[06/14] perf annotate-data: Maintain variable type info

Message ID 20240202220459.527138-7-namhyung@kernel.org
State New
Headers
Series perf tools: Remaining bits of data type profiling (v5) |

Commit Message

Namhyung Kim Feb. 2, 2024, 10:04 p.m. UTC
  As it collected basic block and variable information in each scope, it
now can build a state table to find matching variable at the location.

The struct type_state is to keep the type info saved in each register
and stack slot.  The update_var_state() updates the table when it finds
variables in the current address.  It expects die_collect_vars() filled
a list of variables with type info and starting address.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/annotate-data.c | 155 ++++++++++++++++++++++++++++++++
 tools/perf/util/annotate-data.h |  29 ++++++
 tools/perf/util/dwarf-aux.c     |   4 +
 3 files changed, 188 insertions(+)
  

Comments

Ian Rogers Feb. 3, 2024, 2:44 a.m. UTC | #1
On Fri, Feb 2, 2024 at 2:05 PM Namhyung Kim <namhyung@kernel.org> wrote:
>
> As it collected basic block and variable information in each scope, it
> now can build a state table to find matching variable at the location.
>
> The struct type_state is to keep the type info saved in each register
> and stack slot.  The update_var_state() updates the table when it finds
> variables in the current address.  It expects die_collect_vars() filled
> a list of variables with type info and starting address.
>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/util/annotate-data.c | 155 ++++++++++++++++++++++++++++++++
>  tools/perf/util/annotate-data.h |  29 ++++++
>  tools/perf/util/dwarf-aux.c     |   4 +
>  3 files changed, 188 insertions(+)
>
> diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
> index b8e60c42af8c..f8768c224bcc 100644
> --- a/tools/perf/util/annotate-data.c
> +++ b/tools/perf/util/annotate-data.c
> @@ -23,6 +23,57 @@
>  #include "symbol.h"
>  #include "symbol_conf.h"
>
> +/* Type information in a register, valid when ok is true */
> +struct type_state_reg {
> +       Dwarf_Die type;
> +       bool ok;
> +       bool scratch;
> +};
> +
> +/* Type information in a stack location, dynamically allocated */
> +struct type_state_stack {
> +       struct list_head list;
> +       Dwarf_Die type;
> +       int offset;
> +       int size;
> +       bool compound;
> +};
> +
> +/* FIXME: This should be arch-dependent */
> +#define TYPE_STATE_MAX_REGS  16

Perhaps 32, presumably 16 won't work on Arm64.

Thanks,
Ian

> +
> +/*
> + * State table to maintain type info in each register and stack location.
> + * It'll be updated when new variable is allocated or type info is moved
> + * to a new location (register or stack).  As it'd be used with the
> + * shortest path of basic blocks, it only maintains a single table.
> + */
> +struct type_state {
> +       struct type_state_reg regs[TYPE_STATE_MAX_REGS];
> +       struct list_head stack_vars;
> +};
> +
> +static bool has_reg_type(struct type_state *state, int reg)
> +{
> +       return (unsigned)reg < ARRAY_SIZE(state->regs);
> +}
> +
> +void init_type_state(struct type_state *state, struct arch *arch __maybe_unused)
> +{
> +       memset(state, 0, sizeof(*state));
> +       INIT_LIST_HEAD(&state->stack_vars);
> +}
> +
> +void exit_type_state(struct type_state *state)
> +{
> +       struct type_state_stack *stack, *tmp;
> +
> +       list_for_each_entry_safe(stack, tmp, &state->stack_vars, list) {
> +               list_del(&stack->list);
> +               free(stack);
> +       }
> +}
> +
>  /*
>   * Compare type name and size to maintain them in a tree.
>   * I'm not sure if DWARF would have information of a single type in many
> @@ -238,6 +289,110 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
>         return 0;
>  }
>
> +static struct type_state_stack *find_stack_state(struct type_state *state,
> +                                                int offset)
> +{
> +       struct type_state_stack *stack;
> +
> +       list_for_each_entry(stack, &state->stack_vars, list) {
> +               if (offset == stack->offset)
> +                       return stack;
> +
> +               if (stack->compound && stack->offset < offset &&
> +                   offset < stack->offset + stack->size)
> +                       return stack;
> +       }
> +       return NULL;
> +}
> +
> +static void set_stack_state(struct type_state_stack *stack, int offset,
> +                           Dwarf_Die *type_die)
> +{
> +       int tag;
> +       Dwarf_Word size;
> +
> +       if (dwarf_aggregate_size(type_die, &size) < 0)
> +               size = 0;
> +
> +       tag = dwarf_tag(type_die);
> +
> +       stack->type = *type_die;
> +       stack->size = size;
> +       stack->offset = offset;
> +
> +       switch (tag) {
> +       case DW_TAG_structure_type:
> +       case DW_TAG_union_type:
> +               stack->compound = true;
> +               break;
> +       default:
> +               stack->compound = false;
> +               break;
> +       }
> +}
> +
> +static struct type_state_stack *findnew_stack_state(struct type_state *state,
> +                                                   int offset, Dwarf_Die *type_die)
> +{
> +       struct type_state_stack *stack = find_stack_state(state, offset);
> +
> +       if (stack) {
> +               set_stack_state(stack, offset, type_die);
> +               return stack;
> +       }
> +
> +       stack = malloc(sizeof(*stack));
> +       if (stack) {
> +               set_stack_state(stack, offset, type_die);
> +               list_add(&stack->list, &state->stack_vars);
> +       }
> +       return stack;
> +}
> +
> +/**
> + * update_var_state - Update type state using given variables
> + * @state: type state table
> + * @dloc: data location info
> + * @addr: instruction address to update
> + * @var_types: list of variables with type info
> + *
> + * This function fills the @state table using @var_types info.  Each variable
> + * is used only at the given location and updates an entry in the table.
> + */
> +void update_var_state(struct type_state *state, struct data_loc_info *dloc,
> +                     u64 addr, struct die_var_type *var_types)
> +{
> +       Dwarf_Die mem_die;
> +       struct die_var_type *var;
> +       int fbreg = dloc->fbreg;
> +       int fb_offset = 0;
> +
> +       if (dloc->fb_cfa) {
> +               if (die_get_cfa(dloc->di->dbg, addr, &fbreg, &fb_offset) < 0)
> +                       fbreg = -1;
> +       }
> +
> +       for (var = var_types; var != NULL; var = var->next) {
> +               if (var->addr != addr)
> +                       continue;
> +               /* Get the type DIE using the offset */
> +               if (!dwarf_offdie(dloc->di->dbg, var->die_off, &mem_die))
> +                       continue;
> +
> +               if (var->reg == DWARF_REG_FB) {
> +                       findnew_stack_state(state, var->offset, &mem_die);
> +               } else if (var->reg == fbreg) {
> +                       findnew_stack_state(state, var->offset - fb_offset, &mem_die);
> +               } else if (has_reg_type(state, var->reg)) {
> +                       struct type_state_reg *reg;
> +
> +                       reg = &state->regs[var->reg];
> +                       reg->type = mem_die;
> +                       reg->ok = true;
> +               }
> +       }
> +}
> +
>  /* The result will be saved in @type_die */
>  static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
>  {
> diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
> index ad6493ea2c8e..7fbb9eb2e96f 100644
> --- a/tools/perf/util/annotate-data.h
> +++ b/tools/perf/util/annotate-data.h
> @@ -8,9 +8,12 @@
>  #include <linux/types.h>
>
>  struct annotated_op_loc;
> +struct arch;
>  struct debuginfo;
> +struct die_var_type;
>  struct evsel;
>  struct map_symbol;
> +struct type_state;
>
>  /**
>   * struct annotated_member - Type of member field
> @@ -146,6 +149,16 @@ int annotated_data_type__update_samples(struct annotated_data_type *adt,
>  /* Release all data type information in the tree */
>  void annotated_data_type__tree_delete(struct rb_root *root);
>
> +/* Initialize type state table */
> +void init_type_state(struct type_state *state, struct arch *arch);
> +
> +/* Destroy type state table */
> +void exit_type_state(struct type_state *state);
> +
> +/* Update type state table using variables */
> +void update_var_state(struct type_state *state, struct data_loc_info *dloc,
> +                     u64 addr, struct die_var_type *var_types);
> +
>  #else /* HAVE_DWARF_SUPPORT */
>
>  static inline struct annotated_data_type *
> @@ -168,6 +181,22 @@ static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe
>  {
>  }
>
> +static inline void init_type_state(struct type_state *state __maybe_unused,
> +                                  struct arch *arch __maybe_unused)
> +{
> +}
> +
> +static inline void exit_type_state(struct type_state *state __maybe_unused)
> +{
> +}
> +
> +static inline void update_var_state(struct type_state *state __maybe_unused,
> +                                   struct data_loc_info *dloc __maybe_unused,
> +                                   u64 addr __maybe_unused,
> +                                   struct die_var_type *var_types __maybe_unused)
> +{
> +}
> +
>  #endif /* HAVE_DWARF_SUPPORT */
>
>  #endif /* _PERF_ANNOTATE_DATA_H */
> diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
> index 39851ff1d5c4..f88a8fb4a350 100644
> --- a/tools/perf/util/dwarf-aux.c
> +++ b/tools/perf/util/dwarf-aux.c
> @@ -9,6 +9,7 @@
>  #include <stdlib.h>
>  #include "debug.h"
>  #include "dwarf-aux.h"
> +#include "dwarf-regs.h"
>  #include "strbuf.h"
>  #include "string2.h"
>
> @@ -1147,6 +1148,8 @@ static int reg_from_dwarf_op(Dwarf_Op *op)
>         case DW_OP_regx:
>         case DW_OP_bregx:
>                 return op->number;
> +       case DW_OP_fbreg:
> +               return DWARF_REG_FB;
>         default:
>                 break;
>         }
> @@ -1160,6 +1163,7 @@ static int offset_from_dwarf_op(Dwarf_Op *op)
>         case DW_OP_regx:
>                 return 0;
>         case DW_OP_breg0 ... DW_OP_breg31:
> +       case DW_OP_fbreg:
>                 return op->number;
>         case DW_OP_bregx:
>                 return op->number2;
> --
> 2.43.0.594.gd9cf4e227d-goog
>
  
Namhyung Kim Feb. 6, 2024, 11:06 p.m. UTC | #2
On Fri, Feb 2, 2024 at 6:45 PM Ian Rogers <irogers@google.com> wrote:
>
> On Fri, Feb 2, 2024 at 2:05 PM Namhyung Kim <namhyung@kernel.org> wrote:
> >
> > As it collected basic block and variable information in each scope, it
> > now can build a state table to find matching variable at the location.
> >
> > The struct type_state is to keep the type info saved in each register
> > and stack slot.  The update_var_state() updates the table when it finds
> > variables in the current address.  It expects die_collect_vars() filled
> > a list of variables with type info and starting address.
> >
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> >  tools/perf/util/annotate-data.c | 155 ++++++++++++++++++++++++++++++++
> >  tools/perf/util/annotate-data.h |  29 ++++++
> >  tools/perf/util/dwarf-aux.c     |   4 +
> >  3 files changed, 188 insertions(+)
> >
> > diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
> > index b8e60c42af8c..f8768c224bcc 100644
> > --- a/tools/perf/util/annotate-data.c
> > +++ b/tools/perf/util/annotate-data.c
> > @@ -23,6 +23,57 @@
> >  #include "symbol.h"
> >  #include "symbol_conf.h"
> >
> > +/* Type information in a register, valid when ok is true */
> > +struct type_state_reg {
> > +       Dwarf_Die type;
> > +       bool ok;
> > +       bool scratch;
> > +};
> > +
> > +/* Type information in a stack location, dynamically allocated */
> > +struct type_state_stack {
> > +       struct list_head list;
> > +       Dwarf_Die type;
> > +       int offset;
> > +       int size;
> > +       bool compound;
> > +};
> > +
> > +/* FIXME: This should be arch-dependent */
> > +#define TYPE_STATE_MAX_REGS  16
>
> Perhaps 32, presumably 16 won't work on Arm64.

Right, but right now I'm targeting x86_64 only.
Maybe we can change it later when it supports Arm64.

Thanks,
Namhyung
  

Patch

diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index b8e60c42af8c..f8768c224bcc 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -23,6 +23,57 @@ 
 #include "symbol.h"
 #include "symbol_conf.h"
 
+/* Type information in a register, valid when ok is true */
+struct type_state_reg {
+	Dwarf_Die type;
+	bool ok;
+	bool scratch;
+};
+
+/* Type information in a stack location, dynamically allocated */
+struct type_state_stack {
+	struct list_head list;
+	Dwarf_Die type;
+	int offset;
+	int size;
+	bool compound;
+};
+
+/* FIXME: This should be arch-dependent */
+#define TYPE_STATE_MAX_REGS  16
+
+/*
+ * State table to maintain type info in each register and stack location.
+ * It'll be updated when new variable is allocated or type info is moved
+ * to a new location (register or stack).  As it'd be used with the
+ * shortest path of basic blocks, it only maintains a single table.
+ */
+struct type_state {
+	struct type_state_reg regs[TYPE_STATE_MAX_REGS];
+	struct list_head stack_vars;
+};
+
+static bool has_reg_type(struct type_state *state, int reg)
+{
+	return (unsigned)reg < ARRAY_SIZE(state->regs);
+}
+
+void init_type_state(struct type_state *state, struct arch *arch __maybe_unused)
+{
+	memset(state, 0, sizeof(*state));
+	INIT_LIST_HEAD(&state->stack_vars);
+}
+
+void exit_type_state(struct type_state *state)
+{
+	struct type_state_stack *stack, *tmp;
+
+	list_for_each_entry_safe(stack, tmp, &state->stack_vars, list) {
+		list_del(&stack->list);
+		free(stack);
+	}
+}
+
 /*
  * Compare type name and size to maintain them in a tree.
  * I'm not sure if DWARF would have information of a single type in many
@@ -238,6 +289,110 @@  static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 	return 0;
 }
 
+static struct type_state_stack *find_stack_state(struct type_state *state,
+						 int offset)
+{
+	struct type_state_stack *stack;
+
+	list_for_each_entry(stack, &state->stack_vars, list) {
+		if (offset == stack->offset)
+			return stack;
+
+		if (stack->compound && stack->offset < offset &&
+		    offset < stack->offset + stack->size)
+			return stack;
+	}
+	return NULL;
+}
+
+static void set_stack_state(struct type_state_stack *stack, int offset,
+			    Dwarf_Die *type_die)
+{
+	int tag;
+	Dwarf_Word size;
+
+	if (dwarf_aggregate_size(type_die, &size) < 0)
+		size = 0;
+
+	tag = dwarf_tag(type_die);
+
+	stack->type = *type_die;
+	stack->size = size;
+	stack->offset = offset;
+
+	switch (tag) {
+	case DW_TAG_structure_type:
+	case DW_TAG_union_type:
+		stack->compound = true;
+		break;
+	default:
+		stack->compound = false;
+		break;
+	}
+}
+
+static struct type_state_stack *findnew_stack_state(struct type_state *state,
+						    int offset, Dwarf_Die *type_die)
+{
+	struct type_state_stack *stack = find_stack_state(state, offset);
+
+	if (stack) {
+		set_stack_state(stack, offset, type_die);
+		return stack;
+	}
+
+	stack = malloc(sizeof(*stack));
+	if (stack) {
+		set_stack_state(stack, offset, type_die);
+		list_add(&stack->list, &state->stack_vars);
+	}
+	return stack;
+}
+
+/**
+ * update_var_state - Update type state using given variables
+ * @state: type state table
+ * @dloc: data location info
+ * @addr: instruction address to update
+ * @var_types: list of variables with type info
+ *
+ * This function fills the @state table using @var_types info.  Each variable
+ * is used only at the given location and updates an entry in the table.
+ */
+void update_var_state(struct type_state *state, struct data_loc_info *dloc,
+		      u64 addr, struct die_var_type *var_types)
+{
+	Dwarf_Die mem_die;
+	struct die_var_type *var;
+	int fbreg = dloc->fbreg;
+	int fb_offset = 0;
+
+	if (dloc->fb_cfa) {
+		if (die_get_cfa(dloc->di->dbg, addr, &fbreg, &fb_offset) < 0)
+			fbreg = -1;
+	}
+
+	for (var = var_types; var != NULL; var = var->next) {
+		if (var->addr != addr)
+			continue;
+		/* Get the type DIE using the offset */
+		if (!dwarf_offdie(dloc->di->dbg, var->die_off, &mem_die))
+			continue;
+
+		if (var->reg == DWARF_REG_FB) {
+			findnew_stack_state(state, var->offset, &mem_die);
+		} else if (var->reg == fbreg) {
+			findnew_stack_state(state, var->offset - fb_offset, &mem_die);
+		} else if (has_reg_type(state, var->reg)) {
+			struct type_state_reg *reg;
+
+			reg = &state->regs[var->reg];
+			reg->type = mem_die;
+			reg->ok = true;
+		}
+	}
+}
+
 /* The result will be saved in @type_die */
 static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
 {
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index ad6493ea2c8e..7fbb9eb2e96f 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -8,9 +8,12 @@ 
 #include <linux/types.h>
 
 struct annotated_op_loc;
+struct arch;
 struct debuginfo;
+struct die_var_type;
 struct evsel;
 struct map_symbol;
+struct type_state;
 
 /**
  * struct annotated_member - Type of member field
@@ -146,6 +149,16 @@  int annotated_data_type__update_samples(struct annotated_data_type *adt,
 /* Release all data type information in the tree */
 void annotated_data_type__tree_delete(struct rb_root *root);
 
+/* Initialize type state table */
+void init_type_state(struct type_state *state, struct arch *arch);
+
+/* Destroy type state table */
+void exit_type_state(struct type_state *state);
+
+/* Update type state table using variables */
+void update_var_state(struct type_state *state, struct data_loc_info *dloc,
+		      u64 addr, struct die_var_type *var_types);
+
 #else /* HAVE_DWARF_SUPPORT */
 
 static inline struct annotated_data_type *
@@ -168,6 +181,22 @@  static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe
 {
 }
 
+static inline void init_type_state(struct type_state *state __maybe_unused,
+				   struct arch *arch __maybe_unused)
+{
+}
+
+static inline void exit_type_state(struct type_state *state __maybe_unused)
+{
+}
+
+static inline void update_var_state(struct type_state *state __maybe_unused,
+				    struct data_loc_info *dloc __maybe_unused,
+				    u64 addr __maybe_unused,
+				    struct die_var_type *var_types __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_SUPPORT */
 
 #endif /* _PERF_ANNOTATE_DATA_H */
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 39851ff1d5c4..f88a8fb4a350 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -9,6 +9,7 @@ 
 #include <stdlib.h>
 #include "debug.h"
 #include "dwarf-aux.h"
+#include "dwarf-regs.h"
 #include "strbuf.h"
 #include "string2.h"
 
@@ -1147,6 +1148,8 @@  static int reg_from_dwarf_op(Dwarf_Op *op)
 	case DW_OP_regx:
 	case DW_OP_bregx:
 		return op->number;
+	case DW_OP_fbreg:
+		return DWARF_REG_FB;
 	default:
 		break;
 	}
@@ -1160,6 +1163,7 @@  static int offset_from_dwarf_op(Dwarf_Op *op)
 	case DW_OP_regx:
 		return 0;
 	case DW_OP_breg0 ... DW_OP_breg31:
+	case DW_OP_fbreg:
 		return op->number;
 	case DW_OP_bregx:
 		return op->number2;