lkml.org 
[lkml]   [2022]   [Jun]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: [PATCH v2 4/6] perf cpumap: Fix alignment for masks in event encoding
Hi Ian,

On Tue, Jun 14, 2022 at 7:34 AM Ian Rogers <irogers@google.com> wrote:
>
> A mask encoding of a cpu map is laid out as:
> u16 nr
> u16 long_size
> unsigned long mask[];
> However, the mask may be 8-byte aligned meaning there is a 4-byte pad
> after long_size. This means 32-bit and 64-bit builds see the mask as
> being at different offsets. On top of this the structure is in the byte
> data[] encoded as:
> u16 type
> char data[]
> This means the mask's struct isn't the required 4 or 8 byte aligned, but
> is offset by 2. Consequently the long reads and writes are causing
> undefined behavior as the alignment is broken.
>
> Fix the mask struct by creating explicit 32 and 64-bit variants, use a
> union to avoid data[] and casts; the struct must be packed so the
> layout matches the existing perf.data layout. Taking an address of a
> member of a packed struct breaks alignment so pass the packed
> perf_record_cpu_map_data to functions, so they can access variables with
> the right alignment.
>
> As the 64-bit version has 4 bytes of padding, optimizing writing to only
> write the 32-bit version.
>
> Signed-off-by: Ian Rogers <irogers@google.com>
> ---
> tools/lib/perf/include/perf/event.h | 36 +++++++++++--
> tools/perf/tests/cpumap.c | 19 ++++---
> tools/perf/util/cpumap.c | 80 +++++++++++++++++++++++------
> tools/perf/util/cpumap.h | 4 +-
> tools/perf/util/session.c | 30 +++++------
> tools/perf/util/synthetic-events.c | 34 +++++++-----
> 6 files changed, 143 insertions(+), 60 deletions(-)
>
> diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h
> index e7758707cadd..d2d32589758a 100644
> --- a/tools/lib/perf/include/perf/event.h
> +++ b/tools/lib/perf/include/perf/event.h
> @@ -6,6 +6,7 @@
> #include <linux/types.h>
> #include <linux/limits.h>
> #include <linux/bpf.h>
> +#include <linux/compiler.h>
> #include <sys/types.h> /* pid_t */
>
> #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem))
> @@ -153,20 +154,47 @@ enum {
> PERF_CPU_MAP__MASK = 1,
> };
>
> +/*
> + * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[]
> + * and each entry is a value for a CPU in the map.
> + */
> struct cpu_map_entries {
> __u16 nr;
> __u16 cpu[];
> };
>
> -struct perf_record_record_cpu_map {
> +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */
> +struct perf_record_mask_cpu_map32 {
> + /* Number of mask values. */
> __u16 nr;
> + /* Constant 4. */
> __u16 long_size;
> - unsigned long mask[];
> + /* Bitmap data. */
> + __u32 mask[];
> };
>
> -struct perf_record_cpu_map_data {
> +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */
> +struct perf_record_mask_cpu_map64 {
> + /* Number of mask values. */
> + __u16 nr;
> + /* Constant 8. */
> + __u16 long_size;
> + /* Legacy padding. */
> + char __pad[4];
> + /* Bitmap data. */
> + __u64 mask[];
> +};
> +
> +struct __packed perf_record_cpu_map_data {
> __u16 type;
> - char data[];
> + union {
> + /* Used when type == PERF_CPU_MAP__CPUS. */
> + struct cpu_map_entries cpus_data;
> + /* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */
> + struct perf_record_mask_cpu_map32 mask32_data;
> + /* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */
> + struct perf_record_mask_cpu_map64 mask64_data;
> + };
> };

How about moving the 'type' to the union as well?
This way we don't need to pack the entire struct
and can have a common struct for 32 and 64 bit..

struct cpu_map_entries {
__u16 type;
__u16 nr;
__u16 cpu[];
};

struct perf_record_mask_cpu_map {
__u16 type;
__u16 nr;
__u16 long_size; // still needed?
__u16 pad;
unsigned long mask[];
};

// changed it to union
union perf_record_cpu_map_data {
__u16 type;
struct cpu_map_entries cpus_data;
struct perf_record_mask_cpu_map mask_data;
};

Thanks,
Namhyung

\
 
 \ /
  Last update: 2022-06-15 00:46    [W:0.203 / U:0.812 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site