kallsyms: new /proc/kallmodsyms with builtin modules and symbol sizes

/proc/kallsyms is very useful for tracers and other tools that need to
map kernel symbols to addresses.

It would be useful if:

- there were a mapping between kernel symbol and module name
  that only changed when the kernel source code is changed.
  This mapping should not change simply because a module
  becomes built into the kernel.

- there were symbol size information to determine whether an
  address is within a symbol or outside it, especially given
  that there could be huge gaps between symbols.

Therefore:

- Introduce a new config parameter CONFIG_KALLMODSYMS.

- Generate a file "modules_thick.builtin" that maps from
  the thin archives that make up built-in modules to their
  constituent object files.

- Generate a linker map ".tmp_vmlinux.map", converting it
  into ".tmp_vmlinux.ranges", mapping address ranges to
  object files.

- Change scripts/kallsyms.c stdin from "nm" to "nm -S" so that
  symbol sizes are available.  Have sort_symbols() incorporate
  size info.  Emit size info in the *.s output file.  Skip the
  .init.scratch section.

- If CONFIG_KALLMODSYMS, have scripts/kallsyms also read
  "modules_thick.builtin" and ".tmp_vmlinux.ranges" to map
  symbol addresses to built-in-module names and then write
  those module names and per-symbol module information to
  the *.s output file.

- Change module_get_kallsym() to return symbol size as well.

- In kernel/kallsyms:
  - Use new, accurate symbol size information in get_symbol_pos(),
    both to identify the correct symbol and to return correct size
    information.
  - Introduce a field builtin_module to say if the symbol is in a
    built-in module.
  - If CONFIG_KALLMODSYMS, produce a new /proc/kallmodsyms file,
    akin to /proc/kallsyms but with built-in-module names and symbol
    sizes.

The resulting /proc/kallmodsyms file looks like this:
    ffffffff8b013d20 409 t pt_buffer_setup_aux
    ffffffff8b014130 11f T intel_pt_interrupt
    ffffffff8b014250 2d T cpu_emergency_stop_pt
    ffffffff8b014280 13a t rapl_pmu_event_init      [intel_rapl_perf]
    ffffffff8b0143c0 bb t rapl_event_update [intel_rapl_perf]
    ffffffff8b014480 10 t rapl_pmu_event_read       [intel_rapl_perf]
    ffffffff8b014490 a3 t rapl_cpu_offline  [intel_rapl_perf]
    ffffffff8b014540 24 t __rapl_event_show [intel_rapl_perf]
    ffffffff8b014570 f2 t rapl_pmu_event_stop       [intel_rapl_perf]
This is emitted even if intel_rapl_perf is built into the kernel.

As with /proc/kallsyms, non-root usage produces addresses that are
all zero;  symbol sizes are treated similarly.

Programs that consume /proc/kallmodsyms should note that unlike
/proc/kallsyms, kernel symbols for built-in modules may appear
interspersed with other symbols that are part of different modules or
of the kernel.

Orabug: 30544408
Signed-off-by: Kris Van Hees <[email protected]>
Signed-off-by: Nick Alcock <[email protected]>
Signed-off-by: Eugene Loh <[email protected]>
Reviewed-by: Nick Alcock <[email protected]>
Reviewed-by: Kris Van Hees <[email protected]>

Author: kvanhees

.gitignore

@@ -47,6 +47,7 @@
 Module.symvers
 modules.builtin
 modules.order
+modules_thick.builtin
 
 #
 # Top-level generic files

Documentation/dontdiff

@@ -180,6 +180,7 @@ modpost
 modules.builtin
 modules.builtin.modinfo
 modules.order
+modules_thick.builtin
 modversions.h*
 nconf
 nconf-cfg

Makefile

@@ -1080,7 +1080,7 @@ cmd_link-vmlinux =                                                 \
 	$(CONFIG_SHELL) $< $(LD) $(KBUILD_LDFLAGS) $(LDFLAGS_vmlinux) ;    \
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
-vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) FORCE
+vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) modules_thick.builtin FORCE
 	+$(call if_changed,link-vmlinux)
 
 targets := vmlinux
@@ -1295,17 +1295,6 @@ modules: $(if $(KBUILD_BUILTIN),vmlinux) modules.order modules.builtin
 modules.order: descend
 	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
 
-modbuiltin-dirs := $(addprefix _modbuiltin_, $(build-dirs))
-
-modules.builtin: $(modbuiltin-dirs)
-	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
-
-PHONY += $(modbuiltin-dirs)
-# tristate.conf is not included from this Makefile. Add it as a prerequisite
-# here to make it self-healing in case somebody accidentally removes it.
-$(modbuiltin-dirs): include/config/tristate.conf
-	$(Q)$(MAKE) $(modbuiltin)=$(patsubst _modbuiltin_%,%,$@)
-
 # Target to prepare building external modules
 PHONY += modules_prepare
 modules_prepare: prepare
@@ -1358,6 +1347,33 @@ modules modules_install:
 
 endif # CONFIG_MODULES
 
+# modules.builtin has a 'thick' form which maps from kernel modules (or rather
+# the object file names they would have had had they not been built in) to their
+# constituent object files: kallsyms uses this to determine which modules any
+# given object file is part of.  (We cannot eliminate the slight redundancy
+# here without double-expansion.)
+
+modbuiltin-dirs := $(addprefix _modbuiltin_, $(build-dirs))
+
+modbuiltin-thick-dirs := $(addprefix _modbuiltin_thick_, $(build-dirs))
+
+modules.builtin: $(modbuiltin-dirs)
+	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
+
+modules_thick.builtin: $(modbuiltin-thick-dirs)
+	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
+
+PHONY += $(modbuiltin-dirs) $(modbuiltin-thick-dirs)
+# tristate.conf is not included from this Makefile. Add it as a prerequisite
+# here to make it self-healing in case somebody accidentally removes it.
+$(modbuiltin-dirs): include/config/tristate.conf
+	$(Q)$(MAKE) $(modbuiltin)=$(patsubst _modbuiltin_%,%,$@) \
+			builtin-file=modules.builtin
+
+$(modbuiltin-thick-dirs): include/config/tristate.conf
+	$(Q)$(MAKE) $(modbuiltin)=$(patsubst _modbuiltin_thick_%,%,$@) \
+			builtin-file=modules_thick.builtin
+
 ###
 # Cleaning is done on three levels.
 # make clean     Delete most generated files
@@ -1677,6 +1693,7 @@ clean: $(clean-dirs)
 		-o -name '*.asn1.[ch]' \
 		-o -name '*.symtypes' -o -name 'modules.order' \
 		-o -name modules.builtin -o -name '.tmp_*.o.*' \
+		-o -name modules_thick.builtin \
 		-o -name '*.c.[012]*.*' \
 		-o -name '*.ll' \
 		-o -name '*.gcno' \) -type f -print | xargs rm -f

include/linux/module.h

@@ -592,7 +592,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
-			char *name, char *module_name, int *exported);
+		       char *name, char *module_name, unsigned long *size,
+		       int *exported);
 
 /* Look for this name: can be of form module:name. */
 unsigned long module_kallsyms_lookup_name(const char *name);
@@ -774,8 +775,8 @@ static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *
 }
 
 static inline int module_get_kallsym(unsigned int symnum, unsigned long *value,
-					char *type, char *name,
-					char *module_name, int *exported)
+				     char *type, char *name, char *module_name,
+				     unsigned long *size, int *exported)
 {
 	return -ERANGE;
 }

init/Kconfig

@@ -1429,6 +1429,14 @@ config POSIX_TIMERS
 
 	  If unsure say y.
 
+config KALLMODSYMS
+	default y
+	bool "Enable support for /proc/kallmodsyms" if EXPERT
+	depends on KALLSYMS
+	help
+	  This option enables the /proc/kallmodsyms file, which maps symbols
+	  to addresses and their associated modules.
+
 config PRINTK
 	default y
 	bool "Enable support for printk" if EXPERT