diff options
Diffstat (limited to 'scripts')
115 files changed, 14089 insertions, 5593 deletions
diff --git a/scripts/.gitignore b/scripts/.gitignore index 3dbb8bb2457b..c2ef68848da5 100644 --- a/scripts/.gitignore +++ b/scripts/.gitignore @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only /asn1_compiler +/gen_packed_field_checks /generate_rust_target /insert-sys-cert /kallsyms diff --git a/scripts/Makefile b/scripts/Makefile index 6bcda4b9d054..46f860529df5 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -47,13 +47,14 @@ HOSTCFLAGS_sorttable.o += -DMCOUNT_SORT_ENABLED endif # The following programs are only built on demand -hostprogs += unifdef +hostprogs += unifdef gen_packed_field_checks # The module linker script is preprocessed on demand targets += module.lds subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins -subdir-$(CONFIG_MODVERSIONS) += genksyms +subdir-$(CONFIG_GENKSYMS) += genksyms +subdir-$(CONFIG_GENDWARFKSYMS) += gendwarfksyms subdir-$(CONFIG_SECURITY_SELINUX) += selinux subdir-$(CONFIG_SECURITY_IPE) += ipe diff --git a/scripts/Makefile.btf b/scripts/Makefile.btf index c3cbeb13de50..db76335dd917 100644 --- a/scripts/Makefile.btf +++ b/scripts/Makefile.btf @@ -23,8 +23,10 @@ else # Switch to using --btf_features for v1.26 and later. pahole-flags-$(call test-ge, $(pahole-ver), 126) = -j$(JOBS) --btf_features=encode_force,var,float,enum64,decl_tag,type_tag,optimized_func,consistent_func,decl_tag_kfuncs +pahole-flags-$(call test-ge, $(pahole-ver), 130) += --btf_features=attributes + ifneq ($(KBUILD_EXTMOD),) -module-pahole-flags-$(call test-ge, $(pahole-ver), 126) += --btf_features=distilled_base +module-pahole-flags-$(call test-ge, $(pahole-ver), 128) += --btf_features=distilled_base endif endif diff --git a/scripts/Makefile.build b/scripts/Makefile.build index c16e4cf54d77..557e725ab932 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -20,10 +20,6 @@ always-m := targets := subdir-y := subdir-m := -EXTRA_AFLAGS := -EXTRA_CFLAGS := -EXTRA_CPPFLAGS := -EXTRA_LDFLAGS := asflags-y := ccflags-y := rustflags-y := @@ -87,7 +83,7 @@ else ifeq ($(KBUILD_CHECKSRC),2) endif ifneq ($(KBUILD_EXTRA_WARN),) - cmd_checkdoc = $(srctree)/scripts/kernel-doc -none $(KDOCFLAGS) \ + cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(KDOCFLAGS) \ $(if $(findstring 2, $(KBUILD_EXTRA_WARN)), -Wall) \ $< endif @@ -107,13 +103,24 @@ cmd_cpp_i_c = $(CPP) $(c_flags) -o $@ $< $(obj)/%.i: $(obj)/%.c FORCE $(call if_changed_dep,cpp_i_c) +getexportsymbols = $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/$(1)/p' + +gendwarfksyms = $(objtree)/scripts/gendwarfksyms/gendwarfksyms \ + $(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes)) \ + $(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable) + genksyms = $(objtree)/scripts/genksyms/genksyms \ $(if $(KBUILD_SYMTYPES), -T $(@:.o=.symtypes)) \ $(if $(KBUILD_PRESERVE), -p) \ $(addprefix -r , $(wildcard $(@:.o=.symref))) # These mirror gensymtypes_S and co below, keep them in synch. +ifdef CONFIG_GENDWARFKSYMS +cmd_gensymtypes_c = $(if $(skip_gendwarfksyms),, \ + $(call getexportsymbols,\1) | $(gendwarfksyms) $@) +else cmd_gensymtypes_c = $(CPP) -D__GENKSYMS__ $(c_flags) $< | $(genksyms) +endif # CONFIG_GENDWARFKSYMS # LLVM assembly # Generate .ll files from .c @@ -183,7 +190,9 @@ endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT is-standard-object = $(if $(filter-out y%, $(OBJECT_FILES_NON_STANDARD_$(target-stem).o)$(OBJECT_FILES_NON_STANDARD)n),$(is-kernel-object)) +ifdef CONFIG_OBJTOOL $(obj)/%.o: private objtool-enabled = $(if $(is-standard-object),$(if $(delay-objtool),$(is-single-obj-m),y)) +endif ifneq ($(findstring 1, $(KBUILD_EXTRA_WARN)),) cmd_warn_shared_object = $(if $(word 2, $(modname-multi)),$(warning $(kbuild-file): $*.o is added to multiple modules: $(modname-multi))) @@ -213,7 +222,16 @@ $(obj)/%.lst: $(obj)/%.c FORCE # Compile Rust sources (.rs) # --------------------------------------------------------------------------- -rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons +# The features in this list are the ones allowed for non-`rust/` code. +# +# - Stable since Rust 1.81.0: `feature(lint_reasons)`. +# - Stable since Rust 1.82.0: `feature(asm_const)`, `feature(raw_ref_op)`. +# - Stable since Rust 1.87.0: `feature(asm_goto)`. +# - Expected to become stable: `feature(arbitrary_self_types)`. +# +# Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on +# the unstable features in use. +rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,raw_ref_op # `--out-dir` is required to avoid temporaries being created by `rustc` in the # current working directory, which may be not accessible in the out-of-tree @@ -224,7 +242,7 @@ rust_common_cmd = \ -Zallow-features=$(rust_allowed_features) \ -Zcrate-attr=no_std \ -Zcrate-attr='feature($(rust_allowed_features))' \ - -Zunstable-options --extern kernel \ + -Zunstable-options --extern pin_init --extern kernel \ --crate-type rlib -L $(objtree)/rust/ \ --crate-name $(basename $(notdir $@)) \ --sysroot=/dev/null \ @@ -286,14 +304,26 @@ $(obj)/%.rs: $(obj)/%.rs.S FORCE # This is convoluted. The .S file must first be preprocessed to run guards and # expand names, then the resulting exports must be constructed into plain # EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed -# to make the genksyms input. +# to make the genksyms input or compiled into an object for gendwarfksyms. # # These mirror gensymtypes_c and co above, keep them in synch. -cmd_gensymtypes_S = \ - { echo "\#include <linux/kernel.h>" ; \ - echo "\#include <asm/asm-prototypes.h>" ; \ - $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/EXPORT_SYMBOL(\1);/p' ; } | \ - $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms) +getasmexports = \ + { echo "\#include <linux/kernel.h>" ; \ + echo "\#include <linux/string.h>" ; \ + echo "\#include <asm/asm-prototypes.h>" ; \ + $(call getexportsymbols,EXPORT_SYMBOL(\1);) ; } + +ifdef CONFIG_GENDWARFKSYMS +cmd_gensymtypes_S = \ + $(getasmexports) | \ + $(CC) $(c_flags) -c -o $(@:.o=.gendwarfksyms.o) -xc -; \ + $(call getexportsymbols,\1) | \ + $(gendwarfksyms) $(@:.o=.gendwarfksyms.o) +else +cmd_gensymtypes_S = \ + $(getasmexports) | \ + $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms) +endif # CONFIG_GENDWARFKSYMS quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@ cmd_cpp_s_S = $(CPP) $(a_flags) -o $@ $< diff --git a/scripts/Makefile.clang b/scripts/Makefile.clang index 2435efae67f5..b67636b28c35 100644 --- a/scripts/Makefile.clang +++ b/scripts/Makefile.clang @@ -12,6 +12,8 @@ CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu CLANG_TARGET_FLAGS_sparc := sparc64-linux-gnu CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu +# This is only for i386 UM builds, which need the 32-bit target not -m32 +CLANG_TARGET_FLAGS_i386 := i386-linux-gnu CLANG_TARGET_FLAGS_um := $(CLANG_TARGET_FLAGS_$(SUBARCH)) CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(SRCARCH)) diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler index 8c1029687e2e..ef91910de265 100644 --- a/scripts/Makefile.compiler +++ b/scripts/Makefile.compiler @@ -43,7 +43,7 @@ as-instr = $(call try-run,\ # __cc-option # Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586) __cc-option = $(call try-run,\ - $(1) -Werror $(2) $(3) -c -x c /dev/null -o "$$TMP",$(3),$(4)) + $(1) -Werror $(2) $(3:-Wno-%=-W%) -c -x c /dev/null -o "$$TMP",$(3),$(4)) # cc-option # Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586) @@ -57,16 +57,20 @@ cc-option-yn = $(if $(call cc-option,$1),y,n) # cc-disable-warning # Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable) -cc-disable-warning = $(if $(call cc-option,-W$(strip $1)),-Wno-$(strip $1)) +cc-disable-warning = $(call cc-option,-Wno-$(strip $1)) # gcc-min-version -# Usage: cflags-$(call gcc-min-version, 70100) += -foo +# Usage: cflags-$(call gcc-min-version, 110100) += -foo gcc-min-version = $(call test-ge, $(CONFIG_GCC_VERSION), $1) # clang-min-version # Usage: cflags-$(call clang-min-version, 110000) += -foo clang-min-version = $(call test-ge, $(CONFIG_CLANG_VERSION), $1) +# rustc-min-version +# Usage: rustc-$(call rustc-min-version, 108500) += -Cfoo +rustc-min-version = $(call test-ge, $(CONFIG_RUSTC_VERSION), $1) + # ld-option # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y) ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) @@ -75,8 +79,8 @@ ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3)) # Usage: MY_RUSTFLAGS += $(call __rustc-option,$(RUSTC),$(MY_RUSTFLAGS),-Cinstrument-coverage,-Zinstrument-coverage) # TODO: remove RUSTC_BOOTSTRAP=1 when we raise the minimum GNU Make version to 4.4 __rustc-option = $(call try-run,\ - echo '#![allow(missing_docs)]#![feature(no_core)]#![no_core]' | RUSTC_BOOTSTRAP=1\ - $(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null,$(2)) $(3)\ + echo '$(pound)![allow(missing_docs)]$(pound)![feature(no_core)]$(pound)![no_core]' | RUSTC_BOOTSTRAP=1\ + $(1) --sysroot=/dev/null $(filter-out --sysroot=/dev/null --target=%,$(2)) $(3)\ --crate-type=rlib --out-dir=$(TMPOUT) --emit=obj=- - >/dev/null,$(3),$(4)) # rustc-option diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf index 226ea3df3b4b..a44307f08e9d 100644 --- a/scripts/Makefile.defconf +++ b/scripts/Makefile.defconf @@ -1,6 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Configuration heplers +cmd_merge_fragments = \ + $(srctree)/scripts/kconfig/merge_config.sh \ + $4 -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$2 \ + $(foreach config,$3,$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + # Creates 'merged defconfigs' # --------------------------------------------------------------------------- # Usage: @@ -8,9 +13,7 @@ # # Input config fragments without '.config' suffix define merge_into_defconfig - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ - -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \ - $(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + $(call cmd,merge_fragments,$1,$2) +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig endef @@ -22,8 +25,6 @@ endef # # Input config fragments without '.config' suffix define merge_into_defconfig_override - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ - -Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \ - $(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + $(call cmd,merge_fragments,$1,$2,-Q) +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig endef diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 1d13cecc7cc7..dca175fffcab 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -8,6 +8,7 @@ # Default set of warnings, always enabled KBUILD_CFLAGS += -Wall +KBUILD_CFLAGS += -Wextra KBUILD_CFLAGS += -Wundef KBUILD_CFLAGS += -Werror=implicit-function-declaration KBUILD_CFLAGS += -Werror=implicit-int @@ -15,8 +16,8 @@ KBUILD_CFLAGS += -Werror=return-type KBUILD_CFLAGS += -Werror=strict-prototypes KBUILD_CFLAGS += -Wno-format-security KBUILD_CFLAGS += -Wno-trigraphs -KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,) -KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) +KBUILD_CFLAGS += $(call cc-option, -Wno-frame-address) +KBUILD_CFLAGS += $(call cc-option, -Wno-address-of-packed-member) KBUILD_CFLAGS += -Wmissing-declarations KBUILD_CFLAGS += -Wmissing-prototypes @@ -31,6 +32,23 @@ KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds ifdef CONFIG_CC_IS_CLANG # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable. KBUILD_CFLAGS += -Wno-gnu + +# Clang checks for overflow/truncation with '%p', while GCC does not: +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219 +KBUILD_CFLAGS += $(call cc-option, -Wno-format-overflow-non-kprintf) +KBUILD_CFLAGS += $(call cc-option, -Wno-format-truncation-non-kprintf) + +# Clang may emit a warning when a const variable, such as the dummy variables +# in typecheck(), or const member of an aggregate type are not initialized, +# which can result in unexpected behavior. However, in many audited cases of +# the "field" variant of the warning, this is intentional because the field is +# never used within a particular call path, the field is within a union with +# other non-const members, or the containing object is not const so the field +# can be modified via memcpy() / memset(). While the variable warning also gets +# disabled with this same switch, there should not be too much coverage lost +# because -Wuninitialized will still flag when an uninitialized const variable +# is used. +KBUILD_CFLAGS += $(call cc-option, -Wno-default-const-init-unsafe) else # gcc inanely warns about local variables called 'main' @@ -38,10 +56,15 @@ KBUILD_CFLAGS += -Wno-main endif # These result in bogus false positives -KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer) +KBUILD_CFLAGS += $(call cc-option, -Wno-dangling-pointer) -# Variable Length Arrays (VLAs) should not be used anywhere in the kernel -KBUILD_CFLAGS += -Wvla +# Stack Variable Length Arrays (VLAs) must not be used in the kernel. +# Function array parameters should, however, be usable, but -Wvla will +# warn for those. Clang has no way yet to distinguish between the VLA +# types, so depend on GCC for now to keep stack VLAs out of the tree. +# https://github.com/llvm/llvm-project/issues/57098 +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98217 +KBUILD_CFLAGS += $(call cc-option,-Wvla-larger-than=1) # disable pointer signed / unsigned warnings in gcc 4.0 KBUILD_CFLAGS += -Wno-pointer-sign @@ -51,6 +74,13 @@ KBUILD_CFLAGS += -Wno-pointer-sign # globally built with -Wcast-function-type. KBUILD_CFLAGS += $(call cc-option, -Wcast-function-type) +# Currently, disable -Wstringop-overflow for GCC 11, globally. +KBUILD_CFLAGS-$(CONFIG_CC_NO_STRINGOP_OVERFLOW) += $(call cc-option, -Wno-stringop-overflow) +KBUILD_CFLAGS-$(CONFIG_CC_STRINGOP_OVERFLOW) += $(call cc-option, -Wstringop-overflow) + +# Currently, disable -Wunterminated-string-initialization as broken +KBUILD_CFLAGS += $(call cc-option, -Wno-unterminated-string-initialization) + # The allocators already balk at large sizes, so silence the compiler # warnings for bounds checks involving those possible values. While # -Wno-alloc-size-larger-than would normally be used here, earlier versions @@ -77,7 +107,6 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # Warn if there is an enum types mismatch KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion) -KBUILD_CFLAGS += -Wextra KBUILD_CFLAGS += -Wunused # @@ -96,19 +125,14 @@ else # Some diagnostics enabled by default are noisy. # Suppress them by using -Wno... except for W=1. -KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned) -KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) +KBUILD_CFLAGS += $(call cc-option, -Wno-unused-but-set-variable) +KBUILD_CFLAGS += $(call cc-option, -Wno-unused-const-variable) +KBUILD_CFLAGS += $(call cc-option, -Wno-packed-not-aligned) +KBUILD_CFLAGS += $(call cc-option, -Wno-format-overflow) ifdef CONFIG_CC_IS_GCC -KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) -else -# Clang checks for overflow/truncation with '%p', while GCC does not: -# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219 -KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf) -KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf) +KBUILD_CFLAGS += $(call cc-option, -Wno-format-truncation) endif -KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +KBUILD_CFLAGS += $(call cc-option, -Wno-stringop-truncation) KBUILD_CFLAGS += -Wno-override-init # alias for -Wno-initializer-overrides in clang @@ -126,11 +150,10 @@ ifeq ($(call clang-min-version, 120000),y) KBUILD_CFLAGS += -Wformat-insufficient-args endif endif -KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) +KBUILD_CFLAGS += $(call cc-option, -Wno-pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare -KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) +KBUILD_CFLAGS += $(call cc-option, -Wno-unaligned-access) KBUILD_CFLAGS += -Wno-enum-compare-conditional -KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif @@ -154,6 +177,10 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers KBUILD_CFLAGS += -Wno-type-limits KBUILD_CFLAGS += -Wno-shift-negative-value +ifdef CONFIG_CC_IS_CLANG +KBUILD_CFLAGS += -Wno-enum-enum-conversion +endif + ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += -Wno-maybe-uninitialized endif diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins index e4deaf5fa571..435ab3f0ec44 100644 --- a/scripts/Makefile.gcc-plugins +++ b/scripts/Makefile.gcc-plugins @@ -8,20 +8,6 @@ ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY endif export DISABLE_LATENT_ENTROPY_PLUGIN -gcc-plugin-$(CONFIG_GCC_PLUGIN_STRUCTLEAK) += structleak_plugin.so -gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_VERBOSE) \ - += -fplugin-arg-structleak_plugin-verbose -gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF) \ - += -fplugin-arg-structleak_plugin-byref -gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL) \ - += -fplugin-arg-structleak_plugin-byref-all -ifdef CONFIG_GCC_PLUGIN_STRUCTLEAK - DISABLE_STRUCTLEAK_PLUGIN += -fplugin-arg-structleak_plugin-disable -endif -export DISABLE_STRUCTLEAK_PLUGIN -gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK) \ - += -DSTRUCTLEAK_PLUGIN - gcc-plugin-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak_plugin.so gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK) \ += -DSTACKLEAK_PLUGIN @@ -36,15 +22,9 @@ ifdef CONFIG_GCC_PLUGIN_STACKLEAK endif export DISABLE_STACKLEAK_PLUGIN -gcc-plugin-$(CONFIG_GCC_PLUGIN_ARM_SSP_PER_TASK) += arm_ssp_per_task_plugin.so -ifdef CONFIG_GCC_PLUGIN_ARM_SSP_PER_TASK - DISABLE_ARM_SSP_PER_TASK_PLUGIN += -fplugin-arg-arm_ssp_per_task_plugin-disable -endif -export DISABLE_ARM_SSP_PER_TASK_PLUGIN - # All the plugin CFLAGS are collected here in case a build target needs to # filter them out of the KBUILD_CFLAGS. -GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y)) +GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y)) -DGCC_PLUGINS export GCC_PLUGINS_CFLAGS # Add the flags to the build! @@ -52,8 +32,6 @@ KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS) # Some plugins are enabled outside of this Makefile, but they still need to # be included in GCC_PLUGIN so they can get built. -gcc-plugin-external-$(CONFIG_GCC_PLUGIN_SANCOV) \ - += sancov_plugin.so gcc-plugin-external-$(CONFIG_GCC_PLUGIN_RANDSTRUCT) \ += randomize_layout_plugin.so diff --git a/scripts/Makefile.kcov b/scripts/Makefile.kcov index 67e8cfe3474b..78305a84ba9d 100644 --- a/scripts/Makefile.kcov +++ b/scripts/Makefile.kcov @@ -1,6 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only -kcov-flags-$(CONFIG_CC_HAS_SANCOV_TRACE_PC) += -fsanitize-coverage=trace-pc +kcov-flags-y += -fsanitize-coverage=trace-pc kcov-flags-$(CONFIG_KCOV_ENABLE_COMPARISONS) += -fsanitize-coverage=trace-cmp -kcov-flags-$(CONFIG_GCC_PLUGIN_SANCOV) += -fplugin=$(objtree)/scripts/gcc-plugins/sancov_plugin.so + +kcov-rflags-y += -Cpasses=sancov-module +kcov-rflags-y += -Cllvm-args=-sanitizer-coverage-level=3 +kcov-rflags-y += -Cllvm-args=-sanitizer-coverage-trace-pc +kcov-rflags-$(CONFIG_KCOV_ENABLE_COMPARISONS) += -Cllvm-args=-sanitizer-coverage-trace-compares export CFLAGS_KCOV := $(kcov-flags-y) +export RUSTFLAGS_KCOV := $(kcov-rflags-y) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 7395200538da..2b332645e0c2 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -1,9 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -# Backward compatibility -asflags-y += $(EXTRA_AFLAGS) -ccflags-y += $(EXTRA_CFLAGS) -cppflags-y += $(EXTRA_CPPFLAGS) -ldflags-y += $(EXTRA_LDFLAGS) # flags that take effect in current and sub directories KBUILD_AFLAGS += $(subdir-asflags-y) @@ -166,14 +161,17 @@ _c_flags += $(if $(patsubst n%,, \ $(UBSAN_SANITIZE_$(target-stem).o)$(UBSAN_SANITIZE)$(is-kernel-object)), \ $(CFLAGS_UBSAN)) _c_flags += $(if $(patsubst n%,, \ - $(UBSAN_SIGNED_WRAP_$(target-stem).o)$(UBSAN_SANITIZE_$(target-stem).o)$(UBSAN_SIGNED_WRAP)$(UBSAN_SANITIZE)$(is-kernel-object)), \ - $(CFLAGS_UBSAN_SIGNED_WRAP)) + $(UBSAN_INTEGER_WRAP_$(target-stem).o)$(UBSAN_SANITIZE_$(target-stem).o)$(UBSAN_INTEGER_WRAP)$(UBSAN_SANITIZE)$(is-kernel-object)), \ + $(CFLAGS_UBSAN_INTEGER_WRAP)) endif ifeq ($(CONFIG_KCOV),y) _c_flags += $(if $(patsubst n%,, \ $(KCOV_INSTRUMENT_$(target-stem).o)$(KCOV_INSTRUMENT)$(if $(is-kernel-object),$(CONFIG_KCOV_INSTRUMENT_ALL))), \ $(CFLAGS_KCOV)) +_rust_flags += $(if $(patsubst n%,, \ + $(KCOV_INSTRUMENT_$(target-stem).o)$(KCOV_INSTRUMENT)$(if $(is-kernel-object),$(CONFIG_KCOV_INSTRUMENT_ALL))), \ + $(RUSTFLAGS_KCOV)) endif # @@ -275,8 +273,9 @@ objtool-args-$(CONFIG_MITIGATION_SLS) += --sls objtool-args-$(CONFIG_STACK_VALIDATION) += --stackval objtool-args-$(CONFIG_HAVE_STATIC_CALL_INLINE) += --static-call objtool-args-$(CONFIG_HAVE_UACCESS_VALIDATION) += --uaccess -objtool-args-$(CONFIG_GCOV_KERNEL) += --no-unreachable +objtool-args-$(or $(CONFIG_GCOV_KERNEL),$(CONFIG_KCOV)) += --no-unreachable objtool-args-$(CONFIG_PREFIX_SYMBOLS) += --prefix=$(CONFIG_FUNCTION_PADDING_BYTES) +objtool-args-$(CONFIG_OBJTOOL_WERROR) += --Werror objtool-args = $(objtool-args-y) \ $(if $(delay-objtool), --link) \ @@ -287,6 +286,8 @@ delay-objtool := $(or $(CONFIG_LTO_CLANG),$(CONFIG_X86_KERNEL_IBT)) cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool-args) $@) cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) +objtool-enabled := y + endif # CONFIG_OBJTOOL # Useful for describing the dependency of composite objects @@ -298,15 +299,28 @@ $(foreach m, $1, \ $(addprefix $(obj)/, $(call suffix-search, $(patsubst $(obj)/%,%,$m), $2, $3)))) endef +# Remove ".." and "." from a path, without using "realpath" +# Usage: +# $(call normalize_path,path/to/../file) +define normalize_path +$(strip $(eval elements :=) \ +$(foreach elem,$(subst /, ,$1), \ + $(if $(filter-out .,$(elem)), \ + $(if $(filter ..,$(elem)), \ + $(eval elements := $(wordlist 2,$(words $(elements)),x $(elements))), \ + $(eval elements := $(elements) $(elem))))) \ +$(subst $(space),/,$(elements))) +endef + # Build commands # =========================================================================== # These are shared by some Makefile.* files. -objtool-enabled := y - ifdef CONFIG_LTO_CLANG -# objtool cannot process LLVM IR. Make $(LD) covert LLVM IR to ELF here. -cmd_ld_single = $(if $(objtool-enabled), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@) +# Run $(LD) here to convert LLVM IR to ELF in the following cases: +# - when this object needs objtool processing, as objtool cannot process LLVM IR +# - when this is a single-object module, as modpost cannot process LLVM IR +cmd_ld_single = $(if $(objtool-enabled)$(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@) endif quiet_cmd_cc_o_c = CC $(quiet_modtag) $@ @@ -345,6 +359,11 @@ quiet_cmd_copy = COPY $@ $(obj)/%: $(src)/%_shipped $(call cmd,copy) +# Touch a file +# =========================================================================== +quiet_cmd_touch = TOUCH $(call normalize_path,$@) + cmd_touch = touch $@ + # Commands useful for building a boot image # =========================================================================== # diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index f97c9926ed31..1628198f3e83 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -105,7 +105,7 @@ else sig-key := $(CONFIG_MODULE_SIG_KEY) endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ + cmd_sign = $(objtree)/scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" $(objtree)/certs/signing_key.x509 $@ \ $(if $(KBUILD_EXTMOD),|| true) ifeq ($(sign-only),) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index ab0e94ea6249..d7d45067d08b 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -43,6 +43,8 @@ MODPOST = $(objtree)/scripts/mod/modpost modpost-args = \ $(if $(CONFIG_MODULES),-M) \ $(if $(CONFIG_MODVERSIONS),-m) \ + $(if $(CONFIG_BASIC_MODVERSIONS),-b) \ + $(if $(CONFIG_EXTENDED_MODVERSIONS),-x) \ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ $(if $(KBUILD_MODPOST_WARN),-w) \ diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan index b2d3b273b802..734a102e6b56 100644 --- a/scripts/Makefile.ubsan +++ b/scripts/Makefile.ubsan @@ -1,5 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 +# Shared with KVM/arm64. +export CFLAGS_UBSAN_TRAP := $(call cc-option,-fsanitize-trap=undefined,-fsanitize-undefined-trap-on-error) + # Enable available and selected UBSAN features. ubsan-cflags-$(CONFIG_UBSAN_ALIGNMENT) += -fsanitize=alignment ubsan-cflags-$(CONFIG_UBSAN_BOUNDS_STRICT) += -fsanitize=bounds-strict @@ -10,9 +13,16 @@ ubsan-cflags-$(CONFIG_UBSAN_DIV_ZERO) += -fsanitize=integer-divide-by-zero ubsan-cflags-$(CONFIG_UBSAN_UNREACHABLE) += -fsanitize=unreachable ubsan-cflags-$(CONFIG_UBSAN_BOOL) += -fsanitize=bool ubsan-cflags-$(CONFIG_UBSAN_ENUM) += -fsanitize=enum -ubsan-cflags-$(CONFIG_UBSAN_TRAP) += $(call cc-option,-fsanitize-trap=undefined,-fsanitize-undefined-trap-on-error) +ubsan-cflags-$(CONFIG_UBSAN_TRAP) += $(CFLAGS_UBSAN_TRAP) export CFLAGS_UBSAN := $(ubsan-cflags-y) -ubsan-signed-wrap-cflags-$(CONFIG_UBSAN_SIGNED_WRAP) += -fsanitize=signed-integer-overflow -export CFLAGS_UBSAN_SIGNED_WRAP := $(ubsan-signed-wrap-cflags-y) +ubsan-integer-wrap-cflags-$(CONFIG_UBSAN_INTEGER_WRAP) += \ + -DINTEGER_WRAP \ + -fsanitize-undefined-ignore-overflow-pattern=all \ + -fsanitize=signed-integer-overflow \ + -fsanitize=unsigned-integer-overflow \ + -fsanitize=implicit-signed-integer-truncation \ + -fsanitize=implicit-unsigned-integer-truncation \ + -fsanitize-ignorelist=$(srctree)/scripts/integer-wrap-ignore.scl +export CFLAGS_UBSAN_INTEGER_WRAP := $(ubsan-integer-wrap-cflags-y) diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index 873caaa55313..b64862dc6f08 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -9,6 +9,20 @@ include $(srctree)/scripts/Makefile.lib targets := +ifdef CONFIG_ARCH_VMLINUX_NEEDS_RELOCS +vmlinux-final := vmlinux.unstripped + +quiet_cmd_strip_relocs = RSTRIP $@ + cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' --remove-section=!'.rel*.dyn' $< $@ + +vmlinux: $(vmlinux-final) FORCE + $(call if_changed,strip_relocs) + +targets += vmlinux +else +vmlinux-final := vmlinux +endif + %.o: %.c FORCE $(call if_changed_rule,cc_o_c) @@ -47,7 +61,7 @@ targets += .builtin-dtbs-list ifdef CONFIG_GENERIC_BUILTIN_DTB targets += .builtin-dtbs.S .builtin-dtbs.o -vmlinux: .builtin-dtbs.o +$(vmlinux-final): .builtin-dtbs.o endif # vmlinux @@ -55,11 +69,11 @@ endif ifdef CONFIG_MODULES targets += .vmlinux.export.o -vmlinux: .vmlinux.export.o +$(vmlinux-final): .vmlinux.export.o endif ifdef CONFIG_ARCH_WANTS_PRE_LINK_VMLINUX -vmlinux: arch/$(SRCARCH)/tools/vmlinux.arch.o +$(vmlinux-final): arch/$(SRCARCH)/tools/vmlinux.arch.o arch/$(SRCARCH)/tools/vmlinux.arch.o: vmlinux.o FORCE $(Q)$(MAKE) $(build)=arch/$(SRCARCH)/tools $@ @@ -69,17 +83,21 @@ ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) # Final link of vmlinux with optional arch pass after final link cmd_link_vmlinux = \ - $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)"; \ + $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)" "$@"; \ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) -targets += vmlinux -vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE +targets += $(vmlinux-final) +$(vmlinux-final): scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE +$(call if_changed_dep,link_vmlinux) ifdef CONFIG_DEBUG_INFO_BTF -vmlinux: $(RESOLVE_BTFIDS) +$(vmlinux-final): $(RESOLVE_BTFIDS) +endif + +ifdef CONFIG_BUILDTIME_TABLE_SORT +$(vmlinux-final): scripts/sorttable endif -# module.builtin.ranges +# modules.builtin.ranges # --------------------------------------------------------------------------- ifdef CONFIG_BUILTIN_MODULE_RANGES __default: modules.builtin.ranges @@ -92,7 +110,7 @@ modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \ modules.builtin vmlinux.map vmlinux.o.map FORCE $(call if_changed,modules_builtin_ranges) -vmlinux.map: vmlinux +vmlinux.map: $(vmlinux-final) @: endif diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 0b6e2ebf60dc..b024ffb3e201 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -30,13 +30,20 @@ endif # objtool for vmlinux.o # --------------------------------------------------------------------------- # -# For LTO and IBT, objtool doesn't run on individual translation units. -# Run everything on vmlinux instead. +# For delay-objtool (IBT or LTO), objtool doesn't run on individual translation +# units. Instead it runs on vmlinux.o. +# +# For !delay-objtool + CONFIG_NOINSTR_VALIDATION, it runs on both translation +# units and vmlinux.o, with the latter only used for noinstr/unret validation. objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION)) -vmlinux-objtool-args-$(delay-objtool) += $(objtool-args-y) -vmlinux-objtool-args-$(CONFIG_GCOV_KERNEL) += --no-unreachable +ifeq ($(delay-objtool),y) +vmlinux-objtool-args-y += $(objtool-args-y) +else +vmlinux-objtool-args-$(CONFIG_OBJTOOL_WERROR) += --Werror +endif + vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \ $(if $(or $(CONFIG_MITIGATION_UNRET_ENTRY),$(CONFIG_MITIGATION_SRSO)), --unret) @@ -66,7 +73,7 @@ vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE targets += vmlinux.o -# module.builtin.modinfo +# modules.builtin.modinfo # --------------------------------------------------------------------------- OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary @@ -75,7 +82,7 @@ targets += modules.builtin.modinfo modules.builtin.modinfo: vmlinux.o FORCE $(call if_changed,objcopy) -# module.builtin +# modules.builtin # --------------------------------------------------------------------------- # The second line aids cases where multiple modules share the same object. diff --git a/scripts/bash-completion/make b/scripts/bash-completion/make new file mode 100644 index 000000000000..42e8dcead25a --- /dev/null +++ b/scripts/bash-completion/make @@ -0,0 +1,451 @@ +# SPDX-License-Identifier: GPL-2.0-only +# bash completion for GNU make with kbuild extension -*- shell-script -*- + +# Load the default completion script for make. It is typically located at +# /usr/share/bash-completion/completions/make, but we do not rely on it. +__kbuild_load_default_make_completion() +{ + local -a dirs=("${BASH_COMPLETION_USER_DIR:-${XDG_DATA_HOME:-$HOME/.local/share}/bash-completion}/completions") + local ifs=$IFS IFS=: dir compfile this_dir + + for dir in ${XDG_DATA_DIRS:-/usr/local/share:/usr/share}; do + dirs+=("$dir"/bash-completion/completions) + done + IFS=$ifs + + this_dir="$(realpath "$(dirname "${BASH_SOURCE[0]}")")" + + for dir in "${dirs[@]}"; do + if [[ ! -d ${dir} || ${dir} = "${this_dir}" ]]; then + continue + fi + + for compfile in make make.bash _make; do + compfile=$dir/$compfile + # Avoid trying to source dirs; https://bugzilla.redhat.com/903540 + if [[ -f ${compfile} ]] && . "${compfile}" &>/dev/null; then + + __kbuild_default_make_completion=$( + # shellcheck disable=SC2046 # word splitting is the point here + set -- $(complete -p make) + + while [[ $# -gt 1 && "$1" != -F ]]; do + shift + done + + if [[ "$1" = -F ]]; then + echo "$2" + fi + ) + + return + fi + done + done +} + +__kbuild_load_default_make_completion + +__kbuild_handle_variable() +{ + local var=${1%%=*} + local cur=${cur#"${var}"=} + local srctree=$2 + local keywords=() + + case $var in + ARCH) + # sub-directories under arch/ + keywords+=($(find "${srctree}/arch" -mindepth 1 -maxdepth 1 -type d -printf '%P\n')) + # architectures hard-coded in the top Makefile + keywords+=(i386 x86_64 sparc32 sparc64 parisc64) + ;; + CROSS_COMPILE) + # toolchains with a full path + local cross_compile=() + local c c2 + _filedir + + for c in "${COMPREPLY[@]}"; do + # eval for tilde expansion + # suppress error, as this fails when it contains a space + eval "c2=${c}" 2>/dev/null || continue + if [[ ${c} == *-elfedit && ! -d ${c2} && -x ${c2} ]]; then + cross_compile+=("${c%elfedit}") + fi + done + + # toolchains in the PATH environment + while read -r c; do + if [[ ${c} == *-elfedit ]]; then + keywords+=("${c%elfedit}") + fi + done < <(compgen -c) + + COMPREPLY=() + _filedir -d + + # Add cross_compile directly without passing it to compgen. + # Otherwise, toolchain paths with a tilde do not work. + # e.g.) + # CROSS_COMPILE=~/0day/gcc-14.2.0-nolibc/aarch64-linux/bin/aarch64-linux- + COMPREPLY+=("${cross_compile[@]}") + ;; + LLVM) + # LLVM=1 uses the default 'clang' etc. + keywords+=(1) + + # suffix for a particular version. LLVM=-18 uses 'clang-18' etc. + while read -r c; do + if [[ ${c} == clang-[0-9]* ]]; then + keywords+=("${c#clang}") + fi + done < <(compgen -c) + + # directory path to LLVM toolchains + _filedir -d + ;; + KCONFIG_ALLCONFIG) + # KCONFIG_ALLCONFIG=1 selects the default fragment + keywords+=(1) + # or the path to a fragment file + _filedir + ;; + C | KBUILD_CHECKSRC) + keywords+=(1 2) + ;; + V | KBUILD_VERBOSE) + keywords+=({,1}{,2}) + ;; + W | KBUILD_EXTRA_WARN) + keywords+=({,1}{,2}{,3}{,c}{,e}) + ;; + KBUILD_ABS_SRCTREE | KBUILD_MODPOST_NOFINAL | KBUILD_MODPOST_WARN | \ + CLIPPY | KBUILD_CLIPPY | KCONFIG_NOSILENTUPDATE | \ + KCONFIG_OVERWRITECONFIG | KCONFIG_WARN_UNKNOWN_SYMBOL | \ + KCONFIG_WERROR ) + keywords+=(1) + ;; + INSTALL_MOD_STRIP) + keywords+=(1 --strip-debug --strip-unneeded) + ;; + O | KBUILD_OUTPUT | M | KBUILD_EXTMOD | MO | KBUILD_EXTMOD_OUTPUT | *_PATH) + # variables that take a directory. + _filedir -d + return + ;; + KBUILD_EXTRA_SYMBOL | KBUILD_KCONFIG | KCONFIG_CONFIG) + # variables that take a file. + _filedir + return + esac + + COMPREPLY+=($(compgen -W "${keywords[*]}" -- "${cur}")) +} + +# Check the -C, -f options and 'source' symlink. Return the source tree we are +# working in. +__kbuild_get_srctree() +{ + local words=("$@") + local cwd makef_dir + + # see if a path was specified with -C/--directory + for ((i = 1; i < ${#words[@]}; i++)); do + if [[ ${words[i]} == -@(C|-directory) ]]; then + # eval for tilde expansion. + # suppress error, as this fails when it contains a space + eval "cwd=${words[i + 1]}" 2>/dev/null + break + fi + done + + if [[ -z ${cwd} ]]; then + cwd=. + fi + + # see if a Makefile was specified with -f/--file/--makefile + for ((i = 1; i < ${#words[@]}; i++)); do + if [[ ${words[i]} == -@(f|-?(make)file) ]]; then + # eval for tilde expansion + # suppress error, as this fails when it contains a space + eval "makef_dir=${words[i + 1]%/*}" 2>/dev/null + break + fi + done + + if [ -z "${makef_dir}" ]; then + makef_dir=${cwd} + elif [[ ${makef_dir} != /* ]]; then + makef_dir=${cwd}/${makef_dir} + fi + + # If ${makef_dir} is a build directory created by the O= option, there + # is a symbolic link 'source', which points to the kernel source tree. + if [[ -L ${makef_dir}/source ]]; then + makef_dir=$(readlink "${makef_dir}/source") + fi + + echo "${makef_dir}" +} + +# Get SRCARCH to do a little more clever things +__kbuild_get_srcarch() +{ + local words=("$@") + local arch srcarch uname_m + + # see if ARCH= is explicitly specified + for ((i = 1; i < ${#words[@]}; i++)); do + if [[ ${words[i]} == ARCH=* ]]; then + arch=${words[i]#ARCH=} + break + fi + done + + # If ARCH= is not specified, check the build marchine's architecture + if [[ -z ${arch} ]]; then + uname_m=$(uname -m) + + # shellcheck disable=SC2209 # 'sh' is SuperH, not a shell command + case ${uname_m} in + arm64 | aarch64*) arch=arm64 ;; + arm* | sa110) arch=arm ;; + i?86 | x86_64) arch=x86 ;; + loongarch*) arch=loongarch ;; + mips*) arch=mips ;; + ppc*) arch=powerpc ;; + riscv*) arch=riscv ;; + s390x) arch=s390 ;; + sh[234]*) arch=sh ;; + sun4u) arch=sparc64 ;; + *) arch=${uname_m} ;; + esac + fi + + case ${arch} in + parisc64) srcarch=parisc ;; + sparc32 | sparc64) srcarch=sparc ;; + i386 | x86_64) srcarch=x86 ;; + *) srcarch=${arch} ;; + esac + + echo "$srcarch" +} + +# small Makefile to parse obj-* syntax +__kbuild_tmp_makefile() +{ +cat <<'EOF' +.PHONY: __default +__default: + $(foreach m,$(obj-y) $(obj-m) $(obj-),$(foreach s, -objs -y -m -,$($(m:%.o=%$s))) $(m)) +EOF +echo "include ${1}" +} + +_make_for_kbuild () +{ + # shellcheck disable=SC2034 # these are set by _init_completion + local cur prev words cword split + _init_completion -s || return + + local srctree + srctree=$(__kbuild_get_srctree "${words[@]}") + + # If 'kernel' and 'Documentation' directories are found, we assume this + # is a kernel tree. Otherwise, we fall back to the generic rule provided + # by the bash-completion project. + if [[ ! -d ${srctree}/kernel || ! -d ${srctree}/Documentation ]]; then + if [ -n "${__kbuild_default_make_completion}" ]; then + "${__kbuild_default_make_completion}" "$@" + fi + return + fi + + # make options with a parameter (copied from the bash-completion project) + case ${prev} in + --file | --makefile | --old-file | --assume-old | --what-if | --new-file | \ + --assume-new | -!(-*)[foW]) + _filedir + return + ;; + --include-dir | --directory | -!(-*)[ICm]) + _filedir -d + return + ;; + -!(-*)E) + COMPREPLY=($(compgen -v -- "$cur")) + return + ;; + --eval | -!(-*)[DVx]) + return + ;; + --jobs | -!(-*)j) + COMPREPLY=($(compgen -W "{1..$(($(_ncpus) * 2))}" -- "$cur")) + return + ;; + esac + + local keywords=() + + case ${cur} in + -*) + # make options (copied from the bash-completion project) + local opts + opts="$(_parse_help "$1")" + COMPREPLY=($(compgen -W "${opts:-$(_parse_usage "$1")}" -- "$cur")) + if [[ ${COMPREPLY-} == *= ]]; then + compopt -o nospace + fi + return + ;; + *=*) + __kbuild_handle_variable "${cur}" "${srctree}" + return + ;; + KBUILD_*) + # There are many variables prefixed with 'KBUILD_'. + # Display them only when 'KBUILD_' is entered. + # shellcheck disable=SC2191 # '=' is appended for variables + keywords+=( + KBUILD_{CHECKSRC,EXTMOD,EXTMOD_OUTPUT,OUTPUT,VERBOSE,EXTRA_WARN,CLIPPY}= + KBUILD_BUILD_{USER,HOST,TIMESTAMP}= + KBUILD_MODPOST_{NOFINAL,WARN}= + KBUILD_{ABS_SRCTREE,EXTRA_SYMBOLS,KCONFIG}= + ) + ;; + KCONFIG_*) + # There are many variables prefixed with 'KCONFIG_'. + # Display them only when 'KCONFIG_' is entered. + # shellcheck disable=SC2191 # '=' is appended for variables + keywords+=( + KCONFIG_{CONFIG,ALLCONFIG,NOSILENTUPDATE,OVERWRITECONFIG}= + KCONFIG_{SEED,PROBABILITY}= + KCONFIG_WARN_UNKNOWN_SYMBOL= + KCONFIG_WERROR= + ) + ;; + *) + # By default, hide KBUILD_* and KCONFIG_* variables. + # Instead, display only the prefix parts. + keywords+=(KBUILD_ KCONFIG_) + ;; + esac + + if [[ ${cur} != /* && ${cur} != *//* ]]; then + local dir srcarch kbuild_file tmp + srcarch=$(__kbuild_get_srcarch "${words[@]}") + + # single build + dir=${cur} + while true; do + if [[ ${dir} == */* ]]; then + dir=${dir%/*} + else + dir=. + fi + + # Search for 'Kbuild' or 'Makefile' in the parent + # directories (may not be a direct parent) + if [[ -f ${srctree}/${dir}/Kbuild ]]; then + kbuild_file=${srctree}/${dir}/Kbuild + break + fi + if [[ -f ${srctree}/${dir}/Makefile ]]; then + kbuild_file=${srctree}/${dir}/Makefile + break + fi + + if [[ ${dir} == . ]]; then + break + fi + done + + if [[ -n ${kbuild_file} ]]; then + tmp=($(__kbuild_tmp_makefile "${kbuild_file}" | + SRCARCH=${srcarch} obj=${dir} src=${srctree}/${dir} \ + "${1}" -n -f - 2>/dev/null)) + + # Add $(obj)/ prefix + if [[ ${dir} != . ]]; then + tmp=("${tmp[@]/#/${dir}\/}") + fi + + keywords+=("${tmp[@]}") + fi + + # *_defconfig and *.config files. These might be grouped into + # subdirectories, e.g., arch/powerpc/configs/*/*_defconfig. + if [[ ${cur} == */* ]]; then + dir=${cur%/*} + else + dir=. + fi + + tmp=($(find "${srctree}/arch/${srcarch}/configs/${dir}" \ + "${srctree}/kernel/configs/${dir}" \ + -mindepth 1 -maxdepth 1 -type d -printf '%P/\n' \ + -o -printf '%P\n' 2>/dev/null)) + + if [[ ${dir} != . ]]; then + tmp=("${tmp[@]/#/${dir}\/}") + fi + + keywords+=("${tmp[@]}") + fi + + # shellcheck disable=SC2191 # '=' is appended for variables + keywords+=( + # + # variables (append =) + # + ARCH= + CROSS_COMPILE= + LLVM= + C= M= MO= O= V= W= + INSTALL{,_MOD,_HDR,_DTBS}_PATH= + KERNELRELEASE= + + # + # targets + # + all help + clean mrproper distclean + clang-{tidy,analyzer} compile_commands.json + coccicheck + dtbs{,_check,_install} dt_binding_{check,schemas} + headers{,_install} + vmlinux install + modules{,_prepare,_install,_sign} + vdso_install + tags TAGS cscope gtags + rust{available,fmt,fmtcheck} + kernel{version,release} image_name + kselftest{,-all,-install,-clean,-merge} + + # configuration + {,old,olddef,sync,def,savedef,rand,listnew,helpnew,test,tiny}config + {,build_}{menu,n,g,x}config + local{mod,yes}config + all{no,yes,mod,def}config + {yes2mod,mod2yes,mod2no}config + + # docs + {html,textinfo,info,latex,pdf,epub,xml,linkcheck,refcheck,clean}docs + + # package + {,bin,src}{rpm,deb}-pkg + {pacman,dir,tar}-pkg + tar{,gz,bz2,xz,zst}-pkg + perf-tar{,gz,bz2,xz,zst}-src-pkg + ) + + COMPREPLY=($(compgen -W "${keywords[*]}" -- "${cur}")) + + # Do not append a space for variables, subdirs, "KBUILD_", "KCONFIG_". + if [[ ${COMPREPLY-} == *[=/] || ${COMPREPLY-} =~ ^(KBUILD|KCONFIG)_$ ]]; then + compopt -o nospace + fi + +} && complete -F _make_for_kbuild make diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile index dd289a6725ac..fb8e2c38fbc7 100644 --- a/scripts/basic/Makefile +++ b/scripts/basic/Makefile @@ -14,3 +14,8 @@ cmd_create_randstruct_seed = \ $(obj)/randstruct.seed: $(gen-randstruct-seed) FORCE $(call if_changed,create_randstruct_seed) always-$(CONFIG_RANDSTRUCT) += randstruct.seed + +# integer-wrap: if the .scl file changes, we need to do a full rebuild. +$(obj)/../../include/generated/integer-wrap.h: $(srctree)/scripts/integer-wrap-ignore.scl FORCE + $(call if_changed,touch) +always-$(CONFIG_UBSAN_INTEGER_WRAP) += ../../include/generated/integer-wrap.h diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index e74a01a85070..c77dc40f7689 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -8,6 +8,7 @@ from __future__ import print_function import argparse +import json import re import sys, os import subprocess @@ -37,11 +38,17 @@ class APIElement(object): @desc: textual description of the symbol @ret: (optional) description of any associated return value """ - def __init__(self, proto='', desc='', ret='', attrs=[]): + def __init__(self, proto='', desc='', ret=''): self.proto = proto self.desc = desc self.ret = ret - self.attrs = attrs + + def to_dict(self): + return { + 'proto': self.proto, + 'desc': self.desc, + 'ret': self.ret + } class Helper(APIElement): @@ -51,8 +58,9 @@ class Helper(APIElement): @desc: textual description of the helper function @ret: description of the return value of the helper function """ - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) + def __init__(self, proto='', desc='', ret='', attrs=[]): + super().__init__(proto, desc, ret) + self.attrs = attrs self.enum_val = None def proto_break_down(self): @@ -81,6 +89,12 @@ class Helper(APIElement): return res + def to_dict(self): + d = super().to_dict() + d["attrs"] = self.attrs + d.update(self.proto_break_down()) + return d + ATTRS = { '__bpf_fastcall': 'bpf_fastcall' @@ -675,7 +689,7 @@ COMMANDS self.print_elem(command) -class PrinterHelpers(Printer): +class PrinterHelpersHeader(Printer): """ A printer for dumping collected information about helpers as C header to be included from BPF program. @@ -896,6 +910,43 @@ class PrinterHelpers(Printer): print(') = (void *) %d;' % helper.enum_val) print('') + +class PrinterHelpersJSON(Printer): + """ + A printer for dumping collected information about helpers as a JSON file. + @parser: A HeaderParser with Helper objects + """ + + def __init__(self, parser): + self.elements = parser.helpers + self.elem_number_check( + parser.desc_unique_helpers, + parser.define_unique_helpers, + "helper", + "___BPF_FUNC_MAPPER", + ) + + def print_all(self): + helper_dicts = [helper.to_dict() for helper in self.elements] + out_dict = {'helpers': helper_dicts} + print(json.dumps(out_dict, indent=4)) + + +class PrinterSyscallJSON(Printer): + """ + A printer for dumping collected syscall information as a JSON file. + @parser: A HeaderParser with APIElement objects + """ + + def __init__(self, parser): + self.elements = parser.commands + self.elem_number_check(parser.desc_syscalls, parser.enum_syscalls, 'syscall', 'bpf_cmd') + + def print_all(self): + syscall_dicts = [syscall.to_dict() for syscall in self.elements] + out_dict = {'syscall': syscall_dicts} + print(json.dumps(out_dict, indent=4)) + ############################################################################### # If script is launched from scripts/ from kernel tree and can access @@ -905,9 +956,17 @@ script = os.path.abspath(sys.argv[0]) linuxRoot = os.path.dirname(os.path.dirname(script)) bpfh = os.path.join(linuxRoot, 'include/uapi/linux/bpf.h') +# target -> output format -> printer printers = { - 'helpers': PrinterHelpersRST, - 'syscall': PrinterSyscallRST, + 'helpers': { + 'rst': PrinterHelpersRST, + 'json': PrinterHelpersJSON, + 'header': PrinterHelpersHeader, + }, + 'syscall': { + 'rst': PrinterSyscallRST, + 'json': PrinterSyscallJSON + }, } argParser = argparse.ArgumentParser(description=""" @@ -917,6 +976,8 @@ rst2man utility. """) argParser.add_argument('--header', action='store_true', help='generate C header file') +argParser.add_argument('--json', action='store_true', + help='generate a JSON') if (os.path.isfile(bpfh)): argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h', default=bpfh) @@ -924,17 +985,35 @@ else: argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h') argParser.add_argument('target', nargs='?', default='helpers', choices=printers.keys(), help='eBPF API target') -args = argParser.parse_args() - -# Parse file. -headerParser = HeaderParser(args.filename) -headerParser.run() -# Print formatted output to standard output. -if args.header: - if args.target != 'helpers': - raise NotImplementedError('Only helpers header generation is supported') - printer = PrinterHelpers(headerParser) -else: - printer = printers[args.target](headerParser) -printer.print_all() +def error_die(message: str): + argParser.print_usage(file=sys.stderr) + print('Error: {}'.format(message), file=sys.stderr) + exit(1) + +def parse_and_dump(): + args = argParser.parse_args() + + # Parse file. + headerParser = HeaderParser(args.filename) + headerParser.run() + + if args.header and args.json: + error_die('Use either --header or --json, not both') + + output_format = 'rst' + if args.header: + output_format = 'header' + elif args.json: + output_format = 'json' + + try: + printer = printers[args.target][output_format](headerParser) + # Print formatted output to standard output. + printer.print_all() + except KeyError: + error_die('Unsupported target/format combination: "{}", "{}"' + .format(args.target, output_format)) + +if __name__ == "__main__": + parse_and_dump() diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 9eed3683ad76..664f7b7a622c 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -113,7 +113,8 @@ Options: --max-line-length=n set the maximum line length, (default $max_line_length) if exceeded, warn on patches requires --strict for use with --file - --min-conf-desc-length=n set the min description length, if shorter, warn + --min-conf-desc-length=n set the minimum description length for config symbols + in lines, if shorter, warn (default $min_conf_desc_length) --tab-size=n set the number of spaces for tab (default $tabsize) --root=PATH PATH to the kernel tree root --no-summary suppress the per-file summary @@ -150,6 +151,24 @@ EOM exit($exitcode); } +my $DO_WHILE_0_ADVICE = q{ + do {} while (0) advice is over-stated in a few situations: + + The more obvious case is macros, like MODULE_PARM_DESC, invoked at + file-scope, where C disallows code (it must be in functions). See + $exceptions if you have one to add by name. + + More troublesome is declarative macros used at top of new scope, + like DECLARE_PER_CPU. These might just compile with a do-while-0 + wrapper, but would be incorrect. Most of these are handled by + detecting struct,union,etc declaration primitives in $exceptions. + + Theres also macros called inside an if (block), which "return" an + expression. These cannot do-while, and need a ({}) wrapper. + + Enjoy this qualification while we work to improve our heuristics. +}; + sub uniq { my %seen; return grep { !$seen{$_}++ } @_; @@ -834,20 +853,12 @@ foreach my $entry (@mode_permission_funcs) { $mode_perms_search = "(?:${mode_perms_search})"; our %deprecated_apis = ( - "synchronize_rcu_bh" => "synchronize_rcu", - "synchronize_rcu_bh_expedited" => "synchronize_rcu_expedited", - "call_rcu_bh" => "call_rcu", - "rcu_barrier_bh" => "rcu_barrier", - "synchronize_sched" => "synchronize_rcu", - "synchronize_sched_expedited" => "synchronize_rcu_expedited", - "call_rcu_sched" => "call_rcu", - "rcu_barrier_sched" => "rcu_barrier", - "get_state_synchronize_sched" => "get_state_synchronize_rcu", - "cond_synchronize_sched" => "cond_synchronize_rcu", "kmap" => "kmap_local_page", "kunmap" => "kunmap_local", "kmap_atomic" => "kmap_local_page", "kunmap_atomic" => "kunmap_local", + "srcu_read_lock_lite" => "srcu_read_lock_fast", + "srcu_read_unlock_lite" => "srcu_read_unlock_fast", ); #Create a search pattern for all these strings to speed up a loop below @@ -2875,7 +2886,7 @@ sub process { if ($realfile =~ m@^include/asm/@) { ERROR("MODIFIED_INCLUDE_ASM", - "do not modify files in include/asm, change architecture specific files in include/asm-<architecture>\n" . "$here$rawline\n"); + "do not modify files in include/asm, change architecture specific files in arch/<architecture>/include/asm\n" . "$here$rawline\n"); } $found_file = 1; } @@ -3230,19 +3241,19 @@ sub process { my $tag_case = not ($tag eq "Fixes:"); my $tag_space = not ($line =~ /^fixes:? [0-9a-f]{5,40} ($balanced_parens)/i); - my $id_length = not ($orig_commit =~ /^[0-9a-f]{12}$/i); + my $id_length = not ($orig_commit =~ /^[0-9a-f]{12,40}$/i); my $id_case = not ($orig_commit !~ /[A-F]/); my $id = "0123456789ab"; my ($cid, $ctitle) = git_commit_info($orig_commit, $id, $title); - if ($ctitle ne $title || $tag_case || $tag_space || - $id_length || $id_case || !$title_has_quotes) { + if (defined($cid) && ($ctitle ne $title || $tag_case || $tag_space || $id_length || $id_case || !$title_has_quotes)) { + my $fixed = "Fixes: $cid (\"$ctitle\")"; if (WARN("BAD_FIXES_TAG", - "Please use correct Fixes: style 'Fixes: <12 chars of sha1> (\"<title line>\")' - ie: 'Fixes: $cid (\"$ctitle\")'\n" . $herecurr) && + "Please use correct Fixes: style 'Fixes: <12+ chars of sha1> (\"<title line>\")' - ie: '$fixed'\n" . $herecurr) && $fix) { - $fixed[$fixlinenr] = "Fixes: $cid (\"$ctitle\")"; + $fixed[$fixlinenr] = $fixed; } } } @@ -3655,7 +3666,7 @@ sub process { $help_length < $min_conf_desc_length) { my $stat_real = get_stat_real($linenr, $ln - 1); WARN("CONFIG_DESCRIPTION", - "please write a help paragraph that fully describes the config symbol\n" . "$here\n$stat_real\n"); + "please write a help paragraph that fully describes the config symbol with at least $min_conf_desc_length lines\n" . "$here\n$stat_real\n"); } } @@ -3699,20 +3710,6 @@ sub process { } } - if (($realfile =~ /Makefile.*/ || $realfile =~ /Kbuild.*/) && - ($line =~ /\+(EXTRA_[A-Z]+FLAGS).*/)) { - my $flag = $1; - my $replacement = { - 'EXTRA_AFLAGS' => 'asflags-y', - 'EXTRA_CFLAGS' => 'ccflags-y', - 'EXTRA_CPPFLAGS' => 'cppflags-y', - 'EXTRA_LDFLAGS' => 'ldflags-y', - }; - - WARN("DEPRECATED_VARIABLE", - "Use of $flag is deprecated, please use \`$replacement->{$flag} instead.\n" . $herecurr) if ($replacement->{$flag}); - } - # check for DT compatible documentation if (defined $root && (($realfile =~ /\.dtsi?$/ && $line =~ /^\+\s*compatible\s*=\s*\"/) || @@ -4827,7 +4824,7 @@ sub process { } # do not use BUG() or variants - if ($line =~ /\b(?!AA_|BUILD_|DCCP_|IDA_|KVM_|RWLOCK_|snd_|SPIN_)(?:[a-zA-Z_]*_)?BUG(?:_ON)?(?:_[A-Z_]+)?\s*\(/) { + if ($line =~ /\b(?!AA_|BUILD_|IDA_|KVM_|RWLOCK_|snd_|SPIN_)(?:[a-zA-Z_]*_)?BUG(?:_ON)?(?:_[A-Z_]+)?\s*\(/) { my $msg_level = \&WARN; $msg_level = \&CHK if ($file); &{$msg_level}("AVOID_BUG", @@ -5513,9 +5510,9 @@ sub process { } } -# check for unnecessary parentheses around comparisons in if uses -# when !drivers/staging or command-line uses --strict - if (($realfile !~ m@^(?:drivers/staging/)@ || $check_orig) && +# check for unnecessary parentheses around comparisons +# except in drivers/staging + if (($realfile !~ m@^(?:drivers/staging/)@) && $perl_version_ok && defined($stat) && $stat =~ /(^.\s*if\s*($balanced_parens))/) { my $if_stat = $1; @@ -5843,6 +5840,8 @@ sub process { #CamelCase if ($var !~ /^$Constant$/ && $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && +#Ignore C keywords + $var !~ /^_Generic$/ && #Ignore some autogenerated defines and enum values $var !~ /^(?:[A-Z]+_){1,5}[A-Z]{1,3}[a-z]/ && #Ignore Page<foo> variants @@ -5904,9 +5903,9 @@ sub process { } } -# multi-statement macros should be enclosed in a do while loop, grab the -# first statement and ensure its the whole macro if its not enclosed -# in a known good container +# Usually multi-statement macros should be enclosed in a do {} while +# (0) loop. Grab the first statement and ensure its the whole macro +# if its not enclosed in a known good container if ($realfile !~ m@/vmlinux.lds.h$@ && $line =~ /^.\s*\#\s*define\s*$Ident(\()?/) { my $ln = $linenr; @@ -5959,10 +5958,13 @@ sub process { my $exceptions = qr{ $Declare| + # named exceptions module_param_named| MODULE_PARM_DESC| DECLARE_PER_CPU| DEFINE_PER_CPU| + static_assert| + # declaration primitives __typeof__\(| union| struct| @@ -5997,11 +5999,11 @@ sub process { ERROR("MULTISTATEMENT_MACRO_USE_DO_WHILE", "Macros starting with if should be enclosed by a do - while loop to avoid possible if/else logic defects\n" . "$herectx"); } elsif ($dstat =~ /;/) { - ERROR("MULTISTATEMENT_MACRO_USE_DO_WHILE", - "Macros with multiple statements should be enclosed in a do - while loop\n" . "$herectx"); + WARN("MULTISTATEMENT_MACRO_USE_DO_WHILE", + "Non-declarative macros with multiple statements should be enclosed in a do - while loop\n" . "$herectx\nBUT SEE:\n$DO_WHILE_0_ADVICE"); } else { ERROR("COMPLEX_MACRO", - "Macros with complex values should be enclosed in parentheses\n" . "$herectx"); + "Macros with complex values should be enclosed in parentheses\n" . "$herectx\nBUT SEE:\n$DO_WHILE_0_ADVICE"); } } @@ -6045,7 +6047,7 @@ sub process { } # check if this is an unused argument - if ($define_stmt !~ /\b$arg\b/) { + if ($define_stmt !~ /\b$arg\b/ && $define_stmt) { WARN("MACRO_ARG_UNUSED", "Argument '$arg' is not used in function-like macro\n" . "$herectx"); } @@ -6912,7 +6914,7 @@ sub process { ($extension eq "f" && defined $qualifier && $qualifier !~ /^w/) || ($extension eq "4" && - defined $qualifier && $qualifier !~ /^cc/)) { + defined $qualifier && $qualifier !~ /^c(?:[hlbc]|hR)$/)) { $bad_specifier = $specifier; last; } diff --git a/scripts/clang-tools/gen_compile_commands.py b/scripts/clang-tools/gen_compile_commands.py index e4fb686dfaa9..96e6e46ad1a7 100755 --- a/scripts/clang-tools/gen_compile_commands.py +++ b/scripts/clang-tools/gen_compile_commands.py @@ -167,10 +167,10 @@ def process_line(root_directory, command_prefix, file_path): root_directory or file_directory. """ # The .cmd files are intended to be included directly by Make, so they - # escape the pound sign '#', either as '\#' or '$(pound)' (depending on the - # kernel version). The compile_commands.json file is not interepreted - # by Make, so this code replaces the escaped version with '#'. - prefix = command_prefix.replace(r'\#', '#').replace('$(pound)', '#') + # escape the pound sign '#' as '$(pound)'. The compile_commands.json file + # is not interepreted by Make, so this code replaces the escaped version + # with '#'. + prefix = command_prefix.replace('$(pound)', '#') # Return the canonical path, eliminating any symbolic links encountered in the path. abs_path = os.path.realpath(os.path.join(root_directory, file_path)) diff --git a/scripts/coccinelle/misc/newline_in_nl_msg.cocci b/scripts/coccinelle/misc/newline_in_nl_msg.cocci index 9baffe55d917..2814f6b205b9 100644 --- a/scripts/coccinelle/misc/newline_in_nl_msg.cocci +++ b/scripts/coccinelle/misc/newline_in_nl_msg.cocci @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /// -/// Catch strings ending in newline with GENL_SET_ERR_MSG, NL_SET_ERR_MSG, -/// NL_SET_ERR_MSG_MOD. +/// Catch strings ending in newline with (GE)NL_SET_ERR_MSG*. /// // Confidence: Very High // Copyright: (C) 2020 Intel Corporation @@ -17,7 +16,11 @@ expression e; constant m; position p; @@ - \(GENL_SET_ERR_MSG\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\)(e,m@p) + \(GENL_SET_ERR_MSG\|GENL_SET_ERR_MSG_FMT\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\| + NL_SET_ERR_MSG_FMT\|NL_SET_ERR_MSG_FMT_MOD\|NL_SET_ERR_MSG_WEAK\| + NL_SET_ERR_MSG_WEAK_MOD\|NL_SET_ERR_MSG_ATTR_POL\| + NL_SET_ERR_MSG_ATTR_POL_FMT\|NL_SET_ERR_MSG_ATTR\| + NL_SET_ERR_MSG_ATTR_FMT\)(e,m@p,...) @script:python@ m << r.m; @@ -32,7 +35,7 @@ expression r.e; constant r.m; position r.p; @@ - fname(e,m@p) + fname(e,m@p,...) //---------------------------------------------------------- // For context mode @@ -43,7 +46,7 @@ identifier r1.fname; expression r.e; constant r.m; @@ -* fname(e,m) +* fname(e,m,...) //---------------------------------------------------------- // For org mode diff --git a/scripts/coccinelle/misc/secs_to_jiffies.cocci b/scripts/coccinelle/misc/secs_to_jiffies.cocci new file mode 100644 index 000000000000..416f348174ca --- /dev/null +++ b/scripts/coccinelle/misc/secs_to_jiffies.cocci @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0-only +/// +/// Find usages of: +/// - msecs_to_jiffies(value*1000) +/// - msecs_to_jiffies(value*MSEC_PER_SEC) +/// +// Confidence: High +// Copyright: (C) 2024 Easwar Hariharan, Microsoft +// Keywords: secs, seconds, jiffies +// + +virtual patch + +@depends on patch@ constant C; @@ + +- msecs_to_jiffies(C * 1000) ++ secs_to_jiffies(C) + +@depends on patch@ constant C; @@ + +- msecs_to_jiffies(C * MSEC_PER_SEC) ++ secs_to_jiffies(C) + +@depends on patch@ expression E; @@ + +- msecs_to_jiffies(E * 1000) ++ secs_to_jiffies(E) + +@depends on patch@ expression E; @@ + +- msecs_to_jiffies(E * MSEC_PER_SEC) ++ secs_to_jiffies(E) diff --git a/scripts/config b/scripts/config index ff88e2faefd3..ea475c07de28 100755 --- a/scripts/config +++ b/scripts/config @@ -32,6 +32,7 @@ commands: Disable option directly after other option --module-after|-M beforeopt option Turn option into module directly after other option + --refresh Refresh the config using old settings commands can be repeated multiple times @@ -124,16 +125,22 @@ undef_var() { txt_delete "^# $name is not set" "$FN" } -if [ "$1" = "--file" ]; then - FN="$2" - if [ "$FN" = "" ] ; then - usage +FN=.config +CMDS=() +while [[ $# -gt 0 ]]; do + if [ "$1" = "--file" ]; then + if [ "$2" = "" ]; then + usage + fi + FN="$2" + shift 2 + else + CMDS+=("$1") + shift fi - shift 2 -else - FN=.config -fi +done +set -- "${CMDS[@]}" if [ "$1" = "" ] ; then usage fi @@ -217,9 +224,8 @@ while [ "$1" != "" ] ; do set_var "${CONFIG_}$B" "${CONFIG_}$B=m" "${CONFIG_}$A" ;; - # undocumented because it ignores --file (fixme) --refresh) - yes "" | make oldconfig + yes "" | make oldconfig KCONFIG_CONFIG=$FN ;; *) diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check index 68083f2f1122..408b1dbe7884 100755 --- a/scripts/documentation-file-ref-check +++ b/scripts/documentation-file-ref-check @@ -92,7 +92,7 @@ while (<IN>) { next if ($f =~ m,^Next/,); # Makefiles and scripts contain nasty expressions to parse docs - next if ($f =~ m/Makefile/ || $f =~ m/\.sh$/); + next if ($f =~ m/Makefile/ || $f =~ m/\.(sh|py|pl|~|rej|org|orig)$/); # It doesn't make sense to parse hidden files next if ($f =~ m#/\.#); diff --git a/scripts/extract-fwblobs b/scripts/extract-fwblobs new file mode 100755 index 000000000000..53729124e5a0 --- /dev/null +++ b/scripts/extract-fwblobs @@ -0,0 +1,30 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# ----------------------------------------------------------------------------- +# Extracts the vmlinux built-in firmware blobs - requires a non-stripped image +# ----------------------------------------------------------------------------- + +if [ -z "$1" ]; then + echo "Must provide a non-stripped vmlinux as argument" + exit 1 +fi + +read -r RD_ADDR_HEX RD_OFF_HEX <<< "$( readelf -SW "$1" |\ +grep -w rodata | awk '{print "0x"$5" 0x"$6}' )" + +FW_SYMS="$(readelf -sW "$1" |\ +awk -n '/fw_end/ { end=$2 ; print name " 0x" start " 0x" end; } { start=$2; name=$8; }')" + +while IFS= read -r entry; do + read -r FW_NAME FW_ADDR_ST_HEX FW_ADDR_END_HEX <<< "$entry" + + # Notice kernel prepends _fw_ and appends _bin to the FW name + # in rodata; hence we hereby filter that out. + FW_NAME=${FW_NAME:4:-4} + + FW_OFFSET="$(printf "%d" $((FW_ADDR_ST_HEX - RD_ADDR_HEX + RD_OFF_HEX)))" + FW_SIZE="$(printf "%d" $((FW_ADDR_END_HEX - FW_ADDR_ST_HEX)))" + + dd if="$1" of="./${FW_NAME}" bs="${FW_SIZE}" count=1 iflag=skip_bytes skip="${FW_OFFSET}" +done <<< "${FW_SYMS}" diff --git a/scripts/find-unused-docs.sh b/scripts/find-unused-docs.sh index ee6a50e33aba..d6d397fbf917 100755 --- a/scripts/find-unused-docs.sh +++ b/scripts/find-unused-docs.sh @@ -54,7 +54,7 @@ for file in `find $1 -name '*.c'`; do if [[ ${FILES_INCLUDED[$file]+_} ]]; then continue; fi - str=$(scripts/kernel-doc -export "$file" 2>/dev/null) + str=$(PYTHONDONTWRITEBYTECODE=1 scripts/kernel-doc -export "$file" 2>/dev/null) if [[ -n "$str" ]]; then echo "$file" fi diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index e383cda05367..6b34ba19358d 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -19,16 +19,6 @@ menuconfig GCC_PLUGINS if GCC_PLUGINS -config GCC_PLUGIN_SANCOV - bool - # Plugin can be removed once the kernel only supports GCC 6+ - depends on !CC_HAS_SANCOV_TRACE_PC - help - This plugin inserts a __sanitizer_cov_trace_pc() call at the start of - basic blocks. It supports all gcc versions with plugin support (from - gcc-4.5 on). It is based on the commit "Add fuzzing coverage support" - by Dmitry Vyukov <dvyukov@google.com>. - config GCC_PLUGIN_LATENT_ENTROPY bool "Generate some entropy during boot and runtime" help @@ -46,8 +36,4 @@ config GCC_PLUGIN_LATENT_ENTROPY * https://grsecurity.net/ * https://pax.grsecurity.net/ -config GCC_PLUGIN_ARM_SSP_PER_TASK - bool - depends on GCC_PLUGINS && ARM - endif diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index 320afd3cf8e8..05b14aba41ef 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -66,3 +66,7 @@ quiet_cmd_plugin_cxx_o_c = HOSTCXX $@ $(plugin-objs): $(obj)/%.o: $(src)/%.c FORCE $(call if_changed_dep,plugin_cxx_o_c) + +$(obj)/../../include/generated/gcc-plugins.h: $(plugin-single) $(plugin-multi) FORCE + $(call if_changed,touch) +always-y += ../../include/generated/gcc-plugins.h diff --git a/scripts/gcc-plugins/arm_ssp_per_task_plugin.c b/scripts/gcc-plugins/arm_ssp_per_task_plugin.c deleted file mode 100644 index 7328d037f975..000000000000 --- a/scripts/gcc-plugins/arm_ssp_per_task_plugin.c +++ /dev/null @@ -1,107 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include "gcc-common.h" - -__visible int plugin_is_GPL_compatible; - -static unsigned int canary_offset; - -static unsigned int arm_pertask_ssp_rtl_execute(void) -{ - rtx_insn *insn; - - for (insn = get_insns(); insn; insn = NEXT_INSN(insn)) { - const char *sym; - rtx body; - rtx current; - - /* - * Find a SET insn involving a SYMBOL_REF to __stack_chk_guard - */ - if (!INSN_P(insn)) - continue; - body = PATTERN(insn); - if (GET_CODE(body) != SET || - GET_CODE(SET_SRC(body)) != SYMBOL_REF) - continue; - sym = XSTR(SET_SRC(body), 0); - if (strcmp(sym, "__stack_chk_guard")) - continue; - - /* - * Replace the source of the SET insn with an expression that - * produces the address of the current task's stack canary value - */ - current = gen_reg_rtx(Pmode); - - emit_insn_before(gen_load_tp_hard(current), insn); - - SET_SRC(body) = gen_rtx_PLUS(Pmode, current, - GEN_INT(canary_offset)); - } - return 0; -} - -#define PASS_NAME arm_pertask_ssp_rtl - -#define NO_GATE -#include "gcc-generate-rtl-pass.h" - -#if BUILDING_GCC_VERSION >= 9000 -static bool no(void) -{ - return false; -} - -static void arm_pertask_ssp_start_unit(void *gcc_data, void *user_data) -{ - targetm.have_stack_protect_combined_set = no; - targetm.have_stack_protect_combined_test = no; -} -#endif - -__visible int plugin_init(struct plugin_name_args *plugin_info, - struct plugin_gcc_version *version) -{ - const char * const plugin_name = plugin_info->base_name; - const int argc = plugin_info->argc; - const struct plugin_argument *argv = plugin_info->argv; - int i; - - if (!plugin_default_version_check(version, &gcc_version)) { - error(G_("incompatible gcc/plugin versions")); - return 1; - } - - for (i = 0; i < argc; ++i) { - if (!strcmp(argv[i].key, "disable")) - return 0; - - /* all remaining options require a value */ - if (!argv[i].value) { - error(G_("no value supplied for option '-fplugin-arg-%s-%s'"), - plugin_name, argv[i].key); - return 1; - } - - if (!strcmp(argv[i].key, "offset")) { - canary_offset = atoi(argv[i].value); - continue; - } - error(G_("unknown option '-fplugin-arg-%s-%s'"), - plugin_name, argv[i].key); - return 1; - } - - PASS_INFO(arm_pertask_ssp_rtl, "expand", 1, PASS_POS_INSERT_AFTER); - - register_callback(plugin_info->base_name, PLUGIN_PASS_MANAGER_SETUP, - NULL, &arm_pertask_ssp_rtl_pass_info); - -#if BUILDING_GCC_VERSION >= 9000 - register_callback(plugin_info->base_name, PLUGIN_START_UNIT, - arm_pertask_ssp_start_unit, NULL); -#endif - - return 0; -} diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 3222c1070444..6cb6d1051815 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -3,11 +3,7 @@ #define GCC_COMMON_H_INCLUDED #include "bversion.h" -#if BUILDING_GCC_VERSION >= 6000 #include "gcc-plugin.h" -#else -#include "plugin.h" -#endif #include "plugin-version.h" #include "config.h" #include "system.h" @@ -39,9 +35,7 @@ #include "hash-map.h" -#if BUILDING_GCC_VERSION >= 7000 #include "memmodel.h" -#endif #include "emit-rtl.h" #include "debug.h" #include "target.h" @@ -74,9 +68,7 @@ #include "context.h" #include "tree-ssa-alias.h" #include "tree-ssa.h" -#if BUILDING_GCC_VERSION >= 7000 #include "tree-vrp.h" -#endif #include "tree-ssanames.h" #include "print-tree.h" #include "tree-eh.h" @@ -123,6 +115,38 @@ static inline tree build_const_char_string(int len, const char *str) return cstr; } +static inline void __add_type_attr(tree type, const char *attr, tree args) +{ + tree oldattr; + + if (type == NULL_TREE) + return; + oldattr = lookup_attribute(attr, TYPE_ATTRIBUTES(type)); + if (oldattr != NULL_TREE) { + gcc_assert(TREE_VALUE(oldattr) == args || TREE_VALUE(TREE_VALUE(oldattr)) == TREE_VALUE(args)); + return; + } + + TYPE_ATTRIBUTES(type) = copy_list(TYPE_ATTRIBUTES(type)); + TYPE_ATTRIBUTES(type) = tree_cons(get_identifier(attr), args, TYPE_ATTRIBUTES(type)); +} + +static inline void add_type_attr(tree type, const char *attr, tree args) +{ + tree main_variant = TYPE_MAIN_VARIANT(type); + + __add_type_attr(TYPE_CANONICAL(type), attr, args); + __add_type_attr(TYPE_CANONICAL(main_variant), attr, args); + __add_type_attr(main_variant, attr, args); + + for (type = TYPE_NEXT_VARIANT(main_variant); type; type = TYPE_NEXT_VARIANT(type)) { + if (!lookup_attribute(attr, TYPE_ATTRIBUTES(type))) + TYPE_ATTRIBUTES(type) = TYPE_ATTRIBUTES(main_variant); + + __add_type_attr(TYPE_CANONICAL(type), attr, args); + } +} + #define PASS_INFO(NAME, REF, ID, POS) \ struct register_pass_info NAME##_pass_info = { \ .pass = make_##NAME##_pass(), \ @@ -149,16 +173,6 @@ static inline opt_pass *get_pass_for_id(int id) return g->get_passes()->get_pass_for_id(id); } -#if BUILDING_GCC_VERSION < 6000 -/* gimple related */ -template <> -template <> -inline bool is_a_helper<const gassign *>::test(const_gimple gs) -{ - return gs->code == GIMPLE_ASSIGN; -} -#endif - #define TODO_verify_ssa TODO_verify_il #define TODO_verify_flow TODO_verify_il #define TODO_verify_stmts TODO_verify_il @@ -181,7 +195,6 @@ static inline const char *get_decl_section_name(const_tree decl) #define varpool_get_node(decl) varpool_node::get(decl) #define dump_varpool_node(file, node) (node)->dump(file) -#if BUILDING_GCC_VERSION >= 8000 #define cgraph_create_edge(caller, callee, call_stmt, count, freq) \ (caller)->create_edge((callee), (call_stmt), (count)) @@ -189,15 +202,6 @@ static inline const char *get_decl_section_name(const_tree decl) old_call_stmt, call_stmt, count, freq, reason) \ (caller)->create_edge_including_clones((callee), \ (old_call_stmt), (call_stmt), (count), (reason)) -#else -#define cgraph_create_edge(caller, callee, call_stmt, count, freq) \ - (caller)->create_edge((callee), (call_stmt), (count), (freq)) - -#define cgraph_create_edge_including_clones(caller, callee, \ - old_call_stmt, call_stmt, count, freq, reason) \ - (caller)->create_edge_including_clones((callee), \ - (old_call_stmt), (call_stmt), (count), (freq), (reason)) -#endif typedef struct cgraph_node *cgraph_node_ptr; typedef struct cgraph_edge *cgraph_edge_p; @@ -293,14 +297,12 @@ static inline void cgraph_call_edge_duplication_hooks(cgraph_edge *cs1, cgraph_e symtab->call_edge_duplication_hooks(cs1, cs2); } -#if BUILDING_GCC_VERSION >= 6000 typedef gimple *gimple_ptr; typedef const gimple *const_gimple_ptr; #define gimple gimple_ptr #define const_gimple const_gimple_ptr #undef CONST_CAST_GIMPLE #define CONST_CAST_GIMPLE(X) CONST_CAST(gimple, (X)) -#endif /* gimple related */ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree lhs, tree op1, tree op2 MEM_STAT_DECL) @@ -400,15 +402,7 @@ static inline void ipa_remove_stmt_references(symtab_node *referring_node, gimpl referring_node->remove_stmt_references(stmt); } -#if BUILDING_GCC_VERSION < 6000 -#define get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, preversep, pvolatilep, keep_aligning) \ - get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, pvolatilep, keep_aligning) -#define gen_rtx_set(ARG0, ARG1) gen_rtx_SET(VOIDmode, (ARG0), (ARG1)) -#endif - -#if BUILDING_GCC_VERSION >= 6000 #define gen_rtx_set(ARG0, ARG1) gen_rtx_SET((ARG0), (ARG1)) -#endif #ifdef __cplusplus static inline void debug_tree(const_tree t) @@ -425,15 +419,8 @@ static inline void debug_gimple_stmt(const_gimple s) #define debug_gimple_stmt(s) debug_gimple_stmt(CONST_CAST_GIMPLE(s)) #endif -#if BUILDING_GCC_VERSION >= 7000 #define get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, preversep, pvolatilep, keep_aligning) \ get_inner_reference(exp, pbitsize, pbitpos, poffset, pmode, punsignedp, preversep, pvolatilep) -#endif - -#if BUILDING_GCC_VERSION < 7000 -#define SET_DECL_ALIGN(decl, align) DECL_ALIGN(decl) = (align) -#define SET_DECL_MODE(decl, mode) DECL_MODE(decl) = (mode) -#endif #if BUILDING_GCC_VERSION >= 14000 #define last_stmt(x) last_nondebug_stmt(x) diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c index 5694df3da2e9..ff65a4f87f24 100644 --- a/scripts/gcc-plugins/randomize_layout_plugin.c +++ b/scripts/gcc-plugins/randomize_layout_plugin.c @@ -73,6 +73,9 @@ static tree handle_randomize_layout_attr(tree *node, tree name, tree args, int f if (TYPE_P(*node)) { type = *node; + } else if (TREE_CODE(*node) == FIELD_DECL) { + *no_add_attrs = false; + return NULL_TREE; } else { gcc_assert(TREE_CODE(*node) == TYPE_DECL); type = TREE_TYPE(*node); @@ -344,35 +347,18 @@ static int relayout_struct(tree type) shuffle(type, (tree *)newtree, shuffle_length); - /* - * set up a bogus anonymous struct field designed to error out on unnamed struct initializers - * as gcc provides no other way to detect such code - */ - list = make_node(FIELD_DECL); - TREE_CHAIN(list) = newtree[0]; - TREE_TYPE(list) = void_type_node; - DECL_SIZE(list) = bitsize_zero_node; - DECL_NONADDRESSABLE_P(list) = 1; - DECL_FIELD_BIT_OFFSET(list) = bitsize_zero_node; - DECL_SIZE_UNIT(list) = size_zero_node; - DECL_FIELD_OFFSET(list) = size_zero_node; - DECL_CONTEXT(list) = type; - // to satisfy the constify plugin - TREE_READONLY(list) = 1; - for (i = 0; i < num_fields - 1; i++) TREE_CHAIN(newtree[i]) = newtree[i+1]; TREE_CHAIN(newtree[num_fields - 1]) = NULL_TREE; + add_type_attr(type, "randomize_performed", NULL_TREE); + add_type_attr(type, "designated_init", NULL_TREE); + if (has_flexarray) + add_type_attr(type, "has_flexarray", NULL_TREE); + main_variant = TYPE_MAIN_VARIANT(type); - for (variant = main_variant; variant; variant = TYPE_NEXT_VARIANT(variant)) { - TYPE_FIELDS(variant) = list; - TYPE_ATTRIBUTES(variant) = copy_list(TYPE_ATTRIBUTES(variant)); - TYPE_ATTRIBUTES(variant) = tree_cons(get_identifier("randomize_performed"), NULL_TREE, TYPE_ATTRIBUTES(variant)); - TYPE_ATTRIBUTES(variant) = tree_cons(get_identifier("designated_init"), NULL_TREE, TYPE_ATTRIBUTES(variant)); - if (has_flexarray) - TYPE_ATTRIBUTES(type) = tree_cons(get_identifier("has_flexarray"), NULL_TREE, TYPE_ATTRIBUTES(type)); - } + for (variant = main_variant; variant; variant = TYPE_NEXT_VARIANT(variant)) + TYPE_FIELDS(variant) = newtree[0]; /* * force a re-layout of the main variant @@ -440,10 +426,8 @@ static void randomize_type(tree type) if (lookup_attribute("randomize_layout", TYPE_ATTRIBUTES(TYPE_MAIN_VARIANT(type))) || is_pure_ops_struct(type)) relayout_struct(type); - for (variant = TYPE_MAIN_VARIANT(type); variant; variant = TYPE_NEXT_VARIANT(variant)) { - TYPE_ATTRIBUTES(type) = copy_list(TYPE_ATTRIBUTES(type)); - TYPE_ATTRIBUTES(type) = tree_cons(get_identifier("randomize_considered"), NULL_TREE, TYPE_ATTRIBUTES(type)); - } + add_type_attr(type, "randomize_considered", NULL_TREE); + #ifdef __DEBUG_PLUGIN fprintf(stderr, "Marking randomize_considered on struct %s\n", ORIG_TYPE_NAME(type)); #ifdef __DEBUG_VERBOSE diff --git a/scripts/gcc-plugins/sancov_plugin.c b/scripts/gcc-plugins/sancov_plugin.c deleted file mode 100644 index b76cb9c42cec..000000000000 --- a/scripts/gcc-plugins/sancov_plugin.c +++ /dev/null @@ -1,134 +0,0 @@ -/* - * Copyright 2011-2016 by Emese Revfy <re.emese@gmail.com> - * Licensed under the GPL v2, or (at your option) v3 - * - * Homepage: - * https://github.com/ephox-gcc-plugins/sancov - * - * This plugin inserts a __sanitizer_cov_trace_pc() call at the start of basic blocks. - * It supports all gcc versions with plugin support (from gcc-4.5 on). - * It is based on the commit "Add fuzzing coverage support" by Dmitry Vyukov <dvyukov@google.com>. - * - * You can read about it more here: - * https://gcc.gnu.org/viewcvs/gcc?limit_changes=0&view=revision&revision=231296 - * https://lwn.net/Articles/674854/ - * https://github.com/google/syzkaller - * https://lwn.net/Articles/677764/ - * - * Usage: - * make run - */ - -#include "gcc-common.h" - -__visible int plugin_is_GPL_compatible; - -tree sancov_fndecl; - -static struct plugin_info sancov_plugin_info = { - .version = PLUGIN_VERSION, - .help = "sancov plugin\n", -}; - -static unsigned int sancov_execute(void) -{ - basic_block bb; - - /* Remove this line when this plugin and kcov will be in the kernel. - if (!strcmp(DECL_NAME_POINTER(current_function_decl), DECL_NAME_POINTER(sancov_fndecl))) - return 0; - */ - - FOR_EACH_BB_FN(bb, cfun) { - const_gimple stmt; - gcall *gcall; - gimple_stmt_iterator gsi = gsi_after_labels(bb); - - if (gsi_end_p(gsi)) - continue; - - stmt = gsi_stmt(gsi); - gcall = as_a_gcall(gimple_build_call(sancov_fndecl, 0)); - gimple_set_location(gcall, gimple_location(stmt)); - gsi_insert_before(&gsi, gcall, GSI_SAME_STMT); - } - return 0; -} - -#define PASS_NAME sancov - -#define NO_GATE -#define TODO_FLAGS_FINISH TODO_dump_func | TODO_verify_stmts | TODO_update_ssa_no_phi | TODO_verify_flow - -#include "gcc-generate-gimple-pass.h" - -static void sancov_start_unit(void __unused *gcc_data, void __unused *user_data) -{ - tree leaf_attr, nothrow_attr; - tree BT_FN_VOID = build_function_type_list(void_type_node, NULL_TREE); - - sancov_fndecl = build_fn_decl("__sanitizer_cov_trace_pc", BT_FN_VOID); - - DECL_ASSEMBLER_NAME(sancov_fndecl); - TREE_PUBLIC(sancov_fndecl) = 1; - DECL_EXTERNAL(sancov_fndecl) = 1; - DECL_ARTIFICIAL(sancov_fndecl) = 1; - DECL_PRESERVE_P(sancov_fndecl) = 1; - DECL_UNINLINABLE(sancov_fndecl) = 1; - TREE_USED(sancov_fndecl) = 1; - - nothrow_attr = tree_cons(get_identifier("nothrow"), NULL, NULL); - decl_attributes(&sancov_fndecl, nothrow_attr, 0); - gcc_assert(TREE_NOTHROW(sancov_fndecl)); - leaf_attr = tree_cons(get_identifier("leaf"), NULL, NULL); - decl_attributes(&sancov_fndecl, leaf_attr, 0); -} - -__visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version) -{ - int i; - const char * const plugin_name = plugin_info->base_name; - const int argc = plugin_info->argc; - const struct plugin_argument * const argv = plugin_info->argv; - bool enable = true; - - static const struct ggc_root_tab gt_ggc_r_gt_sancov[] = { - { - .base = &sancov_fndecl, - .nelt = 1, - .stride = sizeof(sancov_fndecl), - .cb = >_ggc_mx_tree_node, - .pchw = >_pch_nx_tree_node - }, - LAST_GGC_ROOT_TAB - }; - - /* BBs can be split afterwards?? */ - PASS_INFO(sancov, "asan", 0, PASS_POS_INSERT_BEFORE); - - if (!plugin_default_version_check(version, &gcc_version)) { - error(G_("incompatible gcc/plugin versions")); - return 1; - } - - for (i = 0; i < argc; ++i) { - if (!strcmp(argv[i].key, "no-sancov")) { - enable = false; - continue; - } - error(G_("unknown option '-fplugin-arg-%s-%s'"), plugin_name, argv[i].key); - } - - register_callback(plugin_name, PLUGIN_INFO, NULL, &sancov_plugin_info); - - if (!enable) - return 0; - -#if BUILDING_GCC_VERSION < 6000 - register_callback(plugin_name, PLUGIN_START_UNIT, &sancov_start_unit, NULL); - register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, (void *)>_ggc_r_gt_sancov); - register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &sancov_pass_info); -#endif - - return 0; -} diff --git a/scripts/gcc-plugins/structleak_plugin.c b/scripts/gcc-plugins/structleak_plugin.c deleted file mode 100644 index d8c744233832..000000000000 --- a/scripts/gcc-plugins/structleak_plugin.c +++ /dev/null @@ -1,257 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright 2013-2017 by PaX Team <pageexec@freemail.hu> - * - * Note: the choice of the license means that the compilation process is - * NOT 'eligible' as defined by gcc's library exception to the GPL v3, - * but for the kernel it doesn't matter since it doesn't link against - * any of the gcc libraries - * - * gcc plugin to forcibly initialize certain local variables that could - * otherwise leak kernel stack to userland if they aren't properly initialized - * by later code - * - * Homepage: https://pax.grsecurity.net/ - * - * Options: - * -fplugin-arg-structleak_plugin-disable - * -fplugin-arg-structleak_plugin-verbose - * -fplugin-arg-structleak_plugin-byref - * -fplugin-arg-structleak_plugin-byref-all - * - * Usage: - * $ # for 4.5/4.6/C based 4.7 - * $ gcc -I`gcc -print-file-name=plugin`/include -I`gcc -print-file-name=plugin`/include/c-family -fPIC -shared -O2 -o structleak_plugin.so structleak_plugin.c - * $ # for C++ based 4.7/4.8+ - * $ g++ -I`g++ -print-file-name=plugin`/include -I`g++ -print-file-name=plugin`/include/c-family -fPIC -shared -O2 -o structleak_plugin.so structleak_plugin.c - * $ gcc -fplugin=./structleak_plugin.so test.c -O2 - * - * TODO: eliminate redundant initializers - */ - -#include "gcc-common.h" - -/* unused C type flag in all versions 4.5-6 */ -#define TYPE_USERSPACE(TYPE) TYPE_LANG_FLAG_5(TYPE) - -__visible int plugin_is_GPL_compatible; - -static struct plugin_info structleak_plugin_info = { - .version = PLUGIN_VERSION, - .help = "disable\tdo not activate plugin\n" - "byref\tinit structs passed by reference\n" - "byref-all\tinit anything passed by reference\n" - "verbose\tprint all initialized variables\n", -}; - -#define BYREF_STRUCT 1 -#define BYREF_ALL 2 - -static bool verbose; -static int byref; - -static tree handle_user_attribute(tree *node, tree name, tree args, int flags, bool *no_add_attrs) -{ - *no_add_attrs = true; - - /* check for types? for now accept everything linux has to offer */ - if (TREE_CODE(*node) != FIELD_DECL) - return NULL_TREE; - - *no_add_attrs = false; - return NULL_TREE; -} - -static struct attribute_spec user_attr = { }; - -static void register_attributes(void *event_data, void *data) -{ - user_attr.name = "user"; - user_attr.handler = handle_user_attribute; - user_attr.affects_type_identity = true; - - register_attribute(&user_attr); -} - -static tree get_field_type(tree field) -{ - return strip_array_types(TREE_TYPE(field)); -} - -static bool is_userspace_type(tree type) -{ - tree field; - - for (field = TYPE_FIELDS(type); field; field = TREE_CHAIN(field)) { - tree fieldtype = get_field_type(field); - enum tree_code code = TREE_CODE(fieldtype); - - if (code == RECORD_TYPE || code == UNION_TYPE) - if (is_userspace_type(fieldtype)) - return true; - - if (lookup_attribute("user", DECL_ATTRIBUTES(field))) - return true; - } - return false; -} - -static void finish_type(void *event_data, void *data) -{ - tree type = (tree)event_data; - - if (type == NULL_TREE || type == error_mark_node) - return; - - if (TREE_CODE(type) == ENUMERAL_TYPE) - return; - - if (TYPE_USERSPACE(type)) - return; - - if (is_userspace_type(type)) - TYPE_USERSPACE(type) = 1; -} - -static void initialize(tree var) -{ - basic_block bb; - gimple_stmt_iterator gsi; - tree initializer; - gimple init_stmt; - tree type; - - /* this is the original entry bb before the forced split */ - bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun)); - - /* first check if variable is already initialized, warn otherwise */ - for (gsi = gsi_start_bb(bb); !gsi_end_p(gsi); gsi_next(&gsi)) { - gimple stmt = gsi_stmt(gsi); - tree rhs1; - - /* we're looking for an assignment of a single rhs... */ - if (!gimple_assign_single_p(stmt)) - continue; - rhs1 = gimple_assign_rhs1(stmt); - /* ... of a non-clobbering expression... */ - if (TREE_CLOBBER_P(rhs1)) - continue; - /* ... to our variable... */ - if (gimple_get_lhs(stmt) != var) - continue; - /* if it's an initializer then we're good */ - if (TREE_CODE(rhs1) == CONSTRUCTOR) - return; - } - - /* these aren't the 0days you're looking for */ - if (verbose) - inform(DECL_SOURCE_LOCATION(var), - "%s variable will be forcibly initialized", - (byref && TREE_ADDRESSABLE(var)) ? "byref" - : "userspace"); - - /* build the initializer expression */ - type = TREE_TYPE(var); - if (AGGREGATE_TYPE_P(type)) - initializer = build_constructor(type, NULL); - else - initializer = fold_convert(type, integer_zero_node); - - /* build the initializer stmt */ - init_stmt = gimple_build_assign(var, initializer); - gsi = gsi_after_labels(single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun))); - gsi_insert_before(&gsi, init_stmt, GSI_NEW_STMT); - update_stmt(init_stmt); -} - -static unsigned int structleak_execute(void) -{ - basic_block bb; - tree var; - unsigned int i; - - /* split the first bb where we can put the forced initializers */ - gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun))); - bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun)); - if (!single_pred_p(bb)) { - split_edge(single_succ_edge(ENTRY_BLOCK_PTR_FOR_FN(cfun))); - gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun))); - } - - /* enumerate all local variables and forcibly initialize our targets */ - FOR_EACH_LOCAL_DECL(cfun, i, var) { - tree type = TREE_TYPE(var); - - gcc_assert(DECL_P(var)); - if (!auto_var_in_fn_p(var, current_function_decl)) - continue; - - /* only care about structure types unless byref-all */ - if (byref != BYREF_ALL && TREE_CODE(type) != RECORD_TYPE && TREE_CODE(type) != UNION_TYPE) - continue; - - /* if the type is of interest, examine the variable */ - if (TYPE_USERSPACE(type) || - (byref && TREE_ADDRESSABLE(var))) - initialize(var); - } - - return 0; -} - -#define PASS_NAME structleak -#define NO_GATE -#define PROPERTIES_REQUIRED PROP_cfg -#define TODO_FLAGS_FINISH TODO_verify_il | TODO_verify_ssa | TODO_verify_stmts | TODO_dump_func | TODO_remove_unused_locals | TODO_update_ssa | TODO_ggc_collect | TODO_verify_flow -#include "gcc-generate-gimple-pass.h" - -__visible int plugin_init(struct plugin_name_args *plugin_info, struct plugin_gcc_version *version) -{ - int i; - const char * const plugin_name = plugin_info->base_name; - const int argc = plugin_info->argc; - const struct plugin_argument * const argv = plugin_info->argv; - bool enable = true; - - PASS_INFO(structleak, "early_optimizations", 1, PASS_POS_INSERT_BEFORE); - - if (!plugin_default_version_check(version, &gcc_version)) { - error(G_("incompatible gcc/plugin versions")); - return 1; - } - - if (strncmp(lang_hooks.name, "GNU C", 5) && !strncmp(lang_hooks.name, "GNU C+", 6)) { - inform(UNKNOWN_LOCATION, G_("%s supports C only, not %s"), plugin_name, lang_hooks.name); - enable = false; - } - - for (i = 0; i < argc; ++i) { - if (!strcmp(argv[i].key, "disable")) { - enable = false; - continue; - } - if (!strcmp(argv[i].key, "verbose")) { - verbose = true; - continue; - } - if (!strcmp(argv[i].key, "byref")) { - byref = BYREF_STRUCT; - continue; - } - if (!strcmp(argv[i].key, "byref-all")) { - byref = BYREF_ALL; - continue; - } - error(G_("unknown option '-fplugin-arg-%s-%s'"), plugin_name, argv[i].key); - } - - register_callback(plugin_name, PLUGIN_INFO, NULL, &structleak_plugin_info); - if (enable) { - register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, &structleak_pass_info); - register_callback(plugin_name, PLUGIN_FINISH_TYPE, finish_type, NULL); - } - register_callback(plugin_name, PLUGIN_ATTRIBUTES, register_attributes, NULL); - - return 0; -} diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh deleted file mode 100755 index 9459ca4f0f11..000000000000 --- a/scripts/gcc-x86_32-has-stack-protector.sh +++ /dev/null @@ -1,8 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -# This requires GCC 8.1 or better. Specifically, we require -# -mstack-protector-guard-reg, added by -# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708 - -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs" diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh deleted file mode 100755 index f680bb01aeeb..000000000000 --- a/scripts/gcc-x86_64-has-stack-protector.sh +++ /dev/null @@ -1,4 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs" diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 2f11c4f9c345..6edf4ef61636 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -46,7 +46,7 @@ def per_cpu(var_ptr, cpu): # !CONFIG_SMP case offset = 0 pointer = var_ptr.cast(utils.get_long_type()) + offset - return pointer.cast(var_ptr.type).dereference() + return pointer.cast(var_ptr.type) cpu_mask = {} @@ -141,7 +141,7 @@ LxCpus() class PerCpu(gdb.Function): """Return per-cpu variable. -$lx_per_cpu("VAR"[, CPU]): Return the per-cpu variable called VAR for the +$lx_per_cpu(VAR[, CPU]): Return the per-cpu variable called VAR for the given CPU number. If CPU is omitted, the CPU of the current context is used. Note that VAR has to be quoted as string.""" @@ -149,11 +149,29 @@ Note that VAR has to be quoted as string.""" super(PerCpu, self).__init__("lx_per_cpu") def invoke(self, var, cpu=-1): - return per_cpu(var.address, cpu) + return per_cpu(var.address, cpu).dereference() PerCpu() + +class PerCpuPtr(gdb.Function): + """Return per-cpu pointer. + +$lx_per_cpu_ptr(VAR[, CPU]): Return the per-cpu pointer called VAR for the +given CPU number. If CPU is omitted, the CPU of the current context is used. +Note that VAR has to be quoted as string.""" + + def __init__(self): + super(PerCpuPtr, self).__init__("lx_per_cpu_ptr") + + def invoke(self, var, cpu=-1): + return per_cpu(var, cpu) + + +PerCpuPtr() + + def get_current_task(cpu): task_ptr_type = task_type.get_type().pointer() @@ -164,10 +182,10 @@ def get_current_task(cpu): var_ptr = gdb.parse_and_eval("(struct task_struct *)cpu_tasks[0].task") return var_ptr.dereference() else: - var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") + var_ptr = gdb.parse_and_eval("¤t_task") return per_cpu(var_ptr, cpu).dereference() elif utils.is_target_arch("aarch64"): - current_task_addr = gdb.parse_and_eval("$SP_EL0") + current_task_addr = gdb.parse_and_eval("(unsigned long)$SP_EL0") if (current_task_addr >> 63) != 0: current_task = current_task_addr.cast(task_ptr_type) return current_task.dereference() diff --git a/scripts/gdb/linux/pgtable.py b/scripts/gdb/linux/pgtable.py index 30d837f3dfae..09aac2421fb8 100644 --- a/scripts/gdb/linux/pgtable.py +++ b/scripts/gdb/linux/pgtable.py @@ -29,11 +29,9 @@ def page_mask(level=1): raise Exception(f'Unknown page level: {level}') -#page_offset_base in case CONFIG_DYNAMIC_MEMORY_LAYOUT is disabled -POB_NO_DYNAMIC_MEM_LAYOUT = '0xffff888000000000' def _page_offset_base(): pob_symbol = gdb.lookup_global_symbol('page_offset_base') - pob = pob_symbol.name if pob_symbol else POB_NO_DYNAMIC_MEM_LAYOUT + pob = pob_symbol.name return gdb.parse_and_eval(pob) diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index f6c1b063775a..2332bd8eddf1 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -14,7 +14,9 @@ import gdb import os import re +import struct +from itertools import count from linux import modules, utils, constants @@ -36,23 +38,52 @@ if hasattr(gdb, 'Breakpoint'): # Disable pagination while reporting symbol (re-)loading. # The console input is blocked in this context so that we would # get stuck waiting for the user to acknowledge paged output. - show_pagination = gdb.execute("show pagination", to_string=True) - pagination = show_pagination.endswith("on.\n") - gdb.execute("set pagination off") - - if module_name in cmd.loaded_modules: - gdb.write("refreshing all symbols to reload module " - "'{0}'\n".format(module_name)) - cmd.load_all_symbols() - else: - cmd.load_module_symbols(module) - - # restore pagination state - gdb.execute("set pagination %s" % ("on" if pagination else "off")) + with utils.pagination_off(): + if module_name in cmd.loaded_modules: + gdb.write("refreshing all symbols to reload module " + "'{0}'\n".format(module_name)) + cmd.load_all_symbols() + else: + cmd.load_module_symbols(module) return False +def get_vmcore_s390(): + with utils.qemu_phy_mem_mode(): + vmcore_info = 0x0e0c + paddr_vmcoreinfo_note = gdb.parse_and_eval("*(unsigned long long *)" + + hex(vmcore_info)) + if paddr_vmcoreinfo_note == 0 or paddr_vmcoreinfo_note & 1: + # In the early boot case, extract vm_layout.kaslr_offset from the + # vmlinux image in physical memory. + if paddr_vmcoreinfo_note == 0: + kaslr_offset_phys = 0 + else: + kaslr_offset_phys = paddr_vmcoreinfo_note - 1 + with utils.pagination_off(): + gdb.execute("symbol-file {0} -o {1}".format( + utils.get_vmlinux(), hex(kaslr_offset_phys))) + kaslr_offset = gdb.parse_and_eval("vm_layout.kaslr_offset") + return "KERNELOFFSET=" + hex(kaslr_offset)[2:] + inferior = gdb.selected_inferior() + elf_note = inferior.read_memory(paddr_vmcoreinfo_note, 12) + n_namesz, n_descsz, n_type = struct.unpack(">III", elf_note) + desc_paddr = paddr_vmcoreinfo_note + len(elf_note) + n_namesz + 1 + return gdb.parse_and_eval("(char *)" + hex(desc_paddr)).string() + + +def get_kerneloffset(): + if utils.is_target_arch('s390'): + try: + vmcore_str = get_vmcore_s390() + except gdb.error as e: + gdb.write("{}\n".format(e)) + return None + return utils.parse_vmcore(vmcore_str).kerneloffset + return None + + class LxSymbols(gdb.Command): """(Re-)load symbols of Linux kernel and currently loaded modules. @@ -95,10 +126,14 @@ lx-symbols command.""" except gdb.error: return str(module_addr) - attrs = sect_attrs['attrs'] - section_name_to_address = { - attrs[n]['battr']['attr']['name'].string(): attrs[n]['address'] - for n in range(int(sect_attrs['nsections']))} + section_name_to_address = {} + for i in count(): + # this is a NULL terminated array + if sect_attrs['grp']['bin_attrs'][i] == 0x0: + break + + attr = sect_attrs['grp']['bin_attrs'][i].dereference() + section_name_to_address[attr['attr']['name'].string()] = attr['private'] textaddr = section_name_to_address.get(".text", module_addr) args = [] @@ -149,13 +184,14 @@ lx-symbols command.""" saved_states.append({'breakpoint': bp, 'enabled': bp.enabled}) # drop all current symbols and reload vmlinux - orig_vmlinux = 'vmlinux' - for obj in gdb.objfiles(): - if (obj.filename.endswith('vmlinux') or - obj.filename.endswith('vmlinux.debug')): - orig_vmlinux = obj.filename + orig_vmlinux = utils.get_vmlinux() gdb.execute("symbol-file", to_string=True) - gdb.execute("symbol-file {0}".format(orig_vmlinux)) + kerneloffset = get_kerneloffset() + if kerneloffset is None: + offset_arg = "" + else: + offset_arg = " -o " + hex(kerneloffset) + gdb.execute("symbol-file {0}{1}".format(orig_vmlinux, offset_arg)) self.loaded_modules = [] module_list = modules.module_list() diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index 245ab297ea84..e11f6f67961a 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -11,6 +11,11 @@ # This work is licensed under the terms of the GNU GPL version 2. # +import contextlib +import dataclasses +import re +import typing + import gdb @@ -195,7 +200,7 @@ def get_gdbserver_type(): def probe_kgdb(): try: - thread_info = gdb.execute("info thread 2", to_string=True) + thread_info = gdb.execute("info thread 1", to_string=True) return "shadowCPU" in thread_info except gdb.error: return False @@ -216,3 +221,53 @@ def gdb_eval_or_none(expresssion): return gdb.parse_and_eval(expresssion) except gdb.error: return None + + +@contextlib.contextmanager +def qemu_phy_mem_mode(): + connection = gdb.selected_inferior().connection + orig = connection.send_packet("qqemu.PhyMemMode") + if orig not in b"01": + raise gdb.error("Unexpected qemu.PhyMemMode") + orig = orig.decode() + if connection.send_packet("Qqemu.PhyMemMode:1") != b"OK": + raise gdb.error("Failed to set qemu.PhyMemMode") + try: + yield + finally: + if connection.send_packet("Qqemu.PhyMemMode:" + orig) != b"OK": + raise gdb.error("Failed to restore qemu.PhyMemMode") + + +@dataclasses.dataclass +class VmCore: + kerneloffset: typing.Optional[int] + + +def parse_vmcore(s): + match = re.search(r"KERNELOFFSET=([0-9a-f]+)", s) + if match is None: + kerneloffset = None + else: + kerneloffset = int(match.group(1), 16) + return VmCore(kerneloffset=kerneloffset) + + +def get_vmlinux(): + vmlinux = 'vmlinux' + for obj in gdb.objfiles(): + if (obj.filename.endswith('vmlinux') or + obj.filename.endswith('vmlinux.debug')): + vmlinux = obj.filename + return vmlinux + + +@contextlib.contextmanager +def pagination_off(): + show_pagination = gdb.execute("show pagination", to_string=True) + pagination = show_pagination.endswith("on.\n") + gdb.execute("set pagination off") + try: + yield + finally: + gdb.execute("set pagination %s" % ("on" if pagination else "off")) diff --git a/scripts/gen-crc-consts.py b/scripts/gen-crc-consts.py new file mode 100755 index 000000000000..f9b44fc3a03f --- /dev/null +++ b/scripts/gen-crc-consts.py @@ -0,0 +1,291 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0-or-later +# +# Script that generates constants for computing the given CRC variant(s). +# +# Copyright 2025 Google LLC +# +# Author: Eric Biggers <ebiggers@google.com> + +import sys + +# XOR (add) an iterable of polynomials. +def xor(iterable): + res = 0 + for val in iterable: + res ^= val + return res + +# Multiply two polynomials. +def clmul(a, b): + return xor(a << i for i in range(b.bit_length()) if (b & (1 << i)) != 0) + +# Polynomial division floor(a / b). +def div(a, b): + q = 0 + while a.bit_length() >= b.bit_length(): + q ^= 1 << (a.bit_length() - b.bit_length()) + a ^= b << (a.bit_length() - b.bit_length()) + return q + +# Reduce the polynomial 'a' modulo the polynomial 'b'. +def reduce(a, b): + return a ^ clmul(div(a, b), b) + +# Reflect the bits of a polynomial. +def bitreflect(poly, num_bits): + assert poly.bit_length() <= num_bits + return xor(((poly >> i) & 1) << (num_bits - 1 - i) for i in range(num_bits)) + +# Format a polynomial as hex. Bit-reflect it if the CRC is lsb-first. +def fmt_poly(variant, poly, num_bits): + if variant.lsb: + poly = bitreflect(poly, num_bits) + return f'0x{poly:0{2*num_bits//8}x}' + +# Print a pair of 64-bit polynomial multipliers. They are always passed in the +# order [HI64_TERMS, LO64_TERMS] but will be printed in the appropriate order. +def print_mult_pair(variant, mults): + mults = list(mults if variant.lsb else reversed(mults)) + terms = ['HI64_TERMS', 'LO64_TERMS'] if variant.lsb else ['LO64_TERMS', 'HI64_TERMS'] + for i in range(2): + print(f'\t\t{fmt_poly(variant, mults[i]["val"], 64)},\t/* {terms[i]}: {mults[i]["desc"]} */') + +# Pretty-print a polynomial. +def pprint_poly(prefix, poly): + terms = [f'x^{i}' for i in reversed(range(poly.bit_length())) + if (poly & (1 << i)) != 0] + j = 0 + while j < len(terms): + s = prefix + terms[j] + (' +' if j < len(terms) - 1 else '') + j += 1 + while j < len(terms) and len(s) < 73: + s += ' ' + terms[j] + (' +' if j < len(terms) - 1 else '') + j += 1 + print(s) + prefix = ' * ' + (' ' * (len(prefix) - 3)) + +# Print a comment describing constants generated for the given CRC variant. +def print_header(variant, what): + print('/*') + s = f'{"least" if variant.lsb else "most"}-significant-bit-first CRC-{variant.bits}' + print(f' * {what} generated for {s} using') + pprint_poly(' * G(x) = ', variant.G) + print(' */') + +class CrcVariant: + def __init__(self, bits, generator_poly, bit_order): + self.bits = bits + if bit_order not in ['lsb', 'msb']: + raise ValueError('Invalid value for bit_order') + self.lsb = bit_order == 'lsb' + self.name = f'crc{bits}_{bit_order}_0x{generator_poly:0{(2*bits+7)//8}x}' + if self.lsb: + generator_poly = bitreflect(generator_poly, bits) + self.G = generator_poly ^ (1 << bits) + +# Generate tables for CRC computation using the "slice-by-N" method. +# N=1 corresponds to the traditional byte-at-a-time table. +def gen_slicebyN_tables(variants, n): + for v in variants: + print('') + print_header(v, f'Slice-by-{n} CRC table') + print(f'static const u{v.bits} __maybe_unused {v.name}_table[{256*n}] = {{') + s = '' + for i in range(256 * n): + # The i'th table entry is the CRC of the message consisting of byte + # i % 256 followed by i // 256 zero bytes. + poly = (bitreflect(i % 256, 8) if v.lsb else i % 256) << (v.bits + 8*(i//256)) + next_entry = fmt_poly(v, reduce(poly, v.G), v.bits) + ',' + if len(s + next_entry) > 71: + print(f'\t{s}') + s = '' + s += (' ' if s else '') + next_entry + if s: + print(f'\t{s}') + print('};') + +def print_riscv_const(v, bits_per_long, name, val, desc): + print(f'\t.{name} = {fmt_poly(v, val, bits_per_long)}, /* {desc} */') + +def do_gen_riscv_clmul_consts(v, bits_per_long): + (G, n, lsb) = (v.G, v.bits, v.lsb) + + pow_of_x = 3 * bits_per_long - (1 if lsb else 0) + print_riscv_const(v, bits_per_long, 'fold_across_2_longs_const_hi', + reduce(1 << pow_of_x, G), f'x^{pow_of_x} mod G') + pow_of_x = 2 * bits_per_long - (1 if lsb else 0) + print_riscv_const(v, bits_per_long, 'fold_across_2_longs_const_lo', + reduce(1 << pow_of_x, G), f'x^{pow_of_x} mod G') + + pow_of_x = bits_per_long - 1 + n + print_riscv_const(v, bits_per_long, 'barrett_reduction_const_1', + div(1 << pow_of_x, G), f'floor(x^{pow_of_x} / G)') + + val = G - (1 << n) + desc = f'G - x^{n}' + if lsb: + val <<= bits_per_long - n + desc = f'({desc}) * x^{bits_per_long - n}' + print_riscv_const(v, bits_per_long, 'barrett_reduction_const_2', val, desc) + +def gen_riscv_clmul_consts(variants): + print('') + print('struct crc_clmul_consts {'); + print('\tunsigned long fold_across_2_longs_const_hi;'); + print('\tunsigned long fold_across_2_longs_const_lo;'); + print('\tunsigned long barrett_reduction_const_1;'); + print('\tunsigned long barrett_reduction_const_2;'); + print('};'); + for v in variants: + print(''); + if v.bits > 32: + print_header(v, 'Constants') + print('#ifdef CONFIG_64BIT') + print(f'static const struct crc_clmul_consts {v.name}_consts __maybe_unused = {{') + do_gen_riscv_clmul_consts(v, 64) + print('};') + print('#endif') + else: + print_header(v, 'Constants') + print(f'static const struct crc_clmul_consts {v.name}_consts __maybe_unused = {{') + print('#ifdef CONFIG_64BIT') + do_gen_riscv_clmul_consts(v, 64) + print('#else') + do_gen_riscv_clmul_consts(v, 32) + print('#endif') + print('};') + +# Generate constants for carryless multiplication based CRC computation. +def gen_x86_pclmul_consts(variants): + # These are the distances, in bits, to generate folding constants for. + FOLD_DISTANCES = [2048, 1024, 512, 256, 128] + + for v in variants: + (G, n, lsb) = (v.G, v.bits, v.lsb) + print('') + print_header(v, 'CRC folding constants') + print('static const struct {') + if not lsb: + print('\tu8 bswap_mask[16];') + for i in FOLD_DISTANCES: + print(f'\tu64 fold_across_{i}_bits_consts[2];') + print('\tu8 shuf_table[48];') + print('\tu64 barrett_reduction_consts[2];') + print(f'}} {v.name}_consts ____cacheline_aligned __maybe_unused = {{') + + # Byte-reflection mask, needed for msb-first CRCs + if not lsb: + print('\t.bswap_mask = {' + ', '.join(str(i) for i in reversed(range(16))) + '},') + + # Fold constants for all distances down to 128 bits + for i in FOLD_DISTANCES: + print(f'\t.fold_across_{i}_bits_consts = {{') + # Given 64x64 => 128 bit carryless multiplication instructions, two + # 64-bit fold constants are needed per "fold distance" i: one for + # HI64_TERMS that is basically x^(i+64) mod G and one for LO64_TERMS + # that is basically x^i mod G. The exact values however undergo a + # couple adjustments, described below. + mults = [] + for j in [64, 0]: + pow_of_x = i + j + if lsb: + # Each 64x64 => 128 bit carryless multiplication instruction + # actually generates a 127-bit product in physical bits 0 + # through 126, which in the lsb-first case represent the + # coefficients of x^1 through x^127, not x^0 through x^126. + # Thus in the lsb-first case, each such instruction + # implicitly adds an extra factor of x. The below removes a + # factor of x from each constant to compensate for this. + # For n < 64 the x could be removed from either the reduced + # part or unreduced part, but for n == 64 the reduced part + # is the only option. Just always use the reduced part. + pow_of_x -= 1 + # Make a factor of x^(64-n) be applied unreduced rather than + # reduced, to cause the product to use only the x^(64-n) and + # higher terms and always be zero in the lower terms. Usually + # this makes no difference as it does not affect the product's + # congruence class mod G and the constant remains 64-bit, but + # part of the final reduction from 128 bits does rely on this + # property when it reuses one of the constants. + pow_of_x -= 64 - n + mults.append({ 'val': reduce(1 << pow_of_x, G) << (64 - n), + 'desc': f'(x^{pow_of_x} mod G) * x^{64-n}' }) + print_mult_pair(v, mults) + print('\t},') + + # Shuffle table for handling 1..15 bytes at end + print('\t.shuf_table = {') + print('\t\t' + (16*'-1, ').rstrip()) + print('\t\t' + ''.join(f'{i:2}, ' for i in range(16)).rstrip()) + print('\t\t' + (16*'-1, ').rstrip()) + print('\t},') + + # Barrett reduction constants for reducing 128 bits to the final CRC + print('\t.barrett_reduction_consts = {') + mults = [] + + val = div(1 << (63+n), G) + desc = f'floor(x^{63+n} / G)' + if not lsb: + val = (val << 1) - (1 << 64) + desc = f'({desc} * x) - x^64' + mults.append({ 'val': val, 'desc': desc }) + + val = G - (1 << n) + desc = f'G - x^{n}' + if lsb and n == 64: + assert (val & 1) != 0 # The x^0 term should always be nonzero. + val >>= 1 + desc = f'({desc} - x^0) / x' + else: + pow_of_x = 64 - n - (1 if lsb else 0) + val <<= pow_of_x + desc = f'({desc}) * x^{pow_of_x}' + mults.append({ 'val': val, 'desc': desc }) + + print_mult_pair(v, mults) + print('\t},') + + print('};') + +def parse_crc_variants(vars_string): + variants = [] + for var_string in vars_string.split(','): + bits, bit_order, generator_poly = var_string.split('_') + assert bits.startswith('crc') + bits = int(bits.removeprefix('crc')) + assert generator_poly.startswith('0x') + generator_poly = generator_poly.removeprefix('0x') + assert len(generator_poly) % 2 == 0 + generator_poly = int(generator_poly, 16) + variants.append(CrcVariant(bits, generator_poly, bit_order)) + return variants + +if len(sys.argv) != 3: + sys.stderr.write(f'Usage: {sys.argv[0]} CONSTS_TYPE[,CONSTS_TYPE]... CRC_VARIANT[,CRC_VARIANT]...\n') + sys.stderr.write(' CONSTS_TYPE can be sliceby[1-8], riscv_clmul, or x86_pclmul\n') + sys.stderr.write(' CRC_VARIANT is crc${num_bits}_${bit_order}_${generator_poly_as_hex}\n') + sys.stderr.write(' E.g. crc16_msb_0x8bb7 or crc32_lsb_0xedb88320\n') + sys.stderr.write(' Polynomial must use the given bit_order and exclude x^{num_bits}\n') + sys.exit(1) + +print('/* SPDX-License-Identifier: GPL-2.0-or-later */') +print('/*') +print(' * CRC constants generated by:') +print(' *') +print(f' *\t{sys.argv[0]} {" ".join(sys.argv[1:])}') +print(' *') +print(' * Do not edit manually.') +print(' */') +consts_types = sys.argv[1].split(',') +variants = parse_crc_variants(sys.argv[2]) +for consts_type in consts_types: + if consts_type.startswith('sliceby'): + gen_slicebyN_tables(variants, int(consts_type.removeprefix('sliceby'))) + elif consts_type == 'riscv_clmul': + gen_riscv_clmul_consts(variants) + elif consts_type == 'x86_pclmul': + gen_x86_pclmul_consts(variants) + else: + raise ValueError(f'Unknown consts_type: {consts_type}') diff --git a/scripts/gen_packed_field_checks.c b/scripts/gen_packed_field_checks.c new file mode 100644 index 000000000000..60042b7616ee --- /dev/null +++ b/scripts/gen_packed_field_checks.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024, Intel Corporation +#include <stdbool.h> +#include <stdio.h> + +#define MAX_PACKED_FIELD_SIZE 50 + +int main(int argc, char **argv) +{ + /* The first macro doesn't need a 'do {} while(0)' loop */ + printf("#define CHECK_PACKED_FIELDS_1(fields) \\\n"); + printf("\tCHECK_PACKED_FIELD(fields, 0)\n\n"); + + /* Remaining macros require a do/while loop, and are implemented + * recursively by calling the previous iteration's macro. + */ + for (int i = 2; i <= MAX_PACKED_FIELD_SIZE; i++) { + printf("#define CHECK_PACKED_FIELDS_%d(fields) do { \\\n", i); + printf("\tCHECK_PACKED_FIELDS_%d(fields); \\\n", i - 1); + printf("\tCHECK_PACKED_FIELD(fields, %d); \\\n", i - 1); + printf("} while (0)\n\n"); + } + + printf("#define CHECK_PACKED_FIELDS(fields) \\\n"); + + for (int i = 1; i <= MAX_PACKED_FIELD_SIZE; i++) + printf("\t__builtin_choose_expr(ARRAY_SIZE(fields) == %d, ({ CHECK_PACKED_FIELDS_%d(fields); }), \\\n", + i, i); + + printf("\t({ BUILD_BUG_ON_MSG(1, \"CHECK_PACKED_FIELDS() must be regenerated to support array sizes larger than %d.\"); }) \\\n", + MAX_PACKED_FIELD_SIZE); + + for (int i = 1; i <= MAX_PACKED_FIELD_SIZE; i++) + printf(")"); + + printf("\n"); +} diff --git a/scripts/gendwarfksyms/.gitignore b/scripts/gendwarfksyms/.gitignore new file mode 100644 index 000000000000..0927f8d3cd96 --- /dev/null +++ b/scripts/gendwarfksyms/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +/gendwarfksyms diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile new file mode 100644 index 000000000000..6334c7d3c4d5 --- /dev/null +++ b/scripts/gendwarfksyms/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +hostprogs-always-y += gendwarfksyms + +gendwarfksyms-objs += gendwarfksyms.o +gendwarfksyms-objs += cache.o +gendwarfksyms-objs += die.o +gendwarfksyms-objs += dwarf.o +gendwarfksyms-objs += kabi.o +gendwarfksyms-objs += symbols.o +gendwarfksyms-objs += types.o + +HOSTLDLIBS_gendwarfksyms := -ldw -lelf -lz diff --git a/scripts/gendwarfksyms/cache.c b/scripts/gendwarfksyms/cache.c new file mode 100644 index 000000000000..c9c19b86a686 --- /dev/null +++ b/scripts/gendwarfksyms/cache.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +struct cache_item { + unsigned long key; + int value; + struct hlist_node hash; +}; + +void cache_set(struct cache *cache, unsigned long key, int value) +{ + struct cache_item *ci; + + ci = xmalloc(sizeof(struct cache_item)); + ci->key = key; + ci->value = value; + hash_add(cache->cache, &ci->hash, hash_32(key)); +} + +int cache_get(struct cache *cache, unsigned long key) +{ + struct cache_item *ci; + + hash_for_each_possible(cache->cache, ci, hash, hash_32(key)) { + if (ci->key == key) + return ci->value; + } + + return -1; +} + +void cache_init(struct cache *cache) +{ + hash_init(cache->cache); +} + +void cache_free(struct cache *cache) +{ + struct hlist_node *tmp; + struct cache_item *ci; + + hash_for_each_safe(cache->cache, ci, tmp, hash) { + free(ci); + } + + hash_init(cache->cache); +} diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c new file mode 100644 index 000000000000..6183bbbe7b54 --- /dev/null +++ b/scripts/gendwarfksyms/die.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <string.h> +#include "gendwarfksyms.h" + +#define DIE_HASH_BITS 16 + +/* {die->addr, state} -> struct die * */ +static HASHTABLE_DEFINE(die_map, 1 << DIE_HASH_BITS); + +static unsigned int map_hits; +static unsigned int map_misses; + +static inline unsigned int die_hash(uintptr_t addr, enum die_state state) +{ + return hash_32(addr_hash(addr) ^ (unsigned int)state); +} + +static void init_die(struct die *cd) +{ + cd->state = DIE_INCOMPLETE; + cd->mapped = false; + cd->fqn = NULL; + cd->tag = -1; + cd->addr = 0; + INIT_LIST_HEAD(&cd->fragments); +} + +static struct die *create_die(Dwarf_Die *die, enum die_state state) +{ + struct die *cd; + + cd = xmalloc(sizeof(struct die)); + init_die(cd); + cd->addr = (uintptr_t)die->addr; + + hash_add(die_map, &cd->hash, die_hash(cd->addr, state)); + return cd; +} + +int __die_map_get(uintptr_t addr, enum die_state state, struct die **res) +{ + struct die *cd; + + hash_for_each_possible(die_map, cd, hash, die_hash(addr, state)) { + if (cd->addr == addr && cd->state == state) { + *res = cd; + return 0; + } + } + + return -1; +} + +struct die *die_map_get(Dwarf_Die *die, enum die_state state) +{ + struct die *cd; + + if (__die_map_get((uintptr_t)die->addr, state, &cd) == 0) { + map_hits++; + return cd; + } + + map_misses++; + return create_die(die, state); +} + +static void reset_die(struct die *cd) +{ + struct die_fragment *tmp; + struct die_fragment *df; + + list_for_each_entry_safe(df, tmp, &cd->fragments, list) { + if (df->type == FRAGMENT_STRING) + free(df->data.str); + free(df); + } + + if (cd->fqn && *cd->fqn) + free(cd->fqn); + init_die(cd); +} + +void die_map_for_each(die_map_callback_t func, void *arg) +{ + struct hlist_node *tmp; + struct die *cd; + + hash_for_each_safe(die_map, cd, tmp, hash) { + func(cd, arg); + } +} + +void die_map_free(void) +{ + struct hlist_node *tmp; + unsigned int stats[DIE_LAST + 1]; + struct die *cd; + int i; + + memset(stats, 0, sizeof(stats)); + + hash_for_each_safe(die_map, cd, tmp, hash) { + stats[cd->state]++; + reset_die(cd); + free(cd); + } + hash_init(die_map); + + if (map_hits + map_misses > 0) + debug("hits %u, misses %u (hit rate %.02f%%)", map_hits, + map_misses, + (100.0f * map_hits) / (map_hits + map_misses)); + + for (i = 0; i <= DIE_LAST; i++) + debug("%s: %u entries", die_state_name(i), stats[i]); +} + +static struct die_fragment *append_item(struct die *cd) +{ + struct die_fragment *df; + + df = xmalloc(sizeof(struct die_fragment)); + df->type = FRAGMENT_EMPTY; + list_add_tail(&df->list, &cd->fragments); + return df; +} + +void die_map_add_string(struct die *cd, const char *str) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.str = xstrdup(str); + df->type = FRAGMENT_STRING; +} + +void die_map_add_linebreak(struct die *cd, int linebreak) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.linebreak = linebreak; + df->type = FRAGMENT_LINEBREAK; +} + +void die_map_add_die(struct die *cd, struct die *child) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.addr = child->addr; + df->type = FRAGMENT_DIE; +} diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c new file mode 100644 index 000000000000..eed247d8abfc --- /dev/null +++ b/scripts/gendwarfksyms/dwarf.c @@ -0,0 +1,1171 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <assert.h> +#include <inttypes.h> +#include <stdarg.h> +#include "gendwarfksyms.h" + +/* See get_union_kabi_status */ +#define KABI_PREFIX "__kabi_" +#define KABI_PREFIX_LEN (sizeof(KABI_PREFIX) - 1) +#define KABI_RESERVED_PREFIX "reserved" +#define KABI_RESERVED_PREFIX_LEN (sizeof(KABI_RESERVED_PREFIX) - 1) +#define KABI_RENAMED_PREFIX "renamed" +#define KABI_RENAMED_PREFIX_LEN (sizeof(KABI_RENAMED_PREFIX) - 1) +#define KABI_IGNORED_PREFIX "ignored" +#define KABI_IGNORED_PREFIX_LEN (sizeof(KABI_IGNORED_PREFIX) - 1) + +static inline bool is_kabi_prefix(const char *name) +{ + return name && !strncmp(name, KABI_PREFIX, KABI_PREFIX_LEN); +} + +enum kabi_status { + /* >0 to stop DIE processing */ + KABI_NORMAL = 1, + KABI_RESERVED, + KABI_IGNORED, +}; + +static bool do_linebreak; +static int indentation_level; + +/* Line breaks and indentation for pretty-printing */ +static void process_linebreak(struct die *cache, int n) +{ + indentation_level += n; + do_linebreak = true; + die_map_add_linebreak(cache, n); +} + +#define DEFINE_GET_ATTR(attr, type) \ + static bool get_##attr##_attr(Dwarf_Die *die, unsigned int id, \ + type *value) \ + { \ + Dwarf_Attribute da; \ + return dwarf_attr(die, id, &da) && \ + !dwarf_form##attr(&da, value); \ + } + +DEFINE_GET_ATTR(flag, bool) +DEFINE_GET_ATTR(udata, Dwarf_Word) + +static bool get_ref_die_attr(Dwarf_Die *die, unsigned int id, Dwarf_Die *value) +{ + Dwarf_Attribute da; + + /* dwarf_formref_die returns a pointer instead of an error value. */ + return dwarf_attr(die, id, &da) && dwarf_formref_die(&da, value); +} + +#define DEFINE_GET_STRING_ATTR(attr) \ + static const char *get_##attr##_attr(Dwarf_Die *die) \ + { \ + Dwarf_Attribute da; \ + if (dwarf_attr(die, DW_AT_##attr, &da)) \ + return dwarf_formstring(&da); \ + return NULL; \ + } + +DEFINE_GET_STRING_ATTR(name) +DEFINE_GET_STRING_ATTR(linkage_name) + +static const char *get_symbol_name(Dwarf_Die *die) +{ + const char *name; + + /* rustc uses DW_AT_linkage_name for exported symbols */ + name = get_linkage_name_attr(die); + if (!name) + name = get_name_attr(die); + + return name; +} + +static bool match_export_symbol(struct state *state, Dwarf_Die *die) +{ + Dwarf_Die *source = die; + Dwarf_Die origin; + + /* If the DIE has an abstract origin, use it for type information. */ + if (get_ref_die_attr(die, DW_AT_abstract_origin, &origin)) + source = &origin; + + state->sym = symbol_get(get_symbol_name(die)); + + /* Look up using the origin name if there are no matches. */ + if (!state->sym && source != die) + state->sym = symbol_get(get_symbol_name(source)); + + state->die = *source; + return !!state->sym; +} + +/* DW_AT_decl_file -> struct srcfile */ +static struct cache srcfile_cache; + +static bool is_definition_private(Dwarf_Die *die) +{ + Dwarf_Word filenum; + Dwarf_Files *files; + Dwarf_Die cudie; + const char *s; + int res; + + /* + * Definitions in .c files cannot change the public ABI, + * so consider them private. + */ + if (!get_udata_attr(die, DW_AT_decl_file, &filenum)) + return false; + + res = cache_get(&srcfile_cache, filenum); + if (res >= 0) + return !!res; + + if (!dwarf_cu_die(die->cu, &cudie, NULL, NULL, NULL, NULL, NULL, NULL)) + error("dwarf_cu_die failed: '%s'", dwarf_errmsg(-1)); + + if (dwarf_getsrcfiles(&cudie, &files, NULL)) + error("dwarf_getsrcfiles failed: '%s'", dwarf_errmsg(-1)); + + s = dwarf_filesrc(files, filenum, NULL, NULL); + if (!s) + error("dwarf_filesrc failed: '%s'", dwarf_errmsg(-1)); + + s = strrchr(s, '.'); + res = s && !strcmp(s, ".c"); + cache_set(&srcfile_cache, filenum, res); + + return !!res; +} + +static bool is_kabi_definition(struct die *cache, Dwarf_Die *die) +{ + bool value; + + if (get_flag_attr(die, DW_AT_declaration, &value) && value) + return false; + + if (kabi_is_declonly(cache->fqn)) + return false; + + return !is_definition_private(die); +} + +/* + * Type string processing + */ +static void process(struct die *cache, const char *s) +{ + s = s ?: "<null>"; + + if (dump_dies && do_linebreak) { + fputs("\n", stderr); + for (int i = 0; i < indentation_level; i++) + fputs(" ", stderr); + do_linebreak = false; + } + if (dump_dies) + fputs(s, stderr); + + if (cache) + die_debug_r("cache %p string '%s'", cache, s); + die_map_add_string(cache, s); +} + +#define MAX_FMT_BUFFER_SIZE 128 + +static void process_fmt(struct die *cache, const char *fmt, ...) +{ + char buf[MAX_FMT_BUFFER_SIZE]; + va_list args; + + va_start(args, fmt); + + if (checkp(vsnprintf(buf, sizeof(buf), fmt, args)) >= sizeof(buf)) + error("vsnprintf overflow: increase MAX_FMT_BUFFER_SIZE"); + + process(cache, buf); + va_end(args); +} + +static void update_fqn(struct die *cache, Dwarf_Die *die) +{ + struct die *fqn; + + if (!cache->fqn) { + if (!__die_map_get((uintptr_t)die->addr, DIE_FQN, &fqn) && + *fqn->fqn) + cache->fqn = xstrdup(fqn->fqn); + else + cache->fqn = ""; + } +} + +static void process_fqn(struct die *cache, Dwarf_Die *die) +{ + update_fqn(cache, die); + if (*cache->fqn) + process(cache, " "); + process(cache, cache->fqn); +} + +#define DEFINE_PROCESS_UDATA_ATTRIBUTE(attribute) \ + static void process_##attribute##_attr(struct die *cache, \ + Dwarf_Die *die) \ + { \ + Dwarf_Word value; \ + if (get_udata_attr(die, DW_AT_##attribute, &value)) \ + process_fmt(cache, " " #attribute "(%" PRIu64 ")", \ + value); \ + } + +DEFINE_PROCESS_UDATA_ATTRIBUTE(accessibility) +DEFINE_PROCESS_UDATA_ATTRIBUTE(alignment) +DEFINE_PROCESS_UDATA_ATTRIBUTE(bit_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(byte_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) +DEFINE_PROCESS_UDATA_ATTRIBUTE(data_bit_offset) +DEFINE_PROCESS_UDATA_ATTRIBUTE(data_member_location) +DEFINE_PROCESS_UDATA_ATTRIBUTE(discr_value) + +/* Match functions -- die_match_callback_t */ +#define DEFINE_MATCH(type) \ + static bool match_##type##_type(Dwarf_Die *die) \ + { \ + return dwarf_tag(die) == DW_TAG_##type##_type; \ + } + +DEFINE_MATCH(enumerator) +DEFINE_MATCH(formal_parameter) +DEFINE_MATCH(member) +DEFINE_MATCH(subrange) + +bool match_all(Dwarf_Die *die) +{ + return true; +} + +int process_die_container(struct state *state, struct die *cache, + Dwarf_Die *die, die_callback_t func, + die_match_callback_t match) +{ + Dwarf_Die current; + int res; + + /* Track the first item in lists. */ + if (state) + state->first_list_item = true; + + res = checkp(dwarf_child(die, ¤t)); + while (!res) { + if (match(¤t)) { + /* <0 = error, 0 = continue, >0 = stop */ + res = checkp(func(state, cache, ¤t)); + if (res) + goto out; + } + + res = checkp(dwarf_siblingof(¤t, ¤t)); + } + + res = 0; +out: + if (state) + state->first_list_item = false; + + return res; +} + +static int process_type(struct state *state, struct die *parent, + Dwarf_Die *die); + +static void process_type_attr(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Die type; + + if (get_ref_die_attr(die, DW_AT_type, &type)) { + check(process_type(state, cache, &type)); + return; + } + + /* Compilers can omit DW_AT_type -- print out 'void' to clarify */ + process(cache, "base_type void"); +} + +static void process_list_comma(struct state *state, struct die *cache) +{ + if (state->first_list_item) { + state->first_list_item = false; + } else { + process(cache, " ,"); + process_linebreak(cache, 0); + } +} + +/* Comma-separated with DW_AT_type */ +static void __process_list_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + const char *name = get_name_attr(die); + + if (stable) { + if (is_kabi_prefix(name)) + name = NULL; + state->kabi.orig_name = NULL; + } + + process_list_comma(state, cache); + process(cache, type); + process_type_attr(state, cache, die); + + if (stable && state->kabi.orig_name) + name = state->kabi.orig_name; + if (name) { + process(cache, " "); + process(cache, name); + } + + process_accessibility_attr(cache, die); + process_bit_size_attr(cache, die); + process_data_bit_offset_attr(cache, die); + process_data_member_location_attr(cache, die); +} + +#define DEFINE_PROCESS_LIST_TYPE(type) \ + static void process_##type##_type(struct state *state, \ + struct die *cache, Dwarf_Die *die) \ + { \ + __process_list_type(state, cache, die, #type " "); \ + } + +DEFINE_PROCESS_LIST_TYPE(formal_parameter) +DEFINE_PROCESS_LIST_TYPE(member) + +/* Container types with DW_AT_type */ +static void __process_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + process_type_attr(state, cache, die); + process_linebreak(cache, -1); + process(cache, "}"); + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); +} + +#define DEFINE_PROCESS_TYPE(type) \ + static void process_##type##_type(struct state *state, \ + struct die *cache, Dwarf_Die *die) \ + { \ + __process_type(state, cache, die, #type "_type"); \ + } + +DEFINE_PROCESS_TYPE(atomic) +DEFINE_PROCESS_TYPE(const) +DEFINE_PROCESS_TYPE(immutable) +DEFINE_PROCESS_TYPE(packed) +DEFINE_PROCESS_TYPE(pointer) +DEFINE_PROCESS_TYPE(reference) +DEFINE_PROCESS_TYPE(restrict) +DEFINE_PROCESS_TYPE(rvalue_reference) +DEFINE_PROCESS_TYPE(shared) +DEFINE_PROCESS_TYPE(template_type_parameter) +DEFINE_PROCESS_TYPE(volatile) +DEFINE_PROCESS_TYPE(typedef) + +static void process_subrange_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Word count = 0; + + if (get_udata_attr(die, DW_AT_count, &count)) + process_fmt(cache, "[%" PRIu64 "]", count); + else if (get_udata_attr(die, DW_AT_upper_bound, &count)) + process_fmt(cache, "[%" PRIu64 "]", count + 1); + else + process(cache, "[]"); +} + +static void process_array_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "array_type"); + /* Array size */ + check(process_die_container(state, cache, die, process_type, + match_subrange_type)); + process(cache, " {"); + process_linebreak(cache, 1); + process_type_attr(state, cache, die); + process_linebreak(cache, -1); + process(cache, "}"); +} + +static void __process_subroutine_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + process(cache, type); + process(cache, " ("); + process_linebreak(cache, 1); + /* Parameters */ + check(process_die_container(state, cache, die, process_type, + match_formal_parameter_type)); + process_linebreak(cache, -1); + process(cache, ")"); + process_linebreak(cache, 0); + /* Return type */ + process(cache, "-> "); + process_type_attr(state, cache, die); +} + +static void process_subroutine_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_subroutine_type(state, cache, die, "subroutine_type"); +} + +static void process_variant_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process_list_comma(state, cache); + process(cache, "variant {"); + process_linebreak(cache, 1); + check(process_die_container(state, cache, die, process_type, + match_member_type)); + process_linebreak(cache, -1); + process(cache, "}"); + process_discr_value_attr(cache, die); +} + +static void process_variant_part_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process_list_comma(state, cache); + process(cache, "variant_part {"); + process_linebreak(cache, 1); + check(process_die_container(state, cache, die, process_type, + match_all)); + process_linebreak(cache, -1); + process(cache, "}"); +} + +static int get_kabi_status(Dwarf_Die *die, const char **suffix) +{ + const char *name = get_name_attr(die); + + if (suffix) + *suffix = NULL; + + if (is_kabi_prefix(name)) { + name += KABI_PREFIX_LEN; + + if (!strncmp(name, KABI_RESERVED_PREFIX, + KABI_RESERVED_PREFIX_LEN)) + return KABI_RESERVED; + if (!strncmp(name, KABI_IGNORED_PREFIX, + KABI_IGNORED_PREFIX_LEN)) + return KABI_IGNORED; + + if (!strncmp(name, KABI_RENAMED_PREFIX, + KABI_RENAMED_PREFIX_LEN)) { + if (suffix) { + name += KABI_RENAMED_PREFIX_LEN; + *suffix = name; + } + return KABI_RESERVED; + } + } + + return KABI_NORMAL; +} + +static int check_struct_member_kabi_status(struct state *state, + struct die *__unused, Dwarf_Die *die) +{ + int res; + + assert(dwarf_tag(die) == DW_TAG_member_type); + + /* + * If the union member is a struct, expect the __kabi field to + * be the first member of the structure, i.e..: + * + * union { + * type new_member; + * struct { + * type __kabi_field; + * } + * }; + */ + res = get_kabi_status(die, &state->kabi.orig_name); + + if (res == KABI_RESERVED && + !get_ref_die_attr(die, DW_AT_type, &state->kabi.placeholder)) + error("structure member missing a type?"); + + return res; +} + +static int check_union_member_kabi_status(struct state *state, + struct die *__unused, Dwarf_Die *die) +{ + Dwarf_Die type; + int res; + + assert(dwarf_tag(die) == DW_TAG_member_type); + + if (!get_ref_die_attr(die, DW_AT_type, &type)) + error("union member missing a type?"); + + /* + * We expect a union with two members. Check if either of them + * has a __kabi name prefix, i.e.: + * + * union { + * ... + * type memberN; // <- type, N = {0,1} + * ... + * }; + * + * The member can also be a structure type, in which case we'll + * check the first structure member. + * + * In any case, stop processing after we've seen two members. + */ + res = get_kabi_status(die, &state->kabi.orig_name); + + if (res == KABI_RESERVED) + state->kabi.placeholder = type; + if (res != KABI_NORMAL) + return res; + + if (dwarf_tag(&type) == DW_TAG_structure_type) + res = checkp(process_die_container( + state, NULL, &type, check_struct_member_kabi_status, + match_member_type)); + + if (res <= KABI_NORMAL && ++state->kabi.members < 2) + return 0; /* Continue */ + + return res; +} + +static int get_union_kabi_status(Dwarf_Die *die, Dwarf_Die *placeholder, + const char **orig_name) +{ + struct state state; + int res; + + if (!stable) + return KABI_NORMAL; + + /* + * To maintain a stable kABI, distributions may choose to reserve + * space in structs for later use by adding placeholder members, + * for example: + * + * struct s { + * u32 a; + * // an 8-byte placeholder for future use + * u64 __kabi_reserved_0; + * }; + * + * When the reserved member is taken into use, the type change + * would normally cause the symbol version to change as well, but + * if the replacement uses the following convention, gendwarfksyms + * continues to use the placeholder type for versioning instead, + * thus maintaining the same symbol version: + * + * struct s { + * u32 a; + * union { + * // placeholder replaced with a new member `b` + * struct t b; + * struct { + * // the placeholder type that is still + * // used for versioning + * u64 __kabi_reserved_0; + * }; + * }; + * }; + * + * I.e., as long as the replaced member is in a union, and the + * placeholder has a __kabi_reserved name prefix, we'll continue + * to use the placeholder type (here u64) for version calculation + * instead of the union type. + * + * It's also possible to ignore new members from versioning if + * they've been added to alignment holes, for example, by + * including them in a union with another member that uses the + * __kabi_ignored name prefix: + * + * struct s { + * u32 a; + * // an alignment hole is used to add `n` + * union { + * u32 n; + * // hide the entire union member from versioning + * u8 __kabi_ignored_0; + * }; + * u64 b; + * }; + * + * Note that the user of this feature is responsible for ensuring + * that the structure actually remains ABI compatible. + */ + memset(&state.kabi, 0, sizeof(struct kabi_state)); + + res = checkp(process_die_container(&state, NULL, die, + check_union_member_kabi_status, + match_member_type)); + + if (res == KABI_RESERVED) { + if (placeholder) + *placeholder = state.kabi.placeholder; + if (orig_name) + *orig_name = state.kabi.orig_name; + } + + return res; +} + +static bool is_kabi_ignored(Dwarf_Die *die) +{ + Dwarf_Die type; + + if (!stable) + return false; + + if (!get_ref_die_attr(die, DW_AT_type, &type)) + error("member missing a type?"); + + return dwarf_tag(&type) == DW_TAG_union_type && + checkp(get_union_kabi_status(&type, NULL, NULL)) == KABI_IGNORED; +} + +static int ___process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + switch (dwarf_tag(die)) { + case DW_TAG_member: + if (is_kabi_ignored(die)) + return 0; + return check(process_type(state, cache, die)); + case DW_TAG_variant_part: + return check(process_type(state, cache, die)); + case DW_TAG_class_type: + case DW_TAG_enumeration_type: + case DW_TAG_structure_type: + case DW_TAG_template_type_parameter: + case DW_TAG_union_type: + case DW_TAG_subprogram: + /* Skip non-member types, including member functions */ + return 0; + default: + error("unexpected structure_type child: %x", dwarf_tag(die)); + } +} + +static void __process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type, + die_callback_t process_func, + die_match_callback_t match_func) +{ + bool expand; + + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + + expand = state->expand.expand && is_kabi_definition(cache, die); + + if (expand) { + state->expand.current_fqn = cache->fqn; + check(process_die_container(state, cache, die, process_func, + match_func)); + } + + process_linebreak(cache, -1); + process(cache, "}"); + + if (expand) { + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); + } +} + +#define DEFINE_PROCESS_STRUCTURE_TYPE(structure) \ + static void process_##structure##_type( \ + struct state *state, struct die *cache, Dwarf_Die *die) \ + { \ + __process_structure_type(state, cache, die, \ + #structure "_type", \ + ___process_structure_type, \ + match_all); \ + } + +DEFINE_PROCESS_STRUCTURE_TYPE(class) +DEFINE_PROCESS_STRUCTURE_TYPE(structure) + +static void process_union_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Die placeholder; + + int res = checkp(get_union_kabi_status(die, &placeholder, + &state->kabi.orig_name)); + + if (res == KABI_RESERVED) + check(process_type(state, cache, &placeholder)); + if (res > KABI_NORMAL) + return; + + __process_structure_type(state, cache, die, "union_type", + ___process_structure_type, match_all); +} + +static void process_enumerator_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + bool overridden = false; + Dwarf_Word value; + + if (stable) { + /* Get the fqn before we process anything */ + update_fqn(cache, die); + + if (kabi_is_enumerator_ignored(state->expand.current_fqn, + cache->fqn)) + return; + + overridden = kabi_get_enumerator_value( + state->expand.current_fqn, cache->fqn, &value); + } + + process_list_comma(state, cache); + process(cache, "enumerator"); + process_fqn(cache, die); + + if (overridden || get_udata_attr(die, DW_AT_const_value, &value)) { + process(cache, " = "); + process_fmt(cache, "%" PRIu64, value); + } +} + +static void process_enumeration_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_structure_type(state, cache, die, "enumeration_type", + process_type, match_enumerator_type); +} + +static void process_base_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "base_type"); + process_fqn(cache, die); + process_byte_size_attr(cache, die); + process_encoding_attr(cache, die); + process_alignment_attr(cache, die); +} + +static void process_unspecified_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + /* + * These can be emitted for stand-alone assembly code, which means we + * might run into them in vmlinux.o. + */ + process(cache, "unspecified_type"); +} + +static void process_cached(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + struct die_fragment *df; + Dwarf_Die child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + die_debug_b("cache %p STRING '%s'", cache, + df->data.str); + process(NULL, df->data.str); + break; + case FRAGMENT_LINEBREAK: + process_linebreak(NULL, df->data.linebreak); + break; + case FRAGMENT_DIE: + if (!dwarf_die_addr_die(dwarf_cu_getdwarf(die->cu), + (void *)df->data.addr, &child)) + error("dwarf_die_addr_die failed"); + die_debug_b("cache %p DIE addr %" PRIxPTR " tag %x", + cache, df->data.addr, dwarf_tag(&child)); + check(process_type(state, NULL, &child)); + break; + default: + error("empty die_fragment"); + } + } +} + +static void state_init(struct state *state) +{ + state->expand.expand = true; + state->expand.current_fqn = NULL; + cache_init(&state->expansion_cache); +} + +static void expansion_state_restore(struct expansion_state *state, + struct expansion_state *saved) +{ + state->expand = saved->expand; + state->current_fqn = saved->current_fqn; +} + +static void expansion_state_save(struct expansion_state *state, + struct expansion_state *saved) +{ + expansion_state_restore(saved, state); +} + +static bool is_expanded_type(int tag) +{ + return tag == DW_TAG_class_type || tag == DW_TAG_structure_type || + tag == DW_TAG_union_type || tag == DW_TAG_enumeration_type; +} + +#define PROCESS_TYPE(type) \ + case DW_TAG_##type##_type: \ + process_##type##_type(state, cache, die); \ + break; + +static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) +{ + enum die_state want_state = DIE_COMPLETE; + struct die *cache; + struct expansion_state saved; + int tag = dwarf_tag(die); + + expansion_state_save(&state->expand, &saved); + + /* + * Structures and enumeration types are expanded only once per + * exported symbol. This is sufficient for detecting ABI changes + * within the structure. + */ + if (is_expanded_type(tag)) { + if (cache_was_expanded(&state->expansion_cache, die->addr)) + state->expand.expand = false; + + if (state->expand.expand) + cache_mark_expanded(&state->expansion_cache, die->addr); + else + want_state = DIE_UNEXPANDED; + } + + /* + * If we have want_state already cached, use it instead of walking + * through DWARF. + */ + cache = die_map_get(die, want_state); + + if (cache->state == want_state) { + die_debug_g("cached addr %p tag %x -- %s", die->addr, tag, + die_state_name(cache->state)); + + process_cached(state, cache, die); + die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); + return 0; + } + + die_debug_g("addr %p tag %x -- %s -> %s", die->addr, tag, + die_state_name(cache->state), die_state_name(want_state)); + + switch (tag) { + /* Type modifiers */ + PROCESS_TYPE(atomic) + PROCESS_TYPE(const) + PROCESS_TYPE(immutable) + PROCESS_TYPE(packed) + PROCESS_TYPE(pointer) + PROCESS_TYPE(reference) + PROCESS_TYPE(restrict) + PROCESS_TYPE(rvalue_reference) + PROCESS_TYPE(shared) + PROCESS_TYPE(volatile) + /* Container types */ + PROCESS_TYPE(class) + PROCESS_TYPE(structure) + PROCESS_TYPE(union) + PROCESS_TYPE(enumeration) + /* Subtypes */ + PROCESS_TYPE(enumerator) + PROCESS_TYPE(formal_parameter) + PROCESS_TYPE(member) + PROCESS_TYPE(subrange) + PROCESS_TYPE(template_type_parameter) + PROCESS_TYPE(variant) + PROCESS_TYPE(variant_part) + /* Other types */ + PROCESS_TYPE(array) + PROCESS_TYPE(base) + PROCESS_TYPE(subroutine) + PROCESS_TYPE(typedef) + PROCESS_TYPE(unspecified) + default: + error("unexpected type: %x", tag); + } + + die_debug_r("parent %p cache %p die addr %p tag %x", parent, cache, + die->addr, tag); + + /* Update cache state and append to the parent (if any) */ + cache->tag = tag; + cache->state = want_state; + die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); + return 0; +} + +/* + * Exported symbol processing + */ +static struct die *get_symbol_cache(struct state *state, Dwarf_Die *die) +{ + struct die *cache; + + cache = die_map_get(die, DIE_SYMBOL); + + if (cache->state != DIE_INCOMPLETE) + return NULL; /* We already processed a symbol for this DIE */ + + cache->tag = dwarf_tag(die); + return cache; +} + +static void process_symbol(struct state *state, Dwarf_Die *die, + die_callback_t process_func) +{ + struct die *cache; + + symbol_set_die(state->sym, die); + + cache = get_symbol_cache(state, die); + if (!cache) + return; + + debug("%s", state->sym->name); + check(process_func(state, cache, die)); + cache->state = DIE_SYMBOL; + if (dump_dies) + fputs("\n", stderr); +} + +static int __process_subprogram(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_subroutine_type(state, cache, die, "subprogram"); + return 0; +} + +static void process_subprogram(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_subprogram); +} + +static int __process_variable(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "variable "); + process_type_attr(state, cache, die); + return 0; +} + +static void process_variable(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_variable); +} + +static void save_symbol_ptr(struct state *state) +{ + Dwarf_Die ptr_type; + Dwarf_Die type; + + if (!get_ref_die_attr(&state->die, DW_AT_type, &ptr_type) || + dwarf_tag(&ptr_type) != DW_TAG_pointer_type) + error("%s must be a pointer type!", + get_symbol_name(&state->die)); + + if (!get_ref_die_attr(&ptr_type, DW_AT_type, &type)) + error("%s pointer missing a type attribute?", + get_symbol_name(&state->die)); + + /* + * Save the symbol pointer DIE in case the actual symbol is + * missing from the DWARF. Clang, for example, intentionally + * omits external symbols from the debugging information. + */ + if (dwarf_tag(&type) == DW_TAG_subroutine_type) + symbol_set_ptr(state->sym, &type); + else + symbol_set_ptr(state->sym, &ptr_type); +} + +static int process_exported_symbols(struct state *unused, struct die *cache, + Dwarf_Die *die) +{ + int tag = dwarf_tag(die); + + switch (tag) { + /* Possible containers of exported symbols */ + case DW_TAG_namespace: + case DW_TAG_class_type: + case DW_TAG_structure_type: + return check(process_die_container( + NULL, cache, die, process_exported_symbols, match_all)); + + /* Possible exported symbols */ + case DW_TAG_subprogram: + case DW_TAG_variable: { + struct state state; + + if (!match_export_symbol(&state, die)) + return 0; + + state_init(&state); + + if (is_symbol_ptr(get_symbol_name(&state.die))) + save_symbol_ptr(&state); + else if (tag == DW_TAG_subprogram) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + cache_free(&state.expansion_cache); + return 0; + } + default: + return 0; + } +} + +static void process_symbol_ptr(struct symbol *sym, void *arg) +{ + struct state state; + Dwarf *dwarf = arg; + + if (sym->state != SYMBOL_UNPROCESSED || !sym->ptr_die_addr) + return; + + debug("%s", sym->name); + state_init(&state); + state.sym = sym; + + if (!dwarf_die_addr_die(dwarf, (void *)sym->ptr_die_addr, &state.die)) + error("dwarf_die_addr_die failed for symbol ptr: '%s'", + sym->name); + + if (dwarf_tag(&state.die) == DW_TAG_subroutine_type) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + cache_free(&state.expansion_cache); +} + +static int resolve_fqns(struct state *parent, struct die *unused, + Dwarf_Die *die) +{ + struct state state; + struct die *cache; + const char *name; + bool use_prefix; + char *prefix = NULL; + char *fqn = ""; + int tag; + + if (!__die_map_get((uintptr_t)die->addr, DIE_FQN, &cache)) + return 0; + + tag = dwarf_tag(die); + + /* + * Only namespaces and structures need to pass a prefix to the next + * scope. + */ + use_prefix = tag == DW_TAG_namespace || tag == DW_TAG_class_type || + tag == DW_TAG_structure_type; + + state.expand.current_fqn = NULL; + name = get_name_attr(die); + + if (parent && parent->expand.current_fqn && (use_prefix || name)) { + /* + * The fqn for the current DIE, and if needed, a prefix for the + * next scope. + */ + if (asprintf(&prefix, "%s::%s", parent->expand.current_fqn, + name ? name : "<anonymous>") < 0) + error("asprintf failed"); + + if (use_prefix) + state.expand.current_fqn = prefix; + + /* + * Use fqn only if the DIE has a name. Otherwise fqn will + * remain empty. + */ + if (name) { + fqn = prefix; + /* prefix will be freed by die_map. */ + prefix = NULL; + } + } else if (name) { + /* No prefix from the previous scope. Use only the name. */ + fqn = xstrdup(name); + + if (use_prefix) + state.expand.current_fqn = fqn; + } + + /* If the DIE has a non-empty name, cache it. */ + if (*fqn) { + cache = die_map_get(die, DIE_FQN); + /* Move ownership of fqn to die_map. */ + cache->fqn = fqn; + cache->state = DIE_FQN; + } + + check(process_die_container(&state, NULL, die, resolve_fqns, + match_all)); + + free(prefix); + return 0; +} + +void process_cu(Dwarf_Die *cudie) +{ + check(process_die_container(NULL, NULL, cudie, resolve_fqns, + match_all)); + + check(process_die_container(NULL, NULL, cudie, process_exported_symbols, + match_all)); + + symbol_for_each(process_symbol_ptr, dwarf_cu_getdwarf(cudie->cu)); + + cache_free(&srcfile_cache); +} diff --git a/scripts/gendwarfksyms/examples/kabi.h b/scripts/gendwarfksyms/examples/kabi.h new file mode 100644 index 000000000000..97a5669b083d --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Google LLC + * + * Example macros for maintaining kABI stability. + * + * This file is based on android_kabi.h, which has the following notice: + * + * Heavily influenced by rh_kabi.h which came from the RHEL/CENTOS kernel + * and was: + * Copyright (c) 2014 Don Zickus + * Copyright (c) 2015-2018 Jiri Benc + * Copyright (c) 2015 Sabrina Dubroca, Hannes Frederic Sowa + * Copyright (c) 2016-2018 Prarit Bhargava + * Copyright (c) 2017 Paolo Abeni, Larry Woodman + */ + +#ifndef __KABI_H__ +#define __KABI_H__ + +/* Kernel macros for userspace testing. */ +#ifndef __aligned +#define __aligned(x) __attribute__((__aligned__(x))) +#endif +#ifndef __used +#define __used __attribute__((__used__)) +#endif +#ifndef __section +#define __section(section) __attribute__((__section__(section))) +#endif +#ifndef __PASTE +#define ___PASTE(a, b) a##b +#define __PASTE(a, b) ___PASTE(a, b) +#endif +#ifndef __stringify +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) +#endif + +#define __KABI_RULE(hint, target, value) \ + static const char __PASTE(__gendwarfksyms_rule_, \ + __COUNTER__)[] __used __aligned(1) \ + __section(".discard.gendwarfksyms.kabi_rules") = \ + "1\0" #hint "\0" #target "\0" #value + +#define __KABI_NORMAL_SIZE_ALIGN(_orig, _new) \ + union { \ + _Static_assert( \ + sizeof(struct { _new; }) <= sizeof(struct { _orig; }), \ + __FILE__ ":" __stringify(__LINE__) ": " __stringify( \ + _new) " is larger than " __stringify(_orig)); \ + _Static_assert( \ + __alignof__(struct { _new; }) <= \ + __alignof__(struct { _orig; }), \ + __FILE__ ":" __stringify(__LINE__) ": " __stringify( \ + _orig) " is not aligned the same as " __stringify(_new)); \ + } + +#define __KABI_REPLACE(_orig, _new) \ + union { \ + _new; \ + struct { \ + _orig; \ + }; \ + __KABI_NORMAL_SIZE_ALIGN(_orig, _new); \ + } + +/* + * KABI_DECLONLY(fqn) + * Treat the struct/union/enum fqn as a declaration, i.e. even if + * a definition is available, don't expand the contents. + */ +#define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, ) + +/* + * KABI_ENUMERATOR_IGNORE(fqn, field) + * When expanding enum fqn, skip the provided field. This makes it + * possible to hide added enum fields from versioning. + */ +#define KABI_ENUMERATOR_IGNORE(fqn, field) \ + __KABI_RULE(enumerator_ignore, fqn field, ) + +/* + * KABI_ENUMERATOR_VALUE(fqn, field, value) + * When expanding enum fqn, use the provided value for the + * specified field. This makes it possible to override enumerator + * values when calculating versions. + */ +#define KABI_ENUMERATOR_VALUE(fqn, field, value) \ + __KABI_RULE(enumerator_value, fqn field, value) + +/* + * KABI_RESERVE + * Reserve some "padding" in a structure for use by LTS backports. + * This is normally placed at the end of a structure. + * number: the "number" of the padding variable in the structure. Start with + * 1 and go up. + */ +#define KABI_RESERVE(n) unsigned long __kabi_reserved##n + +/* + * KABI_RESERVE_ARRAY + * Same as _BACKPORT_RESERVE but allocates an array with the specified + * size in bytes. + */ +#define KABI_RESERVE_ARRAY(n, s) \ + unsigned char __aligned(8) __kabi_reserved##n[s] + +/* + * KABI_IGNORE + * Add a new field that's ignored in versioning. + */ +#define KABI_IGNORE(n, _new) \ + union { \ + _new; \ + unsigned char __kabi_ignored##n; \ + } + +/* + * KABI_REPLACE + * Replace a field with a compatible new field. + */ +#define KABI_REPLACE(_oldtype, _oldname, _new) \ + __KABI_REPLACE(_oldtype __kabi_renamed##_oldname, struct { _new; }) + +/* + * KABI_USE(number, _new) + * Use a previous padding entry that was defined with KABI_RESERVE + * number: the previous "number" of the padding variable + * _new: the variable to use now instead of the padding variable + */ +#define KABI_USE(number, _new) __KABI_REPLACE(KABI_RESERVE(number), _new) + +/* + * KABI_USE2(number, _new1, _new2) + * Use a previous padding entry that was defined with KABI_RESERVE for + * two new variables that fit into 64 bits. This is good for when you do not + * want to "burn" a 64bit padding variable for a smaller variable size if not + * needed. + */ +#define KABI_USE2(number, _new1, _new2) \ + __KABI_REPLACE( \ + KABI_RESERVE(number), struct { \ + _new1; \ + _new2; \ + }) +/* + * KABI_USE_ARRAY(number, bytes, _new) + * Use a previous padding entry that was defined with KABI_RESERVE_ARRAY + * number: the previous "number" of the padding variable + * bytes: the size in bytes reserved for the array + * _new: the variable to use now instead of the padding variable + */ +#define KABI_USE_ARRAY(number, bytes, _new) \ + __KABI_REPLACE(KABI_RESERVE_ARRAY(number, bytes), _new) + +#endif /* __KABI_H__ */ diff --git a/scripts/gendwarfksyms/examples/kabi_ex.c b/scripts/gendwarfksyms/examples/kabi_ex.c new file mode 100644 index 000000000000..0b7ffd830541 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kabi_ex.c + * + * Copyright (C) 2024 Google LLC + * + * Examples for kABI stability features with --stable. See kabi_ex.h + * for details. + */ + +#include "kabi_ex.h" + +struct s e0; +enum e e1; + +struct ex0a ex0a; +struct ex0b ex0b; +struct ex0c ex0c; + +struct ex1a ex1a; +struct ex1b ex1b; +struct ex1c ex1c; + +struct ex2a ex2a; +struct ex2b ex2b; +struct ex2c ex2c; + +struct ex3a ex3a; +struct ex3b ex3b; +struct ex3c ex3c; diff --git a/scripts/gendwarfksyms/examples/kabi_ex.h b/scripts/gendwarfksyms/examples/kabi_ex.h new file mode 100644 index 000000000000..1736e0f65208 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * kabi_ex.h + * + * Copyright (C) 2024 Google LLC + * + * Examples for kABI stability features with --stable. + */ + +/* + * The comments below each example contain the expected gendwarfksyms + * output, which can be verified using LLVM's FileCheck tool: + * + * https://llvm.org/docs/CommandGuide/FileCheck.html + * + * Usage: + * + * $ gcc -g -c examples/kabi_ex.c -o examples/kabi_ex.o + * + * $ nm examples/kabi_ex.o | awk '{ print $NF }' | \ + * ./gendwarfksyms --stable --dump-dies \ + * examples/kabi_ex.o 2>&1 >/dev/null | \ + * FileCheck examples/kabi_ex.h --check-prefix=STABLE + */ + +#ifndef __KABI_EX_H__ +#define __KABI_EX_H__ + +#include "kabi.h" + +/* + * Example: kABI rules + */ + +struct s { + int a; +}; + +KABI_DECLONLY(s); + +/* + * STABLE: variable structure_type s { + * STABLE-NEXT: } + */ + +enum e { + A, + B, + C, + D, +}; + +KABI_ENUMERATOR_IGNORE(e, B); +KABI_ENUMERATOR_IGNORE(e, C); +KABI_ENUMERATOR_VALUE(e, D, 123456789); + +/* + * STABLE: variable enumeration_type e { + * STABLE-NEXT: enumerator A = 0 , + * STABLE-NEXT: enumerator D = 123456789 + * STABLE-NEXT: } byte_size(4) +*/ + +/* + * Example: Reserved fields + */ +struct ex0a { + int a; + KABI_RESERVE(0); + KABI_RESERVE(1); +}; + +/* + * STABLE: variable structure_type ex0a { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +struct ex0b { + int a; + KABI_RESERVE(0); + KABI_USE2(1, int b, int c); +}; + +/* + * STABLE: variable structure_type ex0b { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +struct ex0c { + int a; + KABI_USE(0, void *p); + KABI_USE2(1, int b, int c); +}; + +/* + * STABLE: variable structure_type ex0c { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +/* + * Example: A reserved array + */ + +struct ex1a { + unsigned int a; + KABI_RESERVE_ARRAY(0, 64); +}; + +/* + * STABLE: variable structure_type ex1a { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +struct ex1b { + unsigned int a; + KABI_USE_ARRAY( + 0, 64, struct { + void *p; + KABI_RESERVE_ARRAY(1, 56); + }); +}; + +/* + * STABLE: variable structure_type ex1b { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +struct ex1c { + unsigned int a; + KABI_USE_ARRAY(0, 64, void *p[8]); +}; + +/* + * STABLE: variable structure_type ex1c { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +/* + * Example: An ignored field added to an alignment hole + */ + +struct ex2a { + int a; + unsigned long b; + int c; + unsigned long d; +}; + +/* + * STABLE: variable structure_type ex2a { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + +struct ex2b { + int a; + KABI_IGNORE(0, unsigned int n); + unsigned long b; + int c; + unsigned long d; +}; + +_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2b), "ex2a size doesn't match ex2b"); + +/* + * STABLE: variable structure_type ex2b { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + +struct ex2c { + int a; + KABI_IGNORE(0, unsigned int n); + unsigned long b; + int c; + KABI_IGNORE(1, unsigned int m); + unsigned long d; +}; + +_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2c), "ex2a size doesn't match ex2c"); + +/* + * STABLE: variable structure_type ex2c { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + + +/* + * Example: A replaced field + */ + +struct ex3a { + unsigned long a; + unsigned long unused; +}; + +/* + * STABLE: variable structure_type ex3a { + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +struct ex3b { + unsigned long a; + KABI_REPLACE(unsigned long, unused, unsigned long renamed); +}; + +_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3b), "ex3a size doesn't match ex3b"); + +/* + * STABLE: variable structure_type ex3b { + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +struct ex3c { + unsigned long a; + KABI_REPLACE(unsigned long, unused, long replaced); +}; + +_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3c), "ex3a size doesn't match ex3c"); + +/* + * STABLE: variable structure_type ex3c { + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +#endif /* __KABI_EX_H__ */ diff --git a/scripts/gendwarfksyms/examples/symbolptr.c b/scripts/gendwarfksyms/examples/symbolptr.c new file mode 100644 index 000000000000..88bc1bd60da8 --- /dev/null +++ b/scripts/gendwarfksyms/examples/symbolptr.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + * + * Example for symbol pointers. When compiled with Clang, gendwarfkyms + * uses a symbol pointer for `f`. + * + * $ clang -g -c examples/symbolptr.c -o examples/symbolptr.o + * $ echo -e "f\ng\np" | ./gendwarfksyms -d examples/symbolptr.o + */ + +/* Kernel macros for userspace testing. */ +#ifndef __used +#define __used __attribute__((__used__)) +#endif +#ifndef __section +#define __section(section) __attribute__((__section__(section))) +#endif + +#define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; + +extern void f(unsigned int arg); +void g(int *arg); +void g(int *arg) {} + +struct s; +extern struct s *p; + +__GENDWARFKSYMS_EXPORT(f); +__GENDWARFKSYMS_EXPORT(g); +__GENDWARFKSYMS_EXPORT(p); diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c new file mode 100644 index 000000000000..08ae61eb327e --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <fcntl.h> +#include <getopt.h> +#include <errno.h> +#include <stdarg.h> +#include <string.h> +#include <unistd.h> +#include "gendwarfksyms.h" + +/* + * Options + */ + +/* Print debugging information to stderr */ +int debug; +/* Dump DIE contents */ +int dump_dies; +/* Print debugging information about die_map changes */ +int dump_die_map; +/* Print out type strings (i.e. type_map) */ +int dump_types; +/* Print out expanded type strings used for symbol versions */ +int dump_versions; +/* Support kABI stability features */ +int stable; +/* Write a symtypes file */ +int symtypes; +static const char *symtypes_file; + +static void usage(void) +{ + fputs("Usage: gendwarfksyms [options] elf-object-file ... < symbol-list\n\n" + "Options:\n" + " -d, --debug Print debugging information\n" + " --dump-dies Dump DWARF DIE contents\n" + " --dump-die-map Print debugging information about die_map changes\n" + " --dump-types Dump type strings\n" + " --dump-versions Dump expanded type strings used for symbol versions\n" + " -s, --stable Support kABI stability features\n" + " -T, --symtypes file Write a symtypes file\n" + " -h, --help Print this message\n" + "\n", + stderr); +} + +static int process_module(Dwfl_Module *mod, void **userdata, const char *name, + Dwarf_Addr base, void *arg) +{ + Dwarf_Addr dwbias; + Dwarf_Die cudie; + Dwarf_CU *cu = NULL; + Dwarf *dbg; + FILE *symfile = arg; + int res; + + debug("%s", name); + dbg = dwfl_module_getdwarf(mod, &dwbias); + + /* + * Look for exported symbols in each CU, follow the DIE tree, and add + * the entries to die_map. + */ + do { + res = dwarf_get_units(dbg, cu, &cu, NULL, NULL, &cudie, NULL); + if (res < 0) + error("dwarf_get_units failed: no debugging information?"); + if (res == 1) + break; /* No more units */ + + process_cu(&cudie); + } while (cu); + + /* + * Use die_map to expand type strings, write them to `symfile`, and + * calculate symbol versions. + */ + generate_symtypes_and_versions(symfile); + die_map_free(); + + return DWARF_CB_OK; +} + +static const Dwfl_Callbacks callbacks = { + .section_address = dwfl_offline_section_address, + .find_debuginfo = dwfl_standard_find_debuginfo, +}; + +int main(int argc, char **argv) +{ + FILE *symfile = NULL; + unsigned int n; + int opt; + + static const struct option opts[] = { + { "debug", 0, NULL, 'd' }, + { "dump-dies", 0, &dump_dies, 1 }, + { "dump-die-map", 0, &dump_die_map, 1 }, + { "dump-types", 0, &dump_types, 1 }, + { "dump-versions", 0, &dump_versions, 1 }, + { "stable", 0, NULL, 's' }, + { "symtypes", 1, NULL, 'T' }, + { "help", 0, NULL, 'h' }, + { 0, 0, NULL, 0 } + }; + + while ((opt = getopt_long(argc, argv, "dsT:h", opts, NULL)) != EOF) { + switch (opt) { + case 0: + break; + case 'd': + debug = 1; + break; + case 's': + stable = 1; + break; + case 'T': + symtypes = 1; + symtypes_file = optarg; + break; + case 'h': + usage(); + return 0; + default: + usage(); + return 1; + } + } + + if (dump_die_map) + dump_dies = 1; + + if (optind >= argc) { + usage(); + error("no input files?"); + } + + symbol_read_exports(stdin); + + if (symtypes_file) { + symfile = fopen(symtypes_file, "w"); + if (!symfile) + error("fopen failed for '%s': %s", symtypes_file, + strerror(errno)); + } + + for (n = optind; n < argc; n++) { + Dwfl *dwfl; + int fd; + + fd = open(argv[n], O_RDONLY); + if (fd == -1) + error("open failed for '%s': %s", argv[n], + strerror(errno)); + + symbol_read_symtab(fd); + kabi_read_rules(fd); + + dwfl = dwfl_begin(&callbacks); + if (!dwfl) + error("dwfl_begin failed for '%s': %s", argv[n], + dwarf_errmsg(-1)); + + if (!dwfl_report_offline(dwfl, argv[n], argv[n], fd)) + error("dwfl_report_offline failed for '%s': %s", + argv[n], dwarf_errmsg(-1)); + + dwfl_report_end(dwfl, NULL, NULL); + + if (dwfl_getmodules(dwfl, &process_module, symfile, 0)) + error("dwfl_getmodules failed for '%s'", argv[n]); + + dwfl_end(dwfl); + kabi_free(); + } + + if (symfile) + check(fclose(symfile)); + + symbol_print_versions(); + symbol_free(); + + return 0; +} diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h new file mode 100644 index 000000000000..2feec168bf73 --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Google LLC + */ + +#include <dwarf.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <stdlib.h> +#include <stdio.h> + +#include <hash.h> +#include <hashtable.h> +#include <xalloc.h> + +#ifndef __GENDWARFKSYMS_H +#define __GENDWARFKSYMS_H + +/* + * Options -- in gendwarfksyms.c + */ +extern int debug; +extern int dump_dies; +extern int dump_die_map; +extern int dump_types; +extern int dump_versions; +extern int stable; +extern int symtypes; + +/* + * Output helpers + */ +#define __PREFIX "gendwarfksyms: " +#define __println(prefix, format, ...) \ + fprintf(stderr, prefix __PREFIX "%s: " format "\n", __func__, \ + ##__VA_ARGS__) + +#define debug(format, ...) \ + do { \ + if (debug) \ + __println("", format, ##__VA_ARGS__); \ + } while (0) + +#define warn(format, ...) __println("warning: ", format, ##__VA_ARGS__) +#define error(format, ...) \ + do { \ + __println("error: ", format, ##__VA_ARGS__); \ + exit(1); \ + } while (0) + +#define __die_debug(color, format, ...) \ + do { \ + if (dump_dies && dump_die_map) \ + fprintf(stderr, \ + "\033[" #color "m<" format ">\033[39m", \ + __VA_ARGS__); \ + } while (0) + +#define die_debug_r(format, ...) __die_debug(91, format, __VA_ARGS__) +#define die_debug_g(format, ...) __die_debug(92, format, __VA_ARGS__) +#define die_debug_b(format, ...) __die_debug(94, format, __VA_ARGS__) + +/* + * Error handling helpers + */ +#define __check(expr, test) \ + ({ \ + int __res = expr; \ + if (test) \ + error("`%s` failed: %d", #expr, __res); \ + __res; \ + }) + +/* Error == non-zero values */ +#define check(expr) __check(expr, __res) +/* Error == negative values */ +#define checkp(expr) __check(expr, __res < 0) + +/* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */ +#define DW_TAG_enumerator_type DW_TAG_enumerator +#define DW_TAG_formal_parameter_type DW_TAG_formal_parameter +#define DW_TAG_member_type DW_TAG_member +#define DW_TAG_template_type_parameter_type DW_TAG_template_type_parameter +#define DW_TAG_typedef_type DW_TAG_typedef +#define DW_TAG_variant_part_type DW_TAG_variant_part +#define DW_TAG_variant_type DW_TAG_variant + +/* + * symbols.c + */ + +/* See symbols.c:is_symbol_ptr */ +#define SYMBOL_PTR_PREFIX "__gendwarfksyms_ptr_" +#define SYMBOL_PTR_PREFIX_LEN (sizeof(SYMBOL_PTR_PREFIX) - 1) + +static inline unsigned int addr_hash(uintptr_t addr) +{ + return hash_ptr((const void *)addr); +} + +enum symbol_state { + SYMBOL_UNPROCESSED, + SYMBOL_MAPPED, + SYMBOL_PROCESSED +}; + +struct symbol_addr { + uint32_t section; + Elf64_Addr address; +}; + +struct symbol { + const char *name; + struct symbol_addr addr; + struct hlist_node addr_hash; + struct hlist_node name_hash; + enum symbol_state state; + uintptr_t die_addr; + uintptr_t ptr_die_addr; + unsigned long crc; +}; + +typedef void (*symbol_callback_t)(struct symbol *, void *arg); + +bool is_symbol_ptr(const char *name); +void symbol_read_exports(FILE *file); +void symbol_read_symtab(int fd); +struct symbol *symbol_get(const char *name); +void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr); +void symbol_set_die(struct symbol *sym, Dwarf_Die *die); +void symbol_set_crc(struct symbol *sym, unsigned long crc); +void symbol_for_each(symbol_callback_t func, void *arg); +void symbol_print_versions(void); +void symbol_free(void); + +/* + * die.c + */ + +enum die_state { + DIE_INCOMPLETE, + DIE_FQN, + DIE_UNEXPANDED, + DIE_COMPLETE, + DIE_SYMBOL, + DIE_LAST = DIE_SYMBOL +}; + +enum die_fragment_type { + FRAGMENT_EMPTY, + FRAGMENT_STRING, + FRAGMENT_LINEBREAK, + FRAGMENT_DIE +}; + +struct die_fragment { + enum die_fragment_type type; + union { + char *str; + int linebreak; + uintptr_t addr; + } data; + struct list_head list; +}; + +#define CASE_CONST_TO_STR(name) \ + case name: \ + return #name; + +static inline const char *die_state_name(enum die_state state) +{ + switch (state) { + CASE_CONST_TO_STR(DIE_INCOMPLETE) + CASE_CONST_TO_STR(DIE_FQN) + CASE_CONST_TO_STR(DIE_UNEXPANDED) + CASE_CONST_TO_STR(DIE_COMPLETE) + CASE_CONST_TO_STR(DIE_SYMBOL) + } + + error("unexpected die_state: %d", state); +} + +struct die { + enum die_state state; + bool mapped; + char *fqn; + int tag; + uintptr_t addr; + struct list_head fragments; + struct hlist_node hash; +}; + +typedef void (*die_map_callback_t)(struct die *, void *arg); + +int __die_map_get(uintptr_t addr, enum die_state state, struct die **res); +struct die *die_map_get(Dwarf_Die *die, enum die_state state); +void die_map_add_string(struct die *pd, const char *str); +void die_map_add_linebreak(struct die *pd, int linebreak); +void die_map_for_each(die_map_callback_t func, void *arg); +void die_map_add_die(struct die *pd, struct die *child); +void die_map_free(void); + +/* + * cache.c + */ + +#define CACHE_HASH_BITS 10 + +/* A cache for addresses we've already seen. */ +struct cache { + HASHTABLE_DECLARE(cache, 1 << CACHE_HASH_BITS); +}; + +void cache_set(struct cache *cache, unsigned long key, int value); +int cache_get(struct cache *cache, unsigned long key); +void cache_init(struct cache *cache); +void cache_free(struct cache *cache); + +static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr) +{ + cache_set(cache, addr, 1); +} + +static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr) +{ + return cache_get(cache, addr) == 1; +} + +static inline void cache_mark_expanded(struct cache *cache, void *addr) +{ + __cache_mark_expanded(cache, (uintptr_t)addr); +} + +static inline bool cache_was_expanded(struct cache *cache, void *addr) +{ + return __cache_was_expanded(cache, (uintptr_t)addr); +} + +/* + * dwarf.c + */ + +struct expansion_state { + bool expand; + const char *current_fqn; +}; + +struct kabi_state { + int members; + Dwarf_Die placeholder; + const char *orig_name; +}; + +struct state { + struct symbol *sym; + Dwarf_Die die; + + /* List expansion */ + bool first_list_item; + + /* Structure expansion */ + struct expansion_state expand; + struct cache expansion_cache; + + /* Reserved or ignored members */ + struct kabi_state kabi; +}; + +typedef int (*die_callback_t)(struct state *state, struct die *cache, + Dwarf_Die *die); +typedef bool (*die_match_callback_t)(Dwarf_Die *die); +bool match_all(Dwarf_Die *die); + +int process_die_container(struct state *state, struct die *cache, + Dwarf_Die *die, die_callback_t func, + die_match_callback_t match); + +void process_cu(Dwarf_Die *cudie); + +/* + * types.c + */ + +void generate_symtypes_and_versions(FILE *file); + +/* + * kabi.c + */ + +bool kabi_is_enumerator_ignored(const char *fqn, const char *field); +bool kabi_get_enumerator_value(const char *fqn, const char *field, + unsigned long *value); +bool kabi_is_declonly(const char *fqn); + +void kabi_read_rules(int fd); +void kabi_free(void); + +#endif /* __GENDWARFKSYMS_H */ diff --git a/scripts/gendwarfksyms/kabi.c b/scripts/gendwarfksyms/kabi.c new file mode 100644 index 000000000000..66f01fcd1607 --- /dev/null +++ b/scripts/gendwarfksyms/kabi.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> + +#include "gendwarfksyms.h" + +#define KABI_RULE_SECTION ".discard.gendwarfksyms.kabi_rules" +#define KABI_RULE_VERSION "1" + +/* + * The rule section consists of four null-terminated strings per + * entry: + * + * 1. version + * Entry format version. Must match KABI_RULE_VERSION. + * + * 2. type + * Type of the kABI rule. Must be one of the tags defined below. + * + * 3. target + * Rule-dependent target, typically the fully qualified name of + * the target DIE. + * + * 4. value + * Rule-dependent value. + */ +#define KABI_RULE_MIN_ENTRY_SIZE \ + (/* version\0 */ 2 + /* type\0 */ 2 + /* target\0" */ 1 + \ + /* value\0 */ 1) +#define KABI_RULE_EMPTY_VALUE "" + +/* + * Rule: declonly + * - For the struct/enum/union in the target field, treat it as a + * declaration only even if a definition is available. + */ +#define KABI_RULE_TAG_DECLONLY "declonly" + +/* + * Rule: enumerator_ignore + * - For the enum_field in the target field, ignore the enumerator. + */ +#define KABI_RULE_TAG_ENUMERATOR_IGNORE "enumerator_ignore" + +/* + * Rule: enumerator_value + * - For the fqn_field in the target field, set the value to the + * unsigned integer in the value field. + */ +#define KABI_RULE_TAG_ENUMERATOR_VALUE "enumerator_value" + +enum kabi_rule_type { + KABI_RULE_TYPE_UNKNOWN, + KABI_RULE_TYPE_DECLONLY, + KABI_RULE_TYPE_ENUMERATOR_IGNORE, + KABI_RULE_TYPE_ENUMERATOR_VALUE, +}; + +#define RULE_HASH_BITS 7 + +struct rule { + enum kabi_rule_type type; + const char *target; + const char *value; + struct hlist_node hash; +}; + +/* { type, target } -> struct rule */ +static HASHTABLE_DEFINE(rules, 1 << RULE_HASH_BITS); + +static inline unsigned int rule_values_hash(enum kabi_rule_type type, + const char *target) +{ + return hash_32(type) ^ hash_str(target); +} + +static inline unsigned int rule_hash(const struct rule *rule) +{ + return rule_values_hash(rule->type, rule->target); +} + +static inline const char *get_rule_field(const char **pos, ssize_t *left) +{ + const char *start = *pos; + size_t len; + + if (*left <= 0) + error("unexpected end of kABI rules"); + + len = strnlen(start, *left) + 1; + *pos += len; + *left -= len; + + return start; +} + +void kabi_read_rules(int fd) +{ + GElf_Shdr shdr_mem; + GElf_Shdr *shdr; + Elf_Data *rule_data = NULL; + Elf_Scn *scn; + Elf *elf; + size_t shstrndx; + const char *rule_str; + ssize_t left; + int i; + + const struct { + enum kabi_rule_type type; + const char *tag; + } rule_types[] = { + { + .type = KABI_RULE_TYPE_DECLONLY, + .tag = KABI_RULE_TAG_DECLONLY, + }, + { + .type = KABI_RULE_TYPE_ENUMERATOR_IGNORE, + .tag = KABI_RULE_TAG_ENUMERATOR_IGNORE, + }, + { + .type = KABI_RULE_TYPE_ENUMERATOR_VALUE, + .tag = KABI_RULE_TAG_ENUMERATOR_VALUE, + }, + }; + + if (!stable) + return; + + if (elf_version(EV_CURRENT) != EV_CURRENT) + error("elf_version failed: %s", elf_errmsg(-1)); + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) + error("elf_begin failed: %s", elf_errmsg(-1)); + + if (elf_getshdrstrndx(elf, &shstrndx) < 0) + error("elf_getshdrstrndx failed: %s", elf_errmsg(-1)); + + scn = elf_nextscn(elf, NULL); + + while (scn) { + const char *sname; + + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + sname = elf_strptr(elf, shstrndx, shdr->sh_name); + if (!sname) + error("elf_strptr failed: %s", elf_errmsg(-1)); + + if (!strcmp(sname, KABI_RULE_SECTION)) { + rule_data = elf_getdata(scn, NULL); + if (!rule_data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + break; + } + + scn = elf_nextscn(elf, scn); + } + + if (!rule_data) { + debug("kABI rules not found"); + check(elf_end(elf)); + return; + } + + rule_str = rule_data->d_buf; + left = shdr->sh_size; + + if (left < KABI_RULE_MIN_ENTRY_SIZE) + error("kABI rule section too small: %zd bytes", left); + + if (rule_str[left - 1] != '\0') + error("kABI rules are not null-terminated"); + + while (left > KABI_RULE_MIN_ENTRY_SIZE) { + enum kabi_rule_type type = KABI_RULE_TYPE_UNKNOWN; + const char *field; + struct rule *rule; + + /* version */ + field = get_rule_field(&rule_str, &left); + + if (strcmp(field, KABI_RULE_VERSION)) + error("unsupported kABI rule version: '%s'", field); + + /* type */ + field = get_rule_field(&rule_str, &left); + + for (i = 0; i < ARRAY_SIZE(rule_types); i++) { + if (!strcmp(field, rule_types[i].tag)) { + type = rule_types[i].type; + break; + } + } + + if (type == KABI_RULE_TYPE_UNKNOWN) + error("unsupported kABI rule type: '%s'", field); + + rule = xmalloc(sizeof(struct rule)); + + rule->type = type; + rule->target = xstrdup(get_rule_field(&rule_str, &left)); + rule->value = xstrdup(get_rule_field(&rule_str, &left)); + + hash_add(rules, &rule->hash, rule_hash(rule)); + + debug("kABI rule: type: '%s', target: '%s', value: '%s'", field, + rule->target, rule->value); + } + + if (left > 0) + warn("unexpected data at the end of the kABI rules section"); + + check(elf_end(elf)); +} + +bool kabi_is_declonly(const char *fqn) +{ + struct rule *rule; + + if (!stable) + return false; + if (!fqn || !*fqn) + return false; + + hash_for_each_possible(rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_DECLONLY, fqn)) { + if (rule->type == KABI_RULE_TYPE_DECLONLY && + !strcmp(fqn, rule->target)) + return true; + } + + return false; +} + +static char *get_enumerator_target(const char *fqn, const char *field) +{ + char *target = NULL; + + if (asprintf(&target, "%s %s", fqn, field) < 0) + error("asprintf failed for '%s %s'", fqn, field); + + return target; +} + +static unsigned long get_ulong_value(const char *value) +{ + unsigned long result = 0; + char *endptr = NULL; + + errno = 0; + result = strtoul(value, &endptr, 10); + + if (errno || *endptr) + error("invalid unsigned value '%s'", value); + + return result; +} + +bool kabi_is_enumerator_ignored(const char *fqn, const char *field) +{ + bool match = false; + struct rule *rule; + char *target; + + if (!stable) + return false; + if (!fqn || !*fqn || !field || !*field) + return false; + + target = get_enumerator_target(fqn, field); + + hash_for_each_possible( + rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_IGNORE, target)) { + if (rule->type == KABI_RULE_TYPE_ENUMERATOR_IGNORE && + !strcmp(target, rule->target)) { + match = true; + break; + } + } + + free(target); + return match; +} + +bool kabi_get_enumerator_value(const char *fqn, const char *field, + unsigned long *value) +{ + bool match = false; + struct rule *rule; + char *target; + + if (!stable) + return false; + if (!fqn || !*fqn || !field || !*field) + return false; + + target = get_enumerator_target(fqn, field); + + hash_for_each_possible(rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_VALUE, + target)) { + if (rule->type == KABI_RULE_TYPE_ENUMERATOR_VALUE && + !strcmp(target, rule->target)) { + *value = get_ulong_value(rule->value); + match = true; + break; + } + } + + free(target); + return match; +} + +void kabi_free(void) +{ + struct hlist_node *tmp; + struct rule *rule; + + hash_for_each_safe(rules, rule, tmp, hash) { + free((void *)rule->target); + free((void *)rule->value); + free(rule); + } + + hash_init(rules); +} diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c new file mode 100644 index 000000000000..327f87389c34 --- /dev/null +++ b/scripts/gendwarfksyms/symbols.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +#define SYMBOL_HASH_BITS 12 + +/* struct symbol_addr -> struct symbol */ +static HASHTABLE_DEFINE(symbol_addrs, 1 << SYMBOL_HASH_BITS); +/* name -> struct symbol */ +static HASHTABLE_DEFINE(symbol_names, 1 << SYMBOL_HASH_BITS); + +static inline unsigned int symbol_addr_hash(const struct symbol_addr *addr) +{ + return hash_32(addr->section ^ addr_hash(addr->address)); +} + +static unsigned int __for_each_addr(struct symbol *sym, symbol_callback_t func, + void *data) +{ + struct hlist_node *tmp; + struct symbol *match = NULL; + unsigned int processed = 0; + + hash_for_each_possible_safe(symbol_addrs, match, tmp, addr_hash, + symbol_addr_hash(&sym->addr)) { + if (match == sym) + continue; /* Already processed */ + + if (match->addr.section == sym->addr.section && + match->addr.address == sym->addr.address) { + func(match, data); + ++processed; + } + } + + return processed; +} + +/* + * For symbols without debugging information (e.g. symbols defined in other + * TUs), we also match __gendwarfksyms_ptr_<symbol_name> symbols, which the + * kernel uses to ensure type information is present in the TU that exports + * the symbol. A __gendwarfksyms_ptr pointer must have the same type as the + * exported symbol, e.g.: + * + * typeof(symname) *__gendwarf_ptr_symname = &symname; + */ +bool is_symbol_ptr(const char *name) +{ + return name && !strncmp(name, SYMBOL_PTR_PREFIX, SYMBOL_PTR_PREFIX_LEN); +} + +static unsigned int for_each(const char *name, symbol_callback_t func, + void *data) +{ + struct hlist_node *tmp; + struct symbol *match; + + if (!name || !*name) + return 0; + if (is_symbol_ptr(name)) + name += SYMBOL_PTR_PREFIX_LEN; + + hash_for_each_possible_safe(symbol_names, match, tmp, name_hash, + hash_str(name)) { + if (strcmp(match->name, name)) + continue; + + /* Call func for the match, and all address matches */ + if (func) + func(match, data); + + if (match->addr.section != SHN_UNDEF) + return __for_each_addr(match, func, data) + 1; + + return 1; + } + + return 0; +} + +static void set_crc(struct symbol *sym, void *data) +{ + unsigned long *crc = data; + + if (sym->state == SYMBOL_PROCESSED && sym->crc != *crc) + warn("overriding version for symbol %s (crc %lx vs. %lx)", + sym->name, sym->crc, *crc); + + sym->state = SYMBOL_PROCESSED; + sym->crc = *crc; +} + +void symbol_set_crc(struct symbol *sym, unsigned long crc) +{ + if (for_each(sym->name, set_crc, &crc) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static void set_ptr(struct symbol *sym, void *data) +{ + sym->ptr_die_addr = (uintptr_t)((Dwarf_Die *)data)->addr; +} + +void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr) +{ + if (for_each(sym->name, set_ptr, ptr) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static void set_die(struct symbol *sym, void *data) +{ + sym->die_addr = (uintptr_t)((Dwarf_Die *)data)->addr; + sym->state = SYMBOL_MAPPED; +} + +void symbol_set_die(struct symbol *sym, Dwarf_Die *die) +{ + if (for_each(sym->name, set_die, die) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static bool is_exported(const char *name) +{ + return for_each(name, NULL, NULL) > 0; +} + +void symbol_read_exports(FILE *file) +{ + struct symbol *sym; + char *line = NULL; + char *name = NULL; + size_t size = 0; + int nsym = 0; + + while (getline(&line, &size, file) > 0) { + if (sscanf(line, "%ms\n", &name) != 1) + error("malformed input line: %s", line); + + if (is_exported(name)) { + /* Ignore duplicates */ + free(name); + continue; + } + + sym = xcalloc(1, sizeof(struct symbol)); + sym->name = name; + sym->addr.section = SHN_UNDEF; + sym->state = SYMBOL_UNPROCESSED; + + hash_add(symbol_names, &sym->name_hash, hash_str(sym->name)); + ++nsym; + + debug("%s", sym->name); + } + + free(line); + debug("%d exported symbols", nsym); +} + +static void get_symbol(struct symbol *sym, void *arg) +{ + struct symbol **res = arg; + + if (sym->state == SYMBOL_UNPROCESSED) + *res = sym; +} + +struct symbol *symbol_get(const char *name) +{ + struct symbol *sym = NULL; + + for_each(name, get_symbol, &sym); + return sym; +} + +void symbol_for_each(symbol_callback_t func, void *arg) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + func(sym, arg); + } +} + +typedef void (*elf_symbol_callback_t)(const char *name, GElf_Sym *sym, + Elf32_Word xndx, void *arg); + +static void elf_for_each_global(int fd, elf_symbol_callback_t func, void *arg) +{ + size_t sym_size; + GElf_Shdr shdr_mem; + GElf_Shdr *shdr; + Elf_Data *xndx_data = NULL; + Elf_Scn *scn; + Elf *elf; + + if (elf_version(EV_CURRENT) != EV_CURRENT) + error("elf_version failed: %s", elf_errmsg(-1)); + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) + error("elf_begin failed: %s", elf_errmsg(-1)); + + scn = elf_nextscn(elf, NULL); + + while (scn) { + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + if (shdr->sh_type == SHT_SYMTAB_SHNDX) { + xndx_data = elf_getdata(scn, NULL); + if (!xndx_data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + break; + } + + scn = elf_nextscn(elf, scn); + } + + sym_size = gelf_fsize(elf, ELF_T_SYM, 1, EV_CURRENT); + scn = elf_nextscn(elf, NULL); + + while (scn) { + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + if (shdr->sh_type == SHT_SYMTAB) { + unsigned int nsyms; + unsigned int n; + Elf_Data *data = elf_getdata(scn, NULL); + + if (!data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + + if (shdr->sh_entsize != sym_size) + error("expected sh_entsize (%lu) to be %zu", + shdr->sh_entsize, sym_size); + + nsyms = shdr->sh_size / shdr->sh_entsize; + + for (n = 1; n < nsyms; ++n) { + const char *name = NULL; + Elf32_Word xndx = 0; + GElf_Sym sym_mem; + GElf_Sym *sym; + + sym = gelf_getsymshndx(data, xndx_data, n, + &sym_mem, &xndx); + if (!sym) + error("gelf_getsymshndx failed: %s", + elf_errmsg(-1)); + + if (GELF_ST_BIND(sym->st_info) == STB_LOCAL) + continue; + + if (sym->st_shndx != SHN_XINDEX) + xndx = sym->st_shndx; + + name = elf_strptr(elf, shdr->sh_link, + sym->st_name); + if (!name) + error("elf_strptr failed: %s", + elf_errmsg(-1)); + + /* Skip empty symbol names */ + if (*name) + func(name, sym, xndx, arg); + } + } + + scn = elf_nextscn(elf, scn); + } + + check(elf_end(elf)); +} + +static void set_symbol_addr(struct symbol *sym, void *arg) +{ + struct symbol_addr *addr = arg; + + if (sym->addr.section == SHN_UNDEF) { + sym->addr = *addr; + hash_add(symbol_addrs, &sym->addr_hash, + symbol_addr_hash(&sym->addr)); + + debug("%s -> { %u, %lx }", sym->name, sym->addr.section, + sym->addr.address); + } else if (sym->addr.section != addr->section || + sym->addr.address != addr->address) { + warn("multiple addresses for symbol %s?", sym->name); + } +} + +static void elf_set_symbol_addr(const char *name, GElf_Sym *sym, + Elf32_Word xndx, void *arg) +{ + struct symbol_addr addr = { .section = xndx, .address = sym->st_value }; + + /* Set addresses for exported symbols */ + if (addr.section != SHN_UNDEF) + for_each(name, set_symbol_addr, &addr); +} + +void symbol_read_symtab(int fd) +{ + elf_for_each_global(fd, elf_set_symbol_addr, NULL); +} + +void symbol_print_versions(void) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + if (sym->state != SYMBOL_PROCESSED) + warn("no information for symbol %s", sym->name); + + printf("#SYMVER %s 0x%08lx\n", sym->name, sym->crc); + } +} + +void symbol_free(void) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + free((void *)sym->name); + free(sym); + } + + hash_init(symbol_addrs); + hash_init(symbol_names); +} diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c new file mode 100644 index 000000000000..6f37289104ff --- /dev/null +++ b/scripts/gendwarfksyms/types.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <inttypes.h> +#include <stdio.h> +#include <zlib.h> + +#include "gendwarfksyms.h" + +static struct cache expansion_cache; + +/* + * A simple linked list of shared or owned strings to avoid copying strings + * around when not necessary. + */ +struct type_list_entry { + const char *str; + void *owned; + struct list_head list; +}; + +static void type_list_free(struct list_head *list) +{ + struct type_list_entry *entry; + struct type_list_entry *tmp; + + list_for_each_entry_safe(entry, tmp, list, list) { + if (entry->owned) + free(entry->owned); + free(entry); + } + + INIT_LIST_HEAD(list); +} + +static int type_list_append(struct list_head *list, const char *s, void *owned) +{ + struct type_list_entry *entry; + + if (!s) + return 0; + + entry = xmalloc(sizeof(struct type_list_entry)); + entry->str = s; + entry->owned = owned; + list_add_tail(&entry->list, list); + + return strlen(entry->str); +} + +static void type_list_write(struct list_head *list, FILE *file) +{ + struct type_list_entry *entry; + + list_for_each_entry(entry, list, list) { + if (entry->str) + checkp(fputs(entry->str, file)); + } +} + +/* + * An expanded type string in symtypes format. + */ +struct type_expansion { + char *name; + size_t len; + struct list_head expanded; + struct hlist_node hash; +}; + +static void type_expansion_init(struct type_expansion *type) +{ + type->name = NULL; + type->len = 0; + INIT_LIST_HEAD(&type->expanded); +} + +static inline void type_expansion_free(struct type_expansion *type) +{ + free(type->name); + type->name = NULL; + type->len = 0; + type_list_free(&type->expanded); +} + +static void type_expansion_append(struct type_expansion *type, const char *s, + void *owned) +{ + type->len += type_list_append(&type->expanded, s, owned); +} + +/* + * type_map -- the longest expansions for each type. + * + * const char *name -> struct type_expansion * + */ +#define TYPE_HASH_BITS 12 +static HASHTABLE_DEFINE(type_map, 1 << TYPE_HASH_BITS); + +static int type_map_get(const char *name, struct type_expansion **res) +{ + struct type_expansion *e; + + hash_for_each_possible(type_map, e, hash, hash_str(name)) { + if (!strcmp(name, e->name)) { + *res = e; + return 0; + } + } + + return -1; +} + +static void type_map_add(const char *name, struct type_expansion *type) +{ + struct type_expansion *e; + + if (type_map_get(name, &e)) { + e = xmalloc(sizeof(struct type_expansion)); + type_expansion_init(e); + e->name = xstrdup(name); + + hash_add(type_map, &e->hash, hash_str(e->name)); + + if (dump_types) + debug("adding %s", e->name); + } else { + /* Use the longest available expansion */ + if (type->len <= e->len) + return; + + type_list_free(&e->expanded); + + if (dump_types) + debug("replacing %s", e->name); + } + + /* Take ownership of type->expanded */ + list_replace_init(&type->expanded, &e->expanded); + e->len = type->len; + + if (dump_types) { + checkp(fputs(e->name, stderr)); + checkp(fputs(" ", stderr)); + type_list_write(&e->expanded, stderr); + checkp(fputs("\n", stderr)); + } +} + +static void type_map_write(FILE *file) +{ + struct type_expansion *e; + struct hlist_node *tmp; + + if (!file) + return; + + hash_for_each_safe(type_map, e, tmp, hash) { + checkp(fputs(e->name, file)); + checkp(fputs(" ", file)); + type_list_write(&e->expanded, file); + checkp(fputs("\n", file)); + } +} + +static void type_map_free(void) +{ + struct type_expansion *e; + struct hlist_node *tmp; + + hash_for_each_safe(type_map, e, tmp, hash) { + type_expansion_free(e); + free(e); + } + + hash_init(type_map); +} + +/* + * CRC for a type, with an optional fully expanded type string for + * debugging. + */ +struct version { + struct type_expansion type; + unsigned long crc; +}; + +static void version_init(struct version *version) +{ + version->crc = crc32(0, NULL, 0); + type_expansion_init(&version->type); +} + +static void version_free(struct version *version) +{ + type_expansion_free(&version->type); +} + +static void version_add(struct version *version, const char *s) +{ + version->crc = crc32(version->crc, (void *)s, strlen(s)); + if (dump_versions) + type_expansion_append(&version->type, s, NULL); +} + +/* + * Type reference format: <prefix>#<name>, where prefix: + * s -> structure + * u -> union + * e -> enum + * t -> typedef + * + * Names with spaces are additionally wrapped in single quotes. + */ +static inline bool is_type_prefix(const char *s) +{ + return (s[0] == 's' || s[0] == 'u' || s[0] == 'e' || s[0] == 't') && + s[1] == '#'; +} + +static char get_type_prefix(int tag) +{ + switch (tag) { + case DW_TAG_class_type: + case DW_TAG_structure_type: + return 's'; + case DW_TAG_union_type: + return 'u'; + case DW_TAG_enumeration_type: + return 'e'; + case DW_TAG_typedef_type: + return 't'; + default: + return 0; + } +} + +static char *get_type_name(struct die *cache) +{ + const char *quote; + char prefix; + char *name; + + if (cache->state == DIE_INCOMPLETE) { + warn("found incomplete cache entry: %p", cache); + return NULL; + } + if (cache->state == DIE_SYMBOL || cache->state == DIE_FQN) + return NULL; + if (!cache->fqn || !*cache->fqn) + return NULL; + + prefix = get_type_prefix(cache->tag); + if (!prefix) + return NULL; + + /* Wrap names with spaces in single quotes */ + quote = strstr(cache->fqn, " ") ? "'" : ""; + + /* <prefix>#<type_name>\0 */ + if (asprintf(&name, "%c#%s%s%s", prefix, quote, cache->fqn, quote) < 0) + error("asprintf failed for '%s'", cache->fqn); + + return name; +} + +static void __calculate_version(struct version *version, struct list_head *list) +{ + struct type_list_entry *entry; + struct type_expansion *e; + + /* Calculate a CRC over an expanded type string */ + list_for_each_entry(entry, list, list) { + if (is_type_prefix(entry->str)) { + check(type_map_get(entry->str, &e)); + + /* + * It's sufficient to expand each type reference just + * once to detect changes. + */ + if (cache_was_expanded(&expansion_cache, e)) { + version_add(version, entry->str); + } else { + cache_mark_expanded(&expansion_cache, e); + __calculate_version(version, &e->expanded); + } + } else { + version_add(version, entry->str); + } + } +} + +static void calculate_version(struct version *version, struct list_head *list) +{ + version_init(version); + __calculate_version(version, list); + cache_free(&expansion_cache); +} + +static void __type_expand(struct die *cache, struct type_expansion *type, + bool recursive); + +static void type_expand_child(struct die *cache, struct type_expansion *type, + bool recursive) +{ + struct type_expansion child; + char *name; + + name = get_type_name(cache); + if (!name) { + __type_expand(cache, type, recursive); + return; + } + + if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) { + __cache_mark_expanded(&expansion_cache, cache->addr); + type_expansion_init(&child); + __type_expand(cache, &child, true); + type_map_add(name, &child); + type_expansion_free(&child); + } + + type_expansion_append(type, name, name); +} + +static void __type_expand(struct die *cache, struct type_expansion *type, + bool recursive) +{ + struct die_fragment *df; + struct die *child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + type_expansion_append(type, df->data.str, NULL); + break; + case FRAGMENT_DIE: + /* Use a complete die_map expansion if available */ + if (__die_map_get(df->data.addr, DIE_COMPLETE, + &child) && + __die_map_get(df->data.addr, DIE_UNEXPANDED, + &child)) + error("unknown child: %" PRIxPTR, + df->data.addr); + + type_expand_child(child, type, recursive); + break; + case FRAGMENT_LINEBREAK: + /* + * Keep whitespace in the symtypes format, but avoid + * repeated spaces. + */ + if (list_is_last(&df->list, &cache->fragments) || + list_next_entry(df, list)->type != + FRAGMENT_LINEBREAK) + type_expansion_append(type, " ", NULL); + break; + default: + error("empty die_fragment in %p", cache); + } + } +} + +static void type_expand(struct die *cache, struct type_expansion *type, + bool recursive) +{ + type_expansion_init(type); + __type_expand(cache, type, recursive); + cache_free(&expansion_cache); +} + +static void expand_type(struct die *cache, void *arg) +{ + struct type_expansion type; + char *name; + + if (cache->mapped) + return; + + cache->mapped = true; + + /* + * Skip unexpanded die_map entries if there's a complete + * expansion available for this DIE. + */ + if (cache->state == DIE_UNEXPANDED && + !__die_map_get(cache->addr, DIE_COMPLETE, &cache)) { + if (cache->mapped) + return; + + cache->mapped = true; + } + + name = get_type_name(cache); + if (!name) + return; + + debug("%s", name); + type_expand(cache, &type, true); + type_map_add(name, &type); + + type_expansion_free(&type); + free(name); +} + +static void expand_symbol(struct symbol *sym, void *arg) +{ + struct type_expansion type; + struct version version; + struct die *cache; + + /* + * No need to expand again unless we want a symtypes file entry + * for the symbol. Note that this means `sym` has the same address + * as another symbol that was already processed. + */ + if (!symtypes && sym->state == SYMBOL_PROCESSED) + return; + + if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache)) + return; /* We'll warn about missing CRCs later. */ + + type_expand(cache, &type, false); + + /* If the symbol already has a version, don't calculate it again. */ + if (sym->state != SYMBOL_PROCESSED) { + calculate_version(&version, &type.expanded); + symbol_set_crc(sym, version.crc); + debug("%s = %lx", sym->name, version.crc); + + if (dump_versions) { + checkp(fputs(sym->name, stderr)); + checkp(fputs(" ", stderr)); + type_list_write(&version.type.expanded, stderr); + checkp(fputs("\n", stderr)); + } + + version_free(&version); + } + + /* These aren't needed in type_map unless we want a symtypes file. */ + if (symtypes) + type_map_add(sym->name, &type); + + type_expansion_free(&type); +} + +void generate_symtypes_and_versions(FILE *file) +{ + cache_init(&expansion_cache); + + /* + * die_map processing: + * + * 1. die_map contains all types referenced in exported symbol + * signatures, but can contain duplicates just like the original + * DWARF, and some references may not be fully expanded depending + * on how far we processed the DIE tree for that specific symbol. + * + * For each die_map entry, find the longest available expansion, + * and add it to type_map. + */ + die_map_for_each(expand_type, NULL); + + /* + * 2. For each exported symbol, expand the die_map type, and use + * type_map expansions to calculate a symbol version from the + * fully expanded type string. + */ + symbol_for_each(expand_symbol, NULL); + + /* + * 3. If a symtypes file is requested, write type_map contents to + * the file. + */ + type_map_write(file); + type_map_free(); +} diff --git a/scripts/generate_builtin_ranges.awk b/scripts/generate_builtin_ranges.awk index b9ec761b3bef..d4bd5c2b998c 100755 --- a/scripts/generate_builtin_ranges.awk +++ b/scripts/generate_builtin_ranges.awk @@ -282,6 +282,11 @@ ARGIND == 2 && !anchor && NF == 2 && $1 ~ /^0x/ && $2 !~ /^0x/ { # section. # ARGIND == 2 && sect && NF == 4 && /^ [^ \*]/ && !($1 in sect_addend) { + # There are a few sections with constant data (without symbols) that + # can get resized during linking, so it is best to ignore them. + if ($1 ~ /^\.rodata\.(cst|str)[0-9]/) + next; + if (!($1 in sect_base)) { sect_base[$1] = base; diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py index 09e1d166d8d2..7c3ea2b55041 100755 --- a/scripts/generate_rust_analyzer.py +++ b/scripts/generate_rust_analyzer.py @@ -8,6 +8,7 @@ import json import logging import os import pathlib +import subprocess import sys def args_crates_cfgs(cfgs): @@ -18,7 +19,7 @@ def args_crates_cfgs(cfgs): return crates_cfgs -def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): +def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs, core_edition): # Generate the configuration list. cfg = [] with open(objtree / "include" / "generated" / "rustc_cfg") as fd: @@ -34,29 +35,50 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): crates_indexes = {} crates_cfgs = args_crates_cfgs(cfgs) - def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False): - crates_indexes[display_name] = len(crates) - crates.append({ + def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False, edition="2021"): + crate = { "display_name": display_name, "root_module": str(root_module), "is_workspace_member": is_workspace_member, "is_proc_macro": is_proc_macro, "deps": [{"crate": crates_indexes[dep], "name": dep} for dep in deps], "cfg": cfg, - "edition": "2021", + "edition": edition, "env": { "RUST_MODFILE": "This is only for rust-analyzer" } - }) - - # First, the ones in `rust/` since they are a bit special. - append_crate( - "core", - sysroot_src / "core" / "src" / "lib.rs", - [], - cfg=crates_cfgs.get("core", []), - is_workspace_member=False, - ) + } + if is_proc_macro: + proc_macro_dylib_name = subprocess.check_output( + [os.environ["RUSTC"], "--print", "file-names", "--crate-name", display_name, "--crate-type", "proc-macro", "-"], + stdin=subprocess.DEVNULL, + ).decode('utf-8').strip() + crate["proc_macro_dylib_path"] = f"{objtree}/rust/{proc_macro_dylib_name}" + crates_indexes[display_name] = len(crates) + crates.append(crate) + + def append_sysroot_crate( + display_name, + deps, + cfg=[], + edition="2021", + ): + append_crate( + display_name, + sysroot_src / display_name / "src" / "lib.rs", + deps, + cfg, + is_workspace_member=False, + edition=edition, + ) + + # NB: sysroot crates reexport items from one another so setting up our transitive dependencies + # here is important for ensuring that rust-analyzer can resolve symbols. The sources of truth + # for this dependency graph are `(sysroot_src / crate / "Cargo.toml" for crate in crates)`. + append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []), edition=core_edition) + append_sysroot_crate("alloc", ["core"]) + append_sysroot_crate("std", ["alloc", "core"]) + append_sysroot_crate("proc_macro", ["core", "std"]) append_crate( "compiler_builtins", @@ -67,10 +89,9 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): append_crate( "macros", srctree / "rust" / "macros" / "lib.rs", - [], + ["std", "proc_macro"], is_proc_macro=True, ) - crates[-1]["proc_macro_dylib_path"] = f"{objtree}/rust/libmacros.so" append_crate( "build_error", @@ -79,26 +100,48 @@ def generate_crates(srctree, objtree, sysroot_src, external_src, cfgs): ) append_crate( - "bindings", - srctree / "rust"/ "bindings" / "lib.rs", - ["core"], - cfg=cfg, + "pin_init_internal", + srctree / "rust" / "pin-init" / "internal" / "src" / "lib.rs", + [], + cfg=["kernel"], + is_proc_macro=True, ) - crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True)) append_crate( - "kernel", - srctree / "rust" / "kernel" / "lib.rs", - ["core", "macros", "build_error", "bindings"], - cfg=cfg, + "pin_init", + srctree / "rust" / "pin-init" / "src" / "lib.rs", + ["core", "pin_init_internal", "macros"], + cfg=["kernel"], ) - crates[-1]["source"] = { - "include_dirs": [ - str(srctree / "rust" / "kernel"), - str(objtree / "rust") - ], - "exclude_dirs": [], - } + + append_crate( + "ffi", + srctree / "rust" / "ffi.rs", + ["core", "compiler_builtins"], + ) + + def append_crate_with_generated( + display_name, + deps, + ): + append_crate( + display_name, + srctree / "rust"/ display_name / "lib.rs", + deps, + cfg=cfg, + ) + crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True)) + crates[-1]["source"] = { + "include_dirs": [ + str(srctree / "rust" / display_name), + str(objtree / "rust") + ], + "exclude_dirs": [], + } + + append_crate_with_generated("bindings", ["core", "ffi"]) + append_crate_with_generated("uapi", ["core", "ffi"]) + append_crate_with_generated("kernel", ["core", "macros", "build_error", "pin_init", "ffi", "bindings", "uapi"]) def is_root_crate(build_file, target): try: @@ -136,6 +179,7 @@ def main(): parser = argparse.ArgumentParser() parser.add_argument('--verbose', '-v', action='store_true') parser.add_argument('--cfgs', action='append', default=[]) + parser.add_argument("core_edition") parser.add_argument("srctree", type=pathlib.Path) parser.add_argument("objtree", type=pathlib.Path) parser.add_argument("sysroot", type=pathlib.Path) @@ -152,7 +196,7 @@ def main(): assert args.sysroot in args.sysroot_src.parents rust_project = { - "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs), + "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src, args.exttree, args.cfgs, args.core_edition), "sysroot": str(args.sysroot), } diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 0d00ac3723b5..39c82908ff3a 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -165,6 +165,18 @@ impl KernelConfig { let option = "CONFIG_".to_owned() + option; self.0.contains_key(&option) } + + /// Is the rustc version at least `major.minor.patch`? + fn rustc_version_atleast(&self, major: u32, minor: u32, patch: u32) -> bool { + let check_version = 100000 * major + 100 * minor + patch; + let actual_version = self + .0 + .get("CONFIG_RUSTC_VERSION") + .unwrap() + .parse::<u32>() + .unwrap(); + check_version <= actual_version + } } fn main() { @@ -172,7 +184,9 @@ fn main() { let mut ts = TargetSpec::new(); // `llvm-target`s are taken from `scripts/Makefile.clang`. - if cfg.has("ARM64") { + if cfg.has("ARM") { + panic!("arm uses the builtin rustc target"); + } else if cfg.has("ARM64") { panic!("arm64 uses the builtin rustc aarch64-unknown-none target"); } else if cfg.has("RISCV") { if cfg.has("64BIT") { @@ -182,6 +196,9 @@ fn main() { } } else if cfg.has("X86_64") { ts.push("arch", "x86_64"); + if cfg.rustc_version_atleast(1, 86, 0) { + ts.push("rustc-abi", "x86-softfloat"); + } ts.push( "data-layout", "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128", @@ -192,7 +209,7 @@ fn main() { // target feature of the same name plus the other two target features in // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated - // flag); see https://github.com/rust-lang/rust/issues/116852. + // flag); see <https://github.com/rust-lang/rust/issues/116852>. features += ",+retpoline-external-thunk"; features += ",+retpoline-indirect-branches"; features += ",+retpoline-indirect-calls"; @@ -201,7 +218,7 @@ fn main() { // The kernel uses `-mharden-sls=all`, which Clang maps to both these target features in // `clang/lib/Driver/ToolChains/Arch/X86.cpp`. These should be eventually enabled via // `-Ctarget-feature` when `rustc` starts recognizing them (or via a new dedicated - // flag); see https://github.com/rust-lang/rust/issues/116851. + // flag); see <https://github.com/rust-lang/rust/issues/116851>. features += ",+harden-sls-ijmp"; features += ",+harden-sls-ret"; } @@ -215,6 +232,9 @@ fn main() { panic!("32-bit x86 only works under UML"); } ts.push("arch", "x86"); + if cfg.rustc_version_atleast(1, 86, 0) { + ts.push("rustc-abi", "x86-softfloat"); + } ts.push( "data-layout", "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128", diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile index 312edccda736..4350311fb7b3 100644 --- a/scripts/genksyms/Makefile +++ b/scripts/genksyms/Makefile @@ -4,24 +4,6 @@ hostprogs-always-y += genksyms genksyms-objs := genksyms.o parse.tab.o lex.lex.o -# FIXME: fix the ambiguous grammar in parse.y and delete this hack -# -# Suppress shift/reduce, reduce/reduce conflicts warnings -# unless W=1 is specified. -# -# Just in case, run "$(YACC) --version" without suppressing stderr -# so that 'bison: not found' will be displayed if it is missing. -ifeq ($(findstring 1,$(KBUILD_EXTRA_WARN)),) - -quiet_cmd_bison_no_warn = $(quiet_cmd_bison) - cmd_bison_no_warn = $(YACC) --version >/dev/null; \ - $(cmd_bison) 2>/dev/null - -$(obj)/pars%.tab.c $(obj)/pars%.tab.h: $(src)/pars%.y FORCE - $(call if_changed,bison_no_warn) - -endif - # -I needed for generated C source to include headers in source tree HOSTCFLAGS_parse.tab.o := -I $(src) HOSTCFLAGS_lex.lex.o := -I $(src) diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 07f9b8cfb233..8b0d7ac73dbb 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -12,18 +12,19 @@ #include <stdio.h> #include <string.h> +#include <stdint.h> #include <stdlib.h> #include <unistd.h> #include <assert.h> #include <stdarg.h> #include <getopt.h> +#include <hashtable.h> + #include "genksyms.h" /*----------------------------------------------------------------------*/ -#define HASH_BUCKETS 4096 - -static struct symbol *symtab[HASH_BUCKETS]; +static HASHTABLE_DEFINE(symbol_hashtable, 1U << 12); static FILE *debugfile; int cur_line = 1; @@ -60,7 +61,7 @@ static void print_type_name(enum symbol_type type, const char *name); /*----------------------------------------------------------------------*/ -static const unsigned int crctab32[] = { +static const uint32_t crctab32[] = { 0x00000000U, 0x77073096U, 0xee0e612cU, 0x990951baU, 0x076dc419U, 0x706af48fU, 0xe963a535U, 0x9e6495a3U, 0x0edb8832U, 0x79dcb8a4U, 0xe0d5e91eU, 0x97d2d988U, 0x09b64c2bU, 0x7eb17cbdU, 0xe7b82d07U, @@ -115,19 +116,19 @@ static const unsigned int crctab32[] = { 0x2d02ef8dU }; -static unsigned long partial_crc32_one(unsigned char c, unsigned long crc) +static uint32_t partial_crc32_one(uint8_t c, uint32_t crc) { return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8); } -static unsigned long partial_crc32(const char *s, unsigned long crc) +static uint32_t partial_crc32(const char *s, uint32_t crc) { while (*s) crc = partial_crc32_one(*s++, crc); return crc; } -static unsigned long crc32(const char *s) +static uint32_t crc32(const char *s) { return partial_crc32(s, 0xffffffff) ^ 0xffffffff; } @@ -151,14 +152,14 @@ static enum symbol_type map_to_ns(enum symbol_type t) struct symbol *find_symbol(const char *name, enum symbol_type ns, int exact) { - unsigned long h = crc32(name) % HASH_BUCKETS; struct symbol *sym; - for (sym = symtab[h]; sym; sym = sym->hash_next) + hash_for_each_possible(symbol_hashtable, sym, hnode, crc32(name)) { if (map_to_ns(sym->type) == map_to_ns(ns) && strcmp(name, sym->name) == 0 && sym->is_declared) break; + } if (exact && sym && sym->type != ns) return NULL; @@ -224,64 +225,56 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, return NULL; } - h = crc32(name) % HASH_BUCKETS; - for (sym = symtab[h]; sym; sym = sym->hash_next) { - if (map_to_ns(sym->type) == map_to_ns(type) && - strcmp(name, sym->name) == 0) { - if (is_reference) - /* fall through */ ; - else if (sym->type == type && - equal_list(sym->defn, defn)) { - if (!sym->is_declared && sym->is_override) { - print_location(); - print_type_name(type, name); - fprintf(stderr, " modversion is " - "unchanged\n"); - } - sym->is_declared = 1; - return sym; - } else if (!sym->is_declared) { - if (sym->is_override && flag_preserve) { - print_location(); - fprintf(stderr, "ignoring "); - print_type_name(type, name); - fprintf(stderr, " modversion change\n"); - sym->is_declared = 1; - return sym; - } else { - status = is_unknown_symbol(sym) ? - STATUS_DEFINED : STATUS_MODIFIED; - } - } else { - error_with_pos("redefinition of %s", name); - return sym; + h = crc32(name); + hash_for_each_possible(symbol_hashtable, sym, hnode, h) { + if (map_to_ns(sym->type) != map_to_ns(type) || + strcmp(name, sym->name)) + continue; + + if (is_reference) { + break; + } else if (sym->type == type && equal_list(sym->defn, defn)) { + if (!sym->is_declared && sym->is_override) { + print_location(); + print_type_name(type, name); + fprintf(stderr, " modversion is unchanged\n"); } + sym->is_declared = 1; + } else if (sym->is_declared) { + error_with_pos("redefinition of %s", name); + } else if (sym->is_override && flag_preserve) { + print_location(); + fprintf(stderr, "ignoring "); + print_type_name(type, name); + fprintf(stderr, " modversion change\n"); + sym->is_declared = 1; + } else { + status = is_unknown_symbol(sym) ? + STATUS_DEFINED : STATUS_MODIFIED; break; } + free_list(defn, NULL); + return sym; } if (sym) { - struct symbol **psym; + hash_del(&sym->hnode); - for (psym = &symtab[h]; *psym; psym = &(*psym)->hash_next) { - if (*psym == sym) { - *psym = sym->hash_next; - break; - } - } + free_list(sym->defn, NULL); + free(sym->name); + free(sym); --nsyms; } sym = xmalloc(sizeof(*sym)); - sym->name = name; + sym->name = xstrdup(name); sym->type = type; sym->defn = defn; sym->expansion_trail = NULL; sym->visited = NULL; sym->is_extern = is_extern; - sym->hash_next = symtab[h]; - symtab[h] = sym; + hash_add(symbol_hashtable, &sym->hnode, h); sym->is_declared = !is_reference; sym->status = status; @@ -480,7 +473,7 @@ static void read_reference(FILE *f) defn = def; def = read_node(f); } - subsym = add_reference_symbol(xstrdup(sym->string), sym->tag, + subsym = add_reference_symbol(sym->string, sym->tag, defn, is_extern); subsym->is_override = is_override; free_node(sym); @@ -525,7 +518,7 @@ static void print_list(FILE * f, struct string_list *list) } } -static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc) +static uint32_t expand_and_crc_sym(struct symbol *sym, uint32_t crc) { struct string_list *list = sym->defn; struct string_list **e, **b; @@ -632,7 +625,7 @@ static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc) void export_symbol(const char *name) { struct symbol *sym; - unsigned long crc; + uint32_t crc; int has_changed = 0; sym = find_symbol(name, SYM_NORMAL, 0); @@ -680,7 +673,7 @@ void export_symbol(const char *name) if (flag_dump_defs) fputs(">\n", debugfile); - printf("#SYMVER %s 0x%08lx\n", name, crc); + printf("#SYMVER %s 0x%08lx\n", name, (unsigned long)crc); } /*----------------------------------------------------------------------*/ @@ -832,9 +825,9 @@ int main(int argc, char **argv) } if (flag_debug) { - fprintf(debugfile, "Hash table occupancy %d/%d = %g\n", - nsyms, HASH_BUCKETS, - (double)nsyms / (double)HASH_BUCKETS); + fprintf(debugfile, "Hash table occupancy %d/%zd = %g\n", + nsyms, HASH_SIZE(symbol_hashtable), + (double)nsyms / HASH_SIZE(symbol_hashtable)); } if (dumpfile) diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 21ed2ec2d98c..0c355075f0e6 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -12,8 +12,11 @@ #ifndef MODUTILS_GENKSYMS_H #define MODUTILS_GENKSYMS_H 1 +#include <stdbool.h> #include <stdio.h> +#include <list_types.h> + enum symbol_type { SYM_NORMAL, SYM_TYPEDEF, SYM_ENUM, SYM_STRUCT, SYM_UNION, SYM_ENUM_CONST @@ -31,8 +34,8 @@ struct string_list { }; struct symbol { - struct symbol *hash_next; - const char *name; + struct hlist_node hnode; + char *name; enum symbol_type type; struct string_list *defn; struct symbol *expansion_trail; @@ -64,6 +67,8 @@ struct string_list *copy_list_range(struct string_list *start, int yylex(void); int yyparse(void); +extern bool dont_want_type_specifier; + void error_with_pos(const char *, ...) __attribute__ ((format(printf, 1, 2))); /*----------------------------------------------------------------------*/ diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c index b85e0979a00c..ee1499d27061 100644 --- a/scripts/genksyms/keywords.c +++ b/scripts/genksyms/keywords.c @@ -17,6 +17,8 @@ static struct resword { { "__signed__", SIGNED_KEYW }, { "__typeof", TYPEOF_KEYW }, { "__typeof__", TYPEOF_KEYW }, + { "__typeof_unqual", TYPEOF_KEYW }, + { "__typeof_unqual__", TYPEOF_KEYW }, { "__volatile", VOLATILE_KEYW }, { "__volatile__", VOLATILE_KEYW }, { "__builtin_va_list", VA_LIST_KEYW }, @@ -40,6 +42,10 @@ static struct resword { // KAO. }, // { "attribute", ATTRIBUTE_KEYW }, + // X86 named address space qualifiers + { "__seg_gs", X86_SEG_KEYW }, + { "__seg_fs", X86_SEG_KEYW }, + { "auto", AUTO_KEYW }, { "char", CHAR_KEYW }, { "const", CONST_KEYW }, @@ -57,6 +63,7 @@ static struct resword { { "struct", STRUCT_KEYW }, { "typedef", TYPEDEF_KEYW }, { "typeof", TYPEOF_KEYW }, + { "typeof_unqual", TYPEOF_KEYW }, { "union", UNION_KEYW }, { "unsigned", UNSIGNED_KEYW }, { "void", VOID_KEYW }, diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l index a4d7495eaf75..f81033af1528 100644 --- a/scripts/genksyms/lex.l +++ b/scripts/genksyms/lex.l @@ -12,6 +12,7 @@ %{ #include <limits.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <ctype.h> @@ -50,6 +51,7 @@ MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) %% +u?int(8|16|32|64)x(1|2|4|8|16)_t return BUILTIN_INT_KEYW; /* Keep track of our location in the original source files. */ ^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n return FILENAME; @@ -113,6 +115,12 @@ MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) /* The second stage lexer. Here we incorporate knowledge of the state of the parser to tailor the tokens that are returned. */ +/* + * The lexer cannot distinguish whether a typedef'ed string is a TYPE or an + * IDENT. We need a hint from the parser to handle this accurately. + */ +bool dont_want_type_specifier; + int yylex(void) { @@ -168,10 +176,10 @@ repeat: switch (lexstate) { case ST_NORMAL: + APP; switch (token) { case IDENT: - APP; { int r = is_reserved_word(yytext, yyleng); if (r >= 0) @@ -207,7 +215,7 @@ repeat: goto repeat; } } - if (!suppress_type_lookup) + if (!suppress_type_lookup && !dont_want_type_specifier) { if (find_symbol(yytext, SYM_TYPEDEF, 1)) token = TYPE; @@ -216,13 +224,11 @@ repeat: break; case '[': - APP; lexstate = ST_BRACKET; count = 1; goto repeat; case '{': - APP; if (dont_want_brace_phrase) break; lexstate = ST_BRACE; @@ -230,12 +236,10 @@ repeat: goto repeat; case '=': case ':': - APP; lexstate = ST_EXPRESSION; break; default: - APP; break; } break; @@ -431,7 +435,12 @@ fini: if (suppress_type_lookup > 0) --suppress_type_lookup; - if (dont_want_brace_phrase > 0) + + /* + * __attribute__() can be placed immediately after the 'struct' keyword. + * e.g.) struct __attribute__((__packed__)) foo { ... }; + */ + if (token != ATTRIBUTE_PHRASE && dont_want_brace_phrase > 0) --dont_want_brace_phrase; yylval = &next_node->next; diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 8e9b5e69e8f0..efdcf07c4eb6 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -12,6 +12,7 @@ %{ #include <assert.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include "genksyms.h" @@ -90,6 +91,8 @@ static void record_compound(struct string_list **keyw, %token TYPEOF_KEYW %token VA_LIST_KEYW +%token X86_SEG_KEYW + %token EXPORT_SYMBOL_KEYW %token ASM_PHRASE @@ -148,32 +151,45 @@ simple_declaration: current_name = NULL; } $$ = $3; + dont_want_type_specifier = false; } ; init_declarator_list_opt: - /* empty */ { $$ = NULL; } - | init_declarator_list + /* empty */ { $$ = NULL; } + | init_declarator_list { free_list(decl_spec, NULL); $$ = $1; } ; init_declarator_list: init_declarator { struct string_list *decl = *$1; *$1 = NULL; + + /* avoid sharing among multiple init_declarators */ + if (decl_spec) + decl_spec = copy_list_range(decl_spec, NULL); + add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; $$ = $1; + dont_want_type_specifier = true; } - | init_declarator_list ',' init_declarator - { struct string_list *decl = *$3; - *$3 = NULL; + | init_declarator_list ',' attribute_opt init_declarator + { struct string_list *decl = *$4; + *$4 = NULL; free_list(*$2, NULL); *$2 = decl_spec; + + /* avoid sharing among multiple init_declarators */ + if (decl_spec) + decl_spec = copy_list_range(decl_spec, NULL); + add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; - $$ = $3; + $$ = $4; + dont_want_type_specifier = true; } ; @@ -189,8 +205,9 @@ decl_specifier_seq_opt: ; decl_specifier_seq: - decl_specifier { decl_spec = *$1; } + attribute_opt decl_specifier { decl_spec = *$2; } | decl_specifier_seq decl_specifier { decl_spec = *$2; } + | decl_specifier_seq ATTRIBUTE_PHRASE { decl_spec = *$2; } ; decl_specifier: @@ -200,7 +217,8 @@ decl_specifier: remove_node($1); $$ = $1; } - | type_specifier + | type_specifier { dont_want_type_specifier = true; $$ = $1; } + | type_qualifier ; storage_class_specifier: @@ -213,24 +231,23 @@ storage_class_specifier: type_specifier: simple_type_specifier - | cvar_qualifier | TYPEOF_KEYW '(' parameter_declaration ')' | TYPEOF_PHRASE /* References to s/u/e's defined elsewhere. Rearrange things so that it is easier to expand the definition fully later. */ - | STRUCT_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_STRUCT; $$ = $2; } - | UNION_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_UNION; $$ = $2; } + | STRUCT_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_STRUCT; $$ = $3; } + | UNION_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_UNION; $$ = $3; } | ENUM_KEYW IDENT { remove_node($1); (*$2)->tag = SYM_ENUM; $$ = $2; } /* Full definitions of an s/u/e. Record it. */ - | STRUCT_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_STRUCT); $$ = $3; } - | UNION_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_UNION); $$ = $3; } + | STRUCT_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_STRUCT); $$ = $4; } + | UNION_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_UNION); $$ = $4; } | ENUM_KEYW IDENT enum_body { record_compound($1, $2, $3, SYM_ENUM); $$ = $3; } /* @@ -239,8 +256,8 @@ type_specifier: | ENUM_KEYW enum_body { add_symbol(NULL, SYM_ENUM, NULL, 0); $$ = $2; } /* Anonymous s/u definitions. Nothing needs doing. */ - | STRUCT_KEYW class_body { $$ = $2; } - | UNION_KEYW class_body { $$ = $2; } + | STRUCT_KEYW attribute_opt class_body { $$ = $3; } + | UNION_KEYW attribute_opt class_body { $$ = $3; } ; simple_type_specifier: @@ -260,22 +277,25 @@ simple_type_specifier: ; ptr_operator: - '*' cvar_qualifier_seq_opt + '*' type_qualifier_seq_opt { $$ = $2 ? $2 : $1; } ; -cvar_qualifier_seq_opt: +type_qualifier_seq_opt: /* empty */ { $$ = NULL; } - | cvar_qualifier_seq + | type_qualifier_seq ; -cvar_qualifier_seq: - cvar_qualifier - | cvar_qualifier_seq cvar_qualifier { $$ = $2; } +type_qualifier_seq: + type_qualifier + | ATTRIBUTE_PHRASE + | type_qualifier_seq type_qualifier { $$ = $2; } + | type_qualifier_seq ATTRIBUTE_PHRASE { $$ = $2; } ; -cvar_qualifier: - CONST_KEYW | VOLATILE_KEYW | ATTRIBUTE_PHRASE +type_qualifier: + X86_SEG_KEYW + | CONST_KEYW | VOLATILE_KEYW | RESTRICT_KEYW { /* restrict has no effect in prototypes so ignore it */ remove_node($1); @@ -297,15 +317,7 @@ direct_declarator: current_name = (*$1)->string; $$ = $1; } - } - | TYPE - { if (current_name != NULL) { - error_with_pos("unexpected second declaration name"); - YYERROR; - } else { - current_name = (*$1)->string; - $$ = $1; - } + dont_want_type_specifier = false; } | direct_declarator '(' parameter_declaration_clause ')' { $$ = $4; } @@ -325,16 +337,19 @@ nested_declarator: ; direct_nested_declarator: - IDENT - | TYPE - | direct_nested_declarator '(' parameter_declaration_clause ')' + direct_nested_declarator1 + | direct_nested_declarator1 '(' parameter_declaration_clause ')' { $$ = $4; } - | direct_nested_declarator '(' error ')' + ; + +direct_nested_declarator1: + IDENT { $$ = $1; dont_want_type_specifier = false; } + | direct_nested_declarator1 '(' error ')' { $$ = $4; } - | direct_nested_declarator BRACKET_PHRASE + | direct_nested_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' nested_declarator ')' - { $$ = $3; } + | '(' attribute_opt nested_declarator ')' + { $$ = $4; } | '(' error ')' { $$ = $3; } ; @@ -352,45 +367,57 @@ parameter_declaration_list_opt: parameter_declaration_list: parameter_declaration + { $$ = $1; dont_want_type_specifier = false; } | parameter_declaration_list ',' parameter_declaration - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } ; parameter_declaration: - decl_specifier_seq m_abstract_declarator + decl_specifier_seq abstract_declarator_opt { $$ = $2 ? $2 : $1; } ; -m_abstract_declarator: - ptr_operator m_abstract_declarator +abstract_declarator_opt: + /* empty */ { $$ = NULL; } + | abstract_declarator + ; + +abstract_declarator: + ptr_operator + | ptr_operator abstract_declarator { $$ = $2 ? $2 : $1; } - | direct_m_abstract_declarator + | direct_abstract_declarator attribute_opt + { $$ = $2; dont_want_type_specifier = false; } ; -direct_m_abstract_declarator: - /* empty */ { $$ = NULL; } - | IDENT +direct_abstract_declarator: + direct_abstract_declarator1 + | direct_abstract_declarator1 open_paren parameter_declaration_clause ')' + { $$ = $4; } + | open_paren parameter_declaration_clause ')' + { $$ = $3; } + ; + +direct_abstract_declarator1: + IDENT { /* For version 2 checksums, we don't want to remember private parameter names. */ remove_node($1); $$ = $1; } - /* This wasn't really a typedef name but an identifier that - shadows one. */ - | TYPE - { remove_node($1); - $$ = $1; - } - | direct_m_abstract_declarator '(' parameter_declaration_clause ')' - { $$ = $4; } - | direct_m_abstract_declarator '(' error ')' + | direct_abstract_declarator1 open_paren error ')' { $$ = $4; } - | direct_m_abstract_declarator BRACKET_PHRASE + | direct_abstract_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' m_abstract_declarator ')' - { $$ = $3; } - | '(' error ')' + | open_paren attribute_opt abstract_declarator ')' + { $$ = $4; } + | open_paren error ')' { $$ = $3; } + | BRACKET_PHRASE + ; + +open_paren: + '(' { $$ = $1; dont_want_type_specifier = false; } ; function_definition: @@ -430,9 +457,9 @@ member_specification: member_declaration: decl_specifier_seq_opt member_declarator_list_opt ';' - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } | error ';' - { $$ = $2; } + { $$ = $2; dont_want_type_specifier = false; } ; member_declarator_list_opt: @@ -442,7 +469,9 @@ member_declarator_list_opt: member_declarator_list: member_declarator - | member_declarator_list ',' member_declarator { $$ = $3; } + { $$ = $1; dont_want_type_specifier = true; } + | member_declarator_list ',' member_declarator + { $$ = $3; dont_want_type_specifier = true; } ; member_declarator: @@ -457,7 +486,7 @@ member_bitfield_declarator: attribute_opt: /* empty */ { $$ = NULL; } - | attribute_opt ATTRIBUTE_PHRASE + | attribute_opt ATTRIBUTE_PHRASE { $$ = $2; } ; enum_body: @@ -472,12 +501,12 @@ enumerator_list: enumerator: IDENT { - const char *name = strdup((*$1)->string); + const char *name = (*$1)->string; add_symbol(name, SYM_ENUM_CONST, NULL, 0); } | IDENT '=' EXPRESSION_PHRASE { - const char *name = strdup((*$1)->string); + const char *name = (*$1)->string; struct string_list *expr = copy_list_range(*$3, *$2); add_symbol(name, SYM_ENUM_CONST, expr, 0); } diff --git a/scripts/get_abi.pl b/scripts/get_abi.pl deleted file mode 100755 index de1c0354b50c..000000000000 --- a/scripts/get_abi.pl +++ /dev/null @@ -1,1103 +0,0 @@ -#!/usr/bin/env perl -# SPDX-License-Identifier: GPL-2.0 - -BEGIN { $Pod::Usage::Formatter = 'Pod::Text::Termcap'; } - -use strict; -use warnings; -use utf8; -use Pod::Usage qw(pod2usage); -use Getopt::Long; -use File::Find; -use IO::Handle; -use Fcntl ':mode'; -use Cwd 'abs_path'; -use Data::Dumper; - -my $help = 0; -my $hint = 0; -my $man = 0; -my $debug = 0; -my $enable_lineno = 0; -my $show_warnings = 1; -my $prefix="Documentation/ABI"; -my $sysfs_prefix="/sys"; -my $search_string; - -# Debug options -my $dbg_what_parsing = 1; -my $dbg_what_open = 2; -my $dbg_dump_abi_structs = 4; -my $dbg_undefined = 8; - -$Data::Dumper::Indent = 1; -$Data::Dumper::Terse = 1; - -# -# If true, assumes that the description is formatted with ReST -# -my $description_is_rst = 1; - -GetOptions( - "debug=i" => \$debug, - "enable-lineno" => \$enable_lineno, - "rst-source!" => \$description_is_rst, - "dir=s" => \$prefix, - 'help|?' => \$help, - "show-hints" => \$hint, - "search-string=s" => \$search_string, - man => \$man -) or pod2usage(2); - -pod2usage(1) if $help; -pod2usage(-exitstatus => 0, -noperldoc, -verbose => 2) if $man; - -pod2usage(2) if (scalar @ARGV < 1 || @ARGV > 2); - -my ($cmd, $arg) = @ARGV; - -pod2usage(2) if ($cmd ne "search" && $cmd ne "rest" && $cmd ne "validate" && $cmd ne "undefined"); -pod2usage(2) if ($cmd eq "search" && !$arg); - -require Data::Dumper if ($debug & $dbg_dump_abi_structs); - -my %data; -my %symbols; - -# -# Displays an error message, printing file name and line -# -sub parse_error($$$$) { - my ($file, $ln, $msg, $data) = @_; - - return if (!$show_warnings); - - $data =~ s/\s+$/\n/; - - print STDERR "Warning: file $file#$ln:\n\t$msg"; - - if ($data ne "") { - print STDERR ". Line\n\t\t$data"; - } else { - print STDERR "\n"; - } -} - -# -# Parse an ABI file, storing its contents at %data -# -sub parse_abi { - my $file = $File::Find::name; - - my $mode = (stat($file))[2]; - return if ($mode & S_IFDIR); - return if ($file =~ m,/README,); - return if ($file =~ m,/\.,); - return if ($file =~ m,\.(rej|org|orig|bak)$,); - - my $name = $file; - $name =~ s,.*/,,; - - my $fn = $file; - $fn =~ s,.*Documentation/ABI/,,; - - my $nametag = "File $fn"; - $data{$nametag}->{what} = "File $name"; - $data{$nametag}->{type} = "File"; - $data{$nametag}->{file} = $name; - $data{$nametag}->{filepath} = $file; - $data{$nametag}->{is_file} = 1; - $data{$nametag}->{line_no} = 1; - - my $type = $file; - $type =~ s,.*/(.*)/.*,$1,; - - my $what; - my $new_what; - my $tag = ""; - my $ln; - my $xrefs; - my $space; - my @labels; - my $label = ""; - - print STDERR "Opening $file\n" if ($debug & $dbg_what_open); - open IN, $file; - while(<IN>) { - $ln++; - if (m/^(\S+)(:\s*)(.*)/i) { - my $new_tag = lc($1); - my $sep = $2; - my $content = $3; - - if (!($new_tag =~ m/(what|where|date|kernelversion|contact|description|users)/)) { - if ($tag eq "description") { - # New "tag" is actually part of - # description. Don't consider it a tag - $new_tag = ""; - } elsif ($tag ne "") { - parse_error($file, $ln, "tag '$tag' is invalid", $_); - } - } - - # Invalid, but it is a common mistake - if ($new_tag eq "where") { - parse_error($file, $ln, "tag 'Where' is invalid. Should be 'What:' instead", ""); - $new_tag = "what"; - } - - if ($new_tag =~ m/what/) { - $space = ""; - $content =~ s/[,.;]$//; - - push @{$symbols{$content}->{file}}, " $file:" . ($ln - 1); - - if ($tag =~ m/what/) { - $what .= "\xac" . $content; - } else { - if ($what) { - parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description}); - - foreach my $w(split /\xac/, $what) { - $symbols{$w}->{xref} = $what; - }; - } - - $what = $content; - $label = $content; - $new_what = 1; - } - push @labels, [($content, $label)]; - $tag = $new_tag; - - push @{$data{$nametag}->{symbols}}, $content if ($data{$nametag}->{what}); - next; - } - - if ($tag ne "" && $new_tag) { - $tag = $new_tag; - - if ($new_what) { - @{$data{$what}->{label_list}} = @labels if ($data{$nametag}->{what}); - @labels = (); - $label = ""; - $new_what = 0; - - $data{$what}->{type} = $type; - if (!defined($data{$what}->{file})) { - $data{$what}->{file} = $name; - $data{$what}->{filepath} = $file; - } else { - $data{$what}->{description} .= "\n\n" if (defined($data{$what}->{description})); - if ($name ne $data{$what}->{file}) { - $data{$what}->{file} .= " " . $name; - $data{$what}->{filepath} .= " " . $file; - } - } - print STDERR "\twhat: $what\n" if ($debug & $dbg_what_parsing); - $data{$what}->{line_no} = $ln; - } else { - $data{$what}->{line_no} = $ln if (!defined($data{$what}->{line_no})); - } - - if (!$what) { - parse_error($file, $ln, "'What:' should come first:", $_); - next; - } - if ($new_tag eq "description") { - $sep =~ s,:, ,; - $content = ' ' x length($new_tag) . $sep . $content; - while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {} - if ($content =~ m/^(\s*)(\S.*)$/) { - # Preserve initial spaces for the first line - $space = $1; - $content = "$2\n"; - $data{$what}->{$tag} .= $content; - } else { - undef($space); - } - - } else { - $data{$what}->{$tag} = $content; - } - next; - } - } - - # Store any contents before tags at the database - if (!$tag && $data{$nametag}->{what}) { - $data{$nametag}->{description} .= $_; - next; - } - - if ($tag eq "description") { - my $content = $_; - while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {} - if (m/^\s*\n/) { - $data{$what}->{$tag} .= "\n"; - next; - } - - if (!defined($space)) { - # Preserve initial spaces for the first line - if ($content =~ m/^(\s*)(\S.*)$/) { - $space = $1; - $content = "$2\n"; - } - } else { - $space = "" if (!($content =~ s/^($space)//)); - } - $data{$what}->{$tag} .= $content; - - next; - } - if (m/^\s*(.*)/) { - $data{$what}->{$tag} .= "\n$1"; - $data{$what}->{$tag} =~ s/\n+$//; - next; - } - - # Everything else is error - parse_error($file, $ln, "Unexpected content", $_); - } - $data{$nametag}->{description} =~ s/^\n+// if ($data{$nametag}->{description}); - if ($what) { - parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description}); - - foreach my $w(split /\xac/,$what) { - $symbols{$w}->{xref} = $what; - }; - } - close IN; -} - -sub create_labels { - my %labels; - - foreach my $what (keys %data) { - next if ($data{$what}->{file} eq "File"); - - foreach my $p (@{$data{$what}->{label_list}}) { - my ($content, $label) = @{$p}; - $label = "abi_" . $label . " "; - $label =~ tr/A-Z/a-z/; - - # Convert special chars to "_" - $label =~s/([\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\xff])/_/g; - $label =~ s,_+,_,g; - $label =~ s,_$,,; - - # Avoid duplicated labels - while (defined($labels{$label})) { - my @chars = ("A".."Z", "a".."z"); - $label .= $chars[rand @chars]; - } - $labels{$label} = 1; - - $data{$what}->{label} = $label; - - # only one label is enough - last; - } - } -} - -# -# Outputs the book on ReST format -# - -# \b doesn't work well with paths. So, we need to define something else: -# Boundaries are punct characters, spaces and end-of-line -my $start = qr {(^|\s|\() }x; -my $bondary = qr { ([,.:;\)\s]|\z) }x; -my $xref_match = qr { $start(\/(sys|config|proc|dev|kvd)\/[^,.:;\)\s]+)$bondary }x; -my $symbols = qr { ([\x01-\x08\x0e-\x1f\x21-\x2f\x3a-\x40\x7b-\xff]) }x; - -sub output_rest { - create_labels(); - - my $part = ""; - - foreach my $what (sort { - ($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") || - $a cmp $b - } keys %data) { - my $type = $data{$what}->{type}; - - my @file = split / /, $data{$what}->{file}; - my @filepath = split / /, $data{$what}->{filepath}; - - if ($enable_lineno) { - printf ".. LINENO %s%s#%s\n\n", - $prefix, $file[0], - $data{$what}->{line_no}; - } - - my $w = $what; - - if ($type ne "File") { - my $cur_part = $what; - if ($what =~ '/') { - if ($what =~ m#^(\/?(?:[\w\-]+\/?){1,2})#) { - $cur_part = "Symbols under $1"; - $cur_part =~ s,/$,,; - } - } - - if ($cur_part ne "" && $part ne $cur_part) { - $part = $cur_part; - my $bar = $part; - $bar =~ s/./-/g; - print "$part\n$bar\n\n"; - } - - printf ".. _%s:\n\n", $data{$what}->{label}; - - my @names = split /\xac/,$w; - my $len = 0; - - foreach my $name (@names) { - $name =~ s/$symbols/\\$1/g; - $name = "**$name**"; - $len = length($name) if (length($name) > $len); - } - - print "+-" . "-" x $len . "-+\n"; - foreach my $name (@names) { - printf "| %s", $name . " " x ($len - length($name)) . " |\n"; - print "+-" . "-" x $len . "-+\n"; - } - - print "\n"; - } - - for (my $i = 0; $i < scalar(@filepath); $i++) { - my $path = $filepath[$i]; - my $f = $file[$i]; - - $path =~ s,.*/(.*/.*),$1,;; - $path =~ s,[/\-],_,g;; - my $fileref = "abi_file_".$path; - - if ($type eq "File") { - print ".. _$fileref:\n\n"; - } else { - print "Defined on file :ref:`$f <$fileref>`\n\n"; - } - } - - if ($type eq "File") { - my $bar = $w; - $bar =~ s/./-/g; - print "$w\n$bar\n\n"; - } - - my $desc = ""; - $desc = $data{$what}->{description} if (defined($data{$what}->{description})); - $desc =~ s/\s+$/\n/; - - if (!($desc =~ /^\s*$/)) { - if ($description_is_rst) { - # Remove title markups from the description - # Having titles inside ABI files will only work if extra - # care would be taken in order to strictly follow the same - # level order for each markup. - $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g; - - # Enrich text by creating cross-references - - my $new_desc = ""; - my $init_indent = -1; - my $literal_indent = -1; - - open(my $fh, "+<", \$desc); - while (my $d = <$fh>) { - my $indent = $d =~ m/^(\s+)/; - my $spaces = length($indent); - $init_indent = $indent if ($init_indent < 0); - if ($literal_indent >= 0) { - if ($spaces > $literal_indent) { - $new_desc .= $d; - next; - } else { - $literal_indent = -1; - } - } else { - if ($d =~ /()::$/ && !($d =~ /^\s*\.\./)) { - $literal_indent = $spaces; - } - } - - $d =~ s,Documentation/(?!devicetree)(\S+)\.rst,:doc:`/$1`,g; - - my @matches = $d =~ m,Documentation/ABI/([\w\/\-]+),g; - foreach my $f (@matches) { - my $xref = $f; - my $path = $f; - $path =~ s,.*/(.*/.*),$1,;; - $path =~ s,[/\-],_,g;; - $xref .= " <abi_file_" . $path . ">"; - $d =~ s,\bDocumentation/ABI/$f\b,:ref:`$xref`,g; - } - - # Seek for cross reference symbols like /sys/... - @matches = $d =~ m/$xref_match/g; - - foreach my $s (@matches) { - next if (!($s =~ m,/,)); - if (defined($data{$s}) && defined($data{$s}->{label})) { - my $xref = $s; - - $xref =~ s/$symbols/\\$1/g; - $xref = ":ref:`$xref <" . $data{$s}->{label} . ">`"; - - $d =~ s,$start$s$bondary,$1$xref$2,g; - } - } - $new_desc .= $d; - } - close $fh; - - - print "$new_desc\n\n"; - } else { - $desc =~ s/^\s+//; - - # Remove title markups from the description, as they won't work - $desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g; - - if ($desc =~ m/\:\n/ || $desc =~ m/\n[\t ]+/ || $desc =~ m/[\x00-\x08\x0b-\x1f\x7b-\xff]/) { - # put everything inside a code block - $desc =~ s/\n/\n /g; - - print "::\n\n"; - print " $desc\n\n"; - } else { - # Escape any special chars from description - $desc =~s/([\x00-\x08\x0b-\x1f\x21-\x2a\x2d\x2f\x3c-\x40\x5c\x5e-\x60\x7b-\xff])/\\$1/g; - print "$desc\n\n"; - } - } - } else { - print "DESCRIPTION MISSING for $what\n\n" if (!$data{$what}->{is_file}); - } - - if ($data{$what}->{symbols}) { - printf "Has the following ABI:\n\n"; - - foreach my $content(@{$data{$what}->{symbols}}) { - my $label = $data{$symbols{$content}->{xref}}->{label}; - - # Escape special chars from content - $content =~s/([\x00-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])/\\$1/g; - - print "- :ref:`$content <$label>`\n\n"; - } - } - - if (defined($data{$what}->{users})) { - my $users = $data{$what}->{users}; - - $users =~ s/\n/\n\t/g; - printf "Users:\n\t%s\n\n", $users if ($users ne ""); - } - - } -} - -# -# Searches for ABI symbols -# -sub search_symbols { - foreach my $what (sort keys %data) { - next if (!($what =~ m/($arg)/)); - - my $type = $data{$what}->{type}; - next if ($type eq "File"); - - my $file = $data{$what}->{filepath}; - - $what =~ s/\xac/, /g; - my $bar = $what; - $bar =~ s/./-/g; - - print "\n$what\n$bar\n\n"; - - my $kernelversion = $data{$what}->{kernelversion} if (defined($data{$what}->{kernelversion})); - my $contact = $data{$what}->{contact} if (defined($data{$what}->{contact})); - my $users = $data{$what}->{users} if (defined($data{$what}->{users})); - my $date = $data{$what}->{date} if (defined($data{$what}->{date})); - my $desc = $data{$what}->{description} if (defined($data{$what}->{description})); - - $kernelversion =~ s/^\s+// if ($kernelversion); - $contact =~ s/^\s+// if ($contact); - if ($users) { - $users =~ s/^\s+//; - $users =~ s/\n//g; - } - $date =~ s/^\s+// if ($date); - $desc =~ s/^\s+// if ($desc); - - printf "Kernel version:\t\t%s\n", $kernelversion if ($kernelversion); - printf "Date:\t\t\t%s\n", $date if ($date); - printf "Contact:\t\t%s\n", $contact if ($contact); - printf "Users:\t\t\t%s\n", $users if ($users); - print "Defined on file(s):\t$file\n\n"; - print "Description:\n\n$desc"; - } -} - -# Exclude /sys/kernel/debug and /sys/kernel/tracing from the search path -sub dont_parse_special_attributes { - if (($File::Find::dir =~ m,^/sys/kernel,)) { - return grep {!/(debug|tracing)/ } @_; - } - - if (($File::Find::dir =~ m,^/sys/fs,)) { - return grep {!/(pstore|bpf|fuse)/ } @_; - } - - return @_ -} - -my %leaf; -my %aliases; -my @files; -my %root; - -sub graph_add_file { - my $file = shift; - my $type = shift; - - my $dir = $file; - $dir =~ s,^(.*/).*,$1,; - $file =~ s,.*/,,; - - my $name; - my $file_ref = \%root; - foreach my $edge(split "/", $dir) { - $name .= "$edge/"; - if (!defined ${$file_ref}{$edge}) { - ${$file_ref}{$edge} = { }; - } - $file_ref = \%{$$file_ref{$edge}}; - ${$file_ref}{"__name"} = [ $name ]; - } - $name .= "$file"; - ${$file_ref}{$file} = { - "__name" => [ $name ] - }; - - return \%{$$file_ref{$file}}; -} - -sub graph_add_link { - my $file = shift; - my $link = shift; - - # Traverse graph to find the reference - my $file_ref = \%root; - foreach my $edge(split "/", $file) { - $file_ref = \%{$$file_ref{$edge}} || die "Missing node!"; - } - - # do a BFS - - my @queue; - my %seen; - my $st; - - push @queue, $file_ref; - $seen{$start}++; - - while (@queue) { - my $v = shift @queue; - my @child = keys(%{$v}); - - foreach my $c(@child) { - next if $seen{$$v{$c}}; - next if ($c eq "__name"); - - if (!defined($$v{$c}{"__name"})) { - printf STDERR "Error: Couldn't find a non-empty name on a children of $file/.*: "; - print STDERR Dumper(%{$v}); - exit; - } - - # Add new name - my $name = @{$$v{$c}{"__name"}}[0]; - if ($name =~ s#^$file/#$link/#) { - push @{$$v{$c}{"__name"}}, $name; - } - # Add child to the queue and mark as seen - push @queue, $$v{$c}; - $seen{$c}++; - } - } -} - -my $escape_symbols = qr { ([\x01-\x08\x0e-\x1f\x21-\x29\x2b-\x2d\x3a-\x40\x7b-\xfe]) }x; -sub parse_existing_sysfs { - my $file = $File::Find::name; - - my $mode = (lstat($file))[2]; - my $abs_file = abs_path($file); - - my @tmp; - push @tmp, $file; - push @tmp, $abs_file if ($abs_file ne $file); - - foreach my $f(@tmp) { - # Ignore cgroup, as this is big and has zero docs under ABI - return if ($f =~ m#^/sys/fs/cgroup/#); - - # Ignore firmware as it is documented elsewhere - # Either ACPI or under Documentation/devicetree/bindings/ - return if ($f =~ m#^/sys/firmware/#); - - # Ignore some sysfs nodes that aren't actually part of ABI - return if ($f =~ m#/sections|notes/#); - - # Would need to check at - # Documentation/admin-guide/kernel-parameters.txt, but this - # is not easily parseable. - return if ($f =~ m#/parameters/#); - } - - if (S_ISLNK($mode)) { - $aliases{$file} = $abs_file; - return; - } - - return if (S_ISDIR($mode)); - - # Trivial: file is defined exactly the same way at ABI What: - return if (defined($data{$file})); - return if (defined($data{$abs_file})); - - push @files, graph_add_file($abs_file, "file"); -} - -sub get_leave($) -{ - my $what = shift; - my $leave; - - my $l = $what; - my $stop = 1; - - $leave = $l; - $leave =~ s,/$,,; - $leave =~ s,.*/,,; - $leave =~ s/[\(\)]//g; - - # $leave is used to improve search performance at - # check_undefined_symbols, as the algorithm there can seek - # for a small number of "what". It also allows giving a - # hint about a leave with the same name somewhere else. - # However, there are a few occurences where the leave is - # either a wildcard or a number. Just group such cases - # altogether. - if ($leave =~ m/\.\*/ || $leave eq "" || $leave =~ /\\d/) { - $leave = "others"; - } - - return $leave; -} - -my @not_found; - -sub check_file($$) -{ - my $file_ref = shift; - my $names_ref = shift; - my @names = @{$names_ref}; - my $file = $names[0]; - - my $found_string; - - my $leave = get_leave($file); - if (!defined($leaf{$leave})) { - $leave = "others"; - } - my @expr = @{$leaf{$leave}->{expr}}; - die ("\rmissing rules for $leave") if (!defined($leaf{$leave})); - - my $path = $file; - $path =~ s,(.*/).*,$1,; - - if ($search_string) { - return if (!($file =~ m#$search_string#)); - $found_string = 1; - } - - for (my $i = 0; $i < @names; $i++) { - if ($found_string && $hint) { - if (!$i) { - print STDERR "--> $names[$i]\n"; - } else { - print STDERR " $names[$i]\n"; - } - } - foreach my $re (@expr) { - print STDERR "$names[$i] =~ /^$re\$/\n" if ($debug && $dbg_undefined); - if ($names[$i] =~ $re) { - return; - } - } - } - - if ($leave ne "others") { - my @expr = @{$leaf{"others"}->{expr}}; - for (my $i = 0; $i < @names; $i++) { - foreach my $re (@expr) { - print STDERR "$names[$i] =~ /^$re\$/\n" if ($debug && $dbg_undefined); - if ($names[$i] =~ $re) { - return; - } - } - } - } - - push @not_found, $file if (!$search_string || $found_string); - - if ($hint && (!$search_string || $found_string)) { - my $what = $leaf{$leave}->{what}; - $what =~ s/\xac/\n\t/g; - if ($leave ne "others") { - print STDERR "\r more likely regexes:\n\t$what\n"; - } else { - print STDERR "\r tested regexes:\n\t$what\n"; - } - } -} - -sub check_undefined_symbols { - my $num_files = scalar @files; - my $next_i = 0; - my $start_time = times; - - @files = sort @files; - - my $last_time = $start_time; - - # When either debug or hint is enabled, there's no sense showing - # progress, as the progress will be overriden. - if ($hint || ($debug && $dbg_undefined)) { - $next_i = $num_files; - } - - my $is_console; - $is_console = 1 if (-t STDERR); - - for (my $i = 0; $i < $num_files; $i++) { - my $file_ref = $files[$i]; - my @names = @{$$file_ref{"__name"}}; - - check_file($file_ref, \@names); - - my $cur_time = times; - - if ($i == $next_i || $cur_time > $last_time + 1) { - my $percent = $i * 100 / $num_files; - - my $tm = $cur_time - $start_time; - my $time = sprintf "%d:%02d", int($tm), 60 * ($tm - int($tm)); - - printf STDERR "\33[2K\r", if ($is_console); - printf STDERR "%s: processing sysfs files... %i%%: $names[0]", $time, $percent; - printf STDERR "\n", if (!$is_console); - STDERR->flush(); - - $next_i = int (($percent + 1) * $num_files / 100); - $last_time = $cur_time; - } - } - - my $cur_time = times; - my $tm = $cur_time - $start_time; - my $time = sprintf "%d:%02d", int($tm), 60 * ($tm - int($tm)); - - printf STDERR "\33[2K\r", if ($is_console); - printf STDERR "%s: processing sysfs files... done\n", $time; - - foreach my $file (@not_found) { - print "$file not found.\n"; - } -} - -sub undefined_symbols { - print STDERR "Reading $sysfs_prefix directory contents..."; - find({ - wanted =>\&parse_existing_sysfs, - preprocess =>\&dont_parse_special_attributes, - no_chdir => 1 - }, $sysfs_prefix); - print STDERR "done.\n"; - - $leaf{"others"}->{what} = ""; - - print STDERR "Converting ABI What fields into regexes..."; - foreach my $w (sort keys %data) { - foreach my $what (split /\xac/,$w) { - next if (!($what =~ m/^$sysfs_prefix/)); - - # Convert what into regular expressions - - # Escape dot characters - $what =~ s/\./\xf6/g; - - # Temporarily change [0-9]+ type of patterns - $what =~ s/\[0\-9\]\+/\xff/g; - - # Temporarily change [\d+-\d+] type of patterns - $what =~ s/\[0\-\d+\]/\xff/g; - $what =~ s/\[(\d+)\]/\xf4$1\xf5/g; - - # Temporarily change [0-9] type of patterns - $what =~ s/\[(\d)\-(\d)\]/\xf4$1-$2\xf5/g; - - # Handle multiple option patterns - $what =~ s/[\{\<\[]([\w_]+)(?:[,|]+([\w_]+)){1,}[\}\>\]]/($1|$2)/g; - - # Handle wildcards - $what =~ s,\*,.*,g; - $what =~ s,/\xf6..,/.*,g; - $what =~ s/\<[^\>]+\>/.*/g; - $what =~ s/\{[^\}]+\}/.*/g; - $what =~ s/\[[^\]]+\]/.*/g; - - $what =~ s/[XYZ]/.*/g; - - # Recover [0-9] type of patterns - $what =~ s/\xf4/[/g; - $what =~ s/\xf5/]/g; - - # Remove duplicated spaces - $what =~ s/\s+/ /g; - - # Special case: this ABI has a parenthesis on it - $what =~ s/sqrt\(x^2\+y^2\+z^2\)/sqrt\(x^2\+y^2\+z^2\)/; - - # Special case: drop comparition as in: - # What: foo = <something> - # (this happens on a few IIO definitions) - $what =~ s,\s*\=.*$,,; - - # Escape all other symbols - $what =~ s/$escape_symbols/\\$1/g; - $what =~ s/\\\\/\\/g; - $what =~ s/\\([\[\]\(\)\|])/$1/g; - $what =~ s/(\d+)\\(-\d+)/$1$2/g; - - $what =~ s/\xff/\\d+/g; - - # Special case: IIO ABI which a parenthesis. - $what =~ s/sqrt(.*)/sqrt\(.*\)/; - - # Simplify regexes with multiple .* - $what =~ s#(?:\.\*){2,}##g; -# $what =~ s#\.\*/\.\*#.*#g; - - # Recover dot characters - $what =~ s/\xf6/\./g; - - my $leave = get_leave($what); - - my $added = 0; - foreach my $l (split /\|/, $leave) { - if (defined($leaf{$l})) { - next if ($leaf{$l}->{what} =~ m/\b$what\b/); - $leaf{$l}->{what} .= "\xac" . $what; - $added = 1; - } else { - $leaf{$l}->{what} = $what; - $added = 1; - } - } - if ($search_string && $added) { - print STDERR "What: $what\n" if ($what =~ m#$search_string#); - } - - } - } - # Compile regexes - foreach my $l (sort keys %leaf) { - my @expr; - foreach my $w(sort split /\xac/, $leaf{$l}->{what}) { - push @expr, qr /^$w$/; - } - $leaf{$l}->{expr} = \@expr; - } - - # Take links into account - foreach my $link (sort keys %aliases) { - my $abs_file = $aliases{$link}; - graph_add_link($abs_file, $link); - } - print STDERR "done.\n"; - - check_undefined_symbols; -} - -# Ensure that the prefix will always end with a slash -# While this is not needed for find, it makes the patch nicer -# with --enable-lineno -$prefix =~ s,/?$,/,; - -if ($cmd eq "undefined" || $cmd eq "search") { - $show_warnings = 0; -} -# -# Parses all ABI files located at $prefix dir -# -find({wanted =>\&parse_abi, no_chdir => 1}, $prefix); - -print STDERR Data::Dumper->Dump([\%data], [qw(*data)]) if ($debug & $dbg_dump_abi_structs); - -# -# Handles the command -# -if ($cmd eq "undefined") { - undefined_symbols; -} elsif ($cmd eq "search") { - search_symbols; -} else { - if ($cmd eq "rest") { - output_rest; - } - - # Warn about duplicated ABI entries - foreach my $what(sort keys %symbols) { - my @files = @{$symbols{$what}->{file}}; - - next if (scalar(@files) == 1); - - printf STDERR "Warning: $what is defined %d times: @files\n", - scalar(@files); - } -} - -__END__ - -=head1 NAME - -get_abi.pl - parse the Linux ABI files and produce a ReST book. - -=head1 SYNOPSIS - -B<get_abi.pl> [--debug <level>] [--enable-lineno] [--man] [--help] - [--(no-)rst-source] [--dir=<dir>] [--show-hints] - [--search-string <regex>] - <COMMAND> [<ARGUMENT>] - -Where B<COMMAND> can be: - -=over 8 - -B<search> I<SEARCH_REGEX> - search for I<SEARCH_REGEX> inside ABI - -B<rest> - output the ABI in ReST markup language - -B<validate> - validate the ABI contents - -B<undefined> - existing symbols at the system that aren't - defined at Documentation/ABI - -=back - -=head1 OPTIONS - -=over 8 - -=item B<--dir> - -Changes the location of the ABI search. By default, it uses -the Documentation/ABI directory. - -=item B<--rst-source> and B<--no-rst-source> - -The input file may be using ReST syntax or not. Those two options allow -selecting between a rst-compliant source ABI (B<--rst-source>), or a -plain text that may be violating ReST spec, so it requres some escaping -logic (B<--no-rst-source>). - -=item B<--enable-lineno> - -Enable output of .. LINENO lines. - -=item B<--debug> I<debug level> - -Print debug information according with the level, which is given by the -following bitmask: - - - 1: Debug parsing What entries from ABI files; - - 2: Shows what files are opened from ABI files; - - 4: Dump the structs used to store the contents of the ABI files. - -=item B<--show-hints> - -Show hints about possible definitions for the missing ABI symbols. -Used only when B<undefined>. - -=item B<--search-string> I<regex string> - -Show only occurences that match a search string. -Used only when B<undefined>. - -=item B<--help> - -Prints a brief help message and exits. - -=item B<--man> - -Prints the manual page and exits. - -=back - -=head1 DESCRIPTION - -Parse the Linux ABI files from ABI DIR (usually located at Documentation/ABI), -allowing to search for ABI symbols or to produce a ReST book containing -the Linux ABI documentation. - -=head1 EXAMPLES - -Search for all stable symbols with the word "usb": - -=over 8 - -$ scripts/get_abi.pl search usb --dir Documentation/ABI/stable - -=back - -Search for all symbols that match the regex expression "usb.*cap": - -=over 8 - -$ scripts/get_abi.pl search usb.*cap - -=back - -Output all obsoleted symbols in ReST format - -=over 8 - -$ scripts/get_abi.pl rest --dir Documentation/ABI/obsolete - -=back - -=head1 BUGS - -Report bugs to Mauro Carvalho Chehab <mchehab+huawei@kernel.org> - -=head1 COPYRIGHT - -Copyright (c) 2016-2021 by Mauro Carvalho Chehab <mchehab+huawei@kernel.org>. - -License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>. - -This is free software: you are free to change and redistribute it. -There is NO WARRANTY, to the extent permitted by law. - -=cut diff --git a/scripts/get_abi.py b/scripts/get_abi.py new file mode 100755 index 000000000000..7ce4748a46d2 --- /dev/null +++ b/scripts/get_abi.py @@ -0,0 +1,214 @@ +#!/usr/bin/env python3 +# pylint: disable=R0903 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# SPDX-License-Identifier: GPL-2.0 + +""" +Parse ABI documentation and produce results from it. +""" + +import argparse +import logging +import os +import sys + +# Import Python modules + +LIB_DIR = "lib/abi" +SRC_DIR = os.path.dirname(os.path.realpath(__file__)) + +sys.path.insert(0, os.path.join(SRC_DIR, LIB_DIR)) + +from abi_parser import AbiParser # pylint: disable=C0413 +from abi_regex import AbiRegex # pylint: disable=C0413 +from helpers import ABI_DIR, DEBUG_HELP # pylint: disable=C0413 +from system_symbols import SystemSymbols # pylint: disable=C0413 + +# Command line classes + + +REST_DESC = """ +Produce output in ReST format. + +The output is done on two sections: + +- Symbols: show all parsed symbols in alphabetic order; +- Files: cross reference the content of each file with the symbols on it. +""" + +class AbiRest: + """Initialize an argparse subparser for rest output""" + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("rest", + formatter_class=argparse.RawTextHelpFormatter, + description=REST_DESC) + + parser.add_argument("--enable-lineno", action="store_true", + help="enable lineno") + parser.add_argument("--raw", action="store_true", + help="output text as contained in the ABI files. " + "It not used, output will contain dynamically" + " generated cross references when possible.") + parser.add_argument("--no-file", action="store_true", + help="Don't the files section") + parser.add_argument("--show-hints", help="Show-hints") + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + parser = AbiParser(args.dir, debug=args.debug) + parser.parse_abi() + parser.check_issues() + + for t in parser.doc(args.raw, not args.no_file): + if args.enable_lineno: + print (f".. LINENO {t[1]}#{t[2]}\n\n") + + print(t[0]) + +class AbiValidate: + """Initialize an argparse subparser for ABI validation""" + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("validate", + formatter_class=argparse.ArgumentDefaultsHelpFormatter, + description="list events") + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + parser = AbiParser(args.dir, debug=args.debug) + parser.parse_abi() + parser.check_issues() + + +class AbiSearch: + """Initialize an argparse subparser for ABI search""" + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("search", + formatter_class=argparse.ArgumentDefaultsHelpFormatter, + description="Search ABI using a regular expression") + + parser.add_argument("expression", + help="Case-insensitive search pattern for the ABI symbol") + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + parser = AbiParser(args.dir, debug=args.debug) + parser.parse_abi() + parser.search_symbols(args.expression) + +UNDEFINED_DESC=""" +Check undefined ABIs on local machine. + +Read sysfs devnodes and check if the devnodes there are defined inside +ABI documentation. + +The search logic tries to minimize the number of regular expressions to +search per each symbol. + +By default, it runs on a single CPU, as Python support for CPU threads +is still experimental, and multi-process runs on Python is very slow. + +On experimental tests, if the number of ABI symbols to search per devnode +is contained on a limit of ~150 regular expressions, using a single CPU +is a lot faster than using multiple processes. However, if the number of +regular expressions to check is at the order of ~30000, using multiple +CPUs speeds up the check. +""" + +class AbiUndefined: + """ + Initialize an argparse subparser for logic to check undefined ABI at + the current machine's sysfs + """ + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("undefined", + formatter_class=argparse.RawTextHelpFormatter, + description=UNDEFINED_DESC) + + parser.add_argument("-S", "--sysfs-dir", default="/sys", + help="directory where sysfs is mounted") + parser.add_argument("-s", "--search-string", + help="search string regular expression to limit symbol search") + parser.add_argument("-H", "--show-hints", action="store_true", + help="Hints about definitions for missing ABI symbols.") + parser.add_argument("-j", "--jobs", "--max-workers", type=int, default=1, + help="If bigger than one, enables multiprocessing.") + parser.add_argument("-c", "--max-chunk-size", type=int, default=50, + help="Maximum number of chunk size") + parser.add_argument("-f", "--found", action="store_true", + help="Also show found items. " + "Helpful to debug the parser."), + parser.add_argument("-d", "--dry-run", action="store_true", + help="Don't actually search for undefined. " + "Helpful to debug the parser."), + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + abi = AbiRegex(args.dir, debug=args.debug, + search_string=args.search_string) + + abi_symbols = SystemSymbols(abi=abi, hints=args.show_hints, + sysfs=args.sysfs_dir) + + abi_symbols.check_undefined_symbols(dry_run=args.dry_run, + found=args.found, + max_workers=args.jobs, + chunk_size=args.max_chunk_size) + + +def main(): + """Main program""" + + parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter) + + parser.add_argument("-d", "--debug", type=int, default=0, help="debug level") + parser.add_argument("-D", "--dir", default=ABI_DIR, help=DEBUG_HELP) + + subparsers = parser.add_subparsers() + + AbiRest(subparsers) + AbiValidate(subparsers) + AbiSearch(subparsers) + AbiUndefined(subparsers) + + args = parser.parse_args() + + if args.debug: + level = logging.DEBUG + else: + level = logging.INFO + + logging.basicConfig(level=level, format="[%(levelname)s] %(message)s") + + if "func" in args: + args.func(args) + else: + sys.exit(f"Please specify a valid command for {sys.argv[0]}") + + +# Call main method +if __name__ == "__main__": + main() diff --git a/scripts/get_feat.pl b/scripts/get_feat.pl index 5c5397eeb237..40fb28c8424e 100755 --- a/scripts/get_feat.pl +++ b/scripts/get_feat.pl @@ -512,13 +512,13 @@ print STDERR Data::Dumper->Dump([\%data], [qw(*data)]) if ($debug); # Handles the command # if ($cmd eq "current") { - $arch = qx(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/'); + $arch = qx(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/' | sed 's/s390x/s390/'); $arch =~s/\s+$//; } if ($cmd eq "ls" or $cmd eq "list") { if (!$arch) { - $arch = qx(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/'); + $arch = qx(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/' | sed 's/s390x/s390/'); $arch =~s/\s+$//; } diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 5ac02e198737..4414194bedcf 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -50,6 +50,7 @@ my $output_multiline = 1; my $output_separator = ", "; my $output_roles = 0; my $output_rolestats = 1; +my $output_substatus = undef; my $output_section_maxlen = 50; my $scm = 0; my $tree = 1; @@ -269,6 +270,7 @@ if (!GetOptions( 'separator=s' => \$output_separator, 'subsystem!' => \$subsystem, 'status!' => \$status, + 'substatus!' => \$output_substatus, 'scm!' => \$scm, 'tree!' => \$tree, 'web!' => \$web, @@ -314,6 +316,10 @@ $output_multiline = 0 if ($output_separator ne ", "); $output_rolestats = 1 if ($interactive); $output_roles = 1 if ($output_rolestats); +if (!defined $output_substatus) { + $output_substatus = $email && $output_roles && -t STDOUT; +} + if ($sections || $letters ne "") { $sections = 1; $email = 0; @@ -637,6 +643,7 @@ my @web = (); my @bug = (); my @subsystem = (); my @status = (); +my @substatus = (); my %deduplicate_name_hash = (); my %deduplicate_address_hash = (); @@ -651,6 +658,11 @@ if ($scm) { output(@scm); } +if ($output_substatus) { + @substatus = uniq(@substatus); + output(@substatus); +} + if ($status) { @status = uniq(@status); output(@status); @@ -859,6 +871,7 @@ sub get_maintainers { @bug = (); @subsystem = (); @status = (); + @substatus = (); %deduplicate_name_hash = (); %deduplicate_address_hash = (); if ($email_git_all_signature_types) { @@ -1071,8 +1084,9 @@ MAINTAINER field selection options: --moderated => include moderated lists(s) if any (default: true) --s => include subscriber only list(s) if any (default: false) --remove-duplicates => minimize duplicate email names/addresses - --roles => show roles (status:subsystem, git-signer, list, etc...) + --roles => show roles (role:subsystem, git-signer, list, etc...) --rolestats => show roles and statistics (commits/total_commits, %) + --substatus => show subsystem status if not Maintained (default: match --roles when output is tty)" --file-emails => add email addresses found in -f file (default: 0 (off)) --fixes => for patches, add signatures of commits with 'Fixes: <commit>' (default: 1 (on)) --scm => print SCM tree(s) if any @@ -1284,8 +1298,9 @@ sub get_maintainer_role { my $start = find_starting_index($index); my $end = find_ending_index($index); - my $role = "unknown"; + my $role = "maintainer"; my $subsystem = get_subsystem_name($index); + my $status = "unknown"; for ($i = $start + 1; $i < $end; $i++) { my $tv = $typevalue[$i]; @@ -1293,23 +1308,13 @@ sub get_maintainer_role { my $ptype = $1; my $pvalue = $2; if ($ptype eq "S") { - $role = $pvalue; + $status = $pvalue; } } } - $role = lc($role); - if ($role eq "supported") { - $role = "supporter"; - } elsif ($role eq "maintained") { - $role = "maintainer"; - } elsif ($role eq "odd fixes") { - $role = "odd fixer"; - } elsif ($role eq "orphan") { - $role = "orphan minder"; - } elsif ($role eq "obsolete") { - $role = "obsolete minder"; - } elsif ($role eq "buried alive in reporters") { + $status = lc($status); + if ($status eq "buried alive in reporters") { $role = "chief penguin"; } @@ -1335,7 +1340,9 @@ sub add_categories { my $start = find_starting_index($index); my $end = find_ending_index($index); - push(@subsystem, $typevalue[$start]); + my $subsystem = $typevalue[$start]; + push(@subsystem, $subsystem); + my $status = "Unknown"; for ($i = $start + 1; $i < $end; $i++) { my $tv = $typevalue[$i]; @@ -1386,8 +1393,8 @@ sub add_categories { } } elsif ($ptype eq "R") { if ($email_reviewer) { - my $subsystem = get_subsystem_name($i); - push_email_addresses($pvalue, "reviewer:$subsystem" . $suffix); + my $subs = get_subsystem_name($i); + push_email_addresses($pvalue, "reviewer:$subs" . $suffix); } } elsif ($ptype eq "T") { push(@scm, $pvalue . $suffix); @@ -1397,9 +1404,14 @@ sub add_categories { push(@bug, $pvalue . $suffix); } elsif ($ptype eq "S") { push(@status, $pvalue . $suffix); + $status = $pvalue; } } } + + if ($subsystem ne "THE REST" and $status ne "Maintained") { + push(@substatus, $subsystem . " status: " . $status . $suffix) + } } sub email_inuse { @@ -1903,6 +1915,7 @@ EOT $done = 1; $output_rolestats = 0; $output_roles = 0; + $output_substatus = 0; last; } elsif ($nr =~ /^\d+$/ && $nr > 0 && $nr <= $count) { $selected{$nr - 1} = !$selected{$nr - 1}; diff --git a/scripts/integer-wrap-ignore.scl b/scripts/integer-wrap-ignore.scl new file mode 100644 index 000000000000..431c3053a4a2 --- /dev/null +++ b/scripts/integer-wrap-ignore.scl @@ -0,0 +1,3 @@ +[{unsigned-integer-overflow,signed-integer-overflow,implicit-signed-integer-truncation,implicit-unsigned-integer-truncation}] +type:* +type:size_t=sanitize diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 03852da3d249..4b0234e4b12f 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -5,7 +5,7 @@ * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. * - * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S + * Usage: kallsyms [--all-symbols] in.map > out.S * * Table compression uses all the unused char codes on the symbols and * maps these to the most used substrings (tokens). For instance, it might @@ -37,7 +37,6 @@ struct sym_entry { unsigned long long addr; unsigned int len; unsigned int seq; - bool percpu_absolute; unsigned char sym[]; }; @@ -55,14 +54,9 @@ static struct addr_range text_ranges[] = { #define text_range_text (&text_ranges[0]) #define text_range_inittext (&text_ranges[1]) -static struct addr_range percpu_range = { - "__per_cpu_start", "__per_cpu_end", -1ULL, 0 -}; - static struct sym_entry **table; static unsigned int table_size, table_cnt; static int all_symbols; -static int absolute_percpu; static int token_profit[0x10000]; @@ -73,7 +67,7 @@ static unsigned char best_table_len[256]; static void usage(void) { - fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n"); + fprintf(stderr, "Usage: kallsyms [--all-symbols] in.map > out.S\n"); exit(1); } @@ -164,7 +158,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len) return NULL; check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges)); - check_symbol_range(name, addr, &percpu_range, 1); /* include the type field in the symbol name, so that it gets * compressed together */ @@ -175,7 +168,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len) sym->len = len; sym->sym[0] = type; strcpy(sym_name(sym), name); - sym->percpu_absolute = false; return sym; } @@ -319,11 +311,6 @@ static int expand_symbol(const unsigned char *data, int len, char *result) return total; } -static bool symbol_absolute(const struct sym_entry *s) -{ - return s->percpu_absolute; -} - static int compare_names(const void *a, const void *b) { int ret; @@ -455,22 +442,11 @@ static void write_src(void) */ long long offset; - bool overflow; - - if (!absolute_percpu) { - offset = table[i]->addr - relative_base; - overflow = offset < 0 || offset > UINT_MAX; - } else if (symbol_absolute(table[i])) { - offset = table[i]->addr; - overflow = offset < 0 || offset > INT_MAX; - } else { - offset = relative_base - table[i]->addr - 1; - overflow = offset < INT_MIN || offset >= 0; - } - if (overflow) { + + offset = table[i]->addr - relative_base; + if (offset < 0 || offset > UINT_MAX) { fprintf(stderr, "kallsyms failure: " - "%s symbol value %#llx out of range in relative mode\n", - symbol_absolute(table[i]) ? "absolute" : "relative", + "relative symbol value %#llx out of range\n", table[i]->addr); exit(EXIT_FAILURE); } @@ -725,36 +701,15 @@ static void sort_symbols(void) qsort(table, table_cnt, sizeof(table[0]), compare_symbols); } -static void make_percpus_absolute(void) -{ - unsigned int i; - - for (i = 0; i < table_cnt; i++) - if (symbol_in_range(table[i], &percpu_range, 1)) { - /* - * Keep the 'A' override for percpu symbols to - * ensure consistent behavior compared to older - * versions of this tool. - */ - table[i]->sym[0] = 'A'; - table[i]->percpu_absolute = true; - } -} - /* find the minimum non-absolute symbol address */ static void record_relative_base(void) { - unsigned int i; - - for (i = 0; i < table_cnt; i++) - if (!symbol_absolute(table[i])) { - /* - * The table is sorted by address. - * Take the first non-absolute symbol value. - */ - relative_base = table[i]->addr; - return; - } + /* + * The table is sorted by address. + * Take the first symbol value. + */ + if (table_cnt) + relative_base = table[0]->addr; } int main(int argc, char **argv) @@ -762,7 +717,6 @@ int main(int argc, char **argv) while (1) { static const struct option long_options[] = { {"all-symbols", no_argument, &all_symbols, 1}, - {"absolute-percpu", no_argument, &absolute_percpu, 1}, {}, }; @@ -779,8 +733,6 @@ int main(int argc, char **argv) read_map(argv[optind]); shrink_table(); - if (absolute_percpu) - make_percpus_absolute(); sort_symbols(); record_relative_base(); optimize_token_table(); diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index a0a0be38cbdc..fb50bd4f4103 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -105,9 +105,11 @@ configfiles = $(wildcard $(srctree)/kernel/configs/$(1) $(srctree)/arch/$(SRCARC all-config-fragments = $(call configfiles,*.config) config-fragments = $(call configfiles,$@) +cmd_merge_fragments = $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) + %.config: $(obj)/conf $(if $(config-fragments),, $(error $@ fragment does not exists on this architecture)) - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) + $(call cmd,merge_fragments) $(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig PHONY += tinyconfig diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 4286d5e7f95d..ac95661a1c9d 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -360,10 +360,12 @@ int conf_read_simple(const char *name, int def) *p = '\0'; - in = zconf_fopen(env); + name = env; + + in = zconf_fopen(name); if (in) { conf_message("using defaults found in %s", - env); + name); goto load; } @@ -383,7 +385,7 @@ load: def_flags = SYMBOL_DEF << def; for_all_symbols(sym) { - sym->flags &= ~(def_flags|SYMBOL_VALID); + sym->flags &= ~def_flags; switch (sym->type) { case S_INT: case S_HEX: @@ -396,7 +398,11 @@ load: } } - expr_invalidate_all(); + if (def == S_DEF_USER) { + for_all_symbols(sym) + sym->flags &= ~SYMBOL_VALID; + expr_invalidate_all(); + } while (getline_stripped(&line, &line_asize, in) != -1) { struct menu *choice; @@ -462,6 +468,9 @@ load: if (conf_set_sym_val(sym, def, def_flags, val)) continue; + if (def != S_DEF_USER) + continue; + /* * If this is a choice member, give it the highest priority. * If conflicting CONFIG options are given from an input file, @@ -965,10 +974,8 @@ static int conf_touch_deps(void) depfile_path[depfile_prefix_len] = 0; conf_read_simple(name, S_DEF_AUTO); - sym_calc_value(modules_sym); for_all_symbols(sym) { - sym_calc_value(sym); if (sym_is_choice(sym)) continue; if (sym->flags & SYMBOL_WRITE) { @@ -1082,12 +1089,12 @@ int conf_write_autoconf(int overwrite) if (ret) return -1; - if (conf_touch_deps()) - return 1; - for_all_symbols(sym) sym_calc_value(sym); + if (conf_touch_deps()) + return 1; + ret = __conf_write_autoconf(conf_get_autoheader_name(), print_symbol_for_c, &comment_style_c); diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 0b7952471c18..79c09b378be8 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -112,8 +112,8 @@ INITFILE=$1 shift; if [ ! -r "$INITFILE" ]; then - echo "The base file '$INITFILE' does not exist. Exit." >&2 - exit 1 + echo "The base file '$INITFILE' does not exist. Creating one..." >&2 + touch "$INITFILE" fi MERGE_LIST=$* diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 6c92ef1e16ef..eaa465b0ccf9 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -1464,8 +1464,8 @@ void ConfigMainWindow::loadConfig(void) { QString str; - str = QFileDialog::getOpenFileName(this, "", configname); - if (str.isNull()) + str = QFileDialog::getOpenFileName(this, QString(), configname); + if (str.isEmpty()) return; if (conf_read(str.toLocal8Bit().constData())) @@ -1491,8 +1491,8 @@ void ConfigMainWindow::saveConfigAs(void) { QString str; - str = QFileDialog::getSaveFileName(this, "", configname); - if (str.isNull()) + str = QFileDialog::getSaveFileName(this, QString(), configname); + if (str.isEmpty()) return; if (conf_write(str.toLocal8Bit().constData())) { diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 89b84bf8e21f..d57f8cbba291 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -388,6 +388,7 @@ static void sym_warn_unmet_dep(const struct symbol *sym) " Selected by [m]:\n"); fputs(str_get(&gs), stderr); + str_free(&gs); sym_warnings++; } @@ -878,7 +879,7 @@ const char *sym_get_string_value(struct symbol *sym) default: ; } - return (const char *)sym->curr.val; + return sym->curr.val; } bool sym_is_changeable(const struct symbol *sym) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 4ee843d3600e..3b6ef807791a 100755..120000 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1,2560 +1 @@ -#!/usr/bin/env perl -# SPDX-License-Identifier: GPL-2.0 -# vim: softtabstop=4 - -use warnings; -use strict; - -## Copyright (c) 1998 Michael Zucchi, All Rights Reserved ## -## Copyright (C) 2000, 1 Tim Waugh <twaugh@redhat.com> ## -## Copyright (C) 2001 Simon Huggins ## -## Copyright (C) 2005-2012 Randy Dunlap ## -## Copyright (C) 2012 Dan Luedtke ## -## ## -## #define enhancements by Armin Kuster <akuster@mvista.com> ## -## Copyright (c) 2000 MontaVista Software, Inc. ## -# -# Copyright (C) 2022 Tomasz WarnieÅ‚Å‚o (POD) - -use Pod::Usage qw/pod2usage/; - -=head1 NAME - -kernel-doc - Print formatted kernel documentation to stdout - -=head1 SYNOPSIS - - kernel-doc [-h] [-v] [-Werror] [-Wall] [-Wreturn] [-Wshort-desc[ription]] [-Wcontents-before-sections] - [ -man | - -rst [-sphinx-version VERSION] [-enable-lineno] | - -none - ] - [ - -export | - -internal | - [-function NAME] ... | - [-nosymbol NAME] ... - ] - [-no-doc-sections] - [-export-file FILE] ... - FILE ... - -Run `kernel-doc -h` for details. - -=head1 DESCRIPTION - -Read C language source or header FILEs, extract embedded documentation comments, -and print formatted documentation to standard output. - -The documentation comments are identified by the "/**" opening comment mark. - -See Documentation/doc-guide/kernel-doc.rst for the documentation comment syntax. - -=cut - -# more perldoc at the end of the file - -## init lots of data - -my $errors = 0; -my $warnings = 0; -my $anon_struct_union = 0; - -# match expressions used to find embedded type information -my $type_constant = '\b``([^\`]+)``\b'; -my $type_constant2 = '\%([-_*\w]+)'; -my $type_func = '(\w+)\(\)'; -my $type_param = '\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)'; -my $type_param_ref = '([\!~\*]?)\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)'; -my $type_fp_param = '\@(\w+)\(\)'; # Special RST handling for func ptr params -my $type_fp_param2 = '\@(\w+->\S+)\(\)'; # Special RST handling for structs with func ptr params -my $type_env = '(\$\w+)'; -my $type_enum = '\&(enum\s*([_\w]+))'; -my $type_struct = '\&(struct\s*([_\w]+))'; -my $type_typedef = '\&(typedef\s*([_\w]+))'; -my $type_union = '\&(union\s*([_\w]+))'; -my $type_member = '\&([_\w]+)(\.|->)([_\w]+)'; -my $type_fallback = '\&([_\w]+)'; -my $type_member_func = $type_member . '\(\)'; - -# Output conversion substitutions. -# One for each output format - -# these are pretty rough -my @highlights_man = ( - [$type_constant, "\$1"], - [$type_constant2, "\$1"], - [$type_func, "\\\\fB\$1\\\\fP"], - [$type_enum, "\\\\fI\$1\\\\fP"], - [$type_struct, "\\\\fI\$1\\\\fP"], - [$type_typedef, "\\\\fI\$1\\\\fP"], - [$type_union, "\\\\fI\$1\\\\fP"], - [$type_param, "\\\\fI\$1\\\\fP"], - [$type_param_ref, "\\\\fI\$1\$2\\\\fP"], - [$type_member, "\\\\fI\$1\$2\$3\\\\fP"], - [$type_fallback, "\\\\fI\$1\\\\fP"] - ); -my $blankline_man = ""; - -# rst-mode -my @highlights_rst = ( - [$type_constant, "``\$1``"], - [$type_constant2, "``\$1``"], - - # Note: need to escape () to avoid func matching later - [$type_member_func, "\\:c\\:type\\:`\$1\$2\$3\\\\(\\\\) <\$1>`"], - [$type_member, "\\:c\\:type\\:`\$1\$2\$3 <\$1>`"], - [$type_fp_param, "**\$1\\\\(\\\\)**"], - [$type_fp_param2, "**\$1\\\\(\\\\)**"], - [$type_func, "\$1()"], - [$type_enum, "\\:c\\:type\\:`\$1 <\$2>`"], - [$type_struct, "\\:c\\:type\\:`\$1 <\$2>`"], - [$type_typedef, "\\:c\\:type\\:`\$1 <\$2>`"], - [$type_union, "\\:c\\:type\\:`\$1 <\$2>`"], - - # in rst this can refer to any type - [$type_fallback, "\\:c\\:type\\:`\$1`"], - [$type_param_ref, "**\$1\$2**"] - ); -my $blankline_rst = "\n"; - -# read arguments -if ($#ARGV == -1) { - pod2usage( - -message => "No arguments!\n", - -exitval => 1, - -verbose => 99, - -sections => 'SYNOPSIS', - -output => \*STDERR, - ); -} - -my $kernelversion; -my ($sphinx_major, $sphinx_minor, $sphinx_patch); - -my $dohighlight = ""; - -my $verbose = 0; -my $Werror = 0; -my $Wreturn = 0; -my $Wshort_desc = 0; -my $Wcontents_before_sections = 0; -my $output_mode = "rst"; -my $output_preformatted = 0; -my $no_doc_sections = 0; -my $enable_lineno = 0; -my @highlights = @highlights_rst; -my $blankline = $blankline_rst; -my $modulename = "Kernel API"; - -use constant { - OUTPUT_ALL => 0, # output all symbols and doc sections - OUTPUT_INCLUDE => 1, # output only specified symbols - OUTPUT_EXPORTED => 2, # output exported symbols - OUTPUT_INTERNAL => 3, # output non-exported symbols -}; -my $output_selection = OUTPUT_ALL; -my $show_not_found = 0; # No longer used - -my @export_file_list; - -my @build_time; -if (defined($ENV{'KBUILD_BUILD_TIMESTAMP'}) && - (my $seconds = `date -d "${ENV{'KBUILD_BUILD_TIMESTAMP'}}" +%s`) ne '') { - @build_time = gmtime($seconds); -} else { - @build_time = localtime; -} - -my $man_date = ('January', 'February', 'March', 'April', 'May', 'June', - 'July', 'August', 'September', 'October', - 'November', 'December')[$build_time[4]] . - " " . ($build_time[5]+1900); - -# Essentially these are globals. -# They probably want to be tidied up, made more localised or something. -# CAVEAT EMPTOR! Some of the others I localised may not want to be, which -# could cause "use of undefined value" or other bugs. -my ($function, %function_table, %parametertypes, $declaration_purpose); -my %nosymbol_table = (); -my $declaration_start_line; -my ($type, $declaration_name, $return_type); -my ($newsection, $newcontents, $prototype, $brcount, %source_map); - -if (defined($ENV{'KBUILD_VERBOSE'}) && $ENV{'KBUILD_VERBOSE'} =~ '1') { - $verbose = 1; -} - -if (defined($ENV{'KCFLAGS'})) { - my $kcflags = "$ENV{'KCFLAGS'}"; - - if ($kcflags =~ /(\s|^)-Werror(\s|$)/) { - $Werror = 1; - } -} - -# reading this variable is for backwards compat just in case -# someone was calling it with the variable from outside the -# kernel's build system -if (defined($ENV{'KDOC_WERROR'})) { - $Werror = "$ENV{'KDOC_WERROR'}"; -} -# other environment variables are converted to command-line -# arguments in cmd_checkdoc in the build system - -# Generated docbook code is inserted in a template at a point where -# docbook v3.1 requires a non-zero sequence of RefEntry's; see: -# https://www.oasis-open.org/docbook/documentation/reference/html/refentry.html -# We keep track of number of generated entries and generate a dummy -# if needs be to ensure the expanded template can be postprocessed -# into html. -my $section_counter = 0; - -my $lineprefix=""; - -# Parser states -use constant { - STATE_NORMAL => 0, # normal code - STATE_NAME => 1, # looking for function name - STATE_BODY_MAYBE => 2, # body - or maybe more description - STATE_BODY => 3, # the body of the comment - STATE_BODY_WITH_BLANK_LINE => 4, # the body, which has a blank line - STATE_PROTO => 5, # scanning prototype - STATE_DOCBLOCK => 6, # documentation block - STATE_INLINE => 7, # gathering doc outside main block -}; -my $state; -my $in_doc_sect; -my $leading_space; - -# Inline documentation state -use constant { - STATE_INLINE_NA => 0, # not applicable ($state != STATE_INLINE) - STATE_INLINE_NAME => 1, # looking for member name (@foo:) - STATE_INLINE_TEXT => 2, # looking for member documentation - STATE_INLINE_END => 3, # done - STATE_INLINE_ERROR => 4, # error - Comment without header was found. - # Spit a warning as it's not - # proper kernel-doc and ignore the rest. -}; -my $inline_doc_state; - -#declaration types: can be -# 'function', 'struct', 'union', 'enum', 'typedef' -my $decl_type; - -# Name of the kernel-doc identifier for non-DOC markups -my $identifier; - -my $doc_start = '^/\*\*\s*$'; # Allow whitespace at end of comment start. -my $doc_end = '\*/'; -my $doc_com = '\s*\*\s*'; -my $doc_com_body = '\s*\* ?'; -my $doc_decl = $doc_com . '(\w+)'; -# @params and a strictly limited set of supported section names -# Specifically: -# Match @word: -# @...: -# @{section-name}: -# while trying to not match literal block starts like "example::" -# -my $doc_sect = $doc_com . - '\s*(\@[.\w]+|\@\.\.\.|description|context|returns?|notes?|examples?)\s*:([^:].*)?$'; -my $doc_content = $doc_com_body . '(.*)'; -my $doc_block = $doc_com . 'DOC:\s*(.*)?'; -my $doc_inline_start = '^\s*/\*\*\s*$'; -my $doc_inline_sect = '\s*\*\s*(@\s*[\w][\w\.]*\s*):(.*)'; -my $doc_inline_end = '^\s*\*/\s*$'; -my $doc_inline_oneline = '^\s*/\*\*\s*(@[\w\s]+):\s*(.*)\s*\*/\s*$'; -my $export_symbol = '^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*;'; -my $export_symbol_ns = '^\s*EXPORT_SYMBOL_NS(_GPL)?\s*\(\s*(\w+)\s*,\s*"\S+"\)\s*;'; -my $function_pointer = qr{([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)}; -my $attribute = qr{__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)}i; - -my %parameterdescs; -my %parameterdesc_start_lines; -my @parameterlist; -my %sections; -my @sectionlist; -my %section_start_lines; -my $sectcheck; -my $struct_actual; - -my $contents = ""; -my $new_start_line = 0; - -# the canonical section names. see also $doc_sect above. -my $section_default = "Description"; # default section -my $section_intro = "Introduction"; -my $section = $section_default; -my $section_context = "Context"; -my $section_return = "Return"; - -my $undescribed = "-- undescribed --"; - -reset_state(); - -while ($ARGV[0] =~ m/^--?(.*)/) { - my $cmd = $1; - shift @ARGV; - if ($cmd eq "man") { - $output_mode = "man"; - @highlights = @highlights_man; - $blankline = $blankline_man; - } elsif ($cmd eq "rst") { - $output_mode = "rst"; - @highlights = @highlights_rst; - $blankline = $blankline_rst; - } elsif ($cmd eq "none") { - $output_mode = "none"; - } elsif ($cmd eq "module") { # not needed for XML, inherits from calling document - $modulename = shift @ARGV; - } elsif ($cmd eq "function") { # to only output specific functions - $output_selection = OUTPUT_INCLUDE; - $function = shift @ARGV; - $function_table{$function} = 1; - } elsif ($cmd eq "nosymbol") { # Exclude specific symbols - my $symbol = shift @ARGV; - $nosymbol_table{$symbol} = 1; - } elsif ($cmd eq "export") { # only exported symbols - $output_selection = OUTPUT_EXPORTED; - %function_table = (); - } elsif ($cmd eq "internal") { # only non-exported symbols - $output_selection = OUTPUT_INTERNAL; - %function_table = (); - } elsif ($cmd eq "export-file") { - my $file = shift @ARGV; - push(@export_file_list, $file); - } elsif ($cmd eq "v") { - $verbose = 1; - } elsif ($cmd eq "Werror") { - $Werror = 1; - } elsif ($cmd eq "Wreturn") { - $Wreturn = 1; - } elsif ($cmd eq "Wshort-desc" or $cmd eq "Wshort-description") { - $Wshort_desc = 1; - } elsif ($cmd eq "Wcontents-before-sections") { - $Wcontents_before_sections = 1; - } elsif ($cmd eq "Wall") { - $Wreturn = 1; - $Wshort_desc = 1; - $Wcontents_before_sections = 1; - } elsif (($cmd eq "h") || ($cmd eq "help")) { - pod2usage(-exitval => 0, -verbose => 2); - } elsif ($cmd eq 'no-doc-sections') { - $no_doc_sections = 1; - } elsif ($cmd eq 'enable-lineno') { - $enable_lineno = 1; - } elsif ($cmd eq 'show-not-found') { - $show_not_found = 1; # A no-op but don't fail - } elsif ($cmd eq "sphinx-version") { - my $ver_string = shift @ARGV; - if ($ver_string =~ m/^(\d+)(\.\d+)?(\.\d+)?/) { - $sphinx_major = $1; - if (defined($2)) { - $sphinx_minor = substr($2,1); - } else { - $sphinx_minor = 0; - } - if (defined($3)) { - $sphinx_patch = substr($3,1) - } else { - $sphinx_patch = 0; - } - } else { - die "Sphinx version should either major.minor or major.minor.patch format\n"; - } - } else { - # Unknown argument - pod2usage( - -message => "Argument unknown!\n", - -exitval => 1, - -verbose => 99, - -sections => 'SYNOPSIS', - -output => \*STDERR, - ); - } - if ($#ARGV < 0){ - pod2usage( - -message => "FILE argument missing\n", - -exitval => 1, - -verbose => 99, - -sections => 'SYNOPSIS', - -output => \*STDERR, - ); - } -} - -# continue execution near EOF; - -# The C domain dialect changed on Sphinx 3. So, we need to check the -# version in order to produce the right tags. -sub findprog($) -{ - foreach(split(/:/, $ENV{PATH})) { - return "$_/$_[0]" if(-x "$_/$_[0]"); - } -} - -sub get_sphinx_version() -{ - my $ver; - - my $cmd = "sphinx-build"; - if (!findprog($cmd)) { - my $cmd = "sphinx-build3"; - if (!findprog($cmd)) { - $sphinx_major = 1; - $sphinx_minor = 2; - $sphinx_patch = 0; - printf STDERR "Warning: Sphinx version not found. Using default (Sphinx version %d.%d.%d)\n", - $sphinx_major, $sphinx_minor, $sphinx_patch; - return; - } - } - - open IN, "$cmd --version 2>&1 |"; - while (<IN>) { - if (m/^\s*sphinx-build\s+([\d]+)\.([\d\.]+)(\+\/[\da-f]+)?$/) { - $sphinx_major = $1; - $sphinx_minor = $2; - $sphinx_patch = $3; - last; - } - # Sphinx 1.2.x uses a different format - if (m/^\s*Sphinx.*\s+([\d]+)\.([\d\.]+)$/) { - $sphinx_major = $1; - $sphinx_minor = $2; - $sphinx_patch = $3; - last; - } - } - close IN; -} - -# get kernel version from env -sub get_kernel_version() { - my $version = 'unknown kernel version'; - - if (defined($ENV{'KERNELVERSION'})) { - $version = $ENV{'KERNELVERSION'}; - } - return $version; -} - -# -sub print_lineno { - my $lineno = shift; - if ($enable_lineno && defined($lineno)) { - print ".. LINENO " . $lineno . "\n"; - } -} - -sub emit_warning { - my $location = shift; - my $msg = shift; - print STDERR "$location: warning: $msg"; - ++$warnings; -} -## -# dumps section contents to arrays/hashes intended for that purpose. -# -sub dump_section { - my $file = shift; - my $name = shift; - my $contents = join "\n", @_; - - if ($name =~ m/$type_param/) { - $name = $1; - $parameterdescs{$name} = $contents; - $sectcheck = $sectcheck . $name . " "; - $parameterdesc_start_lines{$name} = $new_start_line; - $new_start_line = 0; - } elsif ($name eq "@\.\.\.") { - $name = "..."; - $parameterdescs{$name} = $contents; - $sectcheck = $sectcheck . $name . " "; - $parameterdesc_start_lines{$name} = $new_start_line; - $new_start_line = 0; - } else { - if (defined($sections{$name}) && ($sections{$name} ne "")) { - # Only warn on user specified duplicate section names. - if ($name ne $section_default) { - emit_warning("${file}:$.", "duplicate section name '$name'\n"); - } - $sections{$name} .= $contents; - } else { - $sections{$name} = $contents; - push @sectionlist, $name; - $section_start_lines{$name} = $new_start_line; - $new_start_line = 0; - } - } -} - -## -# dump DOC: section after checking that it should go out -# -sub dump_doc_section { - my $file = shift; - my $name = shift; - my $contents = join "\n", @_; - - if ($no_doc_sections) { - return; - } - - return if (defined($nosymbol_table{$name})); - - if (($output_selection == OUTPUT_ALL) || - (($output_selection == OUTPUT_INCLUDE) && - defined($function_table{$name}))) - { - dump_section($file, $name, $contents); - output_blockhead({'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'module' => $modulename, - 'content-only' => ($output_selection != OUTPUT_ALL), }); - } -} - -## -# output function -# -# parameterdescs, a hash. -# function => "function name" -# parameterlist => @list of parameters -# parameterdescs => %parameter descriptions -# sectionlist => @list of sections -# sections => %section descriptions -# - -sub output_highlight { - my $contents = join "\n",@_; - my $line; - -# DEBUG -# if (!defined $contents) { -# use Carp; -# confess "output_highlight got called with no args?\n"; -# } - -# print STDERR "contents b4:$contents\n"; - eval $dohighlight; - die $@ if $@; -# print STDERR "contents af:$contents\n"; - - foreach $line (split "\n", $contents) { - if (! $output_preformatted) { - $line =~ s/^\s*//; - } - if ($line eq ""){ - if (! $output_preformatted) { - print $lineprefix, $blankline; - } - } else { - if ($output_mode eq "man" && substr($line, 0, 1) eq ".") { - print "\\&$line"; - } else { - print $lineprefix, $line; - } - } - print "\n"; - } -} - -## -# output function in man -sub output_function_man(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - my $count; - my $func_macro = $args{'func_macro'}; - my $paramcount = $#{$args{'parameterlist'}}; # -1 is empty - - print ".TH \"$args{'function'}\" 9 \"$args{'function'}\" \"$man_date\" \"Kernel Hacker's Manual\" LINUX\n"; - - print ".SH NAME\n"; - print $args{'function'} . " \\- " . $args{'purpose'} . "\n"; - - print ".SH SYNOPSIS\n"; - if ($args{'functiontype'} ne "") { - print ".B \"" . $args{'functiontype'} . "\" " . $args{'function'} . "\n"; - } else { - print ".B \"" . $args{'function'} . "\n"; - } - $count = 0; - my $parenth = "("; - my $post = ","; - foreach my $parameter (@{$args{'parameterlist'}}) { - if ($count == $#{$args{'parameterlist'}}) { - $post = ");"; - } - $type = $args{'parametertypes'}{$parameter}; - if ($type =~ m/$function_pointer/) { - # pointer-to-function - print ".BI \"" . $parenth . $1 . "\" " . " \") (" . $2 . ")" . $post . "\"\n"; - } else { - $type =~ s/([^\*])$/$1 /; - print ".BI \"" . $parenth . $type . "\" " . " \"" . $post . "\"\n"; - } - $count++; - $parenth = ""; - } - - $paramcount = $#{$args{'parameterlist'}}; # -1 is empty - if ($paramcount >= 0) { - print ".SH ARGUMENTS\n"; - } - foreach $parameter (@{$args{'parameterlist'}}) { - my $parameter_name = $parameter; - $parameter_name =~ s/\[.*//; - - print ".IP \"" . $parameter . "\" 12\n"; - output_highlight($args{'parameterdescs'}{$parameter_name}); - } - foreach $section (@{$args{'sectionlist'}}) { - print ".SH \"", uc $section, "\"\n"; - output_highlight($args{'sections'}{$section}); - } -} - -## -# output enum in man -sub output_enum_man(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - my $count; - - print ".TH \"$args{'module'}\" 9 \"enum $args{'enum'}\" \"$man_date\" \"API Manual\" LINUX\n"; - - print ".SH NAME\n"; - print "enum " . $args{'enum'} . " \\- " . $args{'purpose'} . "\n"; - - print ".SH SYNOPSIS\n"; - print "enum " . $args{'enum'} . " {\n"; - $count = 0; - foreach my $parameter (@{$args{'parameterlist'}}) { - print ".br\n.BI \" $parameter\"\n"; - if ($count == $#{$args{'parameterlist'}}) { - print "\n};\n"; - last; - } else { - print ", \n.br\n"; - } - $count++; - } - - print ".SH Constants\n"; - foreach $parameter (@{$args{'parameterlist'}}) { - my $parameter_name = $parameter; - $parameter_name =~ s/\[.*//; - - print ".IP \"" . $parameter . "\" 12\n"; - output_highlight($args{'parameterdescs'}{$parameter_name}); - } - foreach $section (@{$args{'sectionlist'}}) { - print ".SH \"$section\"\n"; - output_highlight($args{'sections'}{$section}); - } -} - -## -# output struct in man -sub output_struct_man(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - - print ".TH \"$args{'module'}\" 9 \"" . $args{'type'} . " " . $args{'struct'} . "\" \"$man_date\" \"API Manual\" LINUX\n"; - - print ".SH NAME\n"; - print $args{'type'} . " " . $args{'struct'} . " \\- " . $args{'purpose'} . "\n"; - - my $declaration = $args{'definition'}; - $declaration =~ s/\t/ /g; - $declaration =~ s/\n/"\n.br\n.BI \"/g; - print ".SH SYNOPSIS\n"; - print $args{'type'} . " " . $args{'struct'} . " {\n.br\n"; - print ".BI \"$declaration\n};\n.br\n\n"; - - print ".SH Members\n"; - foreach $parameter (@{$args{'parameterlist'}}) { - ($parameter =~ /^#/) && next; - - my $parameter_name = $parameter; - $parameter_name =~ s/\[.*//; - - ($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next; - print ".IP \"" . $parameter . "\" 12\n"; - output_highlight($args{'parameterdescs'}{$parameter_name}); - } - foreach $section (@{$args{'sectionlist'}}) { - print ".SH \"$section\"\n"; - output_highlight($args{'sections'}{$section}); - } -} - -## -# output typedef in man -sub output_typedef_man(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - - print ".TH \"$args{'module'}\" 9 \"$args{'typedef'}\" \"$man_date\" \"API Manual\" LINUX\n"; - - print ".SH NAME\n"; - print "typedef " . $args{'typedef'} . " \\- " . $args{'purpose'} . "\n"; - - foreach $section (@{$args{'sectionlist'}}) { - print ".SH \"$section\"\n"; - output_highlight($args{'sections'}{$section}); - } -} - -sub output_blockhead_man(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - my $count; - - print ".TH \"$args{'module'}\" 9 \"$args{'module'}\" \"$man_date\" \"API Manual\" LINUX\n"; - - foreach $section (@{$args{'sectionlist'}}) { - print ".SH \"$section\"\n"; - output_highlight($args{'sections'}{$section}); - } -} - -## -# output in restructured text -# - -# -# This could use some work; it's used to output the DOC: sections, and -# starts by putting out the name of the doc section itself, but that tends -# to duplicate a header already in the template file. -# -sub output_blockhead_rst(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - - foreach $section (@{$args{'sectionlist'}}) { - next if (defined($nosymbol_table{$section})); - - if ($output_selection != OUTPUT_INCLUDE) { - print ".. _$section:\n\n"; - print "**$section**\n\n"; - } - print_lineno($section_start_lines{$section}); - output_highlight_rst($args{'sections'}{$section}); - print "\n"; - } -} - -# -# Apply the RST highlights to a sub-block of text. -# -sub highlight_block($) { - # The dohighlight kludge requires the text be called $contents - my $contents = shift; - eval $dohighlight; - die $@ if $@; - return $contents; -} - -# -# Regexes used only here. -# -my $sphinx_literal = '^[^.].*::$'; -my $sphinx_cblock = '^\.\.\ +code-block::'; - -sub output_highlight_rst { - my $input = join "\n",@_; - my $output = ""; - my $line; - my $in_literal = 0; - my $litprefix; - my $block = ""; - - foreach $line (split "\n",$input) { - # - # If we're in a literal block, see if we should drop out - # of it. Otherwise pass the line straight through unmunged. - # - if ($in_literal) { - if (! ($line =~ /^\s*$/)) { - # - # If this is the first non-blank line in a literal - # block we need to figure out what the proper indent is. - # - if ($litprefix eq "") { - $line =~ /^(\s*)/; - $litprefix = '^' . $1; - $output .= $line . "\n"; - } elsif (! ($line =~ /$litprefix/)) { - $in_literal = 0; - } else { - $output .= $line . "\n"; - } - } else { - $output .= $line . "\n"; - } - } - # - # Not in a literal block (or just dropped out) - # - if (! $in_literal) { - $block .= $line . "\n"; - if (($line =~ /$sphinx_literal/) || ($line =~ /$sphinx_cblock/)) { - $in_literal = 1; - $litprefix = ""; - $output .= highlight_block($block); - $block = "" - } - } - } - - if ($block) { - $output .= highlight_block($block); - } - foreach $line (split "\n", $output) { - print $lineprefix . $line . "\n"; - } -} - -sub output_function_rst(%) { - my %args = %{$_[0]}; - my ($parameter, $section); - my $oldprefix = $lineprefix; - - my $signature = ""; - my $func_macro = $args{'func_macro'}; - my $paramcount = $#{$args{'parameterlist'}}; # -1 is empty - - if ($func_macro) { - $signature = $args{'function'}; - } else { - if ($args{'functiontype'}) { - $signature = $args{'functiontype'} . " "; - } - $signature .= $args{'function'} . " ("; - } - - my $count = 0; - foreach my $parameter (@{$args{'parameterlist'}}) { - if ($count ne 0) { - $signature .= ", "; - } - $count++; - $type = $args{'parametertypes'}{$parameter}; - - if ($type =~ m/$function_pointer/) { - # pointer-to-function - $signature .= $1 . $parameter . ") (" . $2 . ")"; - } else { - $signature .= $type; - } - } - - if (!$func_macro) { - $signature .= ")"; - } - - if ($sphinx_major < 3) { - if ($args{'typedef'}) { - print ".. c:type:: ". $args{'function'} . "\n\n"; - print_lineno($declaration_start_line); - print " **Typedef**: "; - $lineprefix = ""; - output_highlight_rst($args{'purpose'}); - print "\n\n**Syntax**\n\n"; - print " ``$signature``\n\n"; - } else { - print ".. c:function:: $signature\n\n"; - } - } else { - if ($args{'typedef'} || $args{'functiontype'} eq "") { - print ".. c:macro:: ". $args{'function'} . "\n\n"; - - if ($args{'typedef'}) { - print_lineno($declaration_start_line); - print " **Typedef**: "; - $lineprefix = ""; - output_highlight_rst($args{'purpose'}); - print "\n\n**Syntax**\n\n"; - print " ``$signature``\n\n"; - } else { - print "``$signature``\n\n"; - } - } else { - print ".. c:function:: $signature\n\n"; - } - } - - if (!$args{'typedef'}) { - print_lineno($declaration_start_line); - $lineprefix = " "; - output_highlight_rst($args{'purpose'}); - print "\n"; - } - - # - # Put our descriptive text into a container (thus an HTML <div>) to help - # set the function prototypes apart. - # - $lineprefix = " "; - if ($paramcount >= 0) { - print ".. container:: kernelindent\n\n"; - print $lineprefix . "**Parameters**\n\n"; - } - foreach $parameter (@{$args{'parameterlist'}}) { - my $parameter_name = $parameter; - $parameter_name =~ s/\[.*//; - $type = $args{'parametertypes'}{$parameter}; - - if ($type ne "") { - print $lineprefix . "``$type``\n"; - } else { - print $lineprefix . "``$parameter``\n"; - } - - print_lineno($parameterdesc_start_lines{$parameter_name}); - - $lineprefix = " "; - if (defined($args{'parameterdescs'}{$parameter_name}) && - $args{'parameterdescs'}{$parameter_name} ne $undescribed) { - output_highlight_rst($args{'parameterdescs'}{$parameter_name}); - } else { - print $lineprefix . "*undescribed*\n"; - } - $lineprefix = " "; - print "\n"; - } - - output_section_rst(@_); - $lineprefix = $oldprefix; -} - -sub output_section_rst(%) { - my %args = %{$_[0]}; - my $section; - my $oldprefix = $lineprefix; - - foreach $section (@{$args{'sectionlist'}}) { - print $lineprefix . "**$section**\n\n"; - print_lineno($section_start_lines{$section}); - output_highlight_rst($args{'sections'}{$section}); - print "\n"; - } - print "\n"; -} - -sub output_enum_rst(%) { - my %args = %{$_[0]}; - my ($parameter); - my $oldprefix = $lineprefix; - my $count; - my $outer; - - if ($sphinx_major < 3) { - my $name = "enum " . $args{'enum'}; - print "\n\n.. c:type:: " . $name . "\n\n"; - } else { - my $name = $args{'enum'}; - print "\n\n.. c:enum:: " . $name . "\n\n"; - } - print_lineno($declaration_start_line); - $lineprefix = " "; - output_highlight_rst($args{'purpose'}); - print "\n"; - - print ".. container:: kernelindent\n\n"; - $outer = $lineprefix . " "; - $lineprefix = $outer . " "; - print $outer . "**Constants**\n\n"; - foreach $parameter (@{$args{'parameterlist'}}) { - print $outer . "``$parameter``\n"; - - if ($args{'parameterdescs'}{$parameter} ne $undescribed) { - output_highlight_rst($args{'parameterdescs'}{$parameter}); - } else { - print $lineprefix . "*undescribed*\n"; - } - print "\n"; - } - print "\n"; - $lineprefix = $oldprefix; - output_section_rst(@_); -} - -sub output_typedef_rst(%) { - my %args = %{$_[0]}; - my ($parameter); - my $oldprefix = $lineprefix; - my $name; - - if ($sphinx_major < 3) { - $name = "typedef " . $args{'typedef'}; - } else { - $name = $args{'typedef'}; - } - print "\n\n.. c:type:: " . $name . "\n\n"; - print_lineno($declaration_start_line); - $lineprefix = " "; - output_highlight_rst($args{'purpose'}); - print "\n"; - - $lineprefix = $oldprefix; - output_section_rst(@_); -} - -sub output_struct_rst(%) { - my %args = %{$_[0]}; - my ($parameter); - my $oldprefix = $lineprefix; - - if ($sphinx_major < 3) { - my $name = $args{'type'} . " " . $args{'struct'}; - print "\n\n.. c:type:: " . $name . "\n\n"; - } else { - my $name = $args{'struct'}; - if ($args{'type'} eq 'union') { - print "\n\n.. c:union:: " . $name . "\n\n"; - } else { - print "\n\n.. c:struct:: " . $name . "\n\n"; - } - } - print_lineno($declaration_start_line); - $lineprefix = " "; - output_highlight_rst($args{'purpose'}); - print "\n"; - - print ".. container:: kernelindent\n\n"; - print $lineprefix . "**Definition**::\n\n"; - my $declaration = $args{'definition'}; - $lineprefix = $lineprefix . " "; - $declaration =~ s/\t/$lineprefix/g; - print $lineprefix . $args{'type'} . " " . $args{'struct'} . " {\n$declaration" . $lineprefix . "};\n\n"; - - $lineprefix = " "; - print $lineprefix . "**Members**\n\n"; - foreach $parameter (@{$args{'parameterlist'}}) { - ($parameter =~ /^#/) && next; - - my $parameter_name = $parameter; - $parameter_name =~ s/\[.*//; - - ($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next; - $type = $args{'parametertypes'}{$parameter}; - print_lineno($parameterdesc_start_lines{$parameter_name}); - print $lineprefix . "``" . $parameter . "``\n"; - $lineprefix = " "; - output_highlight_rst($args{'parameterdescs'}{$parameter_name}); - $lineprefix = " "; - print "\n"; - } - print "\n"; - - $lineprefix = $oldprefix; - output_section_rst(@_); -} - -## none mode output functions - -sub output_function_none(%) { -} - -sub output_enum_none(%) { -} - -sub output_typedef_none(%) { -} - -sub output_struct_none(%) { -} - -sub output_blockhead_none(%) { -} - -## -# generic output function for all types (function, struct/union, typedef, enum); -# calls the generated, variable output_ function name based on -# functype and output_mode -sub output_declaration { - no strict 'refs'; - my $name = shift; - my $functype = shift; - my $func = "output_${functype}_$output_mode"; - - return if (defined($nosymbol_table{$name})); - - if (($output_selection == OUTPUT_ALL) || - (($output_selection == OUTPUT_INCLUDE || - $output_selection == OUTPUT_EXPORTED) && - defined($function_table{$name})) || - ($output_selection == OUTPUT_INTERNAL && - !($functype eq "function" && defined($function_table{$name})))) - { - &$func(@_); - $section_counter++; - } -} - -## -# generic output function - calls the right one based on current output mode. -sub output_blockhead { - no strict 'refs'; - my $func = "output_blockhead_" . $output_mode; - &$func(@_); - $section_counter++; -} - -## -# takes a declaration (struct, union, enum, typedef) and -# invokes the right handler. NOT called for functions. -sub dump_declaration($$) { - no strict 'refs'; - my ($prototype, $file) = @_; - my $func = "dump_" . $decl_type; - &$func(@_); -} - -sub dump_union($$) { - dump_struct(@_); -} - -sub dump_struct($$) { - my $x = shift; - my $file = shift; - my $decl_type; - my $members; - my $type = qr{struct|union}; - # For capturing struct/union definition body, i.e. "{members*}qualifiers*" - my $qualifiers = qr{$attribute|__packed|__aligned|____cacheline_aligned_in_smp|____cacheline_aligned}; - my $definition_body = qr{\{(.*)\}\s*$qualifiers*}; - my $struct_members = qr{($type)([^\{\};]+)\{([^\{\}]*)\}([^\{\}\;]*)\;}; - - if ($x =~ /($type)\s+(\w+)\s*$definition_body/) { - $decl_type = $1; - $declaration_name = $2; - $members = $3; - } elsif ($x =~ /typedef\s+($type)\s*$definition_body\s*(\w+)\s*;/) { - $decl_type = $1; - $declaration_name = $3; - $members = $2; - } - - if ($members) { - if ($identifier ne $declaration_name) { - emit_warning("${file}:$.", "expecting prototype for $decl_type $identifier. Prototype was for $decl_type $declaration_name instead\n"); - return; - } - - # ignore members marked private: - $members =~ s/\/\*\s*private:.*?\/\*\s*public:.*?\*\///gosi; - $members =~ s/\/\*\s*private:.*//gosi; - # strip comments: - $members =~ s/\/\*.*?\*\///gos; - # strip attributes - $members =~ s/\s*$attribute/ /gi; - $members =~ s/\s*__aligned\s*\([^;]*\)/ /gos; - $members =~ s/\s*__counted_by\s*\([^;]*\)/ /gos; - $members =~ s/\s*__counted_by_(le|be)\s*\([^;]*\)/ /gos; - $members =~ s/\s*__packed\s*/ /gos; - $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; - $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; - $members =~ s/\s*____cacheline_aligned/ /gos; - # unwrap struct_group(): - # - first eat non-declaration parameters and rewrite for final match - # - then remove macro, outer parens, and trailing semicolon - $members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos; - $members =~ s/\bstruct_group_attr\s*\(([^,]*,){2}/STRUCT_GROUP(/gos; - $members =~ s/\bstruct_group_tagged\s*\(([^,]*),([^,]*),/struct $1 $2; STRUCT_GROUP(/gos; - $members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos; - $members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos; - - my $args = qr{([^,)]+)}; - # replace DECLARE_BITMAP - $members =~ s/__ETHTOOL_DECLARE_LINK_MODE_MASK\s*\(([^\)]+)\)/DECLARE_BITMAP($1, __ETHTOOL_LINK_MODE_MASK_NBITS)/gos; - $members =~ s/DECLARE_PHY_INTERFACE_MASK\s*\(([^\)]+)\)/DECLARE_BITMAP($1, PHY_INTERFACE_MODE_MAX)/gos; - $members =~ s/DECLARE_BITMAP\s*\($args,\s*$args\)/unsigned long $1\[BITS_TO_LONGS($2)\]/gos; - # replace DECLARE_HASHTABLE - $members =~ s/DECLARE_HASHTABLE\s*\($args,\s*$args\)/unsigned long $1\[1 << (($2) - 1)\]/gos; - # replace DECLARE_KFIFO - $members =~ s/DECLARE_KFIFO\s*\($args,\s*$args,\s*$args\)/$2 \*$1/gos; - # replace DECLARE_KFIFO_PTR - $members =~ s/DECLARE_KFIFO_PTR\s*\($args,\s*$args\)/$2 \*$1/gos; - # replace DECLARE_FLEX_ARRAY - $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\($args,\s*$args\)/$1 $2\[\]/gos; - #replace DEFINE_DMA_UNMAP_ADDR - $members =~ s/DEFINE_DMA_UNMAP_ADDR\s*\($args\)/dma_addr_t $1/gos; - #replace DEFINE_DMA_UNMAP_LEN - $members =~ s/DEFINE_DMA_UNMAP_LEN\s*\($args\)/__u32 $1/gos; - my $declaration = $members; - - # Split nested struct/union elements as newer ones - while ($members =~ m/$struct_members/) { - my $newmember; - my $maintype = $1; - my $ids = $4; - my $content = $3; - foreach my $id(split /,/, $ids) { - $newmember .= "$maintype $id; "; - - $id =~ s/[:\[].*//; - $id =~ s/^\s*\**(\S+)\s*/$1/; - foreach my $arg (split /;/, $content) { - next if ($arg =~ m/^\s*$/); - if ($arg =~ m/^([^\(]+\(\*?\s*)([\w\.]*)(\s*\).*)/) { - # pointer-to-function - my $type = $1; - my $name = $2; - my $extra = $3; - next if (!$name); - if ($id =~ m/^\s*$/) { - # anonymous struct/union - $newmember .= "$type$name$extra; "; - } else { - $newmember .= "$type$id.$name$extra; "; - } - } else { - my $type; - my $names; - $arg =~ s/^\s+//; - $arg =~ s/\s+$//; - # Handle bitmaps - $arg =~ s/:\s*\d+\s*//g; - # Handle arrays - $arg =~ s/\[.*\]//g; - # The type may have multiple words, - # and multiple IDs can be defined, like: - # const struct foo, *bar, foobar - # So, we remove spaces when parsing the - # names, in order to match just names - # and commas for the names - $arg =~ s/\s*,\s*/,/g; - if ($arg =~ m/(.*)\s+([\S+,]+)/) { - $type = $1; - $names = $2; - } else { - $newmember .= "$arg; "; - next; - } - foreach my $name (split /,/, $names) { - $name =~ s/^\s*\**(\S+)\s*/$1/; - next if (($name =~ m/^\s*$/)); - if ($id =~ m/^\s*$/) { - # anonymous struct/union - $newmember .= "$type $name; "; - } else { - $newmember .= "$type $id.$name; "; - } - } - } - } - } - $members =~ s/$struct_members/$newmember/; - } - - # Ignore other nested elements, like enums - $members =~ s/(\{[^\{\}]*\})//g; - - create_parameterlist($members, ';', $file, $declaration_name); - check_sections($file, $declaration_name, $decl_type, $sectcheck, $struct_actual); - - # Adjust declaration for better display - $declaration =~ s/([\{;])/$1\n/g; - $declaration =~ s/\}\s+;/};/g; - # Better handle inlined enums - do {} while ($declaration =~ s/(enum\s+\{[^\}]+),([^\n])/$1,\n$2/); - - my @def_args = split /\n/, $declaration; - my $level = 1; - $declaration = ""; - foreach my $clause (@def_args) { - $clause =~ s/^\s+//; - $clause =~ s/\s+$//; - $clause =~ s/\s+/ /; - next if (!$clause); - $level-- if ($clause =~ m/(\})/ && $level > 1); - if (!($clause =~ m/^\s*#/)) { - $declaration .= "\t" x $level; - } - $declaration .= "\t" . $clause . "\n"; - $level++ if ($clause =~ m/(\{)/ && !($clause =~m/\}/)); - } - output_declaration($declaration_name, - 'struct', - {'struct' => $declaration_name, - 'module' => $modulename, - 'definition' => $declaration, - 'parameterlist' => \@parameterlist, - 'parameterdescs' => \%parameterdescs, - 'parametertypes' => \%parametertypes, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose, - 'type' => $decl_type - }); - } else { - print STDERR "${file}:$.: error: Cannot parse struct or union!\n"; - ++$errors; - } -} - - -sub show_warnings($$) { - my $functype = shift; - my $name = shift; - - return 0 if (defined($nosymbol_table{$name})); - - return 1 if ($output_selection == OUTPUT_ALL); - - if ($output_selection == OUTPUT_EXPORTED) { - if (defined($function_table{$name})) { - return 1; - } else { - return 0; - } - } - if ($output_selection == OUTPUT_INTERNAL) { - if (!($functype eq "function" && defined($function_table{$name}))) { - return 1; - } else { - return 0; - } - } - if ($output_selection == OUTPUT_INCLUDE) { - if (defined($function_table{$name})) { - return 1; - } else { - return 0; - } - } - die("Please add the new output type at show_warnings()"); -} - -sub dump_enum($$) { - my $x = shift; - my $file = shift; - my $members; - - # ignore members marked private: - $x =~ s/\/\*\s*private:.*?\/\*\s*public:.*?\*\///gosi; - $x =~ s/\/\*\s*private:.*}/}/gosi; - - $x =~ s@/\*.*?\*/@@gos; # strip comments. - # strip #define macros inside enums - $x =~ s@#\s*((define|ifdef|if)\s+|endif)[^;]*;@@gos; - - if ($x =~ /typedef\s+enum\s*\{(.*)\}\s*(\w*)\s*;/) { - $declaration_name = $2; - $members = $1; - } elsif ($x =~ /enum\s+(\w*)\s*\{(.*)\}/) { - $declaration_name = $1; - $members = $2; - } - - if ($members) { - if ($identifier ne $declaration_name) { - if ($identifier eq "") { - emit_warning("${file}:$.", "wrong kernel-doc identifier on line:\n"); - } else { - emit_warning("${file}:$.", "expecting prototype for enum $identifier. Prototype was for enum $declaration_name instead\n"); - } - return; - } - $declaration_name = "(anonymous)" if ($declaration_name eq ""); - - my %_members; - - $members =~ s/\s+$//; - $members =~ s/\([^;]*?[\)]//g; - - foreach my $arg (split ',', $members) { - $arg =~ s/^\s*(\w+).*/$1/; - push @parameterlist, $arg; - if (!$parameterdescs{$arg}) { - $parameterdescs{$arg} = $undescribed; - if (show_warnings("enum", $declaration_name)) { - emit_warning("${file}:$.", "Enum value '$arg' not described in enum '$declaration_name'\n"); - } - } - $_members{$arg} = 1; - } - - while (my ($k, $v) = each %parameterdescs) { - if (!exists($_members{$k})) { - if (show_warnings("enum", $declaration_name)) { - emit_warning("${file}:$.", "Excess enum value '$k' description in '$declaration_name'\n"); - } - } - } - - output_declaration($declaration_name, - 'enum', - {'enum' => $declaration_name, - 'module' => $modulename, - 'parameterlist' => \@parameterlist, - 'parameterdescs' => \%parameterdescs, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose - }); - } else { - print STDERR "${file}:$.: error: Cannot parse enum!\n"; - ++$errors; - } -} - -my $typedef_type = qr { ((?:\s+[\w\*]+\b){1,8})\s* }x; -my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x; -my $typedef_args = qr { \s*\((.*)\); }x; - -my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x; -my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x; - -sub dump_typedef($$) { - my $x = shift; - my $file = shift; - - $x =~ s@/\*.*?\*/@@gos; # strip comments. - - # Parse function typedef prototypes - if ($x =~ $typedef1 || $x =~ $typedef2) { - $return_type = $1; - $declaration_name = $2; - my $args = $3; - $return_type =~ s/^\s+//; - - if ($identifier ne $declaration_name) { - emit_warning("${file}:$.", "expecting prototype for typedef $identifier. Prototype was for typedef $declaration_name instead\n"); - return; - } - - create_parameterlist($args, ',', $file, $declaration_name); - - output_declaration($declaration_name, - 'function', - {'function' => $declaration_name, - 'typedef' => 1, - 'module' => $modulename, - 'functiontype' => $return_type, - 'parameterlist' => \@parameterlist, - 'parameterdescs' => \%parameterdescs, - 'parametertypes' => \%parametertypes, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose - }); - return; - } - - while (($x =~ /\(*.\)\s*;$/) || ($x =~ /\[*.\]\s*;$/)) { - $x =~ s/\(*.\)\s*;$/;/; - $x =~ s/\[*.\]\s*;$/;/; - } - - if ($x =~ /typedef.*\s+(\w+)\s*;/) { - $declaration_name = $1; - - if ($identifier ne $declaration_name) { - emit_warning("${file}:$.", "expecting prototype for typedef $identifier. Prototype was for typedef $declaration_name instead\n"); - return; - } - - output_declaration($declaration_name, - 'typedef', - {'typedef' => $declaration_name, - 'module' => $modulename, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose - }); - } else { - print STDERR "${file}:$.: error: Cannot parse typedef!\n"; - ++$errors; - } -} - -sub save_struct_actual($) { - my $actual = shift; - - # strip all spaces from the actual param so that it looks like one string item - $actual =~ s/\s*//g; - $struct_actual = $struct_actual . $actual . " "; -} - -sub create_parameterlist($$$$) { - my $args = shift; - my $splitter = shift; - my $file = shift; - my $declaration_name = shift; - my $type; - my $param; - - # temporarily replace commas inside function pointer definition - my $arg_expr = qr{\([^\),]+}; - while ($args =~ /$arg_expr,/) { - $args =~ s/($arg_expr),/$1#/g; - } - - foreach my $arg (split($splitter, $args)) { - # strip comments - $arg =~ s/\/\*.*\*\///; - # ignore argument attributes - $arg =~ s/\sPOS0?\s/ /; - # strip leading/trailing spaces - $arg =~ s/^\s*//; - $arg =~ s/\s*$//; - $arg =~ s/\s+/ /; - - if ($arg =~ /^#/) { - # Treat preprocessor directive as a typeless variable just to fill - # corresponding data structures "correctly". Catch it later in - # output_* subs. - push_parameter($arg, "", "", $file); - } elsif ($arg =~ m/\(.+\)\s*\(/) { - # pointer-to-function - $arg =~ tr/#/,/; - $arg =~ m/[^\(]+\(\*?\s*([\w\[\]\.]*)\s*\)/; - $param = $1; - $type = $arg; - $type =~ s/([^\(]+\(\*?)\s*$param/$1/; - save_struct_actual($param); - push_parameter($param, $type, $arg, $file, $declaration_name); - } elsif ($arg =~ m/\(.+\)\s*\[/) { - # array-of-pointers - $arg =~ tr/#/,/; - $arg =~ m/[^\(]+\(\s*\*\s*([\w\[\]\.]*?)\s*(\s*\[\s*[\w]+\s*\]\s*)*\)/; - $param = $1; - $type = $arg; - $type =~ s/([^\(]+\(\*?)\s*$param/$1/; - save_struct_actual($param); - push_parameter($param, $type, $arg, $file, $declaration_name); - } elsif ($arg) { - $arg =~ s/\s*:\s*/:/g; - $arg =~ s/\s*\[/\[/g; - - my @args = split('\s*,\s*', $arg); - if ($args[0] =~ m/\*/) { - $args[0] =~ s/(\*+)\s*/ $1/; - } - - my @first_arg; - if ($args[0] =~ /^(.*\s+)(.*?\[.*\].*)$/) { - shift @args; - push(@first_arg, split('\s+', $1)); - push(@first_arg, $2); - } else { - @first_arg = split('\s+', shift @args); - } - - unshift(@args, pop @first_arg); - $type = join " ", @first_arg; - - foreach $param (@args) { - if ($param =~ m/^(\*+)\s*(.*)/) { - save_struct_actual($2); - - push_parameter($2, "$type $1", $arg, $file, $declaration_name); - } elsif ($param =~ m/(.*?):(\w+)/) { - if ($type ne "") { # skip unnamed bit-fields - save_struct_actual($1); - push_parameter($1, "$type:$2", $arg, $file, $declaration_name) - } - } else { - save_struct_actual($param); - push_parameter($param, $type, $arg, $file, $declaration_name); - } - } - } - } -} - -sub push_parameter($$$$$) { - my $param = shift; - my $type = shift; - my $org_arg = shift; - my $file = shift; - my $declaration_name = shift; - - if (($anon_struct_union == 1) && ($type eq "") && - ($param eq "}")) { - return; # ignore the ending }; from anon. struct/union - } - - $anon_struct_union = 0; - $param =~ s/[\[\)].*//; - - if ($type eq "" && $param =~ /\.\.\.$/) - { - if (!$param =~ /\w\.\.\.$/) { - # handles unnamed variable parameters - $param = "..."; - } elsif ($param =~ /\w\.\.\.$/) { - # for named variable parameters of the form `x...`, remove the dots - $param =~ s/\.\.\.$//; - } - if (!defined $parameterdescs{$param} || $parameterdescs{$param} eq "") { - $parameterdescs{$param} = "variable arguments"; - } - } - elsif ($type eq "" && ($param eq "" or $param eq "void")) - { - $param="void"; - $parameterdescs{void} = "no arguments"; - } - elsif ($type eq "" && ($param eq "struct" or $param eq "union")) - # handle unnamed (anonymous) union or struct: - { - $type = $param; - $param = "{unnamed_" . $param . "}"; - $parameterdescs{$param} = "anonymous\n"; - $anon_struct_union = 1; - } - elsif ($param =~ "__cacheline_group" ) - # handle cache group enforcing variables: they do not need be described in header files - { - return; # ignore __cacheline_group_begin and __cacheline_group_end - } - - # warn if parameter has no description - # (but ignore ones starting with # as these are not parameters - # but inline preprocessor statements); - # Note: It will also ignore void params and unnamed structs/unions - if (!defined $parameterdescs{$param} && $param !~ /^#/) { - $parameterdescs{$param} = $undescribed; - - if (show_warnings($type, $declaration_name) && $param !~ /\./) { - emit_warning("${file}:$.", "Function parameter or struct member '$param' not described in '$declaration_name'\n"); - } - } - - # strip spaces from $param so that it is one continuous string - # on @parameterlist; - # this fixes a problem where check_sections() cannot find - # a parameter like "addr[6 + 2]" because it actually appears - # as "addr[6", "+", "2]" on the parameter list; - # but it's better to maintain the param string unchanged for output, - # so just weaken the string compare in check_sections() to ignore - # "[blah" in a parameter string; - ###$param =~ s/\s*//g; - push @parameterlist, $param; - $org_arg =~ s/\s\s+/ /g; - $parametertypes{$param} = $org_arg; -} - -sub check_sections($$$$$) { - my ($file, $decl_name, $decl_type, $sectcheck, $prmscheck) = @_; - my @sects = split ' ', $sectcheck; - my @prms = split ' ', $prmscheck; - my $err; - my ($px, $sx); - my $prm_clean; # strip trailing "[array size]" and/or beginning "*" - - foreach $sx (0 .. $#sects) { - $err = 1; - foreach $px (0 .. $#prms) { - $prm_clean = $prms[$px]; - $prm_clean =~ s/\[.*\]//; - $prm_clean =~ s/$attribute//i; - # ignore array size in a parameter string; - # however, the original param string may contain - # spaces, e.g.: addr[6 + 2] - # and this appears in @prms as "addr[6" since the - # parameter list is split at spaces; - # hence just ignore "[..." for the sections check; - $prm_clean =~ s/\[.*//; - - ##$prm_clean =~ s/^\**//; - if ($prm_clean eq $sects[$sx]) { - $err = 0; - last; - } - } - if ($err) { - if ($decl_type eq "function") { - emit_warning("${file}:$.", - "Excess function parameter " . - "'$sects[$sx]' " . - "description in '$decl_name'\n"); - } elsif (($decl_type eq "struct") or - ($decl_type eq "union")) { - emit_warning("${file}:$.", - "Excess $decl_type member " . - "'$sects[$sx]' " . - "description in '$decl_name'\n"); - } - } - } -} - -## -# Checks the section describing the return value of a function. -sub check_return_section { - my $file = shift; - my $declaration_name = shift; - my $return_type = shift; - - # Ignore an empty return type (It's a macro) - # Ignore functions with a "void" return type. (But don't ignore "void *") - if (($return_type eq "") || ($return_type =~ /void\s*\w*\s*$/)) { - return; - } - - if (!defined($sections{$section_return}) || - $sections{$section_return} eq "") - { - emit_warning("${file}:$.", - "No description found for return value of " . - "'$declaration_name'\n"); - } -} - -## -# takes a function prototype and the name of the current file being -# processed and spits out all the details stored in the global -# arrays/hashes. -sub dump_function($$) { - my $prototype = shift; - my $file = shift; - my $func_macro = 0; - - print_lineno($new_start_line); - - $prototype =~ s/^static +//; - $prototype =~ s/^extern +//; - $prototype =~ s/^asmlinkage +//; - $prototype =~ s/^inline +//; - $prototype =~ s/^__inline__ +//; - $prototype =~ s/^__inline +//; - $prototype =~ s/^__always_inline +//; - $prototype =~ s/^noinline +//; - $prototype =~ s/^__FORTIFY_INLINE +//; - $prototype =~ s/__init +//; - $prototype =~ s/__init_or_module +//; - $prototype =~ s/__deprecated +//; - $prototype =~ s/__flatten +//; - $prototype =~ s/__meminit +//; - $prototype =~ s/__must_check +//; - $prototype =~ s/__weak +//; - $prototype =~ s/__sched +//; - $prototype =~ s/_noprof//; - $prototype =~ s/__printf\s*\(\s*\d*\s*,\s*\d*\s*\) +//; - $prototype =~ s/__(?:re)?alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) +//; - $prototype =~ s/__diagnose_as\s*\(\s*\S+\s*(?:,\s*\d+\s*)*\) +//; - $prototype =~ s/DECL_BUCKET_PARAMS\s*\(\s*(\S+)\s*,\s*(\S+)\s*\)/$1, $2/; - my $define = $prototype =~ s/^#\s*define\s+//; #ak added - $prototype =~ s/__attribute_const__ +//; - $prototype =~ s/__attribute__\s*\(\( - (?: - [\w\s]++ # attribute name - (?:\([^)]*+\))? # attribute arguments - \s*+,? # optional comma at the end - )+ - \)\)\s+//x; - - # Yes, this truly is vile. We are looking for: - # 1. Return type (may be nothing if we're looking at a macro) - # 2. Function name - # 3. Function parameters. - # - # All the while we have to watch out for function pointer parameters - # (which IIRC is what the two sections are for), C types (these - # regexps don't even start to express all the possibilities), and - # so on. - # - # If you mess with these regexps, it's a good idea to check that - # the following functions' documentation still comes out right: - # - parport_register_device (function pointer parameters) - # - atomic_set (macro) - # - pci_match_device, __copy_to_user (long return type) - my $name = qr{[a-zA-Z0-9_~:]+}; - my $prototype_end1 = qr{[^\(]*}; - my $prototype_end2 = qr{[^\{]*}; - my $prototype_end = qr{\(($prototype_end1|$prototype_end2)\)}; - my $type1 = qr{[\w\s]+}; - my $type2 = qr{$type1\*+}; - - if ($define && $prototype =~ m/^()($name)\s+/) { - # This is an object-like macro, it has no return type and no parameter - # list. - # Function-like macros are not allowed to have spaces between - # declaration_name and opening parenthesis (notice the \s+). - $return_type = $1; - $declaration_name = $2; - $func_macro = 1; - } elsif ($prototype =~ m/^()($name)\s*$prototype_end/ || - $prototype =~ m/^($type1)\s+($name)\s*$prototype_end/ || - $prototype =~ m/^($type2+)\s*($name)\s*$prototype_end/) { - $return_type = $1; - $declaration_name = $2; - my $args = $3; - - create_parameterlist($args, ',', $file, $declaration_name); - } else { - emit_warning("${file}:$.", "cannot understand function prototype: '$prototype'\n"); - return; - } - - if ($identifier ne $declaration_name) { - emit_warning("${file}:$.", "expecting prototype for $identifier(). Prototype was for $declaration_name() instead\n"); - return; - } - - my $prms = join " ", @parameterlist; - check_sections($file, $declaration_name, "function", $sectcheck, $prms); - - # This check emits a lot of warnings at the moment, because many - # functions don't have a 'Return' doc section. So until the number - # of warnings goes sufficiently down, the check is only performed in - # -Wreturn mode. - # TODO: always perform the check. - if ($Wreturn && !$func_macro) { - check_return_section($file, $declaration_name, $return_type); - } - - # The function parser can be called with a typedef parameter. - # Handle it. - if ($return_type =~ /typedef/) { - output_declaration($declaration_name, - 'function', - {'function' => $declaration_name, - 'typedef' => 1, - 'module' => $modulename, - 'functiontype' => $return_type, - 'parameterlist' => \@parameterlist, - 'parameterdescs' => \%parameterdescs, - 'parametertypes' => \%parametertypes, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose, - 'func_macro' => $func_macro - }); - } else { - output_declaration($declaration_name, - 'function', - {'function' => $declaration_name, - 'module' => $modulename, - 'functiontype' => $return_type, - 'parameterlist' => \@parameterlist, - 'parameterdescs' => \%parameterdescs, - 'parametertypes' => \%parametertypes, - 'sectionlist' => \@sectionlist, - 'sections' => \%sections, - 'purpose' => $declaration_purpose, - 'func_macro' => $func_macro - }); - } -} - -sub reset_state { - $function = ""; - %parameterdescs = (); - %parametertypes = (); - @parameterlist = (); - %sections = (); - @sectionlist = (); - $sectcheck = ""; - $struct_actual = ""; - $prototype = ""; - - $state = STATE_NORMAL; - $inline_doc_state = STATE_INLINE_NA; -} - -sub tracepoint_munge($) { - my $file = shift; - my $tracepointname = 0; - my $tracepointargs = 0; - - if ($prototype =~ m/TRACE_EVENT\((.*?),/) { - $tracepointname = $1; - } - if ($prototype =~ m/DEFINE_SINGLE_EVENT\((.*?),/) { - $tracepointname = $1; - } - if ($prototype =~ m/DEFINE_EVENT\((.*?),(.*?),/) { - $tracepointname = $2; - } - $tracepointname =~ s/^\s+//; #strip leading whitespace - if ($prototype =~ m/TP_PROTO\((.*?)\)/) { - $tracepointargs = $1; - } - if (($tracepointname eq 0) || ($tracepointargs eq 0)) { - emit_warning("${file}:$.", "Unrecognized tracepoint format: \n". - "$prototype\n"); - } else { - $prototype = "static inline void trace_$tracepointname($tracepointargs)"; - $identifier = "trace_$identifier"; - } -} - -sub syscall_munge() { - my $void = 0; - - $prototype =~ s@[\r\n]+@ @gos; # strip newlines/CR's -## if ($prototype =~ m/SYSCALL_DEFINE0\s*\(\s*(a-zA-Z0-9_)*\s*\)/) { - if ($prototype =~ m/SYSCALL_DEFINE0/) { - $void = 1; -## $prototype = "long sys_$1(void)"; - } - - $prototype =~ s/SYSCALL_DEFINE.*\(/long sys_/; # fix return type & func name - if ($prototype =~ m/long (sys_.*?),/) { - $prototype =~ s/,/\(/; - } elsif ($void) { - $prototype =~ s/\)/\(void\)/; - } - - # now delete all of the odd-number commas in $prototype - # so that arg types & arg names don't have a comma between them - my $count = 0; - my $len = length($prototype); - if ($void) { - $len = 0; # skip the for-loop - } - for (my $ix = 0; $ix < $len; $ix++) { - if (substr($prototype, $ix, 1) eq ',') { - $count++; - if ($count % 2 == 1) { - substr($prototype, $ix, 1) = ' '; - } - } - } -} - -sub process_proto_function($$) { - my $x = shift; - my $file = shift; - - $x =~ s@\/\/.*$@@gos; # strip C99-style comments to end of line - - if ($x =~ /^#/ && $x !~ /^#\s*define/) { - # do nothing - } elsif ($x =~ /([^\{]*)/) { - $prototype .= $1; - } - - if (($x =~ /\{/) || ($x =~ /\#\s*define/) || ($x =~ /;/)) { - $prototype =~ s@/\*.*?\*/@@gos; # strip comments. - $prototype =~ s@[\r\n]+@ @gos; # strip newlines/cr's. - $prototype =~ s@^\s+@@gos; # strip leading spaces - - # Handle prototypes for function pointers like: - # int (*pcs_config)(struct foo) - $prototype =~ s@^(\S+\s+)\(\s*\*(\S+)\)@$1$2@gos; - - if ($prototype =~ /SYSCALL_DEFINE/) { - syscall_munge(); - } - if ($prototype =~ /TRACE_EVENT/ || $prototype =~ /DEFINE_EVENT/ || - $prototype =~ /DEFINE_SINGLE_EVENT/) - { - tracepoint_munge($file); - } - dump_function($prototype, $file); - reset_state(); - } -} - -sub process_proto_type($$) { - my $x = shift; - my $file = shift; - - $x =~ s@[\r\n]+@ @gos; # strip newlines/cr's. - $x =~ s@^\s+@@gos; # strip leading spaces - $x =~ s@\s+$@@gos; # strip trailing spaces - $x =~ s@\/\/.*$@@gos; # strip C99-style comments to end of line - - if ($x =~ /^#/) { - # To distinguish preprocessor directive from regular declaration later. - $x .= ";"; - } - - while (1) { - if ( $x =~ /([^\{\};]*)([\{\};])(.*)/ ) { - if( length $prototype ) { - $prototype .= " " - } - $prototype .= $1 . $2; - ($2 eq '{') && $brcount++; - ($2 eq '}') && $brcount--; - if (($2 eq ';') && ($brcount == 0)) { - dump_declaration($prototype, $file); - reset_state(); - last; - } - $x = $3; - } else { - $prototype .= $x; - last; - } - } -} - - -sub map_filename($) { - my $file; - my ($orig_file) = @_; - - if (defined($ENV{'SRCTREE'})) { - $file = "$ENV{'SRCTREE'}" . "/" . $orig_file; - } else { - $file = $orig_file; - } - - if (defined($source_map{$file})) { - $file = $source_map{$file}; - } - - return $file; -} - -sub process_export_file($) { - my ($orig_file) = @_; - my $file = map_filename($orig_file); - - if (!open(IN,"<$file")) { - print STDERR "Error: Cannot open file $file\n"; - ++$errors; - return; - } - - while (<IN>) { - if (/$export_symbol/) { - next if (defined($nosymbol_table{$2})); - $function_table{$2} = 1; - } - if (/$export_symbol_ns/) { - next if (defined($nosymbol_table{$2})); - $function_table{$2} = 1; - } - } - - close(IN); -} - -# -# Parsers for the various processing states. -# -# STATE_NORMAL: looking for the /** to begin everything. -# -sub process_normal() { - if (/$doc_start/o) { - $state = STATE_NAME; # next line is always the function name - $in_doc_sect = 0; - $declaration_start_line = $. + 1; - } -} - -# -# STATE_NAME: Looking for the "name - description" line -# -sub process_name($$) { - my $file = shift; - my $descr; - - if (/$doc_block/o) { - $state = STATE_DOCBLOCK; - $contents = ""; - $new_start_line = $.; - - if ( $1 eq "" ) { - $section = $section_intro; - } else { - $section = $1; - } - } elsif (/$doc_decl/o) { - $identifier = $1; - my $is_kernel_comment = 0; - my $decl_start = qr{$doc_com}; - # test for pointer declaration type, foo * bar() - desc - my $fn_type = qr{\w+\s*\*\s*}; - my $parenthesis = qr{\(\w*\)}; - my $decl_end = qr{[-:].*}; - if (/^$decl_start([\w\s]+?)$parenthesis?\s*$decl_end?$/) { - $identifier = $1; - } - if ($identifier =~ m/^(struct|union|enum|typedef)\b\s*(\S*)/) { - $decl_type = $1; - $identifier = $2; - $is_kernel_comment = 1; - } - # Look for foo() or static void foo() - description; or misspelt - # identifier - elsif (/^$decl_start$fn_type?(\w+)\s*$parenthesis?\s*$decl_end?$/ || - /^$decl_start$fn_type?(\w+.*)$parenthesis?\s*$decl_end$/) { - $identifier = $1; - $decl_type = 'function'; - $identifier =~ s/^define\s+//; - $is_kernel_comment = 1; - } - $identifier =~ s/\s+$//; - - $state = STATE_BODY; - # if there's no @param blocks need to set up default section - # here - $contents = ""; - $section = $section_default; - $new_start_line = $. + 1; - if (/[-:](.*)/) { - # strip leading/trailing/multiple spaces - $descr= $1; - $descr =~ s/^\s*//; - $descr =~ s/\s*$//; - $descr =~ s/\s+/ /g; - $declaration_purpose = $descr; - $state = STATE_BODY_MAYBE; - } else { - $declaration_purpose = ""; - } - - if (!$is_kernel_comment) { - emit_warning("${file}:$.", "This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst\n$_"); - $state = STATE_NORMAL; - } - - if (($declaration_purpose eq "") && $Wshort_desc) { - emit_warning("${file}:$.", "missing initial short description on line:\n$_"); - } - - if ($identifier eq "" && $decl_type ne "enum") { - emit_warning("${file}:$.", "wrong kernel-doc identifier on line:\n$_"); - $state = STATE_NORMAL; - } - - if ($verbose) { - print STDERR "${file}:$.: info: Scanning doc for $decl_type $identifier\n"; - } - } else { - emit_warning("${file}:$.", "Cannot understand $_ on line $. - I thought it was a doc line\n"); - $state = STATE_NORMAL; - } -} - - -# -# STATE_BODY and STATE_BODY_MAYBE: the bulk of a kerneldoc comment. -# -sub process_body($$) { - my $file = shift; - - if ($state == STATE_BODY_WITH_BLANK_LINE && /^\s*\*\s?\S/) { - dump_section($file, $section, $contents); - $section = $section_default; - $new_start_line = $.; - $contents = ""; - } - - if (/$doc_sect/i) { # case insensitive for supported section names - $in_doc_sect = 1; - $newsection = $1; - $newcontents = $2; - - # map the supported section names to the canonical names - if ($newsection =~ m/^description$/i) { - $newsection = $section_default; - } elsif ($newsection =~ m/^context$/i) { - $newsection = $section_context; - } elsif ($newsection =~ m/^returns?$/i) { - $newsection = $section_return; - } elsif ($newsection =~ m/^\@return$/) { - # special: @return is a section, not a param description - $newsection = $section_return; - } - - if (($contents ne "") && ($contents ne "\n")) { - if (!$in_doc_sect && $Wcontents_before_sections) { - emit_warning("${file}:$.", "contents before sections\n"); - } - dump_section($file, $section, $contents); - $section = $section_default; - } - - $in_doc_sect = 1; - $state = STATE_BODY; - $contents = $newcontents; - $new_start_line = $.; - while (substr($contents, 0, 1) eq " ") { - $contents = substr($contents, 1); - } - if ($contents ne "") { - $contents .= "\n"; - } - $section = $newsection; - $leading_space = undef; - } elsif (/$doc_end/) { - if (($contents ne "") && ($contents ne "\n")) { - dump_section($file, $section, $contents); - $section = $section_default; - $contents = ""; - } - # look for doc_com + <text> + doc_end: - if ($_ =~ m'\s*\*\s*[a-zA-Z_0-9:\.]+\*/') { - emit_warning("${file}:$.", "suspicious ending line: $_"); - } - - $prototype = ""; - $state = STATE_PROTO; - $brcount = 0; - $new_start_line = $. + 1; - } elsif (/$doc_content/) { - if ($1 eq "") { - if ($section eq $section_context) { - dump_section($file, $section, $contents); - $section = $section_default; - $contents = ""; - $new_start_line = $.; - $state = STATE_BODY; - } else { - if ($section ne $section_default) { - $state = STATE_BODY_WITH_BLANK_LINE; - } else { - $state = STATE_BODY; - } - $contents .= "\n"; - } - } elsif ($state == STATE_BODY_MAYBE) { - # Continued declaration purpose - chomp($declaration_purpose); - $declaration_purpose .= " " . $1; - $declaration_purpose =~ s/\s+/ /g; - } else { - my $cont = $1; - if ($section =~ m/^@/ || $section eq $section_context) { - if (!defined $leading_space) { - if ($cont =~ m/^(\s+)/) { - $leading_space = $1; - } else { - $leading_space = ""; - } - } - $cont =~ s/^$leading_space//; - } - $contents .= $cont . "\n"; - } - } else { - # i dont know - bad line? ignore. - emit_warning("${file}:$.", "bad line: $_"); - } -} - - -# -# STATE_PROTO: reading a function/whatever prototype. -# -sub process_proto($$) { - my $file = shift; - - if (/$doc_inline_oneline/) { - $section = $1; - $contents = $2; - if ($contents ne "") { - $contents .= "\n"; - dump_section($file, $section, $contents); - $section = $section_default; - $contents = ""; - } - } elsif (/$doc_inline_start/) { - $state = STATE_INLINE; - $inline_doc_state = STATE_INLINE_NAME; - } elsif ($decl_type eq 'function') { - process_proto_function($_, $file); - } else { - process_proto_type($_, $file); - } -} - -# -# STATE_DOCBLOCK: within a DOC: block. -# -sub process_docblock($$) { - my $file = shift; - - if (/$doc_end/) { - dump_doc_section($file, $section, $contents); - $section = $section_default; - $contents = ""; - $function = ""; - %parameterdescs = (); - %parametertypes = (); - @parameterlist = (); - %sections = (); - @sectionlist = (); - $prototype = ""; - $state = STATE_NORMAL; - } elsif (/$doc_content/) { - if ( $1 eq "" ) { - $contents .= $blankline; - } else { - $contents .= $1 . "\n"; - } - } -} - -# -# STATE_INLINE: docbook comments within a prototype. -# -sub process_inline($$) { - my $file = shift; - - # First line (state 1) needs to be a @parameter - if ($inline_doc_state == STATE_INLINE_NAME && /$doc_inline_sect/o) { - $section = $1; - $contents = $2; - $new_start_line = $.; - if ($contents ne "") { - while (substr($contents, 0, 1) eq " ") { - $contents = substr($contents, 1); - } - $contents .= "\n"; - } - $inline_doc_state = STATE_INLINE_TEXT; - # Documentation block end */ - } elsif (/$doc_inline_end/) { - if (($contents ne "") && ($contents ne "\n")) { - dump_section($file, $section, $contents); - $section = $section_default; - $contents = ""; - } - $state = STATE_PROTO; - $inline_doc_state = STATE_INLINE_NA; - # Regular text - } elsif (/$doc_content/) { - if ($inline_doc_state == STATE_INLINE_TEXT) { - $contents .= $1 . "\n"; - # nuke leading blank lines - if ($contents =~ /^\s*$/) { - $contents = ""; - } - } elsif ($inline_doc_state == STATE_INLINE_NAME) { - $inline_doc_state = STATE_INLINE_ERROR; - emit_warning("${file}:$.", "Incorrect use of kernel-doc format: $_"); - } - } -} - - -sub process_file($) { - my $file; - my ($orig_file) = @_; - - $file = map_filename($orig_file); - - if (!open(IN_FILE,"<$file")) { - print STDERR "Error: Cannot open file $file\n"; - ++$errors; - return; - } - - $. = 1; - - $section_counter = 0; - while (<IN_FILE>) { - while (!/^ \*/ && s/\\\s*$//) { - $_ .= <IN_FILE>; - } - # Replace tabs by spaces - while ($_ =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}; - # Hand this line to the appropriate state handler - if ($state == STATE_NORMAL) { - process_normal(); - } elsif ($state == STATE_NAME) { - process_name($file, $_); - } elsif ($state == STATE_BODY || $state == STATE_BODY_MAYBE || - $state == STATE_BODY_WITH_BLANK_LINE) { - process_body($file, $_); - } elsif ($state == STATE_INLINE) { # scanning for inline parameters - process_inline($file, $_); - } elsif ($state == STATE_PROTO) { - process_proto($file, $_); - } elsif ($state == STATE_DOCBLOCK) { - process_docblock($file, $_); - } - } - - # Make sure we got something interesting. - if (!$section_counter && $output_mode ne "none") { - if ($output_selection == OUTPUT_INCLUDE) { - emit_warning("${file}:1", "'$_' not found\n") - for keys %function_table; - } else { - emit_warning("${file}:1", "no structured comments found\n"); - } - } - close IN_FILE; -} - - -if ($output_mode eq "rst") { - get_sphinx_version() if (!$sphinx_major); -} - -$kernelversion = get_kernel_version(); - -# generate a sequence of code that will splice in highlighting information -# using the s// operator. -for (my $k = 0; $k < @highlights; $k++) { - my $pattern = $highlights[$k][0]; - my $result = $highlights[$k][1]; -# print STDERR "scanning pattern:$pattern, highlight:($result)\n"; - $dohighlight .= "\$contents =~ s:$pattern:$result:gs;\n"; -} - -# Read the file that maps relative names to absolute names for -# separate source and object directories and for shadow trees. -if (open(SOURCE_MAP, "<.tmp_filelist.txt")) { - my ($relname, $absname); - while(<SOURCE_MAP>) { - chop(); - ($relname, $absname) = (split())[0..1]; - $relname =~ s:^/+::; - $source_map{$relname} = $absname; - } - close(SOURCE_MAP); -} - -if ($output_selection == OUTPUT_EXPORTED || - $output_selection == OUTPUT_INTERNAL) { - - push(@export_file_list, @ARGV); - - foreach (@export_file_list) { - chomp; - process_export_file($_); - } -} - -foreach (@ARGV) { - chomp; - process_file($_); -} -if ($verbose && $errors) { - print STDERR "$errors errors\n"; -} -if ($verbose && $warnings) { - print STDERR "$warnings warnings\n"; -} - -if ($Werror && $warnings) { - print STDERR "$warnings warnings as Errors\n"; - exit($warnings); -} else { - exit($output_mode eq "none" ? 0 : $errors) -} - -__END__ - -=head1 OPTIONS - -=head2 Output format selection (mutually exclusive): - -=over 8 - -=item -man - -Output troff manual page format. - -=item -rst - -Output reStructuredText format. This is the default. - -=item -none - -Do not output documentation, only warnings. - -=back - -=head2 Output format modifiers - -=head3 reStructuredText only - -=over 8 - -=item -sphinx-version VERSION - -Use the ReST C domain dialect compatible with a specific Sphinx Version. - -If not specified, kernel-doc will auto-detect using the sphinx-build version -found on PATH. - -=back - -=head2 Output selection (mutually exclusive): - -=over 8 - -=item -export - -Only output documentation for the symbols that have been exported using -EXPORT_SYMBOL() and related macros in any input FILE or -export-file FILE. - -=item -internal - -Only output documentation for the symbols that have NOT been exported using -EXPORT_SYMBOL() and related macros in any input FILE or -export-file FILE. - -=item -function NAME - -Only output documentation for the given function or DOC: section title. -All other functions and DOC: sections are ignored. - -May be specified multiple times. - -=item -nosymbol NAME - -Exclude the specified symbol from the output documentation. - -May be specified multiple times. - -=back - -=head2 Output selection modifiers: - -=over 8 - -=item -no-doc-sections - -Do not output DOC: sections. - -=item -export-file FILE - -Specify an additional FILE in which to look for EXPORT_SYMBOL information. - -To be used with -export or -internal. - -May be specified multiple times. - -=back - -=head3 reStructuredText only - -=over 8 - -=item -enable-lineno - -Enable output of .. LINENO lines. - -=back - -=head2 Other parameters: - -=over 8 - -=item -h, -help - -Print this help. - -=item -v - -Verbose output, more warnings and other information. - -=item -Werror - -Treat warnings as errors. - -=back - -=cut +kernel-doc.py
\ No newline at end of file diff --git a/scripts/kernel-doc.pl b/scripts/kernel-doc.pl new file mode 100755 index 000000000000..5db23cbf4eb2 --- /dev/null +++ b/scripts/kernel-doc.pl @@ -0,0 +1,2439 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +# vim: softtabstop=4 + +use warnings; +use strict; + +## Copyright (c) 1998 Michael Zucchi, All Rights Reserved ## +## Copyright (C) 2000, 1 Tim Waugh <twaugh@redhat.com> ## +## Copyright (C) 2001 Simon Huggins ## +## Copyright (C) 2005-2012 Randy Dunlap ## +## Copyright (C) 2012 Dan Luedtke ## +## ## +## #define enhancements by Armin Kuster <akuster@mvista.com> ## +## Copyright (c) 2000 MontaVista Software, Inc. ## +# +# Copyright (C) 2022 Tomasz Warniełło (POD) + +use Pod::Usage qw/pod2usage/; + +=head1 NAME + +kernel-doc - Print formatted kernel documentation to stdout + +=head1 SYNOPSIS + + kernel-doc [-h] [-v] [-Werror] [-Wall] [-Wreturn] [-Wshort-desc[ription]] [-Wcontents-before-sections] + [ -man | + -rst [-enable-lineno] | + -none + ] + [ + -export | + -internal | + [-function NAME] ... | + [-nosymbol NAME] ... + ] + [-no-doc-sections] + [-export-file FILE] ... + FILE ... + +Run `kernel-doc -h` for details. + +=head1 DESCRIPTION + +Read C language source or header FILEs, extract embedded documentation comments, +and print formatted documentation to standard output. + +The documentation comments are identified by the "/**" opening comment mark. + +See Documentation/doc-guide/kernel-doc.rst for the documentation comment syntax. + +=cut + +# more perldoc at the end of the file + +## init lots of data + +my $errors = 0; +my $warnings = 0; +my $anon_struct_union = 0; + +# match expressions used to find embedded type information +my $type_constant = '\b``([^\`]+)``\b'; +my $type_constant2 = '\%([-_*\w]+)'; +my $type_func = '(\w+)\(\)'; +my $type_param = '\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)'; +my $type_param_ref = '([\!~\*]?)\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)'; +my $type_fp_param = '\@(\w+)\(\)'; # Special RST handling for func ptr params +my $type_fp_param2 = '\@(\w+->\S+)\(\)'; # Special RST handling for structs with func ptr params +my $type_env = '(\$\w+)'; +my $type_enum = '\&(enum\s*([_\w]+))'; +my $type_struct = '\&(struct\s*([_\w]+))'; +my $type_typedef = '\&(typedef\s*([_\w]+))'; +my $type_union = '\&(union\s*([_\w]+))'; +my $type_member = '\&([_\w]+)(\.|->)([_\w]+)'; +my $type_fallback = '\&([_\w]+)'; +my $type_member_func = $type_member . '\(\)'; + +# Output conversion substitutions. +# One for each output format + +# these are pretty rough +my @highlights_man = ( + [$type_constant, "\$1"], + [$type_constant2, "\$1"], + [$type_func, "\\\\fB\$1\\\\fP"], + [$type_enum, "\\\\fI\$1\\\\fP"], + [$type_struct, "\\\\fI\$1\\\\fP"], + [$type_typedef, "\\\\fI\$1\\\\fP"], + [$type_union, "\\\\fI\$1\\\\fP"], + [$type_param, "\\\\fI\$1\\\\fP"], + [$type_param_ref, "\\\\fI\$1\$2\\\\fP"], + [$type_member, "\\\\fI\$1\$2\$3\\\\fP"], + [$type_fallback, "\\\\fI\$1\\\\fP"] + ); +my $blankline_man = ""; + +# rst-mode +my @highlights_rst = ( + [$type_constant, "``\$1``"], + [$type_constant2, "``\$1``"], + + # Note: need to escape () to avoid func matching later + [$type_member_func, "\\:c\\:type\\:`\$1\$2\$3\\\\(\\\\) <\$1>`"], + [$type_member, "\\:c\\:type\\:`\$1\$2\$3 <\$1>`"], + [$type_fp_param, "**\$1\\\\(\\\\)**"], + [$type_fp_param2, "**\$1\\\\(\\\\)**"], + [$type_func, "\$1()"], + [$type_enum, "\\:c\\:type\\:`\$1 <\$2>`"], + [$type_struct, "\\:c\\:type\\:`\$1 <\$2>`"], + [$type_typedef, "\\:c\\:type\\:`\$1 <\$2>`"], + [$type_union, "\\:c\\:type\\:`\$1 <\$2>`"], + + # in rst this can refer to any type + [$type_fallback, "\\:c\\:type\\:`\$1`"], + [$type_param_ref, "**\$1\$2**"] + ); +my $blankline_rst = "\n"; + +# read arguments +if ($#ARGV == -1) { + pod2usage( + -message => "No arguments!\n", + -exitval => 1, + -verbose => 99, + -sections => 'SYNOPSIS', + -output => \*STDERR, + ); +} + +my $kernelversion; + +my $dohighlight = ""; + +my $verbose = 0; +my $Werror = 0; +my $Wreturn = 0; +my $Wshort_desc = 0; +my $output_mode = "rst"; +my $output_preformatted = 0; +my $no_doc_sections = 0; +my $enable_lineno = 0; +my @highlights = @highlights_rst; +my $blankline = $blankline_rst; +my $modulename = "Kernel API"; + +use constant { + OUTPUT_ALL => 0, # output all symbols and doc sections + OUTPUT_INCLUDE => 1, # output only specified symbols + OUTPUT_EXPORTED => 2, # output exported symbols + OUTPUT_INTERNAL => 3, # output non-exported symbols +}; +my $output_selection = OUTPUT_ALL; +my $show_not_found = 0; # No longer used + +my @export_file_list; + +my @build_time; +if (defined($ENV{'KBUILD_BUILD_TIMESTAMP'}) && + (my $seconds = `date -d "${ENV{'KBUILD_BUILD_TIMESTAMP'}}" +%s`) ne '') { + @build_time = gmtime($seconds); +} else { + @build_time = localtime; +} + +my $man_date = ('January', 'February', 'March', 'April', 'May', 'June', + 'July', 'August', 'September', 'October', + 'November', 'December')[$build_time[4]] . + " " . ($build_time[5]+1900); + +# Essentially these are globals. +# They probably want to be tidied up, made more localised or something. +# CAVEAT EMPTOR! Some of the others I localised may not want to be, which +# could cause "use of undefined value" or other bugs. +my ($function, %function_table, %parametertypes, $declaration_purpose); +my %nosymbol_table = (); +my $declaration_start_line; +my ($type, $declaration_name, $return_type); +my ($newsection, $newcontents, $prototype, $brcount); + +if (defined($ENV{'KBUILD_VERBOSE'}) && $ENV{'KBUILD_VERBOSE'} =~ '1') { + $verbose = 1; +} + +if (defined($ENV{'KCFLAGS'})) { + my $kcflags = "$ENV{'KCFLAGS'}"; + + if ($kcflags =~ /(\s|^)-Werror(\s|$)/) { + $Werror = 1; + } +} + +# reading this variable is for backwards compat just in case +# someone was calling it with the variable from outside the +# kernel's build system +if (defined($ENV{'KDOC_WERROR'})) { + $Werror = "$ENV{'KDOC_WERROR'}"; +} +# other environment variables are converted to command-line +# arguments in cmd_checkdoc in the build system + +# Generated docbook code is inserted in a template at a point where +# docbook v3.1 requires a non-zero sequence of RefEntry's; see: +# https://www.oasis-open.org/docbook/documentation/reference/html/refentry.html +# We keep track of number of generated entries and generate a dummy +# if needs be to ensure the expanded template can be postprocessed +# into html. +my $section_counter = 0; + +my $lineprefix=""; + +# Parser states +use constant { + STATE_NORMAL => 0, # normal code + STATE_NAME => 1, # looking for function name + STATE_BODY_MAYBE => 2, # body - or maybe more description + STATE_BODY => 3, # the body of the comment + STATE_BODY_WITH_BLANK_LINE => 4, # the body, which has a blank line + STATE_PROTO => 5, # scanning prototype + STATE_DOCBLOCK => 6, # documentation block + STATE_INLINE => 7, # gathering doc outside main block +}; +my $state; +my $leading_space; + +# Inline documentation state +use constant { + STATE_INLINE_NA => 0, # not applicable ($state != STATE_INLINE) + STATE_INLINE_NAME => 1, # looking for member name (@foo:) + STATE_INLINE_TEXT => 2, # looking for member documentation + STATE_INLINE_END => 3, # done + STATE_INLINE_ERROR => 4, # error - Comment without header was found. + # Spit a warning as it's not + # proper kernel-doc and ignore the rest. +}; +my $inline_doc_state; + +#declaration types: can be +# 'function', 'struct', 'union', 'enum', 'typedef' +my $decl_type; + +# Name of the kernel-doc identifier for non-DOC markups +my $identifier; + +my $doc_start = '^/\*\*\s*$'; # Allow whitespace at end of comment start. +my $doc_end = '\*/'; +my $doc_com = '\s*\*\s*'; +my $doc_com_body = '\s*\* ?'; +my $doc_decl = $doc_com . '(\w+)'; +# @params and a strictly limited set of supported section names +# Specifically: +# Match @word: +# @...: +# @{section-name}: +# while trying to not match literal block starts like "example::" +# +my $doc_sect = $doc_com . + '\s*(\@[.\w]+|\@\.\.\.|description|context|returns?|notes?|examples?)\s*:([^:].*)?$'; +my $doc_content = $doc_com_body . '(.*)'; +my $doc_block = $doc_com . 'DOC:\s*(.*)?'; +my $doc_inline_start = '^\s*/\*\*\s*$'; +my $doc_inline_sect = '\s*\*\s*(@\s*[\w][\w\.]*\s*):(.*)'; +my $doc_inline_end = '^\s*\*/\s*$'; +my $doc_inline_oneline = '^\s*/\*\*\s*(@[\w\s]+):\s*(.*)\s*\*/\s*$'; +my $export_symbol = '^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*;'; +my $export_symbol_ns = '^\s*EXPORT_SYMBOL_NS(_GPL)?\s*\(\s*(\w+)\s*,\s*"\S+"\)\s*;'; +my $function_pointer = qr{([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)}; +my $attribute = qr{__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)}i; + +my %parameterdescs; +my %parameterdesc_start_lines; +my @parameterlist; +my %sections; +my @sectionlist; +my %section_start_lines; +my $sectcheck; +my $struct_actual; + +my $contents = ""; +my $new_start_line = 0; + +# the canonical section names. see also $doc_sect above. +my $section_default = "Description"; # default section +my $section_intro = "Introduction"; +my $section = $section_default; +my $section_context = "Context"; +my $section_return = "Return"; + +my $undescribed = "-- undescribed --"; + +reset_state(); + +while ($ARGV[0] =~ m/^--?(.*)/) { + my $cmd = $1; + shift @ARGV; + if ($cmd eq "man") { + $output_mode = "man"; + @highlights = @highlights_man; + $blankline = $blankline_man; + } elsif ($cmd eq "rst") { + $output_mode = "rst"; + @highlights = @highlights_rst; + $blankline = $blankline_rst; + } elsif ($cmd eq "none") { + $output_mode = "none"; + } elsif ($cmd eq "module") { # not needed for XML, inherits from calling document + $modulename = shift @ARGV; + } elsif ($cmd eq "function") { # to only output specific functions + $output_selection = OUTPUT_INCLUDE; + $function = shift @ARGV; + $function_table{$function} = 1; + } elsif ($cmd eq "nosymbol") { # Exclude specific symbols + my $symbol = shift @ARGV; + $nosymbol_table{$symbol} = 1; + } elsif ($cmd eq "export") { # only exported symbols + $output_selection = OUTPUT_EXPORTED; + %function_table = (); + } elsif ($cmd eq "internal") { # only non-exported symbols + $output_selection = OUTPUT_INTERNAL; + %function_table = (); + } elsif ($cmd eq "export-file") { + my $file = shift @ARGV; + push(@export_file_list, $file); + } elsif ($cmd eq "v") { + $verbose = 1; + } elsif ($cmd eq "Werror") { + $Werror = 1; + } elsif ($cmd eq "Wreturn") { + $Wreturn = 1; + } elsif ($cmd eq "Wshort-desc" or $cmd eq "Wshort-description") { + $Wshort_desc = 1; + } elsif ($cmd eq "Wall") { + $Wreturn = 1; + $Wshort_desc = 1; + } elsif (($cmd eq "h") || ($cmd eq "help")) { + pod2usage(-exitval => 0, -verbose => 2); + } elsif ($cmd eq 'no-doc-sections') { + $no_doc_sections = 1; + } elsif ($cmd eq 'enable-lineno') { + $enable_lineno = 1; + } elsif ($cmd eq 'show-not-found') { + $show_not_found = 1; # A no-op but don't fail + } else { + # Unknown argument + pod2usage( + -message => "Argument unknown!\n", + -exitval => 1, + -verbose => 99, + -sections => 'SYNOPSIS', + -output => \*STDERR, + ); + } + if ($#ARGV < 0){ + pod2usage( + -message => "FILE argument missing\n", + -exitval => 1, + -verbose => 99, + -sections => 'SYNOPSIS', + -output => \*STDERR, + ); + } +} + +# continue execution near EOF; + +sub findprog($) +{ + foreach(split(/:/, $ENV{PATH})) { + return "$_/$_[0]" if(-x "$_/$_[0]"); + } +} + +# get kernel version from env +sub get_kernel_version() { + my $version = 'unknown kernel version'; + + if (defined($ENV{'KERNELVERSION'})) { + $version = $ENV{'KERNELVERSION'}; + } + return $version; +} + +# +sub print_lineno { + my $lineno = shift; + if ($enable_lineno && defined($lineno)) { + print ".. LINENO " . $lineno . "\n"; + } +} + +sub emit_warning { + my $location = shift; + my $msg = shift; + print STDERR "$location: warning: $msg"; + ++$warnings; +} +## +# dumps section contents to arrays/hashes intended for that purpose. +# +sub dump_section { + my $file = shift; + my $name = shift; + my $contents = join "\n", @_; + + if ($name =~ m/$type_param/) { + $name = $1; + $parameterdescs{$name} = $contents; + $sectcheck = $sectcheck . $name . " "; + $parameterdesc_start_lines{$name} = $new_start_line; + $new_start_line = 0; + } elsif ($name eq "@\.\.\.") { + $name = "..."; + $parameterdescs{$name} = $contents; + $sectcheck = $sectcheck . $name . " "; + $parameterdesc_start_lines{$name} = $new_start_line; + $new_start_line = 0; + } else { + if (defined($sections{$name}) && ($sections{$name} ne "")) { + # Only warn on user specified duplicate section names. + if ($name ne $section_default) { + emit_warning("${file}:$.", "duplicate section name '$name'\n"); + } + $sections{$name} .= $contents; + } else { + $sections{$name} = $contents; + push @sectionlist, $name; + $section_start_lines{$name} = $new_start_line; + $new_start_line = 0; + } + } +} + +## +# dump DOC: section after checking that it should go out +# +sub dump_doc_section { + my $file = shift; + my $name = shift; + my $contents = join "\n", @_; + + if ($no_doc_sections) { + return; + } + + return if (defined($nosymbol_table{$name})); + + if (($output_selection == OUTPUT_ALL) || + (($output_selection == OUTPUT_INCLUDE) && + defined($function_table{$name}))) + { + dump_section($file, $name, $contents); + output_blockhead({'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'module' => $modulename, + 'content-only' => ($output_selection != OUTPUT_ALL), }); + } +} + +## +# output function +# +# parameterdescs, a hash. +# function => "function name" +# parameterlist => @list of parameters +# parameterdescs => %parameter descriptions +# sectionlist => @list of sections +# sections => %section descriptions +# + +sub output_highlight { + my $contents = join "\n",@_; + my $line; + +# DEBUG +# if (!defined $contents) { +# use Carp; +# confess "output_highlight got called with no args?\n"; +# } + +# print STDERR "contents b4:$contents\n"; + eval $dohighlight; + die $@ if $@; +# print STDERR "contents af:$contents\n"; + + foreach $line (split "\n", $contents) { + if (! $output_preformatted) { + $line =~ s/^\s*//; + } + if ($line eq ""){ + if (! $output_preformatted) { + print $lineprefix, $blankline; + } + } else { + if ($output_mode eq "man" && substr($line, 0, 1) eq ".") { + print "\\&$line"; + } else { + print $lineprefix, $line; + } + } + print "\n"; + } +} + +## +# output function in man +sub output_function_man(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + my $count; + my $func_macro = $args{'func_macro'}; + my $paramcount = $#{$args{'parameterlist'}}; # -1 is empty + + print ".TH \"$args{'function'}\" 9 \"$args{'function'}\" \"$man_date\" \"Kernel Hacker's Manual\" LINUX\n"; + + print ".SH NAME\n"; + print $args{'function'} . " \\- " . $args{'purpose'} . "\n"; + + print ".SH SYNOPSIS\n"; + if ($args{'functiontype'} ne "") { + print ".B \"" . $args{'functiontype'} . "\" " . $args{'function'} . "\n"; + } else { + print ".B \"" . $args{'function'} . "\n"; + } + $count = 0; + my $parenth = "("; + my $post = ","; + foreach my $parameter (@{$args{'parameterlist'}}) { + if ($count == $#{$args{'parameterlist'}}) { + $post = ");"; + } + $type = $args{'parametertypes'}{$parameter}; + if ($type =~ m/$function_pointer/) { + # pointer-to-function + print ".BI \"" . $parenth . $1 . "\" " . " \") (" . $2 . ")" . $post . "\"\n"; + } else { + $type =~ s/([^\*])$/$1 /; + print ".BI \"" . $parenth . $type . "\" " . " \"" . $post . "\"\n"; + } + $count++; + $parenth = ""; + } + + $paramcount = $#{$args{'parameterlist'}}; # -1 is empty + if ($paramcount >= 0) { + print ".SH ARGUMENTS\n"; + } + foreach $parameter (@{$args{'parameterlist'}}) { + my $parameter_name = $parameter; + $parameter_name =~ s/\[.*//; + + print ".IP \"" . $parameter . "\" 12\n"; + output_highlight($args{'parameterdescs'}{$parameter_name}); + } + foreach $section (@{$args{'sectionlist'}}) { + print ".SH \"", uc $section, "\"\n"; + output_highlight($args{'sections'}{$section}); + } +} + +## +# output enum in man +sub output_enum_man(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + my $count; + + print ".TH \"$args{'module'}\" 9 \"enum $args{'enum'}\" \"$man_date\" \"API Manual\" LINUX\n"; + + print ".SH NAME\n"; + print "enum " . $args{'enum'} . " \\- " . $args{'purpose'} . "\n"; + + print ".SH SYNOPSIS\n"; + print "enum " . $args{'enum'} . " {\n"; + $count = 0; + foreach my $parameter (@{$args{'parameterlist'}}) { + print ".br\n.BI \" $parameter\"\n"; + if ($count == $#{$args{'parameterlist'}}) { + print "\n};\n"; + last; + } else { + print ", \n.br\n"; + } + $count++; + } + + print ".SH Constants\n"; + foreach $parameter (@{$args{'parameterlist'}}) { + my $parameter_name = $parameter; + $parameter_name =~ s/\[.*//; + + print ".IP \"" . $parameter . "\" 12\n"; + output_highlight($args{'parameterdescs'}{$parameter_name}); + } + foreach $section (@{$args{'sectionlist'}}) { + print ".SH \"$section\"\n"; + output_highlight($args{'sections'}{$section}); + } +} + +## +# output struct in man +sub output_struct_man(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + + print ".TH \"$args{'module'}\" 9 \"" . $args{'type'} . " " . $args{'struct'} . "\" \"$man_date\" \"API Manual\" LINUX\n"; + + print ".SH NAME\n"; + print $args{'type'} . " " . $args{'struct'} . " \\- " . $args{'purpose'} . "\n"; + + my $declaration = $args{'definition'}; + $declaration =~ s/\t/ /g; + $declaration =~ s/\n/"\n.br\n.BI \"/g; + print ".SH SYNOPSIS\n"; + print $args{'type'} . " " . $args{'struct'} . " {\n.br\n"; + print ".BI \"$declaration\n};\n.br\n\n"; + + print ".SH Members\n"; + foreach $parameter (@{$args{'parameterlist'}}) { + ($parameter =~ /^#/) && next; + + my $parameter_name = $parameter; + $parameter_name =~ s/\[.*//; + + ($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next; + print ".IP \"" . $parameter . "\" 12\n"; + output_highlight($args{'parameterdescs'}{$parameter_name}); + } + foreach $section (@{$args{'sectionlist'}}) { + print ".SH \"$section\"\n"; + output_highlight($args{'sections'}{$section}); + } +} + +## +# output typedef in man +sub output_typedef_man(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + + print ".TH \"$args{'module'}\" 9 \"$args{'typedef'}\" \"$man_date\" \"API Manual\" LINUX\n"; + + print ".SH NAME\n"; + print "typedef " . $args{'typedef'} . " \\- " . $args{'purpose'} . "\n"; + + foreach $section (@{$args{'sectionlist'}}) { + print ".SH \"$section\"\n"; + output_highlight($args{'sections'}{$section}); + } +} + +sub output_blockhead_man(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + my $count; + + print ".TH \"$args{'module'}\" 9 \"$args{'module'}\" \"$man_date\" \"API Manual\" LINUX\n"; + + foreach $section (@{$args{'sectionlist'}}) { + print ".SH \"$section\"\n"; + output_highlight($args{'sections'}{$section}); + } +} + +## +# output in restructured text +# + +# +# This could use some work; it's used to output the DOC: sections, and +# starts by putting out the name of the doc section itself, but that tends +# to duplicate a header already in the template file. +# +sub output_blockhead_rst(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + + foreach $section (@{$args{'sectionlist'}}) { + next if (defined($nosymbol_table{$section})); + + if ($output_selection != OUTPUT_INCLUDE) { + print ".. _$section:\n\n"; + print "**$section**\n\n"; + } + print_lineno($section_start_lines{$section}); + output_highlight_rst($args{'sections'}{$section}); + print "\n"; + } +} + +# +# Apply the RST highlights to a sub-block of text. +# +sub highlight_block($) { + # The dohighlight kludge requires the text be called $contents + my $contents = shift; + eval $dohighlight; + die $@ if $@; + return $contents; +} + +# +# Regexes used only here. +# +my $sphinx_literal = '^[^.].*::$'; +my $sphinx_cblock = '^\.\.\ +code-block::'; + +sub output_highlight_rst { + my $input = join "\n",@_; + my $output = ""; + my $line; + my $in_literal = 0; + my $litprefix; + my $block = ""; + + foreach $line (split "\n",$input) { + # + # If we're in a literal block, see if we should drop out + # of it. Otherwise pass the line straight through unmunged. + # + if ($in_literal) { + if (! ($line =~ /^\s*$/)) { + # + # If this is the first non-blank line in a literal + # block we need to figure out what the proper indent is. + # + if ($litprefix eq "") { + $line =~ /^(\s*)/; + $litprefix = '^' . $1; + $output .= $line . "\n"; + } elsif (! ($line =~ /$litprefix/)) { + $in_literal = 0; + } else { + $output .= $line . "\n"; + } + } else { + $output .= $line . "\n"; + } + } + # + # Not in a literal block (or just dropped out) + # + if (! $in_literal) { + $block .= $line . "\n"; + if (($line =~ /$sphinx_literal/) || ($line =~ /$sphinx_cblock/)) { + $in_literal = 1; + $litprefix = ""; + $output .= highlight_block($block); + $block = "" + } + } + } + + if ($block) { + $output .= highlight_block($block); + } + + $output =~ s/^\n+//g; + $output =~ s/\n+$//g; + + foreach $line (split "\n", $output) { + print $lineprefix . $line . "\n"; + } +} + +sub output_function_rst(%) { + my %args = %{$_[0]}; + my ($parameter, $section); + my $oldprefix = $lineprefix; + + my $signature = ""; + my $func_macro = $args{'func_macro'}; + my $paramcount = $#{$args{'parameterlist'}}; # -1 is empty + + if ($func_macro) { + $signature = $args{'function'}; + } else { + if ($args{'functiontype'}) { + $signature = $args{'functiontype'} . " "; + } + $signature .= $args{'function'} . " ("; + } + + my $count = 0; + foreach my $parameter (@{$args{'parameterlist'}}) { + if ($count ne 0) { + $signature .= ", "; + } + $count++; + $type = $args{'parametertypes'}{$parameter}; + + if ($type =~ m/$function_pointer/) { + # pointer-to-function + $signature .= $1 . $parameter . ") (" . $2 . ")"; + } else { + $signature .= $type; + } + } + + if (!$func_macro) { + $signature .= ")"; + } + + if ($args{'typedef'} || $args{'functiontype'} eq "") { + print ".. c:macro:: ". $args{'function'} . "\n\n"; + + if ($args{'typedef'}) { + print_lineno($declaration_start_line); + print " **Typedef**: "; + $lineprefix = ""; + output_highlight_rst($args{'purpose'}); + print "\n\n**Syntax**\n\n"; + print " ``$signature``\n\n"; + } else { + print "``$signature``\n\n"; + } + } else { + print ".. c:function:: $signature\n\n"; + } + + if (!$args{'typedef'}) { + print_lineno($declaration_start_line); + $lineprefix = " "; + output_highlight_rst($args{'purpose'}); + print "\n"; + } + + # + # Put our descriptive text into a container (thus an HTML <div>) to help + # set the function prototypes apart. + # + $lineprefix = " "; + if ($paramcount >= 0) { + print ".. container:: kernelindent\n\n"; + print $lineprefix . "**Parameters**\n\n"; + } + foreach $parameter (@{$args{'parameterlist'}}) { + my $parameter_name = $parameter; + $parameter_name =~ s/\[.*//; + $type = $args{'parametertypes'}{$parameter}; + + if ($type ne "") { + print $lineprefix . "``$type``\n"; + } else { + print $lineprefix . "``$parameter``\n"; + } + + print_lineno($parameterdesc_start_lines{$parameter_name}); + + $lineprefix = " "; + if (defined($args{'parameterdescs'}{$parameter_name}) && + $args{'parameterdescs'}{$parameter_name} ne $undescribed) { + output_highlight_rst($args{'parameterdescs'}{$parameter_name}); + } else { + print $lineprefix . "*undescribed*\n"; + } + $lineprefix = " "; + print "\n"; + } + + output_section_rst(@_); + $lineprefix = $oldprefix; +} + +sub output_section_rst(%) { + my %args = %{$_[0]}; + my $section; + my $oldprefix = $lineprefix; + + foreach $section (@{$args{'sectionlist'}}) { + print $lineprefix . "**$section**\n\n"; + print_lineno($section_start_lines{$section}); + output_highlight_rst($args{'sections'}{$section}); + print "\n"; + } + print "\n"; +} + +sub output_enum_rst(%) { + my %args = %{$_[0]}; + my ($parameter); + my $oldprefix = $lineprefix; + my $count; + my $outer; + + my $name = $args{'enum'}; + print "\n\n.. c:enum:: " . $name . "\n\n"; + + print_lineno($declaration_start_line); + $lineprefix = " "; + output_highlight_rst($args{'purpose'}); + print "\n"; + + print ".. container:: kernelindent\n\n"; + $outer = $lineprefix . " "; + $lineprefix = $outer . " "; + print $outer . "**Constants**\n\n"; + foreach $parameter (@{$args{'parameterlist'}}) { + print $outer . "``$parameter``\n"; + + if ($args{'parameterdescs'}{$parameter} ne $undescribed) { + output_highlight_rst($args{'parameterdescs'}{$parameter}); + } else { + print $lineprefix . "*undescribed*\n"; + } + print "\n"; + } + print "\n"; + $lineprefix = $oldprefix; + output_section_rst(@_); +} + +sub output_typedef_rst(%) { + my %args = %{$_[0]}; + my ($parameter); + my $oldprefix = $lineprefix; + my $name; + + $name = $args{'typedef'}; + + print "\n\n.. c:type:: " . $name . "\n\n"; + print_lineno($declaration_start_line); + $lineprefix = " "; + output_highlight_rst($args{'purpose'}); + print "\n"; + + $lineprefix = $oldprefix; + output_section_rst(@_); +} + +sub output_struct_rst(%) { + my %args = %{$_[0]}; + my ($parameter); + my $oldprefix = $lineprefix; + + my $name = $args{'struct'}; + if ($args{'type'} eq 'union') { + print "\n\n.. c:union:: " . $name . "\n\n"; + } else { + print "\n\n.. c:struct:: " . $name . "\n\n"; + } + + print_lineno($declaration_start_line); + $lineprefix = " "; + output_highlight_rst($args{'purpose'}); + print "\n"; + + print ".. container:: kernelindent\n\n"; + print $lineprefix . "**Definition**::\n\n"; + my $declaration = $args{'definition'}; + $lineprefix = $lineprefix . " "; + $declaration =~ s/\t/$lineprefix/g; + print $lineprefix . $args{'type'} . " " . $args{'struct'} . " {\n$declaration" . $lineprefix . "};\n\n"; + + $lineprefix = " "; + print $lineprefix . "**Members**\n\n"; + foreach $parameter (@{$args{'parameterlist'}}) { + ($parameter =~ /^#/) && next; + + my $parameter_name = $parameter; + $parameter_name =~ s/\[.*//; + + ($args{'parameterdescs'}{$parameter_name} ne $undescribed) || next; + $type = $args{'parametertypes'}{$parameter}; + print_lineno($parameterdesc_start_lines{$parameter_name}); + print $lineprefix . "``" . $parameter . "``\n"; + $lineprefix = " "; + output_highlight_rst($args{'parameterdescs'}{$parameter_name}); + $lineprefix = " "; + print "\n"; + } + print "\n"; + + $lineprefix = $oldprefix; + output_section_rst(@_); +} + +## none mode output functions + +sub output_function_none(%) { +} + +sub output_enum_none(%) { +} + +sub output_typedef_none(%) { +} + +sub output_struct_none(%) { +} + +sub output_blockhead_none(%) { +} + +## +# generic output function for all types (function, struct/union, typedef, enum); +# calls the generated, variable output_ function name based on +# functype and output_mode +sub output_declaration { + no strict 'refs'; + my $name = shift; + my $functype = shift; + my $func = "output_${functype}_$output_mode"; + + return if (defined($nosymbol_table{$name})); + + if (($output_selection == OUTPUT_ALL) || + (($output_selection == OUTPUT_INCLUDE || + $output_selection == OUTPUT_EXPORTED) && + defined($function_table{$name})) || + ($output_selection == OUTPUT_INTERNAL && + !($functype eq "function" && defined($function_table{$name})))) + { + &$func(@_); + $section_counter++; + } +} + +## +# generic output function - calls the right one based on current output mode. +sub output_blockhead { + no strict 'refs'; + my $func = "output_blockhead_" . $output_mode; + &$func(@_); + $section_counter++; +} + +## +# takes a declaration (struct, union, enum, typedef) and +# invokes the right handler. NOT called for functions. +sub dump_declaration($$) { + no strict 'refs'; + my ($prototype, $file) = @_; + my $func = "dump_" . $decl_type; + &$func(@_); +} + +sub dump_union($$) { + dump_struct(@_); +} + +sub dump_struct($$) { + my $x = shift; + my $file = shift; + my $decl_type; + my $members; + my $type = qr{struct|union}; + # For capturing struct/union definition body, i.e. "{members*}qualifiers*" + my $qualifiers = qr{$attribute|__packed|__aligned|____cacheline_aligned_in_smp|____cacheline_aligned}; + my $definition_body = qr{\{(.*)\}\s*$qualifiers*}; + my $struct_members = qr{($type)([^\{\};]+)\{([^\{\}]*)\}([^\{\}\;]*)\;}; + + if ($x =~ /($type)\s+(\w+)\s*$definition_body/) { + $decl_type = $1; + $declaration_name = $2; + $members = $3; + } elsif ($x =~ /typedef\s+($type)\s*$definition_body\s*(\w+)\s*;/) { + $decl_type = $1; + $declaration_name = $3; + $members = $2; + } + + if ($members) { + if ($identifier ne $declaration_name) { + emit_warning("${file}:$.", "expecting prototype for $decl_type $identifier. Prototype was for $decl_type $declaration_name instead\n"); + return; + } + + # ignore members marked private: + $members =~ s/\/\*\s*private:.*?\/\*\s*public:.*?\*\///gosi; + $members =~ s/\/\*\s*private:.*//gosi; + # strip comments: + $members =~ s/\/\*.*?\*\///gos; + # strip attributes + $members =~ s/\s*$attribute/ /gi; + $members =~ s/\s*__aligned\s*\([^;]*\)/ /gos; + $members =~ s/\s*__counted_by\s*\([^;]*\)/ /gos; + $members =~ s/\s*__counted_by_(le|be)\s*\([^;]*\)/ /gos; + $members =~ s/\s*__packed\s*/ /gos; + $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; + $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; + $members =~ s/\s*____cacheline_aligned/ /gos; + # unwrap struct_group(): + # - first eat non-declaration parameters and rewrite for final match + # - then remove macro, outer parens, and trailing semicolon + $members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos; + $members =~ s/\bstruct_group_attr\s*\(([^,]*,){2}/STRUCT_GROUP(/gos; + $members =~ s/\bstruct_group_tagged\s*\(([^,]*),([^,]*),/struct $1 $2; STRUCT_GROUP(/gos; + $members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos; + $members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos; + + my $args = qr{([^,)]+)}; + # replace DECLARE_BITMAP + $members =~ s/__ETHTOOL_DECLARE_LINK_MODE_MASK\s*\(([^\)]+)\)/DECLARE_BITMAP($1, __ETHTOOL_LINK_MODE_MASK_NBITS)/gos; + $members =~ s/DECLARE_PHY_INTERFACE_MASK\s*\(([^\)]+)\)/DECLARE_BITMAP($1, PHY_INTERFACE_MODE_MAX)/gos; + $members =~ s/DECLARE_BITMAP\s*\($args,\s*$args\)/unsigned long $1\[BITS_TO_LONGS($2)\]/gos; + # replace DECLARE_HASHTABLE + $members =~ s/DECLARE_HASHTABLE\s*\($args,\s*$args\)/unsigned long $1\[1 << (($2) - 1)\]/gos; + # replace DECLARE_KFIFO + $members =~ s/DECLARE_KFIFO\s*\($args,\s*$args,\s*$args\)/$2 \*$1/gos; + # replace DECLARE_KFIFO_PTR + $members =~ s/DECLARE_KFIFO_PTR\s*\($args,\s*$args\)/$2 \*$1/gos; + # replace DECLARE_FLEX_ARRAY + $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\($args,\s*$args\)/$1 $2\[\]/gos; + #replace DEFINE_DMA_UNMAP_ADDR + $members =~ s/DEFINE_DMA_UNMAP_ADDR\s*\($args\)/dma_addr_t $1/gos; + #replace DEFINE_DMA_UNMAP_LEN + $members =~ s/DEFINE_DMA_UNMAP_LEN\s*\($args\)/__u32 $1/gos; + my $declaration = $members; + + # Split nested struct/union elements as newer ones + while ($members =~ m/$struct_members/) { + my $newmember; + my $maintype = $1; + my $ids = $4; + my $content = $3; + foreach my $id(split /,/, $ids) { + $newmember .= "$maintype $id; "; + + $id =~ s/[:\[].*//; + $id =~ s/^\s*\**(\S+)\s*/$1/; + foreach my $arg (split /;/, $content) { + next if ($arg =~ m/^\s*$/); + if ($arg =~ m/^([^\(]+\(\*?\s*)([\w\.]*)(\s*\).*)/) { + # pointer-to-function + my $type = $1; + my $name = $2; + my $extra = $3; + next if (!$name); + if ($id =~ m/^\s*$/) { + # anonymous struct/union + $newmember .= "$type$name$extra; "; + } else { + $newmember .= "$type$id.$name$extra; "; + } + } else { + my $type; + my $names; + $arg =~ s/^\s+//; + $arg =~ s/\s+$//; + # Handle bitmaps + $arg =~ s/:\s*\d+\s*//g; + # Handle arrays + $arg =~ s/\[.*\]//g; + # The type may have multiple words, + # and multiple IDs can be defined, like: + # const struct foo, *bar, foobar + # So, we remove spaces when parsing the + # names, in order to match just names + # and commas for the names + $arg =~ s/\s*,\s*/,/g; + if ($arg =~ m/(.*)\s+([\S+,]+)/) { + $type = $1; + $names = $2; + } else { + $newmember .= "$arg; "; + next; + } + foreach my $name (split /,/, $names) { + $name =~ s/^\s*\**(\S+)\s*/$1/; + next if (($name =~ m/^\s*$/)); + if ($id =~ m/^\s*$/) { + # anonymous struct/union + $newmember .= "$type $name; "; + } else { + $newmember .= "$type $id.$name; "; + } + } + } + } + } + $members =~ s/$struct_members/$newmember/; + } + + # Ignore other nested elements, like enums + $members =~ s/(\{[^\{\}]*\})//g; + + create_parameterlist($members, ';', $file, $declaration_name); + check_sections($file, $declaration_name, $decl_type, $sectcheck, $struct_actual); + + # Adjust declaration for better display + $declaration =~ s/([\{;])/$1\n/g; + $declaration =~ s/\}\s+;/};/g; + # Better handle inlined enums + do {} while ($declaration =~ s/(enum\s+\{[^\}]+),([^\n])/$1,\n$2/); + + my @def_args = split /\n/, $declaration; + my $level = 1; + $declaration = ""; + foreach my $clause (@def_args) { + $clause =~ s/^\s+//; + $clause =~ s/\s+$//; + $clause =~ s/\s+/ /; + next if (!$clause); + $level-- if ($clause =~ m/(\})/ && $level > 1); + if (!($clause =~ m/^\s*#/)) { + $declaration .= "\t" x $level; + } + $declaration .= "\t" . $clause . "\n"; + $level++ if ($clause =~ m/(\{)/ && !($clause =~m/\}/)); + } + output_declaration($declaration_name, + 'struct', + {'struct' => $declaration_name, + 'module' => $modulename, + 'definition' => $declaration, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'parametertypes' => \%parametertypes, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose, + 'type' => $decl_type + }); + } else { + print STDERR "${file}:$.: error: Cannot parse struct or union!\n"; + ++$errors; + } +} + + +sub show_warnings($$) { + my $functype = shift; + my $name = shift; + + return 0 if (defined($nosymbol_table{$name})); + + return 1 if ($output_selection == OUTPUT_ALL); + + if ($output_selection == OUTPUT_EXPORTED) { + if (defined($function_table{$name})) { + return 1; + } else { + return 0; + } + } + if ($output_selection == OUTPUT_INTERNAL) { + if (!($functype eq "function" && defined($function_table{$name}))) { + return 1; + } else { + return 0; + } + } + if ($output_selection == OUTPUT_INCLUDE) { + if (defined($function_table{$name})) { + return 1; + } else { + return 0; + } + } + die("Please add the new output type at show_warnings()"); +} + +sub dump_enum($$) { + my $x = shift; + my $file = shift; + my $members; + + # ignore members marked private: + $x =~ s/\/\*\s*private:.*?\/\*\s*public:.*?\*\///gosi; + $x =~ s/\/\*\s*private:.*}/}/gosi; + + $x =~ s@/\*.*?\*/@@gos; # strip comments. + # strip #define macros inside enums + $x =~ s@#\s*((define|ifdef|if)\s+|endif)[^;]*;@@gos; + + if ($x =~ /typedef\s+enum\s*\{(.*)\}\s*(\w*)\s*;/) { + $declaration_name = $2; + $members = $1; + } elsif ($x =~ /enum\s+(\w*)\s*\{(.*)\}/) { + $declaration_name = $1; + $members = $2; + } + + if ($members) { + if ($identifier ne $declaration_name) { + if ($identifier eq "") { + emit_warning("${file}:$.", "wrong kernel-doc identifier on line:\n"); + } else { + emit_warning("${file}:$.", "expecting prototype for enum $identifier. Prototype was for enum $declaration_name instead\n"); + } + return; + } + $declaration_name = "(anonymous)" if ($declaration_name eq ""); + + my %_members; + + $members =~ s/\s+$//; + $members =~ s/\([^;]*?[\)]//g; + + foreach my $arg (split ',', $members) { + $arg =~ s/^\s*(\w+).*/$1/; + push @parameterlist, $arg; + if (!$parameterdescs{$arg}) { + $parameterdescs{$arg} = $undescribed; + if (show_warnings("enum", $declaration_name)) { + emit_warning("${file}:$.", "Enum value '$arg' not described in enum '$declaration_name'\n"); + } + } + $_members{$arg} = 1; + } + + while (my ($k, $v) = each %parameterdescs) { + if (!exists($_members{$k})) { + if (show_warnings("enum", $declaration_name)) { + emit_warning("${file}:$.", "Excess enum value '$k' description in '$declaration_name'\n"); + } + } + } + + output_declaration($declaration_name, + 'enum', + {'enum' => $declaration_name, + 'module' => $modulename, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose + }); + } else { + print STDERR "${file}:$.: error: Cannot parse enum!\n"; + ++$errors; + } +} + +my $typedef_type = qr { ((?:\s+[\w\*]+\b){0,7}\s+(?:\w+\b|\*+))\s* }x; +my $typedef_ident = qr { \*?\s*(\w\S+)\s* }x; +my $typedef_args = qr { \s*\((.*)\); }x; + +my $typedef1 = qr { typedef$typedef_type\($typedef_ident\)$typedef_args }x; +my $typedef2 = qr { typedef$typedef_type$typedef_ident$typedef_args }x; + +sub dump_typedef($$) { + my $x = shift; + my $file = shift; + + $x =~ s@/\*.*?\*/@@gos; # strip comments. + + # Parse function typedef prototypes + if ($x =~ $typedef1 || $x =~ $typedef2) { + $return_type = $1; + $declaration_name = $2; + my $args = $3; + $return_type =~ s/^\s+//; + + if ($identifier ne $declaration_name) { + emit_warning("${file}:$.", "expecting prototype for typedef $identifier. Prototype was for typedef $declaration_name instead\n"); + return; + } + + create_parameterlist($args, ',', $file, $declaration_name); + + output_declaration($declaration_name, + 'function', + {'function' => $declaration_name, + 'typedef' => 1, + 'module' => $modulename, + 'functiontype' => $return_type, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'parametertypes' => \%parametertypes, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose + }); + return; + } + + while (($x =~ /\(*.\)\s*;$/) || ($x =~ /\[*.\]\s*;$/)) { + $x =~ s/\(*.\)\s*;$/;/; + $x =~ s/\[*.\]\s*;$/;/; + } + + if ($x =~ /typedef.*\s+(\w+)\s*;/) { + $declaration_name = $1; + + if ($identifier ne $declaration_name) { + emit_warning("${file}:$.", "expecting prototype for typedef $identifier. Prototype was for typedef $declaration_name instead\n"); + return; + } + + output_declaration($declaration_name, + 'typedef', + {'typedef' => $declaration_name, + 'module' => $modulename, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose + }); + } else { + print STDERR "${file}:$.: error: Cannot parse typedef!\n"; + ++$errors; + } +} + +sub save_struct_actual($) { + my $actual = shift; + + # strip all spaces from the actual param so that it looks like one string item + $actual =~ s/\s*//g; + $struct_actual = $struct_actual . $actual . " "; +} + +sub create_parameterlist($$$$) { + my $args = shift; + my $splitter = shift; + my $file = shift; + my $declaration_name = shift; + my $type; + my $param; + + # temporarily replace commas inside function pointer definition + my $arg_expr = qr{\([^\),]+}; + while ($args =~ /$arg_expr,/) { + $args =~ s/($arg_expr),/$1#/g; + } + + foreach my $arg (split($splitter, $args)) { + # strip comments + $arg =~ s/\/\*.*\*\///; + # ignore argument attributes + $arg =~ s/\sPOS0?\s/ /; + # strip leading/trailing spaces + $arg =~ s/^\s*//; + $arg =~ s/\s*$//; + $arg =~ s/\s+/ /; + + if ($arg =~ /^#/) { + # Treat preprocessor directive as a typeless variable just to fill + # corresponding data structures "correctly". Catch it later in + # output_* subs. + push_parameter($arg, "", "", $file); + } elsif ($arg =~ m/\(.+\)\s*\(/) { + # pointer-to-function + $arg =~ tr/#/,/; + $arg =~ m/[^\(]+\(\*?\s*([\w\[\]\.]*)\s*\)/; + $param = $1; + $type = $arg; + $type =~ s/([^\(]+\(\*?)\s*$param/$1/; + save_struct_actual($param); + push_parameter($param, $type, $arg, $file, $declaration_name); + } elsif ($arg =~ m/\(.+\)\s*\[/) { + # array-of-pointers + $arg =~ tr/#/,/; + $arg =~ m/[^\(]+\(\s*\*\s*([\w\[\]\.]*?)\s*(\s*\[\s*[\w]+\s*\]\s*)*\)/; + $param = $1; + $type = $arg; + $type =~ s/([^\(]+\(\*?)\s*$param/$1/; + save_struct_actual($param); + push_parameter($param, $type, $arg, $file, $declaration_name); + } elsif ($arg) { + $arg =~ s/\s*:\s*/:/g; + $arg =~ s/\s*\[/\[/g; + + my @args = split('\s*,\s*', $arg); + if ($args[0] =~ m/\*/) { + $args[0] =~ s/(\*+)\s*/ $1/; + } + + my @first_arg; + if ($args[0] =~ /^(.*\s+)(.*?\[.*\].*)$/) { + shift @args; + push(@first_arg, split('\s+', $1)); + push(@first_arg, $2); + } else { + @first_arg = split('\s+', shift @args); + } + + unshift(@args, pop @first_arg); + $type = join " ", @first_arg; + + foreach $param (@args) { + if ($param =~ m/^(\*+)\s*(.*)/) { + save_struct_actual($2); + + push_parameter($2, "$type $1", $arg, $file, $declaration_name); + } elsif ($param =~ m/(.*?):(\w+)/) { + if ($type ne "") { # skip unnamed bit-fields + save_struct_actual($1); + push_parameter($1, "$type:$2", $arg, $file, $declaration_name) + } + } else { + save_struct_actual($param); + push_parameter($param, $type, $arg, $file, $declaration_name); + } + } + } + } +} + +sub push_parameter($$$$$) { + my $param = shift; + my $type = shift; + my $org_arg = shift; + my $file = shift; + my $declaration_name = shift; + + if (($anon_struct_union == 1) && ($type eq "") && + ($param eq "}")) { + return; # ignore the ending }; from anon. struct/union + } + + $anon_struct_union = 0; + $param =~ s/[\[\)].*//; + + if ($type eq "" && $param =~ /\.\.\.$/) + { + if (!$param =~ /\w\.\.\.$/) { + # handles unnamed variable parameters + $param = "..."; + } elsif ($param =~ /\w\.\.\.$/) { + # for named variable parameters of the form `x...`, remove the dots + $param =~ s/\.\.\.$//; + } + if (!defined $parameterdescs{$param} || $parameterdescs{$param} eq "") { + $parameterdescs{$param} = "variable arguments"; + } + } + elsif ($type eq "" && ($param eq "" or $param eq "void")) + { + $param="void"; + $parameterdescs{void} = "no arguments"; + } + elsif ($type eq "" && ($param eq "struct" or $param eq "union")) + # handle unnamed (anonymous) union or struct: + { + $type = $param; + $param = "{unnamed_" . $param . "}"; + $parameterdescs{$param} = "anonymous\n"; + $anon_struct_union = 1; + } + elsif ($param =~ "__cacheline_group" ) + # handle cache group enforcing variables: they do not need be described in header files + { + return; # ignore __cacheline_group_begin and __cacheline_group_end + } + + # warn if parameter has no description + # (but ignore ones starting with # as these are not parameters + # but inline preprocessor statements); + # Note: It will also ignore void params and unnamed structs/unions + if (!defined $parameterdescs{$param} && $param !~ /^#/) { + $parameterdescs{$param} = $undescribed; + + if (show_warnings($type, $declaration_name) && $param !~ /\./) { + emit_warning("${file}:$.", "Function parameter or struct member '$param' not described in '$declaration_name'\n"); + } + } + + # strip spaces from $param so that it is one continuous string + # on @parameterlist; + # this fixes a problem where check_sections() cannot find + # a parameter like "addr[6 + 2]" because it actually appears + # as "addr[6", "+", "2]" on the parameter list; + # but it's better to maintain the param string unchanged for output, + # so just weaken the string compare in check_sections() to ignore + # "[blah" in a parameter string; + ###$param =~ s/\s*//g; + push @parameterlist, $param; + $org_arg =~ s/\s\s+/ /g; + $parametertypes{$param} = $org_arg; +} + +sub check_sections($$$$$) { + my ($file, $decl_name, $decl_type, $sectcheck, $prmscheck) = @_; + my @sects = split ' ', $sectcheck; + my @prms = split ' ', $prmscheck; + my $err; + my ($px, $sx); + my $prm_clean; # strip trailing "[array size]" and/or beginning "*" + + foreach $sx (0 .. $#sects) { + $err = 1; + foreach $px (0 .. $#prms) { + $prm_clean = $prms[$px]; + $prm_clean =~ s/\[.*\]//; + $prm_clean =~ s/$attribute//i; + # ignore array size in a parameter string; + # however, the original param string may contain + # spaces, e.g.: addr[6 + 2] + # and this appears in @prms as "addr[6" since the + # parameter list is split at spaces; + # hence just ignore "[..." for the sections check; + $prm_clean =~ s/\[.*//; + + ##$prm_clean =~ s/^\**//; + if ($prm_clean eq $sects[$sx]) { + $err = 0; + last; + } + } + if ($err) { + if ($decl_type eq "function") { + emit_warning("${file}:$.", + "Excess function parameter " . + "'$sects[$sx]' " . + "description in '$decl_name'\n"); + } elsif (($decl_type eq "struct") or + ($decl_type eq "union")) { + emit_warning("${file}:$.", + "Excess $decl_type member " . + "'$sects[$sx]' " . + "description in '$decl_name'\n"); + } + } + } +} + +## +# Checks the section describing the return value of a function. +sub check_return_section { + my $file = shift; + my $declaration_name = shift; + my $return_type = shift; + + # Ignore an empty return type (It's a macro) + # Ignore functions with a "void" return type. (But don't ignore "void *") + if (($return_type eq "") || ($return_type =~ /void\s*\w*\s*$/)) { + return; + } + + if (!defined($sections{$section_return}) || + $sections{$section_return} eq "") + { + emit_warning("${file}:$.", + "No description found for return value of " . + "'$declaration_name'\n"); + } +} + +## +# takes a function prototype and the name of the current file being +# processed and spits out all the details stored in the global +# arrays/hashes. +sub dump_function($$) { + my $prototype = shift; + my $file = shift; + my $func_macro = 0; + + print_lineno($new_start_line); + + $prototype =~ s/^static +//; + $prototype =~ s/^extern +//; + $prototype =~ s/^asmlinkage +//; + $prototype =~ s/^inline +//; + $prototype =~ s/^__inline__ +//; + $prototype =~ s/^__inline +//; + $prototype =~ s/^__always_inline +//; + $prototype =~ s/^noinline +//; + $prototype =~ s/^__FORTIFY_INLINE +//; + $prototype =~ s/__init +//; + $prototype =~ s/__init_or_module +//; + $prototype =~ s/__deprecated +//; + $prototype =~ s/__flatten +//; + $prototype =~ s/__meminit +//; + $prototype =~ s/__must_check +//; + $prototype =~ s/__weak +//; + $prototype =~ s/__sched +//; + $prototype =~ s/_noprof//; + $prototype =~ s/__printf\s*\(\s*\d*\s*,\s*\d*\s*\) +//; + $prototype =~ s/__(?:re)?alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) +//; + $prototype =~ s/__diagnose_as\s*\(\s*\S+\s*(?:,\s*\d+\s*)*\) +//; + $prototype =~ s/DECL_BUCKET_PARAMS\s*\(\s*(\S+)\s*,\s*(\S+)\s*\)/$1, $2/; + my $define = $prototype =~ s/^#\s*define\s+//; #ak added + $prototype =~ s/__attribute_const__ +//; + $prototype =~ s/__attribute__\s*\(\( + (?: + [\w\s]++ # attribute name + (?:\([^)]*+\))? # attribute arguments + \s*+,? # optional comma at the end + )+ + \)\)\s+//x; + + # Yes, this truly is vile. We are looking for: + # 1. Return type (may be nothing if we're looking at a macro) + # 2. Function name + # 3. Function parameters. + # + # All the while we have to watch out for function pointer parameters + # (which IIRC is what the two sections are for), C types (these + # regexps don't even start to express all the possibilities), and + # so on. + # + # If you mess with these regexps, it's a good idea to check that + # the following functions' documentation still comes out right: + # - parport_register_device (function pointer parameters) + # - atomic_set (macro) + # - pci_match_device, __copy_to_user (long return type) + my $name = qr{[a-zA-Z0-9_~:]+}; + my $prototype_end1 = qr{[^\(]*}; + my $prototype_end2 = qr{[^\{]*}; + my $prototype_end = qr{\(($prototype_end1|$prototype_end2)\)}; + my $type1 = qr{[\w\s]+}; + my $type2 = qr{$type1\*+}; + + if ($define && $prototype =~ m/^()($name)\s+/) { + # This is an object-like macro, it has no return type and no parameter + # list. + # Function-like macros are not allowed to have spaces between + # declaration_name and opening parenthesis (notice the \s+). + $return_type = $1; + $declaration_name = $2; + $func_macro = 1; + } elsif ($prototype =~ m/^()($name)\s*$prototype_end/ || + $prototype =~ m/^($type1)\s+($name)\s*$prototype_end/ || + $prototype =~ m/^($type2+)\s*($name)\s*$prototype_end/) { + $return_type = $1; + $declaration_name = $2; + my $args = $3; + + create_parameterlist($args, ',', $file, $declaration_name); + } else { + emit_warning("${file}:$.", "cannot understand function prototype: '$prototype'\n"); + return; + } + + if ($identifier ne $declaration_name) { + emit_warning("${file}:$.", "expecting prototype for $identifier(). Prototype was for $declaration_name() instead\n"); + return; + } + + my $prms = join " ", @parameterlist; + check_sections($file, $declaration_name, "function", $sectcheck, $prms); + + # This check emits a lot of warnings at the moment, because many + # functions don't have a 'Return' doc section. So until the number + # of warnings goes sufficiently down, the check is only performed in + # -Wreturn mode. + # TODO: always perform the check. + if ($Wreturn && !$func_macro) { + check_return_section($file, $declaration_name, $return_type); + } + + # The function parser can be called with a typedef parameter. + # Handle it. + if ($return_type =~ /typedef/) { + output_declaration($declaration_name, + 'function', + {'function' => $declaration_name, + 'typedef' => 1, + 'module' => $modulename, + 'functiontype' => $return_type, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'parametertypes' => \%parametertypes, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose, + 'func_macro' => $func_macro + }); + } else { + output_declaration($declaration_name, + 'function', + {'function' => $declaration_name, + 'module' => $modulename, + 'functiontype' => $return_type, + 'parameterlist' => \@parameterlist, + 'parameterdescs' => \%parameterdescs, + 'parametertypes' => \%parametertypes, + 'sectionlist' => \@sectionlist, + 'sections' => \%sections, + 'purpose' => $declaration_purpose, + 'func_macro' => $func_macro + }); + } +} + +sub reset_state { + $function = ""; + %parameterdescs = (); + %parametertypes = (); + @parameterlist = (); + %sections = (); + @sectionlist = (); + $sectcheck = ""; + $struct_actual = ""; + $prototype = ""; + + $state = STATE_NORMAL; + $inline_doc_state = STATE_INLINE_NA; +} + +sub tracepoint_munge($) { + my $file = shift; + my $tracepointname = 0; + my $tracepointargs = 0; + + if ($prototype =~ m/TRACE_EVENT\((.*?),/) { + $tracepointname = $1; + } + if ($prototype =~ m/DEFINE_SINGLE_EVENT\((.*?),/) { + $tracepointname = $1; + } + if ($prototype =~ m/DEFINE_EVENT\((.*?),(.*?),/) { + $tracepointname = $2; + } + $tracepointname =~ s/^\s+//; #strip leading whitespace + if ($prototype =~ m/TP_PROTO\((.*?)\)/) { + $tracepointargs = $1; + } + if (($tracepointname eq 0) || ($tracepointargs eq 0)) { + emit_warning("${file}:$.", "Unrecognized tracepoint format: \n". + "$prototype\n"); + } else { + $prototype = "static inline void trace_$tracepointname($tracepointargs)"; + $identifier = "trace_$identifier"; + } +} + +sub syscall_munge() { + my $void = 0; + + $prototype =~ s@[\r\n]+@ @gos; # strip newlines/CR's +## if ($prototype =~ m/SYSCALL_DEFINE0\s*\(\s*(a-zA-Z0-9_)*\s*\)/) { + if ($prototype =~ m/SYSCALL_DEFINE0/) { + $void = 1; +## $prototype = "long sys_$1(void)"; + } + + $prototype =~ s/SYSCALL_DEFINE.*\(/long sys_/; # fix return type & func name + if ($prototype =~ m/long (sys_.*?),/) { + $prototype =~ s/,/\(/; + } elsif ($void) { + $prototype =~ s/\)/\(void\)/; + } + + # now delete all of the odd-number commas in $prototype + # so that arg types & arg names don't have a comma between them + my $count = 0; + my $len = length($prototype); + if ($void) { + $len = 0; # skip the for-loop + } + for (my $ix = 0; $ix < $len; $ix++) { + if (substr($prototype, $ix, 1) eq ',') { + $count++; + if ($count % 2 == 1) { + substr($prototype, $ix, 1) = ' '; + } + } + } +} + +sub process_proto_function($$) { + my $x = shift; + my $file = shift; + + $x =~ s@\/\/.*$@@gos; # strip C99-style comments to end of line + + if ($x =~ /^#/ && $x !~ /^#\s*define/) { + # do nothing + } elsif ($x =~ /([^\{]*)/) { + $prototype .= $1; + } + + if (($x =~ /\{/) || ($x =~ /\#\s*define/) || ($x =~ /;/)) { + $prototype =~ s@/\*.*?\*/@@gos; # strip comments. + $prototype =~ s@[\r\n]+@ @gos; # strip newlines/cr's. + $prototype =~ s@^\s+@@gos; # strip leading spaces + + # Handle prototypes for function pointers like: + # int (*pcs_config)(struct foo) + $prototype =~ s@^(\S+\s+)\(\s*\*(\S+)\)@$1$2@gos; + + if ($prototype =~ /SYSCALL_DEFINE/) { + syscall_munge(); + } + if ($prototype =~ /TRACE_EVENT/ || $prototype =~ /DEFINE_EVENT/ || + $prototype =~ /DEFINE_SINGLE_EVENT/) + { + tracepoint_munge($file); + } + dump_function($prototype, $file); + reset_state(); + } +} + +sub process_proto_type($$) { + my $x = shift; + my $file = shift; + + $x =~ s@[\r\n]+@ @gos; # strip newlines/cr's. + $x =~ s@^\s+@@gos; # strip leading spaces + $x =~ s@\s+$@@gos; # strip trailing spaces + $x =~ s@\/\/.*$@@gos; # strip C99-style comments to end of line + + if ($x =~ /^#/) { + # To distinguish preprocessor directive from regular declaration later. + $x .= ";"; + } + + while (1) { + if ( $x =~ /([^\{\};]*)([\{\};])(.*)/ ) { + if( length $prototype ) { + $prototype .= " " + } + $prototype .= $1 . $2; + ($2 eq '{') && $brcount++; + ($2 eq '}') && $brcount--; + if (($2 eq ';') && ($brcount == 0)) { + dump_declaration($prototype, $file); + reset_state(); + last; + } + $x = $3; + } else { + $prototype .= $x; + last; + } + } +} + + +sub map_filename($) { + my $file; + my ($orig_file) = @_; + + if (defined($ENV{'SRCTREE'})) { + $file = "$ENV{'SRCTREE'}" . "/" . $orig_file; + } else { + $file = $orig_file; + } + + return $file; +} + +sub process_export_file($) { + my ($orig_file) = @_; + my $file = map_filename($orig_file); + + if (!open(IN,"<$file")) { + print STDERR "Error: Cannot open file $file\n"; + ++$errors; + return; + } + + while (<IN>) { + if (/$export_symbol/) { + next if (defined($nosymbol_table{$2})); + $function_table{$2} = 1; + } + if (/$export_symbol_ns/) { + next if (defined($nosymbol_table{$2})); + $function_table{$2} = 1; + } + } + + close(IN); +} + +# +# Parsers for the various processing states. +# +# STATE_NORMAL: looking for the /** to begin everything. +# +sub process_normal() { + if (/$doc_start/o) { + $state = STATE_NAME; # next line is always the function name + $declaration_start_line = $. + 1; + } +} + +# +# STATE_NAME: Looking for the "name - description" line +# +sub process_name($$) { + my $file = shift; + my $descr; + + if (/$doc_block/o) { + $state = STATE_DOCBLOCK; + $contents = ""; + $new_start_line = $.; + + if ( $1 eq "" ) { + $section = $section_intro; + } else { + $section = $1; + } + } elsif (/$doc_decl/o) { + $identifier = $1; + my $is_kernel_comment = 0; + my $decl_start = qr{$doc_com}; + # test for pointer declaration type, foo * bar() - desc + my $fn_type = qr{\w+\s*\*\s*}; + my $parenthesis = qr{\(\w*\)}; + my $decl_end = qr{[-:].*}; + if (/^$decl_start([\w\s]+?)$parenthesis?\s*$decl_end?$/) { + $identifier = $1; + } + if ($identifier =~ m/^(struct|union|enum|typedef)\b\s*(\S*)/) { + $decl_type = $1; + $identifier = $2; + $is_kernel_comment = 1; + } + # Look for foo() or static void foo() - description; or misspelt + # identifier + elsif (/^$decl_start$fn_type?(\w+)\s*$parenthesis?\s*$decl_end?$/ || + /^$decl_start$fn_type?(\w+[^-:]*)$parenthesis?\s*$decl_end$/) { + $identifier = $1; + $decl_type = 'function'; + $identifier =~ s/^define\s+//; + $is_kernel_comment = 1; + } + $identifier =~ s/\s+$//; + + $state = STATE_BODY; + # if there's no @param blocks need to set up default section + # here + $contents = ""; + $section = $section_default; + $new_start_line = $. + 1; + if (/[-:](.*)/) { + # strip leading/trailing/multiple spaces + $descr= $1; + $descr =~ s/^\s*//; + $descr =~ s/\s*$//; + $descr =~ s/\s+/ /g; + $declaration_purpose = $descr; + $state = STATE_BODY_MAYBE; + } else { + $declaration_purpose = ""; + } + + if (!$is_kernel_comment) { + emit_warning("${file}:$.", "This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst\n$_"); + $state = STATE_NORMAL; + } + + if (($declaration_purpose eq "") && $Wshort_desc) { + emit_warning("${file}:$.", "missing initial short description on line:\n$_"); + } + + if ($identifier eq "" && $decl_type ne "enum") { + emit_warning("${file}:$.", "wrong kernel-doc identifier on line:\n$_"); + $state = STATE_NORMAL; + } + + if ($verbose) { + print STDERR "${file}:$.: info: Scanning doc for $decl_type $identifier\n"; + } + } else { + emit_warning("${file}:$.", "Cannot understand $_ on line $. - I thought it was a doc line\n"); + $state = STATE_NORMAL; + } +} + + +# +# STATE_BODY and STATE_BODY_MAYBE: the bulk of a kerneldoc comment. +# +sub process_body($$) { + my $file = shift; + + if ($state == STATE_BODY_WITH_BLANK_LINE && /^\s*\*\s?\S/) { + dump_section($file, $section, $contents); + $section = $section_default; + $new_start_line = $.; + $contents = ""; + } + + if (/$doc_sect/i) { # case insensitive for supported section names + $newsection = $1; + $newcontents = $2; + + # map the supported section names to the canonical names + if ($newsection =~ m/^description$/i) { + $newsection = $section_default; + } elsif ($newsection =~ m/^context$/i) { + $newsection = $section_context; + } elsif ($newsection =~ m/^returns?$/i) { + $newsection = $section_return; + } elsif ($newsection =~ m/^\@return$/) { + # special: @return is a section, not a param description + $newsection = $section_return; + } + + if (($contents ne "") && ($contents ne "\n")) { + dump_section($file, $section, $contents); + $section = $section_default; + } + + $state = STATE_BODY; + $contents = $newcontents; + $new_start_line = $.; + while (substr($contents, 0, 1) eq " ") { + $contents = substr($contents, 1); + } + if ($contents ne "") { + $contents .= "\n"; + } + $section = $newsection; + $leading_space = undef; + } elsif (/$doc_end/) { + if (($contents ne "") && ($contents ne "\n")) { + dump_section($file, $section, $contents); + $section = $section_default; + $contents = ""; + } + # look for doc_com + <text> + doc_end: + if ($_ =~ m'\s*\*\s*[a-zA-Z_0-9:\.]+\*/') { + emit_warning("${file}:$.", "suspicious ending line: $_"); + } + + $prototype = ""; + $state = STATE_PROTO; + $brcount = 0; + $new_start_line = $. + 1; + } elsif (/$doc_content/) { + if ($1 eq "") { + if ($section eq $section_context) { + dump_section($file, $section, $contents); + $section = $section_default; + $contents = ""; + $new_start_line = $.; + $state = STATE_BODY; + } else { + if ($section ne $section_default) { + $state = STATE_BODY_WITH_BLANK_LINE; + } else { + $state = STATE_BODY; + } + $contents .= "\n"; + } + } elsif ($state == STATE_BODY_MAYBE) { + # Continued declaration purpose + chomp($declaration_purpose); + $declaration_purpose .= " " . $1; + $declaration_purpose =~ s/\s+/ /g; + } else { + my $cont = $1; + if ($section =~ m/^@/ || $section eq $section_context) { + if (!defined $leading_space) { + if ($cont =~ m/^(\s+)/) { + $leading_space = $1; + } else { + $leading_space = ""; + } + } + $cont =~ s/^$leading_space//; + } + $contents .= $cont . "\n"; + } + } else { + # i dont know - bad line? ignore. + emit_warning("${file}:$.", "bad line: $_"); + } +} + + +# +# STATE_PROTO: reading a function/whatever prototype. +# +sub process_proto($$) { + my $file = shift; + + if (/$doc_inline_oneline/) { + $section = $1; + $contents = $2; + if ($contents ne "") { + $contents .= "\n"; + dump_section($file, $section, $contents); + $section = $section_default; + $contents = ""; + } + } elsif (/$doc_inline_start/) { + $state = STATE_INLINE; + $inline_doc_state = STATE_INLINE_NAME; + } elsif ($decl_type eq 'function') { + process_proto_function($_, $file); + } else { + process_proto_type($_, $file); + } +} + +# +# STATE_DOCBLOCK: within a DOC: block. +# +sub process_docblock($$) { + my $file = shift; + + if (/$doc_end/) { + dump_doc_section($file, $section, $contents); + $section = $section_default; + $contents = ""; + $function = ""; + %parameterdescs = (); + %parametertypes = (); + @parameterlist = (); + %sections = (); + @sectionlist = (); + $prototype = ""; + $state = STATE_NORMAL; + } elsif (/$doc_content/) { + if ( $1 eq "" ) { + $contents .= $blankline; + } else { + $contents .= $1 . "\n"; + } + } +} + +# +# STATE_INLINE: docbook comments within a prototype. +# +sub process_inline($$) { + my $file = shift; + + # First line (state 1) needs to be a @parameter + if ($inline_doc_state == STATE_INLINE_NAME && /$doc_inline_sect/o) { + $section = $1; + $contents = $2; + $new_start_line = $.; + if ($contents ne "") { + while (substr($contents, 0, 1) eq " ") { + $contents = substr($contents, 1); + } + $contents .= "\n"; + } + $inline_doc_state = STATE_INLINE_TEXT; + # Documentation block end */ + } elsif (/$doc_inline_end/) { + if (($contents ne "") && ($contents ne "\n")) { + dump_section($file, $section, $contents); + $section = $section_default; + $contents = ""; + } + $state = STATE_PROTO; + $inline_doc_state = STATE_INLINE_NA; + # Regular text + } elsif (/$doc_content/) { + if ($inline_doc_state == STATE_INLINE_TEXT) { + $contents .= $1 . "\n"; + # nuke leading blank lines + if ($contents =~ /^\s*$/) { + $contents = ""; + } + } elsif ($inline_doc_state == STATE_INLINE_NAME) { + $inline_doc_state = STATE_INLINE_ERROR; + emit_warning("${file}:$.", "Incorrect use of kernel-doc format: $_"); + } + } +} + + +sub process_file($) { + my $file; + my ($orig_file) = @_; + + $file = map_filename($orig_file); + + if (!open(IN_FILE,"<$file")) { + print STDERR "Error: Cannot open file $file\n"; + ++$errors; + return; + } + + $. = 1; + + $section_counter = 0; + while (<IN_FILE>) { + while (!/^ \*/ && s/\\\s*$//) { + $_ .= <IN_FILE>; + } + # Replace tabs by spaces + while ($_ =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}; + # Hand this line to the appropriate state handler + if ($state == STATE_NORMAL) { + process_normal(); + } elsif ($state == STATE_NAME) { + process_name($file, $_); + } elsif ($state == STATE_BODY || $state == STATE_BODY_MAYBE || + $state == STATE_BODY_WITH_BLANK_LINE) { + process_body($file, $_); + } elsif ($state == STATE_INLINE) { # scanning for inline parameters + process_inline($file, $_); + } elsif ($state == STATE_PROTO) { + process_proto($file, $_); + } elsif ($state == STATE_DOCBLOCK) { + process_docblock($file, $_); + } + } + + # Make sure we got something interesting. + if (!$section_counter && $output_mode ne "none") { + if ($output_selection == OUTPUT_INCLUDE) { + emit_warning("${file}:1", "'$_' not found\n") + for keys %function_table; + } else { + emit_warning("${file}:1", "no structured comments found\n"); + } + } + close IN_FILE; +} + +$kernelversion = get_kernel_version(); + +# generate a sequence of code that will splice in highlighting information +# using the s// operator. +for (my $k = 0; $k < @highlights; $k++) { + my $pattern = $highlights[$k][0]; + my $result = $highlights[$k][1]; +# print STDERR "scanning pattern:$pattern, highlight:($result)\n"; + $dohighlight .= "\$contents =~ s:$pattern:$result:gs;\n"; +} + +if ($output_selection == OUTPUT_EXPORTED || + $output_selection == OUTPUT_INTERNAL) { + + push(@export_file_list, @ARGV); + + foreach (@export_file_list) { + chomp; + process_export_file($_); + } +} + +foreach (@ARGV) { + chomp; + process_file($_); +} +if ($verbose && $errors) { + print STDERR "$errors errors\n"; +} +if ($verbose && $warnings) { + print STDERR "$warnings warnings\n"; +} + +if ($Werror && $warnings) { + print STDERR "$warnings warnings as Errors\n"; + exit($warnings); +} else { + exit($output_mode eq "none" ? 0 : $errors) +} + +__END__ + +=head1 OPTIONS + +=head2 Output format selection (mutually exclusive): + +=over 8 + +=item -man + +Output troff manual page format. + +=item -rst + +Output reStructuredText format. This is the default. + +=item -none + +Do not output documentation, only warnings. + +=back + +=head2 Output format modifiers + +=head3 reStructuredText only + +=head2 Output selection (mutually exclusive): + +=over 8 + +=item -export + +Only output documentation for the symbols that have been exported using +EXPORT_SYMBOL() and related macros in any input FILE or -export-file FILE. + +=item -internal + +Only output documentation for the symbols that have NOT been exported using +EXPORT_SYMBOL() and related macros in any input FILE or -export-file FILE. + +=item -function NAME + +Only output documentation for the given function or DOC: section title. +All other functions and DOC: sections are ignored. + +May be specified multiple times. + +=item -nosymbol NAME + +Exclude the specified symbol from the output documentation. + +May be specified multiple times. + +=back + +=head2 Output selection modifiers: + +=over 8 + +=item -no-doc-sections + +Do not output DOC: sections. + +=item -export-file FILE + +Specify an additional FILE in which to look for EXPORT_SYMBOL information. + +To be used with -export or -internal. + +May be specified multiple times. + +=back + +=head3 reStructuredText only + +=over 8 + +=item -enable-lineno + +Enable output of .. LINENO lines. + +=back + +=head2 Other parameters: + +=over 8 + +=item -h, -help + +Print this help. + +=item -v + +Verbose output, more warnings and other information. + +=item -Werror + +Treat warnings as errors. + +=back + +=cut diff --git a/scripts/kernel-doc.py b/scripts/kernel-doc.py new file mode 100755 index 000000000000..12ae66f40bd7 --- /dev/null +++ b/scripts/kernel-doc.py @@ -0,0 +1,315 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# +# pylint: disable=C0103,R0915 +# +# Converted from the kernel-doc script originally written in Perl +# under GPLv2, copyrighted since 1998 by the following authors: +# +# Aditya Srivastava <yashsri421@gmail.com> +# Akira Yokosawa <akiyks@gmail.com> +# Alexander A. Klimov <grandmaster@al2klimov.de> +# Alexander Lobakin <aleksander.lobakin@intel.com> +# André Almeida <andrealmeid@igalia.com> +# Andy Shevchenko <andriy.shevchenko@linux.intel.com> +# Anna-Maria Behnsen <anna-maria@linutronix.de> +# Armin Kuster <akuster@mvista.com> +# Bart Van Assche <bart.vanassche@sandisk.com> +# Ben Hutchings <ben@decadent.org.uk> +# Borislav Petkov <bbpetkov@yahoo.de> +# Chen-Yu Tsai <wenst@chromium.org> +# Coco Li <lixiaoyan@google.com> +# Conchúr Navid <conchur@web.de> +# Daniel Santos <daniel.santos@pobox.com> +# Danilo Cesar Lemes de Paula <danilo.cesar@collabora.co.uk> +# Dan Luedtke <mail@danrl.de> +# Donald Hunter <donald.hunter@gmail.com> +# Gabriel Krisman Bertazi <krisman@collabora.co.uk> +# Greg Kroah-Hartman <gregkh@linuxfoundation.org> +# Harvey Harrison <harvey.harrison@gmail.com> +# Horia Geanta <horia.geanta@freescale.com> +# Ilya Dryomov <idryomov@gmail.com> +# Jakub Kicinski <kuba@kernel.org> +# Jani Nikula <jani.nikula@intel.com> +# Jason Baron <jbaron@redhat.com> +# Jason Gunthorpe <jgg@nvidia.com> +# Jérémy Bobbio <lunar@debian.org> +# Johannes Berg <johannes.berg@intel.com> +# Johannes Weiner <hannes@cmpxchg.org> +# Jonathan Cameron <Jonathan.Cameron@huawei.com> +# Jonathan Corbet <corbet@lwn.net> +# Jonathan Neuschäfer <j.neuschaefer@gmx.net> +# Kamil Rytarowski <n54@gmx.com> +# Kees Cook <kees@kernel.org> +# Laurent Pinchart <laurent.pinchart@ideasonboard.com> +# Levin, Alexander (Sasha Levin) <alexander.levin@verizon.com> +# Linus Torvalds <torvalds@linux-foundation.org> +# Lucas De Marchi <lucas.demarchi@profusion.mobi> +# Mark Rutland <mark.rutland@arm.com> +# Markus Heiser <markus.heiser@darmarit.de> +# Martin Waitz <tali@admingilde.org> +# Masahiro Yamada <masahiroy@kernel.org> +# Matthew Wilcox <willy@infradead.org> +# Mauro Carvalho Chehab <mchehab+huawei@kernel.org> +# Michal Wajdeczko <michal.wajdeczko@intel.com> +# Michael Zucchi +# Mike Rapoport <rppt@linux.ibm.com> +# Niklas Söderlund <niklas.soderlund@corigine.com> +# Nishanth Menon <nm@ti.com> +# Paolo Bonzini <pbonzini@redhat.com> +# Pavan Kumar Linga <pavan.kumar.linga@intel.com> +# Pavel Pisa <pisa@cmp.felk.cvut.cz> +# Peter Maydell <peter.maydell@linaro.org> +# Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> +# Randy Dunlap <rdunlap@infradead.org> +# Richard Kennedy <richard@rsk.demon.co.uk> +# Rich Walker <rw@shadow.org.uk> +# Rolf Eike Beer <eike-kernel@sf-tec.de> +# Sakari Ailus <sakari.ailus@linux.intel.com> +# Silvio Fricke <silvio.fricke@gmail.com> +# Simon Huggins +# Tim Waugh <twaugh@redhat.com> +# Tomasz Warniełło <tomasz.warniello@gmail.com> +# Utkarsh Tripathi <utripathi2002@gmail.com> +# valdis.kletnieks@vt.edu <valdis.kletnieks@vt.edu> +# Vegard Nossum <vegard.nossum@oracle.com> +# Will Deacon <will.deacon@arm.com> +# Yacine Belkadi <yacine.belkadi.1@gmail.com> +# Yujie Liu <yujie.liu@intel.com> + +""" +kernel_doc +========== + +Print formatted kernel documentation to stdout + +Read C language source or header FILEs, extract embedded +documentation comments, and print formatted documentation +to standard output. + +The documentation comments are identified by the "/**" +opening comment mark. + +See Documentation/doc-guide/kernel-doc.rst for the +documentation comment syntax. +""" + +import argparse +import logging +import os +import sys + +# Import Python modules + +LIB_DIR = "lib/kdoc" +SRC_DIR = os.path.dirname(os.path.realpath(__file__)) + +sys.path.insert(0, os.path.join(SRC_DIR, LIB_DIR)) + +from kdoc_files import KernelFiles # pylint: disable=C0413 +from kdoc_output import RestFormat, ManFormat # pylint: disable=C0413 + +DESC = """ +Read C language source or header FILEs, extract embedded documentation comments, +and print formatted documentation to standard output. + +The documentation comments are identified by the "/**" opening comment mark. + +See Documentation/doc-guide/kernel-doc.rst for the documentation comment syntax. +""" + +EXPORT_FILE_DESC = """ +Specify an additional FILE in which to look for EXPORT_SYMBOL information. + +May be used multiple times. +""" + +EXPORT_DESC = """ +Only output documentation for the symbols that have been +exported using EXPORT_SYMBOL() and related macros in any input +FILE or -export-file FILE. +""" + +INTERNAL_DESC = """ +Only output documentation for the symbols that have NOT been +exported using EXPORT_SYMBOL() and related macros in any input +FILE or -export-file FILE. +""" + +FUNCTION_DESC = """ +Only output documentation for the given function or DOC: section +title. All other functions and DOC: sections are ignored. + +May be used multiple times. +""" + +NOSYMBOL_DESC = """ +Exclude the specified symbol from the output documentation. + +May be used multiple times. +""" + +FILES_DESC = """ +Header and C source files to be parsed. +""" + +WARN_CONTENTS_BEFORE_SECTIONS_DESC = """ +Warns if there are contents before sections (deprecated). + +This option is kept just for backward-compatibility, but it does nothing, +neither here nor at the original Perl script. +""" + + +class MsgFormatter(logging.Formatter): + """Helper class to format warnings on a similar way to kernel-doc.pl""" + + def format(self, record): + record.levelname = record.levelname.capitalize() + return logging.Formatter.format(self, record) + +def main(): + """Main program""" + + parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter, + description=DESC) + + # Normal arguments + + parser.add_argument("-v", "-verbose", "--verbose", action="store_true", + help="Verbose output, more warnings and other information.") + + parser.add_argument("-d", "-debug", "--debug", action="store_true", + help="Enable debug messages") + + parser.add_argument("-M", "-modulename", "--modulename", + default="Kernel API", + help="Allow setting a module name at the output.") + + parser.add_argument("-l", "-enable-lineno", "--enable_lineno", + action="store_true", + help="Enable line number output (only in ReST mode)") + + # Arguments to control the warning behavior + + parser.add_argument("-Wreturn", "--wreturn", action="store_true", + help="Warns about the lack of a return markup on functions.") + + parser.add_argument("-Wshort-desc", "-Wshort-description", "--wshort-desc", + action="store_true", + help="Warns if initial short description is missing") + + parser.add_argument("-Wcontents-before-sections", + "--wcontents-before-sections", action="store_true", + help=WARN_CONTENTS_BEFORE_SECTIONS_DESC) + + parser.add_argument("-Wall", "--wall", action="store_true", + help="Enable all types of warnings") + + parser.add_argument("-Werror", "--werror", action="store_true", + help="Treat warnings as errors.") + + parser.add_argument("-export-file", "--export-file", action='append', + help=EXPORT_FILE_DESC) + + # Output format mutually-exclusive group + + out_group = parser.add_argument_group("Output format selection (mutually exclusive)") + + out_fmt = out_group.add_mutually_exclusive_group() + + out_fmt.add_argument("-m", "-man", "--man", action="store_true", + help="Output troff manual page format.") + out_fmt.add_argument("-r", "-rst", "--rst", action="store_true", + help="Output reStructuredText format (default).") + out_fmt.add_argument("-N", "-none", "--none", action="store_true", + help="Do not output documentation, only warnings.") + + # Output selection mutually-exclusive group + + sel_group = parser.add_argument_group("Output selection (mutually exclusive)") + sel_mut = sel_group.add_mutually_exclusive_group() + + sel_mut.add_argument("-e", "-export", "--export", action='store_true', + help=EXPORT_DESC) + + sel_mut.add_argument("-i", "-internal", "--internal", action='store_true', + help=INTERNAL_DESC) + + sel_mut.add_argument("-s", "-function", "--symbol", action='append', + help=FUNCTION_DESC) + + # Those are valid for all 3 types of filter + parser.add_argument("-n", "-nosymbol", "--nosymbol", action='append', + help=NOSYMBOL_DESC) + + parser.add_argument("-D", "-no-doc-sections", "--no-doc-sections", + action='store_true', help="Don't outputt DOC sections") + + parser.add_argument("files", metavar="FILE", + nargs="+", help=FILES_DESC) + + args = parser.parse_args() + + if args.wall: + args.wreturn = True + args.wshort_desc = True + args.wcontents_before_sections = True + + logger = logging.getLogger() + + if not args.debug: + logger.setLevel(logging.INFO) + else: + logger.setLevel(logging.DEBUG) + + formatter = MsgFormatter('%(levelname)s: %(message)s') + + handler = logging.StreamHandler() + handler.setFormatter(formatter) + + logger.addHandler(handler) + + if args.man: + out_style = ManFormat(modulename=args.modulename) + elif args.none: + out_style = None + else: + out_style = RestFormat() + + kfiles = KernelFiles(verbose=args.verbose, + out_style=out_style, werror=args.werror, + wreturn=args.wreturn, wshort_desc=args.wshort_desc, + wcontents_before_sections=args.wcontents_before_sections) + + kfiles.parse(args.files, export_file=args.export_file) + + for t in kfiles.msg(enable_lineno=args.enable_lineno, export=args.export, + internal=args.internal, symbol=args.symbol, + nosymbol=args.nosymbol, export_file=args.export_file, + no_doc_sections=args.no_doc_sections): + msg = t[1] + if msg: + print(msg) + + error_count = kfiles.errors + if not error_count: + sys.exit(0) + + if args.werror: + print(f"{error_count} warnings as errors") + sys.exit(error_count) + + if args.verbose: + print(f"{error_count} errors") + + if args.none: + sys.exit(0) + + sys.exit(error_count) + + +# Call main method +if __name__ == "__main__": + main() diff --git a/scripts/lib/abi/abi_parser.py b/scripts/lib/abi/abi_parser.py new file mode 100644 index 000000000000..66a738013ce1 --- /dev/null +++ b/scripts/lib/abi/abi_parser.py @@ -0,0 +1,628 @@ +#!/usr/bin/env python3 +# pylint: disable=R0902,R0903,R0911,R0912,R0913,R0914,R0915,R0917,C0302 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# SPDX-License-Identifier: GPL-2.0 + +""" +Parse ABI documentation and produce results from it. +""" + +from argparse import Namespace +import logging +import os +import re + +from pprint import pformat +from random import randrange, seed + +# Import Python modules + +from helpers import AbiDebug, ABI_DIR + + +class AbiParser: + """Main class to parse ABI files""" + + TAGS = r"(what|where|date|kernelversion|contact|description|users)" + XREF = r"(?:^|\s|\()(\/(?:sys|config|proc|dev|kvd)\/[^,.:;\)\s]+)(?:[,.:;\)\s]|\Z)" + + def __init__(self, directory, logger=None, + enable_lineno=False, show_warnings=True, debug=0): + """Stores arguments for the class and initialize class vars""" + + self.directory = directory + self.enable_lineno = enable_lineno + self.show_warnings = show_warnings + self.debug = debug + + if not logger: + self.log = logging.getLogger("get_abi") + else: + self.log = logger + + self.data = {} + self.what_symbols = {} + self.file_refs = {} + self.what_refs = {} + + # Ignore files that contain such suffixes + self.ignore_suffixes = (".rej", ".org", ".orig", ".bak", "~") + + # Regular expressions used on parser + self.re_abi_dir = re.compile(r"(.*)" + ABI_DIR) + self.re_tag = re.compile(r"(\S+)(:\s*)(.*)", re.I) + self.re_valid = re.compile(self.TAGS) + self.re_start_spc = re.compile(r"(\s*)(\S.*)") + self.re_whitespace = re.compile(r"^\s+") + + # Regular used on print + self.re_what = re.compile(r"(\/?(?:[\w\-]+\/?){1,2})") + self.re_escape = re.compile(r"([\.\x01-\x08\x0e-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])") + self.re_unprintable = re.compile(r"([\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\xff]+)") + self.re_title_mark = re.compile(r"\n[\-\*\=\^\~]+\n") + self.re_doc = re.compile(r"Documentation/(?!devicetree)(\S+)\.rst") + self.re_abi = re.compile(r"(Documentation/ABI/)([\w\/\-]+)") + self.re_xref_node = re.compile(self.XREF) + + def warn(self, fdata, msg, extra=None): + """Displays a parse error if warning is enabled""" + + if not self.show_warnings: + return + + msg = f"{fdata.fname}:{fdata.ln}: {msg}" + if extra: + msg += "\n\t\t" + extra + + self.log.warning(msg) + + def add_symbol(self, what, fname, ln=None, xref=None): + """Create a reference table describing where each 'what' is located""" + + if what not in self.what_symbols: + self.what_symbols[what] = {"file": {}} + + if fname not in self.what_symbols[what]["file"]: + self.what_symbols[what]["file"][fname] = [] + + if ln and ln not in self.what_symbols[what]["file"][fname]: + self.what_symbols[what]["file"][fname].append(ln) + + if xref: + self.what_symbols[what]["xref"] = xref + + def _parse_line(self, fdata, line): + """Parse a single line of an ABI file""" + + new_what = False + new_tag = False + content = None + + match = self.re_tag.match(line) + if match: + new = match.group(1).lower() + sep = match.group(2) + content = match.group(3) + + match = self.re_valid.search(new) + if match: + new_tag = match.group(1) + else: + if fdata.tag == "description": + # New "tag" is actually part of description. + # Don't consider it a tag + new_tag = False + elif fdata.tag != "": + self.warn(fdata, f"tag '{fdata.tag}' is invalid", line) + + if new_tag: + # "where" is Invalid, but was a common mistake. Warn if found + if new_tag == "where": + self.warn(fdata, "tag 'Where' is invalid. Should be 'What:' instead") + new_tag = "what" + + if new_tag == "what": + fdata.space = None + + if content not in self.what_symbols: + self.add_symbol(what=content, fname=fdata.fname, ln=fdata.ln) + + if fdata.tag == "what": + fdata.what.append(content.strip("\n")) + else: + if fdata.key: + if "description" not in self.data.get(fdata.key, {}): + self.warn(fdata, f"{fdata.key} doesn't have a description") + + for w in fdata.what: + self.add_symbol(what=w, fname=fdata.fname, + ln=fdata.what_ln, xref=fdata.key) + + fdata.label = content + new_what = True + + key = "abi_" + content.lower() + fdata.key = self.re_unprintable.sub("_", key).strip("_") + + # Avoid duplicated keys but using a defined seed, to make + # the namespace identical if there aren't changes at the + # ABI symbols + seed(42) + + while fdata.key in self.data: + char = randrange(0, 51) + ord("A") + if char > ord("Z"): + char += ord("a") - ord("Z") - 1 + + fdata.key += chr(char) + + if fdata.key and fdata.key not in self.data: + self.data[fdata.key] = { + "what": [content], + "file": [fdata.file_ref], + "path": fdata.ftype, + "line_no": fdata.ln, + } + + fdata.what = self.data[fdata.key]["what"] + + self.what_refs[content] = fdata.key + fdata.tag = new_tag + fdata.what_ln = fdata.ln + + if fdata.nametag["what"]: + t = (content, fdata.key) + if t not in fdata.nametag["symbols"]: + fdata.nametag["symbols"].append(t) + + return + + if fdata.tag and new_tag: + fdata.tag = new_tag + + if new_what: + fdata.label = "" + + if "description" in self.data[fdata.key]: + self.data[fdata.key]["description"] += "\n\n" + + if fdata.file_ref not in self.data[fdata.key]["file"]: + self.data[fdata.key]["file"].append(fdata.file_ref) + + if self.debug == AbiDebug.WHAT_PARSING: + self.log.debug("what: %s", fdata.what) + + if not fdata.what: + self.warn(fdata, "'What:' should come first:", line) + return + + if new_tag == "description": + fdata.space = None + + if content: + sep = sep.replace(":", " ") + + c = " " * len(new_tag) + sep + content + c = c.expandtabs() + + match = self.re_start_spc.match(c) + if match: + # Preserve initial spaces for the first line + fdata.space = match.group(1) + content = match.group(2) + "\n" + + self.data[fdata.key][fdata.tag] = content + + return + + # Store any contents before tags at the database + if not fdata.tag and "what" in fdata.nametag: + fdata.nametag["description"] += line + return + + if fdata.tag == "description": + content = line.expandtabs() + + if self.re_whitespace.sub("", content) == "": + self.data[fdata.key][fdata.tag] += "\n" + return + + if fdata.space is None: + match = self.re_start_spc.match(content) + if match: + # Preserve initial spaces for the first line + fdata.space = match.group(1) + + content = match.group(2) + "\n" + else: + if content.startswith(fdata.space): + content = content[len(fdata.space):] + + else: + fdata.space = "" + + if fdata.tag == "what": + w = content.strip("\n") + if w: + self.data[fdata.key][fdata.tag].append(w) + else: + self.data[fdata.key][fdata.tag] += content + return + + content = line.strip() + if fdata.tag: + if fdata.tag == "what": + w = content.strip("\n") + if w: + self.data[fdata.key][fdata.tag].append(w) + else: + self.data[fdata.key][fdata.tag] += "\n" + content.rstrip("\n") + return + + # Everything else is error + if content: + self.warn(fdata, "Unexpected content", line) + + def parse_readme(self, nametag, fname): + """Parse ABI README file""" + + nametag["what"] = ["Introduction"] + nametag["path"] = "README" + with open(fname, "r", encoding="utf8", errors="backslashreplace") as fp: + for line in fp: + match = self.re_tag.match(line) + if match: + new = match.group(1).lower() + + match = self.re_valid.search(new) + if match: + nametag["description"] += "\n:" + line + continue + + nametag["description"] += line + + def parse_file(self, fname, path, basename): + """Parse a single file""" + + ref = f"abi_file_{path}_{basename}" + ref = self.re_unprintable.sub("_", ref).strip("_") + + # Store per-file state into a namespace variable. This will be used + # by the per-line parser state machine and by the warning function. + fdata = Namespace + + fdata.fname = fname + fdata.name = basename + + pos = fname.find(ABI_DIR) + if pos > 0: + f = fname[pos:] + else: + f = fname + + fdata.file_ref = (f, ref) + self.file_refs[f] = ref + + fdata.ln = 0 + fdata.what_ln = 0 + fdata.tag = "" + fdata.label = "" + fdata.what = [] + fdata.key = None + fdata.xrefs = None + fdata.space = None + fdata.ftype = path.split("/")[0] + + fdata.nametag = {} + fdata.nametag["what"] = [f"ABI file {path}/{basename}"] + fdata.nametag["type"] = "File" + fdata.nametag["path"] = fdata.ftype + fdata.nametag["file"] = [fdata.file_ref] + fdata.nametag["line_no"] = 1 + fdata.nametag["description"] = "" + fdata.nametag["symbols"] = [] + + self.data[ref] = fdata.nametag + + if self.debug & AbiDebug.WHAT_OPEN: + self.log.debug("Opening file %s", fname) + + if basename == "README": + self.parse_readme(fdata.nametag, fname) + return + + with open(fname, "r", encoding="utf8", errors="backslashreplace") as fp: + for line in fp: + fdata.ln += 1 + + self._parse_line(fdata, line) + + if "description" in fdata.nametag: + fdata.nametag["description"] = fdata.nametag["description"].lstrip("\n") + + if fdata.key: + if "description" not in self.data.get(fdata.key, {}): + self.warn(fdata, f"{fdata.key} doesn't have a description") + + for w in fdata.what: + self.add_symbol(what=w, fname=fname, xref=fdata.key) + + def _parse_abi(self, root=None): + """Internal function to parse documentation ABI recursively""" + + if not root: + root = self.directory + + with os.scandir(root) as obj: + for entry in obj: + name = os.path.join(root, entry.name) + + if entry.is_dir(): + self._parse_abi(name) + continue + + if not entry.is_file(): + continue + + basename = os.path.basename(name) + + if basename.startswith("."): + continue + + if basename.endswith(self.ignore_suffixes): + continue + + path = self.re_abi_dir.sub("", os.path.dirname(name)) + + self.parse_file(name, path, basename) + + def parse_abi(self, root=None): + """Parse documentation ABI""" + + self._parse_abi(root) + + if self.debug & AbiDebug.DUMP_ABI_STRUCTS: + self.log.debug(pformat(self.data)) + + def desc_txt(self, desc): + """Print description as found inside ABI files""" + + desc = desc.strip(" \t\n") + + return desc + "\n\n" + + def xref(self, fname): + """ + Converts a Documentation/ABI + basename into a ReST cross-reference + """ + + xref = self.file_refs.get(fname) + if not xref: + return None + else: + return xref + + def desc_rst(self, desc): + """Enrich ReST output by creating cross-references""" + + # Remove title markups from the description + # Having titles inside ABI files will only work if extra + # care would be taken in order to strictly follow the same + # level order for each markup. + desc = self.re_title_mark.sub("\n\n", "\n" + desc) + desc = desc.rstrip(" \t\n").lstrip("\n") + + # Python's regex performance for non-compiled expressions is a lot + # than Perl, as Perl automatically caches them at their + # first usage. Here, we'll need to do the same, as otherwise the + # performance penalty is be high + + new_desc = "" + for d in desc.split("\n"): + if d == "": + new_desc += "\n" + continue + + # Use cross-references for doc files where needed + d = self.re_doc.sub(r":doc:`/\1`", d) + + # Use cross-references for ABI generated docs where needed + matches = self.re_abi.findall(d) + for m in matches: + abi = m[0] + m[1] + + xref = self.file_refs.get(abi) + if not xref: + # This may happen if ABI is on a separate directory, + # like parsing ABI testing and symbol is at stable. + # The proper solution is to move this part of the code + # for it to be inside sphinx/kernel_abi.py + self.log.info("Didn't find ABI reference for '%s'", abi) + else: + new = self.re_escape.sub(r"\\\1", m[1]) + d = re.sub(fr"\b{abi}\b", f":ref:`{new} <{xref}>`", d) + + # Seek for cross reference symbols like /sys/... + # Need to be careful to avoid doing it on a code block + if d[0] not in [" ", "\t"]: + matches = self.re_xref_node.findall(d) + for m in matches: + # Finding ABI here is more complex due to wildcards + xref = self.what_refs.get(m) + if xref: + new = self.re_escape.sub(r"\\\1", m) + d = re.sub(fr"\b{m}\b", f":ref:`{new} <{xref}>`", d) + + new_desc += d + "\n" + + return new_desc + "\n\n" + + def doc(self, output_in_txt=False, show_symbols=True, show_file=True, + filter_path=None): + """Print ABI at stdout""" + + part = None + for key, v in sorted(self.data.items(), + key=lambda x: (x[1].get("type", ""), + x[1].get("what"))): + + wtype = v.get("type", "Symbol") + file_ref = v.get("file") + names = v.get("what", [""]) + + if wtype == "File": + if not show_file: + continue + else: + if not show_symbols: + continue + + if filter_path: + if v.get("path") != filter_path: + continue + + msg = "" + + if wtype != "File": + cur_part = names[0] + if cur_part.find("/") >= 0: + match = self.re_what.match(cur_part) + if match: + symbol = match.group(1).rstrip("/") + cur_part = "Symbols under " + symbol + + if cur_part and cur_part != part: + part = cur_part + msg += part + "\n"+ "-" * len(part) +"\n\n" + + msg += f".. _{key}:\n\n" + + max_len = 0 + for i in range(0, len(names)): # pylint: disable=C0200 + names[i] = "**" + self.re_escape.sub(r"\\\1", names[i]) + "**" + + max_len = max(max_len, len(names[i])) + + msg += "+-" + "-" * max_len + "-+\n" + for name in names: + msg += f"| {name}" + " " * (max_len - len(name)) + " |\n" + msg += "+-" + "-" * max_len + "-+\n" + msg += "\n" + + for ref in file_ref: + if wtype == "File": + msg += f".. _{ref[1]}:\n\n" + else: + base = os.path.basename(ref[0]) + msg += f"Defined on file :ref:`{base} <{ref[1]}>`\n\n" + + if wtype == "File": + msg += names[0] +"\n" + "-" * len(names[0]) +"\n\n" + + desc = v.get("description") + if not desc and wtype != "File": + msg += f"DESCRIPTION MISSING for {names[0]}\n\n" + + if desc: + if output_in_txt: + msg += self.desc_txt(desc) + else: + msg += self.desc_rst(desc) + + symbols = v.get("symbols") + if symbols: + msg += "Has the following ABI:\n\n" + + for w, label in symbols: + # Escape special chars from content + content = self.re_escape.sub(r"\\\1", w) + + msg += f"- :ref:`{content} <{label}>`\n\n" + + users = v.get("users") + if users and users.strip(" \t\n"): + users = users.strip("\n").replace('\n', '\n\t') + msg += f"Users:\n\t{users}\n\n" + + ln = v.get("line_no", 1) + + yield (msg, file_ref[0][0], ln) + + def check_issues(self): + """Warn about duplicated ABI entries""" + + for what, v in self.what_symbols.items(): + files = v.get("file") + if not files: + # Should never happen if the parser works properly + self.log.warning("%s doesn't have a file associated", what) + continue + + if len(files) == 1: + continue + + f = [] + for fname, lines in sorted(files.items()): + if not lines: + f.append(f"{fname}") + elif len(lines) == 1: + f.append(f"{fname}:{lines[0]}") + else: + m = fname + "lines " + m += ", ".join(str(x) for x in lines) + f.append(m) + + self.log.warning("%s is defined %d times: %s", what, len(f), "; ".join(f)) + + def search_symbols(self, expr): + """ Searches for ABI symbols """ + + regex = re.compile(expr, re.I) + + found_keys = 0 + for t in sorted(self.data.items(), key=lambda x: [0]): + v = t[1] + + wtype = v.get("type", "") + if wtype == "File": + continue + + for what in v.get("what", [""]): + if regex.search(what): + found_keys += 1 + + kernelversion = v.get("kernelversion", "").strip(" \t\n") + date = v.get("date", "").strip(" \t\n") + contact = v.get("contact", "").strip(" \t\n") + users = v.get("users", "").strip(" \t\n") + desc = v.get("description", "").strip(" \t\n") + + files = [] + for f in v.get("file", ()): + files.append(f[0]) + + what = str(found_keys) + ". " + what + title_tag = "-" * len(what) + + print(f"\n{what}\n{title_tag}\n") + + if kernelversion: + print(f"Kernel version:\t\t{kernelversion}") + + if date: + print(f"Date:\t\t\t{date}") + + if contact: + print(f"Contact:\t\t{contact}") + + if users: + print(f"Users:\t\t\t{users}") + + print("Defined on file(s):\t" + ", ".join(files)) + + if desc: + desc = desc.strip("\n") + print(f"\n{desc}\n") + + if not found_keys: + print(f"Regular expression /{expr}/ not found.") diff --git a/scripts/lib/abi/abi_regex.py b/scripts/lib/abi/abi_regex.py new file mode 100644 index 000000000000..8a57846cbc69 --- /dev/null +++ b/scripts/lib/abi/abi_regex.py @@ -0,0 +1,234 @@ +#!/usr/bin/env python3 +# xxpylint: disable=R0903 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# SPDX-License-Identifier: GPL-2.0 + +""" +Convert ABI what into regular expressions +""" + +import re +import sys + +from pprint import pformat + +from abi_parser import AbiParser +from helpers import AbiDebug + +class AbiRegex(AbiParser): + """Extends AbiParser to search ABI nodes with regular expressions""" + + # Escape only ASCII visible characters + escape_symbols = r"([\x21-\x29\x2b-\x2d\x3a-\x40\x5c\x60\x7b-\x7e])" + leave_others = "others" + + # Tuples with regular expressions to be compiled and replacement data + re_whats = [ + # Drop escape characters that might exist + (re.compile("\\\\"), ""), + + # Temporarily escape dot characters + (re.compile(r"\."), "\xf6"), + + # Temporarily change [0-9]+ type of patterns + (re.compile(r"\[0\-9\]\+"), "\xff"), + + # Temporarily change [\d+-\d+] type of patterns + (re.compile(r"\[0\-\d+\]"), "\xff"), + (re.compile(r"\[0:\d+\]"), "\xff"), + (re.compile(r"\[(\d+)\]"), "\xf4\\\\d+\xf5"), + + # Temporarily change [0-9] type of patterns + (re.compile(r"\[(\d)\-(\d)\]"), "\xf4\1-\2\xf5"), + + # Handle multiple option patterns + (re.compile(r"[\{\<\[]([\w_]+)(?:[,|]+([\w_]+)){1,}[\}\>\]]"), r"(\1|\2)"), + + # Handle wildcards + (re.compile(r"([^\/])\*"), "\\1\\\\w\xf7"), + (re.compile(r"/\*/"), "/.*/"), + (re.compile(r"/\xf6\xf6\xf6"), "/.*"), + (re.compile(r"\<[^\>]+\>"), "\\\\w\xf7"), + (re.compile(r"\{[^\}]+\}"), "\\\\w\xf7"), + (re.compile(r"\[[^\]]+\]"), "\\\\w\xf7"), + + (re.compile(r"XX+"), "\\\\w\xf7"), + (re.compile(r"([^A-Z])[XYZ]([^A-Z])"), "\\1\\\\w\xf7\\2"), + (re.compile(r"([^A-Z])[XYZ]$"), "\\1\\\\w\xf7"), + (re.compile(r"_[AB]_"), "_\\\\w\xf7_"), + + # Recover [0-9] type of patterns + (re.compile(r"\xf4"), "["), + (re.compile(r"\xf5"), "]"), + + # Remove duplicated spaces + (re.compile(r"\s+"), r" "), + + # Special case: drop comparison as in: + # What: foo = <something> + # (this happens on a few IIO definitions) + (re.compile(r"\s*\=.*$"), ""), + + # Escape all other symbols + (re.compile(escape_symbols), r"\\\1"), + (re.compile(r"\\\\"), r"\\"), + (re.compile(r"\\([\[\]\(\)\|])"), r"\1"), + (re.compile(r"(\d+)\\(-\d+)"), r"\1\2"), + + (re.compile(r"\xff"), r"\\d+"), + + # Special case: IIO ABI which a parenthesis. + (re.compile(r"sqrt(.*)"), r"sqrt(.*)"), + + # Simplify regexes with multiple .* + (re.compile(r"(?:\.\*){2,}"), ""), + + # Recover dot characters + (re.compile(r"\xf6"), "\\."), + # Recover plus characters + (re.compile(r"\xf7"), "+"), + ] + re_has_num = re.compile(r"\\d") + + # Symbol name after escape_chars that are considered a devnode basename + re_symbol_name = re.compile(r"(\w|\\[\.\-\:])+$") + + # List of popular group names to be skipped to minimize regex group size + # Use AbiDebug.SUBGROUP_SIZE to detect those + skip_names = set(["devices", "hwmon"]) + + def regex_append(self, what, new): + """ + Get a search group for a subset of regular expressions. + + As ABI may have thousands of symbols, using a for to search all + regular expressions is at least O(n^2). When there are wildcards, + the complexity increases substantially, eventually becoming exponential. + + To avoid spending too much time on them, use a logic to split + them into groups. The smaller the group, the better, as it would + mean that searches will be confined to a small number of regular + expressions. + + The conversion to a regex subset is tricky, as we need something + that can be easily obtained from the sysfs symbol and from the + regular expression. So, we need to discard nodes that have + wildcards. + + If it can't obtain a subgroup, place the regular expression inside + a special group (self.leave_others). + """ + + search_group = None + + for search_group in reversed(new.split("/")): + if not search_group or search_group in self.skip_names: + continue + if self.re_symbol_name.match(search_group): + break + + if not search_group: + search_group = self.leave_others + + if self.debug & AbiDebug.SUBGROUP_MAP: + self.log.debug("%s: mapped as %s", what, search_group) + + try: + if search_group not in self.regex_group: + self.regex_group[search_group] = [] + + self.regex_group[search_group].append(re.compile(new)) + if self.search_string: + if what.find(self.search_string) >= 0: + print(f"What: {what}") + except re.PatternError: + self.log.warning("Ignoring '%s' as it produced an invalid regex:\n" + " '%s'", what, new) + + def get_regexes(self, what): + """ + Given an ABI devnode, return a list of all regular expressions that + may match it, based on the sub-groups created by regex_append() + """ + + re_list = [] + + patches = what.split("/") + patches.reverse() + patches.append(self.leave_others) + + for search_group in patches: + if search_group in self.regex_group: + re_list += self.regex_group[search_group] + + return re_list + + def __init__(self, *args, **kwargs): + """ + Override init method to get verbose argument + """ + + self.regex_group = None + self.search_string = None + self.re_string = None + + if "search_string" in kwargs: + self.search_string = kwargs.get("search_string") + del kwargs["search_string"] + + if self.search_string: + + try: + self.re_string = re.compile(self.search_string) + except re.PatternError as e: + msg = f"{self.search_string} is not a valid regular expression" + raise ValueError(msg) from e + + super().__init__(*args, **kwargs) + + def parse_abi(self, *args, **kwargs): + + super().parse_abi(*args, **kwargs) + + self.regex_group = {} + + print("Converting ABI What fields into regexes...", file=sys.stderr) + + for t in sorted(self.data.items(), key=lambda x: x[0]): + v = t[1] + if v.get("type") == "File": + continue + + v["regex"] = [] + + for what in v.get("what", []): + if not what.startswith("/sys"): + continue + + new = what + for r, s in self.re_whats: + try: + new = r.sub(s, new) + except re.PatternError as e: + # Help debugging troubles with new regexes + raise re.PatternError(f"{e}\nwhile re.sub('{r.pattern}', {s}, str)") from e + + v["regex"].append(new) + + if self.debug & AbiDebug.REGEX: + self.log.debug("%-90s <== %s", new, what) + + # Store regex into a subgroup to speedup searches + self.regex_append(what, new) + + if self.debug & AbiDebug.SUBGROUP_DICT: + self.log.debug("%s", pformat(self.regex_group)) + + if self.debug & AbiDebug.SUBGROUP_SIZE: + biggestd_keys = sorted(self.regex_group.keys(), + key= lambda k: len(self.regex_group[k]), + reverse=True) + + print("Top regex subgroups:", file=sys.stderr) + for k in biggestd_keys[:10]: + print(f"{k} has {len(self.regex_group[k])} elements", file=sys.stderr) diff --git a/scripts/lib/abi/helpers.py b/scripts/lib/abi/helpers.py new file mode 100644 index 000000000000..639b23e4ca33 --- /dev/null +++ b/scripts/lib/abi/helpers.py @@ -0,0 +1,38 @@ +#!/usr/bin/env python3 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# pylint: disable=R0903 +# SPDX-License-Identifier: GPL-2.0 + +""" +Helper classes for ABI parser +""" + +ABI_DIR = "Documentation/ABI/" + + +class AbiDebug: + """Debug levels""" + + WHAT_PARSING = 1 + WHAT_OPEN = 2 + DUMP_ABI_STRUCTS = 4 + UNDEFINED = 8 + REGEX = 16 + SUBGROUP_MAP = 32 + SUBGROUP_DICT = 64 + SUBGROUP_SIZE = 128 + GRAPH = 256 + + +DEBUG_HELP = """ +1 - enable debug parsing logic +2 - enable debug messages on file open +4 - enable debug for ABI parse data +8 - enable extra debug information to identify troubles + with ABI symbols found at the local machine that + weren't found on ABI documentation (used only for + undefined subcommand) +16 - enable debug for what to regex conversion +32 - enable debug for symbol regex subgroups +64 - enable debug for sysfs graph tree variable +""" diff --git a/scripts/lib/abi/system_symbols.py b/scripts/lib/abi/system_symbols.py new file mode 100644 index 000000000000..f15c94a6e33c --- /dev/null +++ b/scripts/lib/abi/system_symbols.py @@ -0,0 +1,378 @@ +#!/usr/bin/env python3 +# pylint: disable=R0902,R0912,R0914,R0915,R1702 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# SPDX-License-Identifier: GPL-2.0 + +""" +Parse ABI documentation and produce results from it. +""" + +import os +import re +import sys + +from concurrent import futures +from datetime import datetime +from random import shuffle + +from helpers import AbiDebug + +class SystemSymbols: + """Stores arguments for the class and initialize class vars""" + + def graph_add_file(self, path, link=None): + """ + add a file path to the sysfs graph stored at self.root + """ + + if path in self.files: + return + + name = "" + ref = self.root + for edge in path.split("/"): + name += edge + "/" + if edge not in ref: + ref[edge] = {"__name": [name.rstrip("/")]} + + ref = ref[edge] + + if link and link not in ref["__name"]: + ref["__name"].append(link.rstrip("/")) + + self.files.add(path) + + def print_graph(self, root_prefix="", root=None, level=0): + """Prints a reference tree graph using UTF-8 characters""" + + if not root: + root = self.root + level = 0 + + # Prevent endless traverse + if level > 5: + return + + if level > 0: + prefix = "├──" + last_prefix = "└──" + else: + prefix = "" + last_prefix = "" + + items = list(root.items()) + + names = root.get("__name", []) + for k, edge in items: + if k == "__name": + continue + + if not k: + k = "/" + + if len(names) > 1: + k += " links: " + ",".join(names[1:]) + + if edge == items[-1][1]: + print(root_prefix + last_prefix + k) + p = root_prefix + if level > 0: + p += " " + self.print_graph(p, edge, level + 1) + else: + print(root_prefix + prefix + k) + p = root_prefix + "│ " + self.print_graph(p, edge, level + 1) + + def _walk(self, root): + """ + Walk through sysfs to get all devnodes that aren't ignored. + + By default, uses /sys as sysfs mounting point. If another + directory is used, it replaces them to /sys at the patches. + """ + + with os.scandir(root) as obj: + for entry in obj: + path = os.path.join(root, entry.name) + if self.sysfs: + p = path.replace(self.sysfs, "/sys", count=1) + else: + p = path + + if self.re_ignore.search(p): + return + + # Handle link first to avoid directory recursion + if entry.is_symlink(): + real = os.path.realpath(path) + if not self.sysfs: + self.aliases[path] = real + else: + real = real.replace(self.sysfs, "/sys", count=1) + + # Add absfile location to graph if it doesn't exist + if not self.re_ignore.search(real): + # Add link to the graph + self.graph_add_file(real, p) + + elif entry.is_file(): + self.graph_add_file(p) + + elif entry.is_dir(): + self._walk(path) + + def __init__(self, abi, sysfs="/sys", hints=False): + """ + Initialize internal variables and get a list of all files inside + sysfs that can currently be parsed. + + Please notice that there are several entries on sysfs that aren't + documented as ABI. Ignore those. + + The real paths will be stored under self.files. Aliases will be + stored in separate, as self.aliases. + """ + + self.abi = abi + self.log = abi.log + + if sysfs != "/sys": + self.sysfs = sysfs.rstrip("/") + else: + self.sysfs = None + + self.hints = hints + + self.root = {} + self.aliases = {} + self.files = set() + + dont_walk = [ + # Those require root access and aren't documented at ABI + f"^{sysfs}/kernel/debug", + f"^{sysfs}/kernel/tracing", + f"^{sysfs}/fs/pstore", + f"^{sysfs}/fs/bpf", + f"^{sysfs}/fs/fuse", + + # This is not documented at ABI + f"^{sysfs}/module", + + f"^{sysfs}/fs/cgroup", # this is big and has zero docs under ABI + f"^{sysfs}/firmware", # documented elsewhere: ACPI, DT bindings + "sections|notes", # aren't actually part of ABI + + # kernel-parameters.txt - not easy to parse + "parameters", + ] + + self.re_ignore = re.compile("|".join(dont_walk)) + + print(f"Reading {sysfs} directory contents...", file=sys.stderr) + self._walk(sysfs) + + def check_file(self, refs, found): + """Check missing ABI symbols for a given sysfs file""" + + res_list = [] + + try: + for names in refs: + fname = names[0] + + res = { + "found": False, + "fname": fname, + "msg": "", + } + res_list.append(res) + + re_what = self.abi.get_regexes(fname) + if not re_what: + self.abi.log.warning(f"missing rules for {fname}") + continue + + for name in names: + for r in re_what: + if self.abi.debug & AbiDebug.UNDEFINED: + self.log.debug("check if %s matches '%s'", name, r.pattern) + if r.match(name): + res["found"] = True + if found: + res["msg"] += f" {fname}: regex:\n\t" + continue + + if self.hints and not res["found"]: + res["msg"] += f" {fname} not found. Tested regexes:\n" + for r in re_what: + res["msg"] += " " + r.pattern + "\n" + + except KeyboardInterrupt: + pass + + return res_list + + def _ref_interactor(self, root): + """Recursive function to interact over the sysfs tree""" + + for k, v in root.items(): + if isinstance(v, dict): + yield from self._ref_interactor(v) + + if root == self.root or k == "__name": + continue + + if self.abi.re_string: + fname = v["__name"][0] + if self.abi.re_string.search(fname): + yield v + else: + yield v + + + def get_fileref(self, all_refs, chunk_size): + """Interactor to group refs into chunks""" + + n = 0 + refs = [] + + for ref in all_refs: + refs.append(ref) + + n += 1 + if n >= chunk_size: + yield refs + n = 0 + refs = [] + + yield refs + + def check_undefined_symbols(self, max_workers=None, chunk_size=50, + found=None, dry_run=None): + """Seach ABI for sysfs symbols missing documentation""" + + self.abi.parse_abi() + + if self.abi.debug & AbiDebug.GRAPH: + self.print_graph() + + all_refs = [] + for ref in self._ref_interactor(self.root): + all_refs.append(ref["__name"]) + + if dry_run: + print("Would check", file=sys.stderr) + for ref in all_refs: + print(", ".join(ref)) + + return + + print("Starting to search symbols (it may take several minutes):", + file=sys.stderr) + start = datetime.now() + old_elapsed = None + + # Python doesn't support multithreading due to limitations on its + # global lock (GIL). While Python 3.13 finally made GIL optional, + # there are still issues related to it. Also, we want to have + # backward compatibility with older versions of Python. + # + # So, use instead multiprocess. However, Python is very slow passing + # data from/to multiple processes. Also, it may consume lots of memory + # if the data to be shared is not small. So, we need to group workload + # in chunks that are big enough to generate performance gains while + # not being so big that would cause out-of-memory. + + num_refs = len(all_refs) + print(f"Number of references to parse: {num_refs}", file=sys.stderr) + + if not max_workers: + max_workers = os.cpu_count() + elif max_workers > os.cpu_count(): + max_workers = os.cpu_count() + + max_workers = max(max_workers, 1) + + max_chunk_size = int((num_refs + max_workers - 1) / max_workers) + chunk_size = min(chunk_size, max_chunk_size) + chunk_size = max(1, chunk_size) + + if max_workers > 1: + executor = futures.ProcessPoolExecutor + + # Place references in a random order. This may help improving + # performance, by mixing complex/simple expressions when creating + # chunks + shuffle(all_refs) + else: + # Python has a high overhead with processes. When there's just + # one worker, it is faster to not create a new process. + # Yet, User still deserves to have a progress print. So, use + # python's "thread", which is actually a single process, using + # an internal schedule to switch between tasks. No performance + # gains for non-IO tasks, but still it can be quickly interrupted + # from time to time to display progress. + executor = futures.ThreadPoolExecutor + + not_found = [] + f_list = [] + with executor(max_workers=max_workers) as exe: + for refs in self.get_fileref(all_refs, chunk_size): + if refs: + try: + f_list.append(exe.submit(self.check_file, refs, found)) + + except KeyboardInterrupt: + return + + total = len(f_list) + + if not total: + if self.abi.re_string: + print(f"No ABI symbol matches {self.abi.search_string}") + else: + self.abi.log.warning("No ABI symbols found") + return + + print(f"{len(f_list):6d} jobs queued on {max_workers} workers", + file=sys.stderr) + + while f_list: + try: + t = futures.wait(f_list, timeout=1, + return_when=futures.FIRST_COMPLETED) + + done = t[0] + + for fut in done: + res_list = fut.result() + + for res in res_list: + if not res["found"]: + not_found.append(res["fname"]) + if res["msg"]: + print(res["msg"]) + + f_list.remove(fut) + except KeyboardInterrupt: + return + + except RuntimeError as e: + self.abi.log.warning(f"Future: {e}") + break + + if sys.stderr.isatty(): + elapsed = str(datetime.now() - start).split(".", maxsplit=1)[0] + if len(f_list) < total: + elapsed += f" ({total - len(f_list)}/{total} jobs completed). " + if elapsed != old_elapsed: + print(elapsed + "\r", end="", flush=True, + file=sys.stderr) + old_elapsed = elapsed + + elapsed = str(datetime.now() - start).split(".", maxsplit=1)[0] + print(elapsed, file=sys.stderr) + + for f in sorted(not_found): + print(f"{f} not found.") diff --git a/scripts/lib/kdoc/kdoc_files.py b/scripts/lib/kdoc/kdoc_files.py new file mode 100644 index 000000000000..9be4a64df71d --- /dev/null +++ b/scripts/lib/kdoc/kdoc_files.py @@ -0,0 +1,291 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# +# pylint: disable=R0903,R0913,R0914,R0917 + +""" +Parse lernel-doc tags on multiple kernel source files. +""" + +import argparse +import logging +import os +import re + +from kdoc_parser import KernelDoc +from kdoc_output import OutputFormat + + +class GlobSourceFiles: + """ + Parse C source code file names and directories via an Interactor. + """ + + def __init__(self, srctree=None, valid_extensions=None): + """ + Initialize valid extensions with a tuple. + + If not defined, assume default C extensions (.c and .h) + + It would be possible to use python's glob function, but it is + very slow, and it is not interactive. So, it would wait to read all + directories before actually do something. + + So, let's use our own implementation. + """ + + if not valid_extensions: + self.extensions = (".c", ".h") + else: + self.extensions = valid_extensions + + self.srctree = srctree + + def _parse_dir(self, dirname): + """Internal function to parse files recursively""" + + with os.scandir(dirname) as obj: + for entry in obj: + name = os.path.join(dirname, entry.name) + + if entry.is_dir(): + yield from self._parse_dir(name) + + if not entry.is_file(): + continue + + basename = os.path.basename(name) + + if not basename.endswith(self.extensions): + continue + + yield name + + def parse_files(self, file_list, file_not_found_cb): + """ + Define an interator to parse all source files from file_list, + handling directories if any + """ + + if not file_list: + return + + for fname in file_list: + if self.srctree: + f = os.path.join(self.srctree, fname) + else: + f = fname + + if os.path.isdir(f): + yield from self._parse_dir(f) + elif os.path.isfile(f): + yield f + elif file_not_found_cb: + file_not_found_cb(fname) + + +class KernelFiles(): + """ + Parse kernel-doc tags on multiple kernel source files. + + There are two type of parsers defined here: + - self.parse_file(): parses both kernel-doc markups and + EXPORT_SYMBOL* macros; + - self.process_export_file(): parses only EXPORT_SYMBOL* macros. + """ + + def warning(self, msg): + """Ancillary routine to output a warning and increment error count""" + + self.config.log.warning(msg) + self.errors += 1 + + def error(self, msg): + """Ancillary routine to output an error and increment error count""" + + self.config.log.error(msg) + self.errors += 1 + + def parse_file(self, fname): + """ + Parse a single Kernel source. + """ + + # Prevent parsing the same file twice if results are cached + if fname in self.files: + return + + doc = KernelDoc(self.config, fname) + export_table, entries = doc.parse_kdoc() + + self.export_table[fname] = export_table + + self.files.add(fname) + self.export_files.add(fname) # parse_kdoc() already check exports + + self.results[fname] = entries + + def process_export_file(self, fname): + """ + Parses EXPORT_SYMBOL* macros from a single Kernel source file. + """ + + # Prevent parsing the same file twice if results are cached + if fname in self.export_files: + return + + doc = KernelDoc(self.config, fname) + export_table = doc.parse_export() + + if not export_table: + self.error(f"Error: Cannot check EXPORT_SYMBOL* on {fname}") + export_table = set() + + self.export_table[fname] = export_table + self.export_files.add(fname) + + def file_not_found_cb(self, fname): + """ + Callback to warn if a file was not found. + """ + + self.error(f"Cannot find file {fname}") + + def __init__(self, verbose=False, out_style=None, + werror=False, wreturn=False, wshort_desc=False, + wcontents_before_sections=False, + logger=None): + """ + Initialize startup variables and parse all files + """ + + if not verbose: + verbose = bool(os.environ.get("KBUILD_VERBOSE", 0)) + + if out_style is None: + out_style = OutputFormat() + + if not werror: + kcflags = os.environ.get("KCFLAGS", None) + if kcflags: + match = re.search(r"(\s|^)-Werror(\s|$)/", kcflags) + if match: + werror = True + + # reading this variable is for backwards compat just in case + # someone was calling it with the variable from outside the + # kernel's build system + kdoc_werror = os.environ.get("KDOC_WERROR", None) + if kdoc_werror: + werror = kdoc_werror + + # Some variables are global to the parser logic as a whole as they are + # used to send control configuration to KernelDoc class. As such, + # those variables are read-only inside the KernelDoc. + self.config = argparse.Namespace + + self.config.verbose = verbose + self.config.werror = werror + self.config.wreturn = wreturn + self.config.wshort_desc = wshort_desc + self.config.wcontents_before_sections = wcontents_before_sections + + if not logger: + self.config.log = logging.getLogger("kernel-doc") + else: + self.config.log = logger + + self.config.warning = self.warning + + self.config.src_tree = os.environ.get("SRCTREE", None) + + # Initialize variables that are internal to KernelFiles + + self.out_style = out_style + + self.errors = 0 + self.results = {} + + self.files = set() + self.export_files = set() + self.export_table = {} + + def parse(self, file_list, export_file=None): + """ + Parse all files + """ + + glob = GlobSourceFiles(srctree=self.config.src_tree) + + for fname in glob.parse_files(file_list, self.file_not_found_cb): + self.parse_file(fname) + + for fname in glob.parse_files(export_file, self.file_not_found_cb): + self.process_export_file(fname) + + def out_msg(self, fname, name, arg): + """ + Return output messages from a file name using the output style + filtering. + + If output type was not handled by the syler, return None. + """ + + # NOTE: we can add rules here to filter out unwanted parts, + # although OutputFormat.msg already does that. + + return self.out_style.msg(fname, name, arg) + + def msg(self, enable_lineno=False, export=False, internal=False, + symbol=None, nosymbol=None, no_doc_sections=False, + filenames=None, export_file=None): + """ + Interacts over the kernel-doc results and output messages, + returning kernel-doc markups on each interaction + """ + + self.out_style.set_config(self.config) + + if not filenames: + filenames = sorted(self.results.keys()) + + glob = GlobSourceFiles(srctree=self.config.src_tree) + + for fname in filenames: + function_table = set() + + if internal or export: + if not export_file: + export_file = [fname] + + for f in glob.parse_files(export_file, self.file_not_found_cb): + function_table |= self.export_table[f] + + if symbol: + for s in symbol: + function_table.add(s) + + self.out_style.set_filter(export, internal, symbol, nosymbol, + function_table, enable_lineno, + no_doc_sections) + + msg = "" + if fname not in self.results: + self.config.log.warning("No kernel-doc for file %s", fname) + continue + + for name, arg in self.results[fname]: + m = self.out_msg(fname, name, arg) + + if m is None: + ln = arg.get("ln", 0) + dtype = arg.get('type', "") + + self.config.log.warning("%s:%d Can't handle %s", + fname, ln, dtype) + else: + msg += m + + if msg: + yield fname, msg diff --git a/scripts/lib/kdoc/kdoc_output.py b/scripts/lib/kdoc/kdoc_output.py new file mode 100644 index 000000000000..86102e628d91 --- /dev/null +++ b/scripts/lib/kdoc/kdoc_output.py @@ -0,0 +1,793 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# +# pylint: disable=C0301,R0902,R0911,R0912,R0913,R0914,R0915,R0917 + +""" +Implement output filters to print kernel-doc documentation. + +The implementation uses a virtual base class (OutputFormat) which +contains a dispatches to virtual methods, and some code to filter +out output messages. + +The actual implementation is done on one separate class per each type +of output. Currently, there are output classes for ReST and man/troff. +""" + +import os +import re +from datetime import datetime + +from kdoc_parser import KernelDoc, type_param +from kdoc_re import KernRe + + +function_pointer = KernRe(r"([^\(]*\(\*)\s*\)\s*\(([^\)]*)\)", cache=False) + +# match expressions used to find embedded type information +type_constant = KernRe(r"\b``([^\`]+)``\b", cache=False) +type_constant2 = KernRe(r"\%([-_*\w]+)", cache=False) +type_func = KernRe(r"(\w+)\(\)", cache=False) +type_param_ref = KernRe(r"([\!~\*]?)\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)", cache=False) + +# Special RST handling for func ptr params +type_fp_param = KernRe(r"\@(\w+)\(\)", cache=False) + +# Special RST handling for structs with func ptr params +type_fp_param2 = KernRe(r"\@(\w+->\S+)\(\)", cache=False) + +type_env = KernRe(r"(\$\w+)", cache=False) +type_enum = KernRe(r"\&(enum\s*([_\w]+))", cache=False) +type_struct = KernRe(r"\&(struct\s*([_\w]+))", cache=False) +type_typedef = KernRe(r"\&(typedef\s*([_\w]+))", cache=False) +type_union = KernRe(r"\&(union\s*([_\w]+))", cache=False) +type_member = KernRe(r"\&([_\w]+)(\.|->)([_\w]+)", cache=False) +type_fallback = KernRe(r"\&([_\w]+)", cache=False) +type_member_func = type_member + KernRe(r"\(\)", cache=False) + + +class OutputFormat: + """ + Base class for OutputFormat. If used as-is, it means that only + warnings will be displayed. + """ + + # output mode. + OUTPUT_ALL = 0 # output all symbols and doc sections + OUTPUT_INCLUDE = 1 # output only specified symbols + OUTPUT_EXPORTED = 2 # output exported symbols + OUTPUT_INTERNAL = 3 # output non-exported symbols + + # Virtual member to be overriden at the inherited classes + highlights = [] + + def __init__(self): + """Declare internal vars and set mode to OUTPUT_ALL""" + + self.out_mode = self.OUTPUT_ALL + self.enable_lineno = None + self.nosymbol = {} + self.symbol = None + self.function_table = None + self.config = None + self.no_doc_sections = False + + self.data = "" + + def set_config(self, config): + """ + Setup global config variables used by both parser and output. + """ + + self.config = config + + def set_filter(self, export, internal, symbol, nosymbol, function_table, + enable_lineno, no_doc_sections): + """ + Initialize filter variables according with the requested mode. + + Only one choice is valid between export, internal and symbol. + + The nosymbol filter can be used on all modes. + """ + + self.enable_lineno = enable_lineno + self.no_doc_sections = no_doc_sections + self.function_table = function_table + + if symbol: + self.out_mode = self.OUTPUT_INCLUDE + elif export: + self.out_mode = self.OUTPUT_EXPORTED + elif internal: + self.out_mode = self.OUTPUT_INTERNAL + else: + self.out_mode = self.OUTPUT_ALL + + if nosymbol: + self.nosymbol = set(nosymbol) + + + def highlight_block(self, block): + """ + Apply the RST highlights to a sub-block of text. + """ + + for r, sub in self.highlights: + block = r.sub(sub, block) + + return block + + def out_warnings(self, args): + """ + Output warnings for identifiers that will be displayed. + """ + + warnings = args.get('warnings', []) + + for log_msg in warnings: + self.config.warning(log_msg) + + def check_doc(self, name, args): + """Check if DOC should be output""" + + if self.no_doc_sections: + return False + + if name in self.nosymbol: + return False + + if self.out_mode == self.OUTPUT_ALL: + self.out_warnings(args) + return True + + if self.out_mode == self.OUTPUT_INCLUDE: + if name in self.function_table: + self.out_warnings(args) + return True + + return False + + def check_declaration(self, dtype, name, args): + """ + Checks if a declaration should be output or not based on the + filtering criteria. + """ + + if name in self.nosymbol: + return False + + if self.out_mode == self.OUTPUT_ALL: + self.out_warnings(args) + return True + + if self.out_mode in [self.OUTPUT_INCLUDE, self.OUTPUT_EXPORTED]: + if name in self.function_table: + return True + + if self.out_mode == self.OUTPUT_INTERNAL: + if dtype != "function": + self.out_warnings(args) + return True + + if name not in self.function_table: + self.out_warnings(args) + return True + + return False + + def msg(self, fname, name, args): + """ + Handles a single entry from kernel-doc parser + """ + + self.data = "" + + dtype = args.get('type', "") + + if dtype == "doc": + self.out_doc(fname, name, args) + return self.data + + if not self.check_declaration(dtype, name, args): + return self.data + + if dtype == "function": + self.out_function(fname, name, args) + return self.data + + if dtype == "enum": + self.out_enum(fname, name, args) + return self.data + + if dtype == "typedef": + self.out_typedef(fname, name, args) + return self.data + + if dtype in ["struct", "union"]: + self.out_struct(fname, name, args) + return self.data + + # Warn if some type requires an output logic + self.config.log.warning("doesn't now how to output '%s' block", + dtype) + + return None + + # Virtual methods to be overridden by inherited classes + # At the base class, those do nothing. + def out_doc(self, fname, name, args): + """Outputs a DOC block""" + + def out_function(self, fname, name, args): + """Outputs a function""" + + def out_enum(self, fname, name, args): + """Outputs an enum""" + + def out_typedef(self, fname, name, args): + """Outputs a typedef""" + + def out_struct(self, fname, name, args): + """Outputs a struct""" + + +class RestFormat(OutputFormat): + """Consts and functions used by ReST output""" + + highlights = [ + (type_constant, r"``\1``"), + (type_constant2, r"``\1``"), + + # Note: need to escape () to avoid func matching later + (type_member_func, r":c:type:`\1\2\3\\(\\) <\1>`"), + (type_member, r":c:type:`\1\2\3 <\1>`"), + (type_fp_param, r"**\1\\(\\)**"), + (type_fp_param2, r"**\1\\(\\)**"), + (type_func, r"\1()"), + (type_enum, r":c:type:`\1 <\2>`"), + (type_struct, r":c:type:`\1 <\2>`"), + (type_typedef, r":c:type:`\1 <\2>`"), + (type_union, r":c:type:`\1 <\2>`"), + + # in rst this can refer to any type + (type_fallback, r":c:type:`\1`"), + (type_param_ref, r"**\1\2**") + ] + blankline = "\n" + + sphinx_literal = KernRe(r'^[^.].*::$', cache=False) + sphinx_cblock = KernRe(r'^\.\.\ +code-block::', cache=False) + + def __init__(self): + """ + Creates class variables. + + Not really mandatory, but it is a good coding style and makes + pylint happy. + """ + + super().__init__() + self.lineprefix = "" + + def print_lineno(self, ln): + """Outputs a line number""" + + if self.enable_lineno and ln is not None: + ln += 1 + self.data += f".. LINENO {ln}\n" + + def output_highlight(self, args): + """ + Outputs a C symbol that may require being converted to ReST using + the self.highlights variable + """ + + input_text = args + output = "" + in_literal = False + litprefix = "" + block = "" + + for line in input_text.strip("\n").split("\n"): + + # If we're in a literal block, see if we should drop out of it. + # Otherwise, pass the line straight through unmunged. + if in_literal: + if line.strip(): # If the line is not blank + # If this is the first non-blank line in a literal block, + # figure out the proper indent. + if not litprefix: + r = KernRe(r'^(\s*)') + if r.match(line): + litprefix = '^' + r.group(1) + else: + litprefix = "" + + output += line + "\n" + elif not KernRe(litprefix).match(line): + in_literal = False + else: + output += line + "\n" + else: + output += line + "\n" + + # Not in a literal block (or just dropped out) + if not in_literal: + block += line + "\n" + if self.sphinx_literal.match(line) or self.sphinx_cblock.match(line): + in_literal = True + litprefix = "" + output += self.highlight_block(block) + block = "" + + # Handle any remaining block + if block: + output += self.highlight_block(block) + + # Print the output with the line prefix + for line in output.strip("\n").split("\n"): + self.data += self.lineprefix + line + "\n" + + def out_section(self, args, out_docblock=False): + """ + Outputs a block section. + + This could use some work; it's used to output the DOC: sections, and + starts by putting out the name of the doc section itself, but that + tends to duplicate a header already in the template file. + """ + + sectionlist = args.get('sectionlist', []) + sections = args.get('sections', {}) + section_start_lines = args.get('section_start_lines', {}) + + for section in sectionlist: + # Skip sections that are in the nosymbol_table + if section in self.nosymbol: + continue + + if out_docblock: + if not self.out_mode == self.OUTPUT_INCLUDE: + self.data += f".. _{section}:\n\n" + self.data += f'{self.lineprefix}**{section}**\n\n' + else: + self.data += f'{self.lineprefix}**{section}**\n\n' + + self.print_lineno(section_start_lines.get(section, 0)) + self.output_highlight(sections[section]) + self.data += "\n" + self.data += "\n" + + def out_doc(self, fname, name, args): + if not self.check_doc(name, args): + return + self.out_section(args, out_docblock=True) + + def out_function(self, fname, name, args): + + oldprefix = self.lineprefix + signature = "" + + func_macro = args.get('func_macro', False) + if func_macro: + signature = args['function'] + else: + if args.get('functiontype'): + signature = args['functiontype'] + " " + signature += args['function'] + " (" + + parameterlist = args.get('parameterlist', []) + parameterdescs = args.get('parameterdescs', {}) + parameterdesc_start_lines = args.get('parameterdesc_start_lines', {}) + + ln = args.get('declaration_start_line', 0) + + count = 0 + for parameter in parameterlist: + if count != 0: + signature += ", " + count += 1 + dtype = args['parametertypes'].get(parameter, "") + + if function_pointer.search(dtype): + signature += function_pointer.group(1) + parameter + function_pointer.group(3) + else: + signature += dtype + + if not func_macro: + signature += ")" + + self.print_lineno(ln) + if args.get('typedef') or not args.get('functiontype'): + self.data += f".. c:macro:: {args['function']}\n\n" + + if args.get('typedef'): + self.data += " **Typedef**: " + self.lineprefix = "" + self.output_highlight(args.get('purpose', "")) + self.data += "\n\n**Syntax**\n\n" + self.data += f" ``{signature}``\n\n" + else: + self.data += f"``{signature}``\n\n" + else: + self.data += f".. c:function:: {signature}\n\n" + + if not args.get('typedef'): + self.print_lineno(ln) + self.lineprefix = " " + self.output_highlight(args.get('purpose', "")) + self.data += "\n" + + # Put descriptive text into a container (HTML <div>) to help set + # function prototypes apart + self.lineprefix = " " + + if parameterlist: + self.data += ".. container:: kernelindent\n\n" + self.data += f"{self.lineprefix}**Parameters**\n\n" + + for parameter in parameterlist: + parameter_name = KernRe(r'\[.*').sub('', parameter) + dtype = args['parametertypes'].get(parameter, "") + + if dtype: + self.data += f"{self.lineprefix}``{dtype}``\n" + else: + self.data += f"{self.lineprefix}``{parameter}``\n" + + self.print_lineno(parameterdesc_start_lines.get(parameter_name, 0)) + + self.lineprefix = " " + if parameter_name in parameterdescs and \ + parameterdescs[parameter_name] != KernelDoc.undescribed: + + self.output_highlight(parameterdescs[parameter_name]) + self.data += "\n" + else: + self.data += f"{self.lineprefix}*undescribed*\n\n" + self.lineprefix = " " + + self.out_section(args) + self.lineprefix = oldprefix + + def out_enum(self, fname, name, args): + + oldprefix = self.lineprefix + name = args.get('enum', '') + parameterlist = args.get('parameterlist', []) + parameterdescs = args.get('parameterdescs', {}) + ln = args.get('declaration_start_line', 0) + + self.data += f"\n\n.. c:enum:: {name}\n\n" + + self.print_lineno(ln) + self.lineprefix = " " + self.output_highlight(args.get('purpose', '')) + self.data += "\n" + + self.data += ".. container:: kernelindent\n\n" + outer = self.lineprefix + " " + self.lineprefix = outer + " " + self.data += f"{outer}**Constants**\n\n" + + for parameter in parameterlist: + self.data += f"{outer}``{parameter}``\n" + + if parameterdescs.get(parameter, '') != KernelDoc.undescribed: + self.output_highlight(parameterdescs[parameter]) + else: + self.data += f"{self.lineprefix}*undescribed*\n\n" + self.data += "\n" + + self.lineprefix = oldprefix + self.out_section(args) + + def out_typedef(self, fname, name, args): + + oldprefix = self.lineprefix + name = args.get('typedef', '') + ln = args.get('declaration_start_line', 0) + + self.data += f"\n\n.. c:type:: {name}\n\n" + + self.print_lineno(ln) + self.lineprefix = " " + + self.output_highlight(args.get('purpose', '')) + + self.data += "\n" + + self.lineprefix = oldprefix + self.out_section(args) + + def out_struct(self, fname, name, args): + + name = args.get('struct', "") + purpose = args.get('purpose', "") + declaration = args.get('definition', "") + dtype = args.get('type', "struct") + ln = args.get('declaration_start_line', 0) + + parameterlist = args.get('parameterlist', []) + parameterdescs = args.get('parameterdescs', {}) + parameterdesc_start_lines = args.get('parameterdesc_start_lines', {}) + + self.data += f"\n\n.. c:{dtype}:: {name}\n\n" + + self.print_lineno(ln) + + oldprefix = self.lineprefix + self.lineprefix += " " + + self.output_highlight(purpose) + self.data += "\n" + + self.data += ".. container:: kernelindent\n\n" + self.data += f"{self.lineprefix}**Definition**::\n\n" + + self.lineprefix = self.lineprefix + " " + + declaration = declaration.replace("\t", self.lineprefix) + + self.data += f"{self.lineprefix}{dtype} {name}" + ' {' + "\n" + self.data += f"{declaration}{self.lineprefix}" + "};\n\n" + + self.lineprefix = " " + self.data += f"{self.lineprefix}**Members**\n\n" + for parameter in parameterlist: + if not parameter or parameter.startswith("#"): + continue + + parameter_name = parameter.split("[", maxsplit=1)[0] + + if parameterdescs.get(parameter_name) == KernelDoc.undescribed: + continue + + self.print_lineno(parameterdesc_start_lines.get(parameter_name, 0)) + + self.data += f"{self.lineprefix}``{parameter}``\n" + + self.lineprefix = " " + self.output_highlight(parameterdescs[parameter_name]) + self.lineprefix = " " + + self.data += "\n" + + self.data += "\n" + + self.lineprefix = oldprefix + self.out_section(args) + + +class ManFormat(OutputFormat): + """Consts and functions used by man pages output""" + + highlights = ( + (type_constant, r"\1"), + (type_constant2, r"\1"), + (type_func, r"\\fB\1\\fP"), + (type_enum, r"\\fI\1\\fP"), + (type_struct, r"\\fI\1\\fP"), + (type_typedef, r"\\fI\1\\fP"), + (type_union, r"\\fI\1\\fP"), + (type_param, r"\\fI\1\\fP"), + (type_param_ref, r"\\fI\1\2\\fP"), + (type_member, r"\\fI\1\2\3\\fP"), + (type_fallback, r"\\fI\1\\fP") + ) + blankline = "" + + date_formats = [ + "%a %b %d %H:%M:%S %Z %Y", + "%a %b %d %H:%M:%S %Y", + "%Y-%m-%d", + "%b %d %Y", + "%B %d %Y", + "%m %d %Y", + ] + + def __init__(self, modulename): + """ + Creates class variables. + + Not really mandatory, but it is a good coding style and makes + pylint happy. + """ + + super().__init__() + self.modulename = modulename + + dt = None + tstamp = os.environ.get("KBUILD_BUILD_TIMESTAMP") + if tstamp: + for fmt in self.date_formats: + try: + dt = datetime.strptime(tstamp, fmt) + break + except ValueError: + pass + + if not dt: + dt = datetime.now() + + self.man_date = dt.strftime("%B %Y") + + def output_highlight(self, block): + """ + Outputs a C symbol that may require being highlighted with + self.highlights variable using troff syntax + """ + + contents = self.highlight_block(block) + + if isinstance(contents, list): + contents = "\n".join(contents) + + for line in contents.strip("\n").split("\n"): + line = KernRe(r"^\s*").sub("", line) + if not line: + continue + + if line[0] == ".": + self.data += "\\&" + line + "\n" + else: + self.data += line + "\n" + + def out_doc(self, fname, name, args): + sectionlist = args.get('sectionlist', []) + sections = args.get('sections', {}) + + if not self.check_doc(name, args): + return + + self.data += f'.TH "{self.modulename}" 9 "{self.modulename}" "{self.man_date}" "API Manual" LINUX' + "\n" + + for section in sectionlist: + self.data += f'.SH "{section}"' + "\n" + self.output_highlight(sections.get(section)) + + def out_function(self, fname, name, args): + """output function in man""" + + parameterlist = args.get('parameterlist', []) + parameterdescs = args.get('parameterdescs', {}) + sectionlist = args.get('sectionlist', []) + sections = args.get('sections', {}) + + self.data += f'.TH "{args["function"]}" 9 "{args["function"]}" "{self.man_date}" "Kernel Hacker\'s Manual" LINUX' + "\n" + + self.data += ".SH NAME\n" + self.data += f"{args['function']} \\- {args['purpose']}\n" + + self.data += ".SH SYNOPSIS\n" + if args.get('functiontype', ''): + self.data += f'.B "{args["functiontype"]}" {args["function"]}' + "\n" + else: + self.data += f'.B "{args["function"]}' + "\n" + + count = 0 + parenth = "(" + post = "," + + for parameter in parameterlist: + if count == len(parameterlist) - 1: + post = ");" + + dtype = args['parametertypes'].get(parameter, "") + if function_pointer.match(dtype): + # Pointer-to-function + self.data += f'".BI "{parenth}{function_pointer.group(1)}" " ") ({function_pointer.group(2)}){post}"' + "\n" + else: + dtype = KernRe(r'([^\*])$').sub(r'\1 ', dtype) + + self.data += f'.BI "{parenth}{dtype}" "{post}"' + "\n" + count += 1 + parenth = "" + + if parameterlist: + self.data += ".SH ARGUMENTS\n" + + for parameter in parameterlist: + parameter_name = re.sub(r'\[.*', '', parameter) + + self.data += f'.IP "{parameter}" 12' + "\n" + self.output_highlight(parameterdescs.get(parameter_name, "")) + + for section in sectionlist: + self.data += f'.SH "{section.upper()}"' + "\n" + self.output_highlight(sections[section]) + + def out_enum(self, fname, name, args): + + name = args.get('enum', '') + parameterlist = args.get('parameterlist', []) + sectionlist = args.get('sectionlist', []) + sections = args.get('sections', {}) + + self.data += f'.TH "{self.modulename}" 9 "enum {args["enum"]}" "{self.man_date}" "API Manual" LINUX' + "\n" + + self.data += ".SH NAME\n" + self.data += f"enum {args['enum']} \\- {args['purpose']}\n" + + self.data += ".SH SYNOPSIS\n" + self.data += f"enum {args['enum']}" + " {\n" + + count = 0 + for parameter in parameterlist: + self.data += f'.br\n.BI " {parameter}"' + "\n" + if count == len(parameterlist) - 1: + self.data += "\n};\n" + else: + self.data += ", \n.br\n" + + count += 1 + + self.data += ".SH Constants\n" + + for parameter in parameterlist: + parameter_name = KernRe(r'\[.*').sub('', parameter) + self.data += f'.IP "{parameter}" 12' + "\n" + self.output_highlight(args['parameterdescs'].get(parameter_name, "")) + + for section in sectionlist: + self.data += f'.SH "{section}"' + "\n" + self.output_highlight(sections[section]) + + def out_typedef(self, fname, name, args): + module = self.modulename + typedef = args.get('typedef') + purpose = args.get('purpose') + sectionlist = args.get('sectionlist', []) + sections = args.get('sections', {}) + + self.data += f'.TH "{module}" 9 "{typedef}" "{self.man_date}" "API Manual" LINUX' + "\n" + + self.data += ".SH NAME\n" + self.data += f"typedef {typedef} \\- {purpose}\n" + + for section in sectionlist: + self.data += f'.SH "{section}"' + "\n" + self.output_highlight(sections.get(section)) + + def out_struct(self, fname, name, args): + module = self.modulename + struct_type = args.get('type') + struct_name = args.get('struct') + purpose = args.get('purpose') + definition = args.get('definition') + sectionlist = args.get('sectionlist', []) + parameterlist = args.get('parameterlist', []) + sections = args.get('sections', {}) + parameterdescs = args.get('parameterdescs', {}) + + self.data += f'.TH "{module}" 9 "{struct_type} {struct_name}" "{self.man_date}" "API Manual" LINUX' + "\n" + + self.data += ".SH NAME\n" + self.data += f"{struct_type} {struct_name} \\- {purpose}\n" + + # Replace tabs with two spaces and handle newlines + declaration = definition.replace("\t", " ") + declaration = KernRe(r"\n").sub('"\n.br\n.BI "', declaration) + + self.data += ".SH SYNOPSIS\n" + self.data += f"{struct_type} {struct_name} " + "{" + "\n.br\n" + self.data += f'.BI "{declaration}\n' + "};\n.br\n\n" + + self.data += ".SH Members\n" + for parameter in parameterlist: + if parameter.startswith("#"): + continue + + parameter_name = re.sub(r"\[.*", "", parameter) + + if parameterdescs.get(parameter_name) == KernelDoc.undescribed: + continue + + self.data += f'.IP "{parameter}" 12' + "\n" + self.output_highlight(parameterdescs.get(parameter_name)) + + for section in sectionlist: + self.data += f'.SH "{section}"' + "\n" + self.output_highlight(sections.get(section)) diff --git a/scripts/lib/kdoc/kdoc_parser.py b/scripts/lib/kdoc/kdoc_parser.py new file mode 100644 index 000000000000..062453eefc7a --- /dev/null +++ b/scripts/lib/kdoc/kdoc_parser.py @@ -0,0 +1,1745 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# +# pylint: disable=C0301,C0302,R0904,R0912,R0913,R0914,R0915,R0917,R1702 + +""" +kdoc_parser +=========== + +Read a C language source or header FILE and extract embedded +documentation comments +""" + +import re +from pprint import pformat + +from kdoc_re import NestedMatch, KernRe + + +# +# Regular expressions used to parse kernel-doc markups at KernelDoc class. +# +# Let's declare them in lowercase outside any class to make easier to +# convert from the python script. +# +# As those are evaluated at the beginning, no need to cache them +# + +# Allow whitespace at end of comment start. +doc_start = KernRe(r'^/\*\*\s*$', cache=False) + +doc_end = KernRe(r'\*/', cache=False) +doc_com = KernRe(r'\s*\*\s*', cache=False) +doc_com_body = KernRe(r'\s*\* ?', cache=False) +doc_decl = doc_com + KernRe(r'(\w+)', cache=False) + +# @params and a strictly limited set of supported section names +# Specifically: +# Match @word: +# @...: +# @{section-name}: +# while trying to not match literal block starts like "example::" +# +doc_sect = doc_com + \ + KernRe(r'\s*(\@[.\w]+|\@\.\.\.|description|context|returns?|notes?|examples?)\s*:([^:].*)?$', + flags=re.I, cache=False) + +doc_content = doc_com_body + KernRe(r'(.*)', cache=False) +doc_block = doc_com + KernRe(r'DOC:\s*(.*)?', cache=False) +doc_inline_start = KernRe(r'^\s*/\*\*\s*$', cache=False) +doc_inline_sect = KernRe(r'\s*\*\s*(@\s*[\w][\w\.]*\s*):(.*)', cache=False) +doc_inline_end = KernRe(r'^\s*\*/\s*$', cache=False) +doc_inline_oneline = KernRe(r'^\s*/\*\*\s*(@[\w\s]+):\s*(.*)\s*\*/\s*$', cache=False) +attribute = KernRe(r"__attribute__\s*\(\([a-z0-9,_\*\s\(\)]*\)\)", + flags=re.I | re.S, cache=False) + +export_symbol = KernRe(r'^\s*EXPORT_SYMBOL(_GPL)?\s*\(\s*(\w+)\s*\)\s*', cache=False) +export_symbol_ns = KernRe(r'^\s*EXPORT_SYMBOL_NS(_GPL)?\s*\(\s*(\w+)\s*,\s*"\S+"\)\s*', cache=False) + +type_param = KernRe(r"\@(\w*((\.\w+)|(->\w+))*(\.\.\.)?)", cache=False) + +class state: + """ + State machine enums + """ + + # Parser states + NORMAL = 0 # normal code + NAME = 1 # looking for function name + BODY_MAYBE = 2 # body - or maybe more description + BODY = 3 # the body of the comment + BODY_WITH_BLANK_LINE = 4 # the body which has a blank line + PROTO = 5 # scanning prototype + DOCBLOCK = 6 # documentation block + INLINE = 7 # gathering doc outside main block + + name = [ + "NORMAL", + "NAME", + "BODY_MAYBE", + "BODY", + "BODY_WITH_BLANK_LINE", + "PROTO", + "DOCBLOCK", + "INLINE", + ] + + # Inline documentation state + INLINE_NA = 0 # not applicable ($state != INLINE) + INLINE_NAME = 1 # looking for member name (@foo:) + INLINE_TEXT = 2 # looking for member documentation + INLINE_END = 3 # done + INLINE_ERROR = 4 # error - Comment without header was found. + # Spit a warning as it's not + # proper kernel-doc and ignore the rest. + + inline_name = [ + "", + "_NAME", + "_TEXT", + "_END", + "_ERROR", + ] + +SECTION_DEFAULT = "Description" # default section + +class KernelEntry: + + def __init__(self, config, ln): + self.config = config + + self.contents = "" + self.function = "" + self.sectcheck = "" + self.struct_actual = "" + self.prototype = "" + + self.warnings = [] + + self.parameterlist = [] + self.parameterdescs = {} + self.parametertypes = {} + self.parameterdesc_start_lines = {} + + self.section_start_lines = {} + self.sectionlist = [] + self.sections = {} + + self.anon_struct_union = False + + self.leading_space = None + + # State flags + self.brcount = 0 + + self.in_doc_sect = False + self.declaration_start_line = ln + 1 + + # TODO: rename to emit_message after removal of kernel-doc.pl + def emit_msg(self, log_msg, warning=True): + """Emit a message""" + + if not warning: + self.config.log.info(log_msg) + return + + # Delegate warning output to output logic, as this way it + # will report warnings/info only for symbols that are output + + self.warnings.append(log_msg) + return + + def dump_section(self, start_new=True): + """ + Dumps section contents to arrays/hashes intended for that purpose. + """ + + name = self.section + contents = self.contents + + if type_param.match(name): + name = type_param.group(1) + + self.parameterdescs[name] = contents + self.parameterdesc_start_lines[name] = self.new_start_line + + self.sectcheck += name + " " + self.new_start_line = 0 + + elif name == "@...": + name = "..." + self.parameterdescs[name] = contents + self.sectcheck += name + " " + self.parameterdesc_start_lines[name] = self.new_start_line + self.new_start_line = 0 + + else: + if name in self.sections and self.sections[name] != "": + # Only warn on user-specified duplicate section names + if name != SECTION_DEFAULT: + self.emit_msg(self.new_start_line, + f"duplicate section name '{name}'\n") + self.sections[name] += contents + else: + self.sections[name] = contents + self.sectionlist.append(name) + self.section_start_lines[name] = self.new_start_line + self.new_start_line = 0 + +# self.config.log.debug("Section: %s : %s", name, pformat(vars(self))) + + if start_new: + self.section = SECTION_DEFAULT + self.contents = "" + + +class KernelDoc: + """ + Read a C language source or header FILE and extract embedded + documentation comments. + """ + + # Section names + + section_intro = "Introduction" + section_context = "Context" + section_return = "Return" + + undescribed = "-- undescribed --" + + def __init__(self, config, fname): + """Initialize internal variables""" + + self.fname = fname + self.config = config + + # Initial state for the state machines + self.state = state.NORMAL + self.inline_doc_state = state.INLINE_NA + + # Store entry currently being processed + self.entry = None + + # Place all potential outputs into an array + self.entries = [] + + def emit_msg(self, ln, msg, warning=True): + """Emit a message""" + + log_msg = f"{self.fname}:{ln} {msg}" + + if self.entry: + self.entry.emit_msg(log_msg, warning) + return + + if warning: + self.config.log.warning(log_msg) + else: + self.config.log.info(log_msg) + + def dump_section(self, start_new=True): + """ + Dumps section contents to arrays/hashes intended for that purpose. + """ + + if self.entry: + self.entry.dump_section(start_new) + + # TODO: rename it to store_declaration after removal of kernel-doc.pl + def output_declaration(self, dtype, name, **args): + """ + Stores the entry into an entry array. + + The actual output and output filters will be handled elsewhere + """ + + # The implementation here is different than the original kernel-doc: + # instead of checking for output filters or actually output anything, + # it just stores the declaration content at self.entries, as the + # output will happen on a separate class. + # + # For now, we're keeping the same name of the function just to make + # easier to compare the source code of both scripts + + args["declaration_start_line"] = self.entry.declaration_start_line + args["type"] = dtype + args["warnings"] = self.entry.warnings + + # TODO: use colletions.OrderedDict to remove sectionlist + + sections = args.get('sections', {}) + sectionlist = args.get('sectionlist', []) + + # Drop empty sections + # TODO: improve empty sections logic to emit warnings + for section in ["Description", "Return"]: + if section in sectionlist: + if not sections[section].rstrip(): + del sections[section] + sectionlist.remove(section) + + self.entries.append((name, args)) + + self.config.log.debug("Output: %s:%s = %s", dtype, name, pformat(args)) + + def reset_state(self, ln): + """ + Ancillary routine to create a new entry. It initializes all + variables used by the state machine. + """ + + self.entry = KernelEntry(self.config, ln) + + # State flags + self.state = state.NORMAL + self.inline_doc_state = state.INLINE_NA + + def push_parameter(self, ln, decl_type, param, dtype, + org_arg, declaration_name): + """ + Store parameters and their descriptions at self.entry. + """ + + if self.entry.anon_struct_union and dtype == "" and param == "}": + return # Ignore the ending }; from anonymous struct/union + + self.entry.anon_struct_union = False + + param = KernRe(r'[\[\)].*').sub('', param, count=1) + + if dtype == "" and param.endswith("..."): + if KernRe(r'\w\.\.\.$').search(param): + # For named variable parameters of the form `x...`, + # remove the dots + param = param[:-3] + else: + # Handles unnamed variable parameters + param = "..." + + if param not in self.entry.parameterdescs or \ + not self.entry.parameterdescs[param]: + + self.entry.parameterdescs[param] = "variable arguments" + + elif dtype == "" and (not param or param == "void"): + param = "void" + self.entry.parameterdescs[param] = "no arguments" + + elif dtype == "" and param in ["struct", "union"]: + # Handle unnamed (anonymous) union or struct + dtype = param + param = "{unnamed_" + param + "}" + self.entry.parameterdescs[param] = "anonymous\n" + self.entry.anon_struct_union = True + + # Handle cache group enforcing variables: they do not need + # to be described in header files + elif "__cacheline_group" in param: + # Ignore __cacheline_group_begin and __cacheline_group_end + return + + # Warn if parameter has no description + # (but ignore ones starting with # as these are not parameters + # but inline preprocessor statements) + if param not in self.entry.parameterdescs and not param.startswith("#"): + self.entry.parameterdescs[param] = self.undescribed + + if "." not in param: + if decl_type == 'function': + dname = f"{decl_type} parameter" + else: + dname = f"{decl_type} member" + + self.emit_msg(ln, + f"{dname} '{param}' not described in '{declaration_name}'") + + # Strip spaces from param so that it is one continuous string on + # parameterlist. This fixes a problem where check_sections() + # cannot find a parameter like "addr[6 + 2]" because it actually + # appears as "addr[6", "+", "2]" on the parameter list. + # However, it's better to maintain the param string unchanged for + # output, so just weaken the string compare in check_sections() + # to ignore "[blah" in a parameter string. + + self.entry.parameterlist.append(param) + org_arg = KernRe(r'\s\s+').sub(' ', org_arg) + self.entry.parametertypes[param] = org_arg + + def save_struct_actual(self, actual): + """ + Strip all spaces from the actual param so that it looks like + one string item. + """ + + actual = KernRe(r'\s*').sub("", actual, count=1) + + self.entry.struct_actual += actual + " " + + def create_parameter_list(self, ln, decl_type, args, + splitter, declaration_name): + """ + Creates a list of parameters, storing them at self.entry. + """ + + # temporarily replace all commas inside function pointer definition + arg_expr = KernRe(r'(\([^\),]+),') + while arg_expr.search(args): + args = arg_expr.sub(r"\1#", args) + + for arg in args.split(splitter): + # Strip comments + arg = KernRe(r'\/\*.*\*\/').sub('', arg) + + # Ignore argument attributes + arg = KernRe(r'\sPOS0?\s').sub(' ', arg) + + # Strip leading/trailing spaces + arg = arg.strip() + arg = KernRe(r'\s+').sub(' ', arg, count=1) + + if arg.startswith('#'): + # Treat preprocessor directive as a typeless variable just to fill + # corresponding data structures "correctly". Catch it later in + # output_* subs. + + # Treat preprocessor directive as a typeless variable + self.push_parameter(ln, decl_type, arg, "", + "", declaration_name) + + elif KernRe(r'\(.+\)\s*\(').search(arg): + # Pointer-to-function + + arg = arg.replace('#', ',') + + r = KernRe(r'[^\(]+\(\*?\s*([\w\[\]\.]*)\s*\)') + if r.match(arg): + param = r.group(1) + else: + self.emit_msg(ln, f"Invalid param: {arg}") + param = arg + + dtype = KernRe(r'([^\(]+\(\*?)\s*' + re.escape(param)).sub(r'\1', arg) + self.save_struct_actual(param) + self.push_parameter(ln, decl_type, param, dtype, + arg, declaration_name) + + elif KernRe(r'\(.+\)\s*\[').search(arg): + # Array-of-pointers + + arg = arg.replace('#', ',') + r = KernRe(r'[^\(]+\(\s*\*\s*([\w\[\]\.]*?)\s*(\s*\[\s*[\w]+\s*\]\s*)*\)') + if r.match(arg): + param = r.group(1) + else: + self.emit_msg(ln, f"Invalid param: {arg}") + param = arg + + dtype = KernRe(r'([^\(]+\(\*?)\s*' + re.escape(param)).sub(r'\1', arg) + + self.save_struct_actual(param) + self.push_parameter(ln, decl_type, param, dtype, + arg, declaration_name) + + elif arg: + arg = KernRe(r'\s*:\s*').sub(":", arg) + arg = KernRe(r'\s*\[').sub('[', arg) + + args = KernRe(r'\s*,\s*').split(arg) + if args[0] and '*' in args[0]: + args[0] = re.sub(r'(\*+)\s*', r' \1', args[0]) + + first_arg = [] + r = KernRe(r'^(.*\s+)(.*?\[.*\].*)$') + if args[0] and r.match(args[0]): + args.pop(0) + first_arg.extend(r.group(1)) + first_arg.append(r.group(2)) + else: + first_arg = KernRe(r'\s+').split(args.pop(0)) + + args.insert(0, first_arg.pop()) + dtype = ' '.join(first_arg) + + for param in args: + if KernRe(r'^(\*+)\s*(.*)').match(param): + r = KernRe(r'^(\*+)\s*(.*)') + if not r.match(param): + self.emit_msg(ln, f"Invalid param: {param}") + continue + + param = r.group(1) + + self.save_struct_actual(r.group(2)) + self.push_parameter(ln, decl_type, r.group(2), + f"{dtype} {r.group(1)}", + arg, declaration_name) + + elif KernRe(r'(.*?):(\w+)').search(param): + r = KernRe(r'(.*?):(\w+)') + if not r.match(param): + self.emit_msg(ln, f"Invalid param: {param}") + continue + + if dtype != "": # Skip unnamed bit-fields + self.save_struct_actual(r.group(1)) + self.push_parameter(ln, decl_type, r.group(1), + f"{dtype}:{r.group(2)}", + arg, declaration_name) + else: + self.save_struct_actual(param) + self.push_parameter(ln, decl_type, param, dtype, + arg, declaration_name) + + def check_sections(self, ln, decl_name, decl_type, sectcheck, prmscheck): + """ + Check for errors inside sections, emitting warnings if not found + parameters are described. + """ + + sects = sectcheck.split() + prms = prmscheck.split() + err = False + + for sx in range(len(sects)): # pylint: disable=C0200 + err = True + for px in range(len(prms)): # pylint: disable=C0200 + prm_clean = prms[px] + prm_clean = KernRe(r'\[.*\]').sub('', prm_clean) + prm_clean = attribute.sub('', prm_clean) + + # ignore array size in a parameter string; + # however, the original param string may contain + # spaces, e.g.: addr[6 + 2] + # and this appears in @prms as "addr[6" since the + # parameter list is split at spaces; + # hence just ignore "[..." for the sections check; + prm_clean = KernRe(r'\[.*').sub('', prm_clean) + + if prm_clean == sects[sx]: + err = False + break + + if err: + if decl_type == 'function': + dname = f"{decl_type} parameter" + else: + dname = f"{decl_type} member" + + self.emit_msg(ln, + f"Excess {dname} '{sects[sx]}' description in '{decl_name}'") + + def check_return_section(self, ln, declaration_name, return_type): + """ + If the function doesn't return void, warns about the lack of a + return description. + """ + + if not self.config.wreturn: + return + + # Ignore an empty return type (It's a macro) + # Ignore functions with a "void" return type (but not "void *") + if not return_type or KernRe(r'void\s*\w*\s*$').search(return_type): + return + + if not self.entry.sections.get("Return", None): + self.emit_msg(ln, + f"No description found for return value of '{declaration_name}'") + + def dump_struct(self, ln, proto): + """ + Store an entry for an struct or union + """ + + type_pattern = r'(struct|union)' + + qualifiers = [ + "__attribute__", + "__packed", + "__aligned", + "____cacheline_aligned_in_smp", + "____cacheline_aligned", + ] + + definition_body = r'\{(.*)\}\s*' + "(?:" + '|'.join(qualifiers) + ")?" + struct_members = KernRe(type_pattern + r'([^\{\};]+)(\{)([^\{\}]*)(\})([^\{\}\;]*)(\;)') + + # Extract struct/union definition + members = None + declaration_name = None + decl_type = None + + r = KernRe(type_pattern + r'\s+(\w+)\s*' + definition_body) + if r.search(proto): + decl_type = r.group(1) + declaration_name = r.group(2) + members = r.group(3) + else: + r = KernRe(r'typedef\s+' + type_pattern + r'\s*' + definition_body + r'\s*(\w+)\s*;') + + if r.search(proto): + decl_type = r.group(1) + declaration_name = r.group(3) + members = r.group(2) + + if not members: + self.emit_msg(ln, f"{proto} error: Cannot parse struct or union!") + return + + if self.entry.identifier != declaration_name: + self.emit_msg(ln, + f"expecting prototype for {decl_type} {self.entry.identifier}. Prototype was for {decl_type} {declaration_name} instead\n") + return + + args_pattern = r'([^,)]+)' + + sub_prefixes = [ + (KernRe(r'\/\*\s*private:.*?\/\*\s*public:.*?\*\/', re.S | re.I), ''), + (KernRe(r'\/\*\s*private:.*', re.S | re.I), ''), + + # Strip comments + (KernRe(r'\/\*.*?\*\/', re.S), ''), + + # Strip attributes + (attribute, ' '), + (KernRe(r'\s*__aligned\s*\([^;]*\)', re.S), ' '), + (KernRe(r'\s*__counted_by\s*\([^;]*\)', re.S), ' '), + (KernRe(r'\s*__counted_by_(le|be)\s*\([^;]*\)', re.S), ' '), + (KernRe(r'\s*__packed\s*', re.S), ' '), + (KernRe(r'\s*CRYPTO_MINALIGN_ATTR', re.S), ' '), + (KernRe(r'\s*____cacheline_aligned_in_smp', re.S), ' '), + (KernRe(r'\s*____cacheline_aligned', re.S), ' '), + + # Unwrap struct_group macros based on this definition: + # __struct_group(TAG, NAME, ATTRS, MEMBERS...) + # which has variants like: struct_group(NAME, MEMBERS...) + # Only MEMBERS arguments require documentation. + # + # Parsing them happens on two steps: + # + # 1. drop struct group arguments that aren't at MEMBERS, + # storing them as STRUCT_GROUP(MEMBERS) + # + # 2. remove STRUCT_GROUP() ancillary macro. + # + # The original logic used to remove STRUCT_GROUP() using an + # advanced regex: + # + # \bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*; + # + # with two patterns that are incompatible with + # Python re module, as it has: + # + # - a recursive pattern: (?1) + # - an atomic grouping: (?>...) + # + # I tried a simpler version: but it didn't work either: + # \bSTRUCT_GROUP\(([^\)]+)\)[^;]*; + # + # As it doesn't properly match the end parenthesis on some cases. + # + # So, a better solution was crafted: there's now a NestedMatch + # class that ensures that delimiters after a search are properly + # matched. So, the implementation to drop STRUCT_GROUP() will be + # handled in separate. + + (KernRe(r'\bstruct_group\s*\(([^,]*,)', re.S), r'STRUCT_GROUP('), + (KernRe(r'\bstruct_group_attr\s*\(([^,]*,){2}', re.S), r'STRUCT_GROUP('), + (KernRe(r'\bstruct_group_tagged\s*\(([^,]*),([^,]*),', re.S), r'struct \1 \2; STRUCT_GROUP('), + (KernRe(r'\b__struct_group\s*\(([^,]*,){3}', re.S), r'STRUCT_GROUP('), + + # Replace macros + # + # TODO: use NestedMatch for FOO($1, $2, ...) matches + # + # it is better to also move those to the NestedMatch logic, + # to ensure that parenthesis will be properly matched. + + (KernRe(r'__ETHTOOL_DECLARE_LINK_MODE_MASK\s*\(([^\)]+)\)', re.S), r'DECLARE_BITMAP(\1, __ETHTOOL_LINK_MODE_MASK_NBITS)'), + (KernRe(r'DECLARE_PHY_INTERFACE_MASK\s*\(([^\)]+)\)', re.S), r'DECLARE_BITMAP(\1, PHY_INTERFACE_MODE_MAX)'), + (KernRe(r'DECLARE_BITMAP\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'unsigned long \1[BITS_TO_LONGS(\2)]'), + (KernRe(r'DECLARE_HASHTABLE\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'unsigned long \1[1 << ((\2) - 1)]'), + (KernRe(r'DECLARE_KFIFO\s*\(' + args_pattern + r',\s*' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\2 *\1'), + (KernRe(r'DECLARE_KFIFO_PTR\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\2 *\1'), + (KernRe(r'(?:__)?DECLARE_FLEX_ARRAY\s*\(' + args_pattern + r',\s*' + args_pattern + r'\)', re.S), r'\1 \2[]'), + (KernRe(r'DEFINE_DMA_UNMAP_ADDR\s*\(' + args_pattern + r'\)', re.S), r'dma_addr_t \1'), + (KernRe(r'DEFINE_DMA_UNMAP_LEN\s*\(' + args_pattern + r'\)', re.S), r'__u32 \1'), + ] + + # Regexes here are guaranteed to have the end limiter matching + # the start delimiter. Yet, right now, only one replace group + # is allowed. + + sub_nested_prefixes = [ + (re.compile(r'\bSTRUCT_GROUP\('), r'\1'), + ] + + for search, sub in sub_prefixes: + members = search.sub(sub, members) + + nested = NestedMatch() + + for search, sub in sub_nested_prefixes: + members = nested.sub(search, sub, members) + + # Keeps the original declaration as-is + declaration = members + + # Split nested struct/union elements + # + # This loop was simpler at the original kernel-doc perl version, as + # while ($members =~ m/$struct_members/) { ... } + # reads 'members' string on each interaction. + # + # Python behavior is different: it parses 'members' only once, + # creating a list of tuples from the first interaction. + # + # On other words, this won't get nested structs. + # + # So, we need to have an extra loop on Python to override such + # re limitation. + + while True: + tuples = struct_members.findall(members) + if not tuples: + break + + for t in tuples: + newmember = "" + maintype = t[0] + s_ids = t[5] + content = t[3] + + oldmember = "".join(t) + + for s_id in s_ids.split(','): + s_id = s_id.strip() + + newmember += f"{maintype} {s_id}; " + s_id = KernRe(r'[:\[].*').sub('', s_id) + s_id = KernRe(r'^\s*\**(\S+)\s*').sub(r'\1', s_id) + + for arg in content.split(';'): + arg = arg.strip() + + if not arg: + continue + + r = KernRe(r'^([^\(]+\(\*?\s*)([\w\.]*)(\s*\).*)') + if r.match(arg): + # Pointer-to-function + dtype = r.group(1) + name = r.group(2) + extra = r.group(3) + + if not name: + continue + + if not s_id: + # Anonymous struct/union + newmember += f"{dtype}{name}{extra}; " + else: + newmember += f"{dtype}{s_id}.{name}{extra}; " + + else: + arg = arg.strip() + # Handle bitmaps + arg = KernRe(r':\s*\d+\s*').sub('', arg) + + # Handle arrays + arg = KernRe(r'\[.*\]').sub('', arg) + + # Handle multiple IDs + arg = KernRe(r'\s*,\s*').sub(',', arg) + + r = KernRe(r'(.*)\s+([\S+,]+)') + + if r.search(arg): + dtype = r.group(1) + names = r.group(2) + else: + newmember += f"{arg}; " + continue + + for name in names.split(','): + name = KernRe(r'^\s*\**(\S+)\s*').sub(r'\1', name).strip() + + if not name: + continue + + if not s_id: + # Anonymous struct/union + newmember += f"{dtype} {name}; " + else: + newmember += f"{dtype} {s_id}.{name}; " + + members = members.replace(oldmember, newmember) + + # Ignore other nested elements, like enums + members = re.sub(r'(\{[^\{\}]*\})', '', members) + + self.create_parameter_list(ln, decl_type, members, ';', + declaration_name) + self.check_sections(ln, declaration_name, decl_type, + self.entry.sectcheck, self.entry.struct_actual) + + # Adjust declaration for better display + declaration = KernRe(r'([\{;])').sub(r'\1\n', declaration) + declaration = KernRe(r'\}\s+;').sub('};', declaration) + + # Better handle inlined enums + while True: + r = KernRe(r'(enum\s+\{[^\}]+),([^\n])') + if not r.search(declaration): + break + + declaration = r.sub(r'\1,\n\2', declaration) + + def_args = declaration.split('\n') + level = 1 + declaration = "" + for clause in def_args: + + clause = clause.strip() + clause = KernRe(r'\s+').sub(' ', clause, count=1) + + if not clause: + continue + + if '}' in clause and level > 1: + level -= 1 + + if not KernRe(r'^\s*#').match(clause): + declaration += "\t" * level + + declaration += "\t" + clause + "\n" + if "{" in clause and "}" not in clause: + level += 1 + + self.output_declaration(decl_type, declaration_name, + struct=declaration_name, + definition=declaration, + parameterlist=self.entry.parameterlist, + parameterdescs=self.entry.parameterdescs, + parametertypes=self.entry.parametertypes, + parameterdesc_start_lines=self.entry.parameterdesc_start_lines, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines, + purpose=self.entry.declaration_purpose) + + def dump_enum(self, ln, proto): + """ + Stores an enum inside self.entries array. + """ + + # Ignore members marked private + proto = KernRe(r'\/\*\s*private:.*?\/\*\s*public:.*?\*\/', flags=re.S).sub('', proto) + proto = KernRe(r'\/\*\s*private:.*}', flags=re.S).sub('}', proto) + + # Strip comments + proto = KernRe(r'\/\*.*?\*\/', flags=re.S).sub('', proto) + + # Strip #define macros inside enums + proto = KernRe(r'#\s*((define|ifdef|if)\s+|endif)[^;]*;', flags=re.S).sub('', proto) + + members = None + declaration_name = None + + r = KernRe(r'typedef\s+enum\s*\{(.*)\}\s*(\w*)\s*;') + if r.search(proto): + declaration_name = r.group(2) + members = r.group(1).rstrip() + else: + r = KernRe(r'enum\s+(\w*)\s*\{(.*)\}') + if r.match(proto): + declaration_name = r.group(1) + members = r.group(2).rstrip() + + if not members: + self.emit_msg(ln, f"{proto}: error: Cannot parse enum!") + return + + if self.entry.identifier != declaration_name: + if self.entry.identifier == "": + self.emit_msg(ln, + f"{proto}: wrong kernel-doc identifier on prototype") + else: + self.emit_msg(ln, + f"expecting prototype for enum {self.entry.identifier}. Prototype was for enum {declaration_name} instead") + return + + if not declaration_name: + declaration_name = "(anonymous)" + + member_set = set() + + members = KernRe(r'\([^;]*?[\)]').sub('', members) + + for arg in members.split(','): + if not arg: + continue + arg = KernRe(r'^\s*(\w+).*').sub(r'\1', arg) + self.entry.parameterlist.append(arg) + if arg not in self.entry.parameterdescs: + self.entry.parameterdescs[arg] = self.undescribed + self.emit_msg(ln, + f"Enum value '{arg}' not described in enum '{declaration_name}'") + member_set.add(arg) + + for k in self.entry.parameterdescs: + if k not in member_set: + self.emit_msg(ln, + f"Excess enum value '%{k}' description in '{declaration_name}'") + + self.output_declaration('enum', declaration_name, + enum=declaration_name, + parameterlist=self.entry.parameterlist, + parameterdescs=self.entry.parameterdescs, + parameterdesc_start_lines=self.entry.parameterdesc_start_lines, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines, + purpose=self.entry.declaration_purpose) + + def dump_declaration(self, ln, prototype): + """ + Stores a data declaration inside self.entries array. + """ + + if self.entry.decl_type == "enum": + self.dump_enum(ln, prototype) + return + + if self.entry.decl_type == "typedef": + self.dump_typedef(ln, prototype) + return + + if self.entry.decl_type in ["union", "struct"]: + self.dump_struct(ln, prototype) + return + + self.output_declaration(self.entry.decl_type, prototype, + entry=self.entry) + + def dump_function(self, ln, prototype): + """ + Stores a function of function macro inside self.entries array. + """ + + func_macro = False + return_type = '' + decl_type = 'function' + + # Prefixes that would be removed + sub_prefixes = [ + (r"^static +", "", 0), + (r"^extern +", "", 0), + (r"^asmlinkage +", "", 0), + (r"^inline +", "", 0), + (r"^__inline__ +", "", 0), + (r"^__inline +", "", 0), + (r"^__always_inline +", "", 0), + (r"^noinline +", "", 0), + (r"^__FORTIFY_INLINE +", "", 0), + (r"__init +", "", 0), + (r"__init_or_module +", "", 0), + (r"__deprecated +", "", 0), + (r"__flatten +", "", 0), + (r"__meminit +", "", 0), + (r"__must_check +", "", 0), + (r"__weak +", "", 0), + (r"__sched +", "", 0), + (r"_noprof", "", 0), + (r"__printf\s*\(\s*\d*\s*,\s*\d*\s*\) +", "", 0), + (r"__(?:re)?alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) +", "", 0), + (r"__diagnose_as\s*\(\s*\S+\s*(?:,\s*\d+\s*)*\) +", "", 0), + (r"DECL_BUCKET_PARAMS\s*\(\s*(\S+)\s*,\s*(\S+)\s*\)", r"\1, \2", 0), + (r"__attribute_const__ +", "", 0), + + # It seems that Python support for re.X is broken: + # At least for me (Python 3.13), this didn't work +# (r""" +# __attribute__\s*\(\( +# (?: +# [\w\s]+ # attribute name +# (?:\([^)]*\))? # attribute arguments +# \s*,? # optional comma at the end +# )+ +# \)\)\s+ +# """, "", re.X), + + # So, remove whitespaces and comments from it + (r"__attribute__\s*\(\((?:[\w\s]+(?:\([^)]*\))?\s*,?)+\)\)\s+", "", 0), + ] + + for search, sub, flags in sub_prefixes: + prototype = KernRe(search, flags).sub(sub, prototype) + + # Macros are a special case, as they change the prototype format + new_proto = KernRe(r"^#\s*define\s+").sub("", prototype) + if new_proto != prototype: + is_define_proto = True + prototype = new_proto + else: + is_define_proto = False + + # Yes, this truly is vile. We are looking for: + # 1. Return type (may be nothing if we're looking at a macro) + # 2. Function name + # 3. Function parameters. + # + # All the while we have to watch out for function pointer parameters + # (which IIRC is what the two sections are for), C types (these + # regexps don't even start to express all the possibilities), and + # so on. + # + # If you mess with these regexps, it's a good idea to check that + # the following functions' documentation still comes out right: + # - parport_register_device (function pointer parameters) + # - atomic_set (macro) + # - pci_match_device, __copy_to_user (long return type) + + name = r'[a-zA-Z0-9_~:]+' + prototype_end1 = r'[^\(]*' + prototype_end2 = r'[^\{]*' + prototype_end = fr'\(({prototype_end1}|{prototype_end2})\)' + + # Besides compiling, Perl qr{[\w\s]+} works as a non-capturing group. + # So, this needs to be mapped in Python with (?:...)? or (?:...)+ + + type1 = r'(?:[\w\s]+)?' + type2 = r'(?:[\w\s]+\*+)+' + + found = False + + if is_define_proto: + r = KernRe(r'^()(' + name + r')\s+') + + if r.search(prototype): + return_type = '' + declaration_name = r.group(2) + func_macro = True + + found = True + + if not found: + patterns = [ + rf'^()({name})\s*{prototype_end}', + rf'^({type1})\s+({name})\s*{prototype_end}', + rf'^({type2})\s*({name})\s*{prototype_end}', + ] + + for p in patterns: + r = KernRe(p) + + if r.match(prototype): + + return_type = r.group(1) + declaration_name = r.group(2) + args = r.group(3) + + self.create_parameter_list(ln, decl_type, args, ',', + declaration_name) + + found = True + break + if not found: + self.emit_msg(ln, + f"cannot understand function prototype: '{prototype}'") + return + + if self.entry.identifier != declaration_name: + self.emit_msg(ln, + f"expecting prototype for {self.entry.identifier}(). Prototype was for {declaration_name}() instead") + return + + prms = " ".join(self.entry.parameterlist) + self.check_sections(ln, declaration_name, "function", + self.entry.sectcheck, prms) + + self.check_return_section(ln, declaration_name, return_type) + + if 'typedef' in return_type: + self.output_declaration(decl_type, declaration_name, + function=declaration_name, + typedef=True, + functiontype=return_type, + parameterlist=self.entry.parameterlist, + parameterdescs=self.entry.parameterdescs, + parametertypes=self.entry.parametertypes, + parameterdesc_start_lines=self.entry.parameterdesc_start_lines, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines, + purpose=self.entry.declaration_purpose, + func_macro=func_macro) + else: + self.output_declaration(decl_type, declaration_name, + function=declaration_name, + typedef=False, + functiontype=return_type, + parameterlist=self.entry.parameterlist, + parameterdescs=self.entry.parameterdescs, + parametertypes=self.entry.parametertypes, + parameterdesc_start_lines=self.entry.parameterdesc_start_lines, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines, + purpose=self.entry.declaration_purpose, + func_macro=func_macro) + + def dump_typedef(self, ln, proto): + """ + Stores a typedef inside self.entries array. + """ + + typedef_type = r'((?:\s+[\w\*]+\b){0,7}\s+(?:\w+\b|\*+))\s*' + typedef_ident = r'\*?\s*(\w\S+)\s*' + typedef_args = r'\s*\((.*)\);' + + typedef1 = KernRe(r'typedef' + typedef_type + r'\(' + typedef_ident + r'\)' + typedef_args) + typedef2 = KernRe(r'typedef' + typedef_type + typedef_ident + typedef_args) + + # Strip comments + proto = KernRe(r'/\*.*?\*/', flags=re.S).sub('', proto) + + # Parse function typedef prototypes + for r in [typedef1, typedef2]: + if not r.match(proto): + continue + + return_type = r.group(1).strip() + declaration_name = r.group(2) + args = r.group(3) + + if self.entry.identifier != declaration_name: + self.emit_msg(ln, + f"expecting prototype for typedef {self.entry.identifier}. Prototype was for typedef {declaration_name} instead\n") + return + + decl_type = 'function' + self.create_parameter_list(ln, decl_type, args, ',', declaration_name) + + self.output_declaration(decl_type, declaration_name, + function=declaration_name, + typedef=True, + functiontype=return_type, + parameterlist=self.entry.parameterlist, + parameterdescs=self.entry.parameterdescs, + parametertypes=self.entry.parametertypes, + parameterdesc_start_lines=self.entry.parameterdesc_start_lines, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines, + purpose=self.entry.declaration_purpose) + return + + # Handle nested parentheses or brackets + r = KernRe(r'(\(*.\)\s*|\[*.\]\s*);$') + while r.search(proto): + proto = r.sub('', proto) + + # Parse simple typedefs + r = KernRe(r'typedef.*\s+(\w+)\s*;') + if r.match(proto): + declaration_name = r.group(1) + + if self.entry.identifier != declaration_name: + self.emit_msg(ln, + f"expecting prototype for typedef {self.entry.identifier}. Prototype was for typedef {declaration_name} instead\n") + return + + self.output_declaration('typedef', declaration_name, + typedef=declaration_name, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines, + purpose=self.entry.declaration_purpose) + return + + self.emit_msg(ln, "error: Cannot parse typedef!") + + @staticmethod + def process_export(function_set, line): + """ + process EXPORT_SYMBOL* tags + + This method doesn't use any variable from the class, so declare it + with a staticmethod decorator. + """ + + # Note: it accepts only one EXPORT_SYMBOL* per line, as having + # multiple export lines would violate Kernel coding style. + + if export_symbol.search(line): + symbol = export_symbol.group(2) + function_set.add(symbol) + return + + if export_symbol_ns.search(line): + symbol = export_symbol_ns.group(2) + function_set.add(symbol) + + def process_normal(self, ln, line): + """ + STATE_NORMAL: looking for the /** to begin everything. + """ + + if not doc_start.match(line): + return + + # start a new entry + self.reset_state(ln) + self.entry.in_doc_sect = False + + # next line is always the function name + self.state = state.NAME + + def process_name(self, ln, line): + """ + STATE_NAME: Looking for the "name - description" line + """ + + if doc_block.search(line): + self.entry.new_start_line = ln + + if not doc_block.group(1): + self.entry.section = self.section_intro + else: + self.entry.section = doc_block.group(1) + + self.entry.identifier = self.entry.section + self.state = state.DOCBLOCK + return + + if doc_decl.search(line): + self.entry.identifier = doc_decl.group(1) + self.entry.is_kernel_comment = False + + decl_start = str(doc_com) # comment block asterisk + fn_type = r"(?:\w+\s*\*\s*)?" # type (for non-functions) + parenthesis = r"(?:\(\w*\))?" # optional parenthesis on function + decl_end = r"(?:[-:].*)" # end of the name part + + # test for pointer declaration type, foo * bar() - desc + r = KernRe(fr"^{decl_start}([\w\s]+?){parenthesis}?\s*{decl_end}?$") + if r.search(line): + self.entry.identifier = r.group(1) + + # Test for data declaration + r = KernRe(r"^\s*\*?\s*(struct|union|enum|typedef)\b\s*(\w*)") + if r.search(line): + self.entry.decl_type = r.group(1) + self.entry.identifier = r.group(2) + self.entry.is_kernel_comment = True + else: + # Look for foo() or static void foo() - description; + # or misspelt identifier + + r1 = KernRe(fr"^{decl_start}{fn_type}(\w+)\s*{parenthesis}\s*{decl_end}?$") + r2 = KernRe(fr"^{decl_start}{fn_type}(\w+[^-:]*){parenthesis}\s*{decl_end}$") + + for r in [r1, r2]: + if r.search(line): + self.entry.identifier = r.group(1) + self.entry.decl_type = "function" + + r = KernRe(r"define\s+") + self.entry.identifier = r.sub("", self.entry.identifier) + self.entry.is_kernel_comment = True + break + + self.entry.identifier = self.entry.identifier.strip(" ") + + self.state = state.BODY + + # if there's no @param blocks need to set up default section here + self.entry.section = SECTION_DEFAULT + self.entry.new_start_line = ln + 1 + + r = KernRe("[-:](.*)") + if r.search(line): + # strip leading/trailing/multiple spaces + self.entry.descr = r.group(1).strip(" ") + + r = KernRe(r"\s+") + self.entry.descr = r.sub(" ", self.entry.descr) + self.entry.declaration_purpose = self.entry.descr + self.state = state.BODY_MAYBE + else: + self.entry.declaration_purpose = "" + + if not self.entry.is_kernel_comment: + self.emit_msg(ln, + f"This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst\n{line}") + self.state = state.NORMAL + + if not self.entry.declaration_purpose and self.config.wshort_desc: + self.emit_msg(ln, + f"missing initial short description on line:\n{line}") + + if not self.entry.identifier and self.entry.decl_type != "enum": + self.emit_msg(ln, + f"wrong kernel-doc identifier on line:\n{line}") + self.state = state.NORMAL + + if self.config.verbose: + self.emit_msg(ln, + f"Scanning doc for {self.entry.decl_type} {self.entry.identifier}", + warning=False) + + return + + # Failed to find an identifier. Emit a warning + self.emit_msg(ln, f"Cannot find identifier on line:\n{line}") + + def process_body(self, ln, line): + """ + STATE_BODY and STATE_BODY_MAYBE: the bulk of a kerneldoc comment. + """ + + if self.state == state.BODY_WITH_BLANK_LINE: + r = KernRe(r"\s*\*\s?\S") + if r.match(line): + self.dump_section() + self.entry.section = SECTION_DEFAULT + self.entry.new_start_line = ln + self.entry.contents = "" + + if doc_sect.search(line): + self.entry.in_doc_sect = True + newsection = doc_sect.group(1) + + if newsection.lower() in ["description", "context"]: + newsection = newsection.title() + + # Special case: @return is a section, not a param description + if newsection.lower() in ["@return", "@returns", + "return", "returns"]: + newsection = "Return" + + # Perl kernel-doc has a check here for contents before sections. + # the logic there is always false, as in_doc_sect variable is + # always true. So, just don't implement Wcontents_before_sections + + # .title() + newcontents = doc_sect.group(2) + if not newcontents: + newcontents = "" + + if self.entry.contents.strip("\n"): + self.dump_section() + + self.entry.new_start_line = ln + self.entry.section = newsection + self.entry.leading_space = None + + self.entry.contents = newcontents.lstrip() + if self.entry.contents: + self.entry.contents += "\n" + + self.state = state.BODY + return + + if doc_end.search(line): + self.dump_section() + + # Look for doc_com + <text> + doc_end: + r = KernRe(r'\s*\*\s*[a-zA-Z_0-9:\.]+\*/') + if r.match(line): + self.emit_msg(ln, f"suspicious ending line: {line}") + + self.entry.prototype = "" + self.entry.new_start_line = ln + 1 + + self.state = state.PROTO + return + + if doc_content.search(line): + cont = doc_content.group(1) + + if cont == "": + if self.entry.section == self.section_context: + self.dump_section() + + self.entry.new_start_line = ln + self.state = state.BODY + else: + if self.entry.section != SECTION_DEFAULT: + self.state = state.BODY_WITH_BLANK_LINE + else: + self.state = state.BODY + + self.entry.contents += "\n" + + elif self.state == state.BODY_MAYBE: + + # Continued declaration purpose + self.entry.declaration_purpose = self.entry.declaration_purpose.rstrip() + self.entry.declaration_purpose += " " + cont + + r = KernRe(r"\s+") + self.entry.declaration_purpose = r.sub(' ', + self.entry.declaration_purpose) + + else: + if self.entry.section.startswith('@') or \ + self.entry.section == self.section_context: + if self.entry.leading_space is None: + r = KernRe(r'^(\s+)') + if r.match(cont): + self.entry.leading_space = len(r.group(1)) + else: + self.entry.leading_space = 0 + + # Double-check if leading space are realy spaces + pos = 0 + for i in range(0, self.entry.leading_space): + if cont[i] != " ": + break + pos += 1 + + cont = cont[pos:] + + # NEW LOGIC: + # In case it is different, update it + if self.entry.leading_space != pos: + self.entry.leading_space = pos + + self.entry.contents += cont + "\n" + return + + # Unknown line, ignore + self.emit_msg(ln, f"bad line: {line}") + + def process_inline(self, ln, line): + """STATE_INLINE: docbook comments within a prototype.""" + + if self.inline_doc_state == state.INLINE_NAME and \ + doc_inline_sect.search(line): + self.entry.section = doc_inline_sect.group(1) + self.entry.new_start_line = ln + + self.entry.contents = doc_inline_sect.group(2).lstrip() + if self.entry.contents != "": + self.entry.contents += "\n" + + self.inline_doc_state = state.INLINE_TEXT + # Documentation block end */ + return + + if doc_inline_end.search(line): + if self.entry.contents not in ["", "\n"]: + self.dump_section() + + self.state = state.PROTO + self.inline_doc_state = state.INLINE_NA + return + + if doc_content.search(line): + if self.inline_doc_state == state.INLINE_TEXT: + self.entry.contents += doc_content.group(1) + "\n" + if not self.entry.contents.strip(" ").rstrip("\n"): + self.entry.contents = "" + + elif self.inline_doc_state == state.INLINE_NAME: + self.emit_msg(ln, + f"Incorrect use of kernel-doc format: {line}") + + self.inline_doc_state = state.INLINE_ERROR + + def syscall_munge(self, ln, proto): # pylint: disable=W0613 + """ + Handle syscall definitions + """ + + is_void = False + + # Strip newlines/CR's + proto = re.sub(r'[\r\n]+', ' ', proto) + + # Check if it's a SYSCALL_DEFINE0 + if 'SYSCALL_DEFINE0' in proto: + is_void = True + + # Replace SYSCALL_DEFINE with correct return type & function name + proto = KernRe(r'SYSCALL_DEFINE.*\(').sub('long sys_', proto) + + r = KernRe(r'long\s+(sys_.*?),') + if r.search(proto): + proto = KernRe(',').sub('(', proto, count=1) + elif is_void: + proto = KernRe(r'\)').sub('(void)', proto, count=1) + + # Now delete all of the odd-numbered commas in the proto + # so that argument types & names don't have a comma between them + count = 0 + length = len(proto) + + if is_void: + length = 0 # skip the loop if is_void + + for ix in range(length): + if proto[ix] == ',': + count += 1 + if count % 2 == 1: + proto = proto[:ix] + ' ' + proto[ix + 1:] + + return proto + + def tracepoint_munge(self, ln, proto): + """ + Handle tracepoint definitions + """ + + tracepointname = None + tracepointargs = None + + # Match tracepoint name based on different patterns + r = KernRe(r'TRACE_EVENT\((.*?),') + if r.search(proto): + tracepointname = r.group(1) + + r = KernRe(r'DEFINE_SINGLE_EVENT\((.*?),') + if r.search(proto): + tracepointname = r.group(1) + + r = KernRe(r'DEFINE_EVENT\((.*?),(.*?),') + if r.search(proto): + tracepointname = r.group(2) + + if tracepointname: + tracepointname = tracepointname.lstrip() + + r = KernRe(r'TP_PROTO\((.*?)\)') + if r.search(proto): + tracepointargs = r.group(1) + + if not tracepointname or not tracepointargs: + self.emit_msg(ln, + f"Unrecognized tracepoint format:\n{proto}\n") + else: + proto = f"static inline void trace_{tracepointname}({tracepointargs})" + self.entry.identifier = f"trace_{self.entry.identifier}" + + return proto + + def process_proto_function(self, ln, line): + """Ancillary routine to process a function prototype""" + + # strip C99-style comments to end of line + r = KernRe(r"\/\/.*$", re.S) + line = r.sub('', line) + + if KernRe(r'\s*#\s*define').match(line): + self.entry.prototype = line + elif line.startswith('#'): + # Strip other macros like #ifdef/#ifndef/#endif/... + pass + else: + r = KernRe(r'([^\{]*)') + if r.match(line): + self.entry.prototype += r.group(1) + " " + + if '{' in line or ';' in line or KernRe(r'\s*#\s*define').match(line): + # strip comments + r = KernRe(r'/\*.*?\*/') + self.entry.prototype = r.sub('', self.entry.prototype) + + # strip newlines/cr's + r = KernRe(r'[\r\n]+') + self.entry.prototype = r.sub(' ', self.entry.prototype) + + # strip leading spaces + r = KernRe(r'^\s+') + self.entry.prototype = r.sub('', self.entry.prototype) + + # Handle self.entry.prototypes for function pointers like: + # int (*pcs_config)(struct foo) + + r = KernRe(r'^(\S+\s+)\(\s*\*(\S+)\)') + self.entry.prototype = r.sub(r'\1\2', self.entry.prototype) + + if 'SYSCALL_DEFINE' in self.entry.prototype: + self.entry.prototype = self.syscall_munge(ln, + self.entry.prototype) + + r = KernRe(r'TRACE_EVENT|DEFINE_EVENT|DEFINE_SINGLE_EVENT') + if r.search(self.entry.prototype): + self.entry.prototype = self.tracepoint_munge(ln, + self.entry.prototype) + + self.dump_function(ln, self.entry.prototype) + self.reset_state(ln) + + def process_proto_type(self, ln, line): + """Ancillary routine to process a type""" + + # Strip newlines/cr's. + line = KernRe(r'[\r\n]+', re.S).sub(' ', line) + + # Strip leading spaces + line = KernRe(r'^\s+', re.S).sub('', line) + + # Strip trailing spaces + line = KernRe(r'\s+$', re.S).sub('', line) + + # Strip C99-style comments to the end of the line + line = KernRe(r"\/\/.*$", re.S).sub('', line) + + # To distinguish preprocessor directive from regular declaration later. + if line.startswith('#'): + line += ";" + + r = KernRe(r'([^\{\};]*)([\{\};])(.*)') + while True: + if r.search(line): + if self.entry.prototype: + self.entry.prototype += " " + self.entry.prototype += r.group(1) + r.group(2) + + self.entry.brcount += r.group(2).count('{') + self.entry.brcount -= r.group(2).count('}') + + self.entry.brcount = max(self.entry.brcount, 0) + + if r.group(2) == ';' and self.entry.brcount == 0: + self.dump_declaration(ln, self.entry.prototype) + self.reset_state(ln) + break + + line = r.group(3) + else: + self.entry.prototype += line + break + + def process_proto(self, ln, line): + """STATE_PROTO: reading a function/whatever prototype.""" + + if doc_inline_oneline.search(line): + self.entry.section = doc_inline_oneline.group(1) + self.entry.contents = doc_inline_oneline.group(2) + + if self.entry.contents != "": + self.entry.contents += "\n" + self.dump_section(start_new=False) + + elif doc_inline_start.search(line): + self.state = state.INLINE + self.inline_doc_state = state.INLINE_NAME + + elif self.entry.decl_type == 'function': + self.process_proto_function(ln, line) + + else: + self.process_proto_type(ln, line) + + def process_docblock(self, ln, line): + """STATE_DOCBLOCK: within a DOC: block.""" + + if doc_end.search(line): + self.dump_section() + self.output_declaration("doc", self.entry.identifier, + sectionlist=self.entry.sectionlist, + sections=self.entry.sections, + section_start_lines=self.entry.section_start_lines) + self.reset_state(ln) + + elif doc_content.search(line): + self.entry.contents += doc_content.group(1) + "\n" + + def parse_export(self): + """ + Parses EXPORT_SYMBOL* macros from a single Kernel source file. + """ + + export_table = set() + + try: + with open(self.fname, "r", encoding="utf8", + errors="backslashreplace") as fp: + + for line in fp: + self.process_export(export_table, line) + + except IOError: + return None + + return export_table + + def parse_kdoc(self): + """ + Open and process each line of a C source file. + The parsing is controlled via a state machine, and the line is passed + to a different process function depending on the state. The process + function may update the state as needed. + + Besides parsing kernel-doc tags, it also parses export symbols. + """ + + cont = False + prev = "" + prev_ln = None + export_table = set() + + try: + with open(self.fname, "r", encoding="utf8", + errors="backslashreplace") as fp: + for ln, line in enumerate(fp): + + line = line.expandtabs().strip("\n") + + # Group continuation lines on prototypes + if self.state == state.PROTO: + if line.endswith("\\"): + prev += line.rstrip("\\") + cont = True + + if not prev_ln: + prev_ln = ln + + continue + + if cont: + ln = prev_ln + line = prev + line + prev = "" + cont = False + prev_ln = None + + self.config.log.debug("%d %s%s: %s", + ln, state.name[self.state], + state.inline_name[self.inline_doc_state], + line) + + # This is an optimization over the original script. + # There, when export_file was used for the same file, + # it was read twice. Here, we use the already-existing + # loop to parse exported symbols as well. + # + # TODO: It should be noticed that not all states are + # needed here. On a future cleanup, process export only + # at the states that aren't handling comment markups. + self.process_export(export_table, line) + + # Hand this line to the appropriate state handler + if self.state == state.NORMAL: + self.process_normal(ln, line) + elif self.state == state.NAME: + self.process_name(ln, line) + elif self.state in [state.BODY, state.BODY_MAYBE, + state.BODY_WITH_BLANK_LINE]: + self.process_body(ln, line) + elif self.state == state.INLINE: # scanning for inline parameters + self.process_inline(ln, line) + elif self.state == state.PROTO: + self.process_proto(ln, line) + elif self.state == state.DOCBLOCK: + self.process_docblock(ln, line) + except OSError: + self.config.log.error(f"Error: Cannot open file {self.fname}") + + return export_table, self.entries diff --git a/scripts/lib/kdoc/kdoc_re.py b/scripts/lib/kdoc/kdoc_re.py new file mode 100644 index 000000000000..e81695b273bf --- /dev/null +++ b/scripts/lib/kdoc/kdoc_re.py @@ -0,0 +1,273 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. + +""" +Regular expression ancillary classes. + +Those help caching regular expressions and do matching for kernel-doc. +""" + +import re + +# Local cache for regular expressions +re_cache = {} + + +class KernRe: + """ + Helper class to simplify regex declaration and usage, + + It calls re.compile for a given pattern. It also allows adding + regular expressions and define sub at class init time. + + Regular expressions can be cached via an argument, helping to speedup + searches. + """ + + def _add_regex(self, string, flags): + """ + Adds a new regex or re-use it from the cache. + """ + + if string in re_cache: + self.regex = re_cache[string] + else: + self.regex = re.compile(string, flags=flags) + + if self.cache: + re_cache[string] = self.regex + + def __init__(self, string, cache=True, flags=0): + """ + Compile a regular expression and initialize internal vars. + """ + + self.cache = cache + self.last_match = None + + self._add_regex(string, flags) + + def __str__(self): + """ + Return the regular expression pattern. + """ + return self.regex.pattern + + def __add__(self, other): + """ + Allows adding two regular expressions into one. + """ + + return KernRe(str(self) + str(other), cache=self.cache or other.cache, + flags=self.regex.flags | other.regex.flags) + + def match(self, string): + """ + Handles a re.match storing its results + """ + + self.last_match = self.regex.match(string) + return self.last_match + + def search(self, string): + """ + Handles a re.search storing its results + """ + + self.last_match = self.regex.search(string) + return self.last_match + + def findall(self, string): + """ + Alias to re.findall + """ + + return self.regex.findall(string) + + def split(self, string): + """ + Alias to re.split + """ + + return self.regex.split(string) + + def sub(self, sub, string, count=0): + """ + Alias to re.sub + """ + + return self.regex.sub(sub, string, count=count) + + def group(self, num): + """ + Returns the group results of the last match + """ + + return self.last_match.group(num) + + +class NestedMatch: + """ + Finding nested delimiters is hard with regular expressions. It is + even harder on Python with its normal re module, as there are several + advanced regular expressions that are missing. + + This is the case of this pattern: + + '\\bSTRUCT_GROUP(\\(((?:(?>[^)(]+)|(?1))*)\\))[^;]*;' + + which is used to properly match open/close parenthesis of the + string search STRUCT_GROUP(), + + Add a class that counts pairs of delimiters, using it to match and + replace nested expressions. + + The original approach was suggested by: + https://stackoverflow.com/questions/5454322/python-how-to-match-nested-parentheses-with-regex + + Although I re-implemented it to make it more generic and match 3 types + of delimiters. The logic checks if delimiters are paired. If not, it + will ignore the search string. + """ + + # TODO: make NestedMatch handle multiple match groups + # + # Right now, regular expressions to match it are defined only up to + # the start delimiter, e.g.: + # + # \bSTRUCT_GROUP\( + # + # is similar to: STRUCT_GROUP\((.*)\) + # except that the content inside the match group is delimiter's aligned. + # + # The content inside parenthesis are converted into a single replace + # group (e.g. r`\1'). + # + # It would be nice to change such definition to support multiple + # match groups, allowing a regex equivalent to. + # + # FOO\((.*), (.*), (.*)\) + # + # it is probably easier to define it not as a regular expression, but + # with some lexical definition like: + # + # FOO(arg1, arg2, arg3) + + DELIMITER_PAIRS = { + '{': '}', + '(': ')', + '[': ']', + } + + RE_DELIM = re.compile(r'[\{\}\[\]\(\)]') + + def _search(self, regex, line): + """ + Finds paired blocks for a regex that ends with a delimiter. + + The suggestion of using finditer to match pairs came from: + https://stackoverflow.com/questions/5454322/python-how-to-match-nested-parentheses-with-regex + but I ended using a different implementation to align all three types + of delimiters and seek for an initial regular expression. + + The algorithm seeks for open/close paired delimiters and place them + into a stack, yielding a start/stop position of each match when the + stack is zeroed. + + The algorithm shoud work fine for properly paired lines, but will + silently ignore end delimiters that preceeds an start delimiter. + This should be OK for kernel-doc parser, as unaligned delimiters + would cause compilation errors. So, we don't need to rise exceptions + to cover such issues. + """ + + stack = [] + + for match_re in regex.finditer(line): + start = match_re.start() + offset = match_re.end() + + d = line[offset - 1] + if d not in self.DELIMITER_PAIRS: + continue + + end = self.DELIMITER_PAIRS[d] + stack.append(end) + + for match in self.RE_DELIM.finditer(line[offset:]): + pos = match.start() + offset + + d = line[pos] + + if d in self.DELIMITER_PAIRS: + end = self.DELIMITER_PAIRS[d] + + stack.append(end) + continue + + # Does the end delimiter match what it is expected? + if stack and d == stack[-1]: + stack.pop() + + if not stack: + yield start, offset, pos + 1 + break + + def search(self, regex, line): + """ + This is similar to re.search: + + It matches a regex that it is followed by a delimiter, + returning occurrences only if all delimiters are paired. + """ + + for t in self._search(regex, line): + + yield line[t[0]:t[2]] + + def sub(self, regex, sub, line, count=0): + """ + This is similar to re.sub: + + It matches a regex that it is followed by a delimiter, + replacing occurrences only if all delimiters are paired. + + if r'\1' is used, it works just like re: it places there the + matched paired data with the delimiter stripped. + + If count is different than zero, it will replace at most count + items. + """ + out = "" + + cur_pos = 0 + n = 0 + + for start, end, pos in self._search(regex, line): + out += line[cur_pos:start] + + # Value, ignoring start/end delimiters + value = line[end:pos - 1] + + # replaces \1 at the sub string, if \1 is used there + new_sub = sub + new_sub = new_sub.replace(r'\1', value) + + out += new_sub + + # Drop end ';' if any + if line[pos] == ';': + pos += 1 + + cur_pos = pos + n += 1 + + if count and count >= n: + break + + # Append the remaining string + l = len(line) + out += line[cur_pos:l] + + return out diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index d853ddb3b28c..51367c2bfc21 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -31,6 +31,7 @@ set -e LD="$1" KBUILD_LDFLAGS="$2" LDFLAGS_vmlinux="$3" +VMLINUX="$4" is_enabled() { grep -q "^$1=y" include/config/auto.conf @@ -97,8 +98,8 @@ vmlinux_link() ldflags="${ldflags} ${wl}--strip-debug" fi - if is_enabled CONFIG_VMLINUX_MAP; then - ldflags="${ldflags} ${wl}-Map=${output}.map" + if [ -n "${generate_map}" ]; then + ldflags="${ldflags} ${wl}-Map=vmlinux.map" fi ${ld} ${ldflags} -o ${output} \ @@ -144,10 +145,6 @@ kallsyms() kallsymopt="${kallsymopt} --all-symbols" fi - if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then - kallsymopt="${kallsymopt} --absolute-percpu" - fi - info KSYMS "${2}.S" scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S" @@ -177,12 +174,14 @@ mksysmap() sorttable() { - ${objtree}/scripts/sorttable ${1} + ${NM} -S ${1} > .tmp_vmlinux.nm-sort + ${objtree}/scripts/sorttable -s .tmp_vmlinux.nm-sort ${1} } cleanup() { rm -f .btf.* + rm -f .tmp_vmlinux.nm-sort rm -f System.map rm -f vmlinux rm -f vmlinux.map @@ -210,6 +209,7 @@ fi btf_vmlinux_bin_o= kallsymso= strip_debug= +generate_map= if is_enabled CONFIG_KALLSYMS; then true > .tmp_vmlinux0.syms @@ -278,19 +278,27 @@ fi strip_debug= -vmlinux_link vmlinux +if is_enabled CONFIG_VMLINUX_MAP; then + generate_map=1 +fi + +vmlinux_link "${VMLINUX}" # fill in BTF IDs if is_enabled CONFIG_DEBUG_INFO_BTF; then - info BTFIDS vmlinux - ${RESOLVE_BTFIDS} vmlinux + info BTFIDS "${VMLINUX}" + RESOLVE_BTFIDS_ARGS="" + if is_enabled CONFIG_WERROR; then + RESOLVE_BTFIDS_ARGS=" --fatal_warnings " + fi + ${RESOLVE_BTFIDS} ${RESOLVE_BTFIDS_ARGS} "${VMLINUX}" fi -mksysmap vmlinux System.map +mksysmap "${VMLINUX}" System.map if is_enabled CONFIG_BUILDTIME_TABLE_SORT; then - info SORTTAB vmlinux - if ! sorttable vmlinux; then + info SORTTAB "${VMLINUX}" + if ! sorttable "${VMLINUX}"; then echo >&2 Failed to sort kernel tables exit 1 fi @@ -306,4 +314,4 @@ if is_enabled CONFIG_KALLSYMS; then fi # For fixdep -echo "vmlinux: $0" > .vmlinux.d +echo "${VMLINUX}: $0" > ".${VMLINUX}.d" diff --git a/scripts/make_fit.py b/scripts/make_fit.py index 4a1bb2f55861..1683e5ec6e67 100755 --- a/scripts/make_fit.py +++ b/scripts/make_fit.py @@ -279,7 +279,11 @@ def build_fit(args): if os.path.splitext(fname)[1] != '.dtb': continue - (model, compat, files) = process_dtb(fname, args) + try: + (model, compat, files) = process_dtb(fname, args) + except Exception as e: + sys.stderr.write(f"Error processing {fname}:\n") + raise e for fn in files: if fn not in fdts: diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index 91c91201212c..0d223b4a9445 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -14,17 +14,17 @@ fi case "$1" in binutils) - echo 2.25.0 + echo 2.30.0 ;; gcc) if [ "$ARCH" = parisc64 ]; then echo 12.0.0 else - echo 5.1.0 + echo 8.1.0 fi ;; llvm) - if [ "$SRCARCH" = s390 ]; then + if [ "$SRCARCH" = s390 -o "$SRCARCH" = x86 ]; then echo 15.0.0 elif [ "$SRCARCH" = loongarch ]; then echo 18.0.0 diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 9c7b404defbd..d3d00e85edf7 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -237,7 +237,6 @@ int main(void) DEVID(typec_device_id); DEVID_FIELD(typec_device_id, svid); - DEVID_FIELD(typec_device_id, mode); DEVID(tee_client_device_id); DEVID_FIELD(tee_client_device_id, uuid); diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 19ec72a69e90..00586119a25b 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1219,17 +1219,12 @@ static void do_tbsvc_entry(struct module *mod, void *symval) module_alias_printf(mod, true, "tbsvc:%s", alias); } -/* Looks like: typec:idNmN */ +/* Looks like: typec:idN */ static void do_typec_entry(struct module *mod, void *symval) { - char alias[256] = {}; - DEF_FIELD(symval, typec_device_id, svid); - DEF_FIELD(symval, typec_device_id, mode); - - ADD(alias, "m", mode != TYPEC_ANY_MODE, mode); - module_alias_printf(mod, false, "typec:id%04X%s", svid, alias); + module_alias_printf(mod, false, "typec:id%04X", svid); } /* Looks like: tee:uuid */ diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7ea59dc4926b..be89921d60b6 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -33,6 +33,10 @@ static bool module_enabled; static bool modversions; /* Is CONFIG_MODULE_SRCVERSION_ALL set? */ static bool all_versions; +/* Is CONFIG_BASIC_MODVERSIONS set? */ +static bool basic_modversions; +/* Is CONFIG_EXTENDED_MODVERSIONS set? */ +static bool extended_modversions; /* If we are modposting external module set to 1 */ static bool external_module; /* Only warn about unresolved symbols */ @@ -94,6 +98,18 @@ static inline bool strends(const char *str, const char *postfix) return strcmp(str + strlen(str) - strlen(postfix), postfix) == 0; } +/** + * get_basename - return the last part of a pathname. + * + * @path: path to extract the filename from. + */ +const char *get_basename(const char *path) +{ + const char *tail = strrchr(path, '/'); + + return tail ? tail + 1 : path; +} + char *read_text_file(const char *filename) { struct stat st; @@ -186,8 +202,8 @@ static struct module *new_module(const char *name, size_t namelen) /* * Set mod->is_gpl_compatible to true by default. If MODULE_LICENSE() - * is missing, do not check the use for EXPORT_SYMBOL_GPL() becasue - * modpost will exit wiht error anyway. + * is missing, do not check the use for EXPORT_SYMBOL_GPL() because + * modpost will exit with an error anyway. */ mod->is_gpl_compatible = true; @@ -503,6 +519,9 @@ static int parse_elf(struct elf_info *info, const char *filename) info->modinfo_len = sechdrs[i].sh_size; } else if (!strcmp(secname, ".export_symbol")) { info->export_symbol_secndx = i; + } else if (!strcmp(secname, ".no_trim_symbol")) { + info->no_trim_symbol = (void *)hdr + sechdrs[i].sh_offset; + info->no_trim_symbol_len = sechdrs[i].sh_size; } if (sechdrs[i].sh_type == SHT_SYMTAB) { @@ -1454,14 +1473,8 @@ static void extract_crcs_for_object(const char *object, struct module *mod) const char *base; int dirlen, ret; - base = strrchr(object, '/'); - if (base) { - base++; - dirlen = base - object; - } else { - dirlen = 0; - base = object; - } + base = get_basename(object); + dirlen = base - object; ret = snprintf(cmd_file, sizeof(cmd_file), "%.*s.%s.cmd", dirlen, object, base); @@ -1562,6 +1575,14 @@ static void read_symbols(const char *modname) /* strip trailing .o */ mod = new_module(modname, strlen(modname) - strlen(".o")); + /* save .no_trim_symbol section for later use */ + if (info.no_trim_symbol_len) { + mod->no_trim_symbol = xmalloc(info.no_trim_symbol_len); + memcpy(mod->no_trim_symbol, info.no_trim_symbol, + info.no_trim_symbol_len); + mod->no_trim_symbol_len = info.no_trim_symbol_len; + } + if (!mod->is_vmlinux) { license = get_modinfo(&info, "license"); if (!license) @@ -1581,7 +1602,7 @@ static void read_symbols(const char *modname) namespace); } - if (extra_warn && !get_modinfo(&info, "description")) + if (!get_modinfo(&info, "description")) warn("missing MODULE_DESCRIPTION() in %s\n", modname); } @@ -1688,11 +1709,7 @@ static void check_exports(struct module *mod) s->crc_valid = exp->crc_valid; s->crc = exp->crc; - basename = strrchr(mod->name, '/'); - if (basename) - basename++; - else - basename = mod->name; + basename = get_basename(mod->name); if (!contains_namespace(&mod->imported_namespaces, exp->namespace)) { modpost_log(!allow_missing_ns_imports, @@ -1724,15 +1741,34 @@ static void handle_white_list_exports(const char *white_list) free(buf); } +/* + * Keep symbols recorded in the .no_trim_symbol section. This is necessary to + * prevent CONFIG_TRIM_UNUSED_KSYMS from dropping EXPORT_SYMBOL because + * symbol_get() relies on the symbol being present in the ksymtab for lookups. + */ +static void keep_no_trim_symbols(struct module *mod) +{ + unsigned long size = mod->no_trim_symbol_len; + + for (char *s = mod->no_trim_symbol; s; s = next_string(s , &size)) { + struct symbol *sym; + + /* + * If find_symbol() returns NULL, this symbol is not provided + * by any module, and symbol_get() will fail. + */ + sym = find_symbol(s); + if (sym) + sym->used = true; + } +} + static void check_modname_len(struct module *mod) { const char *mod_name; - mod_name = strrchr(mod->name, '/'); - if (mod_name == NULL) - mod_name = mod->name; - else - mod_name++; + mod_name = get_basename(mod->name); + if (strlen(mod_name) >= MODULE_NAME_LEN) error("module name is too long [%s.ko]\n", mod->name); } @@ -1806,13 +1842,56 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod) } /** + * Record CRCs for unresolved symbols, supporting long names + */ +static void add_extended_versions(struct buffer *b, struct module *mod) +{ + struct symbol *s; + + if (!extended_modversions) + return; + + buf_printf(b, "\n"); + buf_printf(b, "static const u32 ____version_ext_crcs[]\n"); + buf_printf(b, "__used __section(\"__version_ext_crcs\") = {\n"); + list_for_each_entry(s, &mod->unresolved_symbols, list) { + if (!s->module) + continue; + if (!s->crc_valid) { + warn("\"%s\" [%s.ko] has no CRC!\n", + s->name, mod->name); + continue; + } + buf_printf(b, "\t0x%08x,\n", s->crc); + } + buf_printf(b, "};\n"); + + buf_printf(b, "static const char ____version_ext_names[]\n"); + buf_printf(b, "__used __section(\"__version_ext_names\") =\n"); + list_for_each_entry(s, &mod->unresolved_symbols, list) { + if (!s->module) + continue; + if (!s->crc_valid) + /* + * We already warned on this when producing the crc + * table. + * We need to skip its name too, as the indexes in + * both tables need to align. + */ + continue; + buf_printf(b, "\t\"%s\\0\"\n", s->name); + } + buf_printf(b, ";\n"); +} + +/** * Record CRCs for unresolved symbols **/ static void add_versions(struct buffer *b, struct module *mod) { struct symbol *s; - if (!modversions) + if (!basic_modversions) return; buf_printf(b, "\n"); @@ -1828,11 +1907,16 @@ static void add_versions(struct buffer *b, struct module *mod) continue; } if (strlen(s->name) >= MODULE_NAME_LEN) { - error("too long symbol \"%s\" [%s.ko]\n", - s->name, mod->name); - break; + if (extended_modversions) { + /* this symbol will only be in the extended info */ + continue; + } else { + error("too long symbol \"%s\" [%s.ko]\n", + s->name, mod->name); + break; + } } - buf_printf(b, "\t{ %#8x, \"%s\" },\n", + buf_printf(b, "\t{ 0x%08x, \"%s\" },\n", s->crc, s->name); } @@ -1861,11 +1945,7 @@ static void add_depends(struct buffer *b, struct module *mod) continue; s->module->seen = true; - p = strrchr(s->module->name, '/'); - if (p) - p++; - else - p = s->module->name; + p = get_basename(s->module->name); buf_printf(b, "%s%s", first ? "" : ",", p); first = 0; } @@ -1961,6 +2041,7 @@ static void write_mod_c_file(struct module *mod) add_header(&buf, mod); add_exported_symbols(&buf, mod); add_versions(&buf, mod); + add_extended_versions(&buf, mod); add_depends(&buf, mod); buf_printf(&buf, "\n"); @@ -2126,7 +2207,7 @@ int main(int argc, char **argv) LIST_HEAD(dump_lists); struct dump_list *dl, *dl2; - while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:")) != -1) { + while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:xb")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2175,6 +2256,12 @@ int main(int argc, char **argv) case 'd': missing_namespace_deps = optarg; break; + case 'b': + basic_modversions = true; + break; + case 'x': + extended_modversions = true; + break; default: exit(1); } @@ -2195,6 +2282,8 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { + keep_no_trim_symbols(mod); + if (mod->dump_file || mod->is_vmlinux) continue; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index ffd0a52a606e..9133e4c3803f 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -111,6 +111,8 @@ struct module_alias { * * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases + * @no_trim_symbol: .no_trim_symbol section data + * @no_trim_symbol_len: length of the .no_trim_symbol section */ struct module { struct list_head list; @@ -128,6 +130,8 @@ struct module { // Actual imported namespaces struct list_head imported_namespaces; struct list_head aliases; + char *no_trim_symbol; + unsigned int no_trim_symbol_len; char name[]; }; @@ -141,6 +145,8 @@ struct elf_info { char *strtab; char *modinfo; unsigned int modinfo_len; + char *no_trim_symbol; + unsigned int no_trim_symbol_len; /* support for 32bit section numbers */ @@ -210,6 +216,7 @@ void get_src_version(const char *modname, char sum[], unsigned sumlen); /* from modpost.c */ extern bool target_is_big_endian; extern bool host_is_big_endian; +const char *get_basename(const char *path); char *read_text_file(const char *filename); char *get_line(char **stringp); void *sym_get_data(const struct elf_info *info, const Elf_Sym *sym); diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index 6de9af17599d..3dd28b4d0099 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -309,15 +309,10 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) cmd = xmalloc(strlen(objfile) + sizeof("..cmd")); - base = strrchr(objfile, '/'); - if (base) { - base++; - dirlen = base - objfile; - sprintf(cmd, "%.*s.%s.cmd", dirlen, objfile, base); - } else { - dirlen = 0; - sprintf(cmd, ".%s.cmd", objfile); - } + base = get_basename(objfile); + dirlen = base - objfile; + sprintf(cmd, "%.*s.%s.cmd", dirlen, objfile, base); + dir = xmalloc(dirlen + 1); strncpy(dir, objfile, dirlen); dir[dirlen] = '\0'; @@ -335,7 +330,7 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) line++; p = line; - if (strncmp(line, "source_", sizeof("source_")-1) == 0) { + if (strstarts(line, "source_")) { p = strrchr(line, ' '); if (!p) { warn("malformed line: %s\n", line); @@ -349,7 +344,7 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md) } continue; } - if (strncmp(line, "deps_", sizeof("deps_")-1) == 0) { + if (strstarts(line, "deps_")) { check_files = 1; continue; } diff --git a/scripts/module.lds.S b/scripts/module.lds.S index c2f80f9141d4..450f1088d5fd 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -16,6 +16,7 @@ SECTIONS { *(.discard) *(.discard.*) *(.export_symbol) + *(.no_trim_symbol) } __ksymtab 0 : ALIGN(8) { *(SORT(___ksymtab+*)) } diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index dca706617adc..452374d63c24 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -22,7 +22,6 @@ license=(GPL-2.0-only) makedepends=( bc bison - cpio flex gettext kmod @@ -54,7 +53,7 @@ build() { _package() { pkgdesc="The ${pkgdesc} kernel and modules" - local modulesdir="${pkgdir}/usr/${MODLIB}" + local modulesdir="${pkgdir}/usr/lib/modules/${KERNELRELEASE}" _prologue @@ -82,7 +81,7 @@ _package() { _package-headers() { pkgdesc="Headers and scripts for building modules for the ${pkgdesc} kernel" - local builddir="${pkgdir}/usr/${MODLIB}/build" + local builddir="${pkgdir}/usr/lib/modules/${KERNELRELEASE}/build" _prologue @@ -115,7 +114,7 @@ _package-debug(){ pkgdesc="Non-stripped vmlinux file for the ${pkgdesc} kernel" local debugdir="${pkgdir}/usr/src/debug/${pkgbase}" - local builddir="${pkgdir}/usr/${MODLIB}/build" + local builddir="${pkgdir}/usr/lib/modules/${KERNELRELEASE}/build" _prologue diff --git a/scripts/package/builddeb b/scripts/package/builddeb index ad7aba0f268e..3627ca227e5a 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -5,10 +5,12 @@ # # Simple script to generate a deb package for a Linux kernel. All the # complexity of what to do with a kernel after it is installed or removed -# is left to other scripts and packages: they can install scripts in the -# /etc/kernel/{pre,post}{inst,rm}.d/ directories (or an alternative location -# specified in KDEB_HOOKDIR) that will be called on package install and -# removal. +# is left to other scripts and packages. Scripts can be placed into the +# preinst, postinst, prerm and postrm directories in /etc/kernel or +# /usr/share/kernel. A different list of search directories can be given +# via KDEB_HOOKDIR. Scripts in directories earlier in the list will +# override scripts of the same name in later directories. The script will +# be called on package installation and removal. set -eu @@ -74,10 +76,8 @@ install_maint_scripts () { # kernel packages, as well as kernel packages built using make-kpkg. # make-kpkg sets $INITRD to indicate whether an initramfs is wanted, and # so do we; recent versions of dracut and initramfs-tools will obey this. - debhookdir=${KDEB_HOOKDIR:-/etc/kernel} + debhookdir=${KDEB_HOOKDIR:-/etc/kernel /usr/share/kernel} for script in postinst postrm preinst prerm; do - mkdir -p "${pdir}${debhookdir}/${script}.d" - mkdir -p "${pdir}/DEBIAN" cat <<-EOF > "${pdir}/DEBIAN/${script}" #!/bin/sh @@ -90,7 +90,15 @@ install_maint_scripts () { # Tell initramfs builder whether it's wanted export INITRD=$(if_enabled_echo CONFIG_BLK_DEV_INITRD Yes No) - test -d ${debhookdir}/${script}.d && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" ${debhookdir}/${script}.d + # run-parts will error out if one of its directory arguments does not + # exist, so filter the list of hook directories accordingly. + hookdirs= + for dir in ${debhookdir}; do + test -d "\$dir/${script}.d" || continue + hookdirs="\$hookdirs \$dir/${script}.d" + done + hookdirs="\${hookdirs# }" + test -n "\$hookdirs" && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" \$hookdirs exit 0 EOF chmod 755 "${pdir}/DEBIAN/${script}" diff --git a/scripts/package/debian/rules b/scripts/package/debian/rules index ca07243bd5cd..a417a7f8bbc1 100755 --- a/scripts/package/debian/rules +++ b/scripts/package/debian/rules @@ -21,9 +21,11 @@ ifeq ($(origin KBUILD_VERBOSE),undefined) endif endif -revision = $(lastword $(subst -, ,$(shell dpkg-parsechangelog -S Version))) +revision = $(shell dpkg-parsechangelog -S Version | sed -n 's/.*-//p') CROSS_COMPILE ?= $(filter-out $(DEB_BUILD_GNU_TYPE)-, $(DEB_HOST_GNU_TYPE)-) -make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(revision) $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE)) +make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) \ + $(addprefix KBUILD_BUILD_VERSION=,$(revision)) \ + $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE)) binary-targets := $(addprefix binary-, image image-dbg headers libc-dev) @@ -41,6 +43,10 @@ package = $($(@:binary-%=%-package)) # which package is being processed in the build log. DH_OPTIONS = -p$(package) +# Note: future removal of KDEB_COMPRESS +# dpkg-deb >= 1.21.10 supports the DPKG_DEB_COMPRESSOR_TYPE environment +# variable, which provides the same functionality as KDEB_COMPRESS. The +# KDEB_COMPRESS variable will be removed in the future. define binary $(Q)dh_testdir $(DH_OPTIONS) $(Q)dh_testroot $(DH_OPTIONS) diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index d3c5b104c063..b96538787f3d 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -49,17 +49,10 @@ mkdir -p "${destdir}" # This caters to host programs that participate in Kbuild. objtool and # resolve_btfids are out of scope. if [ "${CC}" != "${HOSTCC}" ]; then - echo "Rebuilding host programs with ${CC}..." - - # This leverages external module building. - # - Clear sub_make_done to allow the top-level Makefile to redo sub-make. - # - Filter out --no-print-directory to print "Entering directory" logs - # when Make changes the working directory. - unset sub_make_done - MAKEFLAGS=$(echo "${MAKEFLAGS}" | sed s/--no-print-directory//) - - cat <<-'EOF' > "${destdir}/Kbuild" - subdir-y := scripts + cat "${destdir}/scripts/Makefile" - <<-'EOF' > "${destdir}/scripts/Kbuild" + subdir-y += basic + hostprogs-always-y += mod/modpost + mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o) EOF # HOSTCXX is not overridden. The C++ compiler is used to build: @@ -67,20 +60,12 @@ if [ "${CC}" != "${HOSTCC}" ]; then # - GCC plugins, which will not work on the installed system even after # being rebuilt. # - # Use the single-target build to avoid the modpost invocation, which - # would overwrite Module.symvers. - "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ - - cat <<-'EOF' > "${destdir}/scripts/Kbuild" - subdir-y := basic - hostprogs-always-y := mod/modpost - mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o) - EOF - - # Run once again to rebuild scripts/basic/ and scripts/mod/modpost. - "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ + # Clear VPATH and srcroot because the source files reside in the output + # directory. + # shellcheck disable=SC2016 # $(MAKE) and $(build) will be expanded by Make + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"$(realpath --relative-base=. "${destdir}")"/scripts - rm -f "${destdir}/Kbuild" "${destdir}/scripts/Kbuild" + rm -f "${destdir}/scripts/Kbuild" fi find "${destdir}" \( -name '.*.cmd' -o -name '*.o' \) -delete diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec index ac3e5ac01d8a..98f206cb7c60 100644 --- a/scripts/package/kernel.spec +++ b/scripts/package/kernel.spec @@ -2,8 +2,6 @@ %{!?_arch: %define _arch dummy} %{!?make: %define make make} %define makeflags %{?_smp_mflags} ARCH=%{ARCH} -%define __spec_install_post /usr/lib/rpm/brp-compress || : -%define debug_package %{nil} Name: kernel Summary: The Linux Kernel @@ -18,6 +16,7 @@ Source1: config Source2: diff.patch Provides: kernel-%{KERNELRELEASE} BuildRequires: bc binutils bison dwarves +BuildRequires: (elfutils-devel or libdw-devel) BuildRequires: (elfutils-libelf-devel or libelf-devel) flex BuildRequires: gcc make openssl openssl-devel perl python3 rsync @@ -46,6 +45,36 @@ This package provides kernel headers and makefiles sufficient to build modules against the %{version} kernel package. %endif +%if %{with_debuginfo} +# list of debuginfo-related options taken from distribution kernel.spec +# files +%undefine _include_minidebuginfo +%undefine _find_debuginfo_dwz_opts +%undefine _unique_build_ids +%undefine _unique_debug_names +%undefine _unique_debug_srcs +%undefine _debugsource_packages +%undefine _debuginfo_subpackages +%global _find_debuginfo_opts -r +%global _missing_build_ids_terminate_build 1 +%global _no_recompute_build_ids 1 +%{debug_package} +%endif +# some (but not all) versions of rpmbuild emit %%debug_package with +# %%install. since we've already emitted it manually, that would cause +# a package redefinition error. ensure that doesn't happen +%define debug_package %{nil} + +# later, we make all modules executable so that find-debuginfo.sh strips +# them up. but they don't actually need to be executable, so remove the +# executable bit, taking care to do it _after_ find-debuginfo.sh has run +%define __spec_install_post \ + %{?__debug_package:%{__debug_install_post}} \ + %{__arch_install_post} \ + %{__os_install_post} \ + find %{buildroot}/lib/modules/%{KERNELRELEASE} -name "*.ko" -type f \\\ + | xargs --no-run-if-empty chmod u-x + %prep %setup -q -n linux cp %{SOURCE1} .config @@ -89,8 +118,22 @@ ln -fns /usr/src/kernels/%{KERNELRELEASE} %{buildroot}/lib/modules/%{KERNELRELEA echo "%exclude /lib/modules/%{KERNELRELEASE}/build" } > %{buildroot}/kernel.list +# make modules executable so that find-debuginfo.sh strips them. this +# will be undone later in %%__spec_install_post +find %{buildroot}/lib/modules/%{KERNELRELEASE} -name "*.ko" -type f \ + | xargs --no-run-if-empty chmod u+x + +%if %{with_debuginfo} +# copying vmlinux directly to the debug directory means it will not get +# stripped (but its source paths will still be collected + fixed up) +mkdir -p %{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE} +cp vmlinux %{buildroot}/usr/lib/debug/lib/modules/%{KERNELRELEASE} +%endif + %clean rm -rf %{buildroot} +rm -f debugfiles.list debuglinks.list debugsourcefiles.list debugsources.list \ + elfbins.list %post if [ -x /usr/bin/kernel-install ]; then diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index b038a1380b8a..d4b007b38a47 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -77,6 +77,8 @@ set_debarch() { debarch=i386 fi ;; + loongarch64) + debarch=loong64 ;; esac if [ -z "$debarch" ]; then debarch=$(dpkg-architecture -qDEB_HOST_ARCH) @@ -155,11 +157,12 @@ while [ $# -gt 0 ]; do done # Some variables and settings used throughout the script -version=$KERNELRELEASE if [ "${KDEB_PKGVERSION:+set}" ]; then packageversion=$KDEB_PKGVERSION else - packageversion=$(${srctree}/scripts/setlocalversion --no-local ${srctree})-$($srctree/scripts/build-version) + upstream_version=$("${srctree}/scripts/setlocalversion" --no-local "${srctree}" | sed 's/-\(rc[1-9]\)/~\1/') + debian_revision=$("${srctree}/scripts/build-version") + packageversion=${upstream_version}-${debian_revision} fi sourcename=${KDEB_SOURCENAME:-linux-upstream} @@ -205,18 +208,18 @@ Priority: optional Maintainer: $maintainer Rules-Requires-Root: no Build-Depends: debhelper-compat (= 12) -Build-Depends-Arch: bc, bison, cpio, flex, +Build-Depends-Arch: bc, bison, flex, gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>, - kmod, libelf-dev:native, + kmod, libdw-dev:native, libelf-dev:native, libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>, python3:native, rsync Homepage: https://www.kernel.org/ -Package: $packagename-$version +Package: $packagename-${KERNELRELEASE} Architecture: $debarch -Description: Linux kernel, version $version +Description: Linux kernel, version ${KERNELRELEASE} This package contains the Linux kernel, modules and corresponding other - files, version: $version. + files, version: ${KERNELRELEASE}. EOF if [ "${SRCARCH}" != um ]; then @@ -235,11 +238,11 @@ EOF if is_enabled CONFIG_MODULES; then cat <<EOF >> debian/control -Package: linux-headers-$version +Package: linux-headers-${KERNELRELEASE} Architecture: $debarch Build-Profiles: <!pkg.${sourcename}.nokernelheaders> -Description: Linux kernel headers for $version on $debarch - This package provides kernel header files for $version on $debarch +Description: Linux kernel headers for ${KERNELRELEASE} on $debarch + This package provides kernel header files for ${KERNELRELEASE} on $debarch . This is useful for people who need to build external modules EOF @@ -249,11 +252,11 @@ fi if is_enabled CONFIG_DEBUG_INFO; then cat <<EOF >> debian/control -Package: linux-image-$version-dbg +Package: linux-image-${KERNELRELEASE}-dbg Section: debug Architecture: $debarch Build-Profiles: <!pkg.${sourcename}.nokerneldbg> -Description: Linux kernel debugging symbols for $version +Description: Linux kernel debugging symbols for ${KERNELRELEASE} This package will come in handy if you need to debug the kernel. It provides all the necessary debug symbols for the kernel and its modules. EOF diff --git a/scripts/package/mkspec b/scripts/package/mkspec index 4dc1466dfc81..c7375bfc25a9 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -23,6 +23,16 @@ else echo '%define with_devel 0' fi +# debuginfo package generation uses find-debuginfo.sh under the hood, +# which only works on uncompressed modules that contain debuginfo +if grep -q CONFIG_DEBUG_INFO=y include/config/auto.conf && + (! grep -q CONFIG_MODULE_COMPRESS=y include/config/auto.conf) && + (! grep -q CONFIG_DEBUG_INFO_SPLIT=y include/config/auto.conf); then +echo '%define with_debuginfo %{?_without_debuginfo: 0} %{?!_without_debuginfo: 1}' +else +echo '%define with_debuginfo 0' +fi + cat<<EOF %define ARCH ${ARCH} %define KERNELRELEASE ${KERNELRELEASE} diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index 93c0ef7fb3fb..d2323de0692c 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -123,8 +123,10 @@ fi # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. # # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 -# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when -# the minimum version is upgraded past that (0.69.1 already fixed the issue). +# (https://github.com/rust-lang/rust-bindgen/pull/2678) and 0.71.0 +# (https://github.com/rust-lang/rust-bindgen/pull/3040). It can be removed when +# the minimum version is upgraded past the latter (0.69.1 and 0.71.1 both fixed +# the issue). rust_bindings_generator_output=$( \ LC_ALL=C "$BINDGEN" --version workaround-for-0.69.0 2>/dev/null ) || rust_bindings_generator_code=$? diff --git a/scripts/rustdoc_test_builder.rs b/scripts/rustdoc_test_builder.rs index e5894652f12c..f7540bcf595a 100644 --- a/scripts/rustdoc_test_builder.rs +++ b/scripts/rustdoc_test_builder.rs @@ -28,7 +28,7 @@ fn main() { // // ``` // fn main() { #[allow(non_snake_case)] fn _doctest_main_rust_kernel_file_rs_28_0() { - // fn main() { #[allow(non_snake_case)] fn _doctest_main_rust_kernel_file_rs_37_0() -> Result<(), impl core::fmt::Debug> { + // fn main() { #[allow(non_snake_case)] fn _doctest_main_rust_kernel_file_rs_37_0() -> Result<(), impl ::core::fmt::Debug> { // ``` // // It should be unlikely that doctest code matches such lines (when code is formatted properly). @@ -49,8 +49,10 @@ fn main() { // Qualify `Result` to avoid the collision with our own `Result` coming from the prelude. let body = body.replace( - &format!("{rustdoc_function_name}() -> Result<(), impl core::fmt::Debug> {{"), - &format!("{rustdoc_function_name}() -> core::result::Result<(), impl core::fmt::Debug> {{"), + &format!("{rustdoc_function_name}() -> Result<(), impl ::core::fmt::Debug> {{"), + &format!( + "{rustdoc_function_name}() -> ::core::result::Result<(), impl ::core::fmt::Debug> {{" + ), ); // For tests that get generated with `Result`, like above, `rustdoc` generates an `unwrap()` on diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs index 5ebd42ae4a3f..1ca253594d38 100644 --- a/scripts/rustdoc_test_gen.rs +++ b/scripts/rustdoc_test_gen.rs @@ -15,8 +15,8 @@ //! - Test code should be able to define functions and call them, without having to carry //! the context. //! -//! - Later on, we may want to be able to test non-kernel code (e.g. `core`, `alloc` or -//! third-party crates) which likely use the standard library `assert*!` macros. +//! - Later on, we may want to be able to test non-kernel code (e.g. `core` or third-party +//! crates) which likely use the standard library `assert*!` macros. //! //! For this reason, instead of the passed context, `kunit_get_current_test()` is used instead //! (i.e. `current->kunit_test`). @@ -87,8 +87,8 @@ fn find_real_path<'a>(srctree: &Path, valid_paths: &'a mut Vec<PathBuf>, file: & assert!( valid_paths.len() > 0, - "No path candidates found. This is likely a bug in the build system, or some files went \ - away while compiling." + "No path candidates found for `{file}`. This is likely a bug in the build system, or some \ + files went away while compiling." ); if valid_paths.len() > 1 { @@ -97,8 +97,8 @@ fn find_real_path<'a>(srctree: &Path, valid_paths: &'a mut Vec<PathBuf>, file: & eprintln!(" {path:?}"); } panic!( - "Several path candidates found, please resolve the ambiguity by renaming a file or \ - folder." + "Several path candidates found for `{file}`, please resolve the ambiguity by renaming \ + a file or folder." ); } @@ -167,12 +167,14 @@ fn main() { rust_tests, r#"/// Generated `{name}` KUnit test case from a Rust documentation test. #[no_mangle] -pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{ +pub extern "C" fn {kunit_name}(__kunit_test: *mut ::kernel::bindings::kunit) {{ /// Overrides the usual [`assert!`] macro with one that calls KUnit instead. #[allow(unused)] macro_rules! assert {{ ($cond:expr $(,)?) => {{{{ - kernel::kunit_assert!("{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $cond); + ::kernel::kunit_assert!( + "{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $cond + ); }}}} }} @@ -180,13 +182,15 @@ pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{ #[allow(unused)] macro_rules! assert_eq {{ ($left:expr, $right:expr $(,)?) => {{{{ - kernel::kunit_assert_eq!("{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $left, $right); + ::kernel::kunit_assert_eq!( + "{kunit_name}", "{real_path}", __DOCTEST_ANCHOR - {line}, $left, $right + ); }}}} }} // Many tests need the prelude, so provide it by default. #[allow(unused)] - use kernel::prelude::*; + use ::kernel::prelude::*; // Unconditionally print the location of the original doctest (i.e. rather than the location in // the generated file) so that developers can easily map the test back to the source code. @@ -197,11 +201,11 @@ pub extern "C" fn {kunit_name}(__kunit_test: *mut kernel::bindings::kunit) {{ // This follows the syntax for declaring test metadata in the proposed KTAP v2 spec, which may // be used for the proposed KUnit test attributes API. Thus hopefully this will make migration // easier later on. - kernel::kunit::info(format_args!(" # {kunit_name}.location: {real_path}:{line}\n")); + ::kernel::kunit::info(format_args!(" # {kunit_name}.location: {real_path}:{line}\n")); /// The anchor where the test code body starts. #[allow(unused)] - static __DOCTEST_ANCHOR: i32 = core::line!() as i32 + {body_offset} + 1; + static __DOCTEST_ANCHOR: i32 = ::core::line!() as i32 + {body_offset} + 1; {{ {body} main(); diff --git a/scripts/selinux/install_policy.sh b/scripts/selinux/install_policy.sh index 24086793b0d8..db40237e60ce 100755 --- a/scripts/selinux/install_policy.sh +++ b/scripts/selinux/install_policy.sh @@ -6,27 +6,24 @@ if [ `id -u` -ne 0 ]; then exit 1 fi -SF=`which setfiles` -if [ $? -eq 1 ]; then +SF=`which setfiles` || { echo "Could not find setfiles" echo "Do you have policycoreutils installed?" exit 1 -fi +} -CP=`which checkpolicy` -if [ $? -eq 1 ]; then +CP=`which checkpolicy` || { echo "Could not find checkpolicy" echo "Do you have checkpolicy installed?" exit 1 -fi +} VERS=`$CP -V | awk '{print $1}'` -ENABLED=`which selinuxenabled` -if [ $? -eq 1 ]; then +ENABLED=`which selinuxenabled` || { echo "Could not find selinuxenabled" echo "Do you have libselinux-utils installed?" exit 1 -fi +} if selinuxenabled; then echo "SELinux is already enabled" diff --git a/scripts/show_delta b/scripts/show_delta index 291ad65e3089..3755b6c6e557 100755 --- a/scripts/show_delta +++ b/scripts/show_delta @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0-only # # show_deltas: Read list of printk messages instrumented with diff --git a/scripts/sorttable.c b/scripts/sorttable.c index 83cdb843d92f..deed676bfe38 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -28,6 +28,7 @@ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> +#include <stdbool.h> #include <string.h> #include <unistd.h> #include <errno.h> @@ -64,14 +65,246 @@ #define EM_LOONGARCH 258 #endif +typedef union { + Elf32_Ehdr e32; + Elf64_Ehdr e64; +} Elf_Ehdr; + +typedef union { + Elf32_Shdr e32; + Elf64_Shdr e64; +} Elf_Shdr; + +typedef union { + Elf32_Sym e32; + Elf64_Sym e64; +} Elf_Sym; + +typedef union { + Elf32_Rela e32; + Elf64_Rela e64; +} Elf_Rela; + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); static void (*w)(uint32_t, uint32_t *); -static void (*w2)(uint16_t, uint16_t *); static void (*w8)(uint64_t, uint64_t *); typedef void (*table_sort_t)(char *, int); +static struct elf_funcs { + int (*compare_extable)(const void *a, const void *b); + uint64_t (*ehdr_shoff)(Elf_Ehdr *ehdr); + uint16_t (*ehdr_shstrndx)(Elf_Ehdr *ehdr); + uint16_t (*ehdr_shentsize)(Elf_Ehdr *ehdr); + uint16_t (*ehdr_shnum)(Elf_Ehdr *ehdr); + uint64_t (*shdr_addr)(Elf_Shdr *shdr); + uint64_t (*shdr_offset)(Elf_Shdr *shdr); + uint64_t (*shdr_size)(Elf_Shdr *shdr); + uint64_t (*shdr_entsize)(Elf_Shdr *shdr); + uint32_t (*shdr_link)(Elf_Shdr *shdr); + uint32_t (*shdr_name)(Elf_Shdr *shdr); + uint32_t (*shdr_type)(Elf_Shdr *shdr); + uint8_t (*sym_type)(Elf_Sym *sym); + uint32_t (*sym_name)(Elf_Sym *sym); + uint64_t (*sym_value)(Elf_Sym *sym); + uint16_t (*sym_shndx)(Elf_Sym *sym); + uint64_t (*rela_offset)(Elf_Rela *rela); + uint64_t (*rela_info)(Elf_Rela *rela); + uint64_t (*rela_addend)(Elf_Rela *rela); + void (*rela_write_addend)(Elf_Rela *rela, uint64_t val); +} e; + +static uint64_t ehdr64_shoff(Elf_Ehdr *ehdr) +{ + return r8(&ehdr->e64.e_shoff); +} + +static uint64_t ehdr32_shoff(Elf_Ehdr *ehdr) +{ + return r(&ehdr->e32.e_shoff); +} + +static uint64_t ehdr_shoff(Elf_Ehdr *ehdr) +{ + return e.ehdr_shoff(ehdr); +} + +#define EHDR_HALF(fn_name) \ +static uint16_t ehdr64_##fn_name(Elf_Ehdr *ehdr) \ +{ \ + return r2(&ehdr->e64.e_##fn_name); \ +} \ + \ +static uint16_t ehdr32_##fn_name(Elf_Ehdr *ehdr) \ +{ \ + return r2(&ehdr->e32.e_##fn_name); \ +} \ + \ +static uint16_t ehdr_##fn_name(Elf_Ehdr *ehdr) \ +{ \ + return e.ehdr_##fn_name(ehdr); \ +} + +EHDR_HALF(shentsize) +EHDR_HALF(shstrndx) +EHDR_HALF(shnum) + +#define SHDR_WORD(fn_name) \ +static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e64.sh_##fn_name); \ +} \ + \ +static uint32_t shdr32_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e32.sh_##fn_name); \ +} \ + \ +static uint32_t shdr_##fn_name(Elf_Shdr *shdr) \ +{ \ + return e.shdr_##fn_name(shdr); \ +} + +#define SHDR_ADDR(fn_name) \ +static uint64_t shdr64_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r8(&shdr->e64.sh_##fn_name); \ +} \ + \ +static uint64_t shdr32_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e32.sh_##fn_name); \ +} \ + \ +static uint64_t shdr_##fn_name(Elf_Shdr *shdr) \ +{ \ + return e.shdr_##fn_name(shdr); \ +} + +#define SHDR_WORD(fn_name) \ +static uint32_t shdr64_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e64.sh_##fn_name); \ +} \ + \ +static uint32_t shdr32_##fn_name(Elf_Shdr *shdr) \ +{ \ + return r(&shdr->e32.sh_##fn_name); \ +} \ +static uint32_t shdr_##fn_name(Elf_Shdr *shdr) \ +{ \ + return e.shdr_##fn_name(shdr); \ +} + +SHDR_ADDR(addr) +SHDR_ADDR(offset) +SHDR_ADDR(size) +SHDR_ADDR(entsize) + +SHDR_WORD(link) +SHDR_WORD(name) +SHDR_WORD(type) + +#define SYM_ADDR(fn_name) \ +static uint64_t sym64_##fn_name(Elf_Sym *sym) \ +{ \ + return r8(&sym->e64.st_##fn_name); \ +} \ + \ +static uint64_t sym32_##fn_name(Elf_Sym *sym) \ +{ \ + return r(&sym->e32.st_##fn_name); \ +} \ + \ +static uint64_t sym_##fn_name(Elf_Sym *sym) \ +{ \ + return e.sym_##fn_name(sym); \ +} + +#define SYM_WORD(fn_name) \ +static uint32_t sym64_##fn_name(Elf_Sym *sym) \ +{ \ + return r(&sym->e64.st_##fn_name); \ +} \ + \ +static uint32_t sym32_##fn_name(Elf_Sym *sym) \ +{ \ + return r(&sym->e32.st_##fn_name); \ +} \ + \ +static uint32_t sym_##fn_name(Elf_Sym *sym) \ +{ \ + return e.sym_##fn_name(sym); \ +} + +#define SYM_HALF(fn_name) \ +static uint16_t sym64_##fn_name(Elf_Sym *sym) \ +{ \ + return r2(&sym->e64.st_##fn_name); \ +} \ + \ +static uint16_t sym32_##fn_name(Elf_Sym *sym) \ +{ \ + return r2(&sym->e32.st_##fn_name); \ +} \ + \ +static uint16_t sym_##fn_name(Elf_Sym *sym) \ +{ \ + return e.sym_##fn_name(sym); \ +} + +static uint8_t sym64_type(Elf_Sym *sym) +{ + return ELF64_ST_TYPE(sym->e64.st_info); +} + +static uint8_t sym32_type(Elf_Sym *sym) +{ + return ELF32_ST_TYPE(sym->e32.st_info); +} + +static uint8_t sym_type(Elf_Sym *sym) +{ + return e.sym_type(sym); +} + +SYM_ADDR(value) +SYM_WORD(name) +SYM_HALF(shndx) + +#define __maybe_unused __attribute__((__unused__)) + +#define RELA_ADDR(fn_name) \ +static uint64_t rela64_##fn_name(Elf_Rela *rela) \ +{ \ + return r8((uint64_t *)&rela->e64.r_##fn_name); \ +} \ + \ +static uint64_t rela32_##fn_name(Elf_Rela *rela) \ +{ \ + return r((uint32_t *)&rela->e32.r_##fn_name); \ +} \ + \ +static uint64_t __maybe_unused rela_##fn_name(Elf_Rela *rela) \ +{ \ + return e.rela_##fn_name(rela); \ +} + +RELA_ADDR(offset) +RELA_ADDR(info) +RELA_ADDR(addend) + +static void rela64_write_addend(Elf_Rela *rela, uint64_t val) +{ + w8(val, (uint64_t *)&rela->e64.r_addend); +} + +static void rela32_write_addend(Elf_Rela *rela, uint64_t val) +{ + w(val, (uint32_t *)&rela->e32.r_addend); +} + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap @@ -146,24 +379,14 @@ static void wbe(uint32_t val, uint32_t *x) put_unaligned_be32(val, x); } -static void w2be(uint16_t val, uint16_t *x) -{ - put_unaligned_be16(val, x); -} - -static void w8be(uint64_t val, uint64_t *x) -{ - put_unaligned_be64(val, x); -} - static void wle(uint32_t val, uint32_t *x) { put_unaligned_le32(val, x); } -static void w2le(uint16_t val, uint16_t *x) +static void w8be(uint64_t val, uint64_t *x) { - put_unaligned_le16(val, x); + put_unaligned_be64(val, x); } static void w8le(uint64_t val, uint64_t *x) @@ -195,10 +418,740 @@ static inline unsigned int get_secindex(unsigned int shndx, return r(&symtab_shndx_start[sym_offs]); } -/* 32 bit and 64 bit are very similar */ -#include "sorttable.h" -#define SORTTABLE_64 -#include "sorttable.h" +static int compare_extable_32(const void *a, const void *b) +{ + Elf32_Addr av = r(a); + Elf32_Addr bv = r(b); + + if (av < bv) + return -1; + return av > bv; +} + +static int compare_extable_64(const void *a, const void *b) +{ + Elf64_Addr av = r8(a); + Elf64_Addr bv = r8(b); + + if (av < bv) + return -1; + return av > bv; +} + +static int compare_extable(const void *a, const void *b) +{ + return e.compare_extable(a, b); +} + +static inline void *get_index(void *start, int entsize, int index) +{ + return start + (entsize * index); +} + +static int extable_ent_size; +static int long_size; + +#define ERRSTR_MAXSZ 256 + +#ifdef UNWINDER_ORC_ENABLED +/* ORC unwinder only support X86_64 */ +#include <asm/orc_types.h> + +static char g_err[ERRSTR_MAXSZ]; +static int *g_orc_ip_table; +static struct orc_entry *g_orc_table; + +static pthread_t orc_sort_thread; + +static inline unsigned long orc_ip(const int *ip) +{ + return (unsigned long)ip + *ip; +} + +static int orc_sort_cmp(const void *_a, const void *_b) +{ + struct orc_entry *orc_a, *orc_b; + const int *a = g_orc_ip_table + *(int *)_a; + const int *b = g_orc_ip_table + *(int *)_b; + unsigned long a_val = orc_ip(a); + unsigned long b_val = orc_ip(b); + + if (a_val > b_val) + return 1; + if (a_val < b_val) + return -1; + + /* + * The "weak" section terminator entries need to always be on the left + * to ensure the lookup code skips them in favor of real entries. + * These terminator entries exist to handle any gaps created by + * whitelisted .o files which didn't get objtool generation. + */ + orc_a = g_orc_table + (a - g_orc_ip_table); + orc_b = g_orc_table + (b - g_orc_ip_table); + if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED) + return 0; + return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; +} + +static void *sort_orctable(void *arg) +{ + int i; + int *idxs = NULL; + int *tmp_orc_ip_table = NULL; + struct orc_entry *tmp_orc_table = NULL; + unsigned int *orc_ip_size = (unsigned int *)arg; + unsigned int num_entries = *orc_ip_size / sizeof(int); + unsigned int orc_size = num_entries * sizeof(struct orc_entry); + + idxs = (int *)malloc(*orc_ip_size); + if (!idxs) { + snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s", + strerror(errno)); + pthread_exit(g_err); + } + + tmp_orc_ip_table = (int *)malloc(*orc_ip_size); + if (!tmp_orc_ip_table) { + snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s", + strerror(errno)); + pthread_exit(g_err); + } + + tmp_orc_table = (struct orc_entry *)malloc(orc_size); + if (!tmp_orc_table) { + snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_table: %s", + strerror(errno)); + pthread_exit(g_err); + } + + /* initialize indices array, convert ip_table to absolute address */ + for (i = 0; i < num_entries; i++) { + idxs[i] = i; + tmp_orc_ip_table[i] = g_orc_ip_table[i] + i * sizeof(int); + } + memcpy(tmp_orc_table, g_orc_table, orc_size); + + qsort(idxs, num_entries, sizeof(int), orc_sort_cmp); + + for (i = 0; i < num_entries; i++) { + if (idxs[i] == i) + continue; + + /* convert back to relative address */ + g_orc_ip_table[i] = tmp_orc_ip_table[idxs[i]] - i * sizeof(int); + g_orc_table[i] = tmp_orc_table[idxs[i]]; + } + + free(idxs); + free(tmp_orc_ip_table); + free(tmp_orc_table); + pthread_exit(NULL); +} +#endif + +#ifdef MCOUNT_SORT_ENABLED + +static int compare_values_64(const void *a, const void *b) +{ + uint64_t av = *(uint64_t *)a; + uint64_t bv = *(uint64_t *)b; + + if (av < bv) + return -1; + return av > bv; +} + +static int compare_values_32(const void *a, const void *b) +{ + uint32_t av = *(uint32_t *)a; + uint32_t bv = *(uint32_t *)b; + + if (av < bv) + return -1; + return av > bv; +} + +static int (*compare_values)(const void *a, const void *b); + +/* Only used for sorting mcount table */ +static void rela_write_addend(Elf_Rela *rela, uint64_t val) +{ + e.rela_write_addend(rela, val); +} + +struct func_info { + uint64_t addr; + uint64_t size; +}; + +/* List of functions created by: nm -S vmlinux */ +static struct func_info *function_list; +static int function_list_size; + +/* Allocate functions in 1k blocks */ +#define FUNC_BLK_SIZE 1024 +#define FUNC_BLK_MASK (FUNC_BLK_SIZE - 1) + +static int add_field(uint64_t addr, uint64_t size) +{ + struct func_info *fi; + int fsize = function_list_size; + + if (!(fsize & FUNC_BLK_MASK)) { + fsize += FUNC_BLK_SIZE; + fi = realloc(function_list, fsize * sizeof(struct func_info)); + if (!fi) + return -1; + function_list = fi; + } + fi = &function_list[function_list_size++]; + fi->addr = addr; + fi->size = size; + return 0; +} + +/* Used for when mcount/fentry is before the function entry */ +static int before_func; + +/* Only return match if the address lies inside the function size */ +static int cmp_func_addr(const void *K, const void *A) +{ + uint64_t key = *(const uint64_t *)K; + const struct func_info *a = A; + + if (key + before_func < a->addr) + return -1; + return key >= a->addr + a->size; +} + +/* Find the function in function list that is bounded by the function size */ +static int find_func(uint64_t key) +{ + return bsearch(&key, function_list, function_list_size, + sizeof(struct func_info), cmp_func_addr) != NULL; +} + +static int cmp_funcs(const void *A, const void *B) +{ + const struct func_info *a = A; + const struct func_info *b = B; + + if (a->addr < b->addr) + return -1; + return a->addr > b->addr; +} + +static int parse_symbols(const char *fname) +{ + FILE *fp; + char addr_str[20]; /* Only need 17, but round up to next int size */ + char size_str[20]; + char type; + + fp = fopen(fname, "r"); + if (!fp) { + perror(fname); + return -1; + } + + while (fscanf(fp, "%16s %16s %c %*s\n", addr_str, size_str, &type) == 3) { + uint64_t addr; + uint64_t size; + + /* Only care about functions */ + if (type != 't' && type != 'T' && type != 'W') + continue; + + addr = strtoull(addr_str, NULL, 16); + size = strtoull(size_str, NULL, 16); + if (add_field(addr, size) < 0) + return -1; + } + fclose(fp); + + qsort(function_list, function_list_size, sizeof(struct func_info), cmp_funcs); + + return 0; +} + +static pthread_t mcount_sort_thread; +static bool sort_reloc; + +static long rela_type; + +static char m_err[ERRSTR_MAXSZ]; + +struct elf_mcount_loc { + Elf_Ehdr *ehdr; + Elf_Shdr *init_data_sec; + uint64_t start_mcount_loc; + uint64_t stop_mcount_loc; +}; + +/* Fill the array with the content of the relocs */ +static int fill_relocs(void *ptr, uint64_t size, Elf_Ehdr *ehdr, uint64_t start_loc) +{ + Elf_Shdr *shdr_start; + Elf_Rela *rel; + unsigned int shnum; + unsigned int count = 0; + int shentsize; + void *array_end = ptr + size; + + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); + + shnum = ehdr_shnum(ehdr); + if (shnum == SHN_UNDEF) + shnum = shdr_size(shdr_start); + + for (int i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); + void *end; + + if (shdr_type(shdr) != SHT_RELA) + continue; + + rel = (void *)ehdr + shdr_offset(shdr); + end = (void *)rel + shdr_size(shdr); + + for (; (void *)rel < end; rel = (void *)rel + shdr_entsize(shdr)) { + uint64_t offset = rela_offset(rel); + + if (offset >= start_loc && offset < start_loc + size) { + if (ptr + long_size > array_end) { + snprintf(m_err, ERRSTR_MAXSZ, + "Too many relocations"); + return -1; + } + + /* Make sure this has the correct type */ + if (rela_info(rel) != rela_type) { + snprintf(m_err, ERRSTR_MAXSZ, + "rela has type %lx but expected %lx\n", + (long)rela_info(rel), rela_type); + return -1; + } + + if (long_size == 4) + *(uint32_t *)ptr = rela_addend(rel); + else + *(uint64_t *)ptr = rela_addend(rel); + ptr += long_size; + count++; + } + } + } + return count; +} + +/* Put the sorted vals back into the relocation elements */ +static void replace_relocs(void *ptr, uint64_t size, Elf_Ehdr *ehdr, uint64_t start_loc) +{ + Elf_Shdr *shdr_start; + Elf_Rela *rel; + unsigned int shnum; + int shentsize; + + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); + + shnum = ehdr_shnum(ehdr); + if (shnum == SHN_UNDEF) + shnum = shdr_size(shdr_start); + + for (int i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); + void *end; + + if (shdr_type(shdr) != SHT_RELA) + continue; + + rel = (void *)ehdr + shdr_offset(shdr); + end = (void *)rel + shdr_size(shdr); + + for (; (void *)rel < end; rel = (void *)rel + shdr_entsize(shdr)) { + uint64_t offset = rela_offset(rel); + + if (offset >= start_loc && offset < start_loc + size) { + if (long_size == 4) + rela_write_addend(rel, *(uint32_t *)ptr); + else + rela_write_addend(rel, *(uint64_t *)ptr); + ptr += long_size; + } + } + } +} + +static int fill_addrs(void *ptr, uint64_t size, void *addrs) +{ + void *end = ptr + size; + int count = 0; + + for (; ptr < end; ptr += long_size, addrs += long_size, count++) { + if (long_size == 4) + *(uint32_t *)ptr = r(addrs); + else + *(uint64_t *)ptr = r8(addrs); + } + return count; +} + +static void replace_addrs(void *ptr, uint64_t size, void *addrs) +{ + void *end = ptr + size; + + for (; ptr < end; ptr += long_size, addrs += long_size) { + if (long_size == 4) + w(*(uint32_t *)ptr, addrs); + else + w8(*(uint64_t *)ptr, addrs); + } +} + +/* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */ +static void *sort_mcount_loc(void *arg) +{ + struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg; + uint64_t offset = emloc->start_mcount_loc - shdr_addr(emloc->init_data_sec) + + shdr_offset(emloc->init_data_sec); + uint64_t size = emloc->stop_mcount_loc - emloc->start_mcount_loc; + unsigned char *start_loc = (void *)emloc->ehdr + offset; + Elf_Ehdr *ehdr = emloc->ehdr; + void *e_msg = NULL; + void *vals; + int count; + + vals = malloc(long_size * size); + if (!vals) { + snprintf(m_err, ERRSTR_MAXSZ, "Failed to allocate sort array"); + pthread_exit(m_err); + } + + if (sort_reloc) { + count = fill_relocs(vals, size, ehdr, emloc->start_mcount_loc); + /* gcc may use relocs to save the addresses, but clang does not. */ + if (!count) { + count = fill_addrs(vals, size, start_loc); + sort_reloc = 0; + } + } else + count = fill_addrs(vals, size, start_loc); + + if (count < 0) { + e_msg = m_err; + goto out; + } + + if (count != size / long_size) { + snprintf(m_err, ERRSTR_MAXSZ, "Expected %u mcount elements but found %u\n", + (int)(size / long_size), count); + e_msg = m_err; + goto out; + } + + /* zero out any locations not found by function list */ + if (function_list_size) { + for (void *ptr = vals; ptr < vals + size; ptr += long_size) { + uint64_t key; + + key = long_size == 4 ? *(uint32_t *)ptr : *(uint64_t *)ptr; + if (!find_func(key)) { + if (long_size == 4) + *(uint32_t *)ptr = 0; + else + *(uint64_t *)ptr = 0; + } + } + } + + compare_values = long_size == 4 ? compare_values_32 : compare_values_64; + + qsort(vals, count, long_size, compare_values); + + if (sort_reloc) + replace_relocs(vals, size, ehdr, emloc->start_mcount_loc); + else + replace_addrs(vals, size, start_loc); + +out: + free(vals); + + pthread_exit(e_msg); +} + +/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ +static void get_mcount_loc(struct elf_mcount_loc *emloc, Elf_Shdr *symtab_sec, + const char *strtab) +{ + Elf_Sym *sym, *end_sym; + int symentsize = shdr_entsize(symtab_sec); + int found = 0; + + sym = (void *)emloc->ehdr + shdr_offset(symtab_sec); + end_sym = (void *)sym + shdr_size(symtab_sec); + + while (sym < end_sym) { + if (!strcmp(strtab + sym_name(sym), "__start_mcount_loc")) { + emloc->start_mcount_loc = sym_value(sym); + if (++found == 2) + break; + } else if (!strcmp(strtab + sym_name(sym), "__stop_mcount_loc")) { + emloc->stop_mcount_loc = sym_value(sym); + if (++found == 2) + break; + } + sym = (void *)sym + symentsize; + } + + if (!emloc->start_mcount_loc) { + fprintf(stderr, "get start_mcount_loc error!"); + return; + } + + if (!emloc->stop_mcount_loc) { + fprintf(stderr, "get stop_mcount_loc error!"); + return; + } +} +#else /* MCOUNT_SORT_ENABLED */ +static inline int parse_symbols(const char *fname) { return 0; } +#endif + +static int do_sort(Elf_Ehdr *ehdr, + char const *const fname, + table_sort_t custom_sort) +{ + int rc = -1; + Elf_Shdr *shdr_start; + Elf_Shdr *strtab_sec = NULL; + Elf_Shdr *symtab_sec = NULL; + Elf_Shdr *extab_sec = NULL; + Elf_Shdr *string_sec; + Elf_Sym *sym; + const Elf_Sym *symtab; + Elf32_Word *symtab_shndx = NULL; + Elf_Sym *sort_needed_sym = NULL; + Elf_Shdr *sort_needed_sec; + uint32_t *sort_needed_loc; + void *sym_start; + void *sym_end; + const char *secstrings; + const char *strtab; + char *extab_image; + int sort_need_index; + int symentsize; + int shentsize; + int idx; + int i; + unsigned int shnum; + unsigned int shstrndx; +#ifdef MCOUNT_SORT_ENABLED + struct elf_mcount_loc mstruct = {0}; +#endif +#ifdef UNWINDER_ORC_ENABLED + unsigned int orc_ip_size = 0; + unsigned int orc_size = 0; + unsigned int orc_num_entries = 0; +#endif + + shdr_start = (Elf_Shdr *)((char *)ehdr + ehdr_shoff(ehdr)); + shentsize = ehdr_shentsize(ehdr); + + shstrndx = ehdr_shstrndx(ehdr); + if (shstrndx == SHN_XINDEX) + shstrndx = shdr_link(shdr_start); + string_sec = get_index(shdr_start, shentsize, shstrndx); + secstrings = (const char *)ehdr + shdr_offset(string_sec); + + shnum = ehdr_shnum(ehdr); + if (shnum == SHN_UNDEF) + shnum = shdr_size(shdr_start); + + for (i = 0; i < shnum; i++) { + Elf_Shdr *shdr = get_index(shdr_start, shentsize, i); + + idx = shdr_name(shdr); + if (!strcmp(secstrings + idx, "__ex_table")) + extab_sec = shdr; + if (!strcmp(secstrings + idx, ".symtab")) + symtab_sec = shdr; + if (!strcmp(secstrings + idx, ".strtab")) + strtab_sec = shdr; + + if (shdr_type(shdr) == SHT_SYMTAB_SHNDX) + symtab_shndx = (Elf32_Word *)((const char *)ehdr + + shdr_offset(shdr)); + +#ifdef MCOUNT_SORT_ENABLED + /* locate the .init.data section in vmlinux */ + if (!strcmp(secstrings + idx, ".init.data")) + mstruct.init_data_sec = shdr; +#endif + +#ifdef UNWINDER_ORC_ENABLED + /* locate the ORC unwind tables */ + if (!strcmp(secstrings + idx, ".orc_unwind_ip")) { + orc_ip_size = shdr_size(shdr); + g_orc_ip_table = (int *)((void *)ehdr + + shdr_offset(shdr)); + } + if (!strcmp(secstrings + idx, ".orc_unwind")) { + orc_size = shdr_size(shdr); + g_orc_table = (struct orc_entry *)((void *)ehdr + + shdr_offset(shdr)); + } +#endif + } /* for loop */ + +#ifdef UNWINDER_ORC_ENABLED + if (!g_orc_ip_table || !g_orc_table) { + fprintf(stderr, + "incomplete ORC unwind tables in file: %s\n", fname); + goto out; + } + + orc_num_entries = orc_ip_size / sizeof(int); + if (orc_ip_size % sizeof(int) != 0 || + orc_size % sizeof(struct orc_entry) != 0 || + orc_num_entries != orc_size / sizeof(struct orc_entry)) { + fprintf(stderr, + "inconsistent ORC unwind table entries in file: %s\n", + fname); + goto out; + } + + /* create thread to sort ORC unwind tables concurrently */ + if (pthread_create(&orc_sort_thread, NULL, + sort_orctable, &orc_ip_size)) { + fprintf(stderr, + "pthread_create orc_sort_thread failed '%s': %s\n", + strerror(errno), fname); + goto out; + } +#endif + if (!extab_sec) { + fprintf(stderr, "no __ex_table in file: %s\n", fname); + goto out; + } + + if (!symtab_sec) { + fprintf(stderr, "no .symtab in file: %s\n", fname); + goto out; + } + + if (!strtab_sec) { + fprintf(stderr, "no .strtab in file: %s\n", fname); + goto out; + } + + extab_image = (void *)ehdr + shdr_offset(extab_sec); + strtab = (const char *)ehdr + shdr_offset(strtab_sec); + symtab = (const Elf_Sym *)((const char *)ehdr + shdr_offset(symtab_sec)); + +#ifdef MCOUNT_SORT_ENABLED + mstruct.ehdr = ehdr; + get_mcount_loc(&mstruct, symtab_sec, strtab); + + if (!mstruct.init_data_sec || !mstruct.start_mcount_loc || !mstruct.stop_mcount_loc) { + fprintf(stderr, + "incomplete mcount's sort in file: %s\n", + fname); + goto out; + } + + /* create thread to sort mcount_loc concurrently */ + if (pthread_create(&mcount_sort_thread, NULL, &sort_mcount_loc, &mstruct)) { + fprintf(stderr, + "pthread_create mcount_sort_thread failed '%s': %s\n", + strerror(errno), fname); + goto out; + } +#endif + + if (custom_sort) { + custom_sort(extab_image, shdr_size(extab_sec)); + } else { + int num_entries = shdr_size(extab_sec) / extable_ent_size; + qsort(extab_image, num_entries, + extable_ent_size, compare_extable); + } + + /* find the flag main_extable_sort_needed */ + sym_start = (void *)ehdr + shdr_offset(symtab_sec); + sym_end = sym_start + shdr_size(symtab_sec); + symentsize = shdr_entsize(symtab_sec); + + for (sym = sym_start; (void *)sym + symentsize < sym_end; + sym = (void *)sym + symentsize) { + if (sym_type(sym) != STT_OBJECT) + continue; + if (!strcmp(strtab + sym_name(sym), + "main_extable_sort_needed")) { + sort_needed_sym = sym; + break; + } + } + + if (!sort_needed_sym) { + fprintf(stderr, + "no main_extable_sort_needed symbol in file: %s\n", + fname); + goto out; + } + + sort_need_index = get_secindex(sym_shndx(sym), + ((void *)sort_needed_sym - (void *)symtab) / symentsize, + symtab_shndx); + sort_needed_sec = get_index(shdr_start, shentsize, sort_need_index); + sort_needed_loc = (void *)ehdr + + shdr_offset(sort_needed_sec) + + sym_value(sort_needed_sym) - shdr_addr(sort_needed_sec); + + /* extable has been sorted, clear the flag */ + w(0, sort_needed_loc); + rc = 0; + +out: +#ifdef UNWINDER_ORC_ENABLED + if (orc_sort_thread) { + void *retval = NULL; + /* wait for ORC tables sort done */ + rc = pthread_join(orc_sort_thread, &retval); + if (rc) { + fprintf(stderr, + "pthread_join failed '%s': %s\n", + strerror(errno), fname); + } else if (retval) { + rc = -1; + fprintf(stderr, + "failed to sort ORC tables '%s': %s\n", + (char *)retval, fname); + } + } +#endif + +#ifdef MCOUNT_SORT_ENABLED + if (mcount_sort_thread) { + void *retval = NULL; + /* wait for mcount sort done */ + rc = pthread_join(mcount_sort_thread, &retval); + if (rc) { + fprintf(stderr, + "pthread_join failed '%s': %s\n", + strerror(errno), fname); + } else if (retval) { + rc = -1; + fprintf(stderr, + "failed to sort mcount '%s': %s\n", + (char *)retval, fname); + } + } +#endif + return rc; +} static int compare_relative_table(const void *a, const void *b) { @@ -267,17 +1220,15 @@ static void sort_relative_table_with_data(char *extab_image, int image_size) static int do_file(char const *const fname, void *addr) { - int rc = -1; - Elf32_Ehdr *ehdr = addr; + Elf_Ehdr *ehdr = addr; table_sort_t custom_sort = NULL; - switch (ehdr->e_ident[EI_DATA]) { + switch (ehdr->e32.e_ident[EI_DATA]) { case ELFDATA2LSB: r = rle; r2 = r2le; r8 = r8le; w = wle; - w2 = w2le; w8 = w8le; break; case ELFDATA2MSB: @@ -285,25 +1236,31 @@ static int do_file(char const *const fname, void *addr) r2 = r2be; r8 = r8be; w = wbe; - w2 = w2be; w8 = w8be; break; default: fprintf(stderr, "unrecognized ELF data encoding %d: %s\n", - ehdr->e_ident[EI_DATA], fname); + ehdr->e32.e_ident[EI_DATA], fname); return -1; } - if (memcmp(ELFMAG, ehdr->e_ident, SELFMAG) != 0 || - (r2(&ehdr->e_type) != ET_EXEC && r2(&ehdr->e_type) != ET_DYN) || - ehdr->e_ident[EI_VERSION] != EV_CURRENT) { + if (memcmp(ELFMAG, ehdr->e32.e_ident, SELFMAG) != 0 || + (r2(&ehdr->e32.e_type) != ET_EXEC && r2(&ehdr->e32.e_type) != ET_DYN) || + ehdr->e32.e_ident[EI_VERSION] != EV_CURRENT) { fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file %s\n", fname); return -1; } - switch (r2(&ehdr->e_machine)) { - case EM_386: + switch (r2(&ehdr->e32.e_machine)) { case EM_AARCH64: +#ifdef MCOUNT_SORT_ENABLED + sort_reloc = true; + rela_type = 0x403; + /* arm64 uses patchable function entry placing before function */ + before_func = 8; +#endif + /* fallthrough */ + case EM_386: case EM_LOONGARCH: case EM_RISCV: case EM_S390: @@ -324,40 +1281,93 @@ static int do_file(char const *const fname, void *addr) break; default: fprintf(stderr, "unrecognized e_machine %d %s\n", - r2(&ehdr->e_machine), fname); + r2(&ehdr->e32.e_machine), fname); return -1; } - switch (ehdr->e_ident[EI_CLASS]) { - case ELFCLASS32: - if (r2(&ehdr->e_ehsize) != sizeof(Elf32_Ehdr) || - r2(&ehdr->e_shentsize) != sizeof(Elf32_Shdr)) { + switch (ehdr->e32.e_ident[EI_CLASS]) { + case ELFCLASS32: { + struct elf_funcs efuncs = { + .compare_extable = compare_extable_32, + .ehdr_shoff = ehdr32_shoff, + .ehdr_shentsize = ehdr32_shentsize, + .ehdr_shstrndx = ehdr32_shstrndx, + .ehdr_shnum = ehdr32_shnum, + .shdr_addr = shdr32_addr, + .shdr_offset = shdr32_offset, + .shdr_link = shdr32_link, + .shdr_size = shdr32_size, + .shdr_name = shdr32_name, + .shdr_type = shdr32_type, + .shdr_entsize = shdr32_entsize, + .sym_type = sym32_type, + .sym_name = sym32_name, + .sym_value = sym32_value, + .sym_shndx = sym32_shndx, + .rela_offset = rela32_offset, + .rela_info = rela32_info, + .rela_addend = rela32_addend, + .rela_write_addend = rela32_write_addend, + }; + + e = efuncs; + long_size = 4; + extable_ent_size = 8; + + if (r2(&ehdr->e32.e_ehsize) != sizeof(Elf32_Ehdr) || + r2(&ehdr->e32.e_shentsize) != sizeof(Elf32_Shdr)) { fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file: %s\n", fname); - break; + return -1; + } + } - rc = do_sort_32(ehdr, fname, custom_sort); break; - case ELFCLASS64: - { - Elf64_Ehdr *const ghdr = (Elf64_Ehdr *)ehdr; - if (r2(&ghdr->e_ehsize) != sizeof(Elf64_Ehdr) || - r2(&ghdr->e_shentsize) != sizeof(Elf64_Shdr)) { + case ELFCLASS64: { + struct elf_funcs efuncs = { + .compare_extable = compare_extable_64, + .ehdr_shoff = ehdr64_shoff, + .ehdr_shentsize = ehdr64_shentsize, + .ehdr_shstrndx = ehdr64_shstrndx, + .ehdr_shnum = ehdr64_shnum, + .shdr_addr = shdr64_addr, + .shdr_offset = shdr64_offset, + .shdr_link = shdr64_link, + .shdr_size = shdr64_size, + .shdr_name = shdr64_name, + .shdr_type = shdr64_type, + .shdr_entsize = shdr64_entsize, + .sym_type = sym64_type, + .sym_name = sym64_name, + .sym_value = sym64_value, + .sym_shndx = sym64_shndx, + .rela_offset = rela64_offset, + .rela_info = rela64_info, + .rela_addend = rela64_addend, + .rela_write_addend = rela64_write_addend, + }; + + e = efuncs; + long_size = 8; + extable_ent_size = 16; + + if (r2(&ehdr->e64.e_ehsize) != sizeof(Elf64_Ehdr) || + r2(&ehdr->e64.e_shentsize) != sizeof(Elf64_Shdr)) { fprintf(stderr, "unrecognized ET_EXEC/ET_DYN file: %s\n", fname); - break; + return -1; } - rc = do_sort_64(ghdr, fname, custom_sort); + } break; default: fprintf(stderr, "unrecognized ELF class %d %s\n", - ehdr->e_ident[EI_CLASS], fname); - break; + ehdr->e32.e_ident[EI_CLASS], fname); + return -1; } - return rc; + return do_sort(ehdr, fname, custom_sort); } int main(int argc, char *argv[]) @@ -365,14 +1375,29 @@ int main(int argc, char *argv[]) int i, n_error = 0; /* gcc-4.3.0 false positive complaint */ size_t size = 0; void *addr = NULL; + int c; + + while ((c = getopt(argc, argv, "s:")) >= 0) { + switch (c) { + case 's': + if (parse_symbols(optarg) < 0) { + fprintf(stderr, "Could not parse %s\n", optarg); + return -1; + } + break; + default: + fprintf(stderr, "usage: sorttable [-s nm-file] vmlinux...\n"); + return 0; + } + } - if (argc < 2) { + if ((argc - optind) < 1) { fprintf(stderr, "usage: sorttable vmlinux...\n"); return 0; } /* Process each file in turn, allowing deep failure. */ - for (i = 1; i < argc; i++) { + for (i = optind; i < argc; i++) { addr = mmap_file(argv[i], &size); if (!addr) { ++n_error; diff --git a/scripts/sorttable.h b/scripts/sorttable.h deleted file mode 100644 index a7c5445baf00..000000000000 --- a/scripts/sorttable.h +++ /dev/null @@ -1,500 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * sorttable.h - * - * Added ORC unwind tables sort support and other updates: - * Copyright (C) 1999-2019 Alibaba Group Holding Limited. by: - * Shile Zhang <shile.zhang@linux.alibaba.com> - * - * Copyright 2011 - 2012 Cavium, Inc. - * - * Some of code was taken out of arch/x86/kernel/unwind_orc.c, written by: - * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com> - * - * Some of this code was taken out of recordmcount.h written by: - * - * Copyright 2009 John F. Reiser <jreiser@BitWagon.com>. All rights reserved. - * Copyright 2010 Steven Rostedt <srostedt@redhat.com>, Red Hat Inc. - */ - -#undef extable_ent_size -#undef compare_extable -#undef get_mcount_loc -#undef sort_mcount_loc -#undef elf_mcount_loc -#undef do_sort -#undef Elf_Addr -#undef Elf_Ehdr -#undef Elf_Shdr -#undef Elf_Rel -#undef Elf_Rela -#undef Elf_Sym -#undef ELF_R_SYM -#undef Elf_r_sym -#undef ELF_R_INFO -#undef Elf_r_info -#undef ELF_ST_BIND -#undef ELF_ST_TYPE -#undef fn_ELF_R_SYM -#undef fn_ELF_R_INFO -#undef uint_t -#undef _r -#undef _w - -#ifdef SORTTABLE_64 -# define extable_ent_size 16 -# define compare_extable compare_extable_64 -# define get_mcount_loc get_mcount_loc_64 -# define sort_mcount_loc sort_mcount_loc_64 -# define elf_mcount_loc elf_mcount_loc_64 -# define do_sort do_sort_64 -# define Elf_Addr Elf64_Addr -# define Elf_Ehdr Elf64_Ehdr -# define Elf_Shdr Elf64_Shdr -# define Elf_Rel Elf64_Rel -# define Elf_Rela Elf64_Rela -# define Elf_Sym Elf64_Sym -# define ELF_R_SYM ELF64_R_SYM -# define Elf_r_sym Elf64_r_sym -# define ELF_R_INFO ELF64_R_INFO -# define Elf_r_info Elf64_r_info -# define ELF_ST_BIND ELF64_ST_BIND -# define ELF_ST_TYPE ELF64_ST_TYPE -# define fn_ELF_R_SYM fn_ELF64_R_SYM -# define fn_ELF_R_INFO fn_ELF64_R_INFO -# define uint_t uint64_t -# define _r r8 -# define _w w8 -#else -# define extable_ent_size 8 -# define compare_extable compare_extable_32 -# define get_mcount_loc get_mcount_loc_32 -# define sort_mcount_loc sort_mcount_loc_32 -# define elf_mcount_loc elf_mcount_loc_32 -# define do_sort do_sort_32 -# define Elf_Addr Elf32_Addr -# define Elf_Ehdr Elf32_Ehdr -# define Elf_Shdr Elf32_Shdr -# define Elf_Rel Elf32_Rel -# define Elf_Rela Elf32_Rela -# define Elf_Sym Elf32_Sym -# define ELF_R_SYM ELF32_R_SYM -# define Elf_r_sym Elf32_r_sym -# define ELF_R_INFO ELF32_R_INFO -# define Elf_r_info Elf32_r_info -# define ELF_ST_BIND ELF32_ST_BIND -# define ELF_ST_TYPE ELF32_ST_TYPE -# define fn_ELF_R_SYM fn_ELF32_R_SYM -# define fn_ELF_R_INFO fn_ELF32_R_INFO -# define uint_t uint32_t -# define _r r -# define _w w -#endif - -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) -/* ORC unwinder only support X86_64 */ -#include <asm/orc_types.h> - -#define ERRSTR_MAXSZ 256 - -char g_err[ERRSTR_MAXSZ]; -int *g_orc_ip_table; -struct orc_entry *g_orc_table; - -pthread_t orc_sort_thread; - -static inline unsigned long orc_ip(const int *ip) -{ - return (unsigned long)ip + *ip; -} - -static int orc_sort_cmp(const void *_a, const void *_b) -{ - struct orc_entry *orc_a, *orc_b; - const int *a = g_orc_ip_table + *(int *)_a; - const int *b = g_orc_ip_table + *(int *)_b; - unsigned long a_val = orc_ip(a); - unsigned long b_val = orc_ip(b); - - if (a_val > b_val) - return 1; - if (a_val < b_val) - return -1; - - /* - * The "weak" section terminator entries need to always be on the left - * to ensure the lookup code skips them in favor of real entries. - * These terminator entries exist to handle any gaps created by - * whitelisted .o files which didn't get objtool generation. - */ - orc_a = g_orc_table + (a - g_orc_ip_table); - orc_b = g_orc_table + (b - g_orc_ip_table); - if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED) - return 0; - return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; -} - -static void *sort_orctable(void *arg) -{ - int i; - int *idxs = NULL; - int *tmp_orc_ip_table = NULL; - struct orc_entry *tmp_orc_table = NULL; - unsigned int *orc_ip_size = (unsigned int *)arg; - unsigned int num_entries = *orc_ip_size / sizeof(int); - unsigned int orc_size = num_entries * sizeof(struct orc_entry); - - idxs = (int *)malloc(*orc_ip_size); - if (!idxs) { - snprintf(g_err, ERRSTR_MAXSZ, "malloc idxs: %s", - strerror(errno)); - pthread_exit(g_err); - } - - tmp_orc_ip_table = (int *)malloc(*orc_ip_size); - if (!tmp_orc_ip_table) { - snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_ip_table: %s", - strerror(errno)); - pthread_exit(g_err); - } - - tmp_orc_table = (struct orc_entry *)malloc(orc_size); - if (!tmp_orc_table) { - snprintf(g_err, ERRSTR_MAXSZ, "malloc tmp_orc_table: %s", - strerror(errno)); - pthread_exit(g_err); - } - - /* initialize indices array, convert ip_table to absolute address */ - for (i = 0; i < num_entries; i++) { - idxs[i] = i; - tmp_orc_ip_table[i] = g_orc_ip_table[i] + i * sizeof(int); - } - memcpy(tmp_orc_table, g_orc_table, orc_size); - - qsort(idxs, num_entries, sizeof(int), orc_sort_cmp); - - for (i = 0; i < num_entries; i++) { - if (idxs[i] == i) - continue; - - /* convert back to relative address */ - g_orc_ip_table[i] = tmp_orc_ip_table[idxs[i]] - i * sizeof(int); - g_orc_table[i] = tmp_orc_table[idxs[i]]; - } - - free(idxs); - free(tmp_orc_ip_table); - free(tmp_orc_table); - pthread_exit(NULL); -} -#endif - -static int compare_extable(const void *a, const void *b) -{ - Elf_Addr av = _r(a); - Elf_Addr bv = _r(b); - - if (av < bv) - return -1; - if (av > bv) - return 1; - return 0; -} -#ifdef MCOUNT_SORT_ENABLED -pthread_t mcount_sort_thread; - -struct elf_mcount_loc { - Elf_Ehdr *ehdr; - Elf_Shdr *init_data_sec; - uint_t start_mcount_loc; - uint_t stop_mcount_loc; -}; - -/* Sort the addresses stored between __start_mcount_loc to __stop_mcount_loc in vmlinux */ -static void *sort_mcount_loc(void *arg) -{ - struct elf_mcount_loc *emloc = (struct elf_mcount_loc *)arg; - uint_t offset = emloc->start_mcount_loc - _r(&(emloc->init_data_sec)->sh_addr) - + _r(&(emloc->init_data_sec)->sh_offset); - uint_t count = emloc->stop_mcount_loc - emloc->start_mcount_loc; - unsigned char *start_loc = (void *)emloc->ehdr + offset; - - qsort(start_loc, count/sizeof(uint_t), sizeof(uint_t), compare_extable); - return NULL; -} - -/* Get the address of __start_mcount_loc and __stop_mcount_loc in System.map */ -static void get_mcount_loc(uint_t *_start, uint_t *_stop) -{ - FILE *file_start, *file_stop; - char start_buff[20]; - char stop_buff[20]; - int len = 0; - - file_start = popen(" grep start_mcount System.map | awk '{print $1}' ", "r"); - if (!file_start) { - fprintf(stderr, "get start_mcount_loc error!"); - return; - } - - file_stop = popen(" grep stop_mcount System.map | awk '{print $1}' ", "r"); - if (!file_stop) { - fprintf(stderr, "get stop_mcount_loc error!"); - pclose(file_start); - return; - } - - while (fgets(start_buff, sizeof(start_buff), file_start) != NULL) { - len = strlen(start_buff); - start_buff[len - 1] = '\0'; - } - *_start = strtoul(start_buff, NULL, 16); - - while (fgets(stop_buff, sizeof(stop_buff), file_stop) != NULL) { - len = strlen(stop_buff); - stop_buff[len - 1] = '\0'; - } - *_stop = strtoul(stop_buff, NULL, 16); - - pclose(file_start); - pclose(file_stop); -} -#endif -static int do_sort(Elf_Ehdr *ehdr, - char const *const fname, - table_sort_t custom_sort) -{ - int rc = -1; - Elf_Shdr *s, *shdr = (Elf_Shdr *)((char *)ehdr + _r(&ehdr->e_shoff)); - Elf_Shdr *strtab_sec = NULL; - Elf_Shdr *symtab_sec = NULL; - Elf_Shdr *extab_sec = NULL; - Elf_Sym *sym; - const Elf_Sym *symtab; - Elf32_Word *symtab_shndx = NULL; - Elf_Sym *sort_needed_sym = NULL; - Elf_Shdr *sort_needed_sec; - Elf_Rel *relocs = NULL; - int relocs_size = 0; - uint32_t *sort_needed_loc; - const char *secstrings; - const char *strtab; - char *extab_image; - int extab_index = 0; - int i; - int idx; - unsigned int shnum; - unsigned int shstrndx; -#ifdef MCOUNT_SORT_ENABLED - struct elf_mcount_loc mstruct = {0}; - uint_t _start_mcount_loc = 0; - uint_t _stop_mcount_loc = 0; -#endif -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - unsigned int orc_ip_size = 0; - unsigned int orc_size = 0; - unsigned int orc_num_entries = 0; -#endif - - shstrndx = r2(&ehdr->e_shstrndx); - if (shstrndx == SHN_XINDEX) - shstrndx = r(&shdr[0].sh_link); - secstrings = (const char *)ehdr + _r(&shdr[shstrndx].sh_offset); - - shnum = r2(&ehdr->e_shnum); - if (shnum == SHN_UNDEF) - shnum = _r(&shdr[0].sh_size); - - for (i = 0, s = shdr; s < shdr + shnum; i++, s++) { - idx = r(&s->sh_name); - if (!strcmp(secstrings + idx, "__ex_table")) { - extab_sec = s; - extab_index = i; - } - if (!strcmp(secstrings + idx, ".symtab")) - symtab_sec = s; - if (!strcmp(secstrings + idx, ".strtab")) - strtab_sec = s; - - if ((r(&s->sh_type) == SHT_REL || - r(&s->sh_type) == SHT_RELA) && - r(&s->sh_info) == extab_index) { - relocs = (void *)ehdr + _r(&s->sh_offset); - relocs_size = _r(&s->sh_size); - } - if (r(&s->sh_type) == SHT_SYMTAB_SHNDX) - symtab_shndx = (Elf32_Word *)((const char *)ehdr + - _r(&s->sh_offset)); - -#ifdef MCOUNT_SORT_ENABLED - /* locate the .init.data section in vmlinux */ - if (!strcmp(secstrings + idx, ".init.data")) { - get_mcount_loc(&_start_mcount_loc, &_stop_mcount_loc); - mstruct.ehdr = ehdr; - mstruct.init_data_sec = s; - mstruct.start_mcount_loc = _start_mcount_loc; - mstruct.stop_mcount_loc = _stop_mcount_loc; - } -#endif - -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - /* locate the ORC unwind tables */ - if (!strcmp(secstrings + idx, ".orc_unwind_ip")) { - orc_ip_size = s->sh_size; - g_orc_ip_table = (int *)((void *)ehdr + - s->sh_offset); - } - if (!strcmp(secstrings + idx, ".orc_unwind")) { - orc_size = s->sh_size; - g_orc_table = (struct orc_entry *)((void *)ehdr + - s->sh_offset); - } -#endif - } /* for loop */ - -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - if (!g_orc_ip_table || !g_orc_table) { - fprintf(stderr, - "incomplete ORC unwind tables in file: %s\n", fname); - goto out; - } - - orc_num_entries = orc_ip_size / sizeof(int); - if (orc_ip_size % sizeof(int) != 0 || - orc_size % sizeof(struct orc_entry) != 0 || - orc_num_entries != orc_size / sizeof(struct orc_entry)) { - fprintf(stderr, - "inconsistent ORC unwind table entries in file: %s\n", - fname); - goto out; - } - - /* create thread to sort ORC unwind tables concurrently */ - if (pthread_create(&orc_sort_thread, NULL, - sort_orctable, &orc_ip_size)) { - fprintf(stderr, - "pthread_create orc_sort_thread failed '%s': %s\n", - strerror(errno), fname); - goto out; - } -#endif - -#ifdef MCOUNT_SORT_ENABLED - if (!mstruct.init_data_sec || !_start_mcount_loc || !_stop_mcount_loc) { - fprintf(stderr, - "incomplete mcount's sort in file: %s\n", - fname); - goto out; - } - - /* create thread to sort mcount_loc concurrently */ - if (pthread_create(&mcount_sort_thread, NULL, &sort_mcount_loc, &mstruct)) { - fprintf(stderr, - "pthread_create mcount_sort_thread failed '%s': %s\n", - strerror(errno), fname); - goto out; - } -#endif - if (!extab_sec) { - fprintf(stderr, "no __ex_table in file: %s\n", fname); - goto out; - } - - if (!symtab_sec) { - fprintf(stderr, "no .symtab in file: %s\n", fname); - goto out; - } - - if (!strtab_sec) { - fprintf(stderr, "no .strtab in file: %s\n", fname); - goto out; - } - - extab_image = (void *)ehdr + _r(&extab_sec->sh_offset); - strtab = (const char *)ehdr + _r(&strtab_sec->sh_offset); - symtab = (const Elf_Sym *)((const char *)ehdr + - _r(&symtab_sec->sh_offset)); - - if (custom_sort) { - custom_sort(extab_image, _r(&extab_sec->sh_size)); - } else { - int num_entries = _r(&extab_sec->sh_size) / extable_ent_size; - qsort(extab_image, num_entries, - extable_ent_size, compare_extable); - } - - /* If there were relocations, we no longer need them. */ - if (relocs) - memset(relocs, 0, relocs_size); - - /* find the flag main_extable_sort_needed */ - for (sym = (void *)ehdr + _r(&symtab_sec->sh_offset); - sym < sym + _r(&symtab_sec->sh_size) / sizeof(Elf_Sym); - sym++) { - if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT) - continue; - if (!strcmp(strtab + r(&sym->st_name), - "main_extable_sort_needed")) { - sort_needed_sym = sym; - break; - } - } - - if (!sort_needed_sym) { - fprintf(stderr, - "no main_extable_sort_needed symbol in file: %s\n", - fname); - goto out; - } - - sort_needed_sec = &shdr[get_secindex(r2(&sym->st_shndx), - sort_needed_sym - symtab, - symtab_shndx)]; - sort_needed_loc = (void *)ehdr + - _r(&sort_needed_sec->sh_offset) + - _r(&sort_needed_sym->st_value) - - _r(&sort_needed_sec->sh_addr); - - /* extable has been sorted, clear the flag */ - w(0, sort_needed_loc); - rc = 0; - -out: -#if defined(SORTTABLE_64) && defined(UNWINDER_ORC_ENABLED) - if (orc_sort_thread) { - void *retval = NULL; - /* wait for ORC tables sort done */ - rc = pthread_join(orc_sort_thread, &retval); - if (rc) { - fprintf(stderr, - "pthread_join failed '%s': %s\n", - strerror(errno), fname); - } else if (retval) { - rc = -1; - fprintf(stderr, - "failed to sort ORC tables '%s': %s\n", - (char *)retval, fname); - } - } -#endif - -#ifdef MCOUNT_SORT_ENABLED - if (mcount_sort_thread) { - void *retval = NULL; - /* wait for mcount sort done */ - rc = pthread_join(mcount_sort_thread, &retval); - if (rc) { - fprintf(stderr, - "pthread_join failed '%s': %s\n", - strerror(errno), fname); - } else if (retval) { - rc = -1; - fprintf(stderr, - "failed to sort mcount '%s': %s\n", - (char *)retval, fname); - } - } -#endif - return rc; -} diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py index 8b8fb115fc81..8d608f61bf37 100755 --- a/scripts/spdxcheck.py +++ b/scripts/spdxcheck.py @@ -214,9 +214,15 @@ class id_parser(object): # Remove trailing xml comment closure if line.strip().endswith('-->'): expr = expr.rstrip('-->').strip() + # Remove trailing Jinja2 comment closure + if line.strip().endswith('#}'): + expr = expr.rstrip('#}').strip() # Special case for SH magic boot code files if line.startswith('LIST \"'): expr = expr.rstrip('\"').strip() + # Remove j2 comment closure + if line.startswith('{#'): + expr = expr.rstrip('#}').strip() self.parse(expr) self.spdx_valid += 1 # diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 05bd9ca1fbfa..ac94fa1c2415 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -222,6 +222,7 @@ autonymous||autonomous auxillary||auxiliary auxilliary||auxiliary avaiable||available +avaialable||available avaible||available availabe||available availabled||available @@ -267,6 +268,7 @@ broadcase||broadcast broadcat||broadcast bufer||buffer bufferred||buffered +bufferur||buffer bufufer||buffer cacluated||calculated caculate||calculate @@ -405,6 +407,7 @@ configutation||configuration congiuration||configuration conider||consider conjuction||conjunction +connction||connection connecetd||connected connectinos||connections connetor||connector @@ -413,6 +416,7 @@ connnections||connections consistancy||consistency consistant||consistent consits||consists +constructred||constructed containes||contains containts||contains contaisn||contains @@ -450,6 +454,7 @@ creationg||creating cryptocraphic||cryptographic cummulative||cumulative cunter||counter +curent||current curently||currently cylic||cyclic dafault||default @@ -461,6 +466,7 @@ decendant||descendant decendants||descendants decompres||decompress decsribed||described +decrese||decrease decription||description detault||default dectected||detected @@ -485,6 +491,7 @@ delare||declare delares||declares delaring||declaring delemiter||delimiter +deley||delay delibrately||deliberately delievered||delivered demodualtor||demodulator @@ -551,6 +558,7 @@ disgest||digest disired||desired dispalying||displaying dissable||disable +dissapeared||disappeared diplay||display directon||direction direcly||directly @@ -606,6 +614,7 @@ eigth||eight elementry||elementary eletronic||electronic embeded||embedded +emtpy||empty enabledi||enabled enbale||enable enble||enable @@ -669,6 +678,7 @@ exmaple||example expecially||especially experies||expires explicite||explicit +explicity||explicitly explicitely||explicitly explict||explicit explictely||explicitly @@ -723,10 +733,12 @@ followign||following followings||following follwing||following fonud||found +forcebly||forcibly forseeable||foreseeable forse||force fortan||fortran forwardig||forwarding +forwared||forwarded frambuffer||framebuffer framming||framing framwork||framework @@ -767,6 +779,7 @@ grahpical||graphical granularty||granularity grapic||graphic grranted||granted +grups||groups guage||gauge guarenteed||guaranteed guarentee||guarantee @@ -780,6 +793,7 @@ hardare||hardware harware||hardware hardward||hardware havind||having +heigth||height heirarchically||hierarchically heirarchy||hierarchy heirachy||hierarchy @@ -788,9 +802,11 @@ hearbeat||heartbeat heterogenous||heterogeneous hexdecimal||hexadecimal hybernate||hibernate +hiearchy||hierarchy hierachy||hierarchy hierarchie||hierarchy homogenous||homogeneous +horizental||horizontal howver||however hsould||should hypervior||hypervisor @@ -842,6 +858,7 @@ independed||independent indiate||indicate indicat||indicate inexpect||inexpected +infalte||inflate inferface||interface infinit||infinite infomation||information @@ -861,6 +878,7 @@ initators||initiators initialiazation||initialization initializationg||initialization initializiation||initialization +initializtion||initialization initialze||initialize initialzed||initialized initialzing||initializing @@ -877,6 +895,7 @@ instanciate||instantiate instanciated||instantiated instuments||instruments insufficent||insufficient +intead||instead inteface||interface integreated||integrated integrety||integrity @@ -1081,6 +1100,7 @@ notications||notifications notifcations||notifications notifed||notified notity||notify +notfify||notify nubmer||number numebr||number numer||number @@ -1122,6 +1142,7 @@ orientatied||orientated orientied||oriented orignal||original originial||original +orphanded||orphaned otherise||otherwise ouput||output oustanding||outstanding @@ -1184,9 +1205,11 @@ peroid||period persistance||persistence persistant||persistent phoneticly||phonetically +pipline||pipeline plaform||platform plalform||platform platfoem||platform +platfomr||platform platfrom||platform plattform||platform pleaes||please @@ -1211,11 +1234,14 @@ preceeding||preceding preceed||precede precendence||precedence precission||precision +predicition||prediction preemptable||preemptible prefered||preferred prefferably||preferably prefitler||prefilter preform||perform +previleged||privileged +previlege||privilege premption||preemption prepaired||prepared prepate||prepare @@ -1289,6 +1315,7 @@ querrying||querying queus||queues randomally||randomly raoming||roaming +readyness||readiness reasearcher||researcher reasearchers||researchers reasearch||research @@ -1305,8 +1332,10 @@ recieves||receives recieving||receiving recogniced||recognised recognizeable||recognizable +recompte||recompute recommanded||recommended recyle||recycle +redect||reject redircet||redirect redirectrion||redirection redundacy||redundancy @@ -1314,6 +1343,7 @@ reename||rename refcounf||refcount refence||reference refered||referred +referencce||reference referenace||reference refererence||reference refering||referring @@ -1348,11 +1378,13 @@ replys||replies reponse||response representaion||representation repsonse||response +reqested||requested reqeust||request reqister||register requed||requeued requestied||requested requiere||require +requieres||requires requirment||requirement requred||required requried||required @@ -1440,6 +1472,7 @@ sequencial||sequential serivce||service serveral||several servive||service +sesion||session setts||sets settting||setting shapshot||snapshot @@ -1602,11 +1635,13 @@ trys||tries thses||these tiggers||triggers tiggered||triggered +tiggerring||triggering tipically||typically timeing||timing timming||timing timout||timeout tmis||this +tolarance||tolerance toogle||toggle torerable||tolerable torlence||tolerance @@ -1633,6 +1668,7 @@ trasfer||transfer trasmission||transmission trasmitter||transmitter treshold||threshold +trigged||triggered triggerd||triggered trigerred||triggered trigerring||triggering @@ -1648,6 +1684,7 @@ uknown||unknown usccess||success uncommited||uncommitted uncompatible||incompatible +uncomressed||uncompressed unconditionaly||unconditionally undeflow||underflow undelying||underlying @@ -1715,6 +1752,7 @@ utitity||utility utitlty||utility vaid||valid vaild||valid +validationg||validating valide||valid variantions||variations varible||variable @@ -1724,6 +1762,7 @@ verbse||verbose veify||verify verfication||verification veriosn||version +versoin||version verisons||versions verison||version veritical||vertical diff --git a/scripts/syscall.tbl b/scripts/syscall.tbl index ebbdb3c42e9f..580b4e246aec 100644 --- a/scripts/syscall.tbl +++ b/scripts/syscall.tbl @@ -407,3 +407,4 @@ 464 common getxattrat sys_getxattrat 465 common listxattrat sys_listxattrat 466 common removexattrat sys_removexattrat +467 common open_tree_attr sys_open_tree_attr diff --git a/scripts/tags.sh b/scripts/tags.sh index b21236377998..98680e9cd7be 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -146,6 +146,7 @@ dogtags() # a ^[^#] is prepended by setup_regex unless an anchor is already present regex_asm=( '/^\(ENTRY\|_GLOBAL\)([[:space:]]*\([[:alnum:]_\\]*\)).*/\2/' + '/^SYM_[[:alnum:]_]*START[[:alnum:]_]*([[:space:]]*\([[:alnum:]_\\]*\)).*/\1/' ) regex_c=( '/^SYSCALL_DEFINE[0-9]([[:space:]]*\([[:alnum:]_]*\).*/sys_\1/' @@ -188,6 +189,7 @@ regex_c=( '/^PCI_OP_WRITE([[:space:]]*\(\w*\).*[1-4])/pci_bus_write_config_\1/' '/\<DEFINE_\(RT_MUTEX\|MUTEX\|SEMAPHORE\|SPINLOCK\)([[:space:]]*\([[:alnum:]_]*\)/\2/v/' '/\<DEFINE_\(RAW_SPINLOCK\|RWLOCK\|SEQLOCK\)([[:space:]]*\([[:alnum:]_]*\)/\2/v/' + '/\<DEFINE_TIMER(\([^,)]*\),/\1/' '/\<DECLARE_\(RWSEM\|COMPLETION\)([[:space:]]*\([[:alnum:]_]\+\)/\2/v/' '/\<DECLARE_BITMAP([[:space:]]*\([[:alnum:]_]\+\)/\1/v/' '/\(^\|\s\)\(\|L\|H\)LIST_HEAD([[:space:]]*\([[:alnum:]_]*\)/\3/v/' @@ -212,6 +214,13 @@ regex_c=( '/^SEQCOUNT_LOCKTYPE(\([^,]*\),[[:space:]]*\([^,]*\),[^)]*)/seqcount_\2_init/' '/^\<DECLARE_IDTENTRY[[:alnum:]_]*([^,)]*,[[:space:]]*\([[:alnum:]_]\+\)/\1/' '/^\<DEFINE_IDTENTRY[[:alnum:]_]*([[:space:]]*\([[:alnum:]_]\+\)/\1/' + '/^\<DEFINE_FREE(\([[:alnum:]_]\+\)/cleanup_\1/' + '/^\<DEFINE_CLASS(\([[:alnum:]_]\+\)/class_\1/' + '/^\<EXTEND_CLASS(\([[:alnum:]_]\+\),[[:space:]]*\([[:alnum:]_]\+\)/class_\1\2/' + '/^\<DEFINE_GUARD(\([[:alnum:]_]\+\)/class_\1/' + '/^\<DEFINE_GUARD_COND(\([[:alnum:]_]\+\),[[:space:]]*\([[:alnum:]_]\+\)/class_\1\2/' + '/^\<DEFINE_LOCK_GUARD_[[:digit:]](\([[:alnum:]_]\+\)/class_\1/' + '/^\<DEFINE_LOCK_GUARD_[[:digit:]]_COND(\([[:alnum:]_]\+\),[[:space:]]*\([[:alnum:]_]\+\)/class_\1\2/' ) regex_kconfig=( '/^[[:blank:]]*\(menu\|\)config[[:blank:]]\+\([[:alnum:]_]\+\)/\2/' @@ -260,7 +269,8 @@ exuberant() # identifiers to ignore by ctags local ign=( ACPI_EXPORT_SYMBOL - DEFINE_{TRACE,MUTEX} + DECLARE_BITMAP + DEFINE_{TRACE,MUTEX,TIMER} EXPORT_SYMBOL EXPORT_SYMBOL_GPL EXPORT_TRACEPOINT_SYMBOL EXPORT_TRACEPOINT_SYMBOL_GPL ____cacheline_aligned ____cacheline_aligned_in_smp diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py deleted file mode 100755 index 42fa87300941..000000000000 --- a/scripts/tracing/draw_functrace.py +++ /dev/null @@ -1,129 +0,0 @@ -#!/usr/bin/env python -# SPDX-License-Identifier: GPL-2.0-only - -""" -Copyright 2008 (c) Frederic Weisbecker <fweisbec@gmail.com> - -This script parses a trace provided by the function tracer in -kernel/trace/trace_functions.c -The resulted trace is processed into a tree to produce a more human -view of the call stack by drawing textual but hierarchical tree of -calls. Only the functions's names and the call time are provided. - -Usage: - Be sure that you have CONFIG_FUNCTION_TRACER - # mount -t tracefs nodev /sys/kernel/tracing - # echo function > /sys/kernel/tracing/current_tracer - $ cat /sys/kernel/tracing/trace_pipe > ~/raw_trace_func - Wait some times but not too much, the script is a bit slow. - Break the pipe (Ctrl + Z) - $ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace - Then you have your drawn trace in draw_functrace -""" - - -import sys, re - -class CallTree: - """ This class provides a tree representation of the functions - call stack. If a function has no parent in the kernel (interrupt, - syscall, kernel thread...) then it is attached to a virtual parent - called ROOT. - """ - ROOT = None - - def __init__(self, func, time = None, parent = None): - self._func = func - self._time = time - if parent is None: - self._parent = CallTree.ROOT - else: - self._parent = parent - self._children = [] - - def calls(self, func, calltime): - """ If a function calls another one, call this method to insert it - into the tree at the appropriate place. - @return: A reference to the newly created child node. - """ - child = CallTree(func, calltime, self) - self._children.append(child) - return child - - def getParent(self, func): - """ Retrieve the last parent of the current node that - has the name given by func. If this function is not - on a parent, then create it as new child of root - @return: A reference to the parent. - """ - tree = self - while tree != CallTree.ROOT and tree._func != func: - tree = tree._parent - if tree == CallTree.ROOT: - child = CallTree.ROOT.calls(func, None) - return child - return tree - - def __repr__(self): - return self.__toString("", True) - - def __toString(self, branch, lastChild): - if self._time is not None: - s = "%s----%s (%s)\n" % (branch, self._func, self._time) - else: - s = "%s----%s\n" % (branch, self._func) - - i = 0 - if lastChild: - branch = branch[:-1] + " " - while i < len(self._children): - if i != len(self._children) - 1: - s += "%s" % self._children[i].__toString(branch +\ - " |", False) - else: - s += "%s" % self._children[i].__toString(branch +\ - " |", True) - i += 1 - return s - -class BrokenLineException(Exception): - """If the last line is not complete because of the pipe breakage, - we want to stop the processing and ignore this line. - """ - pass - -class CommentLineException(Exception): - """ If the line is a comment (as in the beginning of the trace file), - just ignore it. - """ - pass - - -def parseLine(line): - line = line.strip() - if line.startswith("#"): - raise CommentLineException - m = re.match("[^]]+?\\] +([a-z.]+) +([0-9.]+): (\\w+) <-(\\w+)", line) - if m is None: - raise BrokenLineException - return (m.group(2), m.group(3), m.group(4)) - - -def main(): - CallTree.ROOT = CallTree("Root (Nowhere)", None, None) - tree = CallTree.ROOT - - for line in sys.stdin: - try: - calltime, callee, caller = parseLine(line) - except BrokenLineException: - break - except CommentLineException: - continue - tree = tree.getParent(caller) - tree = tree.calls(callee, calltime) - - print(CallTree.ROOT) - -if __name__ == "__main__": - main() |