This patchset adds tracepoints around mmap_lock acquisition. This is useful so
we can measure the latency of lock acquisition, in order to detect contention.
This version is based upon linux-next (since it depends on some recently-merged
patches [1] [2]).
Changes since v2:
- Refactored tracing helper functions so the helpers are simper, but the locking
functinos are slightly more verbose. Overall, this decreased the delta to
mmap_lock.h slightly.
- Fixed a typo in a comment. :)
Changes since v1:
- Functions renamed to reserve the "trace_" prefix for actual tracepoints.
- We no longer measure the duration directly. Instead, users are expected to
construct a synthetic event which computes the interval between "start
locking" and "acquire returned".
- The new helper for checking if tracepoints are enabled in a header is used to
avoid un-inlining any of the lock wrappers. This yields ~zero overhead if the
tracepoints aren't enabled, and therefore obviates the need for a Kconfig for
this change.
[1] https://lore.kernel.org/patchwork/patch/1316922/
[2] https://lore.kernel.org/patchwork/patch/1311996/
Axel Rasmussen (2):
tracing: support "bool" type in synthetic trace events
mmap_lock: add tracepoints around lock acquisition
include/linux/mmap_lock.h | 93 +++++++++++++++++++++++++++++--
include/trace/events/mmap_lock.h | 70 +++++++++++++++++++++++
kernel/trace/trace_events_synth.c | 4 ++
mm/Makefile | 2 +-
mm/mmap_lock.c | 87 +++++++++++++++++++++++++++++
5 files changed, 250 insertions(+), 6 deletions(-)
create mode 100644 include/trace/events/mmap_lock.h
create mode 100644 mm/mmap_lock.c
--
2.28.0.1011.ga647a8990f-goog
The goal of these tracepoints is to be able to debug lock contention
issues. This lock is acquired on most (all?) mmap / munmap / page fault
operations, so a multi-threaded process which does a lot of these can
experience significant contention.
We trace just before we start acquisition, when the acquisition returns
(whether it succeeded or not), and when the lock is released (or
downgraded). The events are broken out by lock type (read / write).
The events are also broken out by memcg path. For container-based
workloads, users often think of several processes in a memcg as a single
logical "task", so collecting statistics at this level is useful.
The end goal is to get latency information. This isn't directly included
in the trace events. Instead, users are expected to compute the time
between "start locking" and "acquire returned", using e.g. synthetic
events or BPF. The benefit we get from this is simpler code.
Because we use tracepoint_enabled() to decide whether or not to trace,
this patch has effectively no overhead unless tracepoints are enabled at
runtime. If tracepoints are enabled, there is a performance impact, but
how much depends on exactly what e.g. the BPF program does.
Signed-off-by: Axel Rasmussen <[email protected]>
---
include/linux/mmap_lock.h | 93 ++++++++++++++++++++++++++++++--
include/trace/events/mmap_lock.h | 70 ++++++++++++++++++++++++
mm/Makefile | 2 +-
mm/mmap_lock.c | 87 ++++++++++++++++++++++++++++++
4 files changed, 246 insertions(+), 6 deletions(-)
create mode 100644 include/trace/events/mmap_lock.h
create mode 100644 mm/mmap_lock.c
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 0707671851a8..6586b42b4faa 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -1,11 +1,63 @@
#ifndef _LINUX_MMAP_LOCK_H
#define _LINUX_MMAP_LOCK_H
+#include <linux/lockdep.h>
+#include <linux/mm_types.h>
#include <linux/mmdebug.h>
+#include <linux/rwsem.h>
+#include <linux/tracepoint-defs.h>
+#include <linux/types.h>
#define MMAP_LOCK_INITIALIZER(name) \
.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),
+DECLARE_TRACEPOINT(mmap_lock_start_locking);
+DECLARE_TRACEPOINT(mmap_lock_acquire_returned);
+DECLARE_TRACEPOINT(mmap_lock_released);
+
+#ifdef CONFIG_TRACING
+
+void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write);
+void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
+ bool success);
+void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write);
+
+static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm,
+ bool write)
+{
+ if (tracepoint_enabled(mmap_lock_start_locking))
+ __mmap_lock_do_trace_start_locking(mm, write);
+}
+
+static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm,
+ bool write, bool success)
+{
+ if (tracepoint_enabled(mmap_lock_acquire_returned))
+ __mmap_lock_do_trace_acquire_returned(mm, write, success);
+}
+
+static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write)
+{
+ if (tracepoint_enabled(mmap_lock_released))
+ __mmap_lock_do_trace_released(mm, write);
+}
+
+#else /* !CONFIG_TRACING */
+
+static inline void __mmap_lock_trace_start_locking(struct mm_struct *mm,
+ bool write)
+{
+}
+static inline void __mmap_lock_trace_acquire_returned(struct mm_struct *mm,
+ bool write, bool success)
+{
+}
+static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write)
+{
+}
+
+#endif /* CONFIG_TRACING */
+
static inline void mmap_init_lock(struct mm_struct *mm)
{
init_rwsem(&mm->mmap_lock);
@@ -13,58 +65,88 @@ static inline void mmap_init_lock(struct mm_struct *mm)
static inline void mmap_write_lock(struct mm_struct *mm)
{
+ __mmap_lock_trace_start_locking(mm, true);
down_write(&mm->mmap_lock);
+ __mmap_lock_trace_acquire_returned(mm, true, true);
}
static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
{
+ __mmap_lock_trace_start_locking(mm, true);
down_write_nested(&mm->mmap_lock, subclass);
+ __mmap_lock_trace_acquire_returned(mm, true, true);
}
static inline int mmap_write_lock_killable(struct mm_struct *mm)
{
- return down_write_killable(&mm->mmap_lock);
+ int ret;
+
+ __mmap_lock_trace_start_locking(mm, true);
+ ret = down_write_killable(&mm->mmap_lock);
+ __mmap_lock_trace_acquire_returned(mm, true, ret == 0);
+ return ret;
}
static inline bool mmap_write_trylock(struct mm_struct *mm)
{
- return down_write_trylock(&mm->mmap_lock) != 0;
+ bool ret;
+
+ __mmap_lock_trace_start_locking(mm, true);
+ ret = down_write_trylock(&mm->mmap_lock) != 0;
+ __mmap_lock_trace_acquire_returned(mm, true, ret);
+ return ret;
}
static inline void mmap_write_unlock(struct mm_struct *mm)
{
up_write(&mm->mmap_lock);
+ __mmap_lock_trace_released(mm, true);
}
static inline void mmap_write_downgrade(struct mm_struct *mm)
{
downgrade_write(&mm->mmap_lock);
+ __mmap_lock_trace_acquire_returned(mm, false, true);
}
static inline void mmap_read_lock(struct mm_struct *mm)
{
+ __mmap_lock_trace_start_locking(mm, false);
down_read(&mm->mmap_lock);
+ __mmap_lock_trace_acquire_returned(mm, false, true);
}
static inline int mmap_read_lock_killable(struct mm_struct *mm)
{
- return down_read_killable(&mm->mmap_lock);
+ int ret;
+
+ __mmap_lock_trace_start_locking(mm, false);
+ ret = down_read_killable(&mm->mmap_lock);
+ __mmap_lock_trace_acquire_returned(mm, false, ret == 0);
+ return ret;
}
static inline bool mmap_read_trylock(struct mm_struct *mm)
{
- return down_read_trylock(&mm->mmap_lock) != 0;
+ bool ret;
+
+ __mmap_lock_trace_start_locking(mm, false);
+ ret = down_read_trylock(&mm->mmap_lock) != 0;
+ __mmap_lock_trace_acquire_returned(mm, false, ret);
+ return ret;
}
static inline void mmap_read_unlock(struct mm_struct *mm)
{
up_read(&mm->mmap_lock);
+ __mmap_lock_trace_released(mm, false);
}
static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
{
- if (down_read_trylock(&mm->mmap_lock)) {
+ if (mmap_read_trylock(mm)) {
rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
+ __mmap_lock_trace_released(mm, false);
return true;
}
return false;
@@ -73,6 +155,7 @@ static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
{
up_read_non_owner(&mm->mmap_lock);
+ __mmap_lock_trace_released(mm, false);
}
static inline void mmap_assert_locked(struct mm_struct *mm)
diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h
new file mode 100644
index 000000000000..ca652b52510e
--- /dev/null
+++ b/include/trace/events/mmap_lock.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mmap_lock
+
+#if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MMAP_LOCK_H
+
+#include <linux/tracepoint.h>
+#include <linux/types.h>
+
+struct mm_struct;
+
+DECLARE_EVENT_CLASS(
+ mmap_lock_template,
+
+ TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write,
+ bool success),
+
+ TP_ARGS(mm, memcg_path, write, success),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ __string(memcg_path, memcg_path)
+ __field(bool, write)
+ __field(bool, success)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ __assign_str(memcg_path, memcg_path);
+ __entry->write = write;
+ __entry->success = success;
+ ),
+
+ TP_printk(
+ "mm=%p memcg_path=%s write=%s success=%s\n",
+ __entry->mm,
+ __get_str(memcg_path),
+ __entry->write ? "true" : "false",
+ __entry->success ? "true" : "false")
+ );
+
+DEFINE_EVENT(mmap_lock_template, mmap_lock_start_locking,
+
+ TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write,
+ bool success),
+
+ TP_ARGS(mm, memcg_path, write, success)
+);
+
+DEFINE_EVENT(mmap_lock_template, mmap_lock_acquire_returned,
+
+ TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write,
+ bool success),
+
+ TP_ARGS(mm, memcg_path, write, success)
+);
+
+DEFINE_EVENT(mmap_lock_template, mmap_lock_released,
+
+ TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write,
+ bool success),
+
+ TP_ARGS(mm, memcg_path, write, success)
+);
+
+#endif /* _TRACE_MMAP_LOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/mm/Makefile b/mm/Makefile
index d5649f1c12c0..1a7ea212fd8b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -52,7 +52,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
mm_init.o percpu.o slab_common.o \
compaction.o vmacache.o \
interval_tree.o list_lru.o workingset.o \
- debug.o gup.o $(mmu-y)
+ debug.o gup.o mmap_lock.o $(mmu-y)
# Give 'page_alloc' its own module-parameter namespace
page-alloc-y := page_alloc.o
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
new file mode 100644
index 000000000000..b849287bd12a
--- /dev/null
+++ b/mm/mmap_lock.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+#define CREATE_TRACE_POINTS
+#include <trace/events/mmap_lock.h>
+
+#include <linux/mm.h>
+#include <linux/cgroup.h>
+#include <linux/memcontrol.h>
+#include <linux/mmap_lock.h>
+#include <linux/percpu.h>
+#include <linux/smp.h>
+#include <linux/trace_events.h>
+
+/*
+ * We have to export these, as drivers use mmap_lock, and our inline functions
+ * in the header check if the tracepoint is enabled. They can't be GPL, as e.g.
+ * the nvidia driver is an existing caller of this code.
+ */
+EXPORT_SYMBOL(__tracepoint_mmap_lock_start_locking);
+EXPORT_SYMBOL(__tracepoint_mmap_lock_acquire_returned);
+EXPORT_SYMBOL(__tracepoint_mmap_lock_released);
+
+#ifdef CONFIG_MEMCG
+
+DEFINE_PER_CPU(char[MAX_FILTER_STR_VAL], trace_memcg_path);
+
+/*
+ * Write the given mm_struct's memcg path to a percpu buffer, and return a
+ * pointer to it. If the path cannot be determined, the buffer will contain the
+ * empty string.
+ *
+ * Note: buffers are allocated per-cpu to avoid locking, so preemption must be
+ * disabled by the caller before calling us, and re-enabled only after the
+ * caller is done with the pointer.
+ */
+static const char *get_mm_memcg_path(struct mm_struct *mm)
+{
+ struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
+
+ if (memcg != NULL && likely(memcg->css.cgroup != NULL)) {
+ char *buf = this_cpu_ptr(trace_memcg_path);
+
+ cgroup_path(memcg->css.cgroup, buf, MAX_FILTER_STR_VAL);
+ return buf;
+ }
+ return "";
+}
+
+#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
+ do { \
+ if (trace_mmap_lock_##type##_enabled()) { \
+ get_cpu(); \
+ trace_mmap_lock_##type(mm, get_mm_memcg_path(mm), \
+ ##__VA_ARGS__); \
+ put_cpu(); \
+ } \
+ } while (0)
+
+#else /* !CONFIG_MEMCG */
+
+#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
+ trace_mmap_lock_##type(mm, "", ##__VA_ARGS__)
+
+#endif /* CONFIG_MEMCG */
+
+/*
+ * Trace calls must be in a separate file, as otherwise there's a circular
+ * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h.
+ */
+
+void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write)
+{
+ TRACE_MMAP_LOCK_EVENT(start_locking, mm, write, true);
+}
+EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking);
+
+void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
+ bool success)
+{
+ TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success);
+}
+EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned);
+
+void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write)
+{
+ TRACE_MMAP_LOCK_EVENT(released, mm, write, true);
+}
+EXPORT_SYMBOL(__mmap_lock_do_trace_released);
--
2.28.0.1011.ga647a8990f-goog
It's common [1] to define tracepoint fields as "bool" when they contain
a true / false value. Currently, defining a synthetic event with a
"bool" field yields EINVAL. It's possible to work around this by using
e.g. u8 (assuming sizeof(bool) is 1, and bool is unsigned; if either of
these properties don't match, you get EINVAL [2]).
Supporting "bool" explicitly makes hooking this up easier and more
portable for userspace.
[1]: grep -r "bool" include/trace/events/
[2]: check_synth_field() in kernel/trace/trace_events_hist.c
Acked-by: Michel Lespinasse <[email protected]>
Signed-off-by: Axel Rasmussen <[email protected]>
---
kernel/trace/trace_events_synth.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 8e1974fbad0e..8f94c84349a6 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -234,6 +234,8 @@ static int synth_field_size(char *type)
size = sizeof(long);
else if (strcmp(type, "unsigned long") == 0)
size = sizeof(unsigned long);
+ else if (strcmp(type, "bool") == 0)
+ size = sizeof(bool);
else if (strcmp(type, "pid_t") == 0)
size = sizeof(pid_t);
else if (strcmp(type, "gfp_t") == 0)
@@ -276,6 +278,8 @@ static const char *synth_field_fmt(char *type)
fmt = "%ld";
else if (strcmp(type, "unsigned long") == 0)
fmt = "%lu";
+ else if (strcmp(type, "bool") == 0)
+ fmt = "%d";
else if (strcmp(type, "pid_t") == 0)
fmt = "%d";
else if (strcmp(type, "gfp_t") == 0)
--
2.28.0.1011.ga647a8990f-goog
Tom,
Can you ack this patch for me?
-- Steve
On Fri, 9 Oct 2020 15:05:23 -0700
Axel Rasmussen <[email protected]> wrote:
> It's common [1] to define tracepoint fields as "bool" when they contain
> a true / false value. Currently, defining a synthetic event with a
> "bool" field yields EINVAL. It's possible to work around this by using
> e.g. u8 (assuming sizeof(bool) is 1, and bool is unsigned; if either of
> these properties don't match, you get EINVAL [2]).
>
> Supporting "bool" explicitly makes hooking this up easier and more
> portable for userspace.
>
> [1]: grep -r "bool" include/trace/events/
> [2]: check_synth_field() in kernel/trace/trace_events_hist.c
>
> Acked-by: Michel Lespinasse <[email protected]>
> Signed-off-by: Axel Rasmussen <[email protected]>
> ---
> kernel/trace/trace_events_synth.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
> index 8e1974fbad0e..8f94c84349a6 100644
> --- a/kernel/trace/trace_events_synth.c
> +++ b/kernel/trace/trace_events_synth.c
> @@ -234,6 +234,8 @@ static int synth_field_size(char *type)
> size = sizeof(long);
> else if (strcmp(type, "unsigned long") == 0)
> size = sizeof(unsigned long);
> + else if (strcmp(type, "bool") == 0)
> + size = sizeof(bool);
> else if (strcmp(type, "pid_t") == 0)
> size = sizeof(pid_t);
> else if (strcmp(type, "gfp_t") == 0)
> @@ -276,6 +278,8 @@ static const char *synth_field_fmt(char *type)
> fmt = "%ld";
> else if (strcmp(type, "unsigned long") == 0)
> fmt = "%lu";
> + else if (strcmp(type, "bool") == 0)
> + fmt = "%d";
> else if (strcmp(type, "pid_t") == 0)
> fmt = "%d";
> else if (strcmp(type, "gfp_t") == 0)
> --
> 2.28.0.1011.ga647a8990f-goog
On Mon, Oct 12, 2020 at 7:46 AM Steven Rostedt <[email protected]> wrote:
>
> On Mon, 12 Oct 2020 09:26:13 -0500
> Tom Zanussi <[email protected]> wrote:
>
> > Hi Steve,
> >
> > Looks ok to me.
> >
> > Acked-by: Tom Zanussi <[email protected]>
>
> Great!
>
> I'll pull this patch into my tree. It doesn't look like patch 2/2 is
> dependent on this and these two can go through different trees.
>
> Is everyone OK if I take this patch through my tree?
Sounds good to me. You're right that there is no compile-time
dependency between the two patches.
Thanks!
>
> -- Steve
Hi Steve,
Looks ok to me.
Acked-by: Tom Zanussi <[email protected]>
Thanks,
Tom
On Mon, 2020-10-12 at 10:15 -0400, Steven Rostedt wrote:
> Tom,
>
> Can you ack this patch for me?
>
> -- Steve
>
>
> On Fri, 9 Oct 2020 15:05:23 -0700
> Axel Rasmussen <[email protected]> wrote:
>
> > It's common [1] to define tracepoint fields as "bool" when they
> > contain
> > a true / false value. Currently, defining a synthetic event with a
> > "bool" field yields EINVAL. It's possible to work around this by
> > using
> > e.g. u8 (assuming sizeof(bool) is 1, and bool is unsigned; if
> > either of
> > these properties don't match, you get EINVAL [2]).
> >
> > Supporting "bool" explicitly makes hooking this up easier and more
> > portable for userspace.
> >
> > [1]: grep -r "bool" include/trace/events/
> > [2]: check_synth_field() in kernel/trace/trace_events_hist.c
> >
> > Acked-by: Michel Lespinasse <[email protected]>
> > Signed-off-by: Axel Rasmussen <[email protected]>
> > ---
> > kernel/trace/trace_events_synth.c | 4 ++++
> > 1 file changed, 4 insertions(+)
> >
> > diff --git a/kernel/trace/trace_events_synth.c
> > b/kernel/trace/trace_events_synth.c
> > index 8e1974fbad0e..8f94c84349a6 100644
> > --- a/kernel/trace/trace_events_synth.c
> > +++ b/kernel/trace/trace_events_synth.c
> > @@ -234,6 +234,8 @@ static int synth_field_size(char *type)
> > size = sizeof(long);
> > else if (strcmp(type, "unsigned long") == 0)
> > size = sizeof(unsigned long);
> > + else if (strcmp(type, "bool") == 0)
> > + size = sizeof(bool);
> > else if (strcmp(type, "pid_t") == 0)
> > size = sizeof(pid_t);
> > else if (strcmp(type, "gfp_t") == 0)
> > @@ -276,6 +278,8 @@ static const char *synth_field_fmt(char *type)
> > fmt = "%ld";
> > else if (strcmp(type, "unsigned long") == 0)
> > fmt = "%lu";
> > + else if (strcmp(type, "bool") == 0)
> > + fmt = "%d";
> > else if (strcmp(type, "pid_t") == 0)
> > fmt = "%d";
> > else if (strcmp(type, "gfp_t") == 0)
> > --
> > 2.28.0.1011.ga647a8990f-goog
>
>
On Mon, 12 Oct 2020 09:26:13 -0500
Tom Zanussi <[email protected]> wrote:
> Hi Steve,
>
> Looks ok to me.
>
> Acked-by: Tom Zanussi <[email protected]>
Great!
I'll pull this patch into my tree. It doesn't look like patch 2/2 is
dependent on this and these two can go through different trees.
Is everyone OK if I take this patch through my tree?
-- Steve
On Fri, 9 Oct 2020, Axel Rasmussen wrote:
> The goal of these tracepoints is to be able to debug lock contention
> issues. This lock is acquired on most (all?) mmap / munmap / page fault
> operations, so a multi-threaded process which does a lot of these can
> experience significant contention.
>
> We trace just before we start acquisition, when the acquisition returns
> (whether it succeeded or not), and when the lock is released (or
> downgraded). The events are broken out by lock type (read / write).
>
> The events are also broken out by memcg path. For container-based
> workloads, users often think of several processes in a memcg as a single
> logical "task", so collecting statistics at this level is useful.
>
> The end goal is to get latency information. This isn't directly included
> in the trace events. Instead, users are expected to compute the time
> between "start locking" and "acquire returned", using e.g. synthetic
> events or BPF. The benefit we get from this is simpler code.
>
> Because we use tracepoint_enabled() to decide whether or not to trace,
> this patch has effectively no overhead unless tracepoints are enabled at
> runtime. If tracepoints are enabled, there is a performance impact, but
> how much depends on exactly what e.g. the BPF program does.
>
> Signed-off-by: Axel Rasmussen <[email protected]>
Acked-by: David Rientjes <[email protected]>
On Fri, 9 Oct 2020, Axel Rasmussen wrote:
> It's common [1] to define tracepoint fields as "bool" when they contain
> a true / false value. Currently, defining a synthetic event with a
> "bool" field yields EINVAL. It's possible to work around this by using
> e.g. u8 (assuming sizeof(bool) is 1, and bool is unsigned; if either of
> these properties don't match, you get EINVAL [2]).
>
> Supporting "bool" explicitly makes hooking this up easier and more
> portable for userspace.
>
> [1]: grep -r "bool" include/trace/events/
> [2]: check_synth_field() in kernel/trace/trace_events_hist.c
>
> Acked-by: Michel Lespinasse <[email protected]>
> Signed-off-by: Axel Rasmussen <[email protected]>
Acked-by: David Rientjes <[email protected]>
On 10/10/20 12:05 AM, Axel Rasmussen wrote:
> The goal of these tracepoints is to be able to debug lock contention
> issues. This lock is acquired on most (all?) mmap / munmap / page fault
> operations, so a multi-threaded process which does a lot of these can
> experience significant contention.
>
> We trace just before we start acquisition, when the acquisition returns
> (whether it succeeded or not), and when the lock is released (or
> downgraded). The events are broken out by lock type (read / write).
>
> The events are also broken out by memcg path. For container-based
> workloads, users often think of several processes in a memcg as a single
> logical "task", so collecting statistics at this level is useful.
>
> The end goal is to get latency information. This isn't directly included
> in the trace events. Instead, users are expected to compute the time
> between "start locking" and "acquire returned", using e.g. synthetic
> events or BPF. The benefit we get from this is simpler code.
>
> Because we use tracepoint_enabled() to decide whether or not to trace,
> this patch has effectively no overhead unless tracepoints are enabled at
> runtime. If tracepoints are enabled, there is a performance impact, but
> how much depends on exactly what e.g. the BPF program does.
>
> Signed-off-by: Axel Rasmussen <[email protected]>
Yeah I agree with this approach that follows the page ref one.
...
> diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
> new file mode 100644
> index 000000000000..b849287bd12a
> --- /dev/null
> +++ b/mm/mmap_lock.c
> @@ -0,0 +1,87 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#define CREATE_TRACE_POINTS
> +#include <trace/events/mmap_lock.h>
> +
> +#include <linux/mm.h>
> +#include <linux/cgroup.h>
> +#include <linux/memcontrol.h>
> +#include <linux/mmap_lock.h>
> +#include <linux/percpu.h>
> +#include <linux/smp.h>
> +#include <linux/trace_events.h>
> +
> +/*
> + * We have to export these, as drivers use mmap_lock, and our inline functions
> + * in the header check if the tracepoint is enabled. They can't be GPL, as e.g.
> + * the nvidia driver is an existing caller of this code.
I don't think this argument works in the kernel community. I would just remove
this comment.
> + */
> +EXPORT_SYMBOL(__tracepoint_mmap_lock_start_locking);
> +EXPORT_SYMBOL(__tracepoint_mmap_lock_acquire_returned);
> +EXPORT_SYMBOL(__tracepoint_mmap_lock_released);
You can use EXPORT_TRACEPOINT_SYMBOL() here.
> +#ifdef CONFIG_MEMCG
> +
> +DEFINE_PER_CPU(char[MAX_FILTER_STR_VAL], trace_memcg_path);
> +
> +/*
> + * Write the given mm_struct's memcg path to a percpu buffer, and return a
> + * pointer to it. If the path cannot be determined, the buffer will contain the
> + * empty string.
> + *
> + * Note: buffers are allocated per-cpu to avoid locking, so preemption must be
> + * disabled by the caller before calling us, and re-enabled only after the
> + * caller is done with the pointer.
> + */
> +static const char *get_mm_memcg_path(struct mm_struct *mm)
> +{
> + struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
> +
> + if (memcg != NULL && likely(memcg->css.cgroup != NULL)) {
> + char *buf = this_cpu_ptr(trace_memcg_path);
> +
> + cgroup_path(memcg->css.cgroup, buf, MAX_FILTER_STR_VAL);
> + return buf;
> + }
> + return "";
> +}
> +
> +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
> + do { \
> + if (trace_mmap_lock_##type##_enabled()) { \
Is this check really needed? We only got called from the functions inlined in
the .h file because tracepoint_enabled() was true in the first place, so this
seems redundant.
> + get_cpu(); \
> + trace_mmap_lock_##type(mm, get_mm_memcg_path(mm), \
> + ##__VA_ARGS__); \
> + put_cpu(); \
> + } \
> + } while (0)
> +
> +#else /* !CONFIG_MEMCG */
> +
> +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
> + trace_mmap_lock_##type(mm, "", ##__VA_ARGS__)
> +
> +#endif /* CONFIG_MEMCG */
> +
> +/*
> + * Trace calls must be in a separate file, as otherwise there's a circular
> + * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h.
> + */
> +
> +void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write)
> +{
> + TRACE_MMAP_LOCK_EVENT(start_locking, mm, write, true);
Seems wasteful to have an always-true success field here. Yeah, not reusing the
same event class for all three tracepoints means more code, but for tracing
efficiency it's worth it, IMHO.
> +}
> +EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking);
> +
> +void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
> + bool success)
> +{
> + TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success);
> +}
> +EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned);
> +
> +void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write)
> +{
> + TRACE_MMAP_LOCK_EVENT(released, mm, write, true);
Ditto.
> +}
> +EXPORT_SYMBOL(__mmap_lock_do_trace_released);
>
On Tue, Oct 20, 2020 at 7:50 AM Vlastimil Babka <[email protected]> wrote:
>
> On 10/10/20 12:05 AM, Axel Rasmussen wrote:
> > The goal of these tracepoints is to be able to debug lock contention
> > issues. This lock is acquired on most (all?) mmap / munmap / page fault
> > operations, so a multi-threaded process which does a lot of these can
> > experience significant contention.
> >
> > We trace just before we start acquisition, when the acquisition returns
> > (whether it succeeded or not), and when the lock is released (or
> > downgraded). The events are broken out by lock type (read / write).
> >
> > The events are also broken out by memcg path. For container-based
> > workloads, users often think of several processes in a memcg as a single
> > logical "task", so collecting statistics at this level is useful.
> >
> > The end goal is to get latency information. This isn't directly included
> > in the trace events. Instead, users are expected to compute the time
> > between "start locking" and "acquire returned", using e.g. synthetic
> > events or BPF. The benefit we get from this is simpler code.
> >
> > Because we use tracepoint_enabled() to decide whether or not to trace,
> > this patch has effectively no overhead unless tracepoints are enabled at
> > runtime. If tracepoints are enabled, there is a performance impact, but
> > how much depends on exactly what e.g. the BPF program does.
> >
> > Signed-off-by: Axel Rasmussen <[email protected]>
>
> Yeah I agree with this approach that follows the page ref one.
>
> ...
>
> > diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
> > new file mode 100644
> > index 000000000000..b849287bd12a
> > --- /dev/null
> > +++ b/mm/mmap_lock.c
> > @@ -0,0 +1,87 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +#define CREATE_TRACE_POINTS
> > +#include <trace/events/mmap_lock.h>
> > +
> > +#include <linux/mm.h>
> > +#include <linux/cgroup.h>
> > +#include <linux/memcontrol.h>
> > +#include <linux/mmap_lock.h>
> > +#include <linux/percpu.h>
> > +#include <linux/smp.h>
> > +#include <linux/trace_events.h>
> > +
> > +/*
> > + * We have to export these, as drivers use mmap_lock, and our inline functions
> > + * in the header check if the tracepoint is enabled. They can't be GPL, as e.g.
> > + * the nvidia driver is an existing caller of this code.
>
> I don't think this argument works in the kernel community. I would just remove
> this comment.
>
> > + */
> > +EXPORT_SYMBOL(__tracepoint_mmap_lock_start_locking);
> > +EXPORT_SYMBOL(__tracepoint_mmap_lock_acquire_returned);
> > +EXPORT_SYMBOL(__tracepoint_mmap_lock_released);
>
> You can use EXPORT_TRACEPOINT_SYMBOL() here.
This is simpler, thanks for the pointer!
Agree the comment isn't needed in this case. I added it mainly since
checkpatch.pl doesn't like the EXPORT_SYMBOL-ing things not defined
just above, but EXPORT_TRACEPOINT_SYMBOL won't raise the same
concerns.
>
> > +#ifdef CONFIG_MEMCG
> > +
> > +DEFINE_PER_CPU(char[MAX_FILTER_STR_VAL], trace_memcg_path);
> > +
> > +/*
> > + * Write the given mm_struct's memcg path to a percpu buffer, and return a
> > + * pointer to it. If the path cannot be determined, the buffer will contain the
> > + * empty string.
> > + *
> > + * Note: buffers are allocated per-cpu to avoid locking, so preemption must be
> > + * disabled by the caller before calling us, and re-enabled only after the
> > + * caller is done with the pointer.
> > + */
> > +static const char *get_mm_memcg_path(struct mm_struct *mm)
> > +{
> > + struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
> > +
> > + if (memcg != NULL && likely(memcg->css.cgroup != NULL)) {
> > + char *buf = this_cpu_ptr(trace_memcg_path);
> > +
> > + cgroup_path(memcg->css.cgroup, buf, MAX_FILTER_STR_VAL);
> > + return buf;
> > + }
> > + return "";
> > +}
> > +
> > +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
> > + do { \
> > + if (trace_mmap_lock_##type##_enabled()) { \
>
> Is this check really needed? We only got called from the functions inlined in
> the .h file because tracepoint_enabled() was true in the first place, so this
> seems redundant.
Right, now that we've moved the check into the header, this isn't needed.
>
> > + get_cpu(); \
> > + trace_mmap_lock_##type(mm, get_mm_memcg_path(mm), \
> > + ##__VA_ARGS__); \
> > + put_cpu(); \
> > + } \
> > + } while (0)
> > +
> > +#else /* !CONFIG_MEMCG */
> > +
> > +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
> > + trace_mmap_lock_##type(mm, "", ##__VA_ARGS__)
> > +
> > +#endif /* CONFIG_MEMCG */
> > +
> > +/*
> > + * Trace calls must be in a separate file, as otherwise there's a circular
> > + * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h.
> > + */
> > +
> > +void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write)
> > +{
> > + TRACE_MMAP_LOCK_EVENT(start_locking, mm, write, true);
>
> Seems wasteful to have an always-true success field here. Yeah, not reusing the
> same event class for all three tracepoints means more code, but for tracing
> efficiency it's worth it, IMHO.
Right, originally I was worried about code size. But, I switched to
not re-using an event class, and I only measure an increase of 524
bytes in .text, which seems trivial.
I'll send a v4 with all of the above changes.
>
> > +}
> > +EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking);
> > +
> > +void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
> > + bool success)
> > +{
> > + TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success);
> > +}
> > +EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned);
> > +
> > +void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write)
> > +{
> > + TRACE_MMAP_LOCK_EVENT(released, mm, write, true);
>
> Ditto.
>
> > +}
> > +EXPORT_SYMBOL(__mmap_lock_do_trace_released);
> >
>