) {
- status = -ENOMEM;
- mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
- goto out3;
- }
ocfs2_set_locking_protocol();
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c40fca98f2b7..77eb628ecc7f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -532,8 +532,7 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
unsigned long totalpages = totalram_pages() + total_swap_pages;
unsigned long points = 0;
- points = oom_badness(task, NULL, NULL, totalpages) *
- 1000 / totalpages;
+ points = oom_badness(task, totalpages) * 1000 / totalpages;
seq_printf(m, "%lu\n", points);
return 0;
@@ -1962,9 +1961,12 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
goto out;
if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
- down_read(&mm->mmap_sem);
- exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end);
- up_read(&mm->mmap_sem);
+ status = down_read_killable(&mm->mmap_sem);
+ if (!status) {
+ exact_vma_exists = !!find_exact_vma(mm, vm_start,
+ vm_end);
+ up_read(&mm->mmap_sem);
+ }
}
mmput(mm);
@@ -2010,8 +2012,11 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
if (rc)
goto out_mmput;
+ rc = down_read_killable(&mm->mmap_sem);
+ if (rc)
+ goto out_mmput;
+
rc = -ENOENT;
- down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
*path = vma->vm_file->f_path;
@@ -2107,7 +2112,11 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
if (!mm)
goto out_put_task;
- down_read(&mm->mmap_sem);
+ result = ERR_PTR(-EINTR);
+ if (down_read_killable(&mm->mmap_sem))
+ goto out_put_mm;
+
+ result = ERR_PTR(-ENOENT);
vma = find_exact_vma(mm, vm_start, vm_end);
if (!vma)
goto out_no_vma;
@@ -2118,6 +2127,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
out_no_vma:
up_read(&mm->mmap_sem);
+out_put_mm:
mmput(mm);
out_put_task:
put_task_struct(task);
@@ -2160,7 +2170,12 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
mm = get_task_mm(task);
if (!mm)
goto out_put_task;
- down_read(&mm->mmap_sem);
+
+ ret = down_read_killable(&mm->mmap_sem);
+ if (ret) {
+ mmput(mm);
+ goto out_put_task;
+ }
nr_files = 0;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 568d90e17c17..465ea0153b2a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -120,7 +120,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
show_val_kb(m, "Committed_AS: ", committed);
seq_printf(m, "VmallocTotal: %8lu kB\n",
(unsigned long)VMALLOC_TOTAL >> 10);
- show_val_kb(m, "VmallocUsed: ", 0ul);
+ show_val_kb(m, "VmallocUsed: ", vmalloc_nr_pages());
show_val_kb(m, "VmallocChunk: ", 0ul);
show_val_kb(m, "Percpu: ", pcpu_nr_pages());
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 01d4eb0e6bd1..dedca3da428a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -166,7 +166,11 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
if (!mm || !mmget_not_zero(mm))
return NULL;
- down_read(&mm->mmap_sem);
+ if (down_read_killable(&mm->mmap_sem)) {
+ mmput(mm);
+ return ERR_PTR(-EINTR);
+ }
+
hold_task_mempolicy(priv);
priv->tail_vma = get_gate_vma(mm);
@@ -417,17 +421,53 @@ struct mem_size_stats {
unsigned long shared_hugetlb;
unsigned long private_hugetlb;
u64 pss;
+ u64 pss_anon;
+ u64 pss_file;
+ u64 pss_shmem;
u64 pss_locked;
u64 swap_pss;
bool check_shmem_swap;
};
+static void smaps_page_accumulate(struct mem_size_stats *mss,
+ struct page *page, unsigned long size, unsigned long pss,
+ bool dirty, bool locked, bool private)
+{
+ mss->pss += pss;
+
+ if (PageAnon(page))
+ mss->pss_anon += pss;
+ else if (PageSwapBacked(page))
+ mss->pss_shmem += pss;
+ else
+ mss->pss_file += pss;
+
+ if (locked)
+ mss->pss_locked += pss;
+
+ if (dirty || PageDirty(page)) {
+ if (private)
+ mss->private_dirty += size;
+ else
+ mss->shared_dirty += size;
+ } else {
+ if (private)
+ mss->private_clean += size;
+ else
+ mss->shared_clean += size;
+ }
+}
+
static void smaps_account(struct mem_size_stats *mss, struct page *page,
bool compound, bool young, bool dirty, bool locked)
{
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
+ /*
+ * First accumulate quantities that depend only on |size| and the type
+ * of the compound page.
+ */
if (PageAnon(page)) {
mss->anonymous += size;
if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
@@ -440,42 +480,25 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
mss->referenced += size;
/*
+ * Then accumulate quantities that may depend on sharing, or that may
+ * differ page-by-page.
+ *
* page_count(page) == 1 guarantees the page is mapped exactly once.
* If any subpage of the compound page mapped with PTE it would elevate
* page_count().
*/
if (page_count(page) == 1) {
- if (dirty || PageDirty(page))
- mss->private_dirty += size;
- else
- mss->private_clean += size;
- mss->pss += (u64)size << PSS_SHIFT;
- if (locked)
- mss->pss_locked += (u64)size << PSS_SHIFT;
+ smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty,
+ locked, true);
return;
}
-
for (i = 0; i < nr; i++, page++) {
int mapcount = page_mapcount(page);
- unsigned long pss = (PAGE_SIZE << PSS_SHIFT);
-
- if (mapcount >= 2) {
- if (dirty || PageDirty(page))
- mss->shared_dirty += PAGE_SIZE;
- else
- mss->shared_clean += PAGE_SIZE;
- mss->pss += pss / mapcount;
- if (locked)
- mss->pss_locked += pss / mapcount;
- } else {
- if (dirty || PageDirty(page))
- mss->private_dirty += PAGE_SIZE;
- else
- mss->private_clean += PAGE_SIZE;
- mss->pss += pss;
- if (locked)
- mss->pss_locked += pss;
- }
+ unsigned long pss = PAGE_SIZE << PSS_SHIFT;
+ if (mapcount >= 2)
+ pss /= mapcount;
+ smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked,
+ mapcount < 2);
}
}
@@ -754,10 +777,23 @@ static void smap_gather_stats(struct vm_area_struct *vma,
seq_put_decimal_ull_width(m, str, (val) >> 10, 8)
/* Show the contents common for smaps and smaps_rollup */
-static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss)
+static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss,
+ bool rollup_mode)
{
SEQ_PUT_DEC("Rss: ", mss->resident);
SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT);
+ if (rollup_mode) {
+ /*
+ * These are meaningful only for smaps_rollup, otherwise two of
+ * them are zero, and the other one is the same as Pss.
+ */
+ SEQ_PUT_DEC(" kB\nPss_Anon: ",
+ mss->pss_anon >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_File: ",
+ mss->pss_file >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_Shmem: ",
+ mss->pss_shmem >> PSS_SHIFT);
+ }
SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean);
SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty);
SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean);
@@ -794,7 +830,7 @@ static int show_smap(struct seq_file *m, void *v)
SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma));
seq_puts(m, " kB\n");
- __show_smap(m, &mss);
+ __show_smap(m, &mss, false);
seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma));
@@ -828,7 +864,10 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
memset(&mss, 0, sizeof(mss));
- down_read(&mm->mmap_sem);
+ ret = down_read_killable(&mm->mmap_sem);
+ if (ret)
+ goto out_put_mm;
+
hold_task_mempolicy(priv);
for (vma = priv->mm->mmap; vma; vma = vma->vm_next) {
@@ -841,12 +880,13 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
seq_pad(m, ' ');
seq_puts(m, "[rollup]\n");
- __show_smap(m, &mss);
+ __show_smap(m, &mss, true);
release_task_mempolicy(priv);
up_read(&mm->mmap_sem);
- mmput(mm);
+out_put_mm:
+ mmput(mm);
out_put_task:
put_task_struct(priv->task);
priv->task = NULL;
@@ -1132,7 +1172,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
goto out_mm;
}
- down_read(&mm->mmap_sem);
+ if (down_read_killable(&mm->mmap_sem)) {
+ count = -EINTR;
+ goto out_mm;
+ }
tlb_gather_mmu(&tlb, mm, 0, -1);
if (type == CLEAR_REFS_SOFT_DIRTY) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -1539,7 +1582,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
/* overflow ? */
if (end < start_vaddr || end > end_vaddr)
end = end_vaddr;
- down_read(&mm->mmap_sem);
+ ret = down_read_killable(&mm->mmap_sem);
+ if (ret)
+ goto out_free;
ret = walk_page_range(start_vaddr, end, &pagemap_walk);
up_read(&mm->mmap_sem);
start_vaddr = end;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 36bf0f2e102e..7907e6419e57 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -211,7 +211,11 @@ static void *m_start(struct seq_file *m, loff_t *pos)
if (!mm || !mmget_not_zero(mm))
return NULL;
- down_read(&mm->mmap_sem);
+ if (down_read_killable(&mm->mmap_sem)) {
+ mmput(mm);
+ return ERR_PTR(-EINTR);
+ }
+
/* start from the Nth VMA */
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
if (n-- == 0)