Re: [PATCH 02/17] perf: Add ability to attach user level registersdump to sample

[Stephane Eranian]

On Sun, Jul 22, 2012 at 2:14 PM, Jiri Olsa <jolsa@xxxxxxxxxx> wrote:
> Introducing PERF_SAMPLE_REGS_USER sample type bit to trigger
> the dump of user level registers on sample. Registers we want
> to dump are specified by sample_regs_user bitmask.
>
> Only user level registers are dumped at the moment. Meaning the
> register values of the user space context as it was before the
> user entered the kernel for whatever reason (syscall, irq,
> exception, or a PMI happening in userspace).
>
> The layout of the sample_regs_user bitmap is described in
> asm/perf_regs.h for archs that support register dump.
>
> This is going to be useful to bring Dwarf CFI based stack
> unwinding on top of samples.
>
> Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> Original-patch-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
> ---
>  include/linux/perf_event.h |   20 ++++++++++++--
>  kernel/events/core.c       |   61 ++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 78 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 76c5c8b..57f209d 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -130,8 +130,9 @@ enum perf_event_sample_format {
>         PERF_SAMPLE_STREAM_ID                   = 1U << 9,
>         PERF_SAMPLE_RAW                         = 1U << 10,
>         PERF_SAMPLE_BRANCH_STACK                = 1U << 11,
> +       PERF_SAMPLE_REGS_USER                   = 1U << 12,
>
> -       PERF_SAMPLE_MAX = 1U << 12,             /* non-ABI */
> +       PERF_SAMPLE_MAX = 1U << 13,             /* non-ABI */
>  };
>
>  /*
> @@ -194,6 +195,7 @@ enum perf_event_read_format {
>  #define PERF_ATTR_SIZE_VER0    64      /* sizeof first published struct */
>  #define PERF_ATTR_SIZE_VER1    72      /* add: config2 */
>  #define PERF_ATTR_SIZE_VER2    80      /* add: branch_sample_type */
> +#define PERF_ATTR_SIZE_VER3    88      /* add: sample_regs_user */
>
>  /*
>   * Hardware event_id to monitor via a performance monitoring event:
> @@ -271,7 +273,13 @@ struct perf_event_attr {
>                 __u64           bp_len;
>                 __u64           config2; /* extension of config1 */
>         };
> -       __u64   branch_sample_type; /* enum branch_sample_type */
> +       __u64   branch_sample_type; /* enum perf_branch_sample_type */
> +
> +       /*
> +        * Defines set of user regs to dump on samples.
> +        * See asm/perf_regs.h for details.
> +        */
> +       __u64   sample_regs_user;
>  };
>
>  /*
> @@ -548,6 +556,9 @@ enum perf_event_type {
>          *        char                  data[size];}&& PERF_SAMPLE_RAW
>          *
>          *      { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
> +        *
> +        *      { u64                   available;
> +        *        u64                   regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
>          * };
>          */
>         PERF_RECORD_SAMPLE                      = 9,
> @@ -609,6 +620,7 @@ struct perf_guest_info_callbacks {
>  #include <linux/static_key.h>
>  #include <linux/atomic.h>
>  #include <linux/sysfs.h>
> +#include <linux/perf_regs.h>
>  #include <asm/local.h>
>
>  struct perf_callchain_entry {
> @@ -1133,6 +1145,7 @@ struct perf_sample_data {
>         struct perf_callchain_entry     *callchain;
>         struct perf_raw_record          *raw;
>         struct perf_branch_stack        *br_stack;
> +       struct pt_regs                  *regs_user;
>  };
>
>  static inline void perf_sample_data_init(struct perf_sample_data *data,
> @@ -1142,7 +1155,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
>         data->addr = addr;
>         data->raw  = NULL;
>         data->br_stack = NULL;
> -       data->period    = period;
> +       data->period = period;
> +       data->regs_user = NULL;
>  }
>
>  extern void perf_output_sample(struct perf_output_handle *handle,
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index f1cf0ed..e817e32 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -3756,6 +3756,33 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs)
>  }
>  EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
>
> +static void
> +perf_output_sample_regs(struct perf_output_handle *handle,
> +                       struct pt_regs *regs, u64 mask)
> +{
> +       int bit;
> +
> +       for_each_set_bit(bit, (const unsigned long *) &mask,
> +                        sizeof(mask) * BITS_PER_BYTE) {
> +               u64 val;
> +
> +               val = perf_reg_value(regs, bit);
> +               perf_output_put(handle, val);
> +       }
> +}
> +
> +static struct pt_regs *perf_sample_regs_user(struct pt_regs *regs)
> +{
> +       if (!user_mode(regs)) {
> +               if (current->mm)
> +                       regs = task_pt_regs(current);
> +               else
> +                       regs = NULL;
> +       }
> +
> +       return regs;
> +}
> +
>  static void __perf_event_header__init_id(struct perf_event_header *header,
>                                          struct perf_sample_data *data,
>                                          struct perf_event *event)
> @@ -4016,6 +4043,23 @@ void perf_output_sample(struct perf_output_handle *handle,
>                         perf_output_put(handle, nr);
>                 }
>         }
> +
> +       if (sample_type & PERF_SAMPLE_REGS_USER) {
> +               u64 avail = (data->regs_user != NULL);
> +
> +               /*
> +                * If there are no regs to dump, notice it through
> +                * first u64 being zero.
> +                */
> +               perf_output_put(handle, avail);
> +
The only role of avail is to report whether or not you've captured actual
registers. Could it be used to report the sampled process ABI (32 vs. 64)
instead? Something like:
      PERF_SAMPLE_REGS_ABI_NONE -> no regs captured (emulate your
current behavior)
      PERF_SAMPLE_REGS_ABI_32 -> 32 bit ABI regs captured
      PERF_SAMPLE_REGS_ABI_64 -> 64 bit ABI regs captured

That could help the tools interpret the register values.

Other than that the patch looks good to me.

Once it's in, I will piggyback on it to add and post a patch to add
interrupted, pebs machine state sampling.

> +               if (avail) {
> +                       u64 mask = event->attr.sample_regs_user;
> +                       perf_output_sample_regs(handle,
> +                                               data->regs_user,
> +                                               mask);
> +               }
> +       }
>  }
>
>  void perf_prepare_sample(struct perf_event_header *header,
> @@ -4067,6 +4111,19 @@ void perf_prepare_sample(struct perf_event_header *header,
>                 }
>                 header->size += size;
>         }
> +
> +       if (sample_type & PERF_SAMPLE_REGS_USER) {
> +               /* regs dump available bool */
> +               int size = sizeof(u64);
> +
> +               data->regs_user = perf_sample_regs_user(regs);
> +               if (data->regs_user) {
> +                       u64 mask = event->attr.sample_regs_user;
> +                       size += hweight64(mask) * sizeof(u64);
> +               }
> +
> +               header->size += size;
> +       }
>  }
>
>  static void perf_event_output(struct perf_event *event,
> @@ -6116,6 +6173,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
>                         attr->branch_sample_type = mask;
>                 }
>         }
> +
> +       if (attr->sample_type & PERF_SAMPLE_REGS_USER)
> +               ret = perf_reg_validate(attr->sample_regs_user);
> +
>  out:
>         return ret;
>
> --
> 1.7.7.6
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/