From: "Steven Rostedt (Google)" <[email protected]>
The saved_cmdlines have three arrays for mapping PIDs to COMMs:
- map_pid_to_cmdline[]
- map_cmdline_to_pid[]
- saved_cmdlines
The map_pid_to_cmdline[] is PID_MAX_DEFAULT in size and holds the index
into the other arrays. The map_cmdline_to_pid[] is a mapping back to the
full pid as it can be larger than PID_MAX_DEFAULT. And the
saved_cmdlines[] just holds the COMMs associated to the pids.
Currently the map_pid_to_cmdline[] and saved_cmdlines[] are allocated
together (in reality the saved_cmdlines is just in the memory of the
rounding of the allocation of the structure as it is always allocated in
powers of two). The map_cmdline_to_pid[] array is allocated separately.
Since the rounding to a power of two is rather large (it allows for 8000
elements in saved_cmdlines), also include the map_cmdline_to_pid[] array.
(This drops it to 6000 by default, which is still plenty for most use
cases). This saves even more memory as the map_cmdline_to_pid[] array
doesn't need to be allocated.
Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/
Signed-off-by: Steven Rostedt (Google) <[email protected]>
---
kernel/trace/trace_sched_switch.c | 13 ++++---------
1 file changed, 4 insertions(+), 9 deletions(-)
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e4fbcc3bede5..210c74dcd016 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -201,7 +201,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
int order;
/* Figure out how much is needed to hold the given number of cmdlines */
- orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+ orig_size = sizeof(*s) + val * (TASK_COMM_LEN + sizeof(int));
order = get_order(orig_size);
size = 1 << (order + PAGE_SHIFT);
page = alloc_pages(GFP_KERNEL, order);
@@ -212,16 +212,11 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
memset(s, 0, sizeof(*s));
/* Round up to actual allocation */
- val = (size - sizeof(*s)) / TASK_COMM_LEN;
+ val = (size - sizeof(*s)) / (TASK_COMM_LEN + sizeof(int));
s->cmdline_num = val;
- s->map_cmdline_to_pid = kmalloc_array(val,
- sizeof(*s->map_cmdline_to_pid),
- GFP_KERNEL);
- if (!s->map_cmdline_to_pid) {
- free_saved_cmdlines_buffer(s);
- return NULL;
- }
+ /* Place map_cmdline_to_pid array right after saved_cmdlines */
+ s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN];
s->cmdline_idx = 0;
memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
--
2.43.0
On Mon, 12 Feb 2024 18:09:41 -0500
Steven Rostedt <[email protected]> wrote:
> From: "Steven Rostedt (Google)" <[email protected]>
>
> The saved_cmdlines have three arrays for mapping PIDs to COMMs:
>
> - map_pid_to_cmdline[]
> - map_cmdline_to_pid[]
> - saved_cmdlines
>
> The map_pid_to_cmdline[] is PID_MAX_DEFAULT in size and holds the index
> into the other arrays. The map_cmdline_to_pid[] is a mapping back to the
> full pid as it can be larger than PID_MAX_DEFAULT. And the
> saved_cmdlines[] just holds the COMMs associated to the pids.
>
> Currently the map_pid_to_cmdline[] and saved_cmdlines[] are allocated
> together (in reality the saved_cmdlines is just in the memory of the
> rounding of the allocation of the structure as it is always allocated in
> powers of two). The map_cmdline_to_pid[] array is allocated separately.
>
> Since the rounding to a power of two is rather large (it allows for 8000
> elements in saved_cmdlines), also include the map_cmdline_to_pid[] array.
> (This drops it to 6000 by default, which is still plenty for most use
> cases). This saves even more memory as the map_cmdline_to_pid[] array
> doesn't need to be allocated.
>
> Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/
>
Looks good to me.
Acked-by: Masami Hiramatsu (Google) <[email protected]>
Thank you,
> Signed-off-by: Steven Rostedt (Google) <[email protected]>
> ---
> kernel/trace/trace_sched_switch.c | 13 ++++---------
> 1 file changed, 4 insertions(+), 9 deletions(-)
>
> diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
> index e4fbcc3bede5..210c74dcd016 100644
> --- a/kernel/trace/trace_sched_switch.c
> +++ b/kernel/trace/trace_sched_switch.c
> @@ -201,7 +201,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> int order;
>
> /* Figure out how much is needed to hold the given number of cmdlines */
> - orig_size = sizeof(*s) + val * TASK_COMM_LEN;
> + orig_size = sizeof(*s) + val * (TASK_COMM_LEN + sizeof(int));
> order = get_order(orig_size);
> size = 1 << (order + PAGE_SHIFT);
> page = alloc_pages(GFP_KERNEL, order);
> @@ -212,16 +212,11 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> memset(s, 0, sizeof(*s));
>
> /* Round up to actual allocation */
> - val = (size - sizeof(*s)) / TASK_COMM_LEN;
> + val = (size - sizeof(*s)) / (TASK_COMM_LEN + sizeof(int));
> s->cmdline_num = val;
>
> - s->map_cmdline_to_pid = kmalloc_array(val,
> - sizeof(*s->map_cmdline_to_pid),
> - GFP_KERNEL);
> - if (!s->map_cmdline_to_pid) {
> - free_saved_cmdlines_buffer(s);
> - return NULL;
> - }
> + /* Place map_cmdline_to_pid array right after saved_cmdlines */
> + s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN];
>
> s->cmdline_idx = 0;
> memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
> --
> 2.43.0
>
--
Masami Hiramatsu (Google) <[email protected]>
On Mon, 2024-02-12 at 18:09 -0500, Steven Rostedt wrote:
> From: "Steven Rostedt (Google)" <[email protected]>
>
> The saved_cmdlines have three arrays for mapping PIDs to COMMs:
>
> - map_pid_to_cmdline[]
> - map_cmdline_to_pid[]
> - saved_cmdlines
>
> The map_pid_to_cmdline[] is PID_MAX_DEFAULT in size and holds the index
> into the other arrays. The map_cmdline_to_pid[] is a mapping back to the
> full pid as it can be larger than PID_MAX_DEFAULT. And the
> saved_cmdlines[] just holds the COMMs associated to the pids.
>
> Currently the map_pid_to_cmdline[] and saved_cmdlines[] are allocated
> together (in reality the saved_cmdlines is just in the memory of the
> rounding of the allocation of the structure as it is always allocated in
> powers of two). The map_cmdline_to_pid[] array is allocated separately.
>
> Since the rounding to a power of two is rather large (it allows for 8000
> elements in saved_cmdlines), also include the map_cmdline_to_pid[] array.
> (This drops it to 6000 by default, which is still plenty for most use
> cases). This saves even more memory as the map_cmdline_to_pid[] array
> doesn't need to be allocated.
This patch does make better use of the extra space and make the
previous change better.
Reviewed-by: Tim Chen <[email protected]>
>
> Link: https://lore.kernel.org/linux-trace-kernel/[email protected]/
>
> Signed-off-by: Steven Rostedt (Google) <[email protected]>
> ---
> kernel/trace/trace_sched_switch.c | 13 ++++---------
> 1 file changed, 4 insertions(+), 9 deletions(-)
>
> diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
> index e4fbcc3bede5..210c74dcd016 100644
> --- a/kernel/trace/trace_sched_switch.c
> +++ b/kernel/trace/trace_sched_switch.c
> @@ -201,7 +201,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> int order;
>
> /* Figure out how much is needed to hold the given number of cmdlines */
> - orig_size = sizeof(*s) + val * TASK_COMM_LEN;
> + orig_size = sizeof(*s) + val * (TASK_COMM_LEN + sizeof(int));
Strictly speaking, *map_cmdline_to_pid is unsigned int so it is more consistent
to use sizeof(unsigned) in line above. But I'm nitpicking and I'm fine to
leave it as is.
> order = get_order(orig_size);
> size = 1 << (order + PAGE_SHIFT);
> page = alloc_pages(GFP_KERNEL, order);
> @@ -212,16 +212,11 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> memset(s, 0, sizeof(*s));
>
> /* Round up to actual allocation */
> - val = (size - sizeof(*s)) / TASK_COMM_LEN;
> + val = (size - sizeof(*s)) / (TASK_COMM_LEN + sizeof(int));
> s->cmdline_num = val;
>
> - s->map_cmdline_to_pid = kmalloc_array(val,
> - sizeof(*s->map_cmdline_to_pid),
> - GFP_KERNEL);
> - if (!s->map_cmdline_to_pid) {
> - free_saved_cmdlines_buffer(s);
> - return NULL;
> - }
> + /* Place map_cmdline_to_pid array right after saved_cmdlines */
> + s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN];
>
> s->cmdline_idx = 0;
> memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
On Mon, 12 Feb 2024 15:39:03 -0800
Tim Chen <[email protected]> wrote:
> > diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
> > index e4fbcc3bede5..210c74dcd016 100644
> > --- a/kernel/trace/trace_sched_switch.c
> > +++ b/kernel/trace/trace_sched_switch.c
> > @@ -201,7 +201,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> > int order;
> >
> > /* Figure out how much is needed to hold the given number of cmdlines */
> > - orig_size = sizeof(*s) + val * TASK_COMM_LEN;
> > + orig_size = sizeof(*s) + val * (TASK_COMM_LEN + sizeof(int));
>
> Strictly speaking, *map_cmdline_to_pid is unsigned int so it is more consistent
> to use sizeof(unsigned) in line above. But I'm nitpicking and I'm fine to
> leave it as is.
I was thinking about making that into a macro as it is used in two places.
/* Holds the size of a cmdline and pid element */
#define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s) \
(TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0]))
orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
>
> > order = get_order(orig_size);
> > size = 1 << (order + PAGE_SHIFT);
> > page = alloc_pages(GFP_KERNEL, order);
> > @@ -212,16 +212,11 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> > memset(s, 0, sizeof(*s));
> >
> > /* Round up to actual allocation */
> > - val = (size - sizeof(*s)) / TASK_COMM_LEN;
> > + val = (size - sizeof(*s)) / (TASK_COMM_LEN + sizeof(int));
val = (size - sizeof(*s)) / SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
-- Steve
> > s->cmdline_num = val;
> >
> > - s->map_cmdline_to_pid = kmalloc_array(val,
> > - sizeof(*s->map_cmdline_to_pid),
> > - GFP_KERNEL);
> > - if (!s->map_cmdline_to_pid) {
> > - free_saved_cmdlines_buffer(s);
> > - return NULL;
> > - }
> > + /* Place map_cmdline_to_pid array right after saved_cmdlines */
> > + s->map_cmdline_to_pid = (unsigned *)&s->saved_cmdlines[val * TASK_COMM_LEN];
> >
> > s->cmdline_idx = 0;
> > memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
On Mon, 2024-02-12 at 19:13 -0500, Steven Rostedt wrote:
> On Mon, 12 Feb 2024 15:39:03 -0800
> Tim Chen <[email protected]> wrote:
>
> > > diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
> > > index e4fbcc3bede5..210c74dcd016 100644
> > > --- a/kernel/trace/trace_sched_switch.c
> > > +++ b/kernel/trace/trace_sched_switch.c
> > > @@ -201,7 +201,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
> > > int order;
> > >
> > > /* Figure out how much is needed to hold the given number of cmdlines */
> > > - orig_size = sizeof(*s) + val * TASK_COMM_LEN;
> > > + orig_size = sizeof(*s) + val * (TASK_COMM_LEN + sizeof(int));
> >
> > Strictly speaking, *map_cmdline_to_pid is unsigned int so it is more consistent
> > to use sizeof(unsigned) in line above. But I'm nitpicking and I'm fine to
> > leave it as is.
>
> I was thinking about making that into a macro as it is used in two places.
>
> /* Holds the size of a cmdline and pid element */
> #define SAVED_CMDLINE_MAP_ELEMENT_SIZE(s) \
> (TASK_COMM_LEN + sizeof((s)->map_cmdline_to_pid[0]))
>
> orig_size = sizeof(*s) + val * SAVED_CMDLINE_MAP_ELEMENT_SIZE(s);
>
>
Looks good. This makes the code more readable.
Tim