[lustre-devel] [PATCH 05/15] lustre: obdclass: reintroduce lu_ref
James Simmons
jsimmons at infradead.org
Sun Aug 22 19:27:36 PDT 2021
Previously lu_ref was removed due to the lack of testing. Intel
brought this back to life so reintroduce this debugging feature.
WC-bug-id: https://jira.whamcloud.com/browse/LU-6142
Lustre-commit: 5c98de856618f30 ("LU-6142 obdclass: resolve lu_ref checkpatch issues")
Reviewed-on: https://review.whamcloud.com/44088
WC-bug-id: https://jira.whamcloud.com/browse/LU-8066
Lustre-commit: 6b319185659104b ("LU-8066 obdclass: move lu_ref to debugfs")
Reviewed-on: https://review.whamcloud.com/44311
Signed-off-by: James Simmons <jsimmons at infradead.org>
Reviewed-by: Andreas Dilger <adilger at whamcloud.com>
Reviewed-by: Arshad Hussain <arshad.hussain at aeoncomputing.com>
Reviewed-by: Neil Brown <neilb at suse.de>
Reviewed-by: Oleg Drokin <green at whamcloud.com>
---
fs/lustre/Kconfig | 9 +
fs/lustre/include/lu_ref.h | 104 ++++++++++--
fs/lustre/obdclass/Makefile | 3 +-
fs/lustre/obdclass/cl_io.c | 8 +
fs/lustre/obdclass/lu_ref.c | 393 ++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 503 insertions(+), 14 deletions(-)
diff --git a/fs/lustre/Kconfig b/fs/lustre/Kconfig
index bb0e4e7..bcd9d0a 100644
--- a/fs/lustre/Kconfig
+++ b/fs/lustre/Kconfig
@@ -61,6 +61,15 @@ config LUSTRE_DEBUG_EXPENSIVE_CHECK
Use with caution. If unsure, say N.
+config LUSTRE_DEBUG_LU_REF
+ bool "Enable Lustre lu_ref checks"
+ depends on LUSTRE_DEBUG_EXPENSIVE_CHECK
+ help
+ lu_ref gives the ability to track references to a given object. It is
+ quite cpu expensive so its disabled by default.
+
+ Use with caution. If unsure, say N.
+
config LUSTRE_TRANSLATE_ERRNOS
bool
depends on LUSTRE_FS && !X86
diff --git a/fs/lustre/include/lu_ref.h b/fs/lustre/include/lu_ref.h
index 493df95..7b368c2 100644
--- a/fs/lustre/include/lu_ref.h
+++ b/fs/lustre/include/lu_ref.h
@@ -104,12 +104,91 @@
* @{
*/
-/*
- * dummy data structures/functions to pass compile for now.
- * We need to reimplement them with kref.
+#ifdef CONFIG_LUSTRE_DEBUG_LU_REF
+
+/**
+ * Data-structure to keep track of references to a given object. This is used
+ * for debugging.
+ *
+ * lu_ref is embedded into an object which other entities (objects, threads,
+ * etc.) refer to.
*/
-struct lu_ref {};
-struct lu_ref_link {};
+struct lu_ref {
+ /**
+ * Spin-lock protecting lu_ref::lf_list.
+ */
+ spinlock_t lf_guard;
+ /**
+ * List of all outstanding references (each represented by struct
+ * lu_ref_link), pointing to this object.
+ */
+ struct list_head lf_list;
+ /**
+ * # of links.
+ */
+ short lf_refs;
+ /**
+ * Flag set when lu_ref_add() failed to allocate lu_ref_link. It is
+ * used to mask spurious failure of the following lu_ref_del().
+ */
+ short lf_failed;
+ /**
+ * flags - attribute for the lu_ref, for pad and future use.
+ */
+ short lf_flags;
+ /**
+ * Where was I initialized?
+ */
+ short lf_line;
+ const char *lf_func;
+ /**
+ * Linkage into a global list of all lu_ref's (lu_ref_refs).
+ */
+ struct list_head lf_linkage;
+};
+
+struct lu_ref_link {
+ struct lu_ref *ll_ref;
+ struct list_head ll_linkage;
+ const char *ll_scope;
+ const void *ll_source;
+};
+
+void lu_ref_init_loc(struct lu_ref *ref, const char *func, const int line);
+void lu_ref_fini(struct lu_ref *ref);
+#define lu_ref_init(ref) lu_ref_init_loc(ref, __func__, __LINE__)
+
+void lu_ref_add(struct lu_ref *ref, const char *scope, const void *source);
+
+void lu_ref_add_atomic(struct lu_ref *ref, const char *scope,
+ const void *source);
+
+void lu_ref_add_at(struct lu_ref *ref, struct lu_ref_link *link,
+ const char *scope, const void *source);
+
+void lu_ref_del(struct lu_ref *ref, const char *scope, const void *source);
+
+void lu_ref_set_at(struct lu_ref *ref, struct lu_ref_link *link,
+ const char *scope, const void *source0, const void *source1);
+
+void lu_ref_del_at(struct lu_ref *ref, struct lu_ref_link *link,
+ const char *scope, const void *source);
+
+void lu_ref_print(const struct lu_ref *ref);
+
+void lu_ref_print_all(void);
+
+int lu_ref_global_init(void);
+
+void lu_ref_global_fini(void);
+
+#else /* !CONFIG_LUSTRE_DEBUG_LU_REF */
+
+struct lu_ref {
+};
+
+struct lu_ref_link {
+};
static inline void lu_ref_init(struct lu_ref *ref)
{
@@ -119,18 +198,16 @@ static inline void lu_ref_fini(struct lu_ref *ref)
{
}
-static inline struct lu_ref_link *lu_ref_add(struct lu_ref *ref,
- const char *scope,
- const void *source)
+static inline void lu_ref_add(struct lu_ref *ref,
+ const char *scope,
+ const void *source)
{
- return NULL;
}
-static inline struct lu_ref_link *lu_ref_add_atomic(struct lu_ref *ref,
- const char *scope,
- const void *source)
+static inline void lu_ref_add_atomic(struct lu_ref *ref,
+ const char *scope,
+ const void *source)
{
- return NULL;
}
static inline void lu_ref_add_at(struct lu_ref *ref,
@@ -172,6 +249,7 @@ static inline void lu_ref_print(const struct lu_ref *ref)
static inline void lu_ref_print_all(void)
{
}
+#endif /* CONFIG_LUSTRE_DEBUG_LU_REF */
/** @} lu */
diff --git a/fs/lustre/obdclass/Makefile b/fs/lustre/obdclass/Makefile
index 1c46ea4..659cdf0 100644
--- a/fs/lustre/obdclass/Makefile
+++ b/fs/lustre/obdclass/Makefile
@@ -6,7 +6,8 @@ obj-$(CONFIG_LUSTRE_FS) += obdclass.o
obdclass-y := llog.o llog_cat.o llog_obd.o llog_swab.o class_obd.o \
genops.o obd_sysfs.o lprocfs_status.o lprocfs_counters.o \
lustre_handles.o lustre_peer.o statfs_pack.o linkea.o \
- obdo.o obd_config.o obd_mount.o lu_object.o lu_ref.o \
+ obdo.o obd_config.o obd_mount.o lu_object.o \
cl_object.o cl_page.o cl_lock.o cl_io.o kernelcomm.o \
jobid.o integrity.o obd_cksum.o range_lock.o \
lu_tgt_descs.o lu_tgt_pool.o
+obdclass-$(CONFIG_LUSTRE_DEBUG_LU_REF) += lu_ref.o
diff --git a/fs/lustre/obdclass/cl_io.c b/fs/lustre/obdclass/cl_io.c
index 9a0373f..f33a5f3 100644
--- a/fs/lustre/obdclass/cl_io.c
+++ b/fs/lustre/obdclass/cl_io.c
@@ -895,6 +895,14 @@ void cl_page_list_move_head(struct cl_page_list *dst, struct cl_page_list *src,
*/
void cl_page_list_splice(struct cl_page_list *src, struct cl_page_list *dst)
{
+#ifdef CONFIG_LUSTRE_DEBUG_LU_REF
+ struct cl_page *page;
+ struct cl_page *tmp;
+
+ cl_page_list_for_each_safe(page, tmp, src)
+ lu_ref_set_at(&page->cp_reference, &page->cp_queue_ref,
+ "queue", src, dst);
+#endif
dst->pl_nr += src->pl_nr;
src->pl_nr = 0;
list_splice_tail_init(&src->pl_pages, &dst->pl_pages);
diff --git a/fs/lustre/obdclass/lu_ref.c b/fs/lustre/obdclass/lu_ref.c
index fd7ac39..0eb92ce 100644
--- a/fs/lustre/obdclass/lu_ref.c
+++ b/fs/lustre/obdclass/lu_ref.c
@@ -42,3 +42,396 @@
#include <obd_class.h>
#include <obd_support.h>
#include <lu_ref.h>
+
+#ifdef CONFIG_LUSTRE_DEBUG_LU_REF
+/**
+ * Asserts a condition for a given lu_ref. Must be called with
+ * lu_ref::lf_guard held.
+ */
+#define REFASSERT(ref, expr) do { \
+ struct lu_ref *__tmp = (ref); \
+ \
+ if (unlikely(!(expr))) { \
+ lu_ref_print(__tmp); \
+ spin_unlock(&__tmp->lf_guard); \
+ lu_ref_print_all(); \
+ LASSERT(0); \
+ spin_lock(&__tmp->lf_guard); \
+ } \
+} while (0)
+
+static struct kmem_cache *lu_ref_link_kmem;
+
+static struct lu_kmem_descr lu_ref_caches[] = {
+ {
+ .ckd_cache = &lu_ref_link_kmem,
+ .ckd_name = "lu_ref_link_kmem",
+ .ckd_size = sizeof(struct lu_ref_link)
+ },
+ {
+ .ckd_cache = NULL
+ }
+};
+
+/**
+ * Global list of active (initialized, but not finalized) lu_ref's.
+ *
+ * Protected by lu_ref_refs_guard.
+ */
+static LIST_HEAD(lu_ref_refs);
+static DEFINE_SPINLOCK(lu_ref_refs_guard);
+static struct lu_ref lu_ref_marker = {
+ .lf_guard = __SPIN_LOCK_UNLOCKED(lu_ref_marker.lf_guard),
+ .lf_list = LIST_HEAD_INIT(lu_ref_marker.lf_list),
+ .lf_linkage = LIST_HEAD_INIT(lu_ref_marker.lf_linkage)
+};
+
+void lu_ref_print(const struct lu_ref *ref)
+{
+ struct lu_ref_link *link;
+
+ CERROR("lu_ref: %p %d %d %s:%d\n",
+ ref, ref->lf_refs, ref->lf_failed, ref->lf_func, ref->lf_line);
+ list_for_each_entry(link, &ref->lf_list, ll_linkage) {
+ CERROR(" link: %s %p\n", link->ll_scope, link->ll_source);
+ }
+}
+
+static int lu_ref_is_marker(const struct lu_ref *ref)
+{
+ return ref == &lu_ref_marker;
+}
+
+void lu_ref_print_all(void)
+{
+ struct lu_ref *ref;
+
+ spin_lock(&lu_ref_refs_guard);
+ list_for_each_entry(ref, &lu_ref_refs, lf_linkage) {
+ if (lu_ref_is_marker(ref))
+ continue;
+
+ spin_lock(&ref->lf_guard);
+ lu_ref_print(ref);
+ spin_unlock(&ref->lf_guard);
+ }
+ spin_unlock(&lu_ref_refs_guard);
+}
+
+void lu_ref_init_loc(struct lu_ref *ref, const char *func, const int line)
+{
+ ref->lf_refs = 0;
+ ref->lf_func = func;
+ ref->lf_line = line;
+ spin_lock_init(&ref->lf_guard);
+ INIT_LIST_HEAD(&ref->lf_list);
+ spin_lock(&lu_ref_refs_guard);
+ list_add(&ref->lf_linkage, &lu_ref_refs);
+ spin_unlock(&lu_ref_refs_guard);
+}
+EXPORT_SYMBOL(lu_ref_init_loc);
+
+void lu_ref_fini(struct lu_ref *ref)
+{
+ spin_lock(&ref->lf_guard);
+ REFASSERT(ref, list_empty(&ref->lf_list));
+ REFASSERT(ref, ref->lf_refs == 0);
+ spin_unlock(&ref->lf_guard);
+ spin_lock(&lu_ref_refs_guard);
+ list_del_init(&ref->lf_linkage);
+ spin_unlock(&lu_ref_refs_guard);
+}
+EXPORT_SYMBOL(lu_ref_fini);
+
+static struct lu_ref_link *lu_ref_add_context(struct lu_ref *ref,
+ int flags,
+ const char *scope,
+ const void *source)
+{
+ struct lu_ref_link *link;
+
+ link = NULL;
+ if (lu_ref_link_kmem) {
+ link = kmem_cache_zalloc(lu_ref_link_kmem, flags);
+ if (link) {
+ link->ll_ref = ref;
+ link->ll_scope = scope;
+ link->ll_source = source;
+ spin_lock(&ref->lf_guard);
+ list_add_tail(&link->ll_linkage, &ref->lf_list);
+ ref->lf_refs++;
+ spin_unlock(&ref->lf_guard);
+ }
+ }
+
+ if (!link) {
+ spin_lock(&ref->lf_guard);
+ ref->lf_failed++;
+ spin_unlock(&ref->lf_guard);
+ link = ERR_PTR(-ENOMEM);
+ }
+
+ return link;
+}
+
+void lu_ref_add(struct lu_ref *ref, const char *scope, const void *source)
+{
+ might_sleep();
+ lu_ref_add_context(ref, GFP_NOFS, scope, source);
+}
+EXPORT_SYMBOL(lu_ref_add);
+
+void lu_ref_add_at(struct lu_ref *ref, struct lu_ref_link *link,
+ const char *scope, const void *source)
+{
+ link->ll_ref = ref;
+ link->ll_scope = scope;
+ link->ll_source = source;
+ spin_lock(&ref->lf_guard);
+ list_add_tail(&link->ll_linkage, &ref->lf_list);
+ ref->lf_refs++;
+ spin_unlock(&ref->lf_guard);
+}
+EXPORT_SYMBOL(lu_ref_add_at);
+
+/**
+ * Version of lu_ref_add() to be used in non-blockable contexts.
+ */
+void lu_ref_add_atomic(struct lu_ref *ref, const char *scope,
+ const void *source)
+{
+ lu_ref_add_context(ref, GFP_ATOMIC, scope, source);
+}
+EXPORT_SYMBOL(lu_ref_add_atomic);
+
+static inline int lu_ref_link_eq(const struct lu_ref_link *link,
+ const char *scope,
+ const void *source)
+{
+ return link->ll_source == source && !strcmp(link->ll_scope, scope);
+}
+
+/**
+ * Maximal chain length seen so far.
+ */
+static unsigned int lu_ref_chain_max_length = 127;
+
+/**
+ * Searches for a lu_ref_link with given [scope, source] within given lu_ref.
+ */
+static struct lu_ref_link *lu_ref_find(struct lu_ref *ref, const char *scope,
+ const void *source)
+{
+ struct lu_ref_link *link;
+ unsigned int iterations;
+
+ iterations = 0;
+ list_for_each_entry(link, &ref->lf_list, ll_linkage) {
+ ++iterations;
+ if (lu_ref_link_eq(link, scope, source)) {
+ if (iterations > lu_ref_chain_max_length) {
+ CWARN("Long lu_ref chain %d \"%s\":%p\n",
+ iterations, scope, source);
+ lu_ref_chain_max_length = iterations * 3 / 2;
+ }
+ return link;
+ }
+ }
+ return NULL;
+}
+
+void lu_ref_del(struct lu_ref *ref, const char *scope, const void *source)
+{
+ struct lu_ref_link *link;
+
+ spin_lock(&ref->lf_guard);
+ link = lu_ref_find(ref, scope, source);
+ if (link) {
+ list_del(&link->ll_linkage);
+ ref->lf_refs--;
+ spin_unlock(&ref->lf_guard);
+ kmem_cache_free(lu_ref_link_kmem, link);
+ } else {
+ REFASSERT(ref, ref->lf_failed > 0);
+ ref->lf_failed--;
+ spin_unlock(&ref->lf_guard);
+ }
+}
+EXPORT_SYMBOL(lu_ref_del);
+
+void lu_ref_set_at(struct lu_ref *ref, struct lu_ref_link *link,
+ const char *scope,
+ const void *source0, const void *source1)
+{
+ spin_lock(&ref->lf_guard);
+ REFASSERT(ref, !IS_ERR_OR_NULL(link));
+ REFASSERT(ref, link->ll_ref == ref);
+ REFASSERT(ref, lu_ref_link_eq(link, scope, source0));
+ link->ll_source = source1;
+ spin_unlock(&ref->lf_guard);
+}
+EXPORT_SYMBOL(lu_ref_set_at);
+
+void lu_ref_del_at(struct lu_ref *ref, struct lu_ref_link *link,
+ const char *scope, const void *source)
+{
+ spin_lock(&ref->lf_guard);
+ REFASSERT(ref, !IS_ERR_OR_NULL(link));
+ REFASSERT(ref, link->ll_ref == ref);
+ REFASSERT(ref, lu_ref_link_eq(link, scope, source));
+ list_del(&link->ll_linkage);
+ ref->lf_refs--;
+ spin_unlock(&ref->lf_guard);
+}
+EXPORT_SYMBOL(lu_ref_del_at);
+
+static void *lu_ref_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ struct lu_ref *ref = seq->private;
+
+ spin_lock(&lu_ref_refs_guard);
+ if (list_empty(&ref->lf_linkage))
+ ref = NULL;
+ spin_unlock(&lu_ref_refs_guard);
+
+ return ref;
+}
+
+static void *lu_ref_seq_next(struct seq_file *seq, void *p, loff_t *pos)
+{
+ struct lu_ref *ref = p;
+ struct lu_ref *next;
+
+ LASSERT(seq->private == p);
+ LASSERT(!list_empty(&ref->lf_linkage));
+
+ (*pos)++;
+ spin_lock(&lu_ref_refs_guard);
+ next = list_entry(ref->lf_linkage.next, struct lu_ref, lf_linkage);
+ if (&next->lf_linkage == &lu_ref_refs)
+ p = NULL;
+ else
+ list_move(&ref->lf_linkage, &next->lf_linkage);
+ spin_unlock(&lu_ref_refs_guard);
+
+ return p;
+}
+
+static void lu_ref_seq_stop(struct seq_file *seq, void *p)
+{
+ /* Nothing to do */
+}
+
+
+static int lu_ref_seq_show(struct seq_file *seq, void *p)
+{
+ struct lu_ref *ref = p;
+ struct lu_ref *next;
+
+ spin_lock(&lu_ref_refs_guard);
+ next = list_entry(ref->lf_linkage.next, struct lu_ref, lf_linkage);
+ if ((&next->lf_linkage == &lu_ref_refs) || lu_ref_is_marker(next)) {
+ spin_unlock(&lu_ref_refs_guard);
+ return 0;
+ }
+
+ /* print the entry */
+ spin_lock(&next->lf_guard);
+ seq_printf(seq, "lu_ref: %p %d %d %s:%d\n",
+ next, next->lf_refs, next->lf_failed,
+ next->lf_func, next->lf_line);
+ if (next->lf_refs > 64) {
+ seq_puts(seq, " too many references, skip\n");
+ } else {
+ struct lu_ref_link *link;
+ int i = 0;
+
+ list_for_each_entry(link, &next->lf_list, ll_linkage)
+ seq_printf(seq, " #%d link: %s %p\n",
+ i++, link->ll_scope, link->ll_source);
+ }
+ spin_unlock(&next->lf_guard);
+ spin_unlock(&lu_ref_refs_guard);
+
+ return 0;
+}
+
+static const struct seq_operations lu_ref_seq_ops = {
+ .start = lu_ref_seq_start,
+ .stop = lu_ref_seq_stop,
+ .next = lu_ref_seq_next,
+ .show = lu_ref_seq_show
+};
+
+static int lu_ref_seq_open(struct inode *inode, struct file *file)
+{
+ struct lu_ref *marker = &lu_ref_marker;
+ int result = 0;
+
+ result = seq_open(file, &lu_ref_seq_ops);
+ if (result == 0) {
+ spin_lock(&lu_ref_refs_guard);
+ if (!list_empty(&marker->lf_linkage))
+ result = -EAGAIN;
+ else
+ list_add(&marker->lf_linkage, &lu_ref_refs);
+ spin_unlock(&lu_ref_refs_guard);
+
+ if (result == 0) {
+ struct seq_file *f = file->private_data;
+
+ f->private = marker;
+ } else {
+ seq_release(inode, file);
+ }
+ }
+
+ return result;
+}
+
+static int lu_ref_seq_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *m = file->private_data;
+ struct lu_ref *ref = m->private;
+
+ spin_lock(&lu_ref_refs_guard);
+ list_del_init(&ref->lf_linkage);
+ spin_unlock(&lu_ref_refs_guard);
+
+ return seq_release(inode, file);
+}
+
+static const struct file_operations lu_ref_dump_fops = {
+ .owner = THIS_MODULE,
+ .open = lu_ref_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = lu_ref_seq_release
+};
+
+int lu_ref_global_init(void)
+{
+ int result;
+
+ CDEBUG(D_CONSOLE,
+ "lu_ref tracking is enabled. Performance isn't.\n");
+
+ result = lu_kmem_init(lu_ref_caches);
+ if (result)
+ return result;
+
+ debugfs_create_file("lu_refs", 0444, debugfs_lustre_root,
+ NULL, &lu_ref_dump_fops);
+
+ return result;
+}
+
+void lu_ref_global_fini(void)
+{
+ /* debugfs file gets cleaned up by debugfs_remove_recursive on
+ * debugfs_lustre_root
+ */
+ lu_kmem_fini(lu_ref_caches);
+}
+
+#endif /* CONFIG_LUSTRE_DEBUG_LU_REF */
--
1.8.3.1
More information about the lustre-devel
mailing list